Search

Modern industrial systems routinely generate data in high volume at high velocity. These high-dimensional data streams (HDDS) provide valuable information at granular levels to quality personnel during root cause investigation in cases of a system fault. The goal of fault analysis using HDDS is twofold: (1) identify abnormal data streams and (2) locate the change point when the processes become out of control. Existing research has largely focused on addressing the two issues separately. In this article, we propose a unified framework by formulating the problem as optimal control of hierarchical missed discovery rates in multiple classifications. Theoretically, we establish that our approach minimizes the number of false discoveries while controlling the missed discovery rates at desired levels. Numerically, we develop a computationally efficient algorithm for solving the optimization and demonstrate its superior performance over the existing methods. A data-driven version of the proposed approach is suggested as well. An application to a real data set in semiconductor manufacturing shows that our approach works well in practice. [ABSTRACT FROM AUTHOR]

This paper introduces a novel approach for enhancing fault diagnosis in industrial equipment systems through the application of sensor network-driven knowledge graph-based in-context learning (KG-ICL). By focusing on the critical role of sensor data in detecting and isolating faults, we construct a domain-specific knowledge graph (DSKG) that encapsulates expert knowledge relevant to industrial equipment. Utilizing a long-length entity similarity (LES) measure, we retrieve relevant information from the DSKG. Our method leverages large language models (LLMs) to conduct causal analysis on textual data related to equipment faults derived from sensor networks, thereby significantly enhancing the accuracy and efficiency of fault diagnosis. This paper details a series of experiments that validate the effectiveness of the KG-ICL method in accurately diagnosing fault causes and locations of industrial equipment systems. By leveraging LLMs and structured knowledge, our approach offers a robust tool for condition monitoring and fault management, thereby improving the reliability and efficiency of operations in industrial sectors. [ABSTRACT FROM AUTHOR]

Root cause diagnosis is able to find the propagation path of faults timely when the fault occurs. Therefore, it is of key significance in the maintenance and fault diagnosis of industrial systems. A commonly used method for root cause diagnosis is causal analysis method. In this work, a causal analysis method Extended Convergent Cross Mapping (ECCM) algorithm is used for root cause diagnosis of industry, however, it has difficulties in dealing with large amounts of steady state data and obtaining accurate propagation paths. Therefore, a causal analysis method based on Kernel Independent Component Analysis (KICA) and ECCM is proposed in this study to deal with the above problems. First, the KICA algorithm is used to detect faults to get the transition process data. Second, the ECCM algorithm is used to construct causal relationship among variables based on the transition process data to construct the fault propagation path diagram. Finally, the effectiveness of the proposed KICA-ECCM algorithm is tested by using the Tennessee Eastman Process and Industrial Process Control Test Facility platform. Compared with the ECCM and GC algorithm, the KICA-ECCM algorithm performs better in terms of accuracy and efficiency. [ABSTRACT FROM AUTHOR]

To need of accurate motor fault diagnosis in industrial system, we propose a fault diagnosis framework that utilizes motor current and electromagnetic signals, combining them with a self-attention-enhanced capsule network for enhanced signal analysis and accuracy. Firstly, the original signal extracted by multiple sensors is constructed into a symmetric point mode (SDP) image, and the visual fault information of different sensors and fusion signals of different motion health states are obtained by the proposed multi-channel image fusion method. Then, the capsule network, combined with self-attention, extracts spatial features from the high-dimensional tensor of the multi-channel fused image for adaptive recognition and extraction. Subsequently, advanced feature vector information is obtained through softmax for diagnosis. Diagnosis results of several datasets indicate that the developed diagnosis framework with compressed image information can availably identify 8 kinds of motor fault states under various loads, and the fault diagnosis rate is as high as 99.95 %, it is helpful for low cost and high-speed diagnosis of motors. In addition, by learning multiple sensor signals in the same state, it obtains stronger robustness and effectiveness than a single signal model. • The symmetric dot pattern (SDP) is used to convert a one-dimensional signal into a two-dimensional visual image. • A multi-sensor fusion (MSF) method based on multi-channel SDP images is proposed. • A multi-channel capsule network based on self-attention mechanism is developed. • The proposed method is verified by fusion diagnosis of multi-channel isomorphic spatial information and heterogeneous information. [ABSTRACT FROM AUTHOR]

Investigating vibrations in mechanical transmission systems to detect and identify the causes of abnormal vibrations remains a prominent focus for researchers. Within industrial transmission systems, rolling bearings play a pivotal role. Utilizing the envelope spectrum of vibration signals to diagnose faults in rolling bearings proves highly reliable due to the bearings' mechanical properties. Under constant shaft rotational speed, most envelope analysis methods can accurately identify faults at the characteristic frequency of rolling bearings. However, numerous transmission systems operate at variable rotational speeds due to technological demands and load fluctuations. In such scenarios, the vibration signals of rolling bearings undergo frequency modulation, rendering conventional vibration analysis methods like envelope spectrum analysis ineffective. Timefrequency analysis is a valuable diagnostic tool for identifying faults in rolling bearings under these conditions. Nonetheless, its practical application, particularly with large-scale data, necessitates high-performance computers capable of processing extensive multi-dimensional matrices. To overcome this challenge, this paper introduces a novel tool based on the Synchrosqueezing Transform (SST) and other resampling techniques. The proposed method additionally incorporates advanced techniques for extracting frequency curves from nonstationary signals to detect the fault characteristic frequencies (FCFs) of rolling bearings. The effectiveness of this approach is showcased through both a simulated example and an experimental instance. Furthermore, a comprehensive comparison of the novel method with existing techniques is provided. [ABSTRACT FROM AUTHOR]

The Controller Area Network (CAN) has been adopted in various reliability-critical industrial systems. However, intermittent connection (IC) problems of network cables may worsen system performance and even threaten operational safety. Recently, there have been several studies on diagnosing intermittent open circuit faults, but the intermittent short circuit (ISC) fault diagnosis has not been addressed. In this paper, a novel ISC fault location method for CANs is proposed based on two-port network modeling. First, the CAN network is modeled as a switched system that depends on the states of the sending nodes using a two-port network approach. An equivalent circuit model and a voltage transfer difference function (VTDF) group are derived for each state where one particular node is sending. Second, upon each fault, corresponding direction events are defined by comparing the two VTDF values that are calculated from the voltages collected at network ends. Then, the fault and health domains can be determined by integrating these direction events with the network topology information according to their statistical significance. Third, a bidirectional eviction localization algorithm is developed to identify ISC fault locations based on the fault and health domains. A testbed is constructed, and case studies are conducted to demonstrate that the proposed method can correctly locate the ISC faults in various network topological layouts. [ABSTRACT FROM AUTHOR]

Neural network (NN)-based methods are extensively used for intelligent fault diagnosis in industrial systems. Nevertheless, due to the limited availability of faulty samples and the presence of noise interference, most existing NN-based methods perform limited diagnosis performance. In response to these challenges, a self-adaptive selection graph pooling method is proposed. Firstly, graph encoders with sharing parameters are designed to extract local structure-feature information (SFI) of multiple sensor-wise sub-graphs. Then, the temporal continuity of the SFI is maintained through time-by-time concatenation, resulting in a global sensor graph and reducing the dependency on data volume from the perspective of adding prior knowledge. Subsequently, leveraging a self-adaptive node selection mechanism, the noise interference of redundant and noisy sensor-wise nodes in the graph is alleviated, allowing the networks to concentrate on the fault-attention nodes. Finally, the local max pooling and global mean pooling of the node-selection graph are incorporated in the readout module to get the multi-scale graph features, which serve as input to a multi-layer perceptron for fault diagnosis. Two experimental studies involving different mechanical and electrical systems demonstrate that the proposed method not only achieves superior diagnosis performance with limited data, but also maintains strong anti-interference ability in noisy environments. Additionally, it exhibits good interpretability through the proposed self-adaptive node selection mechanism and visualization methods. • Introducing SASGPool: A novel data-driven fault diagnosis method. • SASGPool excels with limited samples and noise interference. • Diverse graph topologies capture multiscale sensor data relationships. • Innovative node selection sharpens focus on fault-attention features. • SASGPool achieves precise fault diagnosis in electrical and mechanical systems. [ABSTRACT FROM AUTHOR]

As an important branch of machine learning, deep learning (DL) models with multiple hidden layer structures have the ability to extract highly representative features from the input. At present, fault detection and diagnosis (FDD) and health monitoring solutions developed based on DL models have received extensive attention in academia and industry along with the rapid improvement of computing power. Therefore, this paper focuses on a comprehensive review of DL model–based FDD and health monitoring schemes in view of common problems of industrial systems. First, brief theoretical backgrounds of basic DL models are introduced. Then, related publications are discussed about the development of DL and graphical models in the industrial context. Afterwards, public data sets are summarized, which are associated with several research papers. More importantly, suggestions on DL model–based diagnosis and health monitoring solutions and future developments are given. Our work will have a positive impact on the selection and design of FDD solutions based on DL and graphical models in the future. [ABSTRACT FROM AUTHOR]

Rotating machinery is widely used in modern industrial systems, and its health status can directly impact the operation of the entire system. Timely and accurate diagnosis of rotating machinery faults is crucial for ensuring production safety, reducing economic losses, and improving efficiency. Traditional deep learning methods can only extract features from the vertices of the input data, thereby overlooking the information contained in the relationships between vertices. This paper proposes a Legendre graph convolutional network (LGCN) integrated with a self-attention graph pooling method, which is applied to fault diagnosis of rotating machinery. The SA-LGCN model converts vibration signals from Euclidean space into graph signals in non-Euclidean space, employing a fast local spectral filter based on Legendre polynomials and a self-attention graph pooling method, significantly improving the model's stability and computational efficiency. By applying the proposed method to 10 different planetary gearbox fault tasks, we verify that it offers significant advantages in fault diagnosis accuracy and load adaptability under various working conditions. [ABSTRACT FROM AUTHOR]

Fault detection and diagnosis of nonstationary processes are crucial for ensuring the safety of industrial production systems. However, the nonstationarity of process data poses multifaceted challenges to them. First, conventional stationary fault detection methods encounter difficulties in discerning evolving trends within nonstationary data. Secondly, the majority of current nonstationary fault detection methods directly extract features from all variables, rendering them susceptible to redundant interference. Moreover, nonstationary trends possess the capacity to conceal and modify the correlations among variables. Coupled with the smearing effect of faults, it is challenging to achieve accurate fault diagnosis. To address these challenges, this paper proposes sparse Wasserstein stationary subspace analysis (SWSSA). Specifically, a ℓ 2 , p -norm constraint is introduced to endow the stationary subspace model with excellent sparse representation capability. Furthermore, recognizing that fault variables within the sparse stationary subspace influence only a limited subset of stationary sources, this paper proposes a novel contribution analysis method based on local dynamic preserving projection (LDPP), termed LDPPBC, which can effectively mitigate the smearing effect on nonstationary fault diagnosis. LDPPBC establishes a LDPP matrix by extracting the latent positional information of fault variables within the stationary subspace. This allows LDPPBC to selectively analyze the contributions of variables within the latent fault subspace to achieve precise fault diagnosis while avoiding the interference of variable contributions from the fault-free subspace. Finally, the superiority of the proposed method is thoroughly validated through a numerical simulation, a continuous stirred tank reactor, and a real industrial roaster. • This method can realize fault diagnosis under the influence of nonstationarity. • The smearing effect of faults is effectively mitigated. • Through mathematical deduction, the convergence of the algorithm is proven. [ABSTRACT FROM AUTHOR]

Gearbox fault diagnosis is essential in the maintenance and preventive repair of industrial systems. However, in actual working environments, noise frequently interferes with fault signals, consequently reducing the accuracy of fault diagnosis. To effectively address this issue, this paper incorporates the noise attenuation of the DRSN-CW model. A compound fault detection method for gearboxes, integrated with a cross-attention module, is proposed to enhance fault diagnosis performance in noisy environments. First, frequency domain features are extracted from the public dataset by using the fast Fourier transform (FFT). Furthermore, the cross-attention mechanism model is inserted in the optimal position to improve the extraction and recognition rate of global and local fault features. Finally, noise-related features are filtered through soft thresholds within the network structure to efficiently mitigate noise interference. The experimental results show that, compared to existing network models, the proposed model exhibits superior noise immunity and high-precision fault diagnosis performance. [ABSTRACT FROM AUTHOR]

The Induction Motor (IM) is one of the most frequently used prime movers in most industrial and transportation systems. The motor's stable and safe operation directly influences the secure and reliable operation of such prime movers. Developing an intelligent fault diagnosis system for such motors is very significant. This paper presents an intelligent fault diagnosis method based on the improved functionality of a Convolutional Neural Network (CNN) through its hyperparameter optimization using a nature‐inspired Artificial Bee Colony Optimization (ABCO) algorithm. The proposed diagnostic method introduces and analyses various possible mechanical and electrical faults in the IM. The validation of the proposed method is presented with three different modalities, including vibration, acoustic, and infrared thermography, with their comparative performance analysis. Vibration and acoustic‐based detection are done with time‐frequency scalograms using Constant Q Transform (CQT), which provides enhanced time resolution for lower and higher frequencies. The obtained result indicates that the infrared thermography‐based anomaly detection outperforms the vibration and acoustic‐based diagnosis with 100% classification accuracy. The results signify the potential to diagnose different mechanical and electrical faults in IM with substantial reliability and robustness. [ABSTRACT FROM AUTHOR]

Wavelet transform is a powerful time-frequency-based analysis method often used in gear fault diagnostics. The development of wavelet transform is closely linked to the improvement of resolution. When the high-frequency resolution allows for easy observation of different frequency components, it is a symptom of damage to an individual part of the machine. This study effectively applied the Wavelet analysis technique to diagnose faulty gearboxes operated in non-stationary conditions. This is a complex problem that usual diagnostic approaches need help to solve due to its non-linear character. This work conducted a simulation and real-world testing to show that the newest wavelet analysis techniques work well, showing that they can accurately find gear faults in gearboxes in non-stationary conditions. A thorough overview of the cutting-edge applications of wavelet transform in diagnosing faults in industrial gearbox systems was also given. This work also explained in detail the mathematical ideas behind the continuous wavelet transform, discrete wavelet transforms, and wavelet packet transform. [ABSTRACT FROM AUTHOR]

This study introduces the Adversarial Task Augmented Sequential Meta-Learning (ATASML) framework, designed to enhance fault diagnosis in industrial processes. ATASML integrates adversarial learning with sequential task learning to improve the model's adaptability and robustness, facilitating precise fault identification under varied conditions. Key to ATASML's approach is its novel use of adversarial examples and data-augmentation techniques, including noise injection and temporal warping, which extend the model's exposure to diverse operational scenarios and fault manifestations. This enriched training environment significantly boosts the model's ability to generalize from limited data, a critical advantage in industrial applications where anomaly patterns frequently vary. The framework's performance was rigorously evaluated on two benchmark datasets: the Tennessee Eastman Process (TEP) and the Skoltech Anomaly Benchmark (SKAB), which are representative of complex industrial systems. The results indicate that ATASML outperforms conventional meta-learning models, particularly in scenarios characterized by few-shot learning requirements. Notably, ATASML demonstrated superior accuracy and F1 scores, validating its effectiveness in enhancing fault-diagnosis capabilities. Furthermore, ATASML's strategic incorporation of task sequencing and adversarial tasks optimizes the training process, which not only refines learning outcomes but also improves computational efficiency. This study confirms the utility of the ATASML framework in significantly enhancing the accuracy and reliability of fault-diagnosis systems under diverse and challenging conditions prevalent in industrial processes. [ABSTRACT FROM AUTHOR]

The stable operation of the process industrial system, which is integrated with various complex equipment, is the premise of production, which requires the condition monitoring and diagnosis of the system. Recently, the continuous development of deep learning (DL) has promoted the research of intelligent diagnosis in process industry systems, and the sensor system layout has provided sufficient data foundation for this task. However, these DL-driven approaches have had some shortcomings: (1) the output signals of heterogeneous sensing systems existing in process industry systems are often high-dimensional coupled and (2) the fault diagnosis model built from pure data lacks systematic process knowledge, resulting in inaccurate fitting. To solve these problems, a graph feature fusion-driven fault diagnosis of complex process industry systems is proposed in this paper. First, according to the system's prior knowledge and data characteristics, the original multisource heterogeneous data are divided into two categories. On this basis, the two kinds of data are converted to physical space graphs (PSG) and process knowledge graphs (PKG), respectively, according to the physical space layout and reaction mechanism of the system. Second, the node features and system spatial features of the subgraphs are extracted by the graph convolutional neural network at the same time, and the fault representation information of the subgraph is mined. Finally, the attention mechanism is used to fuse the learned subgraph features getting the global-graph representation for fault diagnosis. Two publicly available process chemistry datasets validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Fault diagnosis is a crucial technology for ensuring the reliable and efficient operation of industrial systems. With the advancement of industrial informatization and intelligence, fault diagnosis methods have the trend shifting from traditional signal processing to deep learning. However, traditional deep learning models are not suitable for industrial scenarios with limited labeled data, imbalanced categories. To address these challenges, this paper proposes a novel approach based on semi-supervised generative adversarial networks (SGANs) to systematically study the fault diagnosis of rolling bearings in the case of unlabeled samples and sparsely labeled samples. In this work, the vibration time-domain vibration signal of the bearing is firstly transformed into a spectrum signal through the fast Fourier transform. This transformed signal is then fed into the GAN model to extract multi-layer sensitive features, providing a deeper understanding of the underlying fault characteristics. Subsequently, the SGAN method utilizes unsupervised learning via spectral clustering algorithms to automatically classify fault patterns in industrial equipment. Furthermore, it enhances semi-supervised learning by incorporating limited label information through softmax functions, effectively discerning the authenticity of unlabeled data. For the effectiveness of SGAN for bearing fault diagnosis, two diverse datasets are utilized including the widely-used Case Western Reserve University dataset and data acquired from South Ural State University. Compared to alternative models, the results underscore SGAN's robustness, achieving high recognition accuracy and clustering performance. The proposed methodology contributes to the advancement of fault diagnosis technologies by combining unsupervised and semi-supervised learning techniques. [ABSTRACT FROM AUTHOR]

Process abnormalities can result in serious accidents that may lead to unexpected loss of life and property. Early fault detection and diagnosis are essential to prevent these accidents. In the efficient operation of industrial systems, alarm systems play a crucial role. Developing new sensors and alarm adjustment networks has increased the possibility of generating multiple alarms. The alarm flood is the most important type of this problem. In this study, a new algorithm is proposed to diagnose the root cause of the fault through the classification of alarm floods. The main novelty of this algorithm is to use transfer entropy as a criterion to detect the similarity between the alarm flood sequences. The other innovations include calculating transfer entropy between the process variable and the alarm data, multi-sensor information fusion for large-scale plants and simultaneous alarms, and proposing an online version of the algorithm for the early prediction of the type of fault occurring. Finally, the Tennessee Eastman Process system, as a simulator, and the Saveh rotary cement kiln, as a real industrial system, are applied to evaluate the proposed method. • Diagnosing the root cause of the faults through the classification of the alarm floods. • Using transfer entropy to detect the similarity between the alarm flood sequences. • Calculation of the transfer entropy between the process variable and the alarm data. • Multi-sensor information fusion for large-scale plant and simultaneous alarms. • An online method for early predict of the root cause of the alarm floods occurring. [ABSTRACT FROM AUTHOR]

The fault detection and isolation (FDI) procedure increases the assurance of quality, reliability, and safety of industrial systems. Several faults may appear simultaneously, and the purpose of multi-fault diagnosis is to identify and locate these multiple faults. This work is particularly interested in the diagnosis based on the structural analysis of the system; residuals can be generated and used as fault indicators by model-based fault detection techniques. The isolation is dependent on the structure of the fault signature matrix. A new fault signature that represents the superposition of the fault is produced by simultaneous fault effects, resulting in an additional column in an extended signature matrix. This remedy is rather combinatorial. This research focuses on two methods to isolate multiple faults: (1) A modified enumerative method; (2) A hybrid ant colony optimization algorithm-genetic algorithm (Hybrid ACO-GA) is adapted to the MFD problem which has the advantage of a better research as well as the hybridization with GA. [ABSTRACT FROM AUTHOR]

The reconstruction-based (RB) approach can effectively suppress the misdiagnosis problem due to the smearing effect in fault isolation. However, the current exploration of the RB approach for large-scale nonlinear systems is still limited. Therefore, this paper proposes a reliable and effective fault diagnosis method based on a reconstructionbased stacked sparse autoencoder (RBSSAE) for high-dimensional industrial systems. In RBSSAE, a reconstruction-based index achieved by the Steffensen iterative method is developed to check whether the given variable(s) are responsible for the faults efficiently. However, the number of possible faulty variable combinations grows exponentially with the system dimension or actual abnormal variables, causing an unbearable computational burden for variable combination optimization. Hence, the proposed RBSSAE utilizes a sequential floating forward selection approach to rapidly isolate the most decisive combination of fault variables, meeting a requirement of online fault diagnosis. Finally, the effectiveness of the RBSSAE is verified on a numerical example and a real industrial case. Comparisons with other state-of-the-art methods are also presented. [ABSTRACT FROM AUTHOR]

In this paper, we propose the gradient-oriented prioritization meta-learning (GOPML) algorithm, a new approach for few-shot fault diagnosis in industrial systems. The GOPML algorithm utilizes gradient information to prioritize tasks, aiming to improve learning efficiency and diagnostic accuracy. This method contrasts with conventional techniques by considering both the magnitude and direction of gradients for task prioritization, which potentially enhances fault classification performance in scenarios with limited data. Our evaluation of GOPML's performance across varied fault conditions and operational contexts includes extensive testing on the Tennessee Eastman Process (TEP) and Skoltech Anomaly Benchmark (SKAB) datasets. The results indicate a consistent level of performance across different dataset divisions, suggesting its utility in practical industrial settings. The adaptability of GOPML to specific task characteristics, particularly in environments with sparse data, represents a notable contribution to the field of meta-learning for industrial fault diagnosis. GOPML shows promise in addressing the challenges of few-shot fault diagnosis in industrial systems, contributing to the growing body of research in this area by offering an approach that balances accuracy and generalization with limited data. [ABSTRACT FROM AUTHOR]

This study presents a novel approach to simulating and monitoring the dynamic performance of high-speed bearings, a critical component in automated industrial production for system efficiency and safety. The newly developed theoretical framework allows for detailed analysis of dynamic responses in these bearings, especially under high-speed conditions. The Short-Time Fourier Transform (STFT) is used to capture time-frequency domain characteristics, while real-time condition monitoring is achieved through a deep learning-based Convolutional Neural Network, enhanced by a multi-head attention mechanism. This method enables managing large datasets, real-time surveillance, and accurate prediction of bearing conditions. Ultimately, this approach provides an innovative perspective for fault diagnosis and performance assessment of high-speed bearings in complex production environments. [ABSTRACT FROM AUTHOR]

One of the major challenges facing fault diagnosis tools is their exposure to noise. The presence of noise may cause false alarms or the inability to detect a progressive fault in the early stages of its occurrence. Continuing previous efforts to address such a problem, in this paper, a noise‐robust diagnosis system for an industrial gas turbine is presented. The proposed structure employs a set of deep residual compensation extreme learning machines (DRCELMs). In this model, an optimal number of compensating blocks are trained to recover some of the lost useful information in the face of noise. Training and testing data required to develop the fault diagnosis model are generated by a performance model of the studied gas turbine. The t‐distributed stochastic neighbor embedding algorithm is employed for visualizing the gas path faults. Furthermore, the performance of the DRCELM is evaluated by comparing it with six other diagnosis models. The results indicate higher robustness of the DRCELM compared to other fault diagnosis systems. The proposed model presents a classification accuracy of >97% in noisy data and an accuracy of >98% in noise‐free data and combined data, while the average of fault positive rate and fault negative rate in noisy data is less than 2.5%. [ABSTRACT FROM AUTHOR]

Modern manufacturing systems are often installed with sensor networks which generate high-dimensional data at high velocity. These data streams offer valuable information about the industrial system's real-time performance. If a shift occurs in the manufacturing process, fault diagnosis based on the data streams becomes a fundamental task as it identifies the affected data streams and provides insights into the root cause. Existing fault diagnostic methods either ignore the correlation between different streams or fail to determine the shift directions. In this paper, we propose a directional fault classification procedure that incorporates the between-stream correlations. We suggest a three-state hidden Markov model that captures the correlation structure and enables inference about the shift direction. We show that our procedure is optimal in the sense that it minimizes the expected number of false discoveries while controlling the proportion of missed signals at a desired level. We also propose a deconvolution-expectation-maximization (DEM) algorithm for estimating the model parameters and establish the asymptotic optimality for the data-driven version of our procedure. Numerical comparisons with an existing approach and an application to a semiconductor production study show that the proposed procedure works well in practice. [ABSTRACT FROM AUTHOR]

The safe operation of the fluid machine is greatly affected by fault states. With the development of data collection technology in process industrial systems, data-based methods are widely applied in fault diagnosis. The observed data of the fluid machine belongs to typical multivariable time series, so the Euclidean features related to the observed timestamps and the non-Euclidean features related to the observed variables need to be extracted simultaneously by the fault diagnosis method. However, the existing diagnostic studies do not involve the explainability analysis of the diagnostic process, which makes it hard to evaluate the contribution of these features to the accurate diagnosis. An explainable diagnosis model based on temporal and graph convolutional neural network is proposed. The class activation map algorithm is improved to perform explainability analysis of the diagnosis process related to the observed variables and timestamps. Using the simulation data of the fluid machine, features related to observed variables and timestamps of six operating states are fully extracted. Through data experiments, this method can be utilized to achieve high-precision fault diagnosis, and can intuitively display the contribution of each observed variable and its each timestamp to network decision-making. This helps to trace system faults and has significant benefits for process safety assurance. [ABSTRACT FROM AUTHOR]

Purpose: The global interest of developing monitoring system is increasing due to the continuous challenges in reliability and accuracy. Automatic fault detection and diagnosis of rotating machinery play an important role for the high efficiency and reliability of modern industrial systems. The key point of having high accurate automatic model for fault detection and diagnosis is obtaining defect features and choosing a representative approach for the model. Methods: In this paper, a model is developed based on Mel Frequency Cepstral Coefficients (MFCC) and gammatone cepstral coefficients (GTCC) that are computed for the input signal frames. Additionally, two global representations (feature concatenation and feature statistics) are adopted to feed Support Vector Machine (SVM) and a temporal representation is used with Long Short-Term Memory (LSTM) and Echo State Network (ESN) classification models. To generalize the proposed model, the experiments are evaluated based on two different datasets (PHM09 and DDS), where the PHM09 contains samples of helical and spur gears while the DDS contains samples from parallel and plenary gearboxes. Results: The results show that the proposed SVM model based on feature concatenation can effectively detect faults from gears and outperforms the other existing methods in the state-of-the-art studies. Conclusion: Base on the result of this paper, a global representation by concatenating frame-based features outperforms global statistical and time-series feature representations. [ABSTRACT FROM AUTHOR]

Incipient fault diagnosis is particularly important in process industrial systems, as its early detection helps to prevent major accidents. Against this background, this study proposes a combined method of mixed kernel principal components analysis and dynamic canonical correlation analysis (MK-DCCA). The robust generalization performance of this approach is demonstrated through experimental validation on a randomly generated dataset. Furthermore, comparative experiments were conducted on a CSTR Simulink model, comparing the MK-DCCA method with DCCA and DCVA methods, demonstrating its excellent detection performance for incipient faults in nonlinear and dynamic systems. Meanwhile, fault identification experiments were conducted, validating the high accuracy of the fault identification method based on contribution. The experimental findings demonstrate that the method possesses a certain industrial significance and academic relevance. [ABSTRACT FROM AUTHOR]

The reliable and safe operation of industrial systems needs to detect and diagnose bearing faults as early as possible. Intelligent fault diagnostic systems that use deep learning convolutional neural network (CNN) techniques have achieved a great deal of success in recent years. In a traditional CNN, the fully connected layer is located in the final three layers, and such a layer consists of multiple layers that are all connected. However, the fully connected layer of the CNN has the disadvantage of too many training parameters, which makes the model training and testing time longer and incurs overfitting. Additionally, because the working load is constantly changing and noise from the place of operation is unavoidable, the efficiency of intelligent fault diagnosis techniques suffers great reductions. In this research, we propose a novel technique that can effectively solve the problem of traditional CNN and accurately identify the bearing fault. Firstly, the best pre-trained CNN model is identified by considering the classification's success rate for bearing fault diagnosis. Secondly, the selected CNN model is modified to effectively reduce the parameter quantities, overfitting, and calculating time of this model. Finally, the best classifier is identified to make a hybrid model concept to achieve the best performance. It is found that the proposed technique performs well under different load conditions, even in noisy environments, with variable signal-to-noise ratio (SNR) values. Our experimental results confirm that this proposed method is highly reliable and efficient in detecting and classifying bearing faults. [ABSTRACT FROM AUTHOR]

It is essential to accurately diagnose bearing faults to avoid property losses or casualties in the industry caused by motor failures. Recently, the methods of fault diagnosis for bearings using deep learning methods have improved the safety of motor operations in a reliable and intelligent way. However, most of the work is mainly suitable for situations where there is sufficient monitoring data of the bearings. In industrial systems, only a small amount of monitoring data can be collected by the bearing sensors due to the harsh monitoring conditions and the short time of the signals of some special motor bearings. To solve the issue above, this paper introduces a transfer learning strategy by focusing on the multi-local model bearing fault based on small sample fusion. The algorithm mainly includes the following steps: (1) constructing a parallel Bi-LSTM sub-network to extract features from bearing vibration and current signals of industrial motor bearings, serially fusing the extracted vibration and current signal features for fault classification, and using them as a source domain fault diagnosis model; (2) measuring the distribution difference between the source domain bearing data and the target bearing data using the maximum mean difference algorithm; (3) based on the distribution differences between the source domain and the target domain, transferring the network parameters of the source domain fault diagnosis model, fine-tuning the network structure of the source domain fault diagnosis model, and obtaining the target domain fault diagnosis model. A performance evaluation reveals that a higher fault diagnosis accuracy under small sample fusion can be maintained by the proposed method compared to other methods. In addition, the early training time of the fault diagnosis model can be reduced, and its generalization ability can be improved to a great extent. Specifically, the fault diagnosis accuracy can be improved to higher than 80% while the training time can be reduced to 15.3% by using the proposed method. [ABSTRACT FROM AUTHOR]

In the last decade, the adoption of technological tools in manufacturing industry, such as the use of the Internet of Things (IoT) and Machine Learning (ML), has led to the advent of the industry 4.0 (I4.0). In this scenario, intelligent devices can generate large volumes of data about industrial machinery and equipment that can be used to make maintenance more efficient. Prognostics and Health Management (PHM) is an emerging maintenance strategy that uses systems' Condition Monitoring through IoT sensors installed on machinery to diagnose their faults or estimate their Remaining Useful Life (RUL). This study aims to conduct a Systematic Literature Review (SLR) on the use of ML techniques in the field of PHM of industrial mechanical systems and equipment. 50 studies resulted eligible for the above-mentioned SLR. Diagnostics and prognostics approach and the ML algorithm types used in the 50 analyzed papers have been analyzed together with the Key Performance Indicators (KPIs) used for their validation. From the analyses, it was found that Shallow Learning and Deep Learning (DL) algorithms are the most applied ones, while KPIs are used differently according to the type of task classification or regression. Moreover, results highlighted that many authors still use artificial datasets to test their algorithms, instead of datasets based on real data retrieved by their components. For the last type of datasets, this paper also introduces a schematic framework to standardize the step-by-step diagnostics and prognostics process carried out by the authors. [ABSTRACT FROM AUTHOR]

In industrial manufacturing systems, failures of machines caused by faults in their key components greatly influence operational safety and system reliability. Many data-driven methods have been developed for machinery diagnostics and prognostics. However, there lacks sufficient labeled data to train a high-performance data-driven model. Moreover, machinery datasets are usually collected from different operation conditions and mechanical components, leading to poor model generalization. To address these concerns, cross-domain transfer learning methods are applied to enhance the feasibility and accuracy of data-driven methods for machinery diagnostics and prognostics. This paper presents a comprehensive survey about how recent studies apply diverse transfer learning methods into machinery tasks including diagnostics and prognostics. Three types of commonly-used transfer methods, i.e., model and parameter transfer, feature matching and adversarial adaptation, are systematically summarized and elaborated on their main ideas, typical models and corresponding representative studies on machinery diagnostics and prognostics. In addition, ten widely-used open-source machinery datasets are presented. Based on recent research progress, this survey expounds emerging challenges and future research directions of transfer learning for industrial applications. This survey presents a systematic review of recent research with clear explanations as well as in-depth insights, thereby helping readers better understand transfer learning for machinery diagnostics and prognostics. [ABSTRACT FROM AUTHOR]

Nonstationary characteristics and lack of time delays analysis remain two large obstacles to diagnosing fault root cause in industrial processes. However, ignoring these two issues, many traditional methods tend to introduce some spurious or indirect causal relationships that interfere with root cause judgments. In this article, multiscale partial symbolic transfer entropy (MPSTE) is proposed to handle the above-mentioned problems. On the one hand, a multivariate multiscale filter module of MPSTE is designed to estimate the information transfer on multiple time scales and detect time delays while considering the indirect causality of the multivariate industrial system. On the other hand, to capture the causal information from the nonstationary processes, MPSTE introduces a segmental symbolization procedure and maps time series into finite rank vectors, overcoming the limitation of stationarity. Moreover, two causal criteria for MPSTE are constructed to identify the direction and significance level of causality correspondingly. MPSTE can thus provide sufficient information for causal relationships and exclude spurious causality. Finally, a causal diagram construction strategy with time delay based on MPSTE is established to diagnose the root cause and trace the fault propagation path. The results of experimental verification in a coal mill rig prove the effectiveness of the proposed strategy. [ABSTRACT FROM AUTHOR]

Copyright of Bearing is the property of Bearing Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Developments in data storage and sensor technologies have allowed the cumulation of a large volume of data from industrial systems. Both structural and non-structural data of industrial systems are collected, which covers data formats of time-series, text, images, sound, etc. Several researchers discussed above were mostly qualitative, and ceratin techniques need expert guidance to conclude on the condition of gearboxes. But, in this study, an improved symbiotic organism search with deep learning enabled fault diagnosis (ISOSDL-FD) model for gearbox fault detection in industrial systems. The proposed ISOSDL-FD technique majorly concentrates on the identification and classification of faults in the gearbox data. In addition, a Fast kurtogram based time-frequency analysis can be used for revealing the energy present in the machinery signals in the time-frequency representation. Moreover, the deep bidirectional recurrent neural network (DBiRNN) is applied for fault detection and classification. At last, the ISOS approach was derived for optimal hyperparameter tuning of the DL method so that the classification performance will be improvised. To illustrate the improvised performance of the ISOSDL-FD algorithm, a comprehensive experimental analysis can be performed. The experimental results stated the betterment of the ISOSDLFD algorithm over current techniques. [ABSTRACT FROM AUTHOR]

Recently, fault diagnosis methods based on domain generalization (DG) have been developed to improve the diagnostic performance of unseen target domains by multi-source domain knowledge transfer. However, existing methods assume that the source domains are discrete and that domain labels are known a priori, which is difficult to satisfy in complex and changing industrial systems. In addition, the gradient update conflict caused by the specific information of source domains leads to the degradation of the DG performance. Therefore, in this study, we relax the discrete domain assumption to the mixed domain setting and propose a novel gradient-consistency strategy cooperative meta-feature learning for mixed-domain generalized machine fault diagnosis. First, a domain feature-guided adaptive normalization module is proposed to normalize the underlying distribution of multi-source domains, and the mixed-source domains are divided into potential domain clusters. Then, a novel meta-feature encoding method is proposed to explicitly encode the overall fault feature structure, which is used to learn the generalized fault feature representation. Finally, a novel gradient consistency update strategy is designed to reduce the impact of domain-specific differences on model generalization. The effectiveness and superiority of the proposed method are verified on many DG diagnostic tasks on two public bearing datasets and the nuclear circulating water pump planetary gearbox dataset. • A novel mixed domain generalization strategy is proposed for machine fault diagnosis. • An adaptive normalization module normalizes and clusters latent domain. • A meta-feature encoding and comparison learning model latent domain fault structures. • A gradient-consistent update strategy reduces domain differences for generalization. [ABSTRACT FROM AUTHOR]

With the advancement of intelligent sensing techniques, massive monitoring signals are collected and accumulated from industrial systems. Given that sensors are often correlated and constructed to reflect graph topology, the signals can be conceptualized as graph data. The polynomial filter-based graph neural networks (GNNs) are commonly employed to exploit information from nodes features and graph topology for graph data analysis. However, the polynomial filter-based GNNs encounter difficulty in accurately modeling sharp changes and the coefficients can vary a lot, making them hard to learn. To address this problem, a novel graph neural network named extended auto-regressive moving average graph neural network (eAGNN) is proposed. Compared with auto-regressive moving average (ARMA) neural network, the order restriction are removed, allowing for the inference of a more general neural network, which enables the modeling of filters with more different shapes. Furthermore, both low-frequency and high-frequency information are explicitly and separately extracted so as to alleviate the burden of the learning process and further enhance the learning capability. Finally, several experiments including public node classification and fault diagnosis were conducted. The results demonstrate that the proposed eAGNN exhibits high performance compared to alternative methods. [Display omitted] • Order restriction in ARMA filters is removed for a more general neural network. • Low and high frequency information are extracted explicitly and separately. • The effect of filter modification on model performance is qualitatively analyzed. • Extensive experiments are utilized to verify the high performance of our model. [ABSTRACT FROM AUTHOR]

High-precision fault diagnosis of rotating machinery plays an important role in industrial systems. Today, rotating machinery often has multiple sensors to monitor equipment condition, so it is important to fuse data from multiple rotating machinery sensors for fault diagnosis. Most of the current multi-sensor fusion fault diagnosis methods are single-level, which cannot fully utilize the effective information in multi-sensor data, and have certain limitations. Therefore, this article proposes a multi-level information fusion fault diagnosis method. Specifically, first, multilayer graph data is constructed by analysing the correlation between different sensors as well as samples to realize multi-sensor data level fusion. Then, convolutional neural network and graph convolutional network are used to extract different types of features from the data, and a feature fusion method based on the attention mechanism is proposed to realize feature enhancement. Finally, a decision fusion strategy based on information entropy is established to reduce the impact of misclassification results and maximize the reliability and robustness of the model output. Experimental validation of the proposed method is carried out using the publicly available dataset and pumped storage unit operational state data. The experimental results show that the proposed strategy is of positive significance to improve multi-sensor data fusion fault diagnosis, and the model has a higher diagnostic accuracy compared with other multi-sensor data fusion fault diagnosis models. • A multi-layer graph data construction method is proposed. • A multi-type feature fusion mechanism based on the attention mechanism is proposed. • A decision fusion strategy based on information entropy is proposed. • A multi-level data fusion framework for fault diagnosis of rotating machinery is proposed. [ABSTRACT FROM AUTHOR]

Deep Learning has been attracting considerable attention as it can autonomously learn important signal features and has shown great potential for fault diagnosis. However, given the variability of high-power variable-frequency industrial systems, especially under unfavorable service conditions such as voltage and load fluctuations, the identification of insulated bearing faults in variable-frequency motors has become a key challenge to be addressed. Moreover, the time-varying nature of insulated bearing data poses common technical difficulties for existing models. To bridge these gaps, this research spearheaded the development of a lightweight spatial–temporal focusing framework equipped with a novel optimizer called LSTA-Net, which was designed to address the challenging problem of insulated bearing fault identification in real-world engineering scenarios. Specifically, this involves an innovative design of the Weight Reducing Recursive Unit (WDRU) strategy and an updated backpropagation formulation, which was skillfully applied to the feature extraction module of the LSTA-Net framework for the first time. Furthermore, a novel optimizer called Stochastic Newton Descent (SND) has been developed and skillfully integrated into the LSTA-Net framework with the newly derived weight update formula, providing unique insights to improve diagnostic performance. Finally, the diagnostic performance of the LSTA-Net framework was evaluated from multiple dimensions based on the same dataset, proving its superiority, generalizability, and robustness. t-SNE technique integration intuitively explains the framework's fault characterization mining process, improving its credibility, reliability, and accuracy. [ABSTRACT FROM AUTHOR]

Gear monitoring and fault diagnosis are vital for preventing accidents and minimizing economic losses in transportation and industrial systems. Traditional methods use vibration sensors and a two-stage analysis approach: preprocessing data to remove noise and extract relevant components, and generating a condition indicator to detect behavioral anomalies in the gears over time. Time synchronous averaging is a notable tool for monitoring gears at constant speeds. Such a tool filters sensor signals and extracts rotation-related components by using statistical measurements as condition indicators. However, it has limitations in scenarios with time-varying sampling rates and fluctuating speeds, where statistical measures may not fully capture changes in system parameters. This article proposes a novel methodology for monitoring gears in multivariate rotordynamical systems under fluctuating speed conditions. The method integrates time synchronous averaging, system identification algorithms, and statistical tools. It generates a time-synchronous average signal considering speed fluctuations, computes a state–space model of gear behavior in healthy states, extracts residual data from a data-driven model, and generates a condition indicator based on the Cauchy–Schwarz divergence. The proposed methodology was evaluated using experimental data from three rotor dynamical setups under different operational conditions. Validation showed its effectiveness, especially under high-load conditions with significant speed fluctuations. • A novel methodology for gears monitoring spinning at fluctuating angular speed is proposed. • The proposed methodology is based on signal processing and system identification techniques. • A condition indicator for gear diagnosis based on Cauchy–Schwarz divergence is established. • Experimental validation was conducted using two rotodynamic setups. • The methodology is compared with existing methods in the literature. [ABSTRACT FROM AUTHOR]

• Pre-trained LLMs are incorporated to perform fault diagnosis of complex systems. • An LLM-diagnosis framework is introduced to integrate and fine-tune LLMs for system fault diagnosis. • Experiments are conducted using open- and closed-source models on two datasets. • We analyze and discuss in several aspects the potential and limitations of the approach. With increasing complexity and interconnectivity of the modern industrial systems, effectively diagnosing faults is a core step to Prognostic and Health Management (PHM). Language models, particularly Large Language Models (LLMs) that pre-trained on massive corpora, have demonstrated remarkable capabilities in Natural Language Processing (NLP) and its related downstream tasks. However, how to leverage these models for facilitating system fault diagnosis and verify its effectiveness is rarely explored. This paper incorporates the potential comprehension ability of pre-trained LLMs, and investigates the efficacy of fine-tuning LLMs for realizing efficient system fault diagnosis. The experiments conducted in this study involve both open-source and closed-source models, and utilize a simulation and a real fault diagnosis dataset. We find that these models consistently achieve high performance across various metrics compared to the baselines. Additionally, qualitative and quantitative analysis is performed to investigate several aspects of the approach, such as the impact of dataset size, data normalization, missing values and explainability of the diagnosis, further showcasing the potential as well as limitations of the approach. [ABSTRACT FROM AUTHOR]

In recent years, some progress has been made in fault diagnosis of multi-block regression model, but multi-block method uses the relationship between variables in Hilbert space to block, while the relationship between variables in complex industrial systems often exists in Banach space. In addition, Bayesian fusion method is used in fault monitoring, which can not accurately process the sub-block information and judge whether the fault information is related to the output. In this paper, a new multi-block method is proposed. Firstly, this method uses Ball Covariance (BCov) suitable for Banach space to describe the correlation between variables, and combines K-means clustering method to block variables to ensure that the blocking method is more reasonable. Secondly, an improved orthogonal decomposition Broyden-Fletcher -Goldfarb-Shanno (BFGS) algorithm is proposed. The MOBFGS algorithm performs orthogonal projection on potential structures, removing information orthogonal to the output from the input block. Furthermore, through complete orthogonal decomposition between the input block and the output block, information related to and unrelated to the output is completely separated, and used to detect output related and unrelated faults, respectively. Thirdly, at the block level, MOBFGS algorithm is used for fault detection and contribution graph method for fault diagnosis. Finally, numerical examples and Tennessee Eastman (TE) process simulation verify the effectiveness of this method. [ABSTRACT FROM AUTHOR]

Process fault detection and diagnosis (FDD) is a predominant task to ensure product quality and process reliability in modern industrial systems. Those traditional FDD techniques are largely based on diagnostic experience. These methods have met significant challenges with immense expansion of plant scale and large numbers of process variables. Recently, deep learning has become the newest trends in process control. The upsurge of deep neural networks (DNNs) in leaning highly discriminative features from complicated process data has provided practitioners with effective process monitoring tools. This paper is to present a review and full developing route of deep learning-based FDD in complex process industries. Firstly, the nature of traditional data projection-based and machine learning-based FDD methods is discussed in process FDD. Secondly, the characteristics of deep learning and their applications in process FDD are illustrated. Thirdly, these typical deep learning techniques, e.g., transfer learning, generative adversarial network, capsule network, graph neural network, are presented for process FDD. These DNNs will effectively solve these problems of fault detection, fault classification, and fault isolation in process. Finally, the developing route of DNN-based process FDD techniques is highlighted for future work. [ABSTRACT FROM AUTHOR]

The Industry 4.0 paradigm aims to obtain high levels of productivity and efficiency, more competitive final products, and compliance with demanding regulations related to industrial safety and cyber-security. To achieve these goals, industrial systems must be equipped with condition monitoring systems for the early detection and localization of faults and cyberattacks. This paper proposes a robust condition-monitoring strategy through the use of Deep Learning algorithms. The proposed scheme was validated using a Tennessee Eastman (TE) process with excellent results. The proposed strategy was compared with other condition monitoring schemes. The higher performance obtained by the proposed scheme indicates its feasibility. [ABSTRACT FROM AUTHOR]

Fault diagnosis of rotating machinery plays a significant role in the reliability and safety of modern industrial systems, which generally requires collaborative fault diagnosis by features extracted from multiple sensors since the multi-channel vibration signals carry a wealth of fault information. However, there is a remaining obstacle for fault diagnosis of multi-source monitoring data: integration of multisensory data. Hence, a novel framework is proposed for fault diagnosis of multi-source monitoring data. First, composite multivariate multi-scale symbolic dynamic entropy is proposed to extract fault features. Second, Laplacian score is introduced to select the distinguishing features with better clustering ability. Finally, the selected features are fed into a logistic regression classifier so that various faults of machinery are diagnosed. The simulation and two case studies using gearbox and pump data are performed to validate and demonstrate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Intelligent mechanical systems are a focused area nowadays. One of the requirements of intelligent mechanical systems is to achieve intelligent fault diagnosis through the real-time acquisition and analysis of data from various sensors installed on mechanical components. In this paper, a new fault diagnosis method is proposed to solve the problems of difficulty in integrating the fault diagnosis algorithm and locating fault parts due to the complexity of modern mechanical systems. The complexity of modern industrial intelligent systems is due to the fact that the systems are composed of multiple components and there are various connections between them. Common fault diagnosis is to design specialized fault identification algorithms for the physical characteristics of each component, and the integration of different algorithms is a major challenge for system performance. Therefore, this paper investigates a general algorithm for the fault diagnosis of complex systems using the timing characteristics of sensors and transfer entropy. The fault diagnosis algorithm is based on the prediction of multi-dimensional long time series using Autoformer, and fault identification is performed based on the deviation of the predicted value from the actual value. After fault identification, a root cause analysis method of faults based on transfer entropy is proposed. The method can locate the component where the fault occurs more accurately based on the analysis of the cause–effect relationship of each component and help maintenance personnel to troubleshoot the fault. [ABSTRACT FROM AUTHOR]

Recently, artificial intelligence (AI)-enabled technologies have been widely employed for complex industrial applications. AI technologies can be utilized to improve efficiency and reduce human labor in industrial applications. At the same time, fault diagnosis (FD) and detection in rotating machinery (RM) becomes a hot research field to assure safety and product quality. Numerous studies based on statistical, machine learning (ML), and mathematical models have been available in the literature for automated fault diagnosis. From this perspective, this study presents a novel sandpiper optimization with an artificial-intelligence-enabled fault diagnosis (SPOAI-FD) technique for intelligent industrial applications. The aim is to detect the existence of faults in machineries. The proposed model involves the design of a continuous wavelet transform (CWT)-based pre-processing approach, which transforms the raw vibration signal into a useful format. In addition, a bidirectional long short-term memory (BLSTM) model is applied as a classifier, and the Faster SqueezeNet model is applied as a feature extractor. In order to modify the hyperparameter values of the BLSTM model, the sandpiper optimization algorithm (SPOA) can be utilized, showing the novelty of the work. A wide range of simulation analyses were conducted on benchmark datasets, and the results highlighted the supremacy of the SPOAI-FD algorithm over recent approaches. [ABSTRACT FROM AUTHOR]

• Diagnosis of twenty faults in refrigeration systems by one classifier is proposed. • CNN, LDA, SVM, PCA-SVM, LDA-SVM classifiers are compared. • Variation of training data is very important to achieve better classification result. • CNN and PCA-SVM can not diagnose the faults satisfactorily. • SVM obtained the best verification result. The functionality of industrial refrigeration systems is important for environment-friendly companies and organizations, since faulty systems can impact human health by lowering food quality, cause pollution, and even lead to increased global warming. Therefore, in this industry, there is a high demand among manufacturers for early and automatic fault diagnosis. In this paper, different machine learning classifiers are tested to find the best solution for diagnosing twenty faults possibly encountered in such systems. All sensor faults and some relevant component faults are simulated in a high fidelity Matlab/Simscape model of the system, which has previously been used for controller development and verification. In this work, Convolutional Neural Networks, Support Vector Machines (SVM), Principal Components Analysis-SVM, Linear Discriminant Analysis-SVM, and Linear Discriminant Analysis classifiers are compared. The results indicate that the fault detection reliability of the algorithms highly depends on how well the training data covers the operation regime. Furthermore, it is found that a well-trained SVM can simultaneously classify twenty types of fault with 95% accuracy when the verification data is taken from different system configurations. [ABSTRACT FROM AUTHOR]

The induction motor plays a vital role in industrial drive systems due to its robustness and easy maintenance but at the same time, it suffers electrical faults, mainly rotor faults such as broken rotor bars. Early shortcoming identification is needed to lessen support expenses and hinder high costs by using failure detection frameworks that give features extraction and pattern grouping of the issue to distinguish the failure in an induction motor using classification models. In this paper, the open-source dataset of the rotor with the broken bars in a three-phase induction motor available on the IEEE data port is used for fault classification. The study aims at fault identification under various loading conditions on the rotor of an induction motor by performing time, frequency, and time-frequency domain feature extraction. The extracted features are provided to the models to classify between the healthy and faulty rotors. The extracted features from the time and frequency domain give an accuracy of up to 87.52% and 88.58%, respectively, using the Random-Forest (RF) model. Whereas, in time-frequency, the Short Time Fourier Transform (STFT) based spectrograms provide reasonably high accuracy, around 97.67%, using a Convolutional Neural Network (CNN) based fine-tuned transfer learning framework for diagnosing induction motor rotor bar severity under various loading conditions. [ABSTRACT FROM AUTHOR]

To solve the problem of nonlinear characteristics neglecting and fault mechanism analysis lacking in fault diagnosis research, a new method of fault mechanism analysis and diagnosis based on nonlinear spectrum is proposed. Firstly, based on the Permanent Magnet Synchronous Motor (PMSM) model of robot, the first 4-order spectrums based on nonlinear output frequency response function (NOFRF) in different states are obtained by batch calculation method. Secondly, the high-frequency spectrum distribution rule of NOFRF spectrum in different states are analyzed. Finally, in the closed-loop simulation environment of robot, the identification method based on data-driven is adopted for NOFRF spectrum calculation to verify power loss fault of PMSM. Meanwhile, the fault diagnosis experiment is also carried out. The experimental results indicate that the key characteristics distribution rule of NOFRF spectrums in the real environment is consistent with the theoretical analysis results, and compared with the traditional fault feature extraction methods by output signal, the diagnosis with fault feature of NOFRF spectrum for industrial robot closed-loop drive system has the highest accuracy, which verifies the validity of NOFRF spectrum as the fault feature. [ABSTRACT FROM AUTHOR]

Rotary encoders are commonly used for dynamic control and positioning of industrial robots. Results of this study suggested that rotary encoder signal can also be used to monitor the efficiency of industrial robot systems effectively after proper processing. A novel strategy using singular spectrum analysis (SSA) integrated with hierarchical hyper-Laplacian prior prototype (HHLP) is proposed in this study for defect detection in industrial robots. Sparsity-assisted techniques are efficient flaw-based extraction techniques that have been extensively investigated in recent years. However, the selection of an appropriate sparse prior from the point of view of probability theory remains unverified. First, SSA enables the separation of complicated encoding signals to several interpretable components, including a trend, a set of cyclic oscillations, and residual oscillations (noise). Second, we describe HHLP by maximizing posterior probability of robot flaw diagnosis. HHLP is proposed to extract noise interference, cyclic pulse, and harmonic interference from the residual signal using the SSA technique. We infer that the hyper-Laplacian prior in the prototype may present a more efficient prototype flaw than the Laplacian prior. In addition, HHLP incorporates physical characteristics necessary to distinguish harmonic intervention. This study primarily establishes a modern prototype that represents the former dispersed from the perspective of maximizing the probability of the latter. Meanwhile, generalized minimax-concave regularization inductive and kurtosis-based weighted sparse prototypes are compared and spectral kurtosis is used to confirm the efficacy of HHLP. Note to Practitioners—This study aims to solve the problem of industrial robot fault diagnosis during the operation process to avoid production delays. Rotary encoder sensor is attached to each joint to collect raw information and identify the robot position. Data from the rotary encoder sensor can also be used for the efficient health status assessment of the performance of the industrial robot system after proper processing. Therefore, a new approach using singular spectrum analysis combined with hierarchical hyper-Laplacian pre-induced prototype is proposed in this study. The residual signal extracted using the singular spectrum analysis method for processing in a hierarchical hyper-Laplacian pre-induced prototype is used to improve the weak fault feature. We describe a hierarchical hyper-Laplacian preprototype by maximizing the posterior probability of the flaw diagnosis. We introduce a hierarchical hyper-Laplacian prior that integrates physical characteristics to distinguish between harmonic interferences. The distribution of coefficients acquired through other dictionaries or transformations and selection of the optimal priority for the extraction of flaw characteristics will be the foci of future investigations. [ABSTRACT FROM AUTHOR]

For nearly a decade, quality-related fault detection algorithms have been widely used in industrial systems. However, the majority of these detection strategies rely on static assumptions of the operating environment. In this paper, taking the time series of variables into consideration, a dynamic kernel entropy component regression (DKECR) framework is proposed to address the instability of quality-related fault detection due to the existing dynamic characteristics. Compared with the typical kernel entropy component analysis method, the proposed method constructs the relationship between process states and quality states to further interpret the direct effect on the product taken by the fault. In the proposed approach, process measurements are converted to a lower-dimensional subspace with a specific angular structure that is more comprehensive than traditional subspace approaches. In addition, the angular statistics and their relevant thresholds are exploited to enhance the quality-related fault detection performance. Finally, the proposed method will be compared with three methods by means of a numerical example and two industrial scenarios to demonstrate its practicality and effectiveness. Note to Practitioners—This paper studies a quality-related fault detection problem for the dynamic nonlinear industrial system. Controlling and measuring the quality state is challenging for the high-level monitoring system of the manufacturing process due to the nonlinear dynamic feature in states. This paper proposes a new data-driven method based on the kernel entropy component analysis method to assess the correlation between the quality and fault in the industrial system, reducing unnecessary overhaul and maintenance. Based on the autoregressive moving average exogenous algorithm, the proposed method captures the dynamic interaction between the process states to decrease false alarms. In the experimental section, the DKECR method outperforms the compared approaches, which can provide stable fault detection results. Additionally, the unique angle structure of the proposed method can supply more information for engineers’ monitoring needs. [ABSTRACT FROM AUTHOR]