Search

For the safety and reliability of the system, Remaining Useful Life (RUL) prediction is considered in many industries. The traditional machine learning techniques must provide more feature representation and adaptive feature extraction. Deep learning techniques like Long Short-Term Memory (LSTM) achieved an excellent performance for RUL prediction. However, the LSTM network mainly relies on the past few data, which may only capture some contextual information. This paper proposes a hybrid combination of Convolution Neural Network (CNN) and LSTM (CNN+LSTM) to solve this problem. The proposed hybrid model predicts how long a machine can operate without breaking down. In the proposed work, 1D horizontal and vertical signals of the mechanical bearing are first converted to 2D images using Continuous Wavelet Transform (CWT). These 2D images are applied to CNN for key feature extraction. Ultimately, these key features are applied to the LSTM deep neural network for predicting the RUL of a mechanical bearing. A PRONOSTIA data is utilized to demonstrate the performance of the proposed model and compare the proposed model with other state-of-the-art methods. Experimental results show that our proposed CNN+LSTM-based hybrid model achieved higher accuracy (98%) with better robustness than existing methods. [ABSTRACT FROM AUTHOR]

Accurate prediction of the engine's remaining useful life (RUL) is essential to ensure the safe operation of the aircraft because. However, traditional deep‐learning based methods for RUL prediction has been limited by interpretability and adjustment for hyperparameters in practical applications due to the intricate potential relations during the degradation process. To address these dilemmas, an improved multi‐strategy tuna swarm optimization‐assisted graph convolutional neural network (IMTSO‐GCN) is developed to achieve RUL prediction in this work. Specifically, mutual information is used to describe potential relationships among measured parameters so that they could be utilized in building edges for these parameters. Besides, considering that not all relational nodes will positively affect the RUL prediction and the inherent hyperparameters of the GCN are high‐dimensional. Inspired by “No Free Lunch (NFL)”, IMTSO is proposed to reduce the optimization cost of hyperparameters, in which cycle chaotic mapping is employed to achieve initialization of the population for improving the uniformity of the initial population distribution. Besides, a novel adaptive approach is proposed to enhance the exploration and exploitation of tuna swarm optimization (TSO). The CMAPSS dataset was used to validate the effectiveness and advancedness of IMTSO‐GCN, and the experimental results show that the R2 of the IMTSO‐GCN is greater than 0.99, RMSE is less than 3, the Score error is within 1. [ABSTRACT FROM AUTHOR]

The degradation state of a bearing can be monitored effectively by using a wear indicator (WI). A WI curve having smoothness and monotonicity can lay a good foundation for predicting the remaining useful life of the bearing. Most traditional models for bearing WI construction, such as time–frequency indicators and signal decomposition, are complicated; for example, some WI construction models need several models to select from, and their fusion depends on the manual experience of engineers. For example, single and mixed traditional time–frequency indicators, such as the root mean square (RMS), Kurtosis, multiple time–frequency domain fusion. However, the mentioned-above time–frequency domain indicators are difficult to adaptively reflect the operating status of the equipment when the operating conditions of the mechanical system change. Some signal decomposition models are combined with other models and rely on manual experience to extract WI, such as the selection of effective intrinsic mode function components function, parameter setting of empirical mode decomposition and ensemble empirical mode decomposition model, etc. Deep learning models, such as stacked auto encoder (SAE) and convolution neural network, have been widely used in bearing health monitoring and WI construction, because its powerful learning and feature extraction capabilities of multiple hidden layer structures. But these deep learning models are designed to use output labels. Particularly when the data volume is large, it requires manpower, material resources, and experienced engineers to label the data, or it is difficult to label and distinguish the categories of data samples. Therefore, to solve these problems and eliminate the need for manual labor, such as labeling data and selecting models for fusion, we propose using SAE without an output label layer to extract WI from original signals directly. However, an extracted WI curve without good monotonicity (Mon) will result in a poor remaining useful life prediction accuracy. To improve the monotonicity of the extracted WI and reduce the complexity of the WI construction model, we propose an unsupervised enhanced SAE without an output layer, named SINSAE, by adding a sine function of an average value which is calculated form start time to current at each hidden layer to eliminate concussion. Moreover, to demonstrate that our proposed model is better than other models, such as the RMS, Kurtosis, multiple time–frequency domain fusion, SAE, SAE without an output layer, and signal decomposition models, the Mon indicator in this study is used to compare the monotonicity of the extracted WI. Lastly, the results of our experiments using different bearing datasets and various working conditions show that the smoothness and monotonicity of the WI curve extracted by the SINSAE is better than that of other models. Moreover, compared to the traditional commonly used single and multiple time–frequency domain indicators, supervised deep learning and basic unsupervised deep models, the unsupervised SINSAE model can increase the Mon indicators from [0.1, 0.8], [0.02, 0.1], [0.1, 0.8] to above 0.9, respectively. [ABSTRACT FROM AUTHOR]

Bearing is the key component to determine the health of machinery, and it is of great significance to monitor its working status in real time and predict its remaining useful life. In recent years, the RUL prediction method based on deep learning has been widely used and achieved good prediction results. Here, a bearing life prediction method based on convolution neural network (CNN), long short term memory (LSTM) and attention mechanism (AM) is proposed. First of all, the time domain and frequency domain features of the original vibration signals of rolling bearings are extracted, and the extracted feature set is normalized as the input of CNN. The main function of CNN is to extract spatial features and reduce the dimension of the data. Then, using LSTM to extract the information that may be ignored by CNN, the feature information extracted by CNN-LSTM is input to the attention mechanism for weighting, and the key information is screened. And then more accurately represent the degradation characteristics of the equipment, and finally get the bearing remaining life. The performance of the model is verified by two sets of public data sets, and the experimental results show that it is compared with the CNN-LSTM method. The root mean square error (RMSE) index based on CNN-LSTM-AM method is reduced by 14.6 % and 13.8 % respectively, and the score index is increased by 2.0 % and 2.4 % respectively. The results show that the proposed method has higher accuracy in bearing RUL prediction. [ABSTRACT FROM AUTHOR]

Monitoring the health of lithium batteries is a crucial undertaking in ensuring the safe and dependable functioning of electric vehicles. Data‐driven methods have been proved to be an effective method for identifying the complex degradation process of batteries. To augment the precision of predicting the remaining useful life (RUL), this paper introduces a pioneering architecture for a denoising autoencoder (DAE). This architecture integrates a stacked convolutional neural network with subsequent layers of bidirectional gated recurrent units within an encoder–decoder framework. The utilization of the DAE network is employed as a means to effectively capture and represent the intricate and nonlinear knowledge associated with degradation data acquired from measured sources. Simultaneously, the reconstruction loss is incorporated into the total loss to improve the accuracy and generalization of the prediction model. The efficacy of the proposed approach is substantiated through the utilization of data sets sourced from the NASA Ames Prognostics Data Repository. The comparative findings suggest that the proposed approach demonstrates an exceptional ability to achieve precise and robust estimation in predicting the RUL, surpassing other advanced methodologies. [ABSTRACT FROM AUTHOR]

To tackle the challenges of performing early fault warning and improving the prediction accuracy for the remaining useful life (RUL) of rolling bearings, this paper proposes a similarity health indicator and a predictive model of CG-conditional generative adversarial network (CGAN), which relies on a CGAN that combines one-dimensional convolutional neural network (CNN) with a bidirectional gate recurrent unit (Bi-GRU). This framework provides a comprehensive theoretical foundation for RUL prediction of rolling bearings. The similarity health indicator allows for early fault warning of rolling bearings without expert knowledge. Within the CGAN framework, the inclusion of constraints guides the generation of samples in a more targeted manner. Additionally, the proposed CG-CGAN model incorporates Bi-GRU to consider both forward and backward information, thus improving the precision of RUL forecasting. Firstly, the similarity indicator between the vibration signals of the rolling bearing over its full life span and the standard vibration signals (healthy status) is calculated. This indicator helps to determine the early deterioration points of the rolling bearings. Secondly, the feature matrix composed of traditional health indicators and similarity health indicator, is utilized to train and test the proposed CG-CGAN model for RUL prediction. Finally, to corroborate the efficacy of the proposed method, two sets of real experiment data of rolling bearing accelerated life from the Intelligent Maintenance Systems (IMS) are utilized. Experimental findings substantiate that the proposed similarity health indicator offers early fault alerts and precisely delineates the performance diminution of the rolling bearing. Furthermore, the put-forward CG-CGAN model achieves high-precision RUL prediction of rolling bearing. [ABSTRACT FROM AUTHOR]

In the realm of prognosticating the remaining useful life (RUL) of pivotal components, such as aircraft engines, a prevalent challenge persists where the available historical life data often proves insufficient. This insufficiency engenders obstacles such as impediments in performance degradation feature extraction, inadequacies in capturing temporal relationships comprehensively, and diminished predictive accuracy. To address this issue, a 1D CNN-GRU prediction model for few-shot conditions is proposed in this paper. In pursuit of more comprehensive data feature extraction and enhanced RUL prognostication precision, the Convolutional Neural Network (CNN) is selected for its capacity to discern high-dimensional features amid the intricate dynamics of the data. Concurrently, the Gated Recurrent Unit (GRU) network is leveraged for its robust capability in extracting temporal features inherent within the data. We combine the two to construct a CNN-GRU hybrid network. Moreover, the integration of data distribution alongside correlation and monotonicity indices is employed to winnow the input of multi-sensor monitoring parameters into the CNN-GRU network. Finally, the engine RULs are predicted by the trained model. In this paper, experiments are conducted on a sub-dataset of the National Aeronautics and Space Administration (NASA) C-MAPSS multi-constraint dataset to validate the effectiveness of the method. Experimental results have demonstrated that this method has high accuracy in RUL prediction tasks, which can powerfully demonstrate its effectiveness. [ABSTRACT FROM AUTHOR]

This document is a summary of a special issue of the journal Processes titled "Process Monitoring and Fault Diagnosis." The issue explores the application of data analytic techniques to enhance stable operation and safety in chemical processes and related industries. The collection of research papers covers various topics, including process fault detection, bearing fault diagnosis, remaining useful life prediction, and more. The papers introduce cutting-edge methodologies and demonstrate their reliability through validation. The issue aims to foster communication and the development of advanced process monitoring techniques. [Extracted from the article]

Accurate prediction of remaining useful life (RUL) plays an important role in maintaining the safe and stable operation of Lithium-ion battery management systems. Aiming at the problem of poor prediction stability of a single model, this paper combines the advantages of data-driven and model-based methods and proposes a RUL prediction method combining convolutional neural network (CNN), bi-directional long and short-term memory neural network (Bi-LSTM), SE attention mechanism (AM) and adaptive unscented Kalman filter (AUKF). First, three types of indirect features that are highly correlated with RUL decay are selected as inputs to the model to improve the accuracy of RUL prediction. Second, a CNN-BLSTM-AM network is used to further extract, select and fuse the indirect features to form predictive measurements of the identified degradation metrics. In addition, we introduce the AUKF model to increase the uncertainty representation of the RUL prediction. Finally, the method is validated on the NASA dataset and the CALCE dataset and compared with other methods. The experimental results show that the method is able to achieve an accurate estimation of RUL, a minimum RMSE of up to 0.0030, and a minimum MAE of up to 0.0024, which has high estimation accuracy and robustness. [ABSTRACT FROM AUTHOR]

As one of the key technologies in battery management system, accurate remaining useful life (RUL) prediction is critical to guarantee the reliability and safety for electrical equipment. However, the generalization and robustness of a single method are limited. A novel fusion data‐driven RUL prediction method CSSA‐ELM‐LSSVR based on charging‐discharging health features extraction is proposed in this paper, which fusions chaotic sparrow search algorithm (CSSA), extreme learning machine (ELM), and least squares support vector regression (LSSVR). First, four health indicators (HIs) are extracted from the charging‐discharging process, which can reflect the battery degradation phenomenon from multiple perspectives. Then, pearson correlation coefficient is used to numerically analyze the correlation between HIs and battery aging capacities. Second, the extracted HIs are used as the inputs for ELM and LSSVR to predict the degradation trend of battery, where CSSA is used for hyperparameters optimization in ELM. Finally, considering that CSSA‐ELM can capture the general trend of degradation curves, while LSSVR can trace the detail changes, a fusion framework based on CSSA‐ELM and LSSVR is proposed for RUL prediction. Two weighting schemes, namely precision‐based weighting (PW) and random forest regressor‐based weighting (RFRW) are put forward to fix the weights of CSSA‐ELM and LSSVR algorithms. Two publicly available datasets from National Aeronautics and Space Administration (NASA) and MIT are adopted to verify the feasibility and effectiveness of the proposed method. The results indicate that the proposed method with any weighting scheme has an overall superior prediction performance for different kinds of batteries compared with CSSA‐ELM, LSSVR, convolution neural network and long short term memory. Moreover, the RFRW scheme has better overall performance. Specifically, the maximum root mean square error of the predicted method is 2.5126%, the mean absolute percentage error is 12.9167%, the mean absolute error is 1.8376%, the predicted RUL errors are within one cycle, and the determination coefficient R2$R^2$ is above 0.97. [ABSTRACT FROM AUTHOR]

Domain adaptation is a transfer learning method that is widely applied for remaining useful life (RUL) prediction under different operating conditions. However, current RUL prediction methods based on domain adaptation only consider minimizing degradation feature differences, while ignoring the correlation between features and labels, which may result in significant errors in the mapping relationship between the two learned by the model, and thus reduce the accuracy of prediction. To address this issue, this paper proposes an unsupervised subdomain adversarial network (USDAN) for RUL estimation under various conditions. On the basis of traditional domain adversarial adaptation networks, the network uses temporal convolutional networks to construct the feature extractor to learn the long‐term dependencies between degradation data, and a multilinear conditioning scheme is designed to combine the features and subdomain labels as input features to the domain discriminator. Finally, with backpropagation and gradient reversal, the feature extractor is prompted to generate cross‐domain invariant features that are correlated with the labels, improving the prediction accuracy and enhancing the transferability of the network. In the experimental section, the public turbofan engine degradation dataset is used to validate the effectiveness of the network, and the comparison with other approaches demonstrates its advantages. [ABSTRACT FROM AUTHOR]

The internal mechanisms of dental air turbine handpieces (DATHs) have become increasingly intricate over time. To enhance the operational reliability of dental procedures and guarantee patient safety, this study formulated temporal convolution network (TCN) prediction models with the functions of causality in time sequence, transmitting memory, learning, storing, and fast convergence for monitoring the health and diagnosing the rotor and collet failure of DATHs. A handpiece mimicking a dentist's hand load of 100 g was employed to repeatedly mill a glass porcelain block back and forth for cutting. An accelerometer was employed to capture vibration signals during free-running of unrestrained operation of the handpiece, aiming to discern the characteristic features of these vibrations. These data were then utilized to create a diagnostic health classification (DHC) for further developing a TCN, a 1D convolutional neural network (CNN), and long short-term memory (LSTM) prediction models. The three frameworks were used and compared for machine learning to establish DHC prediction models for the DATH. The experimental results indicate that, in terms of DHC predicted for the experimental dataset, the square categorical cross-entropy loss function error of the TCN framework was generally lower than that of the 1D CNN, which did not have a memory framework or the drawback of the vanishing gradient problem. In addition, the TCN framework outperformed the LSTM model, which required a longer history to provide sufficient diagnostic ability. Still, high accuracies were achieved both in the direction of feed-drive milling and in the gravity of the handpiece through vibration signals. In general, the failure classification prediction model could accurately predict the health and failure mode of the dental handpiece before the use of the DATH when an embedded sensor was available. Therefore, this model could prove to be a beneficial tool for predicting the deterioration patterns of real dental handpieces in their remaining useful life. [ABSTRACT FROM AUTHOR]

Due to the insufficient sensing field of the temporal convolutional networks (TCN), the key degradation information of the bearing is often ignored, which results in poor prediction of the remaitning useful life (RUL) of bearings. Moreover, the long-term dependence problem of long short-term memory (LSTM) may not be well solved with the increase of data volume and sequence length. Therefore a new prediction method based on Bidirectional temporal convolutional network and Long short-term memory (Bi-TCN-LSTM) was proposed. Firstly, the multi-sensor data was normalized and fused, and then the Bi-TCN-LSTM was used for data feature extraction and deep learning, in which the convolutional attention mechanism (CAM) was introduced into the TCN module, and the three gates of the LSTM were simplified into one gate. It effectively accelerated the learning speed of the prediction model and improved the accuracy of the prediction model. The IEEE PHM 2012 bearing dataset was used to carry out the RUL prediction experiments. The results show that compared with other advanced prediction models, the Bi-TCN-LSTM method has relatively lower prediction error and better performance. [ABSTRACT FROM AUTHOR]

In the context of predicting the remaining useful life (RUL) of rolling bearings, many models often encounter challenges in identifying the starting point of the degradation stage, and the accuracy of predictions is not high. Accordingly, this paper proposes a technique that utilizes particle swarm optimization (PSO) in combination with the fusing of a one-dimensional convolutional neural network (CNN) and a multihead self-attention (MHSA) bidirectional long short-term memory (BiLSTM) network called PSO-CNN-BiLSTM-MHSA. Initially, the original signals undergo correlation signal processing to calculate the features, such as standard deviation, variance, and kurtosis, to help identify the beginning location of the rolling bearing degradation stage. A new dataset is constructed with similar degradation trend features. Subsequently, the particle swarm optimization (PSO) algorithm is employed to find the optimal values of important hyperparameters in the model. Then, a convolutional neural network (CNN) is utilized to extract the deterioration features of rolling bearings in order to predict their remaining lifespan. The degradation features are inputted into the BiLSTM-MHSA network to facilitate the learning process and estimate the remaining lifespan of rolling bearings. Finally, the degradation features are converted to the remaining usable life (RUL) via the fully connected layer. The XJTU-SY rolling bearing accelerated life experimental dataset was used to verify the effectiveness of the proposed method by k-fold cross-validation. After comparing our model to the CNN-LSTM network model and other models, we found that our model can achieve reductions in mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) of 9.27%, 6.76%, and 2.35%, respectively. Therefore, the experimental results demonstrate the model's accuracy in forecasting remaining lifetime and support its ability to forecast breakdowns. [ABSTRACT FROM AUTHOR]

Ensuring precise prediction of the remaining useful life (RUL) for bearings in rolling machinery is crucial for preventing sudden machine failures and optimizing equipment maintenance strategies. Since the significant interference encountered in real industrial environments and the high complexity of the machining process, accurate and robust RUL prediction of rolling bearings is of tremendous research importance. Hence, a novel RUL prediction model called CNN-VAE-MBiLSTM is proposed in this paper by integrating advantages of convolutional neural network (CNN), variational autoencoder (VAE), and multiple bi-directional long short-term memory (MBiLSTM). The proposed approach includes a CNN-VAE model and a MBiLSTM model. The CNN-VAE model performs well for automatically extracting low-dimensional features from time–frequency spectrum of multi-axis signals, which simplifies the construction of features and minimizes the subjective bias of designers. Based on these features, the MBiLSTM model achieves a commendable performance in the prediction of RUL for bearings, which independently captures sequential characteristics of features in each axis and further obtains differences among multi-axis features. The performance of the proposed approach is validated through an industrial case, and the result indicates that it exhibits a higher accuracy and a better anti-noise capacity in RUL predictions than comparable methods. [ABSTRACT FROM AUTHOR]

A single type of sensor is susceptible to interference and limited degradation information can be extracted. Therefore, a multi-information fusion-based bearing remaining useful life prediction method using the dual-channel convolutional neural network (DCCNN) and the gated recurrent unit (GRU) is proposed. Firstly, vibration sensors are utilized as a basis for signal collection, while acoustic emission sensors are introduced as a complement to obtain more comprehensive degradation information. Secondly, the time domain, frequency domain and time-frequency domain features of the vibration signal and acoustic emission signal were extracted respectively to construct a comprehensive bearing degradation feature set. Third, multiple evaluation indicators are used to comprehensively evaluate the degradation features, and effective degradation features that are highly related to bearing degradation are selected for feature fusion. Subsequently, the DCCNN-GRU model was established, which captures and comprehensively utilizes different degradation feature information in each channel through the DCCNN network structure, and employs GRU to process the time relationships and dependencies in sequence data to solves the vanishing gradient problem. Finally, an experimental bearing test bench was constructed to collect data, and this data was used to experimentally validated the model and compared with other methods to demonstrate its feasibility and effectiveness. [ABSTRACT FROM AUTHOR]

The remaining useful life (RUL) prediction of RF circuits is an important tool for circuit reliability. Data-driven-based approaches do not require knowledge of the failure mechanism and reduce the dependence on knowledge of complex circuits, and thus can effectively realize RUL prediction. This manuscript proposes a novel RUL prediction method based on a gated recurrent unit–convolutional neural network (GRU-CNN). Firstly, the data are normalized to improve the efficiency of the algorithm; secondly, the degradation of the circuit is evaluated using the hybrid health score based on the Euclidean and Manhattan distances; then, the life cycle of the RF circuits is segmented based on the hybrid health scores; and finally, an RUL prediction is carried out for the circuits at each stage using the GRU-CNN model. The results show that the RMSE of the GRU-CNN model in the normal operation stage is only 3/5 of that of the GRU and CNN models, while the prediction uncertainty is minimized. [ABSTRACT FROM AUTHOR]

In industry, forecast prediction and health management (PHM) is used to improve system reliability and efficiency. In PHM, remaining useful life (RUL) prediction plays a key role in preventing machine failures and reducing operating costs, especially for reliability requirements such as critical components in aviation as well as for costly equipment. With the development of deep learning techniques, many RUL prediction methods employ convolutional neural network (CNN) and long short-term memory (LSTM) networks and demonstrate superior performance. In this paper, a novel two-stream network based on a bidirectional long short-term memory neural network (BiLSTM) is proposed to establish a two-stage residual life prediction model for mechanical devices using CNN as the feature extractor and BiLSTM as the timing processor, and finally, a particle swarm optimization (PSO) algorithm is used to adjust and optimize the network structural parameters for the initial data. Under the condition of lack of professional knowledge, the adaptive extraction of the features of the data accumulated by the enterprise and the effective processing of a large amount of timing data are achieved. Comparing the prediction results with other models through examples, it shows that the model established in this paper significantly improves the accuracy and efficiency of equipment remaining life prediction. [ABSTRACT FROM AUTHOR]

Lithium-ion batteries are currently widely employed in a variety of applications. Precise estimation of the remaining useful life (RUL) of lithium-ion batteries holds significant function in intelligent battery management systems (BMS). Therefore, in order to increase the fidelity and stabilization of predicting the RUL of lithium-ion batteries, in this paper, an innovative strategy for RUL prediction is proposed by integrating a one-dimensional convolutional neural network (1D CNN) and a bilayer long short-term memory (BLSTM) neural network. Feature extraction is carried out through the input capacity data of the model using 1D CNN, and these deep features are used as the input of the BLSTM. The memory function of the BLSTM is applied to retain key information in the database and to better understand the coupling relationship among consecutive time series data along the time axis, thereby effectively predicting the RUL trends of lithium-ion batteries. Two different types of lithium-ion battery datasets from NASA and CALCE were used to verify the effectiveness of the proposed method. The results show that the proposed method achieves higher prediction accuracy, demonstrates stronger generalization capabilities, and effectively reduces prediction errors compared to other methods. [ABSTRACT FROM AUTHOR]

Predicting the remaining useful life (RUL) of lithium-ion batteries is crucial for enhancing their reliability and safety. Addressing the issue of inaccurate RUL predictions caused by the nonlinear decay resulting from capacity regeneration, this paper proposes an indirect lithium-ion battery RUL prediction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and convolutional neural network (CNN)–bidirectional gated recurrent unit (BiGRU). The method extracts Health Indicators (HI) from the battery-charging stage and employs CEEMDAN to decompose HI into several components. These components are then input into a component prediction model for forecasting. Finally, the predicted component results are fused and input into a capacity prediction model to achieve indirect RUL prediction. Validation is conducted using the lithium-ion battery dataset provided by NASA. The results indicate that, under prediction starting points (STs) of 80 and 100, the maximum average absolute errors do not exceed 0.0096 and 0.0081, and the maximum root mean square errors do not exceed 0.0196 and 0.0115, demonstrating high precision and reliability. [ABSTRACT FROM AUTHOR]

The healthy operation of aircraft engines is crucial for flight safety, and accurate Remaining Useful Life prediction is one of the core technologies involved in aircraft engine prognosis and health management. In recent years, deep learning-based predictive methods within data-driven approaches have shown promising performance. However, for engines experiencing a single fault, such as a High-Pressure Compressor fault, existing deep learning-based predictive methods often face accuracy challenges due to the coupling relationship between different fault modes in the training dataset that includes a mixture of multiple fault modes. In this paper, we propose the FC-AMSLSTM method, a novel approach for Remaining Useful Life prediction specifically targeting High-Pressure Compressor degradation faults. The proposed method effectively addresses the limitations of previous approaches by fault classification and decoupling fault modes from multiple operating conditions using a decline index. Then, attention mechanisms and multi-scale convolutional neural networks are employed to extract spatiotemporal features. The long short-term memory network is then utilized to model RUL estimation. The experiments are conducted using the Commercial Modular Aero-Propulsion System Simulation dataset provided by NASA. The results demonstrate that compared to other prediction models, the FC-AMSLSTM method effectively reduces RUL prediction error for HPC degradation faults under multiple operating conditions. [ABSTRACT FROM AUTHOR]

Accurate prediction of remaining useful life (RUL) plays a significant role in ensuring the safe flight of aircraft. With the recent rapid development of deep learning, there has been a growing trend towards more precise RUL prediction. However, while many current deep learning methods are capable of extracting spatial features—those along the sensor dimension—through convolutional kernels or fully connected layers, their extraction capacity is often limited due to the small scale of kernels and the high uncertainty associated with linear weights. Graph neural networks (GNNs), emerging as effective approaches for processing graph-structured data, explicitly consider the relationships between sensors. This is akin to imposing a constraint on the training process, thereby allowing the learned results to better approximate real-world situations. In order to address the challenge of GNNs in extracting temporal features, we augment our proposed framework for RUL prediction with a Transformer encoder, resulting in the adaptive graph convolutional transformer encoder (AGCTE). A case study using the C-MAPSS dataset is conducted to validate the effectiveness of our proposed model. [ABSTRACT FROM AUTHOR]

Transfer learning and domain adaptation (DA) methods have been utilized in bearing prognostic and health management, but most of the current DA methods do not take into account the feature scale change of degraded features when aligning the feature distribution, and these methods are more suitable for the classification problem, which is more robust to the feature scale change. However, they perform poorly in regression problems. In addition, most of the remaining useful life (RUL) prediction methods require preprocessing such as statistical feature extraction on the signal, which makes the prediction process complicated. To solve the above problems, a DA method based on the representation subspace distance (RSD) is proposed for predicting the bearing RUL under different operating conditions. First, the proposed convolutional neural network (CNN) self-attention (SA) long short term memory network model is utilized to extract the deep features from the original signal, which overcomes the limitations of the CNN in extracting time series. Then, the RSD in the Riemannian geometry of the Grassmann manifold is proposed as a domain transfer loss to learn domain invariant features. The modified method can align the feature distribution of the source domain and the target domain without changing the feature scale. At the same time, the bases mismatch penalization is introduced to avoid destroying the semantic information of the features in the process of domain alignment. Finally, the effectiveness of the proposed method is verified by experiments on four types of transfer tasks, and its superiority is also demonstrated by comparison with other advanced methods. [ABSTRACT FROM AUTHOR]

This document is an editorial for a special issue of the Logic Journal of the IGPL, featuring ten papers presented at the 16th International Conference on Hybrid Artificial Intelligent Systems (HAIS) in Bilbao, Spain. The papers cover a range of topics, including algorithms for solving the Generalized Traveling Salesman Problem, content-based identification of authorship for short texts, evaluation of aircraft engine monitoring data, optimized Convolutional Neural Networks for detecting burrs in images, and methodologies for analyzing the evolution of Nitrogen Dioxide and developing a hybrid model for Lithium Iron Phosphate power cells. The guest editors express their gratitude to the contributors and hope that readers find the special issue useful. [Extracted from the article]

Aeroengines use numerous sensors to detect equipment health and ensure proper operation. Currently, filtering useful sensor data and removing useless data is challenging in predicting the remaining useful life (RUL) of an aeroengine using deep learning. To reduce computational costs and improve prediction performance, we use random forest to evaluate the feature importance of sensor data. Based on the size of the feature corresponding to the Gini index, we select the appropriate sensor. This helps us to determine which sensor to use and ensures that the computational resources are not wasted on unnecessary sensors. Considering that the RUL of equipment changes in a progressively more complex manner as the equipment is used over time, we propose an improved squeeze and excitation block (SSE) and combine it with a convolutional neural network (CNN). By enhancing the feature selection ability of CNN through segmented squeeze and excitation block, the model can focus on important information within features to effectively improve prediction performance. We compared our experiments with other RUL experiments on the CMAPSS aeroengine dataset and then conducted ablation experiments to verify the critical role of the methods we used. [ABSTRACT FROM AUTHOR]

For the remaining useful life (RUL) prediction of rolling bearing under strong background noise, it is hard to get accurate results based on the non-stationary vibration signals because of complex degradation characteristics and difficult extraction of key features. The framework of RUL prediction for rolling bearing is established by integrating multi-domain mixed features and temporal convolutional network (TCN). The variational mode decomposition method based on the dung beetle optimization algorithm is developed to reduce signal noise by determining the optimal parameters adaptively. To construct a health indicator of rolling bearing effectively, an isometric feature mapping algorithm is introduced to reduce the dimensionality of multi-domain mixed features, integrating time-domain, frequency-domain, and entropy features of vibration signals under non-stationary and nonlinear conditions. By considering the advantages of a multi-head attention mechanism (MA) and bidirectional gated recurrent unit (BiGRU), a TCN-based multi-head attention and bidirectional gate (TCNMABG) is developed to predict the RUL of rolling bearing accurately, whose detailed implementation process of TCNMABG is described based on XJTU-SY dataset. To verify the performance of TCNMABG, the FEMTO-ST dataset is introduced to perform the numerical experiments, and the results show that prediction error is reduced by 65.96% on average. [ABSTRACT FROM AUTHOR]

Introduction: Deep learning has demonstrated exceptional prowess in estimating battery capacity. However, its effectiveness is often compromised by performance degradation under a consequence of varying operational conditions and diverse charging/discharging protocols. Methods: To tackle this issue, we introduce the Knowledge Query Domain Mixing-up Network (KQDMN), a domain adaptation-based solution adept at leveraging both domain-specific and invariant knowledge. This innovation enriches the informational content of domain features by segregating the functions of feature extraction and domain alignment, enhancing the efficacy of KQDMN in utilizing diverse knowledge types. Moreover, to identify timedeteriorating features in battery time series data, we employ convolutional operations. These operations are pivotal in extracting multi-scale features from the battery's characteristic curves. Inspired by the Transformer model, we have developed a set of knowledge queries that integrate these multi-scale features seamlessly, thereby enabling extensive global feature extraction. To ensure the retention of domain-specific information, we have instituted two independent feature extraction pathways. Pursuing domain-invariant knowledge, this study introduces cross-attention as a mechanism to connect two domain spaces, effectively diminishing the disparity between source and target distributions. Results and Discussion: This approach is crucial for accurately estimating capacity in batteries with diverse performance characteristics. The practicality and robustness of the proposed method are validated using the MIT battery aging dataset, yielding highly satisfactory outcomes. The Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2) for our capacity estimation process are 0.19%, 0.23%, and 0.997, respectively, highlighting the precision and reliability of our approach. [ABSTRACT FROM AUTHOR]

To further improve the remaining useful life forecasting accuracy of fuel cells using classic deep learning models, a convolutional neural network combining bidirectional long and short-term memory networks (BiLSTM) and attention mechanism (AT) is optimized with the enhanced whale optimization algorithm (EWOA). Singular spectrum analysis preprocesses the attenuation data to eliminate noise and enhance its effective information; the CNN–BiLSTM model extracts spatiotemporal features and learns historical and future information; AT further explores the spatiotemporal correlation; and EWOA optimizes its hyperparameters to reduce human intervention error. Results demonstrate that, compared with long and short-term memory, CNN–LSTM, CNN–BiLSTM, CNN–BiLSTM–AT, and CNN–BiLSTM–AT optimized with other algorithms, the CNN–BiLSTM–AT model optimized with EWOA achieves lower root mean square error, mean absolute error, mean absolute percentage error, and relative errors of 0.1951%–0.2059%, 0.1267%–0.1538%, 0.0319%–0.0366%, and 0.026%–0.036%, respectively, with different training data. Importantly, the proposed model still maintains good prediction robustness with over 40% of the missing data. [ABSTRACT FROM AUTHOR]

In order to realize the remaining useful life (RUL) prediction of mechanical equipment under different operating conditions, a domain adaption residual separable convolutional neural network (DRSCN) model is proposed in this paper. In the DRSCN model, instead of the traditional convolutional layer, a residual separable convolutional module is developed to improve the feature extraction ability of the model. Moreover, a multi-kernel maximum mean discrepancy metric function and an adversarial learning mechanism are embedded in the DRSCN model to enhance its ability to resist domain shifts, thus improving the cross-domain RUL prediction accuracy of the model. The effectiveness of the DRSCN model is verified on an aircraft engine dataset. The experimental results show that the proposed model can realize high-accuracy RUL prediction. [Display omitted] • A DRSCN model is proposed for cross-domain RUL prediction. • MMD is embedded in the DRSCN model to enhance its generalization performance. • Adversarial learning mechanism is adopted to realize domain adaption of the model. • A residual separable convolution module is proposed to replace convolutional layer. [ABSTRACT FROM AUTHOR]

The accurate predictions of remaining useful life (RUL) have become a key and extremely challenging problem. Due to the limitations of the classical convolutional neural network and recurrent neural network structure, the attention mechanism has been introduced to improve feature representation of the long-term bearing degradation data. Transformer network based on attention mechanism is successfully applied in many fields and recognized as an excellent creation for deep learning models. In this paper, a novel lightweight mobile vision transformer (MobileViT) architecture based on deep networks is proposed for the RUL predictions. This new network is named prognostics separable vision Transformer (ProgSViT), which combines the separable convolution and MobileViT. In ProgSViT network, the separable convolutions are first constructed for extracting local feature from the input vibration signal, and the new vision transformer architecture is proposed to learn the global feature representations. In improved MobileViT model, the loss function is optimized, and a new training strategy is provided. Finally, the obtained features are input to the global average pool layers and the full connection layers to perform RUL estimation. Experiment results present the proposed ProgSViT network surpasses the other models in RUL predicting, which possesses higher precision and computational efficiency. [ABSTRACT FROM AUTHOR]

Predicting the remaining useful life (RUL) of the aircraft engine based on historical data plays a pivotal role in formulating maintenance strategies and mitigating the risk of critical failures. None the less, attaining precise RUL predictions often encounters challenges due to the scarcity of historical condition monitoring data. This paper introduces a multiscale deep transfer learning framework via integrating domain adaptation principles. The framework encompasses three integral components: a feature extraction module, an encoding module, and an RUL prediction module. During pre-training phase, the framework leverages a multiscale convolutional neural network to extract distinctive features from data across varying scales. The ensuing parameter transfer adopts a domain adaptation strategy centered around maximum mean discrepancy. This method efficiently facilitates the acquisition of domain-invariant features from the source and target domains. The refined domain adaptation Transformer-based multiscale convolutional neural network model exhibits enhanced suitability for predicting RUL in the target domain under the condition of limited samples. Experiments on the C-MAPSS dataset have shown that the proposed method significantly outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Excessive and untimely maintenance prompts economic losses and unnecessary workload. Therefore, predictive maintenance models are developed to estimate the right time for maintenance. In this study, predictive models that estimate the remaining useful life of turbofan engines have been developed using deep learning algorithms on NASA's turbofan engine degradation simulation dataset. Before equipment failure, the proposed model presents an estimated timeline for maintenance. The experimental studies demonstrated that the stacking ensemble learning and the convolutional neural network (CNN) methods are superior to the other investigated methods. While the convolution neural network (CNN) method was superior to the other investigated methods with an accuracy of 93.93%, the stacking ensemble learning method provided the best result with an accuracy of 95.72%. [ABSTRACT FROM AUTHOR]

In recent years, predictive maintenance tasks, especially for bearings, have become increasingly important. Solutions for these use cases concentrate on the classification of faults and the estimation of the Remaining Useful Life (RUL). As of today, these solutions suffer from a lack of training samples. In addition, these solutions often require high-frequency accelerometers, incurring significant costs. To overcome these challenges, this research proposes a combined classification and RUL estimation solution based on a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network. This solution relies on a hybrid feature extraction approach, making it especially appropriate for low-cost accelerometers with low sampling frequencies. In addition, it uses transfer learning to be suitable for applications with only a few training samples. [ABSTRACT FROM AUTHOR]

Predictive maintenance (PdM) has tremendous potential for reducing total operational costs and turnaround time in industrial manufacturing and maintenance services. In recent years, many deep learning based prediction methods have emerged and advanced the state-of-the-art in the PdM area. This paper proposes a holistic tool wear prediction framework that orchestrates convolutional neural networks for multisensor sequence learning, synthetic features to augment small training datasets, and a meticulously designed training regulation strategy. The effectiveness of the proposed framework is evaluated with computer numerical control (CNC) machine milling datasets available in the public domain. The results show that our method, sCNN-Ex, outperforms state-of-the-art tool wear prediction methods. sCNN-Ex reduces the prediction mean absolute percentage error from existing 32% to 21.7% for steel cases in the NASA milling dataset. [ABSTRACT FROM AUTHOR]

Accurate prediction of remaining useful life (RUL) can ensure the safety and reliability of power batteries during operation, reduce the failure rate and operating costs, and enhance user experience. However, battery degradation is a complex, nonlinear dynamic process that is difficult to fully comprehend and predicting RUL remains a significant challenge. To address this issue, the hybrid data-driven prediction model PCA-CNN-BiLSTM was proposed in this paper, which combines principal component analysis (PCA), convolutional neural network (CNN), and bi-directional long short-term memory (Bi-LSTM) network. PCA was applied to downscale and whiten the health factor (HF) to maximize the extraction of important features of lifespan decay, while reducing the correlation between features. The convolution kernel of the CNN was used to explore the local region feature information of the input information and search for the common patterns among the neighboring data. Additionally, the model parameters and computational efforts were reduced through pooling. Finally, battery RUL prediction was achieved using Bi-LSTM, which has the advantages of effectively enhancing model accuracy and reducing the risk of over-fitting by taking into account both past and future data. The performance of the proposed model was evaluated utilizing NASA and CALCE's battery datasets, and the results suggest that it exhibits a high level of accuracy across various datasets. Compared to other methods, the PCA-CNN-BiLSTM method has the best performance indicators for predicting battery RUL, including RMSE, MAE, MAPE, RUL e and DOL. This indicates that the proposed model has better fitting performance, accuracy, robustness, and generalization ability. [Display omitted] • Propose a novel battery RUL prediction method based on hybrid data-driven model. • Nineteen health factors were extracted, including segmented discharge time and temperature. • The effectiveness of the PCA-CNN-BiLSTM was verified on multiple public datasets. [ABSTRACT FROM AUTHOR]

The bearing is one of the most important components of rotating machinery. Predicting the remaining useful life (RUL) of bearings is of great importance to avoid unforeseen failures in the mechanical system and reduce the maintenance cost of the system. In conventional RUL prediction methods, the influence of noise and timing information on the prediction accuracy is often ignored. To address this problem, a method for RUL prediction of bearings based on data enrichment and adaptive temporal convolutional networks (TCN) is proposed in this paper. First, the sample entropy is used to optimize the singular spectrum decomposition (SSD) and combine with the correlation coefficient, and the data enhancement method based on the enhanced SSD and correlation coefficient (ISSD–CC) is proposed to reduce the signal noise; then, the time domain information is extracted to construct the feature vector. Finally, the Nadam optimizer and adaptive parametric rectified linear unit activation function (APRelu) are introduced, and an improved temporal convolutional network (ITCN) is proposed to improve the adaptive learning ability of TCN for time and time–domain information. IEEE PHM2012 dataset and the XJTU-SY dataset are used to verify the feasibility of the proposed method. The experimental results show that the accuracy of ISSD correlation coefficient and ITCN prediction method in RUL prediction of bearings is better than other comparison methods. [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) prediction is a key aspect of health condition monitoring, which can reduce maintenance costs and improve system operational efficiency. The most existing approaches only extract temporal features or spatial features, and ignore raw mapping features in RUL prediction. However, these different features are highly complementary and relevant for RUL prediction. Different from these approaches, we propose a novel feature-fusion-based end-to-end approach for RUL prediction in this paper, which combines spatiotemporal features and raw mapping features. To begin with, the time attention mechanism is used for the input to weight different time steps. Then convolutional neural networks (CNNs) are used for the weighted input to extract spatial feature maps. Between the CNNs, channel attention and spatial attention mechanisms are applied to the feature maps to learn the importance of channel and spatial distribution. Meanwhile, a bidirectional gated recurrent unit is adopted to capture temporal dependency features. In addition, the raw mapping features are obtained from the input through a fully connected layer to provide additional information. Finally, the three types of obtained features are fused for the final RUL prediction through fully connected networks. Extensive experiments are carried out on the C-MAPSS engine dataset. The results show that the proposed approach outperforms the current deep learning approaches. [ABSTRACT FROM AUTHOR]

Predicting the remaining useful life (RUL) is a pivotal step in ensuring the reliability of lithium-ion batteries (LIBs). In order to enhance the precision and stability of battery RUL prediction, this study introduces an innovative hybrid deep learning model that seamlessly integrates convolutional neural network (CNN) and gated recurrent unit (GRU) architectures. Our primary goal is to significantly improve the accuracy of RUL predictions for LIBs. Our model excels in its predictive capabilities by skillfully extracting intricate features from a diverse array of data sources, including voltage (V), current (I), temperature (T), and capacity. Within this novel architectural design, parallel CNN layers are meticulously crafted to process each input feature individually. This approach enables the extraction of highly pertinent information from multi-channel charging profiles. We subjected our model to rigorous evaluations across three distinct scenarios to validate its effectiveness. When compared to LSTM, GRU, and CNN-LSTM models, our CNN-GRU model showcases a remarkable reduction in root mean square error, mean square error, mean absolute error, and mean absolute percentage error. These results affirm the superior predictive capabilities of our CNN-GRU model, which effectively harnesses the strengths of both CNNs and GRU networks to achieve superior prediction accuracy. This study draws upon NASA data to underscore the outstanding predictive performance of the CNN-GRU model in estimating the RUL of LIBs. [ABSTRACT FROM AUTHOR]

Accurate remaining useful life (RUL) prediction is one of the most challenging problems in the prognostics of turbofan engines. Recently, RUL prediction methods for turbofan engines mainly involve data-driven models. Preprocessing the sensor data is essential for the performance of the prognostic models. Most studies on turbofan engines use piecewise linear (PwL) labeling, which starts with a constant initial RUL value in normal/healthy operating time. In this study, we designed a prognostic procedure that includes difference-based feature construction, change-point-detection-based PwL labeling, and a 1D-CNN-LSTM (one-dimensional–convolutional neural network–long short-term memory) hybrid neural network model for RUL prediction. The procedure was evaluated on the subset FD001 of the C-MAPSS dataset. The proposed procedure was compared with machine learning and deep learning models with and without the new difference feature. Also, the results were compared with the studies that used similar labeling approaches. Our analysis of the numerical results underscores the clear superiority of the proposed 1D-CNN-LSTM model with the difference feature in RUL prediction, with a score of 437.2 and an RMSE value of 16.1. This result illustrates the superior predictive capability of the 1D-CNN-LSTM model, which outperformed traditional machine learning methods and one of the earliest deep learning methods. These findings emphasize the superior predictive capability of the 1D-CNN-LSTM model and underline the potential of the feature engineering process for more accurate and robust RUL prediction in the context of turbofan engine prognostics. [ABSTRACT FROM AUTHOR]

The main goal of this work is to propose an efficient and accurate modern methodology to estimate the useful life of industrial assets used in oil and gas industry suffering from generalized corrosion. It merges the convolutional neural networks, extreme value theory, and bootstrap methods to handle the available corrosion data obtained through nondestructive inspection techniques for structural integrity assessments. It is due to the high cost of inspection techniques actually used in many industries to generate a reliable large amount of data to be analyzed by traditional statistical tools and technical factors, such as the inaccessibility of certain zones of the assets. First, the most appropriate extreme value distribution is determined to best fit the available inspection data, aiming to generate sufficient information for the training and testing processes of a one-dimensional convolutional neural network model to improve the accuracy of the useful life estimation. To demonstrate the main features and capabilities of the methodology, the dataset of AISI 1018 steel tubes of a heat exchanger used in a Brazilian refinery subjected to a general corrosion-type extreme process is retained herein. The results demonstrate that it is an interesting tool for inspection process to assist engineers and/or users in predictive maintenance phases to access the structural integrity of industrial assets subjected to extreme events such as general corrosion. [ABSTRACT FROM AUTHOR]

In recent years, lithium-ion batteries have gained significant attention due to their crucial role in various applications, such as electric vehicles and renewable energy storage. Accurate prediction of the remaining useful life (RUL) of these batteries is essential for optimizing their performance and ensuring reliable operation. In this paper, we propose a novel methodology for RUL prediction using an individual control chart (ICC) to identify and remove degraded data, a convolutional neural network (CNN) to smooth the noise of sensor data and long short-term memory (LSTM) networks to effectively capture both spatial and temporal dependencies within battery data, enabling accurate RUL estimation. We evaluate our proposed model using a comprehensive dataset, and experimental results demonstrate its superior performance compared to existing methods. Our findings highlight the potential of ICC-CNN-LSTM for RUL prediction in lithium-ion batteries and provide valuable insights for future research. [ABSTRACT FROM AUTHOR]

Fuzzy cognitive networks (FCNs) arose from traditional fuzzy cognitive maps (FCMs) to have the advantage of guaranteed convergence to equilibrium points, thus being more suitable than conventional FCMs for a variety of pattern recognition and system identification tasks. Moreover, recent developments led to FCNs with functional weights (FCNs-FW), as a significant FCNs enhancement in terms of storage requirements, efficiency and less human intervention requirements. In this paper we proceed further by introducing hybrid deep learning structures, interweaving FCNs-FW with well established deep neural network (DNN) representative structures and apply the new schemes on a variety of pattern recognition and time series prediction tasks. More specifically, after discussing general issues related to the construction of deep learning structures using FCNs-FW we present three hybrid models, which combine the FCN-FW with convolutional neural networks (CNNs), echo state networks (ESNs) and AutoEncoder (AE) schemes, respectively. The hybrid schemes are tested on diverse benchmark data sets and prove that FCN-FW based hybrid schemes perform equally well or better than state-of-the-art DNN-based schemes, paving thus the way for using cognitive networks to deep learning representative structures. [ABSTRACT FROM AUTHOR]

Accurately evaluating the remaining useful life (RUL) of aircraft engines is crucial for ensuring operational safety and reliability, and serves as a critical foundation for making informed maintenance decisions. In this paper, a novel prediction framework is proposed for forecasting the RUL of engines, which utilizes a dual-frequency enhanced attention network architecture built upon separable convolutional neural networks. First, the information volume criterion (IVC) index and information content threshold (CIT) equation are designed, which are applied to quantitatively quantify the degradation features of the sensor and remove redundant information. In addition, this paper introduces two trainable frequency-enhanced modules, namely the Fourier transform module (FMB-f) and the wavelet transform module (FMB-w), to incorporate physical rules information into the prediction framework, dynamically capture the global trend and local details of the degradation index, and further improve the prediction performance and robustness of the prediction model. Furthermore, the proposed efficient channel attention block generates a unique set of weights for each possible vector sample, which establishes the interdependence among different sensors, thereby augmenting the prediction stability and precision of the framework. The experimental demonstrate that the proposed RUL prediction framework can deliver accurate RUL predictions. • The IVC and CIT are used to quantify and eliminate degradation information. • A dual-frequency block(FEB-f and FEB-w) with trainable parameters is proposed. • FEB-w and FEB-f jointly trained with SDFEPN for dynamic coordination. • The integration of physical rules into the SDFEPN enhances the interpretability. [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) prediction is significant for reliability analysis and the reduction of maintenance costs for turbofan engine systems. However, most of the existing methods capture temporal or spatial features to predict RUL, which leads to the neglect of deep spatio-temporal correlation in the prediction data. In addition, there are usually noise interference and few labels in feature extraction, which causes difficulty in designing robust RUL prediction models. To address these problems, a denoised semi-supervised model based on fully convolutional denoising autoencoder, convolutional neural network, and long short-term memory network (FCDAE-CNN-LSTM) is proposed to predict RUL, where FCDAE is constructed to denoise the original data by parameter fine-tuning and CNN-LSTM is established based on parallel connection for RUL prognosis. The denoising and generalization capabilities of the RUL prediction model are enhanced by the combination of unsupervised denoising and supervised feature extraction in the case of few labeled training data. The superior features of the method lie in that FCDAE effectively captures globalized and localized features and CNN-LSTM captures multi-layer fused spatial–temporal correlations. The Root Mean Square Error (RMSE) and Score of the proposed method on C-MAPSS dataset are 12.01, 16.62, 11.84, 18.21, and 209.44, 1466.03, 205.07, 2338.93, respectively, which have demonstrated that our method achieves the state-of-the-art performance and outperforms other models. [ABSTRACT FROM AUTHOR]

Estimating the remaining useful life (RUL) of proton exchange membrane fuel cells (PEMFCs) is key to predicting and increasing their durability. This paper investigates six deep learning techniques – long short-term memory (LSTM) networks, gated recurrent units (GRU), 1-D convolutional neural network (CNN)-LSTMs, 1D–CNN–GRUs, 1D–CNN–Bidirectional-LSTMs, and 1D–CNN–Bidirectional-GRUs – for RUL and long-term degradation trend prediction for a five-cell PEMFC stack operated with and without current ripples. The hyperparameters of all models are optimized for minimum root-mean-square error (RMSE) of the stack voltage using tree-structured Parzen estimators (TPE) with hyperband pruning. The obtained prediction results are benchmarked using the coefficient of determination (R2), RMSE, and mean absolute percentage error (MAPE) in stack voltage predictions and relative error (RE) in RUL estimates. The comparative analysis for models trained on 50% datasets reveals that the best R2, RMSE, MAPE, and RE of 98.87E-2, 1.258E-3, 0.285E-1, and 0.0425E-1 are offered by the LSTM model for the stack without current ripples. Further, for the stack with current ripples, the best R2, RMSE, MAPE, and RE of 99.482E-2, 1.77E-3, 0.444E-1, and 0.089E-1 are exhibited by the 1D–CNN–Bidirectional-GRU model. The LSTM model also reveals excellent transfer learning performance on the stack with current ripples with the best R2, RMSE, MAPE, and RE of 98.91E-2, 2.455E-3, 0.362E-1, and 0.044E-1, respectively. [Display omitted] • Six deep learning models are developed for PEMFC RUL and degradation prediction. • Hyperparameters of each model are optimized using TPE for static and dynamic loading. • Static loading models exhibited excellent transfer learning performance. • All tuned models performed superior to recent reported approaches in RMSE. • LSTM and 1D–CNN–Bidirectional-GRU demonstrated best results trained on 50% data. [ABSTRACT FROM AUTHOR]

The performance of lithium-ion batteries declines rapidly over time, inducing anxiety in their usage. Ascertaining the capacity of these batteries is difficult to measure directly during online remaining useful life (RUL) prediction, and a single deep learning model falls short of accuracy and applicability in RUL predictive analysis. Hence, this study proposes a lithium-ion battery RUL indirect prediction model, fusing convolutional neural networks and bidirectional gated recurrent units (CNNBiGRU). The analysis of characteristic parameters of battery life status reveals the selection of pressure discharge time, average discharge voltage and average temperature as health factors of lithium-ion batteries. Following this, a CNN-BiGRU model for lithium-ion battery RUL indirect prediction is established, and the Tree-structured Parzen Estimator (TPE) adaptive hyperparameter optimization method is used for CNN-BiGRU model hyperparameter optimization. Overall, comparison experiments on single-model and other fusion models demonstrate our proposed model's superiority in the prediction of RUL in terms of stability and accuracy. [ABSTRACT FROM AUTHOR]

A good weight initialization is crucial to accelerate the convergence of the weights in a neural network. However, training a neural network is still time-consuming, despite recent advances in weight initialization approaches. In this paper, we propose a mathematical framework for the weight initialization in the last layer of a neural network. We first derive analytically a tight constraint on the weights that accelerates the convergence of the weights during the back-propagation algorithm. We then use linear regression and Lagrange multipliers to analytically derive the optimal initial weights and initial bias of the last layer, that minimize the initial training loss given the derived tight constraint. We also show that the restrictive assumption of traditional weight initialization algorithms that the expected value of the weights is zero is redundant for our approach. We first apply our proposed weight initialization approach to a Convolutional Neural Network that predicts the Remaining Useful Life of aircraft engines. The initial training and validation loss are relatively small, the weights do not get stuck in a local optimum, and the convergence of the weights is accelerated. We compare our approach with several benchmark strategies. Compared to the best performing state-of-the-art initialization strategy (Kaiming initialization), our approach needs 34% less epochs to reach the same validation loss. We also apply our approach to ResNets for the CIFAR-100 dataset, combined with transfer learning. Here, the initial accuracy is already at least 53%. This gives a faster weight convergence and a higher test accuracy than the benchmark strategies. [ABSTRACT FROM AUTHOR]

The importance of the quality of life of rotating machinery increases the Bearing fault diagnosis. Deep learning models (DL)-based databases become increasingly smart in the field of fault diagnostics, the latest research has widely used CNNs (convolutional neural networks). This paper proposes a new way to diagnose bearing failures with CNN with Bilinear LSTM. Traditional CNNs are however not easy to detect defects due to the fixed geometry of complex fault diagnosis with different working conditions. Our primary and secondary classifiers at specified layers replace primitive shape convolutions with reconfigurable convolutions, resulting in classification results with stringent feature time-frequency incompatibility and a larger receptive field. To acquire more adaptive knowledge and insight into the proposed approach, we employ the CWRU (Case Western Reserve University) opensource dataset to compare classification accuracy. The bearing dataset has been subjected to comprehensive experiments and evaluations in order to confirm the efficacy of the suggested technique's diagnostic performance in a variety of settings. By comparing multiple perspectives on the same dataset with related tasks, the proposed method's superiority is proved. To limit the effect of noise and avoid temporal oscillations, degraded index sequences are matched with a CNN. Current and previous inspection data are fed into a new CNN-BiLSTM model, which is then used to predict the useful time and compatible power values of bearing RULs. When it comes to output, go with the lifetime percentage. The proposed method has been tested by accelerating bearing operation to failure, and the results show that the method has advantages in predicting RUL more accurately. The results of the experiments suggest that the proposed core distance measurement method is a viable new tool for intelligent rolling bearing diagnosis. The BiLSTM technique is more diagnostic than some generic models, according to experimental results using the 48 K and 12 K CWRU datasets, with overall accuracy of 99.80% and 98.3%, respectively. [ABSTRACT FROM AUTHOR]

This paper constructs a remaining useful life (RUL) prediction model combining a convolutional neural network and a long short‐term memory network (CNNLSTM) to support decision‐making, especially the safety of rotational equipment. It avoids the influence of personnel and realizes the complementary advantages of the network. With the assistance of Bayesian short‐term and long‐term memory neural networks, the remaining life prediction method is able to provide the confidence interval of the remaining life prediction of rolling bearings. The compression between the proposed method and existing state‐of‐the‐art methods validated the good performance of the proposed method. Overall, the proposed method contributes to life prediction and condition‐based maintenance of bearings and complex rotational systems. [ABSTRACT FROM AUTHOR]