Search

With the development of industry and manufacturing, the mechanical structures of equipment have become intricate and complex. Due to the interaction between components, once a failure occurs, it will propagate through the industrial processes, resulting in multiple sensor anomalies. Identifying the root causes of faults and eliminating interference from irrelevant sensor signals are critical issues in enhancing the stability and reliability of intelligent fault diagnosis. The components of industrial processes and their interactions can be represented by a structural attribute graph. The causal subgraph formed by fault signals determines the fault mode, while irrelevant sensor signals constitute a non-causal subgraph. The structure of non-causal subgraphs is relatively simple, and graph neural networks tend to use this part as a shortcut for prediction, leading to a significant decrease in prediction accuracy. To address this issue, a causal intervention graph neural network (CIGNN) framework is proposed. First, the sensor signals are constructed into structural attribute graphs using an attention mechanism. Due to causal and confounding features are highly coupled in graphs, explicitly decoupling them is almost impossible. Then, we design an instrumental variable to implement causal intervention to mitigate the confounding effect. Experimental results on two complex industrial datasets demonstrate the reliability and effectiveness of the proposed method in fault diagnosis. • Formulates GNN-based fault diagnosis as a graph classification task. • Analyzes the causality in GNN-based fault diagnosis process based on causal theory. • Constructs automatically sensor signals into graph data using an attention mechanism. • Designs an instrumental variable for causal intervention on graphs. [ABSTRACT FROM AUTHOR]

By representing the embedded components and their interactions in industrial systems as nodes and edges in a graph, Graph Neural Networks (GNNs) have achieved outstanding results due to their ability to model statistical correlations. However, these correlations may not capture the true causal relationships within the data, thereby impairing the model's performance in fault diagnosis. To address this issue, an Information-based Gradient enhanced Causal Learning Graph Neural Network (IGCL-GNN) is proposed for fault diagnosis of complex industrial processes. First, the information theory in graph representations is theoretically analyzed and the optimization objectives are derived separately for the causal and non-causal parts of the graph neural network, which decouple it into a multi-objective optimization problem. Then, to optimize such problem, a causal disentanglement layer is designed in the graph network that could effectively separate causal and non-causal information in graph representations. Thirdly, a novel gradient reactivation method is proposed to dynamically filter features from the disentangled layers, thereby capture the causal representations of graph data more accurately. For robust and efficient optimization, the multi-objective gradient descent algorithm is employed in this paper. Finally, comparative experiments were conducted on the three-phase flow facility (TFF) dataset, achieving a fault diagnosis accuracy of 98.42% for our proposed method. • Explores causal feature learning in fault diagnosis from an information theory perspective. • Presents a gradient reactivation module for reliable causal subgraph extraction. • Improves the relevance of predictions to causal factors while suppressing the extraction of non-causal features. • Ensures the maximum extraction of real relevant information through the Pareto optimality of the two objectives. [ABSTRACT FROM AUTHOR]

The principle of stochastic resonance (SR) in the noisy Duffing oscillator model has shown benefit for designing novel mechanical fault diagnosis algorithms, where noise is utilized rather than being eliminated. However, there is a clear gap between the model progress and the experimental application. In this article, effort is made trying to narrow the gap by applying the method of moments to obtain the spectral amplification factor within the linear response range to improve the algorithm design, which avoids the conventional time-consuming direct simulations. A strategy for estimating noise, which is critical for programming the algorithm, is proposed and evaluated. Through simulation and experimental data analysis, it is confirmed that the new algorithm has advantages over the overdamped system-based methods as it does not depend on the signal preprocessing techniques such as envelope extraction and high-pass filter. Also, the new method has advantages over the existing underdamped system-based methods as it can decrease the computational time for seeking the optimal parameter by at least one order of magnitude. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural networks (CNNs) have been successfully used for motor fault diagnosis because of its powerful feature extraction ability. However, there are still some barriers of traditional CNNs. Due to the fact of the hierarchical structure, feature resolution of CNNs will be reduced with layer growth, which can lead to the information loss. In addition, the fixed kernel size makes traditional CNNs not suitable for fault diagnosis of motors, which are widely used in nonstationary conditions. Therefore, starting from the physical characteristics of nonstationary vibration signals, a cascade CNN (C-CNN) with progressive optimization is proposed in this article. First, a cascade structure is built to avoid the information loss caused by consecutive convolution striding or pooling. Then, dilated convolution operations are implemented, which can extract the feature maps from different scales and extend the applications of CNN to nonstationary conditions. Furthermore, taking the advantage of the cascade structure, a progressive optimization algorithm is proposed for divide-and-conquer parameters optimization, which enables the C-CNN to converge to a more optimum state and improve the diagnosis performance. The proposed method is verified by two motor fault diagnosis experiments, which are conducted under constant speed and variable speed, respectively. The results show that the proposed method can achieve better performance when rotating speed is either constant or changing than exiting methods. [ABSTRACT FROM AUTHOR]

Motor fault diagnosis is imperative to enhance the reliability and security of industrial systems. However, since motors are often operated under nonstationary conditions, the high complexity of vibration signals raises notable difficulties for fault diagnosis. Therefore, considering the special physical characteristics of motor signals under nonstationary conditions, in this article, we propose a multiscale kernel based residual convolutional neural network (CNN) for motor fault diagnosis. Our contributions mainly fall into two aspects. First, we notice that each motor fault category has various patterns in vibration signals due to the changing operational conditions of the motor. To capture these patterns, a multiscale kernel algorithm is applied in the CNN architecture. Second, since the motor vibration signals are made up of many different components from different transfer paths, they are very complex and variable. To enable the architecture to extract fault features from deep and hierarchical representation spaces, sufficient depth of the network is needed, which will lead to the degradation problem. In the proposed method, residual learning is embedded into the multiscale kernel CNN to avoid performance degradation and build a deeper network. To validate the effectiveness of the proposed networks, a normal motor and five motors with different failures are tested. The results and comparisons with state-of-the-art methods highlight the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Fault diagnosis and remaining useful life (RUL) prediction are always two major issues in modern industrial systems, which are usually regarded as two separated tasks to make the problem easier but ignore the fact that there are certain information of these two tasks that can be shared to improve the performance. Therefore, to capture common features between different relative problems, a joint-loss convolutional neural network (JL-CNN) architecture is proposed in this paper, which can implement bearing fault recognition and RUL prediction in parallel by sharing the parameters and partial networks, meanwhile keeping the output layers of different tasks. The JL-CNN is constructed based on a CNN, which is a widely used deep learning method because of its powerful feature extraction ability. During optimization phase, a JL function is designed to enable the proposed approach to learn the diagnosis–prognosis features and improve generalization while reducing the overfitting risk and computation cost. Moreover, because the information behind the signals of different problems has been shared and exploited deeper, the generalization and the accuracy of results can also be improved. Finally, the effectiveness of the JL-CNN method is validated by run-to-failure dataset. Compared with support vector regression and traditional CNN, the mean-square-error of the proposed method decreases 82.7 $\%$ and 24.9 $\%$ , respectively. Therefore, results and comparisons show that the proposed method can be applied for the intercrossed applications between fault diagnosis and RUL prediction. [ABSTRACT FROM AUTHOR]

As wind power attracts increasing attention and wind turbines (WTs) capacity expands, fault diagnosis of WT is playing a more and more important role in improving reliability, minimizing down time, reducing maintenance costs, and providing reliable power generation. In this paper, a novel sparse time-frequency representation (STFR) method is proposed to increase the diagnostic precision of incipient faults. The proposed method can be applied once the condition is detected as abnormal according to the VDI3834 vibration threshold standard in WT fault diagnosis systems. The proposed method is a novel signal representation method based on the sparse representation theory and Wigner–Ville distribution (WVD), which can overcome the limitations of traditional basis functions expansion and time-frequency analysis methods. In this method, a union of redundant dictionary (URD) is constructed on the basis of the underlying prior information of the oscillate characteristics with multicomponent coupling effect and different morphological waveforms. Therefore, the vibration signal can be sparsely represented over the URD. Then, the sparse coefficients and corresponding atoms can be obtained by solving the basis pursuit denoising problem via alternating direction method of multipliers. Based on the combination of the WVD of each atom and corresponding sparse coefficient, the time-frequency distribution of the vibration signal can be obtained. To verify the effectiveness of the STFR method, a simulation and two field tests in the wind farm are performed. The comparison results with state-of-the-art methods illustrate the superiority and robustness of the proposed method in the engineering applications. [ABSTRACT FROM AUTHOR]

Fault diagnosis of rotating machinery plays a significant role for the reliability and safety of modern industrial systems. As an emerging field in industrial applications and an effective solution for fault recognition, artificial intelligence (AI) techniques have been receiving increasing attention from academia and industry. However, great challenges are met by the AI methods under the different real operating conditions. This paper attempts to present a comprehensive review of AI algorithms in rotating machinery fault diagnosis, from both the views of theory background and industrial applications. A brief introduction of different AI algorithms is presented first, including the following methods: k -nearest neighbour, naive Bayes, support vector machine, artificial neural network and deep learning. Then, a broad literature survey of these AI algorithms in industrial applications is given. Finally, the advantages, limitations, practical implications of different AI algorithms, as well as some new research trends, are discussed. [ABSTRACT FROM AUTHOR]

Bearing plays an essential role in the performance of mechanical system and fault diagnosis of mechanical system is inseparably related to the diagnosis of the bearings. However, it is a challenge to detect weak fault from the complex and non-stationary vibration signals with a large amount of noise, especially at the early stage. To improve the anti-noise ability and detect incipient fault, a novel fault detection method based on a short-time matching method and Support Vector Machine (SVM) is proposed. In this paper, the mechanism of roller bearing is discussed and the impact time frequency dictionary is constructed targeting the multi-component characteristics and fault feature of roller bearing fault vibration signals. Then, a short-time matching method is described and the simulation results show the excellent feature extraction effects in extremely low signal-to-noise ratio (SNR). After extracting the most relevance atoms as features, SVM was trained for fault recognition. Finally, the practical bearing experiments indicate that the proposed method is more effective and efficient than the traditional methods in weak impact signal oscillatory characters extraction and incipient fault diagnosis. [ABSTRACT FROM AUTHOR]