Intelligent Fault Diagnosis of Gearbox Under Variable Working Conditions With Adaptive Intraclass and Interclass Convolutional Neural Network

A Segmented Iterative Learning Scheme-Based Distributed Fault Estimation for Switched Interconnected Nonlinear Systems

In this article, a distributed fault estimation (DFE) approach for switched interconnected nonlinear systems (SINSs) with time delays and external disturbances is proposed using a novel segmented iterative learning scheme (SILS). First, through the utilization of interrelated information among subsystems, a distributed iterative learning observer is developed to enhance the accuracy of fault estimation results, which can realize the fault estimation of all subsystems under time delays and external disturbances. Simultaneously, to facilitate rapid fault information tracking and significantly reduce sensitivity to interference, a new SILS-based fault estimation law is constructed by combining the idea of segmented design with the method of variable gain. Then, an assessment of the convergence of the established fault estimation methodology is conducted, and the configurations of observer gain matrices and iterative learning gain matrices are duly accomplished. Finally, simulation results are showcased to demonstrate the superiority and feasibility of the developed fault estimation approach.

Minimum maximum regularized multiscale convolutional neural network and its application in intelligent fault diagnosis of rotary machines

Convolutional neural networks (CNN) have achieved significant advancements in intelligent fault diagnosis of rotary machines. However, the limitations of using a single scale convolution kernel in convolutional layer and the exclusive focus on classification accuracy by the cross-entropy loss function during model training result in suboptimal diagnostic performance and generalization ability of CNNs in environments with strong background noise and imbalanced data. To address these challenges, a fault recognition method for rotary machines utilizing a minimum maximum regularized multiscale CNN (MMRMCNN) is proposed. A multiscale feature extraction module is devised, which uses convolutional layers with diverse scale kernels to capture multiscale features form input data. Additionally, a minimum maximum regularized objective function is introduced to augment the original cross-entropy loss function. This modification enables the model to consider not only recognition accuracy but also the compactness within classes and separation between classes of learning features during network training. The proposed approach effectively narrows the intra class margin of device health status features while widening the inter class margin, thereby mitigating the impact of noise and data imbalance on the mapping of health status relationship. Performance evaluation of the MMRMCNN is conducted using a measured dataset, the PU bearing dataset, and a rotor dataset. We found that the fault recognition accuracy of the proposed method exceeds 97.79 %, and the accuracy of fault recognition under noisy background and unbalanced data conditions is also above 94.81 % and 94.72 %, respectively. This demonstrate the superior fault recognition capabilities of the proposed method in scenarios characterized by strong background noise and data imbalance. Overall, the results attest to the exceptional performances of the developed MMRMCNN in fault recognition under challenging conditions, underscoring its potential in advancing the field of in Telligent fault diagnosis for rotary machines.

Bayesian Hierarchical Graph Neural Networks With Uncertainty Feedback for Trustworthy Fault Diagnosis of Industrial Processes

Deep learning (DL) methods have been widely applied to intelligent fault diagnosis of industrial processes and achieved state-of-the-art performance. However, fault diagnosis with point estimate may provide untrustworthy decisions. Recently, Bayesian inference shows to be a promising approach to trustworthy fault diagnosis by quantifying the uncertainty of the decisions with a DL model. The uncertainty information is not involved in the training process, which does not help the learning of highly uncertain samples and has little effect on improving the fault diagnosis performance. To address this challenge, we propose a Bayesian hierarchical graph neural network (BHGNN) with an uncertainty feedback mechanism, which formulates a trustworthy fault diagnosis on the Bayesian DL (BDL) framework. Specifically, BHGNN captures the epistemic uncertainty and aleatoric uncertainty via a variational dropout approach and utilizes the uncertainty information of each sample to adjust the strength of the temporal consistency (TC) constraint for robust feature learning. Meanwhile, the BHGNN method models the process data as a hierarchical graph (HG) by leveraging the interaction-aware module and physical topology knowledge of the industrial process, which integrates data with domain knowledge to learn fault representation. Moreover, the experiments on a three-phase flow facility (TFF) and secure water treatment (SWaT) show superior and competitive performance in fault diagnosis and verify the trustworthiness of the proposed method.

PeriodNet: Noise-Robust Fault Diagnosis Method Under Varying Speed Conditions

Rolling bearings are critical components in modern mechanical systems and have been extensively equipped in various rotating machinery. However, their operating conditions are becoming increasingly complex due to diverse working requirements, dramatically increasing their failure risks. Worse still, the interference of strong background noises and the modulation of varying speed conditions make intelligent fault diagnosis very challenging for conventional methods with limited feature extraction capability. To this end, this study proposes a periodic convolutional neural network (PeriodNet), which is an intelligent end-to-end framework for bearing fault diagnosis. The proposed PeriodNet is constructed by inserting a periodic convolutional module (PeriodConv) before a backbone network. PeriodConv is developed based on the generalized short-time noise resist correlation (GeSTNRC) method, which can effectively capture features from noisy vibration signals collected under varying speed conditions. In PeriodConv, GeSTNRC is extended to the weighted version through deep learning (DL) techniques, whose parameters can be optimized during training. Two open-source datasets collected under constant and varying speed conditions are adopted to assess the proposed method. Case studies demonstrate that PeriodNet has excellent generalizability and is effective under varying speed conditions. Experiments adding noise interference further reveal that PeriodNet is highly robust in noisy environments.

SSG-Net: A Multi-Branch Fault Diagnosis Method for Scroll Compressors Using Swin Transformer Sliding Window, Shallow ResNet, and Global Attention Mechanism (GAM)

The reliable operation of scroll compressors is crucial for the efficiency of rotating machinery and refrigeration systems. To address the need for efficient and accurate fault diagnosis in scroll compressor technology under varying operating states, diverse failure modes, and different operating conditions, a multi-branch convolutional neural network fault diagnosis method (SSG-Net) has been developed. This method is based on the Swin Transformer, the Global Attention Mechanism (GAM), and the ResNet architecture. Initially, the one-dimensional time-series signal is converted into a two-dimensional image using the Short-Time Fourier Transform, thereby enriching the feature set for deep learning analysis. Subsequently, the method integrates the window attention mechanism of the Swin Transformer, the 2D convolution of GAM attention, and the shallow ResNet's two-dimensional convolution feature extraction branch network. This integration further optimizes the feature extraction process, enhancing the accuracy of fault feature recognition and sensitivity to data variability. Consequently, by combining the global and local features extracted from these three branch networks, the model significantly improves feature representation capability and robustness. Finally, experimental results on scroll compressor datasets and the CWRU dataset demonstrate diagnostic accuracies of 97.44% and 99.78%, respectively. These results surpass existing comparative models and confirm the model's superior recognition precision and rapid convergence capabilities in complex fault environments.

Variational Attention-Based Interpretable Transformer Network for Rotary Machine Fault Diagnosis

Deep learning technology provides a promising approach for rotary machine fault diagnosis (RMFD), where vibration signals are commonly utilized as input of a deep network model to reveal the internal state of machinery. However, most existing methods fail to mine association relationships within signals. Unlike deep neural networks, transformer networks are capable of capturing association relationships through the global self-attention mechanism to enhance feature representations from vibration signals. Despite this, transformer networks cannot explicitly establish the causal association between signal patterns and fault types, resulting in poor interpretability. To tackle these problems, an interpretable deep learning model named the variational attention-based transformer network (VATN) is proposed for RMFD. VATN is improved from transformer encoder to mine the association relationships within signals. To embed the prior knowledge of the fault type, which can be recognized based on several key features of vibration signals, a sparse constraint is designed for attention weights. Variational inference is employed to force attention weights to samples from Dirichlet distributions, and Laplace approximation is applied to realize reparameterization. Finally, two experimental studies conducted on bevel gear and bearing datasets demonstrate the effectiveness of VATN to other comparison methods, and the heat map of attention weights illustrates the causal association between fault types and signal patterns.

A Multiple Attention Convolutional Neural Networks for Diesel Engine Fault Diagnosis

Fault diagnosis can improve the safety and reliability of diesel engines. An end-to-end method based on a multi-attention convolutional neural network (MACNN) is proposed for accurate and efficient diesel engine fault diagnosis. By optimizing the arrangement and kernel size of the channel and spatial attention modules, the feature extraction capability is improved, and an improved convolutional block attention module (ICBAM) is obtained. Vibration signal features are acquired using a feature extraction model alternating between the convolutional neural network (CNN) and ICBAM. The feature map is recombined to reconstruct the sequence order information. Next, the self-attention mechanism (SAM) is applied to learn the recombined sequence features directly. A Swish activation function is introduced to solve "Dead ReLU" and improve the accuracy. A dynamic learning rate curve is designed to improve the convergence ability of the model. The diesel engine fault simulation experiment is carried out to simulate three kinds of fault types (abnormal valve clearance, abnormal rail pressure, and insufficient fuel supply), and each kind of fault varies in different degrees. The comparison results show that the accuracy of MACNN on the eight-class fault dataset at different speeds is more than 97%. The testing time of the MACNN is much less than the machine running time (for one work cycle). Therefore, the proposed end-to-end fault diagnosis method has a good application prospect.

Gas Turbine Anomaly Detection under Time-Varying Operation Conditions Based on Spectra Alignment and Self-Adaptive Normalization

Gas turbine vibration data may exhibit considerable differences under time-varying conditions, which poses challenges for neural network anomaly detection. We first propose a framework for a gas turbine vibration frequency spectra process under time-varying operation conditions, assisting neural networks' ability to capture weak information. The framework involves scaling spectra for aligning all frequency components related to rotational speed and normalizing frequency amplitude in a self-adaptive way. Degressive beta variational autoencoder is employed for learning spectra characteristics and anomaly detection, while a multi-category anomaly index is proposed to accommodate various operating conditions. Finally, a dataset of blade Foreign Object Damage (FOD) fault occurring under time-varying operating conditions was used to validate the framework and anomaly detection. The results demonstrate that the proposed method can effectively reduce the spectra differences under time-varying conditions, and also detect FOD fault during operation, which are challenging to identify using conventional methods.

Intelligent fault diagnosis algorithm of rolling bearing based on optimization algorithm fusion convolutional neural network

As an essential component of mechanical equipment, the fault diagnosis of rolling bearings may not only guarantee the systematic operation of the equipment, but also minimize any financial losses caused by equipment shutdowns. Fault diagnosis algorithms based on convolutional neural networks (CNN) have been widely used. However, traditional CNNs have limited feature representation capabilities, thereby making it challenging to determine their hyperparameters. This paper proposes a fault diagnosis method that combines a 1D-CNN with an attention mechanism and hyperparameter optimization to overcome the aforementioned limitations; this method improves the search speed for optimal hyperparameters of CNN models, improves the diagnostic accuracy, and enhances the representation of fault feature information in CNNs. First, the 1D-CNN is improved by combining it with an attention mechanism to enhance the fault feature information. Second, a swarm intelligence algorithm based on Differential Evolution (DE) and Grey Wolf Optimization (GWO) is proposed, which not only improves the convergence accuracy, but also increases the search efficiency. Finally, the improved 1D-CNN alongside hyperparameters optimization are used to diagnose the faults of rolling bearings. By using the Case Western Reserve University (CWRU) and Jiangnan University (JNU) datasets, when compared to other common diagnosis models, the results demonstrate the usefulness and dependability of the DE-GWO-CNN algorithm in fault diagnosis applications by demonstrating the increased diagnostic accuracy and superior anti-noise capabilities of the proposed method. The fault diagnosis methodology presented in this paper can accurately identify faults and provide dependable fault classification, thereby assisting technicians in promptly resolving faults and minimizing equipment failures and operational instabilities.

Gear Fault Diagnosis Method Based on Multi-Sensor Information Fusion and VGG

The gearbox is an important component in the mechanical transmission system and plays a key role in aerospace, wind power and other fields. Gear failure is one of the main causes of gearbox failure, and therefore it is very important to accurately diagnose the type of gear failure under different operating conditions. Aiming at the problem that it is difficult to effectively identify the fault types of gears using traditional methods under complex and changeable working conditions, a fault diagnosis method based on multi-sensor information fusion and Visual Geometry Group (VGG) is proposed. First, the power spectral density is calculated with the raw frequency domain signal collected by multiple sensors before being transformed into a power spectral density energy map after information fusion. Second, the obtained energy map is combined with VGG to obtain the fault diagnosis model of the gear. Finally, two datasets are used to verify the effectiveness and generalization ability of the method. The experimental results show that the accuracy of the method can reach 100% at most on both datasets.

Transmission Line Fault Classification of Multi-Dataset Using CatBoost Classifier

Transmission line fault classification forms the basis of fault protection management in power systems. Because faults have adverse effects on transmission lines, adequate measures must be implemented to avoid power outages. This paper focuses on using the categorical boosting (CatBoost) algorithm classifier to analyse and train multiple voltage and current data from a 330 kV and 500 km-long simulated faulty transmission line model designed using Matlab/Simulink. From it, 93,340 fault data sizes were extracted. The CatBoost classifier was employed to classify the faults after different machine learning algorithms were used to train the same data with different parameters. The trainer achieved the best accuracy of 99.54%, with an error of 0.46% for 748 iterations out of 1000. The algorithm was selected for its high performance in classifying faults based on accuracy, precision and speed. In addition, it is easy to use and handles multiple data-sets. In contrast, a support vector machine and an artificial neural network each has a longer training time than the proposed method’s 58.5 s. Proper fault classification techniques assist in the effective fault management and planning of power system control thereby preventing energy waste and providing high performance.