Rotating machinery intelligent diagnosis based on deep learning (DL) has gone through tremendous progress, which can help reduce costly breakdowns. However, different datasets and hyper-parameters are recommended to be used, and few open source codes are publicly available, resulting in unfair comparisons and ineffective improvement. To address these issues, we perform a comprehensive evaluation of four models, including multi-layer perception (MLP), auto-encoder (AE), convolutional neural network (CNN), and recurrent neural network (RNN), with seven datasets to provide a benchmark study. We first gather nine publicly available datasets and give a comprehensive benchmark study of DL-based models with two data split strategies, five input formats, three normalization methods, and four augmentation methods. Second, we integrate the whole evaluation codes into a code library and release it to the public for better comparisons. Third, we use specific-designed cases to point out the existing issues, including class imbalance, generalization ability, interpretability, few-shot learning, and model selection. Finally, we release a unified code framework for comparing and testing models fairly and quickly, emphasize the importance of open source codes, provide the baseline accuracy (a lower bound), and discuss existing issues in this field. The code library is available at: https://github.com/ZhaoZhibin/DL-based-Intelligent-Diagnosis-Benchmark.

Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study.

The data-driven methods in machinery fault diagnosis have become increasingly popular in the past two decades. However, the wide applications of this scheme are generally compromised in real-world conditions because of the discrepancy between the training data and testing data. Although the recently emerging transfer fault diagnosis can learn transferable features from relevant source data and adapt the diagnostic model to the target data, these methods still only work on the target domain with a priori data distribution. The generalization capability of the transferred model cannot be guaranteed for unseen domains. Since the working conditions of machinery are varying during operation, the generalization capability of the diagnosis methods is crucial in this case. To tackle this challenge, this article proposes a domain generalization-based hybrid diagnosis network for deploying to unseen working conditions. The main idea is to regularize the discriminant structure of the deep network with both intrinsic and extrinsic generalization objectives such that the diagnostic model can learn robust features and generalize to unseen domains. The triplet loss minimization of intrinsic multisource data is implemented to facilitate the intraclass compactness and the interclass separability at the class level, leading to a more generalized decision boundary. The extrinsic domain-level regularization is achieved by using adversarial training to further reduce the risk of overfitting. Extensive cross-domain diagnostic experiments on planetary gearbox demonstrate the effectiveness of the proposed method.

A Hybrid Generalization Network for Intelligent Fault Diagnosis of Rotating Machinery Under Unseen Working Conditions

An explainable artificial intelligence approach for unsupervised fault detection and diagnosis in rotating machinery

Deep learning (DL) based methods have swept the field of mechanical fault diagnosis, because of the powerful ability of feature representation. However, many of existing DL methods fail in relationship mining between signals explicitly. Unlike those deep neural networks, graph convolutional networks (GCNs) taking graph data with topological structure as input is more efficient for data relationship mining, making GCN to be powerful for feature representation from graph data in non-Euclidean space. Nevertheless, existing GCNs have two limitations. First, most GCNs are constructed on unweighted graphs, considering importance of neighbors as the same, which is not in line with reality. Second, the receptive field of GCNs is fixed, which limits the effectiveness of GCNs for feature representation. To address these issues, a multireceptive field graph convolutional network (MRF-GCN) is proposed for effective intelligent fault diagnosis. In MRF-GCN, data samples are converted into weighted graphs to indicate differences in relationship of data samples. Moreover, MRF-GCN learns not only features from different receptive field, but also fuses learned features as an enhanced feature representation. To verify the efficacy of MRF-GCN for machine fault diagnosis, case studies are implemented, and the results show that MRF-GCN can achieve superior performance even under imbalanced dataset.

Multireceptive Field Graph Convolutional Networks for Machine Fault Diagnosis

Unsupervised domain adaptation (UDA)-based methods have made great progress in mechanical fault diagnosis under variable working conditions. In UDA, three types of information, including class label, domain label, and data structure, are essential to bridging the labeled source domain and unlabeled target domain. However, most existing UDA-based methods use only the former two information and ignore the modeling of data structure, which make the information contained in the features extracted by the deep network incomplete. To tackle this issue, a domain adversarial graph convolutional network (DAGCN) is proposed to model the three types of information in a unified deep network and achieving UDA. The first two types of information are modeled by the classifier and the domain discriminator, respectively. In data structure modeling, a convolutional neural network (CNN) is first employed to exact features from input signals. After that, the CNN features are input to the proposed graph generation layer to construct instance graphs by mining the relationship of structural characteristics of samples. Then, the instance graphs are modeled by a graph convolutional network, and the maximum mean discrepancy metric is leveraged to estimate the structure discrepancy of instance graphs from different domains. Experimental results conducted on two case studies demonstrate that the proposed DAGCN can not only obtain the best performance among the comparison methods, but also can extract transferable features for domain adaptation. The code library is available at: https://github.com/HazeDT/DAGCN .

Domain Adversarial Graph Convolutional Network for Fault Diagnosis Under Variable Working Conditions

Convolutional neural network (CNN), with the ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, an explanation on the physical meaning of a CNN architecture has rarely been studied. In this article, a novel wavelet-driven deep neural network, termed as WaveletKernelNet (WKN), is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful kernels. Furthermore, only the scale parameter and translation parameter are directly learned from raw data at this CWConv layer. This provides a very effective way to obtain a customized kernel bank, specifically tuned for extracting defect-related impact component embedded in the vibration signal. In addition, three experimental studies using data from laboratory environment are carried out to verify the effectiveness of the proposed method for mechanical fault diagnosis. The experimental results show that the accuracy of the WKNs is higher than CNN by more than 10%, which indicate the importance of the designed CWConv layer. Besides, through theoretical analysis and feature map visualization, it is found that the WKNs are interpretable, have fewer parameters, and have the ability to converge faster within the same training epochs.

WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis

Convolutional neural network (CNN), with ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, explanation on the physical meaning of a CNN architecture has rarely been studied. In this paper, a novel wavelet driven deep neural network termed as WaveletKernelNet (WKN) is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful filters. Furthermore, only the scale parameter and translation parameter are directly learned from raw data at this CWConv layer. This provides a very effective way to obtain a customized filter bank, specifically tuned for extracting defect-related impact component embedded in the vibration signal. In addition, three experimental verification using data from laboratory environment are carried out to verify effectiveness of the proposed method for mechanical fault diagnosis. The results show the importance of the designed CWConv layer and the output of CWConv layer is interpretable. Besides, it is found that WKN has fewer parameters, higher fault classification accuracy and faster convergence speed than standard CNN.

Li Cheng

Papers

WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis

WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis.