Restructured society and environment: A review on potential technological strategies to control the COVID-19 pandemic.

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.

Automatic and reliable fault diagnosis of rotating machinery cross working conditions is of practical importance. For this purpose, ensemble transfer convolutional neural networks (CNNs) driven by multi-channel signals are proposed in this paper. Firstly, a series of source CNNs modified with stochastic pooling and Leaky rectified linear unit (LReLU) are pre-trained using multi-channel signals. Secondly, the learned parameter knowledge of each individual source CNN is transferred to initialize the corresponding target CNN which is then fine-tuned by a few target training samples. Finally, a new decision fusion strategy is designed to flexibly fuse each individual target CNN to obtain the comprehensive result. The proposed method is used to analyze multi-channel signals measured from rotating machinery. The comparison result shows the superiorities of the proposed method over the existing deep transfer learning methods.

Ensemble transfer CNNs driven by multi-channel signals for fault diagnosis of rotating machinery cross working conditions

/pdf/a-perspective-survey-on-deep-transfer-learning-for-fault-m5e3nrkv.pdf

A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges

Applications of machine learning to machine fault diagnosis: A review and roadmap

The invention discloses a mechanical equipment fault diagnosis method based on an expectancy disparity constraint belief network. The method comprises the following steps: firstly acquiring vibrationsignals of mechanical equipment under different health statuses, and extracting translation invariant features; taking the translation invariant features as the input to extract depth features of thevibration signals; taking the depth features as the input, and extracting fault features of the working robustness; and finally training a Softmax classifier based on the extracted fault features forthe working condition robustness, and accomplishing the intelligent diagnosis of the mechanical equipment fault under multiple working conditions by utilizing the trained classifier. By utilizing theexpectancy disparity constraint belief network , the mechanical equipment fault features of the working condition robustness can be directly extracted from the original vibrations signals, and the high diagnosis precision can be obtained under multiple working conditions, the fault recognition robustness is good, the feature distribution disparity under different working conditions is reduced, andthe fault diagnosis precision under the new working condition is improved.

Mechanical equipment fault diagnosis method based on expectancy disparity constraint belief network

The invention discloses a mechanical equipment residual life prediction method based on a laminated separation convolution module, and the method comprises the steps: obtaining original vibration signals of mechanical equipment under different working conditions, carrying out the preprocessing, and building a mechanical equipment residual life prediction model based on the laminated separation convolution module; extracting a high-level typical feature most related to the health condition of the mechanical equipment in the original vibration signal by using a stacking separation convolution module; inputting the high-level typical features into a full connection network to obtain a residual life prediction value of the mechanical equipment; constructing a mean square error objective function of the residual life prediction model, and iteratively updating to-be-trained parameters of the prediction model through an Adam optimization algorithm to obtain an optimal residual life predictionmodel; and finally inputting the pre-processed mechanical equipment vibration signal to complete the prediction of the remaining life of the mechanical equipment. The method has the advantages of higher prediction precision, better stability and stronger robustness.

Jiang Xinwei

Papers

Applications of machine learning to machine fault diagnosis: A review and roadmap

Mechanical equipment fault diagnosis method based on expectancy disparity constraint belief network

Mechanical equipment remaining life prediction method based on stacking separation convolution module