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.

A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox

Rotating machinery plays a critical role in many significant fields. However, the unpredictable machinery faults may lead to the severe damage and losses. Hence, it is of great value to explore the precise approaches for fault diagnosis. With the development of the intelligent fault diagnosis methods based on deep learning, convolutional neural network (CNN) has aroused the attention of researchers in machinery fault diagnosis. In the light of the reduction of difficulty in feature learning and the improvement of final diagnosis accuracy, data preprocessing is necessary and crucial in CNN-based fault diagnosis methods. This review focuses on CNN-based fault diagnosis approaches in rotating machinery. Firstly, data preprocessing methods are overviewed. Then, we emphatically analyze and discuss several main techniques applied in CNN-based intelligent diagnosis, principally including the fast Fourier transform, wavelet transform, data augmentation, S-transform, and cyclic spectral analysis. Finally, the potential challenges and research objects are prospected on data preprocessing in intelligent fault diagnosis of rotary machinery.

/pdf/data-preprocessing-techniques-in-convolutional-neural-11gl3o9h4l.pdf

Data Preprocessing Techniques in Convolutional Neural Network Based on Fault Diagnosis Towards Rotating Machinery

A fault diagnosis method for wind turbines gearbox based on adaptive loss weighted meta-ResNet under noisy labels

Prognostics and Health Management (PHM), including monitoring, diagnosis, prognosis, and health management, occupies an increasingly important position in reducing costly breakdowns and avoiding catastrophic accidents in modern industry. With the development of artificial intelligence (AI), especially deep learning (DL) approaches, the application of AI-enabled methods to monitor, diagnose and predict potential equipment malfunctions has gone through tremendous progress with verified success in both academia and industry. However, there is still a gap to cover monitoring, diagnosis, and prognosis based on AI-enabled methods, simultaneously, and the importance of an open source community, including open source datasets and codes, has not been fully emphasized. To fill this gap, this paper provides a systematic overview of the current development, common technologies, open source datasets, codes, and challenges of AI-enabled PHM methods from three aspects of monitoring, diagnosis, and prognosis.

/pdf/challenges-and-opportunities-of-ai-enabled-monitoring-43p18hy8jm.pdf

Challenges and Opportunities of AI-Enabled Monitoring, Diagnosis & Prognosis: A Review

In this paper, we propose a novel method for the classification of bearing faults using a convolutional neural network (CNN) and vibration spectrum imaging (VSI). The normalized amplitudes of the spectral content extracted from segmented temporal vibratory signals using a time-moving segmentation window are transformed into spectral images for training and testing of the CNN classifier. To show the efficiency of the proposed method, vibratory data for healthy and faulted bearings operating at different speeds are collected from an experimental test bench. The classification accuracy, variable load and speed testing, generalization, and robustness by adding noise to the collected data at different levels (SNR) are then evaluated. The obtained experimental classification results show excellent performance in terms of both accuracy and robustness.

Rolling element bearing fault diagnosis for rotating machinery using vibration spectrum imaging and convolutional neural networks

The development of an intelligent fault diagnosis system to identify automatically and accurately micro-faults affecting motors continues to be a challenge for industrial rotary machinery and needs to be addressed. In this paper, we put forward a novel approach based on ensemble empirical mode decomposition (EEMD) processing for incipient fault diagnosis of rotating machinery. Accurate selection and reconstruction processes are performed to reconstruct new vibration signals with less noise through the application of EEMD processing to original vibration signals. After the rebuilt of vibration signals, manually extracted features from the reconstructed vibration signals are fed then into a multi-class support vector machine and simultaneously to the mentioned technique, generated image representations of the same raw signals are taken afterward as an input to a deep convolutional neural network (CNN) for classification and fault diagnosis. The comparison between these developed methods demonstrates the effectiveness of the deep learning approach that identifies the differences between classes automatically and can successfully classify and locate the faulty bearing status with very high accuracy for the small size of training data.

Mohamed Nacer Saadi

Papers

Rolling element bearing fault diagnosis for rotating machinery using vibration spectrum imaging and convolutional neural networks

Bearing fault diagnostics using EEMD processing and convolutional neural network methods