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

Machinery health prognostics: A systematic review from data acquisition to RUL prediction

A comprehensive review on convolutional neural network in machine fault diagnosis

Traditional feature extraction methods are used to extract the features of signal to construct the fault feature matrix, which exists the complex structure, higher correlation, and redundancy. This will increase the complex fault classification and seriously affect the accuracy and efficiency of fault identification. In order to solve these problems, a new fault diagnosis (PABSFD) method based on the principal component analysis (PCA) and the broad learning system (BLS) is proposed for rotor system in this paper. In the proposed PABSFD method, the PCA with revealing the signal essence is used to reduce the dimension of the constructed feature matrix and decrease the linear feature correlation between data and eliminate the redundant attributes in order to obtain the low-dimensional feature matrix with retaining the essential features for the classification model. Then, the BLS with low time complexity and high classification accuracy is regarded as a classification model to realize the fault identification; it can efficiently accomplish the fault classification of rotor system. Finally, the actual vibration data of rotor system are selected to test and verify the effectiveness of the PABSFD method. The experimental results show that the PCA method can effectively eliminate the feature correlation and realize the dimension reduction of the feature matrix, the BLS can take on better adaptability, faster computation speed, and higher classification accuracy, and the PABSFD method can efficiently and accurately obtain the fault diagnosis results.

/pdf/fault-diagnosis-method-based-on-principal-component-analysis-5fsmpm0rqo.pdf

Fault Diagnosis Method Based on Principal Component Analysis and Broad Learning System

A reliable technique for remaining useful life estimation of rolling element bearings using dynamic regression models

This paper presents a probabilistic model based approach for machinery condition prognosis based on particle filter by integrating physical knowledge with in-process measurements into a state space framework to account for uncertainty and nonlinearity in machinery degradation process. One limitation of conventional particle filter is that condition prognosis is performed based on the model with predetermined parameters obtained from simulation studies or lab-controlled tests. Due to the stochastic nature of machinery defect propagation under varying operating conditions, model parameters may vary in practice which causes prediction errors. To address it, an integrated state prediction and parameter estimation framework based on particle filter and expectation-maximization algorithm is formulated and investigated. The model parameters are adaptively estimated based on expectation-maximization algorithm utilizing hidden degradation state and available in-process measurements. Particle filter is then performed on the identified model with estimated parameters following Bayesian inference scheme to improve the robustness and accuracy of machinery condition prognosis. The effectiveness of the developed method is demonstrated through a simulation study and an experimental run-to-failure bearing test in a wind turbine.

A joint particle filter and expectation maximization approach to machine condition prognosis

https://iopscience.iop.org/article/10.1088/1361-6501/aadfb3/pdf

A novel fusion diagnosis method for rotor system fault based on deep learning and multi-sourced heterogeneous monitoring data

Auxiliary-model-based domain adaptation for reciprocating compressor diagnosis under variable conditions

In this study, a novel fusion diagnosis method for rotating machinery faults is proposed using multi-sourced monitoring data constituted by vibration signals and infrared images. This method consists of multi-sourced monitoring data capturing, data preprocessing and multi-stream convolutional neural network (CNN) based end to end fault diagnosis. As the core of the method, multi-stream CNN integrates feature learning, feature fusion and fault classification into one body, which has two advantages. (1) One is that it can directly process raw multi-sourced monitoring data and learn fault-sensitive features even if the data have completely different formats, which free us from the burdensome signal/image processing and artificial feature extraction. (2) The other is that it can adaptively fuse multi-sourced monitoring data in the feature level, which is propitious to remove the redundant features and preserve complementary information. The proposed method is validated by experimental studies on a rotor test bed, and the results confirm that the proposed method is more effective than other methods

Zhuang Yuan

Papers

A joint particle filter and expectation maximization approach to machine condition prognosis

A novel fusion diagnosis method for rotor system fault based on deep learning and multi-sourced heterogeneous monitoring data

Auxiliary-model-based domain adaptation for reciprocating compressor diagnosis under variable conditions

Multi-Sourced Monitoring Fusion Diagnosis for Rotating Machinery Faults