An Unsupervised Machine Learning Approach for Monitoring Data Fusion and Health Indicator Construction.

Researchers

Journal

Modalities

Models

Abstract

The prediction of system degradation is very important as it serves as an important basis for the formulation of condition-based maintenance strategies. An effective health indicator (HI) plays a key role in the prediction of system degradation as it enables vital information for critical tasks ranging from fault diagnosis to remaining useful life prediction. To address this issue, a method for monitoring data fusion and health indicator construction based on an autoencoder (AE) and a long short-term memory (LSTM) network is proposed in this study to improve the predictability and effectiveness of health indicators. Firstly, an unsupervised method and overall framework for HI construction is built based on a deep autoencoder and an LSTM neural network. The neural network is trained fully based on the normal operating monitoring data and then the construction error of the AE model is adopted as the health indicator of the system. Secondly, we propose related machine learning techniques for monitoring data processing to overcome the issue of data fusion, such as mutual information for sensor selection and t-distributed stochastic neighbor embedding (T-SNE) for operating condition identification. Thirdly, in order to verify the performance of the proposed method, experiments are conducted based on the CMAPSS dataset and results are compared with algorithms of principal component analysis (PCA) and a vanilla autoencoder model. Result shows that the LSTM-AE model outperforms the PCA and Vanilla-AE model in the metrics of monotonicity, trendability, prognosability, and fitness. Fourthly, in order to analyze the impact of the time step of the LSMT-AE model on HI construction, we construct and analyze the system HI curve under different time steps of 5, 10, 15, 20, and 25 cycles. Finally, the results demonstrate that the proposed method for HI construction can effectively characterize the health state of a system, which is helpful for the development of further failure prognostics and converting the scheduled maintenance into condition-based maintenance.