Operational time-series data modeling via LSTM network integrating principal component analysis based on human experience. (October 2021)

• Record Type: Journal Article
• Authors: Yang, Ke; Liu, Yi-liu; Yao, Yu-nan; Fan, Shi-dong; Mosleh, Ali
• Is Part Of: Journal of manufacturing systems. Volume 61(2021)
• Page Start: 746
• Page End: 756
• Publication Date: 2021-10
• Subjects: Principal component analysis -- Long short-term memory network -- Human experience -- Condition monitoring system -- Time series data; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2020.11.020
• Languages: English
• ISSNs: 0278-6125

Abstract

Highlights: A LSTM integrating PCA based on artificial experience is proposed in this paper. PCA based on artificial experience is firstly conducted to extract condition parameters. The LSTM framework can deal with the time series nonlinear data. A dynamic update of the prediction model is performed to avoid the model misalignment. The proposed method outperforms standard models on an auxiliary engine system. Abstract: Today's information technologies involve increasingly intelligent systems, which come at the cost of increasingly complex equipment. Modern monitoring systems collect multi-measuring-point and long-term data which make equipment health prediction a "big data" problem. It is difficult to extract information from such condition monitoring data to accurately estimate or predict health statuses. Deep learning is a powerful tool for big data processing that is widely utilized in image and speech recognition applications, and can also provide effective predictions in industrial processes. This paper proposes the Long Short-term Memory Integrating Principal Component Analysis based on Human Experience (HEPCA-LSTM), which uses operational time-series data for equipment health prognostics. Principal component analysis based on human experience is first conducted to extract condition parameters from the condition monitoring system. The long short-term memory (LSTM) framework is then constructed to predict the target status. Finally, a dynamic update of the prediction model with incoming data is performed at a certain interval to prevent any model misalignment caused by the drifting of relevant variables. The proposed model is validated on a practical case and found to outperform other prediction methods. It utilizes a powerful deep learning analysis method, the LSTM, to fully process big condition monitoring series data; it effectively extracts the features involved with human experience and takes dynamic updates into consideration.