A feature extraction method for predictive maintenance with time‐lagged correlation–based curve‐registration model. Issue 5 (3rd July 2018)

• Record Type: Journal Article
• Authors: Zhang, Shouli; Liu, Chen; Su, Shen; Han, Yanbo; Li, XiaoHong
• Other Names: Sá Silva Jorge guestEditor.; Loureiro António guestEditor.; Skarmeta Antonio guestEditor.; Boavida Fernando guestEditor.
• Is Part Of: International journal of network management. Volume 28:Issue 5(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-07-03
• Subjects: Computer networks -- Management -- Periodicals; 004.6
• DOI: 10.1002/nem.2025
• Languages: English
• ISSNs: 1055-7148

Abstract

Abstract: With the prevalent development and use of predictive maintenance models for Internet‐of‐Things scenarios, the deep learning technology is gaining momentum. Feature extraction helps to increase efficiency in training the deep‐learning–based predictive maintenance model. However, there are common situations of time‐lagged correlations among industrial sensor data, resulting in reduction the effect of feature extraction. In this paper, we propose a feature extraction method for multisensors data with time‐lagged correlation. A curve‐registration method of correlation maximization algorithm is used to solve the problem of time‐lagged correlation for multi sensors. Then we apply a recurrent neural network, namely, long short‐term memory to develop a lightweight predictive maintenance model with the help of proposed feature extraction method. The effectiveness of the proposed feature extraction approach is demonstrated by examining real cases in a power plant. The experimental results indicate that our method can (1) effectively improve the accuracy of prediction and (2) improve the performance of the prediction model. Abstract : Feature extraction helps to increase efficiency in training the deep‐learning–based predictive maintenance model. However, there are common situations of time‐lagged correlations among high‐dimensional industrial sensor data, resulting in reduction the effect of feature extraction. This paper proposes a time‐lagged correlation‐based feature extraction method based on a curve‐registration method of correlation maximization algorithm for multi sensors.With the help of proposed feature extraction method, a long short‐term memory neural network–based lightweight predictive maintenance model is built for the predictive maintenance.