Remaining useful life prediction combining temporal convolutional network with nonlinear target function

作者：Bin Liu, Jing Xu, Chaoli Sun, Xueying Cui, Xiufeng Xie, Hongying Zhi · 发表于：Measurement Science and Technology · 年份：2022 · DOI：10.1088/1361-6501/aca8c2 · 被引用次数：7 · 研究领域：Machine Fault Diagnosis Techniques、Reliability and Maintenance Optimization、Non-Destructive Testing Techniques

Abstract Remaining useful life prediction based on degraded data is the premise of intelligent maintenance of equipment. Since the degradation process is usually complex and changeable, the general deep learning prediction method brings a large prediction deviation since it uses linear target function. In this paper, temporal convolutional network combined with a nonlinear target function (NT-TCN) is proposed to improve the prediction accuracy. The nonlinear target function is constructed using a piecewise function to label degraded data. By means of dilated causal convolution and Mish activation function, the NT-TCN learns the time series characteristics of degeneration. Thus, high precision of life prediction is achieved. By analyzing NASA’s C-MAPSS data set, the prediction results show that the NT-TCN model has lower root mean squared error and evaluation score than the neural network model with the linear target function, which is also superior to some existing prediction methods.