A hybrid ARIMA–WNN approach to model vehicle operating behavior and detect unhealthy states

作者：

Highlights：

• Develop ARIMA–WNN based time-series approach to model vehicle operating.

• Develop threshold-based anomaly detection strategy to timely recognize the unhealthy states of the vehicle.

• Use large scale vehicle operating time series data set to validate proposed approach.

摘要

•Develop ARIMA–WNN based time-series approach to model vehicle operating.•Develop threshold-based anomaly detection strategy to timely recognize the unhealthy states of the vehicle.•Use large scale vehicle operating time series data set to validate proposed approach.

论文关键词：Vehicle operating multiple time series,Unhealthy state detection,Hybrid ARIMA–WNN,Auto-Regressive Integrated Moving Average,Wavelet neural network

论文评审过程：Received 18 January 2021, Revised 26 September 2021, Accepted 5 January 2022, Available online 22 January 2022, Version of Record 29 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116515