Connected Vehicle Diagnostics and Prognostics

• Published in: Prognostics and Health Management of Electronics pp. 479 - 501
• Main Authors: Zhang, Yilu, Du, Xinyu
• Format: Book Chapter
• Language: English
• Published: Chichester, UK Wiley 2018; John Wiley and Sons Ltd
• Edition: 1
• Series: Wiley - IEEE
• Subjects: automatic field data analyzer; connected vehicle diagnostics and prognostics; data collection subsystem; design enhancement suggestions; fault analysis; General Motors internal project; information abstraction subsystem; root cause analysis subsystem; vehicle batteries; Warranties; Support vector machines; Data analysis; Data collection; Batteries; Testing; Vehicles
• ISBN: 1119515335; 9781119515333
• DOI: 10.1002/9781119515326.ch17

This chapter describes a general framework, called an automatic field data analyzer (AFDA), as well as the related data analytic algorithms for connected vehicle diagnostics and prognostics (CVDP). The fault analysis results are provided to product development engineers with actionable design enhancement suggestions. A vehicle battery failure analysis on two years of data from 24 vehicles is performed to demonstrate the effectiveness of the proposed framework. An AFDA framework is developed that analyzes large volumes of on‐road vehicle data, automatically identifies root causes of faults, and eventually provides actionable design enhancement suggestions. The framework and algorithms for the proposed AFDA have been applied to the data collected through a General Motors (GM) internal project. The chapter explains a high‐level diagram of an AFDA. It consists of three parts, namely, the data collection subsystem, the information abstraction subsystem, and the root cause analysis subsystem.