To read this content please select one of the options below:

An integrated data-driven framework for vehicle quality analysis based on maintenance record mining and Bayesian network

Aoxiang Cheng (University of Michigan – Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, China)
Youyi Bi (University of Michigan – Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, China)

International Journal of Quality & Reliability Management

ISSN: 0265-671X

Article publication date: 21 May 2024

57

Abstract

Purpose

The purpose of this paper is to present an integrated data-driven framework for processing and analyzing large-scale vehicle maintenance records to get more comprehensive understanding on vehicle quality.

Design/methodology/approach

We propose a framework for vehicle quality analysis based on maintenance record mining and Bayesian Network. It includes the development of a comprehensive dictionary for efficient classification of maintenance items, and the establishment of a Bayesian Network model for vehicle quality evaluation. The vehicle design parameters, price and performance of functional systems are modeled as node variables in the Bayesian Network. Bayesian Network reasoning is then used to analyze the influence of these nodes on vehicle quality and their respective importance.

Findings

A case study using the maintenance records of 74 sport utility vehicle (SUV) models is presented to demonstrate the validity of the proposed framework. Our results reveal that factors such as vehicle size, chassis issues and engine displacement, can affect the chance of vehicle failures and accidents. The influence of factors such as price and performance of engine and chassis show explicit regional differences.

Originality/value

Previous research usually focuses on limited maintenance records from a single vehicle producer, while our proposed framework enables efficient and systematic processing of larger-scale maintenance records for vehicle quality analysis, which can support auto companies, consumers and regulators to make better decisions in purchase choice-making, vehicle design and market regulation.

Keywords

Acknowledgements

The authors would like to acknowledge the financial support from the National Natural Science Foundation of China (52005328) and Shanghai Science and Technology Commission “Yangfan” Program (20YF1419300). The authors would also like to acknowledge the technical support from Mengyuan Shen and Bohan Feng.

Citation

Cheng, A. and Bi, Y. (2024), "An integrated data-driven framework for vehicle quality analysis based on maintenance record mining and Bayesian network", International Journal of Quality & Reliability Management, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/IJQRM-03-2023-0114

Publisher

:

Emerald Publishing Limited

Copyright © 2024, Emerald Publishing Limited

Related articles