Field reliability modeling based on two-dimensional warranty data with censoring times

ABSTRACT

Warranty data can be used for estimating product reliability, identifying causes of failure and designing warranty policy. Based on two-dimensional warranty data, we utilize an accelerated failure time model to investigate the effect of usage rate on product degradation. The stochastic expectation-maximization algorithm is proposed to estimate parameters of the reliability model considering both censored data and field data. Extensive simulation studies are used to validate the proposed method and to compare it with the maximum likelihood method. The utilities of the results have been demonstrated through real warranty data collected from an automobile manufacturer in China.

KEYWORDS:

• field reliability
• maximum likelihood method
• stochastic expectation-maximization algorithm
• usage rate
• warranty data analysis

About the authors

Anshu Dai is a Ph.D. candidate in the College of Management and Economics at Tianjin University, China. She received her B.S. degree in industrial engineering from Tianjin Polytechnic University, Tianjin, China. Her research interests include warranty data analysis and warranty policy design.

Zhen He is currently an academician of International Academy for Quality and a distinguished professor in College of Management and Economics at Tianjin University, China. He received the B.S., M.S., and Ph.D. degrees from Tianjin University, Tianjin, China, 1988, 1991, and 2000, respectively. His current research interests include warranty management, statistical process controls, design of experiments, and lean six sigma.

Zixian Liu is a professor in the College of Management and Economics at Tianjin University, China. He received his Ph.D. degree from Tianjin University, China. His research interests include warranty policy design, lean production, and hospital management.

Duo Yang is currently a Ph.D. candidate in the College of Management and Economics at Tianjin University, China. His research interests include warranty data analysis and maintenance service.

Shuguang He is a professor in College of Management and Economics at Tianjin University, China. He received his Ph.D. degree from Tianjin University, China. His research interests include statistical process controls, information management, and warranty data analysis.

Acknowledgment

The author would like to thank the reviewers for their constructive comments on the earlier version of the article.

Funding

This work is supported by National Science Foundation of China (NSFC) under Grant No. 71532008, 71225006, 71472132, and 71661147003.