This paper analyses the warranty claims data to identify faulty parts contributing to increasing failure using Weibull Analysis, in the automobile industry. Unlike studies in the past, this study uses 24 month service data to investigate the cause of failure due to faulty parts.Usually, the forecasting of the part failure is done for the 3 months in service (MIS) data and the automobile manufacturers use this parameter to set Key Performance Indicators (KPI) for quality improvement among design engineers. The KPI set using 3MIS data is used to determine 12 MIS and 24MIS KPIs. The period used in the development of KPIs affects the number of failed parts to be selected for improvement. As the monitoring period of countermeasure takes long durations, the repetitive failures added in data during the monitoring period, make the analysis complicated. Also, the seasonal pattern of failures cannot be addressed using 3MIS data. By increasing the analysis period to 24MIS, this paper finds evidence that increase in MIS leads to the identification of faulty parts that are causing repeated failures. The scope of the study extends towardsthe detection of new issues and towards monitoringthe effectiveness of existing countermeasures.This reduces warranty costs for the manufacturer and provides time to develop appropriate countermeasures along with increased monitoring period of failure parts leading to durability quality improvement
Maheshwar Pratap and Naveen Kumar K., “Identifying Durability Failure Parts using 24 Months-In-Service Data: A Case-Based Empirical Study from an Automobile Manufacturer in India”, International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 4, 2019.