Minimization of life cycle costs through optimization of the validation program - a test sample size and warranty cost approach

This paper presents a method for calculating desired reliability demonstration for a product validation process, based on life cycle cost minimization. The paper is written in the context of a high-volume production industry and has a specific application to automotive electronics. The proposed method suggests a way to optimize the target reliability based on minimization of the sum of validation cost and expected reliability-related warranty returns by analytically linking the product validation cost with the expected warranty. Validation cost can be related to a test sample size required for demonstration of a specified reliability with a pre-determined confidence level. Test sample size is in turn often linked to reliability demonstration in environmental tests targeted at durability, such as vibration, high-temperature endurance, and temperature cycling. Higher reliability is expected to reduce the cost of warranty returns, but at the same time to drive up the cost of product development. Thus an optimal solution is possible by finding a target reliability corresponding to the lowest value of the total expected life cycle cost. The methodology in this paper is developed and demonstrated using applications from automotive electronics industry with a case study based on data obtained from the real life warranty databases.