Determining Optimal Reliability Targets Through Analysis of Product Validation Cost and Field Warranty Data
| dc.contributor.advisor | Sandborn, Peter A. | en_US |
| dc.contributor.author | Kleyner, Andre V. | en_US |
| dc.contributor.department | Mechanical Engineering | en_US |
| dc.contributor.publisher | Digital Repository at the University of Maryland | en_US |
| dc.contributor.publisher | University of Maryland (College Park, Md.) | en_US |
| dc.date.accessioned | 2006-02-04T06:55:39Z | |
| dc.date.available | 2006-02-04T06:55:39Z | |
| dc.date.issued | 2005-11-22 | en_US |
| dc.description.abstract | This work develops a new methodology to minimize the life cycle cost of a product using the decision variables controlled by a reliability/quality professional during a product development process. This methodology incorporates all product dependability-related activities into a comprehensive probabilistic cost model that enables minimization of the product's life cycle cost using the product dependability control variables. The primary model inputs include the cost of ownership of test equipment, forecasted cost of warranty returns, and environmental test parameters of a product validation program. Among these parameters, an emphasis is placed upon test duration and test sample size for durability related environmental tests. The warranty forecasting model is based on data mining of past warranty claims, parametric probabilistic analysis of the existing field data, and a piecewise application of several statistical distributions. The modeling process is complicated by insufficient knowledge about the relationship between product quality and product reliability. This can be attributed to the lack of studies establishing the effect of product validation activities on future field failures, overall lack of comprehensive field failure studies, and the market's dictation of warranty terms as opposed to warranties based on engineering rationale. As a result of these complicating factors an innovative approach to estimating the quality-reliability relationship using probabilistic methods and stochastic simulation has been developed. The overall cost model and its minimization are generated using a Monte Carlo method that accounts for the propagation of uncertainties from the model inputs and their parameters to the life cycle cost solution. This research provides reliability and quality professionals with a methodology to evaluate the efficiency of a product validation program from a life cycle cost point of view and identifies ways to improve the validation test flow by adjusting test durations, sample sizes, and equipment utilization. Solutions balance a rigorous theoretical treatment and practical applications and are specifically applied to the electronics industry. | en_US |
| dc.format.extent | 1198248 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | http://hdl.handle.net/1903/3107 | |
| dc.language.iso | en_US | |
| dc.subject.pqcontrolled | Engineering, Mechanical | en_US |
| dc.subject.pquncontrolled | Warranty | en_US |
| dc.subject.pquncontrolled | reliability | en_US |
| dc.subject.pquncontrolled | lifecycle cost | en_US |
| dc.subject.pquncontrolled | dependability | en_US |
| dc.subject.pquncontrolled | warranty forecasting | en_US |
| dc.title | Determining Optimal Reliability Targets Through Analysis of Product Validation Cost and Field Warranty Data | en_US |
| dc.type | Dissertation | en_US |
Files
Original bundle
1 - 1 of 1