Application of generalized linear models for optimizing production stress testing

Abstract

& CONCLUSIONSAccelerated environmental stress tests (EST) are applied during the manufacturing process to improve reliability by precipitating and detecting latent defects. This test represents an in-process manufacturing screen and the objective of performing it is to avoid early field failures that reduce the customer satisfaction level and increase warranty and compensation costs.Temperature cycling during EST is one of the most commonly used test procedures. Although it is an expensive and energy intensive procedure, usually a lengthy test is initially recommended for a new product. Based on the product test performance or a possible manufacturing process modification, the test duration and regime may be changed after some period. Even if the number of test cycles is reduced, EST continues to be an expensive test and a major process bottleneck.This paper uses Generalized Linear Modeling (GLM) to investigate the effects of the production and EST test variables on the population under test. Both the number of units rejected and the time to failure can be modeled as a regression function of covariates representative of the test environment. The field reliability function is written as a product of the unconditional reliability in each segment of the test profile such as dwell, ramp, etc. The next step is to apply the result of the temperature cycle EST GLM to a mathematical cost model. This cost model includes both the test cost and the warranty and compensation costs of the early field failures. The optimum test regime and number of cycles, which minimizes the total cost is determined by combining the GLM and the cost model. In this way the production test regime can be optimized in terms of field reliability/test cost trade-off. Notations T: Initial EST duration, i.e. 480 minutes τ : Optimum EST duration p t : p -quantile of the lifetime distribution 0 t : Failure time in EST C : Fixed cost of performing EST per unit V

Modeling and Adapting Production Environmental Stress Testing

“…This term did not originate here 5 and has been used before in slightly different forms. 6 The risk set consists of a subset of the population with weaknesses that have arisen from the manufacturing process.…”

“…10 In this model, the natural log of the failure count is linearly dependent on the covariates. In test section k, (7) where N k is the number of failures in section k, S k-1 is the number of survivors from section k-1, and D k is the length of section k. The other variables are defined as in equation 5.…”

Stress test optimization using an integrated production test and field reliability model

“…For different warranty policies, the reader is referred to References 25--29 . Honari et al 30 developed a method of optimizing the test time using field and test data. A piecewise regression model was applied by Joyce et al 31 to temperature cycling test in order to optimize the EST.…”

“…While the EST test database may include a column for a unit's serial number, the database of field failures or returns may have this information omitted for a significant portion of the units. In such circumstances, the technique proposed in Honari et al 30 , based on tracking individual units by their serial numbers, cannot be used. Of course it is still possible to develop separate regression models based on the production test and field return databases.…”

“…Honari et al 30 have previously described a methodology for developing an optimum test time when individual unit information is available on performance from test through to the field. One can compare the Comparison of optimum test termination times using the methodologies described in this paper and in Honari et al 30 methodology adopted in this paper to that of Honari et al 30 . By applying both techniques to the same set of production and field data, it is possible to validate the methodology proposed in this paper.…”