A new lot sentencing approach by variables inspection based on process yield

摘要

This study applies the concept of repetitive group sampling (RGS) to develop a new variables sampling plan for lot sentencing on the basis of process fraction nonconforming. The product acceptance determination problem is formulated as a nonlinear optimization problem where the objective function is to minimise the average sample number required for inspection, and the constraints are set by satisfying the acceptable quality level, limiting quality level, producer's risk and consumer's risk in the contract. The proposed lot sentencing approach's behaviour is examined and discussed. The results indicate that the performance of the proposed variables RGS plan is better than that of a conventional variables single sampling plan in terms of the required sample size for inspection. Thus, the proposed approach can help the practitioner efficiently make a decision to determine whether the submitted lots should be accepted.