Development of a multiattribute synthetic-np chart

Over the last few decades, multiattribute control charts have been widely recommended in practice. They outperform the simultaneous uniattribute charts for monitoring multiattribute processes in many applications. Jolayemi [A statistical model for the design of multiattribute control charts. Indian J Stat. 1999;61:351–365] developed a statistical model for the design of a multiattribute np (Mnp) chart. Based on this model, a multiattribute synthetic (MSyn) chart is proposed in this article. Furthermore, the main features of the MSyn chart and Mnp chart are integrated to build a multiattribute Syn-np (MSyn-np) chart. The results of the comparative studies indicate that the new MSyn-np chart significantly outperforms the Mnp chart and MSyn chart by 83% and 27%, respectively, in terms of the average number of defectives over a wide range of process shifts under different circumstances.     

Development of supplier relationship including cost of defectives in the cyclic production

In the supply chain situation, a decision regarding supplier relationship is of high importance. This usually happens on the basis of supplier company parameters. In order to satisfy the demands, a buyer company often expects the supplier company to expedite their operations, i.e., to enhance the related production rate. In this context, presently the focus of this article is on the cyclic production environment at the supplier company premises. Any practical production process is expected to generate defective products also along with the normal usable products. After an estimation of this and the costs concerning defectives, it needs to be modelled in the cyclic manufacturing. This article incorporates specifically the cost of defectives along with the other relevant costs. After developing an interest in the inclusion of these costs, the supplier company is categorised. A contribution of this article is the development of supplier relationship in the discussed environment.     

A computer program for the design of group testing experiments

This paper describes a computer program GTEST for designing group testing experiments for classifying each member of a population of items as “good” or “defective”. The outcome of a test on a group of items is either “negative” (if all items in the group are good) or “positive” (if at least one of the items is defective, but it is not known which). GTEST is based on a Bayesian approach. At each stage, it attempts to maximize (nearly) the expected reduction in the “entropy”, which is a quantitative measure of the amount of uncertainty about the state of the items. The user controls the procedure through specification of the prior probabilities of being defective, restrictions on the construction of the test group, and priorities that are assigned to the items. The nominal prior probabilities can be modified adaptively, to reduce the sensitivity of the procedure to the proportion of defectives in the population.     

Developing a variables two-plan sampling system for product acceptance determination

In this paper, a variables tightened-normal-tightened (TNT) two-plan sampling system based on the widely used capability index C_pk is developed for product acceptance determination when the quality characteristic of products has two-sided specification limits and follows a normal distribution. The operating procedure and operating characteristic (OC) function of the variables TNT two-plan sampling system, and the conditions for solving plan parameters are provided. The behavior of OC curves for the variables TNT sampling system under various parameters is also studied, and compared with the variables single tightened inspection plan and single normal inspection plan.     

Critical acceptance values and sample sizes of a variables sampling plan for very low fraction of defectives

Acceptance sampling plans are practical tools for quality control applications, which involve quality contracting on product orders between the vendor and the buyer. Those sampling plans provide the vendor and the buyer rules for lot sentencing while meeting their preset requirements on product quality. In this paper, we introduce a variables sampling plan for unilateral processes based on the one-sided process capability indices _CPU$C_{\mathrm{PU}}$ (or _CPL)$C_{\mathrm{PL}})$, to deal with lot sentencing problem with very low fraction of defectives. The proposed new sampling plan is developed based on the exact sampling distribution rather than approximation. Practitioners can use the proposed sampling plan to determine accurate number of product items to be inspected and the corresponding critical acceptance value, to make reliable decisions. We also tabulate the required sample size n$n$ and the corresponding critical acceptance value _C0$C_0$ for various α$\alpha$-risks, β$\beta$-risks, and the levels of lot or process fraction of defectives that correspond to acceptable and rejecting quality levels.     

Detecting the two complementary defectives with a balance scale

We consider the problem of finding a pair of irregular boxes from a set of n boxes using a balance scale. One irregular box is heavier and the other lighter than a regular box but the total weight of the two irregular boxes is the same as the total weight of two regular boxes. Let N(w) denote the maximum number of boxes w weighings can handle. We give a weighing scheme such that N(2t) ≥3^t for t ≥2 and N(2t + 1) ≥ 5.3^t-1 for t ≥ 1. The N(2t) result meets the information-theoretic bound and hence is the best possible.