Economic Quality Control of Manufactured Product¹

Abstract

That we cannot make all pieces of a given kind of product identically alike is accepted as a general truth. It follows that the qualities of pieces of the same kind of product differ among themselves, or, in other words, the quality of product must be expected to vary. The causes of this variability are, in general, unknown.The present paper presents a scientific basis for determining when we have gone as far as it is economically feasible to go in eliminating these unknown or chance causes of variability in the quality of a product. When this state has been reached, the product is said to be COl/trolled because it is then possible to set up limits within which the quality may be expected to remain in the future. By securing control, we attain the five economic advantages discussed in Part II r.I I "TRODUCTIO" What is the Problem of Control?W H AT is the problem involved in the control of quality of manu, factured product? To answer this question, let us put ourselves in the position of a manufacturer turning out millions of the same kind of thing every year. Whether it be lead pencils, chewing gum, bars of soap, telephones or automobiles, the problem is much the same. He sets up a standard for the quality of his product and then tries to make all pieces of product conform with this standard. Here his troubles begin. For him standard quality is a bull's-eye, but like a marksman shooting at such a target, he often misses. As is the case in everything we do, unknown or chance causes exert their influence. The problem then is: how much may the quality of a product vary and yet be controlled? In other words, how much variation should we leave to chance?To make a thing the way we want to make it is one popular conception of control. We have been trying to do this for a good many years and we see the fruition of this effort in the marvelous industrial development around us. \Ve have accepted the idea of applying scientific principles but now a change is coming about in the principles themselves which necessitates a new concept of control.A few years ago we were inclined to look forward to the time when a manufacturer would be able to do just what he wanted to do. We shared the enthusiasm of Pope when he said" All chance is but direction thou canst not see," and we looked forward to the time when we would see that direction. I n other words, emphasis was laid 011 the exactness

Evaluating Statistical Methods for Syndromic Surveillance

“…Walter A. Shewhart [She31] developed the concept of the control chart, a graphical statistical tool to help control the behavior of manufacturing processes, and in so doing became one of the founders of the quality control movement. Shewhart's methodology defined a scientific, statistical framework upon which to base decision-making and hence allow objective decisions to be made about how to manage systems.…”

“…Shewhart's algorithm [She31] is probably the simplest and best known of all SPC methods and is widely applied in industry. The basic idea is to sequentially evaluate one observation (or period) at a time, alarming when an observation that is rare under f 0 occurs.…”

Modelling for Designing, Managing and Improving Virtual Enterprises in One-of-a-kind Business

“…In the value generation view, the basic thrust is to reach the best possible value from the perspective of the customer. The value generation view was initiated by Shewhart [21] and further refined in the framework of the quality movement but also in other circles. Principles related to rigorous requirements analysis and systematized flowdown of requirements, for example, are put forward.…”

Bayesian Switching Multiple Disorder Problems

“…Such quickest disorder, or change-point, detection problems have originally arisen and still play a prominent role in quality control, where one observes the output of a production line and wishes to detect deviations from the acceptable levels. After the introduction of the original control charts by Shewhart [34], various modifications of the disorder problem have been recognised (see, e.g. Page [27]) and implemented in a number of applied sciences (see, e.g.…”