الجزءالاول من الفصل ال 21من كتاب ASQ انتظرو الجزء الثانى اليوم 8 م ASQ Auditing Handbook 4th Edition J.P.Russell, editor Chapter 21/1 Process Variation 1. COMMON AND SPECIAL CAUSES (THEORY OF VARIATION) Variation is inherent; it exists in all things. No two entities in the world have exactly the same measurable characteristics. The variation might be small and unnoticeable without the aid of precise and discriminative measuring instruments, or it might be quite large and easily noticeable. Two entities might appear to have the same measurement because of the limitations of the measuring device. Factors Affecting Variation Everything is the result of some process, so the chance for some variation in out¬put is built into every process. Because material inputs are the outputs of some prior process, they are subject to variation, and that variation is transferred to the outputs. Variation will exist even in apparently identical processes using seemingly identical resources. Even though a task is defined and performed in the same manner repeatedly, different operators performing the same task and the same operator performing the same task repeatedly introduce variation. Precision and resolution of the measuring devices, and techniques used to collect data also introduce variation into the output data. Variation can result from changes in various factors, normally classified as follows: 1. People (worker) influences 2. Machinery influences 3. Environmental factors 4. Material influences 5. Measurement influences 6. Method influences The resulting total variation present in any product is a result of the variations from these six main sources. Because the ramifications of variation in quality are Taken from Russell T, Westcott, ed., The Certified Manager of Quality/Organizational Excellence Handbook (Milwaukee, WI: ASQ Quality Press, 2006), pp. 436-440. enormous for managers, knowing a processs capabilities prior to production provides for better utilization of resources. Operating costs are reduced when inspection, rework, safety stock storage, and troubleshooting are eliminated. Proper management requires a deep appreciation of the existence of variation as well as an understanding of its causes and how they can be corrected. Types of Variation Walter Shewhart, the father of modern quality control, was concerned with the low-cost reduction of variation. Shewhart distinguished two kinds of processes: (1) a stable process with inevitable chance variation and (2) an unstable process with assignable cause variation. If the limits of process variation are well within the band of customer tolerance (specification), then the product can be made and shipped with reasonable assurance that the customer will be satisfied. If the limits of process variation just match the band of customer tolerance, then the process should be monitored closely and adjusted when necessary to maximize the amount of satisfactory output. If the limits of process variation extend beyond the band of customer tolerance, output should be inspected to determine whether it meets customer requirements. When the amount of variation can be predicted with confidence, the process is said to be in a state of statistical control (stable). Although a singular value cannot be predicted exactly, it can be anticipated to fall within certain limits. Similarly, the long-term average value can be predicted. In an unstable process every batch of product is a source of excitement! It is impossible to predict how much, if any, of the product will fall within the band of customer tolerance. The costs necessary to produce satisfactory product are unknown because the organization is forced to carry large quantities of safety stock, and bids for new work must include a safety factor. Shewhart developed simple statistical and graphical tools to inform operators and managers about their processes and to detect promptly when a stable process becomes unstable and vice versa. These tools, called control charts, come in various forms to accommodate whether measures are attributes or variables, whether samples are of constant size or not. Deming also recognized Shewharts two sources of variation, calling them common causes and special causes. He also distinguished between the duties of those who work in the process and the managers who work on the process.
Posted on: Wed, 07 Jan 2015 07:00:01 +0000
Trending Topics
Recently Viewed Topics
© 2015