5 - Statistical methods applied to quality control

Abstract

This chapter discusses the statistical methods applied to quality control. There are a number of statistical methods and sampling procedures available now-a-days to assist the manufacturer in guaranteeing his product. These include probability function, failure rate, mean time between failures and probability testing. Probability function is expressed as a decimal or a percentage, and is an estimate of the chances of a particular device performing its mission. Failure rate is normally expressed in terms of the number of failures per unit of time. When calculating failure rates, it is important that age is taken into consideration, as the reliability of a product can vary quite a lot according to how old it is. Variations occur mainly in three stages: (1) during production—failure rates of new electronic equipment are usually much higher than normal because of production errors, defective parts, faulty installation, misalignment etc; (2) while in service—following a normal breakin period, failures becomes less frequent and tend to remain relatively constant throughout the useful life of the equipment; (3) near the end of normal life expectancy—when a product begins to wear out the failure rate tends to increase steadily.