DOD 3235.1-H (3RD Ed), TEST AND EVALUATION OF SYSTEM RELIABILITY, AVAILABILITY, AND MAINTAINABILITY (A PRIMER) (MAR 1982)

DOD 3235.1-H (3RD Ed), TEST AND EVALUATION OF SYSTEM RELIABILITY, AVAILABILITY, AND MAINTAINABILITY (A PRIMER) (MAR 1982)., This handbook is issued under the authority of DoD Instruction 3235.1, “Test and Evaluation of System Reliability, Availability, and Maintainability,” February 1, 1982. Its purpose is to provide instruction in the analytical assessment of System Reliability, Availability, and Maintainability (RAM) performance. One step in the acquisition of military weapon systems and equipment is the verification that the candidate systems do, in fact, perform in accordance with previously specified operational requirements. The verification process involves the design of test programs which provide an adequate data base to support realistic assessments of hardware characteristics. This text outlines the concepts and techniques to be used in structuring such test programs and analyzing the resulting data. Since verifying the performance of every hardware item to be procured is neither practical nor possible, we base our projection of the entire population’s performance on the assessment of an available sample. This sample may consist of the first 10 preproduction aircraft of a projected buy of 725 or 50 percent of a lot of high-reliability pyrotechnic devices. In either case, we are utilizing statistical techniques to project or estimate the true value of some population’s characteristic, such as reliability, maintainability, weight, size, etc. The material contained in the following chapters is designed to familiarize the reader with the various statistical concepts and techniques required to thoroughly understand the relationships among test design, assessment and projection of population characteristics. The beginning chapters present background material on the three basic quantitative system parameters: reliability, availability and maintainability. The various definitions of these basic terms are discussed, as are the relationships among these parameters. The statistical concepts of confidence and producer’s and consumer’s risk are next introduced, with the majority of the text devoted to the practical application and significance of these concepts. The chapters utilize a combination of narrative and case studies to introduce and illustrate the usefulness of the concepts. It will prove quite useful to refer to the case studies while reading through the chapters. This study technique will prove especially helpful in Chapters 7 and 8, which present information on analyzing test data and structuring statistically adequate test programs. Chapter 9 contains an introductory discussion of the reliability growth concept. Chapter 10 presents qualitative aspects of test planning along with a description of data collection requirements.