Exclusive Content & Downloads from ASQ

New Directions for Reliability

Summary: [This abstract is based on the author's abstract.]

Reliability theory used in the United States derives from Wald's sequential analysis developed before World War II. Most reliability test, demonstration, and estimation methods are based on this theory and motivated by Defense Department (DOD) procurement standards. The standards assume exponential distribution based on expectation of uniform failure rates at the system level, since this was the case in the 1950s when reliability theory was being developed. The increased use of high-quality solid-state devices and passive-electronic components results in failure rates that decline over time, however, with the instantaneous failure rate of these components resulting chiefly from manufacturing defects. As components accumulate operating life, the life expectancy improves, so solid-state components do not have the "bathtub curve" seen in older systems with mechanical and electromechanical devices. The appearance of flattening in the operating life period is noted when failure rate data are plotted on a uniform vertical scale against time. This is often an artifact of scaling. Using a logarithmic vertical scale, the failure rate drops indefinitely. The different concepts of older and new failure rate behavior account for discrepancies found between reliability estimates demanded by the DOD and actual results.

Anyone with a subscription, including Site and Enterprise members, can access this article.

Other Ways to Access content:

Join ASQ

Join ASQ as a Full member. Enjoy all the ASQ member benefits including access to many online articles.

  • Topics: Reliability
  • Keywords: Statistical methods,Reliability,Scale parameter,Quality improvement (QI),Reliability theory,Department of Defense (DOD)
  • Author: King, James R.
  • Journal: Quality Engineering