The Experimental Determination of Guided Missile Reliability

If the number of different environmental stresses to which guided missile components and systems are exposed were limited to one or two, suitable experimental design would make laboratory determination of their reliability feasible. In view of the fact, however, that a missile is exposed to a complex of different stresses, there is no practical way in which reliability evaluation can be accomplished through test procedures. On the other hand, it is quite possible to obtain useful estimates of the reliability of the whole missile from the results of a flight-test program. Since this technique will come close to duplicating the environmental stress encountered in tactical flight, a simple ratio of successful flights to total flights will itself yield considerable information. This figure can be refined through the use of moving averages, and reliability estimates can be further validated by presenting the results in terms of confidence belts instead of point estimates.

Operations Research, ISSN 0030-364X, was published as Journal of the Operations Research Society of America from 1952 to 1955 under ISSN 0096-3984.