Monotone restriction model of large-scale complex product reliability evaluation

The development of large-scale complex product is a long time process, and the trial cost is high. Therefore, the test data of these products usually presents small sample and multiphase characteristic. To reduce the evaluation error caused by small sample of one phase, a constraint condition, which is the products' reliability increases monotonously, was introduced to products reliability evaluation, thus the multi-phase test data can be used for the reliability evaluation. Reliability of product usually increases during the development process, therefore, this method has comprehensive applicability. Under such constraint condition, the reliability parameter was considered as a random variable and the reliability parameter distribution function was given first. Then an approximate calculation method for mission reliability and MTBF was presented. Finally, take an aircraft engine for example to compare the result obtained from single phase test data with that based on multi-phase test data. Since the constraint condition is brief and the reliability parameter distribution function can be achieved, this method is more applicable for engineering than traditional AMSAA-Model, and it can gain the reliability interval estimation which can't be obtained from Duane-Model.