Inference on an Adaptive Accelerated Life Test with Application to Smart-Grid Data-Acquisition-Devices

摘要: An accelerated life test (ALT) is often well planned to yield the most statistical information given limited resources. Nevertheless, ALT planning requires rough estimates of model parameters as an input, called values. The discrepancy between values and true may result in insufficient or even no failures at low-stress level, making subsequent data analysis difficult. Motivated by need ALTs acquisition devices used smart grids, adaptive scheme proposed. key idea based on observation that, when product reliability underestimated during design phase, it unlikely observe early stage test. Therefore, level should be elevated protect against failures. Under this framework, order statistics techniques are derive likelihood function assuming a general log-location-scale distribution for lifetime. Confidence intervals constructed large-sample approximation bootstrap method. A simulation study conducted demonstrate advantages compared with simple constant-stress ALT. Its application illustrated using motivating example from grids.