Mapping Reliability Predictors of Low-Voltage Metal Oxide Surge Arresters Using Contour Plots

Abstract

Reliability assessment of MOSA devices requires accurate estimation of life distribution parameters or reliability predictors. Estimated reliability predictors consist of reasonable indicators of failure probability and mean life trends as a result of applied stress over a given period of time. Recent literature suggests finite-value or point-based estimation approach of reliability predictors in the context of continuously-applied distorted voltage stress to MOSA devices. However, this technique is prone to inaccuracies, and may not effectively reflect the impact of applied stress on reliability predictors. In this work, the use of contour plots is proposed as an alternative method for discrete mapping of estimated reliability predictors. Therefore, accelerated life tests - consisting of constant electro-thermal stress of: 85% of the reference voltage with and without harmonics, at the temperature of 135 °C for the time-period of 96 hours - are conducted on a set of low-voltage MOSA sourced from different manufacturers. The experimentally obtained times to failure are consistent with the two-parameter Weibull life distribution. The log-likelihood estimates on the Weibull probability density function are invoked using computational algorithms which yield the contour plots. These plots depict the reliability predictor mappings in the αβ plane. Results show that harmonic content in the applied stress causes extended peak amplitude which represents the point of highest probability of reduced reliability, and thus the highest accuracy point for the estimated shape parameter.

Keywords

• Metal oxide surge arresters
• contour plots
• accelerated life tests
• reliability predictors
• Weibull distribution
• probability density function