Intermittent Fault Modeling and RUL Prediction for Degraded Electrical Connectors in Vibration Environments.

Intermittent faults are very common problems in various kinds of electronic devices. This article is focused on the intermittent fault phenomenon in degraded electrical connectors in vibration environments. To analyze the intermittent faults in degraded electrical connectors, a micro-state contact model is constructed to simulate the resistance variation behavior in vibration environments. The relationship between the intermittent fault behavior and the degradation state is studied, and a health indicator parameter is extracted from the signals to act as a symptom for degradation. A test platform is built to collect the intermittent fault signals from electrical connectors at different degradation states in vibration environments. The degradation curve of the health indicator is used to predict the remaining useful life (RUL) of the electrical connectors. The method of extreme learning machine (ELM) is adopted to conduct the prediction of RUL. The genetic algorithm (GA) is used to optimize the weight and bias parameters in ELM. The results reflect that the intermittent fault characteristic is a proper degradation index in the prediction of RUL for degraded electrical connectors. [ABSTRACT FROM AUTHOR]