Failure Prediction of Critical Electronic Systems in Power Plants Using Artificial Neural Networks

This paper presents an Artificial Neural Network (ANN) model for failure prediction of critical electronic systems in power plants. Reliability modeling of electronic circuits can be best performed by the stressor – susceptibility interaction model. A circuit or a system is deemed to be failed once the stressor has exceeded the susceptibility limits. For on-line prediction, validated stressor vectors may be obtained by direct measurements or sensors which after preprocessing and standardization is fed into the ANN. ANN is trained using the stressor sets obtained using Monte Carlo Analysis (MCA) and is then combined with the susceptibility limits for failure prediction of the circuit or system. The ANN reads the incoming stressor set and recalls the trained pattern and predicts the result. The performance of the proposed method of prediction is evaluated by comparing the experimental results with the actual failure model values.