Failure Prediction of Critical Electronic Systems (1999) [7 citations — 7 self]
Abstract:
ABSTRACT: 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.
Citations
| 8 | Reliability Engineering for Electronic Design – Fuqua - 1987 |
| 6 | A Roberts, Reliability and maintainability of electronic systems, Computer Science press – Arsenault, J - 1980 |
| 4 | Reliability Modeling and Optimization of Electronic circuits by Stressor-Susceptibility Analysis – Abraham - 1998 |
| 4 | A formulation of environmental stress testing and screening – H - 1994 |
| 2 | Reliability Analysis for Engineers – Leitch - 1995 |
| 1 | R T, Reliability Design Handbook, Reliability Analysis – Anderson - 1979 |
| 1 | Neural Network Enhancement for a Reliability Expert System – Rawicz, Girling - 1994 |
| 1 | 4 -3 -2 -1 Sampling Instants Leakage Current ( Amps) Actual Leakage Current Predicted Leakage Current Error (Actual - Predicted ) 10 George Vachtsevanos, A wavelet neural network framework for diagnostics of complex engineered systems – Jenson, Reliability, et al. - 1995 |
| 1 | D T O'Connor, Practical Reliability Engineering, 3 rd edn – Patrick - 1988 |
