Defect Diagnostics of Gas Turbine Engine Using Hybrid SVM-ANN with Module System in Off-Design Condition

초록

In this study, artificial neural network (ANN) and support vector machine (SVM) has been used for engine health monitoring. A large number of nonlinear data are required for defect diagnosis of aircraft gas turbine engine in the various operation regions. The weak point of the ANN is that it is easy to fall in local minima when it learns too much nonlinear data. Accordingly, the classification ratio of defect diagnostic algorithm must be low. The SVM has been proposed for decreasing the number of nonlinear learning data. In off-design condition, the operation region of the engine is wide and the nonlinearity of learning data increases considerably. So, the module system, dividing the while operating region into reasonably small-size sections, has been suggested to solve this problem. The proposed algorithm has diagnosed the defects of triple components as well as single and dual components of the gas turbine engine in off-design condition.