Adaptive two-class C-Support Vector Machine algorithm for turbopump fault detection

Research on turbopump fault detection is significance in engine health monitoring. Support Vector Machine (SVM) is a novel machine learning method, and we can use it in turbopump fault detection to solve the problems such as small sample and nonlinear problems. In this paper, we established a kind of adaptive two-class C-Support Vector Machine (C-SVM) algorithm for fault detection based on original C-SVM algorithm, and described the main parts of the algorithm such as fault feature extraction, kernel function choosing and classifier real-time updating in detail. At last we compared the algorithm with original C-SVM algorithm by the tests of false alarm, missing alarm and computing speed. The test results showed that the adaptive two-class C-SVM algorithm has lower false alarm rate, lower missing alarm rate and lower computing speed.