Fault diagnosis of TE process based on ensemble improved binary-tree SVM

According to the characters of SVM, an improved binary-tree SVM is proposed for multi-class problems. Furthermore aiming at the initial problems about the choice of kernel function and parameters for SVM, an ensemble method is presented to establish ensemble SVM. Here the improved SVM is used as weak learning machine. The new ensemble SVM can improve the performance of single binary-tree SVM. At the end, the new method is used to fault diagnosis of TE process. The experiments demonstrate that the ensemble improved SVM can diagnose the fault efficiently.