Researches on New Fault Diagnosis Method for Process Industry Based on Improved SVM Reduction Algorithm

摘要

Once faults happened in the process industry, it will bring on heavy casualties and fatal property losses, even lead to irreclaimable pollution. Combining the large-scale sample set reduction strategy with SVM, this paper proposed a new improved support vector machine (SVM) training algorithm based on support vectors to solve the difficulty of fault diagnosis of process industry. A new reduction algorithm is presented to reduce large-scale sample set. The constraint threshold is introduced in the new algorithm. The new training algorithm can eliminate the samples correspond to non-support vectors so that poor generation ability caused by large-scale training sample set is solved. A new evaluating indicator of large-scale sample set reduction strategy is also proposed in this paper. The improved SVM algorithm proposed is applied to two typical fault diagnosis of process industry. The results of experiments show that the improved SVM algorithm not only reduces greatly the cost of SVM learning but also markedly increases the speed of classification, and at one time the accuracy of fault diagnosis is not debased.