Based On Rough Set And Least Squares Support Vector Machine Smelting Furnace Fault Diagnosis Method

Imperial Smelting Furnace (ISF) is one of the major equipments in Pb-Zn smelting process, whose stability plays an important role in the smelting process. Therefore keeping the ISF situation stability, diagnosing and eliminating the fault in time is significant to guarantee the smelting process stable and enhance economic efficiency.Based on analyzing the technical process and faults mechanism of the ISP (imperial smelting process), and obtaining fault information from process data, the Rough Set(RS) is applied in data reduced and rules generated for the data information content and redundant information is large in ISP. Firstly, The attribute reduction method based on genetic algorithm with dependability and heuristic attribute value reduction use to remove the redundant information, and then mixed strategy method is used to extract diagnosis rules, finally the fault of ISF is diagnosed. The example proves that this method has a certain diagnosis.Against the fault tolerance of RS in fault diagnosis, the fault diagnosis method based on RS and LS_SVM(Least Squares Support Vector Machine) is studied. Firstly, the fault information is reduced and the fault rule is generated on RS. Then the information is diagnosed by LS_SVM. This method, not only fully develops the reduction ability of RS and the high fault-tolerance ability of SVM, but also gets over the limitations of LS_SVM which is the poor ability to determine the redundancy or usefulness of the knowledge, and effectively decreases the input information of LS_SVM, makes up the defect of RS which is the sensitivity for noise of input information, accordingly improves the accuracy of fault diagnosis. It turns out that the method proposed in this thesis used in fault diagnosis of ISF is high effective.