Blast Furnace Hanging Diagnosis Model Based On ReliefF-Decision Tree

Abstract

Blast furnace hanging is an abnormal furnace condition with the highest frequency. The judgment of hanging mainly relies on manual analysis, but this approach has strong subjectivity and time lag. In order to solve the above problems, this paper proposes a ReliefF - Decision Tree based anomaly diagnosis model to identify the hanging. Firstly, 10 relevant parameters are extracted based on expert experience, and each characteristic parameter is weighted using ReliefF algorithm after preprocessing. Secondly, the calculated weights of the characteristic parameters are sorted from the largest to the smallest, and the seven most effective characteristic parameter sets are selected as the decision nodes of the decision tree, which is constructed according to the expert rules of hanging diagnosis to complete the training and testing of the classifier. Simulation results show that the accuracy of the ReliefF - Decision Tree model reaches 96.5%, and the recognition rate of the two anomalies of “burden stop” and “sudden rise of differential pressure” exceeds 80%, which is 83.1% and 87.5%, respectively, indicating that the performance of the model is good. Finally, the expert diagnosis system is built, which effectively improves the diagnosis efficiency of hanging.