Fault diagnosis of electric porcelain firing kiln process based on random forest and XGBoost

In order to improve the efficiency of electric porcelain firing kiln process fault diagnosis, a random forest and XGBoost-based electric porcelain firing kiln process fault diagnosis method is proposed.A random forest-based feature selection algorithm was first applied to reduce the dimensionality of the fault data, and then the XGBoost algorithm was used to diagnose the firing kiln process faults. Compared with the diagnosis results of traditional classifiers (SVM, KNN and BP), the results showed that XGBoost outperformed the above mentioned algorithms in the diagnosis rate of firing kiln process faults.