A New Method for Dynamic Fault Diagnosis of Electric Appliance

A new method of fault diagnosis by dynamic modeling is put forward to obtain the diagnosis parameters of intelligent appliance in different running stages. The model identification approach using support vector regression (SVR) and immune clone selection algorithm (ICSA) is presented in this paper. The relation between process status and the temperature change rate is analyzed in the paper. For appliance fault with uncertainty, the way of fuzzy inference is applied for actualizing inference engine of fault diagnosis. Experimental results prove that the fault diagnosis method for intelligent appliance is credible in the accuracy.