Fault diagnosis system using case-based reasoning and neural networks for coke oven heating process

For reducing the fault ratio of coke oven heating process, based on the analysis of the fault mechanism and combination of case-based reasoning (CBR) and neural networks, an intelligent fault diagnosis method is proposed for the coke oven heating process. The prediction model of the process variables based on neural networks performs to predict key technical parameters as the fault symptoms that is hard to measure online. The probability of the typical fault and their operation guidance with the help of case-based reasoning technology is obtained. The proposed fault diagnosis system is successfully applied to the coke oven heating process, the fault ratios during production process is decreased, and the proved benefit is achieved.