The casing treatment(CT)has the potential to extend the stable operating range of a compressor at the expense of the efficiency and pressure ratio.The paper applied data mining techniques to the optimization of casing treatment in a high pressure ratio centrifugal compressor,which can analyze the regular and mechanism of CT geometric structures on the performance of the compressor.With the structure parameters of casing treatment analyzed,the key parameters and final design space were obtained.Integrating Kriging meta model,genetic algorithm(GA),design of experiment(DOE)and numerical simulation based on data mining results,the multi-objective optimization method of CT was built.Maximizing isentropic efficiency at design and near stall condition was carried out in the optimization.The optimization results indicated a considerable improvement in the total pressure ratio and isentropic efficiency of the compressor over the whole operating condition.And isentropic efficiency increased by 2.05%,and the stall margin increased by 7.11%.The mechanism behind the performance improvement was further extracted by combining the geometry changes with detailed flow analysis.