In traditional polishing process, polishing parameters are usually set a constant value according to the surface of workpiece. But if the surface of the workpiece is not uniform, the constant polishing parameters will not be polished in the area with large material removal, which will reduce the polishing efficiency and affect the quality of the processing surface. Therefore, a polishing algorithm which deal with this problem using neural network (NNW) and genetic algorithm (GA) is proposed. The NNW is used to predict the polishing performance parameters corresponding to a certain polishing parameters. A training neural network model is used to output 〖JP2〗the objective function including the desired material removal and the surface roughness improvement. In addition, the GA is employed to optimize the polishing parameters. The effectiveness of the proposed algorithm is verified through experiments of polishing uneven surface.