The processing parameters have a particularly significant impact on the quality and efficiency of processing. Selecting the correct processing parameters can greatly improve the processing performance of the machine tool. To this end, by improving the chromosome structure and genetic operators of the GA algorithm, a new GA-BP neural network algorithm is proposed and combined BP neural network method for adaptive crossover and mutation probability optimization. Then, through comparison experiments. After selecting a certain type of CNC EDM machine, find its standard process parameter table and select 50 groups of data as preparation. 30 groups of data are randomly sampled from the inside to serve as training sample data, and the remaining 20 groups serve as performance test samples. Experimental results show that the prediction accuracy of the new algorithm is higher than that of the conventional algorithm, pulse width or peak current. The new prediction results are often closer to the true value, and the prediction accuracy is higher, which can better meet the processing requirements.

加工参数对加工质量和效率的影响尤为显着。选择正确的加工参数可以大大提高机床的加工性能。为此，通过改进GA算法的染色体结构和遗传算子，提出了一种新的GA-BP神经网络算法，并结合BP神经网络方法进行自适应交叉和变异概率优化。然后，通过对比实验。选择某款数控电火花加工机床后，找到其标准工艺参数表，选取50组数据作为准备。从内部随机抽取30组数据作为训练样本数据，其余20组作为性能测试样本。实验结果表明，新算法的预测精度高于传统算法，脉冲宽度或峰值电流。新的预测结果往往更接近真实值，预测精度更高，更能满足加工要求。