基于改进支持向量机的化学镀Ni-P/ZrO2复合镀层显微硬度预测模型的建立

Establishment of Prediction Model for Microhardness of Electroless Ni-P/ZrO2 Composite Coating Based on Improved Support Vector Machine

选取对化学镀Ni-P/ZrO2复合镀层的显微硬度具有代表性的影响因素作为输入变量,以正交试验获得的有限试验数据为样本,先建立基于传统支持向量机的预测模型,再采用遗传算法对传统支持向量机中的惩罚因子与核函数参数进行优化,最终建立基于改进支持向量机的预测模型。通过遗传算法进化迭代,提高改进支持向量机模型的预测精度。选取神经网络模型和传统支持向量机模型作为对比模型。结果表明:改进支持向量机模型的预测精度较高,可以利用该模型对化学镀Ni-P/ZrO2复合镀层的显微硬度进行预测。

The representative influencing factors on the microhardness of electroless Ni-P/ZrO2 composite coating were selected as input variable,and the limited experimental data obtained from orthogonal experiment were taken as samples. Firstly,the prediction model based on traditional support vector machine was established,and then the penalty factor and kernel function parameters in traditional support vector machine were optimized by genetic algorithm. Finally,the prediction model based on improved support vector machine was established. The prediction accuracy of improved support vector machine model was improved via genetic algorithm evolution iteration. Neural network model and traditional support vector machine model were selected as two comparison models,and the results showed that the improved support vector machine model has high prediction accuracy,and it can be used to predict the microhardness of electroless Ni-P/ZrO2 composite coating.