采用遗传相关向量机的工业机器人焊缝跟踪预测

Weld tracking prediction of industrial robot based on G-RVM

为了克服传统焊缝跟踪方法精度低的问题,提出基于遗传相关向量机(G-RVM)的工业机器人焊缝跟踪预测方法,其中应用遗传算法对相关向量机参数进行优化。相关向量机通过构建回归函数以解决焊缝跟踪问题。为验证所设计控制器的有效性,进行了焊缝的跟踪实验,并设计了实验条件。实验结果表明,基于遗传相关向量机的焊缝跟踪误差小于支持向量机法所得数据。可见采用遗传相关向量机的控制更能够适应实际焊接过程的变化。

In order to solve the problem of low forecasting accuracy of traditional weld tracking methods, G-RVM is applied to weld tracking in. Firstly, the principle of weld tracking based on G-RVM is presented, where the parameters of relevance vector regression model is obtained by Genetic Algorithm （ GA ） and training data. In order to testify the effectiveness of the proposed controller, the experiment on weld tracking is performed, and the experimental conditions are designed. The experimental results show that the prediction error of G-RVM is lower than that of support vector machine. Thus, weld tracking based on G-RVM is more suitable for the change of welding process.