基于模糊系统的接触电阻预测算法研究

Study on the prediction algorithm of the contact resistance based on the fuzzy system

运用模糊系统对接触电阻进行预测,通过试验得到试验数据,将试验数据分成训练数据与测试数据,训练数据用于训练模糊系统,测试数据用于测试模糊系统。将梯度下降算法与禁忌搜索算法混合得到改进禁忌搜索算法,训练模糊系统,所用算法依次为梯度下降算法、禁忌搜索算法、所得改进算法,并建立相应的接触电阻回归模型。对所得模型进行测试,结果表明,由改进算法训练模糊系统所得接触电阻模型的测试结果优于其他模型,并且该方法预测接触电阻精确可靠。

The contact resistance is predicted by fuzzy system. The enough data are oment, and ai data are divitied into two parts, training data and testing data. The training data are used to train fuzzy system,and the testing data are used to test fuzzy system. New algoritlim is obtained by combining gradient descent algoritlim and tabu search algoritlim to train the fuzzy system. The training adient descent algoritlim, tabu search algoritlim and the new algoritlim. The regression models of contact resistance are founded. All models are tested, and the prediction effect of the model obtained from newalgorithm is best. The results show that tlie fuzzy system trained by new algoritlim is reliable and precise to predict the contact resistance.