多输出支持向量机混合模型在机车调簧中的应用

Application of Multi-Output Support Vector Regression Hybrid Model in Locomotive Secondary Spring Loads Adjustment

机车二系弹簧加垫高度对二系载荷分布有着显著影响.考虑到车体和弹簧有着不容忽略的非线性特性,提出在机理模型基础上引入多输出支持向量回归机作为补偿算子,构建二系弹簧载荷调整的混合模型用于指导调簧.为提高补偿精度,用遗传算法对补偿算子的参数进行全局优化搜索,得到一组最优参数;同时引入均匀设计试验法采集样本数据,减少采样时间.用HX_D1D型大功率机车的实车数据进行试验,本研究提出的混合模型较BP网络混合模型、机理模型具有更小的均方根误差.试验结果表明:本研究提出的混合模型预测的二系载荷与实际载荷间的均方根误差较机理模型减小33.53%,较BP网络混合模型减小23.69%,可进一步提高调簧模型精度,同时计算用时也较BP网络混合模型大为减少.

The locomotive loads distribution is dramatically influenced by the shims added to those springs. Considering the non-negligible nonlinear characteristics among locomotive bodies and secondary springs, a hybrid model is proposed by utilizing multi-output support vector regiession as a compensation operator for the m<M hanism model. To improve tlie accuracy of compensation and obtain a set of optimal parameters, the genetic algorithm is used to globally optimize the parameters of the compensation operator. At the same time, the unifoirri design method is adopted to arrange the sampling scheme to reduce the sampling time. The proposed hybrid model is evaluated with the testing data set of a HXD1D high-power locomotive. The proposed model outperforms the mechanism model and the BP network hybrid model with respect to the root mean square en*or ( RMSE ). An experimental result shows that the RMSE is reduced by 33. 53% in comparison with the mechanism model and 23. 69% less than that of the BP network model, which can further improve the accuracy of locomotive loads adjustment model. At the same time, the computation time of the proposed model is much less tlian that of the BP network hybrid model.