中文摘要：

为了研究永磁同步直线电机结构参数优化中快速计算问题，提出一种基于组合核函数多输出支持向量机的电机非参数建模方法。通过分析各种核函数的性质，构造高阶多项式和低阶多项式核函数的组合，利用交叉验证的方法对惩罚参数C进行选择，建立永磁直线电机的多输出支持向量机模型。以U型永磁同步直线电机为对象进行仿真和实验，结果表明，利用该方法建立的模型较单一核函数模型，其计算精度有所提高，可达到94%以上，并且该模型的计算效率能够满足电机优化计算中大规模的计算问题。

英文摘要：

In order to solve the rapid computing problems of parameter optimization for the linear motor, a nonparametric modeling method was proposed based on the multiple output support vector machine （SVM）. The SVM model of the permanent magnet synchronous linear motor was established by the ker-nel function combination of the high/low-order polynomial kernel function where the penalty parameter was optimized by the cross validation algorithm. The simulation and experimental results carried out on the combined kernel function and support vector machine indicate that the computational efficiency and precision of the motor model meet the large-scale computing requirements in the motor structure optimiza-tion area.