论文部分内容阅读
牵引电机的磁化曲线是直流牵引电机准确建模及性能分析的基础,以电力机车为例,介绍了利用最小二乘支持向量机对牵引电机磁化曲线进行拟合,从而建立准确的直流牵引电机模型的方法。分析了牵引电机磁路非线性的特性,运用最小二乘支持向量机的回归理论,通过对牵引电机实验所得的磁化曲线数据进行学习,建立了基于LS-SVM的曲线拟合模型。拟合结果表明,该模型比以往的分段线性化和神经网络拟合的速度及精度都有较大的提高,在小样本情况下有更好的泛化能力,为牵引电机建立非线性模型提供了新的参考。在LS-SVM拟合曲线的基础上建立了直流牵引电机仿真模型,仿真结果表明,该模型准确可靠,可用于对直流牵引电机系统性能及控制策略的研究。
The magnetization curve of traction motor is the basis of accurate modeling and performance analysis of DC traction motor. Taking the electric locomotive as an example, the least square support vector machine (LS-SVM) is introduced to fit the magnetization curve of traction motor so as to establish an accurate DC traction motor model Methods. The characteristics of the nonlinearity of traction motor magnetic circuit are analyzed. By using the regression theory of least square support vector machine, the curve fitting model based on LS-SVM is established by learning the magnetization curve data obtained from the traction motor experiment. The fitting results show that the model has a higher speed and accuracy than the previous piecewise linearization and neural network fitting, and has better generalization ability in the case of small samples, and establishes a nonlinear model for the traction motor Provided a new reference. The simulation model of DC traction motor is established on the basis of LS-SVM fitting curve. The simulation results show that the model is accurate and reliable and can be used to study the performance and control strategy of DC traction motor.