针对最小二乘支持向量机(LS-SVM)的稀疏性损失和鲁棒性下降等缺陷,提出了一种改进的LS-SVM算法。利用改进LS-SVM,设计了一个某型飞机平尾液压舵机双闭环控制系统的故障诊断系统。充分利用系统的可测参量,建立了基于改进LS-SVM的平尾液压舵机的全局故障检测模型和局部故障检测模型。仿真结果验证了该方法的有效性。
An improved least squares support vector machines (LS-SVM) was proposed to improve the sparse and robust performance of LS-SVM. By using improved LS-SVM, a fault diagnosis system was designed for hydraulic actuator double closed-loop control system of one aircraft's horizontal tail. The total fault diagnosis model and the partial fault diagnosis model of hydraulic actuator were established based on modified LS-SVM by using the systemic parameters which could be measured. The simulation results show that the method mentioned above is valid.