论文部分内容阅读
控制系统性能估计的研究多数针对线性系统,但是非线性系统本质上更加复杂,用传统的方法进行估计存在局限性。对于一类可由非线性部分叠加线性干扰表示的非线性系统,首先分析了其反馈不变量的存在性,指出此类系统性能估计的关键在于构造超前预测模型。接着用最小二乘支持向量机辨识非线性模型,把最小方差性能估计问题转换成模型参数辨识问题,辨识参数的同时可得系统最小方差估计值。最后通过一个仿真实例把方法和前人所述方法进行了比较,仿真结果验证了方法的有效性。
Most of the studies on performance estimation of control systems are aimed at linear systems, but nonlinear systems are inherently more complex and there are limitations to using traditional methods to estimate them. For a class of nonlinear systems, which can be represented by non-linear part of linear disturbance, the existence of feedback invariant is first analyzed. The key to the performance estimation of such system is to construct the advanced prediction model. Then the least square support vector machine is used to identify the nonlinear model, the minimum variance performance estimation problem is transformed into the model parameter identification problem, and the minimum variance estimation value of the system can be obtained while identifying the parameters. Finally, a simulation example is used to compare the method with the previous one. The simulation results verify the effectiveness of the method.