首页|在线优化参数的无模型预测神经网络自抗扰控制

在线优化参数的无模型预测神经网络自抗扰控制

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
关于难以建模的非线性系统的控制问题，提出具有辅助变量的全格式动态线性化方法逼近非线性系统模型，基于其构建系统的预测模型，给出采用直接极小化指标函数自适应优化算法的参数估计算法，在扩张状态观测器中引入控制输入的微分项，并将控制输入和其微分的系数改进为关于观测状态的函数，因其未知，使用RBF神经网络逼近，利用非线性递推最小二乘法同时优化RBF神经网络参数和自抗扰控制器参数，综上研究提出在线优化参数的无模型预测神经网络自抗扰控制算法。仿真研究验证了上述研究的合理性和有效性，系统响应精度高。
Online Optimization Parameters for Model-Free Predictive Neural Network Active Disturbance Rejection Control
Regarding the control issues of complex nonlinear systems that are difficult to model,a comprehen-sive dynamic linearization method incorporating auxiliary variables is proposed to approximate the nonlinear system model.Parametric estimation algorithm is obtained by using the adaptive optimization algorithm for direct minimiza-tion of index function.Differential term of control input is introduced into the extended state observer,and the con-trol input and the factor of its differential term are transformed into function of observer status.Due to its unknown nature,an RBF neural network is employed for approximation.The nonlinear recursive least squares method is uti-lized to simultaneously optimize the parameters of the RBF neural network and the active disturbance rejection con-troller.In summary,this research proposes a model-free predictive neural network active disturbance rejection con-trol algorithm with online parameter optimization.Simulation studies have validated the rationality and effectiveness of the proposed approach,demonstrating high system response accuracy.

active disturbance rejection controlneural network controlmodel-free adaptive controlpredica-tive-controlnonlinear systemadaptive optimization algorithm for direct minimization of index functionnonlineari-ty recursive least squares methodparameters

侯小秋

展开 >

黑龙江科技大学 电气与控制工程学院,黑龙江 哈尔滨 150022

自抗扰控制 神经网络控制 无模型自适应控制 预测控制 非线性系统 直接极小化指标函数自适应优化算法 非线性递推最小二乘法 在线优化参数

2024

10.19576/j.issn.2096-790X.2024.08.003

黄河科技学院学报

黄河科技学院学报

ISSN：
年,卷(期)：2024.26(8)