基于ISSA的多变量ORVFL网络自适应预测控制

Multivariable ORVFL Network Adaptive Predictive Control Based on ISSA

那新宇 余华鹏 金鑫 王越

Xinyu Na Huapeng Yu Xin Jin Yue Wang

辽宁石油化工大学 信息与控制工程学院，辽宁 抚顺 113001

School of Information and Control Engineering，Liaoning Petrochemical University，Fushun Liaoning 113001，China

针对多输入多输出（Multiple?Input Multiple?Output, MIMO）的非线性系统，提出了一种基于改进的麻雀搜索算法（Improved Sparrow Search Algorithm, ISSA）的在线序列随机权值网络( Online Random Vector Functional?Link Net, ORVFL)自适应预测控制算法(ISSA?MPC)。该算法采用ORVFL网络逼近非线性系统模型，并用于系统过程的多步预测。为了提高麻雀搜索算法的性能，使用该算法对系统性能指标进行了在线优化，求解了每一个采样周期的最优控制律。结果表明，该算法控制性能良好并具有较好的抗模型失配能力。

For the MIMO nonlinear systems, a multivariable ORVFL neural network adaptive predictive control algorithm based on Improved Sparrow Search Algorithm was proposed in this paper. The algorithm uses the ORVFL network to approximate the nonlinear system model, and applies to the multi?step prediction of the system process. In order to improve the performance of the Sparrow Search Algorithm, the algorithm is used to optimize the system performance index online and solve the optimal control law of each sampling period. The results show that the algorithm has good control performance and good anti?model mismatch ability.

国家自然科学基金面上项目(62073158)

10.12422/j.issn.1672-6952.2023.01.014