自动化学报2024，Vol.50Issue(6)：1199-1209,11.DOI:10.16383/j.aas.c220679
基于自组织递归小波神经网络的污水处理过程多变量控制
Multivariate Control of Wastewater Treatment Process Based on Self-organized Recurrent Wavelet Neural Network
摘要
Abstract
The wastewater treatment process(WWTP)is a complex process containing multiple biochemical reac-tions with nonlinear and dynamic characteristics.Therefore,it is a challenge to achieve accurate control of the wastewater treatment process.To solve this problem,a multi-variable control of wastewater treatment process based on the self-organized recurrent wavelet neural network(SRWNN)is proposed.Firstly,to deal with the dy-namicity of wastewater treatment process,according to the firing strength of the wavelet base,the self-organizing mechanism is designed to dynamically adjust the structure of the recurrent wavelet neural network controller to im-prove the control performance.Then,an online learning algorithm combined with adaptive learning rate is used to learn the parameters of controller.In addition,the stability of the controller is proved by the Lyapunov stability theorem.Finally,the benchmark simulation platform is used to conduct simulation.The experimental results show that this control method can effectively improve the integral of absolute error(IAE)and integral of squared error(ISE)of the wastewater treatment process.关键词
神经网络控制/污水处理过程/自组织机制/多变量控制Key words
Neural network control/wastewater treatment process(WWTP)/self-organized mechanism/multi-vari-able control引用本文复制引用
苏尹,杨翠丽,乔俊飞..基于自组织递归小波神经网络的污水处理过程多变量控制[J].自动化学报,2024,50(6):1199-1209,11.基金项目
国家自然科学基金(61890930-5,62021003,61973010),国家重点研发计划(2021ZD0112302)资助 Supported by National Natural Science Foundation of China(61890930-5,62021003,61973010)and National Key Research and Development Program of China(2021ZD0112302) （61890930-5,62021003,61973010）
