作者：张皓1,2, 高瑜翔1,2, 唐军3, 黄天赐1,2, 马腾1,2, 吴美霖1,2
作者单位：1. 成都信息工程大学通信工程学院，四川 成都 610225;
2. 气象信息与信号处理四川省高校重点实验室，四川 成都 610225;
3. 宜宾职业技术学院电子信息与人工智能学院，四川 宜宾 644000
关键词：一阶Sugeno型;模糊神经网络;双模控制器;Matlab
摘要：
针对如何实现一个控制器控制两种不同参数的被控对象，提出基于一阶Sugeno型模糊神经网络训练的双模控制器方法。采取一个网络训练两种被控对象模型，将训练好的网络作为控制器，使其在控制双模型时，具有良好的控制性能。Matlab仿真结果表明一阶Sugeno型模糊神经网络训练的双模控制器，在控制两种被控模型时，都具有最低的超调量和最短的调节时间，稳定性最强，综合性能指标最好，能实现双模自适应，满足控制要求。
Design of a double model temperature controller trained by Sugeno fuzzy neural network
ZHANG Hao1,2, GAO Yuxiang1,2, TANG Jun3, HUANG Tianci1,2, MA Teng1,2, WU Meilin1,2
1. College of Communication Engineering, Chengdu University of Information Technology, Chengdu 610225, China;
2. Meteorological Information and Signal Processing Key Laboratory of Sichuan Education Institutes, Chengdu 610225, China;
3. College of Electronic Information and Artificial Intelligence, Yibin Vocational and Technical College, Yibin 644000, China
Abstract: Aiming at how to realize a controller to control the controlled object with two different parameters, a double model controller method based on first-order Sugeno fuzzy neural network training is proposed. One network is used to train two controlled object models, and the trained network is used as a controller, so that it has good control performance when controlling dual models. Matlab simulation results show that the double model controller trained by the first-order Sugeno fuzzy neural network has the lowest overshoot and the shortest adjustment time when controlling the two controlled models, the strongest stability and the best comprehensive performance indicators, it can realize double model self-adaptation and meet the control requirements.
Keywords: first-order Sugeno type;fuzzy neural network;double model controller;Matlab
2021, 47(10):129-136 收稿日期: 2020-12-14;收到修改稿日期: 2021-01-26
基金项目: 四川省教育厅高校创新团队项目(15TD0022)
作者简介: 张皓（1992-），男，四川雅安市人，硕士研究生，专业方向为智能控制
参考文献
[1] JIN X, CHEN K K, YANG Z, et al. Simulation of hydraulic transplanting robot control system based on fuzzy PID controller[J]. Measurement, 2020, 164: 108023
[2] 张皓, 高瑜翔. 前馈反馈 Smith 预估模糊 PID 组合温度控制算法[J]. 中国测试, 2020, 46(11): 132-138+168
[3] ZHANG J X, LIU J C. BP neural network PID temperature control of beer fermentation tank[C]// Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology(ANIT 2018), 2018.
[4] ZHAO Q, ZHANG H J, CHEN Z H. A heading control strategy based on neural network PID controller[C]// 第32届中国控制与决策会议, 2020.
[5] MOHAMED B, KARA K, OUSSAMA A , et al. Adaptive neural network PID controller[C]// 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe), 2019.
[6] REN X L, YANG Y, GAO L, et al. Research on robot tracking of books returning to bookshelf based on particle swarm optimization fuzzy PID control[C]// 2020 Chinese Control and Decision Conference (CCDC), 2020.
[7] 李雪吉, 程海鹰, 胡志勇, 等. 粒子群优化模糊PID在燃烧器温度控制中的应用[J]. 机械科学与技术, 2021, 40(2): 276-280
[8] YUE H, WANG F, QIN L, et al. Application of fuzzy PID control algorithm based on genetic self-tuning in constant temperature incubator[C]// 2020 Chinese Control and Decision Conference (CCDC), 2020.
[9] 张娓娓, 袁路路. 基于遗传优化模糊PID算法的温室智能控制系统研究[J]. 农机化研究, 2017, 39(7): 209-213
[10] 赵世海, 韩雪. 基于模糊神经网络PID的焙烘机温度控制[J]. 天津工业大学学报, 2019, 38(4): 83-88
[11] 潘玉成, 林鹤之, 陈小利, 等. 基于模糊RBF神经网络的PID控制方法及应用[J]. 机械制造与自动化, 2019, 48(3): 215-219
[12] BAKIRCIOĞLU V, ŞEN M A, KALYONCU M. Adaptive neural-network based fuzzy logic (ANFIS) based trajectory controller design for one leg of a quadruped robot[C]// 5th International Conference on Mechanics and Control Engineering (ICMCE 2016), 2016.
[13] NIELSE M. Neural networks and deep learning[EB/OL]. [2020-12-01].http://neuralnetworksanddeeplearning.com.
[14] 曹承志. 微型计算机控制技术[M]. 北京: 化学工业出版社, 2008: 190.
[15] 王军, 高秀梅, 宋潇潇, 等. 自动控制原理[M]. 北京: 机械工业出版社, 2012: 41.
