基于BP神经网络优化模糊PID控制的防爆门控制策略研究  

Research on control strategy of explosion-proof door based on BP neural network optimized fuzzy PID control

作　　者：陈飞[1] 丁曙光[1] 董玉革[1] CHEN Fei;DING Shuguang;DONG Yuge(College of Mechanical Engineering,Hefei University of Technology,Hefei 230009,China)

机构地区：[1]合肥工业大学机械工程学院,合肥230009

出　　处：《现代制造工程》2022年第12期111-116,共6页Modern Manufacturing Engineering

基　　金：国家重点研发计划重点专项项目(2018YFC0808100)。

摘　　要：为了提高防爆门控制的控制精度、收敛速度、鲁棒性和抗干扰能力,对防爆门系统的特性进行了研究,提出了一种基于BP神经网络对模糊控制和PID控制进行优化的控制策略。这种控制策略,通过对输入变量的模糊化,以及确定隶属度函数和模糊规则来输出PID调控因子,再利用BP神经网络对隶属度中心值和基宽以及权值等参数进行训练调整。利用MATLAB软件的Simulink模块对PID控制、模糊PID控制以及模糊神经网络PID控制这3种控制模式分别进行仿真分析,得出了一种鲁棒性好、控制精度高、收敛速度快及抗干扰能力强的智能防爆门系统的控制方式,改善了防爆门系统的性能。In order to improve the control accuracy, convergence speed, robustness and anti-interference ability of explosion-proof door control, the characteristics of explosion-proof door system are studied, and a control strategy using BP neural network to optimize fuzzy control and PID control is proposed. This control strategy outputs PID control factors by fuzzifying input variables and determining membership function and fuzzy rules, and then uses BP neural network to train and adjust parameters such as membership center value, base width and weight. The Simulink module of MATLAB software is used to simulate and analyze the three control modes of PID control, fuzzy PID control and fuzzy neural network PID control. A control mode of intelligent explosion-proof door system with good robustness, high control precision, fast convergence speed and strong anti-interference ability is obtained, which improves the performance of explosion-proof door system.

关 键 词：防爆门系统 控制策略研究 模糊控制 BP神经网络 

分 类 号：TD726[矿业工程—矿井通风与安全]