taptap下载安装安卓学报 ›› 2022, Vol. 40 ›› Issue (1): 34-39.

• 民用航空 • 上一篇    下一篇

改进的神经网络 PID 在空调温度控制中的应用 

费春国,吴婷娜   

  1. (taptap下载安装安卓电子信息与自动化学院,天津 300300) 
  • 收稿日期:2020-11-30 修回日期:2020-11-30 接受日期:2020-09-28 出版日期:2022-02-22 发布日期:2022-03-17
  • 作者简介:费春国(1974—),男,浙江慈溪人,副教授,博士,研究方向为机场节能减排设备与系统关键技术等。
  • 基金资助:
    中央高校基本科研业务费专项(3122017003)

Application of improved neural network PID in controlling temperature of air conditioner

FEI Chunguo,WU Tingna    

  1. (College of Electronic Information and Automation, CAUC, Tianjin 300300, China) 
  • Received:2020-11-30 Revised:2020-11-30 Accepted:2020-09-28 Online:2022-02-22 Published:2022-03-17

摘要: 为提高候机楼中央空调温度控制水平,针对候机楼中央空调系统具有时滞性、扰动因素较多等特点,提出了 一种基于改进天牛须搜索(IBAS,improved beetle antennae search)算法的模糊径向基函数(RBF,radial basis function)神经网络(PID,proportion integration differentiation)控制方法,建立了空调区域温度控制模型,通过 模糊 RBF 神经网络实现 PID 参数在线整定,解决系统非线性、时变的问题。 同时由于神经网络参数存在难 以选取问题,提出利用天牛须搜索(BAS,beetle antennae search)算法优化模糊 RBF 神经网络参数的方法, 并引入莱维飞行机制和变步长策略对 BAS 算法进行改进,提高其跳出局部最优的能力和稳定性。 仿真结果表明,采用 IBAS 算法优化的模糊 RBF 神经网络 PID 控制方法有效提高了系统的鲁棒性和自适应能力, 对候机楼中央空调系统具有良好的控制效果。

关键词: 候机楼中央空调系统, 温度控制, IBAS(improved beetle antennae search)算法, 模糊 RBF(radial basis func鄄 tion)神经网络, PID(proportion integration differentiation)参数整定

Abstract: In order to improve the temperature control level of central air conditioning system in airport terminal, aiming at the time delay and multiple disturbance factors, a fuzzy radial basis function (RBF) neural network PID control method based on the improved beetle antennae search (IBAS) algorithm is proposed for the characteristics of the central air-conditioning system in the terminal building. The temperature control model of air conditioning area is established, and the PID parameters are on-line adjusted by fuzzy RBF neural network to solve the timevarying and nonlinear problems of the system. At the same time, because the parameters of the neural network are difficult to be properly selected, a method to optimize the parameters of the fuzzy RBF network by the BAS algorithm is proposed, which is improved by the Levy flight mechanism and variable step size strategy, so as to improve the algorithm's ability and stability of jumping out of local optimal. Simulation results show that the fuzzy RBF network PID control method optimized by IBAS algorithm effectively improves the robustness and adaptive ability of the system and has a good control effect on the air conditioning system.

Key words: central air conditioning system in airport terminal, temperature control, improved beetle antennae search (IBAS) algorithm, fuzzy radial basis function(RBF) neural network, proportion integration differentiation(PID) parameter tuning

中图分类号: 

Baidu
map