基于Smith预估器的制冷系统BP神经网络PID控制算法

doi:10.16180/j.cnki.issn1007-7820.2025.08.006

电子科技 ›› 2025, Vol. 38 ›› Issue (8): 42-48.doi: 10.16180/j.cnki.issn1007-7820.2025.08.006

基于Smith预估器的制冷系统BP神经网络PID控制算法

杨远星(), 丁绪东, 王俊超, 吴东

山东建筑大学信息与电气工程学院,山东济南 250101

收稿日期:2024-01-16 修回日期:2024-02-10 出版日期:2025-08-15 发布日期:2025-07-10
通讯作者: 杨远星(1995-),女,E-mail:2377525453@qq.com,硕士研究生。研究方向:智能环境与网络化控制。丁绪东(1971-),男,博士,教授。研究方向:空调系统建模与优化控制。
作者简介:丁绪东(1971-),男,博士,教授。研究方向:空调系统建模与优化控制。
基金资助:
山东省重大科技创新工程项目(2019JZZY020812);山东省自然科学基金(ZR2020MF070)

Research on BP Neural Network PID Control Algorithm of Refrigeration System Based on Smith Predictor

YANG Yuanxing(), DING Xudong, WANG Junchao, WU Dong

The School of Information and Electrical Engineering,Shandong Jianzhu University,Jinan 250101,China

Received:2024-01-16 Revised:2024-02-10 Online:2025-08-15 Published:2025-07-10
Supported by:
Major Science and Technology Innovation Project of Shandong(2019JZZY020812);Natural Science Foundation of Shandong(ZR2020MF070)

摘要/Abstract

摘要：

针对压缩式制冷系统在实际运行过程具有时滞大、高耦合、非线性以及外部干扰等问题,文中提出了一种基于Smith预估器的BP(Back Propagation)神经网络PID(Proportional Integration Differentiation)控制算法。采用Smith预估补偿器预测补偿系统的实际输出,利用其预估补偿机制消除系统的延迟环节,缓解时滞性对系统的影响。利用BP神经网络的自学习能力将压缩式制冷系统解耦为两个独立的回路系统,并整定PID参数以应对系统和外部干扰的变化。MATLAB仿真结果表明,所提控制策略在提高制冷系统的动态性能和抗干扰性能方面具有显著优势,过热度和蒸发温度的调节时间减少了123 s、204 s,超调量下降5.27%、10.22%。且在改变参数情况下具有良好的鲁棒性,降低了控制的超调量,为压缩式制冷系统的稳定运行提供了一种有效的控制方案。

关键词: 压缩式制冷系统, 模型辨识, Smith预估器, PID, 多变量解耦, BP神经网络, MATLAB仿真, 解耦控制

Abstract:

In view of the problems of large time delay, high coupling, nonlinearity and external interference in the actual operation of compression refrigeration system, a BP(Back Propagation) neural network PID(Proponential Integration Differentiation) control algorithm based on Smith predictor is proposed in this study. Smith predictor compensator is used to predict and compensate the actual output of the system, and its predictive compensation mechanism is used to eliminate the delay link of the system and alleviate the influence of time delay on the system. The self-learning ability of BP neural network is used to decouple the compressed refrigeration system into two independent loop systems, and PID parameters are adjusted to cope with the changes of the system and external interference. MATLAB simulation results show that the proposed control strategy has obvious advantages in improving the dynamic performance and anti-interference performance of refrigeration system. The adjustment time of superheat and evaporation temperature is reduced by 123 s and 204 s, and the overshoot is reduced by 5.27% and 10.22%. And it has good robustness under the condition of changing parameters, and also reduces the overshoot of control, which provides an effective control scheme for the stable operation of compression refrigeration system.

Key words: compression refrigeration system, model identification, Smith predictor, PID, multivariate decoupling, BP neural network, MATLAB simulation, decoupling control

中图分类号:

TP273

杨远星, 丁绪东, 王俊超, 吴东. 基于Smith预估器的制冷系统BP神经网络PID控制算法[J]. 电子科技, 2025, 38(8): 42-48.

YANG Yuanxing, DING Xudong, WANG Junchao, WU Dong. Research on BP Neural Network PID Control Algorithm of Refrigeration System Based on Smith Predictor[J]. Electronic Science and Technology, 2025, 38(8): 42-48.

图/表 6

图1

图2

图3

图4

图5

图6

参考文献 20

[1]	李祖强, 黄兴华, 刘茂玲. 太阳能和空气源复合热泵的最优模式切换分析[J]. 太阳能学报, 2023, 44(2):30-36. doi: 10.19912/j.0254-0096.tynxb.2021-1077
	Li Zuqiang, Huang Xinghua, Liu Maoling. Optimal mode switching analysis of solar energy and air source hybrid heat pumps[J]. Acta Energiae Solaris Sincia, 2023, 44(2):30-36.
[2]	Lin J L, Yeh T J. Control of multi-evaporator air-conditioning systems for flow distribution[J]. Energy Conversion and Management, 2009, 50(6):1529-1541.
[3]	刘志宏, 久元溦, 翟耘萱, 等. 基于安排过渡过程的制冷机控温策略设计[J]. 低温与超导, 2021, 49(2):14-17.
	Liu Zhihong, Jiu Yuanwei, Zhai Yunxuan, et al. Design of cryocooler algorithm based on arranging the transient process[J]. Cryogenics and Superconductivity, 2021, 49(2):14-17.
[4]	Li H, Jeong S K, Yoon J I, et al. An empirical model for independent control of variable speed refrigerationsystem[J]. Applied Thermal Engineering, 2008, 28(14-15):1918-1924.
[5]	Li H, Jeong S K, You S S. Feedforward control of capacity and superheat for a variable speed refrigeration system[J]. Applied Thermal Engineering, 2009, 29(5-6):1067-1074.
[6]	Zhao B Y, Zhao Z G, Li Y, et al. An adaptive PID control method to improve the power tracking performance of solar photovoltaic air-conditioning systems[J]. Renewable and Sustainable Energy Reviews, 2019, 11(3):109250-109251.
[7]	Carreno Zagarra J J, Villamizar R, Moreno J C, et al. Active disturbance rejection and PID control of a one stage refrigeration cycle[C]. Florianópolis: IFAC Conference on Advances in Proportional-Integral-Derivative Control, 2018:444-449.
[8]	李兆博, 吴爱国, 何熠, 等. 制冷系统的改进Smith预估补偿和解耦控制[J]. 控制理论与应用, 2013, 30(1):111-117.
	Li Zhaobo, Wu Aiguo, He Yi, et al. Improved Smith predictive compensation and decoupling in refrigeration system[J]. Control Theory and Applications, 2013, 30(1):111-117.
[9]	姬晓娃. 压缩式制冷机组变频控制策略的研究[D]. 济南: 山东建筑大学, 2020:6-20.
	Ji Xiaowa. Research on frequency conversion control strategy of compression refrigeration unit[D]. Jinan: Shandong Jianzhu University, 2020:6-20.
[10]	Wallace M, Das B, Mhaskar P, et al. Offset-free model predictive control of a vapor compression cycle[J]. Journal of Process Control, 2012, 22(7):1374-1386.
[11]	Tesfay M, Alsaleem F, Arunasalam P, et al. Adaptive-model predictive control of electronic expansion valves with adjustable setpoint for evaporator superheat minimization[J]. Building and Environment, 2018, 13(3):151-160.
[12]	Schurt L C, Hermes C J L, Neto A T. Assessment of the controlling envelope of a model-based multivariable controller for vapor compression refrigeration systems[J]. Applied Thermal Engineering, 2010, 30(13):1538-1546.
[13]	赵东亚, 邹涛, 王治平. Smith预估控制研究进展[J]. 化工进展, 2010, 29(8):1406-1410.
	Zhao Dongya, Zou Tao, Wang Zhiping. Progress in study of Smith-predictorler contrller[J]. Chemical Industry and Engineering Progress, 2010, 29(8):1406-1410.
[14]	Bi Q, Cai W J, Lee E L, et al. Robust identification of first-order plus dead-time model from step response[J]. Control Engineering Practice, 1999, 7(1):71-77.
[15]	李冬辉, 高亚男. 压缩式制冷系统预测自抗扰控制[J]. 西安交通大学学报, 2020, 54(11):98-105,120.
	Li Donghui, Gao Yanan. Predictive auto disturbance rejection control for compression refrigeration system[J]. Journal of Xi'an Jiaotong University, 2020, 54(11):98-105,120.
[16]	周爱国, 曾智杰, 乌建中, 等. 风电叶片多点静力测试神经网络PID解耦控制[J]. 测控技术, 2021, 40(3):123-129.
	Zhou Aiguo, Zeng Zhijie, Wu Jianzhong, et al. Neural network PID decoupling control for multi-point static test of wind turbine blades[J]. Measurement and Control Technology, 2021, 40(3):123-129.
[17]	蔡淑敏, 王亚刚, 田涛. 智能PID控制算法研究及MATLAB实现[J]. 电子科技, 2016, 29(7):43-46.
	Cai Shumin, Wang Yagang, Tian Tao. Research on intelligent PID control algorithm and MATLAB simulation[J]. Electronic Science and Technology, 2016, 29(7):43-46.
[18]	陶永华. 新型PID控制及其应用[M]. 2版. 北京: 机械工业出版社, 2002:57-59.
	Tao Yonghua. New PID control and its application[M]. 2nd ed. Beijing: China Machine Press, 2002:57-59.
[19]	孟晓姣, 张世巍, 李小健, 等. 一种基于BP神经网络的车载通信设备性能评估方法[J]. 电子科技, 2021, 34(5):24-28.
	Meng Xiaojiao, Zhang Shiwei, Li Xiaojian, et al. An evaluation method of vehicle-mounted communication equipment performance based on BP neural network[J]. Electronic Science and Technology, 2021, 34(5):24-28.
[20]	Ziegler J, Nichols N. Optimum settings for automatic controllers[J]. Transactions of the American Society of Mechanical Engineers, 1942, 64(8):759-765.

基于Smith预估器的制冷系统BP神经网络PID控制算法

Research on BP Neural Network PID Control Algorithm of Refrigeration System Based on Smith Predictor

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 20

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	张斌, 丁海兵, 王晶, 薛谦忠. 神经网络辅助双频U型槽贴片天线优化[J]. 电子科技, 2025, 38(7): 34-39.
[2]	吴冬, 丁绪东, 孙昊, 马浩翔, 杨远星. 改进粒子群的压缩式制冷系统模糊PID解耦控制[J]. 电子科技, 2025, 38(7): 7-14.
[3]	王俊超, 丁绪东, 杨远星, 刘雨婷, 杨玉萍. 基于神经网络逆模型的制冷系统解耦控制[J]. 电子科技, 2025, 38(7): 82-88.
[4]	张海博, 潘鹏程, 郑峰. 基于改进鲸鱼算法优化的接地网腐蚀速率预测[J]. 电子科技, 2025, 38(5): 8-14.
[5]	韦润通, 王智冲, 李学琪. 基于鲸鱼算法的开关磁阻电机PID参数整定[J]. 电子科技, 2025, 38(4): 59-65.
[6]	叶翔宇, 林晓会, 丁江乔, 解维坤. 基于优化BPNN的FPGA内嵌高速接口总抖动预测方法[J]. 电子科技, 2025, 38(2): 70-77.
[7]	朱扬烁, 吕海玉, 李奕晨, 张凤登. 多核处理器容错实时调度算法[J]. 电子科技, 2025, 38(1): 73-80.
[8]	金睿, 金海, 莫松楠. 基于模糊PID的大型双旋翼无人机[J]. 电子科技, 2024, 37(8): 54-59.
[9]	袁傲, 齐金鹏, 贾灿, 薛宇鑫, 郭阳阳. 一种基于深度学习的时序病变数据段分类方法[J]. 电子科技, 2024, 37(6): 84-91.
[10]	丁祥鑫,张伟,王亚刚. 基于多主导极点法的时滞积分系统PID控制器设计[J]. 电子科技, 2023, 36(8): 56-64.
[11]	苑振博,白勃,张晓薇,罗柳君,尚韬. 基于图像处理的可见光通信自动对准系统[J]. 电子科技, 2023, 36(6): 8-15.
[12]	蔺琳,王万雄. 基于EMD-GWO-SVR组合模型的短期风速预测[J]. 电子科技, 2023, 36(5): 1-8.
[13]	朱铭基,张会林,马立新. 基于Smith预估模糊PID的氨法脱硫控制策略[J]. 电子科技, 2023, 36(5): 80-87.
[14]	孙思男,郝正航. 基于电压电流双环控制的蓄电池并网研究[J]. 电子科技, 2023, 36(2): 13-21.
[15]	胡涛,蒋全. 基于改进蜜獾优化算法的PID参数整定[J]. 电子科技, 2023, 36(12): 46-54.