基于蝙蝠优化BP-PID算法的精准施肥控制系统研究

朱凤磊; 张立新; 胡雪; 赵家伟; 张雄业

基于蝙蝠优化BP-PID算法的精准施肥控制系统研究

朱凤磊¹,
张立新^1,2,,
胡雪^1,3,
赵家伟^1,2,
张雄业¹

1. 石河子大学机械电气工程学院;
2. 石河子大学兵团能源发展研究院;
3. 农业农村部西北农业装备重点实验室

基金项目:

国家科技创新2030-“新一代人工智能”重大项目(2022ZD0115804)

国家自然科学基金项目(52065055)

新疆维吾尔自治区重大科技专项(2022A02012-4)

兵团科技合作计划项目(2022BC004)

详细信息

作者简介:
朱凤磊(1999—),男,硕士生,主要从事物联网智能调控系统技术研究,E-mail:13371285089@163.com

通讯作者:
张立新(1967—),男,教授,博士生导师,主要从事智能水肥调控系统研究,E-mail:Zhl2001730@126.com

中图分类号: S232.3;TP273
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 收稿日期: 2023-05-19
- 刊出日期: 2023-11-17

Precision Fertilizer Application Control System Based on BA Optimization BP-PID Algorithm

1. Department of Mechanical and Electrical Engineering, Shihezi University;
2. Bingtuan Energy Development Institute, Shihezi University;
3. Key Laboratory of Northwest Agricultural Equipment, Ministry of Agriculture and Rural Affairs

摘要

摘要: 水肥一体化技术在棉花、小麦、番茄等大田农作物种植场景中的应用逐渐增多。当前能够快速有效调整大田农作物水肥一体化系统中肥料流量的控制算法研究较为有限。由于水肥一体化系统存在时变性、滞后性与非线性的特点，常见的PID与BP-PID控制算法无法获得预期的控制效果。为此设计一种基于蝙蝠算法（BA）优化的BP神经网络PID控制器。通过采用BA对BP神经网络的初始权值进行优化，加快了BP神经网络的自学习速度，实现对水肥一体化系统中肥料流量的快速精准控制，从而降低了超调量、提高了响应速度。同时，基于STM32单片机搭建了水肥一体化流量调节测试平台，并对该控制器的性能进行了试验验证。结果表明，与常规PID控制器和基于BP神经网络的PID控制器相比，所设计的控制器具有较高的控制精度和鲁棒性，降低了由时滞性、非线性等因素引起的影响。平均最大超调量为4.78%,平均调节时间为41.24 s。特别是在施肥流量为0.6 m³/h时，控制器表现出最佳的综合控制性能，达到了精准施肥的效果。
- 大田水肥一体化 /
- 控制系统 /
- 蝙蝠优化 /
- BP神经网络
Abstract: The application of water-fertilizer integration technology in cotton, wheat, tomato and other field crops planting scenarios is gradually increasing. However, the current research on control algorithms that can quickly and effectively adjust the fertilizer flow in the water-fertilizer integration system for field crops is relatively limited. The water-fertilizer integration system has the characteristics of time-varying, hysteresis and nonlinearity, and the common PID and BP-PID control algorithms cannot obtain the expected control effect. To solve these problems, a BP neural network PID controller based on bat algorithm（BA） optimization was designed. By using BA to optimize the initial weights of the BP neural network, the self-learning speed of the BP neural network was accelerated to achieve fast and accurate control of the fertilizer flow rate in the water-fertilizer integration system, which reduced the amount of overshooting and improved the response speed. At the same time, a water-fertilizer integration flow regulation test platform was built based on STM32 microcontroller, and the performance of the controller was experimentally verified. The results showed that compared with the conventional PID controller and the BP neural network-based PID controller, the designed controller had higher control accuracy and robustness, and reduced the effects caused by time lag, nonlinearity and other factors. The average maximum overshoot was 4.78% and the average regulation time was 41.24 s. Especially when the fertilizer application flow rate was 0.6 m~3/h, the controller showed the best comprehensive control performance and achieved the effect of precise fertilizer application.
- field water fertilization /
- control system /
- BA optimization /
- BP neural network

HTML全文

参考文献(26)

[1]	朱德兰,阮汉铖,吴普特,等.水肥一体机肥液电导率远程模糊PID控制策略[J].农业机械学报,2022,53(1):186-191.ZHU Delan,RUAN Hancheng,WU Pute,et al.Strategy on remote fuzzy PID control for fertilizer liquid conductivity of water fertilizer integrated machine[J].Transactions of the Chinese Society for Agricultural Machinery,2022,53(1):186-191.(in Chinese)
[2]	王鹏宇,徐庆,宋继田,等.智能化蔬菜大棚节水灌溉控制系统设计[J].现代农业装备,2022,43(4):29-32.WANG Pengyu,XU Qing,SONG Jitian,et al.Design of intelligent farmland water-saving irrigation control system[J].Modern Agricultural Equipments,2022,43(4):29-32.(in Chinese)
[3]	李建军,许燕,张冠,等.基于BP神经网络预测和模糊控制的灌溉控制器设计[J].机械设计与研究,2015,31(5):150-154.LI Jianjun,XU Yan,ZHANG Guan,et al.Optimizational design of irrigation controller based on BP neural network prediction and fuzzy control[J].Machine Design & Research,2015,31(5):150-154.(in Chinese)
[4]	熊钦,肖丽萍,蔡金平,等.基于物联网的果园药水肥一体化控制系统设计与实现[J].中国农机化学报,2023,44(3):73-81.XIONG Qin,XIAO Liping,CAI Jinping,et al.Design and implementation of integration of medicine,water and fertilizer control system based on Internet of Things in orchard[J].Journal of Chinese Agricultural Mechanization,2023,44(3):73-81.(in Chinese)
[5]	王庆华,周晶,侯俊才.基于变论域模糊PID的水肥控制策略研究[J].西北农林科技大学学报(自然科学版),2023,51(11):144-154.WANG Qinghua,ZHOU Jing,HOU Juncai.Irrigation and fertilizer control strategy based on variable domain fuzzy PID[J].Journal of Northwest A&F University(Natural Science Edition),2023,51(11):144-154.(in Chinese)
[6]	刘炳铄,兰鹏,魏珉,等.轻简水肥一体化系统设计与实现[J].节水灌溉,2021(2):75-79.LIU Bingshuo,LAN Peng,WEI Min,et al.Design and implementation of a simple water and fertilizer integration system[J].Water Saving Irrigation,2021(2):75-79.(in Chinese)
[7]	LI Yang,ZHAO Ji,JI Shijun.Thermal positioning error modeling of machine tools using a bat algorithm-based back propagation neural network[J].The International Journal of Advanced Manufacturing Technology,2018,97(5):2575-2586.
[8]	曹梦龙,马俊林.改进蝗虫优化算法在模糊神经网络PID控制中的研究[J].电子测量技术,2022,45(20):74-80.CAO Menglong,MA Junlin.Research on improved grasshopper optimization algorithmin PID control of fuzzy neural networks[J].Electronic Measurement Technology,2022,45(20):74-80.(in Chinese)
[9]	杜学武,张明新,沙广涛,等.基于改进蝙蝠算法的模糊PID规则优化研究[J].计算机工程,2020,46(8):305-312.DU Xuewu,ZHANG Mingxin,SHA Guangtao,et al.Research of fuzzy PID rule optimization based on improved bat algorithm[J].Computer Engineering,2020,46(8):305-312.(in Chinese)
[10]	张科学,吴永伟,何满潮,等.基于蝙蝠算法优化的BP神经网络煤层冲击危险性智能综合评价研究[J].现代隧道技术,2023,60(2):38-46.ZHANG Kexue,WU Yongwei,HE Manchao,et al.Research on the intelligent comprehensive evaluation of coal seam impact risk based on the BP neural network optimized by the bat algorithm[J].Modern Tunnelling Technology,2023,60(2):38-46.(in Chinese)
[11]	孔令英,余欣.新疆节水灌溉与农业绿色治理协调发展研究[J].石河子大学学报(哲学社会科学版),2022,36(4):32-39.KONG Lingying,YU Xin.Research on the collaborative development of agricultural green governance and water-saving irrigation in Xinjiang[J].Journal of Shihezi University(Philosophy and Social Sciences),2022,36(4):32-39.(in Chinese)
[12]	袁建平,施一萍,蒋宇,等.改进的BP神经网络PID控制器在温室环境控制中的研究[J].电子测量技术,2019,42(4):19-24.YUAN Jianping,SHI Yiping,JIANG Yu,et al.Research on improved BP neural network PID controller in greenhouse environment control[J].Electronic Measurement Technology,2019,42(4):19-24.(in Chinese)
[13]	王华东,王大羽.蝙蝠算法优化神经网络的无线传感器网络数据融合[J].激光杂志,2015,36(4):164-168.WANG Huadong,WANG Dayu.Wireless sensor network data fusion based on bat algorithm optimizing neural network[J].Laser Journal,2015,36(4):164-168.(in Chinese)
[14]	邵继业,谢昭灵,杨瑞.基于GA-PSO优化BP神经网络的压缩机气阀故障诊断[J].电子科技大学学报,2018,47(5):781-787.SHAO Jiye,XIE Zhaoling,YANG Rui.Fault diagnosis of compressor gas valve based on BP neural network of a particle swarm genetic algorithm[J].Journal of University of Electronic Science and Technology of China,2018,47(5):781-787.(in Chinese)
[15]	李锋,樊玉和,梁辉.基于改进BP神经网络PID控制器温室温湿度控制研究[J].计算机与数字工程,2021,49(5):908-913,986.LI Feng,FAN Yuhe,LIANG Hui.Research on temperature and humidity control of PID controller based on improved BP neural network[J].Computer & Digital Engineering,2021,49(5):908-913,986.(in Chinese)
[16]	MENG Zihao,ZHANG Lixin,WANG Huan,et al.Research and design of precision fertilizer application control system based on PSO-BP-PID algorithm[J].Agriculture,2022,12(9):1395.
[17]	DENG Bo,SHI Yaoyao.Modeling and optimizing the composite prepreg tape winding process based on grey relational analysis coupled with BP neural network and bat algorithm[J].Nanoscale Research Letters,2019,14(1):296.
[18]	孙文峰,刘海洋,王润涛,等.基于神经网络整定的PID控制变量施药系统设计与试验[J].农业机械学报,2020,51(12):55-64,94.SUN Wenfeng,LIU Haiyang,WANG Runtao,et al.Design and experiment of PID control variable application system based on neural network tuning[J].Transactions of the Chinese Society for Agricultural Machinery,2020,51(12):55-64,94.(in Chinese)
[19]	王秀康,邢英英,张富仓.膜下滴灌施肥番茄水肥供应量的优化研究[J].农业机械学报,2016,47(1):141-150.WANG Xiukang,XING Yingying,ZHANG Fucang.Optimal amount of lrrigation and fertilization under drip fertigation for tomato[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(1):141-150.(in Chinese)
[20]	曾雄飞.基于粒子群算法优化BP神经网络的PID控制算法[J].电子设计工程,2022,30(11):69-73,78.ZENG Xiongfei.The PID control algorithm based on particle swarm optimization optimized BP neural network[J].Electronic Design Engineering,2022,30(11):69-73,78.(in Chinese)
[21]	王一建,谢振宇,张鹏,等.磁轴承BP神经网络PID控制算法研究[J].机械制造与自动化,2023,52(4):177-180,213.WANG Yijian,XIE Zhenyu,ZHANG Peng,et al.Research on BP neural network PID control algorithm for magnetic bearing[J].Machine Building & Automation,2023,52(4):177-180,213.(in Chinese)
[22]	侯小秋,李丽华.基于BP神经网络辨识的预测滤波PID控制[J].黄河科技学院学报,2023,25(5):26-31.HOU Xiaoqiu,LI Lihua.Predictive filtering PID control based on BP neural network ldentiftication[J].Journal of Huanghe S&T College,2023,25(5):26-31.(in Chinese)
[23]	赵永杰,张强,潘德法,等.基于蝙蝠算法优化的BP神经网络估算工质沸点温度[J].自动化与仪器仪表,2022(4):75-79.ZHAO Yongjie,ZHANG Qiang,PAN Defa,et al.BP neural network based on bat algorithm optimizationto estimate the boiling point temperature of working medium[J].Automation & Instrumentation,2022(4):75-79.(in Chinese)
[24]	吕石磊,范仁杰,李震,等.基于改进蝙蝠算法和圆柱坐标系的农业无人机航迹规划[J].农业机械学报,2023,54(1):20-29,63.LÜ Shilei,FAN Renjie,LI Zhen,et al.Track planning of agricultural UAV based on improved bat algorithm and cylindrical coordinate system[J].Transactions of the Chinese Society for Agricultural Machinery,2023,54(1):20-29,63.(in Chinese)
[25]	YAN Hongying,CHU Jizheng.RFID positioning algorithm based on BA optimization[C]//2020 5th International Conference on Computer and Communication Systems (ICCCS),2020:854-858.
[26]	郭贝,任金霞.基于蝙蝠算法优化BP神经网络的特征点匹配[J].制造业自动化,2019,41(8):68-70,80.GUO Bei,REN Jinxia.Optimization of BP-based feature point matching based on bat algorithm[J].Manufacturing Automation,2019,41(8):68-70,80.(in Chinese)