基于改进BP−PID的带式输送机速度控制方法

桂改花; 苑占江

doi:10.13272/j.issn.1671-251x.2022080058

基于改进BP−PID的带式输送机速度控制方法

doi: 10.13272/j.issn.1671-251x.2022080058

广东科学技术职业学院计算机工程技术学院(人工智能学院), 广东珠海　519090

基金项目: 广东省普通高校特色创新项目（K01057037）。

详细信息

作者简介:
桂改花（1981—），女，山东聊城人，讲师，硕士，主要研究方向为数学建模、控制算法，E-mail：ggaihua2022@163.com

中图分类号: TD528.1
计量
- 文章访问数: 142
- HTML全文浏览量: 32
- PDF下载量: 11
- 被引次数: 0
出版历程
- 收稿日期: 2022-08-21
- 修回日期: 2023-05-15
- 网络出版日期: 2023-05-22

Speed control method for belt conveyor based on improved BP-PID

Computer Enineering Technical College (Artificial Intelligence College), Guangdong Polytechnic of Science and Technology, Zhuhai 519090, China

摘要

摘要: 针对传统BP−PID控制算法采用梯度下降法求解，存在收敛速度慢、易陷入局部极值且在低信噪比(LSNR)条件下性能下降等问题，提出了一种基于改进遗传模拟退火算法(ImGSAA)优化的BP−PID带式输送机速度控制方法(ImGSAA−BP−PID)。首先将交叉、变异概率取值与迭代时间关联，并引入反余弦函数增加遗传模拟退火算法（GSAA）动态调整和非线性变化适应能力。然后通过对传统Metropolis准则进行加权处理，提出加权Metropolis准则，对新种群个体进行修正，提升GSAA的噪声稳健性。最后利用ImGSAA对BP−PID初始参数进行优化，自动确定BP−PID的最优参数组合，从而提升参数整定的实时性和控制精度及对LSNR环境的适应能力。试验结果表明：① ImGSAA仅需11次迭代即可收敛，表明利用改进的交叉、变异策略和加权Metropolis准则对GSAA进行优化，能够有效提升算法的收敛速度和实时性。② ImGSAA−BP−PID的控制误差为−0.468 5~0.572 3 m/s，与遗传算法（GA）−BP−PID、粒子群算法（PSO）−BP−PID、GSAA−BP−PID的控制方法相比，分别提升了224.88%，104.07%，38.33%。③ ImGSAA性能受LSNR影响最小，迭代15次即收敛于全局最优解，具有较强的噪声稳健性。④ 在LSNR条件下，ImGSAA−BP−PID的控制误差均值下降了3.54%，控制性能明显优于GA−BP−PID，PSO−BP−PID，GSAA−BP−PID，更满足实际工程应用需求。
- 带式输送机 /
- 速度控制 /
- 遗传模拟退火算法 /
- 神经网络-PID /
- 低信噪比 /
- 参数优化
Abstract: The traditional BP-PID control algorithm uses the gradient descent method to solve, which has problems such as slow convergence speed, easy trapping in local extremum, and performance degradation under low signal-to-noise ratio (LSNR) conditions. In order to solve the above problems, a BP PID belt conveyor speed control method (ImGSAA-BP-PID) based on improved genetic simulated annealing algorithm (ImGSAA) optimization is proposed. Firstly, the values of crossover and mutation probabilities are correlated with the iteration time. The inverse cosine function is introduced to enhance the dynamic adjustment and nonlinear change adaptability of GSAA. Secondly, by weighting the traditional Metropolis criterion, a weighted Metropolis criterion is proposed to modify the new population individuals and improve the noise robustness of genetic simulated annealing algorithm (GSAA). Finally, ImGSAA is used to optimize the initial parameters of BP-PID, automatically determining the optimal parameter combination for BP-PID. It improves its real-time parameter tuning, control precision, and adaptability to the LSNR environment. The experimental results show the following points. ① ImGSAA only needs 11 iterations to converge, indicating that optimizing the GSAA using the proposed improved crossover and mutation strategies and weighted Metropolis criteria can effectively improve the convergence speed and real-time performance of the algorithm. ② The control error of ImGSAA-BP-PID is −0.468 5-0.572 3 m/s, which is 224.88%, 104.07%, and 38.33% higher than the control methods based on genetic algorithm (GA)-BP PID, particle swarm optimization (PSO)-BP PID, and GSAA-BP-PID, respectively. ③ The performance of ImGSAA is least affected by LSNR. It converges to the global optimal solution after 15 iterations, which has strong noise robustness. ④ Under LSNR conditions, the average control error of ImGSAA-BP-PID decreases by 3.54%. The control performance is significantly better than GA-BP-PID, PSO-BP-PID, and GSAA-BP-PID, which better meets the practical engineering application requirements.
- belt conveyor /
- speed control /
- genetic simulated annealing algorithm /
- neural network-PID /
- low signal-to-noise ratio /
- parameter optimization

HTML全文

图 1 BP神经网络结构

Figure 1. Structure of BP neural network

下载: 全尺寸图片幻灯片

图 2 ImGSAA−BP−PID控制流程

Figure 2. Control process of the ImGSAA-BP-PID

下载: 全尺寸图片幻灯片

图 3 仿真架构

Figure 3. Simulation structure

下载: 全尺寸图片幻灯片

图 4 各算法迭代过程中参数变化曲线

Figure 4. Parameter change curve during iteration of different algorithms

下载: 全尺寸图片幻灯片

图 5 4种方法速度控制结果

Figure 5. Speed control results of four methods

下载: 全尺寸图片幻灯片

图 6 LSNR条件下速度变化曲线

Figure 6. Speed change curve under LSNR

下载: 全尺寸图片幻灯片

图 7 LSNR条件下参数变化曲线

Figure 7. Parameter change curve under LSNR

下载: 全尺寸图片幻灯片

图 8 LSNR条件下4种方法的速度控制误差

Figure 8. Speed control error of four methods under LSNR

下载: 全尺寸图片幻灯片

图 9 LSNR条件下4种方法的控制性能

Figure 9. Control performance of four methods under LSNR

下载: 全尺寸图片幻灯片

表 1 4种方法控制性能指标

Table 1. Control performance indexes of four methods

控制方法	调整时间/s	峰值/V	峰值时间/s	最大超调量	误差均值/ (m·s⁻¹)	误差均方根
GA−BP−PID	0.0056	1.1382	0.031	24.56	0.3356	1.53
PSO−BP−PID	0.0033	1.0845	0.027	15.31	0.2108	0.76
GSAA−BP−PID	0.0020	1.0056	0.007	10.09	0.1429	0.42
ImGSAA−BP−PID	0.0016	1.0073	0.006	7.11	0.1033	0.25

下载: 导出CSV

表 2 LSNR条件下4种方法控制性能指标

Table 2. Control performance indexes of four methods under LSNR

调速方法	调整时间/s	峰值/V	峰值时间/s	最大超调量	误差均值/ (m·s⁻¹)	误差均方根
GA−BP−PID	0.0079	1.6578	0.062	34.77	0.5590	2.23
PSO−BP−PID	0.0039	1.1067	0.031	16.52	0.2910	0.92
GSAA−BP−PID	0.0055	1.3182	0.047	23.21	0.4755	1.39
ImGSAA−BP−PID	0.0019	1.0348	0.010	8.21	0.1387	0.45

下载: 导出CSV

参考文献(21)

[1]	方崇全. 煤矿带式输送机巡检机器人关键技术研究[J]. 煤炭科学技术,2022,50(5):263-270. FANG Chongquan. Research on key technology of inspection robot for coal mine belt conveyor[J]. Coal Science and Technology,2022,50(5):263-270.
[2]	冯俊宾. 变频调速技术在带式输送机上的节能应用[J]. 机械研究与应用,2021,34(1):142-144. FENG Junbin. Energy saving application of frequency control technology in belt conveyor[J]. Mechanical Research & Application,2021,34(1):142-144.
[3]	杨春雨,顾振,张鑫,等. 基于深度学习的带式输送机煤流量双目视觉测量[J]. 仪器仪表学报,2021,41(8):164-174. YANG Chunyu,GU Zhen,ZHANG Xin,et al. Binocular vision measurement of coal flow of belt conveyors based on deep learning[J]. Chinese Journal of Scientific Instrument,2021,41(8):164-174.
[4]	胡宗镇,赵延立. 基于改进型BP神经网络自整定的PID控制[J]. 电脑与信息技术,2019,27(1):11-13. HU Zongzhen,ZHAO Yanli. PID control based on self-adjusting BP neural network[J]. Computer and Information Technology,2019,27(1):11-13.
[5]	郭伟东,李明,亢俊明,等. 基于机器视觉的矿井输煤系统优化节能控制[J]. 工矿自动化,2020,46(10):69-75. GUO Weidong,LI Ming,KANG Junming,et al. Optimal energy saving control of mine coal transportation system based on machine vision[J]. Industry and Mine Automation,2020,46(10):69-75.
[6]	WANG Guimei,LU Shenghui,LIU Jiehui,et al. Coal volume measurement of belt conveyor based on image processing[J]. Acta Metrologica Sinica,2020,41(6):724-728.
[7]	曹松青,郝万君. 基于NMPC−PID的大型风电机组独立变桨距载荷控制[J]. 计算机应用与软件,2020,37(10):34-40. CAO Songqing,HAO Wanjun. Individual pitch load control of large wind turbines based on NMPC-PID[J]. Computer Applications and Software,2020,37(10):34-40.
[8]	韩东升,杜永贵,庞宇松,等. 基于预见控制的带式输送机调速节能方法[J]. 工矿自动化,2018,44(6):64-68. HAN Dongsheng,DU Yonggui,PANG Yusong,et al. Speed regulation energy saving method of belt conveyor based on preview control[J]. Industry and Mine Automation,2018,44(6):64-68.
[9]	张文静,曹博文,刘曰锋,等. 基于分数阶滑模自适应神经网络的中速磁浮列车运行控制方法[J]. 中国铁道科学,2022,43(2):152-160. ZHANG Wenjing,CAO Bowen,LIU Yuefeng,et al. Operation control method for medium-speed maglev trains based on fractional order sliding mode adaptive neural network[J]. China Railway Science,2022,43(2):152-160.
[10]	龚桂荣. 皮带机巡检机器人控制系统设计与研究[D]. 徐州: 中国矿业大学, 2019. GONG Guirong. Design and research on an inspection robot control system for belt conveyor[D]. Xuzhou: China University of Mining and Technology, 2019.
[11]	彭月,苏芷玄,杨杰,等. 基于PSO−BP−PID单点混合悬浮球控制算法研究[J]. 铁道科学与工程学报,2022,19(6):1511-1520. PENG Yue,SU Zhixuan,YANG jie,et al. On hybrid single-point magnetic levitation ball control algorithm based on BP-PID[J]. Journal of Railway Science and Engineering,2022,19(6):1511-1520.
[12]	吉建华,苗长云,李现国,等. 基于PSO带式输送机PID控制器参数智能整定的适应度函数设计[J]. 机械工程学报,2022,58(3):1123-1129. JI Jianhua,MIAO Changyun,LI Xianguo,et al. Design of fitness function for intelligent parameter tuning of PID controller on belt conveyor with PSO[J]. Journal of Mechanical Engineering,2022,58(3):1123-1129.
[13]	王卉. 基于模糊PID理论的带式输送机调速系统设计[J]. 煤矿机械,2019,40(9):14-16. WANG Hui. Design of speed regulation system for belt conveyor based on fuzzy PID theory[J]. Coal Mine Machinery,2019,40(9):14-16.
[14]	曹江卫,魏霞. 基于RBF−PID控制器的带式输送机自适应调速系统[J]. 煤矿机械,2020,41(5):203-205. CAO Jiangwei,WEI Xia. Adaptive speed regulation system of belt conveyor based on RBF-PID controller[J]. Coal Mine Machinery,2020,41(5):203-205.
[15]	李航,杜璠,胡晓兵,等. 改进的BP神经网络PID控制器在气体浓度控制中的研究[J]. 四川大学学报(自然科学版),2020,57(6):1103-1109. LI Hang,DU Fan,HU Xiaobing,et al. Research on improved BP neural network PID controller in gas concentration control[J]. Journal of Sichuan University(Natural Science Edition),2020,57(6):1103-1109.
[16]	杨华伟,帕孜来•马合木提,张毅. PSO−BP−PID算法在双容水箱系统中的应用[J]. 电气传动,2017,47(5):78-80. YANG Huawei,PAZILAI Mahemuti,ZHANG Yi. Application of PSO-BP-PID algorithm in double tank water system[J]. Electric Drive,2017,47(5):78-80.
[17]	朱馨渝,马平. 基于改进PSO−BP神经网络的PID参数优化方法[J]. 现代电子技术,2022,45(21):127-130. ZHU Xinyu,MA Ping. PID parameter optimization method based on improved PSO-BP neural network[J]. Modern Electronics Technique,2022,45(21):127-130.
[18]	SRINIVAS M,PATNAIK L M. Adaptive probabilities of crossover and mutation in genetic algorithms[J]. IEEE Transactions on Systems,Man,and Cybernetics,1994,24(4):656-667. doi: 10.1109/21.286385
[19]	GAO Chenyang, GAO Yuelin, LV Shanshan. Improved simulated annealing algorithm for flexible job shop scheduling problems[C]. Chinese Control and Decision Conference, Yinchuan, 2016: 2223-2228.
[20]	WANG Zheng,WANG Bo,LIU Chun,et al. Improved BP neural network algorithm to wind power forecast[J]. The Journal of Engineering,2017(13):940-943.
[21]	郭彩杏,郭晓金,柏林江. 改进遗传模拟退火算法优化BP算法研究[J]. 小型微型计算机系统,2019,40(10):2063-2067. GUO Caixing,GUO Xiaojin,BAI Linjiang. Rsearch on improved BP algorithm for genetic simulated annealing algorithm[J]. Journal of Chinese Computer Systems,2019,40(10):2063-2067.