锻压技术

热轧带钢层流冷却的精冷段Smith PSO-BP-PID反馈控制

英文标题：Smith PSO-BP-PID feedback control on fine cold section for laminar cooling of hot rolled strip steel

作者：任长辉田海陶震张健雷思捷

关键词：Smith预估补偿 PID BP-PID PSO-BP-PID Smith PSO-BP-PID

分类号：TG335.5

出版年,卷(期):页码：2023,48(12):177-181

摘要：

为了实现对带钢卷取温度的精确控制，采用以神经网络的前馈控制为主、反馈控制为辅的复合控制策略。层流冷却的精冷段属于大滞后、非线性系统，针对大滞后问题提出使用Smith预估器进行补偿；针对非线性问题，采用多种手段优化的PID控制器，加强其控制的实时性与动态性能。通过BP神经网络对PID控制器进行参数寻优，使用粒子群优化算法对BP神经网络的初始权值和阈值进行优化，并采用改进的粒子群算法来提高其迭代收敛速度。最后，经过仿真验证了Smith PSO-BP-PID的超调量最小，调节时间最短，动态性能最好。

In order to achieve the accurate control of strip steel coiling temperature, a compound control strategy was adopted, which was based on the feedforward control of neural network and supplemented by the feedback control. The fine cooling section of laminar flow cooling was a nonlinear system with large lag, and Smith estimator was proposed to compensate for the problem of large lag. Aiming at the nonlinear problem, the PID controller optimized by various means was used to enhance the real-time and dynamic performance of its control. Furthermore, BP neural network was proposed to optimize the parameters of PID controller, and the particle swarm optimization algorithm was used to optimize the initial weights and thresholds of BP newral network,and the improved particle swarm algorithm was adopted to improve its iterative convergence speed. Finally, the simulation verifies that Smith PSO-BP-PID has the smallest overshoot, the shortest adjustment time and the best dynamic performance.

基金项目：

内蒙古自治区自然科学基金资助项目（2022MS06005）

作者简介：任长辉（1998-），男，硕士研究生 E-mail：2539018956@qq.com 通信作者：田海（1968-），男，硕士，副教授 E-mail：tian680125@163.com

参考文献：

[1]Chen D, Zhang R, Li Z L, et al. Temperature distribution prediction in control cooling process with recurrent neural network for variable-velocity hot rolling strips[J]. The International Journal of Advanced Manufacturing Technology, 2022, 120(11): 7533-7546.

[2]孙莉莉,李博.安钢集团热连轧层流冷却过程控制系统研究及优化[J].数字技术与应用,2015,(4):18.

Sun L L, Li B. Research and optimization of laminar cooling process control system for hot strip rolling in Anshan Iron & Steel Group [J]. Digital Technology & Application,2015,(4):18.

[3]郝智红.谱分解理论在热轧卷取温度控制系统改造中的应用[J].冶金自动化,2014,38(3):29-32.

Hao Z H. Application of spectral decomposition theory on retrofit of hot strip coiling temperature control system [J]. Metallurgical Industry Automation, 2014,38(3):29-32.

[4]Liu E Y, Zhang D H, Sun J, et al. Algorithm design and application of laminar cooling feedback control in hot strip mill [J]. Journal of Iron and Steel Research, International, 2012, 19(4): 39-42.

[5]周继平,田海,魏学松.短冷却线UFC工艺控制系统优化——基于轧后冷却技术[J].工业技术创新,2022,9(1):113-122.

Zhou J P, Tian H, Wei X S. Optimization on control system for short cooling line UFC process-Based on post-rolling cooling technology [J]. Industrial Technology Innovation,2022,9(1):113-122.

[6]Li S H, Li X, Yang Y P. Intelligent model building and GPC-PID based temperature curve control strategy for metallurgical industry[J]. Mathematical Problems in Engineering, 2016,(3): 7454805.1-7454805.16.

[7]Li B Q, Zhang S L, Wang J J, et al. Application of RBF-PID to MN-AGC in hot continuous rolling [A]. Proceeding of 2020 Chinese Control and Decision Conference (CCDC)[C]. Hefei: IEEE, 2020.

[8]Gou L F, Shao W X, Zeng X Y, et al. Rapid simulated annealing algorithm for optimization of aeroengine control based on BP neural network[A]. Proceeding of Chinese Control Conference (CCC) [C]. Guangzhou: IEEE, 2019.

[9]孙丽荣,王国栋,文雄,等.热轧带钢卷取温度前馈补偿的方法研究[J].重型机械,2022,(3):68-72.

Sun L R, Wang G D, Wen X, et al. Research on feedforward compensation method of system identification for coiling temperature of hot strip mills [J]. Heavy Machinery,2022,(3):68-72.

[10]张帅,王俊杰,李爱莲,等. 基于改进GWO-ELM的热轧带钢卷取温度预测[J]. 电子测量技术, 2021, 44(22): 50-55.

Zhang S, Wang J J, Li A L, et al. Improved GWO-ELM based hot rolled strip coiling temperature prediction[J]. Electronic Measurement Technology, 2021, 44(22):50-55.

[11]张坚,双远华,胡建华,等.基于改进的BP神经网络无缝钢管连轧轧制力的预测[J].锻压技术,2022,47(5):153-160.

Zhang J, Shuang Y H, Hu J H, et al. Prediction on rolling force in continuous rolling of seamless steel pipe based on improved BP neural network[J]. Forging & Stamping Technology,2022,47(5):153-160.

[12]朱其萍,徐红玉,王晓强,等.基于PSO-BP的超声滚挤压轴承套圈表面加工硬化程度预测[J].锻压技术,2021,46(11):190-196.

Zhu Q P, Xu H Y, Wang X Q, et al. Prediction on degree of work hardening for surface of bearing ring by ultrasonic rolling extrusion based on PSO-BP[J]. Forging & Stamping Technology, 2021,46(11):190-196.

[13]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 Y, Su Z X, Yang J, 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.

[14]Dong Y K, Zhang Y, Liu F B, et al. Research on an optimization method for injection-production parameters based on an improved particle swarm optimization algorithm[J]. Energies, 2022, 15(8): 1-18.

[15]Wang Y T, Liu J, Li R, et al. Application of PSO-BPNN-PID controller in nutrient solution EC precise control system: Applied research[J]. Sensors, 2022, 22(15): 58.

[16]魏学松,田海,周继平. 卷曲温度控制系统的研究与设计[J]. 自动化应用, 2021，(10): 4-9.

Wei X S, Tian H, Zhou J P. Research and design of curling temperature control system[J]. Automation Application, 2021，(10): 4-9.

服务与反馈：

【文章下载】【加入收藏】