锻压技术

带收缩因子粒子群优化算法对热轧负荷分配的优化

英文标题：Optimization on hot rolling load distribution by particle swarm optimization algorithm with constriction factor

作者：张汉文仲兆准黄虎

分类号：TP18

出版年,卷(期):页码：2020,45(6):194-199

摘要：

为提高实际生产中的热轧带钢质量及生产效率，建立了兼顾负荷均衡和板形最优的负荷分配模型，采用传统经验法对负荷进行初步分配，并在基本粒子群优化算法中引入收缩因子，提出基于带收缩因子的粒子群优化算法，对初始分配结果进行优化。研究表明，与基本粒子群优化算法相比，收缩因子的引入能够有效地控制粒子的飞行速度，并改善粒子群优化算法的局部搜索能力，增强算法的收敛精度与收敛速度。函数测试结果显示，带收缩因子的粒子群优化算法在3类基准函数中的精度均为最优。负荷分配仿真模拟结果表明，该算法可以很好地满足轧制力和相对凸度的目标需求，体现了带收缩因子的粒子群优化算法的优越性与有效性。

In order to improve the quality of hot rolled strip steel and the efficiency of production in actual production, the load distribution model that took into account both load balance and optimal sheet shape was established, and the load was preliminarily distributed by the traditional empirical method. Then, the constriction factor was introduced into the basic particle swarm optimization (PSO) algorithm, and the particle swarm optimization algorithm with constriction factor was proposed to optimize the initial distribution results. The results show that compared with the basic PSO algorithm, the introduction of constriction factor effectively controls the particle flight speed, improves the local search ability of PSO algorithm, and enhances the convergence accuracy and speed of the algorithm. The function test result shows that the PSO algorithm with the constriction factor has the best accuracy among the three types of benchmark functions. Furthermore, the simulation results of load distribution show that the above algorithm meets the requirements of rolling force and relative convexity very well and shows the superiority and effectiveness of PSO algorithm with constriction factor.

基金项目：

国家自然科学基金资助项目（61304095）

张汉文（1994-），男，硕士研究生 E-mail：535171586@qq.com 通讯作者：仲兆准（1980-），男，博士，副教授 E-mail：nustzzz@163.com

参考文献：

［1］姬亚锋. 基于负荷平衡的监控AGC在热连轧中的应用
［J］. 中国冶金, 2014, 24(2):36-39.

Ji Y F. Algorithm design and application of monitor AGC based on load balance
［J］. China Metallurgy, 2014, 24(2):36-39.

［2］李维刚, 刘超, 卞皓，等. 热连轧机负荷分配优化计算策略
［J］. 钢铁研究学报, 2017,29(5): 391-396.

Li W G, Liu C, Bian H, et al. Optimization calculation strategy of load distribution for hot strip mills
［J］. Journal of Iron and Steel Research, 2017,29(5): 391-396.

［3］谷向磊, 黄长清, 蔡央, 等. 智能算法优化轧制规程的优缺点及发展趋势
［J］. 热加工工艺, 2018,47(21): 1-6.

Gu X L, Huang C Q, Cai Y, et al. Advantages and disadvantages of intelligent algorithm for optimizing rolling schedule and its development trend
［J］. Hot Working Technology, 2018,47(21): 1-6.

［4］王焱, 刘景录, 孙一康. 免疫遗传算法对精轧机组负荷分配的优化
［J］. 北京科技大学学报, 2002, 24(3): 339-341.

Wang Y, Liu J L, Sun Y K. Immune genetic algorithms(IGA)based scheduling optimization for finisher
［J］. Journal of University of Science and Technology Beijing, 2002, 24(3): 339-341.

［5］林伟路, 丁小凤, 双远华. BP神经网络对斜轧穿孔轧制力的预测
［J］. 锻压技术, 2018, 43(10):175-178.

Lin W L, Ding X F, Shuang Y H. Prediction on rolling force of oblique rolling piercing based on BP neural network
［J］. Forging & Stamping Technology, 2018, 43(10):175-178.

［6］张良. 基于BP神经网络的预切冲裁断面质量的仿真预测
［J］. 锻压技术, 2018, 43(12):175-179.

Zhang L. Simulation and prediction of cross-section quality for pre-cut blanking based on BP neural network
［J］. Forging & Stamping Technology, 2018, 43(12):175-179.

［7］高蕾, 庞玉华, 孙列, 等. 热连轧精轧带钢厚度预报模型优化研究
［J］. 热加工工艺, 2013, 42(11): 92-95.

Gao L, Pang Y H, Sun L, et al. Optimization of prediction model of thickness in hot continuous precise rolling strip steel
［J］. Hot Working Technology, 2013, 42(11): 92-95.

［8］Hai-Jun L I, Jian-Zhong X U, Wang G D, et al. Improvement on conventional load distribution algorithm in hot tandem mills
［J］. Journal of Iron and Steel Research International, 2007, 14(2): 36-41.

［9］张进之. 热连轧机负荷分配方法的分析和综述
［J］. 宽厚板, 2004, 10(3): 14-21.

Zhang J Z. Analysis and summarization of load distribution method for hot continuous rolling mill
［J］. Wide and Heavy Plate, 2004, 10(3): 14-21.

［10］姚峰, 杨卫东, 张明. 改进粒子群算法及其在热连轧负荷分配中的应用
［J］. 北京科技大学学报, 2009, 31(8): 1061-1066.

Yao F, Yang W D, Zhang M. Improved PSO and its application to load distribution optimization of hot strip mills
［J］. Journal of University of Science and Technology Beijing, 2009, 31(8): 1061-1066.

［11］李荣雨, 张卫杰, 周志勇. 改进的粒子群算法在轧制负荷分配中的优化
［J］. 计算机科学, 2018, 45(7): 220-224，231.

Li R Y, Zhang W J, Zhou Z Y. Improved PSO algorithm and its load distribution of hot strip mills
［J］. Computer Science, 2018, 45(7): 220-224,231.

［12］徐双. 混合粒子群算法在板带热连轧负荷分配中的应用研究
［D］. 北京：冶金自动化研究设计院, 2018.

Xu S. Research and Application of Hybrid Particle Swarm Optimization Algorithm in Load Distribution for Tandem Hot Metal Strip Rolling
［D］. Beijing：Automation Research and Design Institute of Metallurgical Industry, 2018.

［13］贾树晋. 热轧生产计划与负荷分配的多目标群智能算法研究
［D］. 上海：上海交通大学, 2012.

Jia S J. Research on Multi-objective Swarm Intelligence Algorithm for Hot Rolling Production Planning and Load Distribution
［D］. Shanghai：Shanghai Jiao Tong University,2012.

［14］Eberhart R C. Comparing inertia weights and constriction factors in particle swarm optimization
［A］. Proceedings of the 2000 IEEE Congress on Evolutionary Computation
［C］. La Jolla, CA:IEEE, 2000.

服务与反馈：

【文章下载】【加入收藏】