[1]刘明华,张强.支持向量机与神经网络相结合的板带凸度预测[J].智能系统学报,2022,17(3):506-514.[doi:10.11992/tis.202101002]
LIU Minghua,ZHANG Qiang.Prediction of strip crown based on support vector machine and neural network[J].CAAI Transactions on Intelligent Systems,2022,17(3):506-514.[doi:10.11992/tis.202101002]
点击复制
LIU Minghua,ZHANG Qiang.Prediction of strip crown based on support vector machine and neural network[J].CAAI Transactions on Intelligent Systems,2022,17(3):506-514.[doi:10.11992/tis.202101002]
支持向量机与神经网络相结合的板带凸度预测
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
17
期数:
2022年第3期
页码:
506-514
栏目:
学术论文—机器学习
出版日期:
2022-05-05
- Title:
- Prediction of strip crown based on support vector machine and neural network
- Keywords:
- support vector regression; neural network; strip crown; particle swarm optimization algorithm; hot strip rolling process; machine learning; prediction; big data
- 分类号:
- TP16
- 摘要:
- 为提高热轧生产过程中板带凸度的预测精度，提出了一种将粒子群优化算法(particle swarm optimization, PSO)、支持向量回归(support vector regression, SVR)和BP神经网络(back propagation neural network, BPNN)相结合的板带凸度预测模型。采用PSO算法优化SVR模型的参数，建立了PSO-SVR板带凸度预测模型，提出采用BPNN建立板带凸度偏差模型与PSO-SVR板带凸度模型相结合的方法对板带凸度进行预测。采用现场数据对模型的预测精度进行验证，并采用统计指标评价模型的综合性能。仿真结果表明，与PSO-SVR、SVR、BPNN和GA-SVR模型进行比较，PSO-SVR+BPNN模型具有较高的学习能力和泛化能力，并且比GA-SVR模型运算时间短。
- Abstract:
- To improve the prediction accuracy of strip crown in a hot-rolled production process, a modeling method combining particle swarm optimization (PSO) algorithm, support vector regression (SVR), and BP neural network (BPNN) is proposed. The PSO algorithm was employed to optimize the parameters of the SVR model, and the PSO–SVR strip crown prediction model was established. A method combining the BPNN strip crown deviation model with the PSO–SVR strip crown model is also proposed to predict the strip crown. The prediction accuracy of the model was validated with field experimental data, and the comprehensive performance of the model was evaluated using statistical indicators. The simulation results show that in contrast to the PSO–SVR, SVR, BPNN, and GA-SVR models, the PSO–SVR+BPNN model exhibits a greater learning capacity and generalization ability. The computing time of the PSO–SVR+BPNN model is also less than that of the GA-SVR model.
- 参考文献/References:
-
[1] 薛涛, 杜凤山, 孙静娜, 等. 基于FEM-ANN的冷轧带钢轧制力预报[J]. 中南大学学报:自然科学版, 2013, 44(11): 4456–4460
XUE Tao, DU Fengshan, SUN Jingna, et al. Rolling force prediction of cold strip rolling based on FEM-ANN[J]. Journal of Central South University: (science and technology edition), 2013, 44(11): 4456–4460
[2] DENG Jifei, SUN Jie, PENG Wen, et al. Application of neural networks for predicting hot-rolled strip crown[J]. Applied soft computing, 2019, 78: 119–131.
[3] SAMAREH S P H, KHADEMHOSSEINI B H, ALIZADEH Y, et al. Calculation of work roll initial crown based on desired strip profile in hot rolling[J]. Neural Computing and Applications, 2013, 24(5): 1123–1133.
[4] 张强. 基于支持向量机的热轧板带轧制力预测[D]. 西安: 西安建筑科技大学, 2021: 2.
ZHANG Qiang. Prediction of rolling force of hot rolled strip based on support vector machine[D]. Xi’an: Xi’an University of Architecture and Technology, 2021: 2.
[5] CHUN M S, BIGLOU J, Lenard J G, et al. Using neural networks to predict parameters in the hot working of aluminum alloys[J]. Journal of materials processing technology, 1999, 86: 245–251.
[6] 冀秀梅, 王龙, 高克伟, 等. 极限学习机在中厚板轧制力预报中的应用[J]. 钢铁研究学报, 2020, 32(5): 393–399
JI Xiumei, WANG Long, GAO Kewei, et al. Application of ELM to predict plate rolling force[J]. Journal of iron and steel research, 2020, 32(5): 393–399
[7] 马威, 李维刚, 赵云涛, 等. 基于深度学习的热连轧轧制力预测[J]. 钢铁研究学报, 2019, 31(9): 805–815
MA Wei, LI Weigang, ZHAO Yuntao, et al. Prediction of hot-rolled roll force based on deep learning[J]. Journal of iron and steel research, 2019, 31(9): 805–815
[8] WANG Liyong, LI Le, ZHANG Zhihua. Accurate descriptions of hot flow behaviors across β Transus of Ti-6Al-4V alloy by intelligence algorithm GA-SVR[J]. Journal of materials engineering and performance, 2016, 25(9): 3912–3923.
[9] 王前锋. 基于改进型支持向量机算法的轧机轧制力预测[J]. 锻压技术, 2019, 44(4): 131–137
WANG Qianfeng. Rolling force prediction of rolling mill based on improved support vector machine algorithm[J]. Forging and stamping technology, 2019, 44(4): 131–137
[10] 方敏. 轧制过程板形预测控制的研究[D]. 杭州: 杭州电子科技大学, 2015: 55.
FANG Min. Research on flatness prediction control in rolling process[D]. Hangzhou: Hangzhou Dianzi University, 2015: 55.
[11] 朱永波, 张飞, 张勇军, 等. 基于粒子群优化的带钢凸度神经网络预测模型研究[J]. 冶金自动化, 2019, 43(2): 11–15
ZHU Yongbo, ZHANG Fei, ZHANG Yongjun, et al. Particle swarm optimized neural network for strip crown prediction model research[J]. Metallurgical industry automation, 2019, 43(2): 11–15
[12] CHENG M Y, HOANG N D, WU Y W. Hybrid intelligence approach based on LS-SVM and differential evolution for construction cost index estimation: A Taiwan case study[J]. Automation in construction, 2013, 35: 306–313.
[13] VAPNIK V N. The nature of statistical learning theory[J]. IEEE transactions on neural networks, 1997, 8(6): 1564–1564.
[14] VAPNIK V N. An overview of statistical learning theory[J]. IEEE transactions on neural networks, 1999, 10(5): 988–999.
[15] WANG Hu, LI Enying, LI Guangyao. The least square support vector regression coupled with parallel sampling scheme metamodeling technique and application in sheet forming optimization[J]. Materials and design, 2009, 30(5): 1468–1479.
[16] FEI Shengwei, HE Chuangxin. Prediction of dissolved gases content in power transformer oil using BASA-based mixed kernel RVR model[J]. International journal of green energy, 2019, 16(8): 652–656.
[17] WU Dongsheng, YANG Qin, WANG Dazhi. Rolling force prediction based on PSO optimized support vector regression[C]//Seventh International Conference on Natural Computation. Shanghai: IEEE, 2011: 839–483.
[18] WANG Dongshu, TAN Dapei, LIU Lei. Particle swarm optimization algorithm: an overview[J]. Soft computing, 2017, 22(2): 387–408.
[19] Eberhart R, Kennedy J. A new optimizer using particle swarm theory[C]// Proceedings of the 6th International Symposium on Micro Machine and Human Science. Nagoya: IEEE, 1995: 39–43.
[20] 刘明华, 张强, 刘英华, 等. 基于机器学习的热轧轧制力预测[J]. 锻压技术, 2021, 46(10): 233–241
LIU Minghua, ZHANG Qiang, LIU Yinghua, et al. Rolling force prediction of hot rolling based on machine learning method[J]. Forging and stamping technology, 2021, 46(10): 233–241
[21] 杨轻, 杨忠, 许昌亮, 等. 改进PSO算法及其无人机电力巡线规划应用[J]. 应用科技, 2019, 46(3): 80–85.
YANG Qing, YANG Zhong, XU Changliang, Improved particle swarm optimization algorithm and its application in unmanned aerial vehicle power line patrol[J]. Applied science and technology, 2019, 46(3): 80–85.
[22] 高喜峰, 翟立宾, 徐万海. 应用BP神经网络的柔性圆柱涡激振动预报[J]. 哈尔滨工程大学学报, 2020, 41(8): 1150–1155
GAO Xifeng, ZHAI Libin, XU Wanhai. Predicton of vortex-induced vibration of flexible cylinder using BP neural network[J]. Journal of Harbin Engineering University, 2020, 41(8): 1150–1155
[23] 张旭, 杜景林. 改进PSO-GA-BP的PM2.5浓度预测[J]. 计算机工程与设计, 2019, 40(6): 1718–1723
ZHANG Xu, DU Jinglin. PM2.5 concentration prediction based on improved PSO-GA-BP[J]. Computer engineering and design, 2019, 40(6): 1718–1723
[24] ZHOU Yuting, XIA Yufeng, JIANG Lai, et al. Modeling of the hot flow behaviors for Ti-6Al-4V-0.1Ru alloy by GA-BPNN model and its application[J]. High Temperature materials and processes, 2018, 37(6): 551–562.
- 相似文献/References:
-
[1]丁永生.计算智能的新框架：生物网络结构[J].智能系统学报,2007,2(2):26.
DING Yong-sheng.A new scheme for computational intelligence: bio-network architecture[J].CAAI Transactions on Intelligent Systems,2007,2():26.
[2]徐 雄.人工情感的进化控制系统实现[J].智能系统学报,2008,3(2):135.
XU Xiong.Implementation of an evolutionary control system based on artificial emotion[J].CAAI Transactions on Intelligent Systems,2008,3():135.
[3]周孔丹,李 宁,鲁华祥.单电子电路的鲁棒性研究[J].智能系统学报,2008,3(3):195.
ZHOU Kong-dan,LI Ning,LU Hua-xiang.Researching the robustness of single electron devices[J].CAAI Transactions on Intelligent Systems,2008,3():195.
[4]张米娜,韩红桂,乔俊飞.前馈神经网络结构动态增长-修剪方法[J].智能系统学报,2011,6(2):101.
ZHANG Mina,HAN Honggui,QIAO Junfei.Research on dynamic feedforward neural network structure based on growing and pruning methods[J].CAAI Transactions on Intelligent Systems,2011,6():101.
[5]张文辉,高九州,马静,等.漂浮基空间机器人的径向基神经网络鲁棒自适应控制[J].智能系统学报,2011,6(2):114.
ZHANG Wenhui,GAO Jiuzhou,MA Jing,et al.The RBF neural network robust adaptive control of a freefloating space robot[J].CAAI Transactions on Intelligent Systems,2011,6():114.
[6]薄迎春,乔俊飞,杨刚.一种多模块协同参与的神经网络[J].智能系统学报,2011,6(3):225.
BO Yingchun,QIAO Junfei,YANG Gang.A multimodule cooperative neural network[J].CAAI Transactions on Intelligent Systems,2011,6():225.
[7]蒲兴成,张军,张毅.基于神经网络的改进行为协调控制及其在智能轮椅路径规划中的应用[J].智能系统学报,2011,6(5):456.
PU Xingcheng,ZHANG Jun,ZHANG Yi.Modified behavior coordination for intelligent wheelchair path planning based on a neural network[J].CAAI Transactions on Intelligent Systems,2011,6():456.
[8]段海庆,朱齐丹.基于反步自适应神经网络的船舶航迹控制[J].智能系统学报,2012,7(3):259.
DUAN Haiqing,ZHU Qidan.Trajectory tracking control of ships based onan adaptive backstepping neural network[J].CAAI Transactions on Intelligent Systems,2012,7():259.
[9]乔俊飞,逄泽芳,韩红桂.基于改进粒子群算法的污水处理过程神经网络优化控制[J].智能系统学报,2012,7(5):429.
QIAO Junfei,PANG Zefang,HAN Honggui.Neural network optimal control for wastewater treatment processbased on APSO[J].CAAI Transactions on Intelligent Systems,2012,7():429.
[10]郭一,刘金琨.带执行器饱和的柔性关节机器人位置反馈动态面控制[J].智能系统学报,2013,8(1):21.[doi:10.3969/j.issn.1673-4785.201204012]
GUO Yi,LIU Jinkun.Position feedback dynamic surface control for flexible joint robots with actuator saturation[J].CAAI Transactions on Intelligent Systems,2013,8():21.[doi:10.3969/j.issn.1673-4785.201204012]
备注/Memo
收稿日期:2021-01-02。
作者简介:刘明华，副教授，博士，主要研究方向为轧制过程数模与控制。;张强，硕士研究生，主要研究方向为基于支持向量机板材轧制过程建模。
通讯作者:刘明华.E-mail:lmhxauat@163.com
更新日期/Last Update:
1900-01-01