基于循环自编码网络的冷轧轧制力建模方法

doi:10.3969/j.issn.1000-1158.2022.09.11

摘要
图/表
参考文献(18)
相关文章 (15)

全文: PDF (1849 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要在钢铁冷连轧生产过程中,轧制力预测结果直接影响带材的轧制精度和产品质量。为进一步提高轧制力预测精度,同时实现模型的在线更新,避免漂移问题,提出了基于循环自编码网络的轧制力模型。首先,使用循环自编码网络对处理好的输入数据进行特征提取,为了加速网络训练,加入了小批量训练方法,然后使用高斯过程回归模型对提取到的特征进行回归拟合。仿真结果表明,该模型预测精度可达3%以内,能够实现轧制力的高精度在线预测。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	孙浩
	叶国良
	翟博豪
	呼子宇
	赵志伟

关键词 ：计量学, 轧制力预测, 冷连轧;机器学习, 循环自编码网络

Abstract：In the process of cold continuous rolling of steel, the prediction results of rolling force directly affect the rolling precision and product quality of strip. A rolling force model based on AEGRU (autotncoder and gate recurrent unit) network is proposed to improve the accuracy of rolling force prediction, update the model online and avoid the drift problem. First of all, the processed input data is extracted through the AEGRU network. In order to speed up the network training, the mini-batch training method is added. Then the extracted features is fitted by the Gaussian process regression model. The simulation results exhibit that the prediction accuracy of the model can be up to 3%, and the rolling force can be predicted online with high precision.

Key words： metrology rolling force prediction cold rolling machine learning autotncoder and gate recurrent unit network

收稿日期: 2021-03-10 发布日期: 2022-09-19

PACS:

TB931

基金资助:国家自然科学基金(62003296, 62073276, 61803327); 河北省自然科学基金(F2020203031, E2019105123); 河北省高等学校科学技术研究项目(QN2020225, ZD2019311)

作者简介: 孙浩(1985-), 男, 河北霸州人, 燕山大学讲师, 博士, 主要从事进化计算、板带轧制方面的研究。Email:sunhao@ysu.edu.cn

引用本文:

孙浩,叶国良,翟博豪,呼子宇,赵志伟. 基于循环自编码网络的冷轧轧制力建模方法[J]. 计量学报, 2022, 43(9): 1172-1177.
SUN Hao,YE Guo-liang,ZHAI Bo-hao,HU Zi-yu,ZHAO Zhi-wei. Research on Cold Rolling Force Modeling Method Based on AEGRU Network. Acta Metrologica Sinica, 2022, 43(9): 1172-1177.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.09.11 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I9/1172

［1］魏立新, 王恒, 孙浩, 等. 基于改进深度信念网络训练的冷轧轧制力预报［J］. 计量学报, 2021, 42(7):906-912.
Wei L X, Wang H, Sun H, et al. Prediction of cold rolling force based on improved deep belief network training［J］.Acta Metrologica Sinica, 2021, 42(7):906-912.
［2］魏立新, 张宇, 孙浩, 等. 基于改进OS-ELM的冷连轧在线轧制力预报［J］. 计量学报, 2019, 40(1):111-116.
Wei L X, Zhang Y, Sun H, et al. On-line rolling force prediction of tandem cold rolling based on improved OS-ELM［J］. Acta Metrologica Sinica, 2019, 40(1):111-116.
［3］Hu Z Y, Wei Z H, Sun H, et al. Optimization of Metal Rolling Control Using Soft Computing Approaches: A Review［J］. Archives of Computational Methods in Engineering, 2021, 28(2):405-421.
［4］杨景明, 陈伟明, 车海军, 等. 基于粒子群算法优化支持向量机的铝热连轧机轧制力预报［J］. 计量学报, 2016, 37(1):71-74.
Yang J M, Chen W M, Che H J, et al. Prediction of rolling force of aluminum hot tandem Mill based on particle swarm optimization and support vector machine ［J］. Acta Metrologica Sinica, 2016, 37(1):71-74.
［5］白振华, 宋和川, 侯彬, 等. 冷轧机组升降速过程轧制压力变化模型及其影响因素研究［J］. 塑性工程学报, 2017, 24(3):135-141.
Bai Z H, Song H C, Hou B, et al. Influencing factors of rolling pressure and its change model in the speed up and down process of cold rolling mill［J］. Journal of Plastic Engineering, 2017, 24(3):135-141.
［6］朱宝, 乔俊飞. 基于自编码神经网络特征提取的回声状态网络研究及过程建模应用［J］. 化工学报, 2019, 70(12):258-264.
Zhu B, Qiao J F. Research and application of echo state network based on self-coding neural network feature extraction［J］. CIESC Journal, 2019, 70(12):258-264.
［7］Jin H P, Chen X G, Yang J W, et al. Multi-model adaptive soft sensor modeling method using local learning and online support vector regression for nonlinear time-variant batch processes［J］. Chemical Engineering Science, 2015, 131: 282-303.
［8］Yin X H, Niu Z W, He Z, et al. Ensemble deep learning based semi-supervised soft sensor modeling method and its application on quality prediction for coal preparation process［J］. Advanced Engineering Informatics, 2020, 46: 101136-101150.
［9］喻胜华, 邓娟. 基于主成分分析和贝叶斯正则化BP神经网络的GDP预测［J］. 湖南大学学报(社会科学版), 2011, 25(6):42-45.
Yu S H, Deng J. GDP prediction based on principal component analysis and Bayesian regularization BP neural network［J］. Journal of Hunan University (Social Sciences), 2011, 25(6):42-45.
［10］曹卫华, 李熙, 吴敏, 等. 基于极限学习机的热轧薄板轧制力预测模型［J］. 信息与控制, 2014, 43(3):270-275.
Cao W H, Li X,Wu M, et al. Prediction model of hot rolled sheet rolling force based on limit learning machine［J］. Information and Control, 2014, 43(3):270-275.
［11］杨景明, 郭秋辰, 孙浩, 等. 基于改进果蝇算法与最小二乘支持向量机的轧制力预测算法研究［J］. 计量学报, 2016, 37(5):505-508.
Yang J M, Guo Q C, Sun H, et al. Research on Rolling Force Prediction Algorithm Based on Improved Fruit Fly Algorithm and Least Squares Support Vector Machine［J］. Acta Metrologica Sinica, 2016, 37(5):505-508.
［12］Mahmoodkhani Y, Wells M A, Song G. Prediction of roll force in skin pass rolling using numerical and artificial neural network methods［J］. Ironmaking & Steelmaking, 2017,44(4):280-286.
［13］金秀章, 李京. 基于互信息PSO-LSSVM的SO2浓度预测［J］. 计量学报, 2021, 42(5):675-680.
Jin X Z, Li J. Prediction of SO2 concentration based on mutual information PSO-LSSVM［J］. Acta Metrologica Sinica, 2021,42(5):675-680.
［14］Zhang X Y, Ge Z Q. Automatic Deep Extraction of Robust Dynamic Features for Industrial Big Data Modeling and Soft Sensor Application［J］. IEEE Transactions on Industrial Informatics, 2019,16(7): 4456-4467.
［15］Ma Y, Li H G. GRU-Auto-Encoder neural network based methods for diagnosing abnormal operating conditions of steam drums in coal gasification plants［J］. Computers & Chemical Engineering, 2020, 143(8):107097-107118.
［16］张研, 苏国韶, 燕柳斌. 基于高斯过程机器学习方法的隧道围岩分类模型［J］. 现代隧道技术, 2011, 48(6):32-37.
Zhang Y, Su G S,Yan L B. Classification of surrounding rocks in tunnel based on Gaussian process machine learning［J］. Modern Tunneling Technology, 2011, 48(6):32-37.
［17］Ding Z Y, Zhang J, Liu Y. Ensemble Non-Gaussian Local Regression for Industrial Silicon Content Prediction［J］. ISIJ Internationa, 2017, 57(11): 2022-2027.
［18］魏立新, 魏新宇, 孙浩, 等. 基于深度网络训练的铝热轧轧制力预报［J］. 中国有色金属学报, 2018, 28(10):128-134.
Wei L X, Wei X Y, Sun H, et al. Prediction of aluminum hot rolling Force based on deep network training［J］. The Chinese Journal of Nonferrous Metals, 2018, 28(10):128-134.