基于LSTM-JITRVM的冷轧轧制力建模方法研究

孙浩; 赵明达; 李静; 魏立新; 呼子宇

doi:10.3969/j.issn.1000-1158.2023.09.14

PDF(593 KB)

计量学报 ›› 2023, Vol. 44 ›› Issue (9) : 1409-1416. DOI: 10.3969/j.issn.1000-1158.2023.09.14

力学计量

基于LSTM-JITRVM的冷轧轧制力建模方法研究

孙浩¹,赵明达¹,李静²,魏立新¹,呼子宇¹

作者信息 +

Research on Modeling Method of Cold Rolling Force Based on LSTM-JITRVM

SUN Hao¹,ZHAO Ming-da¹,LI Jing²,WEI Li-xin¹,HU Zi-yu¹

Author information +

文章历史 +

摘要

在带钢冷连轧生产过程中,轧制力预测准确度直接影响产品质量。为提高轧制力预测准确度,提出了基于LSTM-JITRVM(long short term memory- just in time relevance vector machine)的轧制力模型。首先,使用循环自编码网络对输入数据进行深层次特征提取,然后使用局部离群因子算法判断测试样本与其邻域点是否属于同一分布,针对不同的分布使用不同的自学习回归模型进行拟合。仿真结果表明,该模型预测准确度可控制在3%以内,能够实现轧制力的高准确度在线预测。

Abstract

In the process of strip cold rolling, the accuracy rolling force directly affects the product quality. In order to further improve the prediction accuracy of rolling force, a rolling force model based on LSTM-JITRVM (long short term memory- just in time relevance vector machine) is proposed. Firstly, the auto-encoding network is used to extract the deep-seated features of the input data. Then the local outlier factor algorithm is used to judge whether the test sample and its neighborhood points belong to the same distribution, and different self-learning regression models are used to fit different distributions. The simulation results show that the prediction accuracy of the model can be controlled within 3%, and the rolling force can be predicted online with high precision.

导出引用

孙浩,赵明达,李静,魏立新,呼子宇. 基于LSTM-JITRVM的冷轧轧制力建模方法研究[J]. 计量学报. 2023, 44(9): 1409-1416 https://doi.org/10.3969/j.issn.1000-1158.2023.09.14

SUN Hao,ZHAO Ming-da,LI Jing,WEI Li-xin,HU Zi-yu. Research on Modeling Method of Cold Rolling Force Based on LSTM-JITRVM[J]. Acta Metrologica Sinica. 2023, 44(9): 1409-1416 https://doi.org/10.3969/j.issn.1000-1158.2023.09.14

中图分类号： TB931

参考文献

［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］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.
［3］Zhang S H, Deng L, Che L Z. An integrated model of rolling force for extra-thick plate by combining theoretical model and neural network model［J］. Journal of Manufacturing Processes, 2022, 75: 100-109.
［4］Yin J C, Perakis A N, Wang N. A real-time ship roll motion prediction using wavelet transform and variable RBF network ［J］. Ocean Engineering, 2018, 160: 10-19.
［5］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 M H, Zhang Q, Liu Y H, et al. Prediction of hot rolling force based on machine learning ［J］. Forging & Stamping Technology, 2021, 46(10): 233-241.
［6］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.
［7］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.
［8］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.
［9］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.
［10］魏立新, 翟博豪, 赵志伟, 等. 基于半监督深度网络的冷连轧轧制力预报［J］. 塑性工程学报, 2020, 27(11): 70-76.
Wei L X, Zhai B H, Zhao Z W, et al. Prediction of continuous cold rolling force based on semi supervised depth network ［J］. Journal of Plastic Engineering, 2020, 27(11): 70-76.
［11］Lee S, Son Y. Motor Load Balancing with Roll Force Prediction for a Cold-Rolling Setup with Neural Networks［J］. Mathematics, 2021, 9(12):1-21.
［12］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): 2070-2076.
Wei L X, Wei X Y, Sun H, et al. Prediction of aluminum hot rolling Force based on deep network training ［J］. Chinese Journal of Nonferrous Metals, 2018, 28(10): 128-134.
［13］Gama J, Liobait I, Bifet A, et al. A Survey on Concept Drift Adaptation ［J］. ACM Computing Surveys, 2014, 46(4): 1-37.
［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］Breunig M M, Kriegel H P, Ng R T, et al. LOF: Identifying Densitybased Local Outliers［C］//International Conference on Management of Data. Dallas, TX, 2000: 93-104.
［16］Jrges C, Berkenbrink C, Stumpe B. Prediction and reconstruction of ocean wave heights based on bathymetric data using LSTM neural networks［J］. Ocean Engineering, 2021, 232: 109046-109064.
［17］Chen Z W, Shi N, Ji Y F, et al. Lithium-ion batteries remaining useful life prediction based on BLS-RVM ［J］. Energy, 2021, 234(87): 121269.
［18］Li Z X, Hao K R, Chen L, et al. PET Viscosity Prediction Using JIT-based Extreme Learning Machine［J］. IFAC-PapersOnLine, 2018, 51(18): 608-613.
［19］Guo F, Xie R M, Huang B. A Deep Learning Just-in-Time Modeling Approach for Soft Sensor Based on Variational Autoencoder ［J］. Chemometrics and Intelligent Laboratory Systems, 2020, 197:103922-103930.
［20］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.

基金

国家重点研发计划(2018YFB1702300);国家自然科学基金(62003296,62073276);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);河北省省级重点实验室绩效补助经费项目(22567612H)