|
|
Research on Cold Rolling Force Prediction Model Based on Improved Deep Belief Network |
WEI Li-xin1,2,WANG Heng1,2,SUN Hao1,2,HU Zi-yu1,2 |
1. Intelligent Control System and Intelligent Equipment Engineering Research Center of Ministry of Education,Yanshan University, Qinhuangdao, Hebei 066004, China
2. Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao, Hebei 066004, China |
|
|
Abstract In the cold rolling process of strip steel, the accuracy of rolling force prediction directly determines the rolling precision and product quality of the strip. The traditional single-hidden layer-based neural network modeling method is simple in structure, and the expression ability and generalization ability of complex functions are restricted. The rolling site environment is complex, and data measurement has noise interference,which will directly affect the forecasting accuracy. Regarding the issue above, an improved deep belief network prediction model based on unsupervised learning is proposed. The construction of denoising-restricted Boltzmann machines and deep networks can improve the systems ability to learn the characteristics of input data, while training the deep network with improved contrast divergence algorithm.Finally,the model is tested by using the measured data of a steel mills 1200mm rolling mill, and three different models are compared and analyzed. The results show that the average relative error of the rolling force prediction of the model is controlled within 4.5%, and the time required for modeling is reduced by 26% compared to the self-encoding network.
|
Received: 18 November 2019
Published: 15 July 2021
|
|
|
|
|
[1]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. Online Cold Rolling Prediction Based on Improved OS-ELM[J]. Acta Metrologica Sinica, 2019, 40 (1): 111-116.
[2]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, 2016, 44 (4): 281-286.
[3]Yin J C, Anastassios N. Perakis. A real-time ship roll motion prediction using wavelet transform and variable RBF network[J]. Ocean Engineering, 2018, 160 (15): 10-19.
[4]牛培峰, 丁翔, 刘楠, 等. 基于混合鸡群算法和核极端学习机的锅炉NOx排放的预测[J]. 计量学报, 2019, 40 (5): 929-936.
Niu P F, Ding F, Liu N, et al. Prediction of Boiler NOx Emission Based on Mixed Chicken Swarm Algorithm and Kernel Extreme Learning Machine [J]. Acta Metrologica Sinica, 2019, 40 (5): 929-936.
[5]Bagheripoor M, Bisadi H. Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process [J]. Applied Mathematical Mode-lling, 2013, 37 (7): 4593-4607.
[6]陶功明, 吴郭贤, 朱华林, 等. 基于高斯过程构建钢轨轧制力模型的方法[J]. 轧钢, 2019, 36 (3): 42-46.
Tao G M, Wu G X, Zhu H L, et al. A method of constructing rail rolling force model based on Gauss process[J]. Steel Rolling, 2019, 36 (3): 42-46.
[7]Chen Z M, Luo Z L. Rolling force prediction based on multiple support vector machines[C]//Proceedings of the 32nd Chinese Control Conference. Xian, China, 2013: 3306-3309.
[8]赵志伟, 杨景明, 车海军, 等. 基于人工蜂群算法与反向传播神经网络的铝热连轧轧制力预测[J]. 计量学报, 2014, 35 (2): 157-160.
Zhao Z W, Yang J M, Che H J, et al. Prediction of Rolling Force Based on Artificial Bee Colony Algorithm and Back Propagation Neural Network in Aluminum Hot Tandem Rolling [J]. Acta Metrologica Sinica, 2014, 35 (2): 157-160.
[9]王智, 张果, 王剑平, 等. 基于PSO-BP神经网络双机架炉卷轧机轧制力的预测[J]. 钢铁研究, 2017, 45 (3): 23-26.
Wang Z, Zhang G, Wang J P, et al. Prediction of rolling force for two-stand steckel mill based on PSO-BP neural network [J]. Research on Iron &Steel, 2017, 45 (3): 23-26.
[10]窦博. 热连轧轧制力贝叶斯神经网络预测与模型优化[J]. 金属制品, 2017, 43 (6): 42-48.
Dou B. Prediction of rolling force and model optimization with Bayes neural network[J]. Metal Products, 2017, 43 (6): 42-48.
[11]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. A Rolling Force Prediction Model for Hot Rolled Sheets Based on Extreme Learning Machine [J]. Information and Control, 2014, 43 (3): 270-275.
[12]马威, 李维刚, 赵云涛, 等. 基于深度学习的热连轧轧制力预报[J]. 钢铁研究学报, 2019, 31 (9): 805-815.
Ma W, Li W G, Zhao Y T, et al. Prediction of hot-rolled roll force based on deep learning[J]. Journal of Iron and Steel Research, 2019, 31 (9): 805-815.
[13]HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18 (7): 1527-1554.
[14]李飞, 高晓光, 万开方. 基于权值动量的RBM加速学习算法研究[J]. 自动化学报, 2018, 43 (7): 1142-1159.
Li F, Gao X G, Wan K F. Research on RBM Accelera-ting Learning Algorithm with Weight Momentum [J]. Acta Automatica Sinica, 2018, 43 (7): 1142-1159.
[15]李飞, 高晓光, 万开方. 基于动态Gibbs采样的RBM训练算法研究[J]. 自动化学报, 2016, 42 (6): 931-942.
Li F, Gao X G, Wan K F. Research on RBM Training Algorithm with Dynamic Gibbs Sampling [J]. Acta Automatica Sinica, 2016, 42 (6): 931-942.
[16]杨杰, 孙亚东, 张俊良, 等. 基于弱监督学习的去噪受限玻尔兹曼机特征提取算法[J]. 电子学报, 2014, 42 (12): 2365-2370.
Yang J, Sun Y D, Zhang J L, et al. Weakly Supervised Learning with Denoising Restricted Boltzmann Machines for Extracting Features [J]. Acta Electronica Sinica, 2014, 42 (12): 2365-2370.
[17]李飞, 高晓光, 万开方. 基于改进并行回火算法的RBM网络训练研究[J]. 自动化学报, 2017, 43 (5): 753-764.
Li F, Gao X G, Wan K F. Research on RBM Networks Training Based on Improved Parallel Tempering Algorithm [J]. Acta Electronica Sinica, 2017, 43 (5): 753-764.
[18]刘彬, 姜甲浩, 刘飞, 等. 基于轧件水平振动的轧机辊系振动补偿模型[J]. 计量学报, 2018, 39 (1): 56-60.
Liu B, Jiang J H, Liu F, et al. Compensative Vibration Model of Roll System Based on Horizontal Vibration of Rolled Piece [J]. Acta Metrologica Sinica, 2018, 39 (1): 56-60.
[19]杨景明, 孙晓娜, 车海军, 等. 基于蚁群算法的神经网络冷连轧轧机轧制力预报[J]. 钢铁, 2009, 44 (3): 52-55.
Yang J M, Sun X N, Che H J, et al. Neural Network Based on Ant Colony Algorithm for Rolling Force Prediction on Tandem Cold Rolling Mill [J]. Iron and Steel, 2009, 44 (3): 52-55.
[20]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[J]. The Chinese Journal of Nonferrous Metals, 2018, 28 (10): 2070-2076. |
|
|
|