|
|
Flatness pattern recognition model based on recurrent neural network |
SONG Ming-ming1,WANG Dong-cheng1, 2,ZHANG Shuai1,XU Yang-huan1,LIU Hong-min1, 2 |
(1. National Engineering Research Center for Equipment and Technology of Cold Rolling Strip,Yanshan University,Qinhuangdao 066004, Hebei, China 2. State Key Laboratory of Metastable Materials Science and Technology,Yanshan University, Qinhuangdao 066004, Hebei, China ) |
|
|
Abstract The flatness pattern recognition is the key link of the flatness control. The traditional flatness pattern recognition has some shortcomings,such as the poor recognition precision and the poor anti-interference ability. With the complexity of the data regression tasks increasing,the classification algorithm based on the deep learning has been used for many tasks such as the data classification, the image processing,the pattern recognition and the feature extraction. A deep learning can achieve a complex function approximation by learning a kind of deep nonlinear network structure. Based on this background,a flatness pattern recognition model based on the recurrent neural network was proposed. The results showed that the flatness pattern recognition model based on RNN could achieve the training of large flatness data,and the recognition accuracy and the generalization ability of the model were very high. It provides a new method for the further improvement of the accuracy of the flatness control.
|
Received: 26 March 2018
Published: 20 November 2018
|
|
|
|
[1] |
张雪伟, 王焱. 智能识别方法在板形识别中的应用及发展趋势[J]. 钢铁研究学报, 2010, 22(1): 1-3.ZHANG Xue-wei, WANG Yan. Application and development trend of intelligent recognition methods for flatness recognition[J]. Journalof Iron and Steel Research, 2010, 22(1): 1-3.
|
[1] |
张雪伟, 王焱. 智能识别方法在板形识别中的应用及发展趋势[J]. 钢铁研究学报, 2010, 22(1): 1-3.ZHANG Xue-wei, WANG Yan. Application and development trend of intelligent recognition methods for flatness recognition[J]. Journalof Iron and Steel Research, 2010, 22(1): 1-3.
|
[2] |
王益群, 尹国芳, 孙旭光. 板形信号模式识别方法的研究[J]. 机械工程学报, 2003, 39(8): 91-94.WANG Yi-qun, YIN Guo-fang, SUN Guang-xu. Research on pattern recognition method of flatness signal[J]. Chinese Journal of Machine Engineering, 2003, 39(8): 91-94.
|
[2] |
王益群, 尹国芳, 孙旭光. 板形信号模式识别方法的研究[J]. 机械工程学报, 2003, 39(8): 91-94.WANG Yi-qun, YIN Guo-fang, SUN Guang-xu. Research on pattern recognition method of flatness signal[J]. Chinese Journal of Machine Engineering, 2003, 39(8): 91-94.
|
[3] |
张秀玲, 刘宏民. 板形模式识别的GA-BP模型和改进的最小二乘法[J]. 钢铁研究学报, 2003, 38(10): 29-34. ZHANG Xiu-ling, LIU Hong-min, Ga-bp model of flatness pattern recongnition and improved least-squares method[J]. Journal of Iron and Steel Research, 2003, 38(10): 29-34.
|
[3] |
张秀玲, 刘宏民. 板形模式识别的GA-BP模型和改进的最小二乘法[J]. 钢铁研究学报, 2003, 38(10): 29-34. ZHANG Xiu-ling, LIU Hong-min, Ga-bp model of flatness pattern recongnition and improved least-squares method[J]. Journal of Iron and Steel Research, 2003, 38(10): 29-34.
|
[4] |
JIA Chun-yu, SHAN Xiu-ying, LIU Hong-min, et al. Fuzzy neural model for flatness pattern recongnition[J]. Journal of Iron and Steel Research, International, 2008, 15(6): 33-38.
|
[4] |
JIA Chun-yu, SHAN Xiu-ying, LIU Hong-min, et al. Fuzzy neural model for flatness pattern recongnition[J]. Journal of Iron and Steel Research, International, 2008, 15(6): 33-38.
|
[5] |
Hinton G E. Learning multiple layers of representation[J]. Trends in Congnitive Sciences, 2007, 11(10): 428-434.
|
[5] |
Hinton G E. Learning multiple layers of representation[J]. Trends in Congnitive Sciences, 2007, 11(10): 428-434.
|
[6] |
孙志军, 薛磊, 许阳明, 王正. 深度学习研究综述[J]. 计算机应用研究, 2012, 29(8): 2806-2810.SUN Zhi-jun, HAN Lei, XU Yang-ming, WANG Zheng. Overview of deep learning[J]. Application Research of Computers, 2012, 29(8): 2806-2810.
|
[6] |
孙志军, 薛磊, 许阳明, 王正. 深度学习研究综述[J]. 计算机应用研究, 2012, 29(8): 2806-2810.SUN Zhi-jun, HAN Lei, XU Yang-ming, WANG Zheng. Overview of deep learning[J]. Application Research of Computers, 2012, 29(8): 2806-2810.
|
[7] |
Zhang Xiao-lei, Wu Ji. Denoising deep neural networks based voice activity detention detention[C]//IEEE International Conference on Acoustics, Speech and Signal Processing, 2013: 853-857.
|
[7] |
Zhang Xiao-lei, Wu Ji. Denoising deep neural networks based voice activity detention detention[C]//IEEE International Conference on Acoustics, Speech and Signal Processing, 2013: 853-857.
|
[8] |
Stuhlsatz A, Lippel J, Zielke T. Feature extraction with deep neural networks by a generalized discriminant analysis [J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(4): 596-608.
|
[8] |
Stuhlsatz A, Lippel J, Zielke T. Feature extraction with deep neural networks by a generalized discriminant analysis [J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(4): 596-608.
|
[9] |
Ciresan D, Meier U, Masci J, et al. Multi-column deep neural network for traffic sign classification[J]. Neural Networks, 2012, 32: 333-338.
|
[9] |
Ciresan D, Meier U, Masci J, et al. Multi-column deep neural network for traffic sign classification[J]. Neural Networks, 2012, 32: 333-338.
|
[10] |
Carnerio G, Nascimento J C. Combining multiple dynamic models and deep learning architectures for tracking the left ventricle endocardium in ultrasound data[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(11): 2592-2607.
|
[10] |
Carnerio G, Nascimento J C. Combining multiple dynamic models and deep learning architectures for tracking the left ventricle endocardium in ultrasound data[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(11): 2592-2607.
|
[11] |
单修迎, 刘宏民, 贾春玉. 含有三次板形的新型板形模式识别方法[J]. 钢铁研究学报, 2010, 45(8): 56-60.SHAN Xiu-ying, LIU Hong-ming, JIA Chun-yu. A recognition method of new flatness pattern containing the cubic flatness[J]. Journal of Iron and Steel Research, 2010, 45(8): 56-60.
|
[11] |
单修迎, 刘宏民, 贾春玉. 含有三次板形的新型板形模式识别方法[J]. 钢铁研究学报, 2010, 45(8): 56-60.SHAN Xiu-ying, LIU Hong-ming, JIA Chun-yu. A recognition method of new flatness pattern containing the cubic flatness[J]. Journal of Iron and Steel Research, 2010, 45(8): 56-60.
|
[12] |
ZHANG Xiu-ling,ZHANG Shao-yu,TAN Guang-zhong, et al. A novel method for flatness pattern recognition via least squares support vector regression[J]. Journal of Iorn and Steel Research, International. 2012, 19(3): 25-30.
|
[12] |
ZHANG Xiu-ling,ZHANG Shao-yu,TAN Guang-zhong, et al. A novel method for flatness pattern recognition via least squares support vector regression[J]. Journal of Iorn and Steel Research, International. 2012, 19(3): 25-30.
|
[13] |
任海鹏, 刘丁. 一种基于遗传算法的板形模式识别方法[J]. 重型机械, 2002(3): 9-12.REN Hai-peng, LIU Ding, A cenetic algorithm approach to shape pattern recognition[J]. Heavy Machine, 2002(3): 9-12.
|
[13] |
任海鹏, 刘丁. 一种基于遗传算法的板形模式识别方法[J]. 重型机械, 2002(3): 9-12.REN Hai-peng, LIU Ding, A cenetic algorithm approach to shape pattern recognition[J]. Heavy Machine, 2002(3): 9-12.
|
[14] |
Hinton G E, Osindero S. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
|
[14] |
Hinton G E, Osindero S. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
|
[15] |
Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
|
[15] |
Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
|
[16] |
Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems, 2012: 1097-1105.
|
[16] |
Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems, 2012: 1097-1105.
|
[17] |
Alpayd E. 机器人学习导论[M]. 范明, 等译. 北京: 机械工业出版社, 2009, 10(12): 1-40.Alpayd E. Introduction to Robot Learning [M]. Translation of Fan Ming and others. Beijing: Machinery Industry Press, 2009, 10(12): 1-40.
|
[17] |
Alpayd E. 机器人学习导论[M]. 范明, 等译. 北京: 机械工业出版社, 2009, 10(12): 1-40.Alpayd E. Introduction to Robot Learning [M]. Translation of Fan Ming and others. Beijing: Machinery Industry Press, 2009, 10(12): 1-40.
|
[18] |
Hinton G E, Training products of experts by minimizing contrastive divergence[J]. Neural Computation. 2002. 14(8): 1771-1800.
|
[18] |
Hinton G E, Training products of experts by minimizing contrastive divergence[J]. Neural Computation. 2002. 14(8): 1771-1800.
|
[19] |
Rumelhart D E, Hinton G E,Williams R J. Learning representions by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536.
|
[19] |
Rumelhart D E, Hinton G E,Williams R J. Learning representions by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536.
|
[20] |
Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation,1997, 9(8): 1735-1780.
|
[20] |
Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation,1997, 9(8): 1735-1780.
|
[21] |
Ger F A,Schimidhuber J. Recurrent nets that time and count[C]// Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. 2000, 3:189-194.
|
[21] |
Ger F A,Schimidhuber J. Recurrent nets that time and count[C]// Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. 2000, 3:189-194.
|
[22] |
Ger F A,Schmidhuber J,Cummins F. Learning to forget: continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471.
|
[22] |
Ger F A,Schmidhuber J,Cummins F. Learning to forget: continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471.
|
[23] |
张秀玲,刘宏民. 变结构神经网络在板形信号模式识别方面的应用[J]. 钢铁研究学报, 2001, 13(2): 62-66.ZHANG Xiu-ling, LIU Hong-min. Pattern recognition of shape signal by variable structure neural network[J]. Journal of Iron and Steel Research, 2001, 13(2): 62-66.
|
[23] |
张秀玲,刘宏民. 变结构神经网络在板形信号模式识别方面的应用[J]. 钢铁研究学报, 2001, 13(2): 62-66.ZHANG Xiu-ling, LIU Hong-min. Pattern recognition of shape signal by variable structure neural network[J]. Journal of Iron and Steel Research, 2001, 13(2): 62-66.
|
[24] |
郑绪枝, 雷靖, 夏薇. 基于快速确定隐层神经元数的BP神经网络算法[J]. 计算机科学, 2012, 39(6), 432-436.ZHENG Xu-zhi, DOU Jing, XIA Wei. Algorithm for bp neural networks by identifying numbers of hidden layer neurons quickly[J]. Computer Science, 2012, 39(6), 432-436.
|
[24] |
郑绪枝, 雷靖, 夏薇. 基于快速确定隐层神经元数的BP神经网络算法[J]. 计算机科学, 2012, 39(6), 432-436.ZHENG Xu-zhi, DOU Jing, XIA Wei. Algorithm for bp neural networks by identifying numbers of hidden layer neurons quickly[J]. Computer Science, 2012, 39(6), 432-436.
|
[25] |
张雨浓, 郭东生, 谭宁, 幂激励前向神经网络最优结构确定算法[J]. 计算机工程与应用, 2011, 47(2): 29-31.ZHANG Yu-nong, GUO Dong-sheng, TAN Ning.Optimal-structure determination of power-activation feed-forward neural net[J]. Computer Engineering and Applications, 2011, 47(2): 29-31.
|
[25] |
张雨浓, 郭东生, 谭宁, 幂激励前向神经网络最优结构确定算法[J]. 计算机工程与应用, 2011, 47(2): 29-31.ZHANG Yu-nong, GUO Dong-sheng, TAN Ning.Optimal-structure determination of power-activation feed-forward neural net[J]. Computer Engineering and Applications, 2011, 47(2): 29-31.
|
[26] |
DP Kingma, J Ba. ADAM: A method for stochastic optimization[J]. Computer Science, 2014:1-15.
|
[26] |
DP Kingma, J Ba. ADAM: A method for stochastic optimization[J]. Computer Science, 2014:1-15.
|
[1] |
TANG Wei, DU Feng-shan, LIN Hai-hai, WEN Jie. Control technology of cold rolled high-strength container plate′s rolling stability[J]. Iron and Steel, 2020, 55(1): 65-71. |
[2] |
LI Wei-gang1,CHEN Jing-cheng1,FAN Li-xia2,XIE Lu1. Automatic identification of microstructure of iron and steel material based on convolutional neural network[J]. JOURNAL OF IRON AND STEEL RESEARCH , 2020, 32(1): 33-43. |
[3] |
MA Wei1,LI Wei-gang1,2,ZHAO Yun-tao1,YAN Bao-kang1. Prediction of hot-rolled roll force based on deep learning[J]. JOURNAL OF IRON AND STEEL RESEARCH , 2019, 31(9): 805-815. |
[4] |
YU Huaxin,WANG Dongcheng,LIU Hongmin,ZHANG Shuai,YANG Lipo. Electric drive scheme design of flatness meter for cold rolling strip[J]. Iron and Steel, 2019, 54(7): 56-60. |
[5] |
ZHANG Dian- hua,SUN Jie,CHEN Shu- zong,LI Xu. Intelligent optimization control of tandem cold rolling process for high precision thin strip[J]. , 2019, 31(2): 180-189. |
[6] |
BAI Zhen-hua, XU Peng, WANG Xiao-lei, HE Zhao-long, WANG Yun-xiang. Development of comprehensive optimum setting technology for roll profile curve of continuous annealing unit[J]. Iron and Steel, 2019, 54(12): 48-54. |
|
|
|
|