基于工业大数据的厚板板形预报系统研发

doi:10.11959/j.issn.2096-3750.2021.00239

Abstract

Abstract:

Thick plate shape is one of the important indicators to measure the quality of thick plate products.The timely prediction of the final plate shape in production is of great significance for adjusting the operation and control of thick plate production.In actual industrial production, thick plate data has many characteristics, such as multiple coupling information, large amount of redundant information, and multi-source heterogeneity of data.Combining the needs of thick plate shape prediction, a thick plate shape prediction system was designed and developed.The data dump function was used to filter and preprocess the industrial big data to remove the coupling information and redundant variables in the data.LSTM neural network, convolutional neural network and 3D convolutional neural network were used to extract data features from data of different dimensions, and the features were fused based on the maximum mutual information coefficient to establish an integrated learning prediction model, which effectively solved the modeling difficulties caused by multi-source heterogeneous data.The actual industrial data of a domestic thick plate production line was used for verification, and the results showed the effectiveness of the developed system.

Key words: thick plate shape, prediction model, multi-source heterogeneous data, system development

CLC Number:

TP18

Yufei MA, Changxin LIU, Wei KONG, Jinliang DING. Research and development of thick plate shape prediction system based on industrial big data[J]. Chinese Journal on Internet of Things, 2021, 5(3): 39-48.

Figures/Tables 9

References 20

[1]	SCHAUSBERGER F , STEINBOECK A , KUGI A . Optimization-based reduction of contour errors of heavy plates in hot rolling[J]. Journal of Process Control, 2016,47: 150-160.
[2]	XIE B S , CAI Q W , YUN Y ,et al. Development of high strength ultra-heavy plate processed with gradient temperature rolling,intercritical quenching and tempering[J]. Materials Science and Engineering:A, 2017,680: 454-468.
[3]	MA X B , LIU H M , SUN J L ,et al. Impact of main drive system of 5 m wide and heavy plate mill on screw-down load deviation[J]. Engineering Failure Analysis, 2017,79: 913-927.
[4]	王国栋 . 高质量中厚板生产关键共性技术研发现状和前景[J]. 轧钢, 2019,36(1): 1-8,30.
	WANG G D . Status and prospects of research and development of key common technologies for high-quality heavy and medium plate production[J]. Steel Rolling, 2019,36(1): 1-8,30.
[5]	LAUGWITZ M , SEUREN S , JOCHUM M ,et al. Development of levelling strategies for heavy plates via controlled FE models[J]. Procedia Engineering, 2017,207: 1349-1354.
[6]	SCHAUSBERGER F , STEINBOECK A , KUGI A . Feedback control of the contour shape in heavy-plate hot rolling[J]. IEEE Transactions on Control Systems Technology, 2018,26(3): 842-856.
[7]	YU W , LI G S , CAI Q W . Effect of a novel gradient temperature rolling process on deformation,microstructure and mechanical properties of ultra-heavy plate[J]. Journal of Materials Processing Technology, 2015,217: 317-326.
[8]	BASANTA-VAL P . An efficient industrial big-data engine[J]. IEEE Transactions on Industrial Informatics, 2018,14(4): 1361-1369.
[9]	WANG T , KE H X , ZHENG X ,et al. Big data cleaning based on mobile edge computing in industrial sensor-cloud[J]. IEEE Transactions on Industrial Informatics, 2020,16(2): 1321-1329.
[10]	焦四海, 丁建华, 闫博 ,等. 厚板数据中心和智能制造的实践与探索[J]. 宝钢技术, 2020(6): 8-15.
	JIAO S H , DING J H , YAN B ,et al. Practice and exploration data center and intelligent manufacture of plate mill[J]. Baosteel Technology, 2020(6): 8-15.
[11]	GUO K H , XU T , KUI X Y ,et al. iFusion:towards efficient intelligence fusion for deep learning from real-time and heterogeneous data[J]. Information Fusion, 2019,51: 215-223.
[12]	NGUYEN T T , PHAM X C , LIEW A W C ,et al. Aggregation of classifiers:a justifiable information granularity approach[J]. IEEE Transactions on Cybernetics, 2019,49(6): 2168-2177.
[13]	王国栋 . 近年我国轧制技术的发展、现状和前景[J]. 轧钢, 2017,34(1): 1-8.
	WANG G D . Development,current situation and prospect of Chinese steel rolling technology in recent years[J]. Steel Rolling, 2017,34(1): 1-8.
[14]	GENG D Q , ZHANG C Y , XIA C J ,et al. Big data-based improved data acquisition and storage system for designing industrial data platform[J]. IEEE Access, 2019,7: 44574-44582.
[15]	FABLET R , VIET P H , LGUENSAT R . Data-driven models for the spatio-temporal interpolation of satellite-derived SST fields[J]. IEEE Transactions on Computational Imaging, 2017,3(4): 647-657.
[16]	JIANG X X , PAN S R , LONG G D ,et al. Cost-sensitive parallel learning framework for insurance intelligence operation[J]. IEEE Transactions on Industrial Electronics, 2019,66(12): 9713-9723.
[17]	LEE S Y , TAMA B A , CHOI C ,et al. Spatial and sequential deep learning approach for predicting temperature distribution in a steel-making continuous casting process[J]. IEEE Access, 2020,8: 21953-21965.
[18]	RESHEF D N , RESHEF Y A , FINUCANE H K ,et al. Detecting novel associations in large data sets[J]. Science, 2011,334(6062): 1518-1524.
[19]	ZHANG K , LIU N , YUAN X F ,et al. Fine-grained age estimation in the wild with attention LSTM networks[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020,30(9): 3140-3152.
[20]	CAO H C , LIU H , SONG E M ,et al. Multi-branch ensemble learning architecture based on 3D CNN for false positive reduction in lung nodule detection[J]. IEEE Access, 2019,7: 67380-67391.

Metrics

Recommended 0

No Suggested Reading articles found!

NO.	数据集	训练集	验证集	测试集
1	Data1	5 601	622	1 000
2	Data2	12 759	1 417	1 000
3	Data3	16 838	1 870	1 000
4	Data4	18 354	2 039	1 000
5	Data5	20 477	2 275	1 000

Research and development of thick plate shape prediction system based on industrial big data

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 20

Related Articles 10

Metrics

Recommended 0

[1]	Biao ZHANG, Ximing WANG, Yifan XU, Wen LI, Hao HAN, Songyi LIU, Xueqiang CHEN. Multi-domain collaborative anti-jamming based on multi-agent deep reinforcement learning [J]. Chinese Journal on Internet of Things, 2022, 6(4): 104-116.
[2]	Zihui LUO, Chengling JIANG, Liang LIU, Xiaolong ZHENG, Huadong MA. Research on deep reinforcement learning based intelligent shop scheduling method [J]. Chinese Journal on Internet of Things, 2022, 6(1): 53-64.
[3]	Jiajun WANG, Wei CAO, Guilong ZHANG, Huaizhi ZHANG, Zixing LING, Xiaoqiang ZHAO. Neural network wind speed prediction based on multiple prediction model and nonlinear combination [J]. Chinese Journal on Internet of Things, 2021, 5(4): 81-89.
[4]	Jianwei LIU, Bin JIANG, Pu YANG. Health-based network node importance assessment [J]. Chinese Journal on Internet of Things, 2021, 5(3): 21-26.
[5]	Yongjun XU, Haoke YANG, Yinghui YE, Qianbin CHEN, Guangyue LU. A survey on resource allocation in backscatter communication networks [J]. Chinese Journal on Internet of Things, 2021, 5(3): 56-69.
[6]	Yuan HUANG, Gang WU, Junyong LIU, Chenxi YANG, Mengpin GAO. Research and design of the intelligent energy management and control platform in the airport area based on the IoT technology [J]. Chinese Journal on Internet of Things, 2021, 5(2): 125-133.
[7]	Xiaoqiang ZHAO, Fan YANG, Zhufeng YAN. Prediction method of soil water content based on SVM optimized by improved salp swarm algorithm [J]. Chinese Journal on Internet of Things, 2021, 5(1): 99-107.
[8]	Shimin FENG,Enjie DING,Zhongyu LIU,Xiao YU,Lei MENG,Zhikai ZHAO. Research on methods of workers’ context description in mines [J]. Chinese Journal on Internet of Things, 2019, 3(4): 9-16.
[9]	Chi JIN,Zhijun LI,Dayang SUN,Fengye HU. Human activity recognition algorithm based on the spatial feature for WBAN [J]. Chinese Journal on Internet of Things, 2019, 3(3): 70-75.
[10]	Shimin FENG,Zhongyu LIU,Xiao YU,Lei MENG,Zhikai ZHAO,Enjie DING. Workers’ context description and unsafe behavior recognition in Internet of things for mines [J]. Chinese Journal on Internet of Things, 2018, 2(4): 93-98.