Application prospects and investigation of image recognition technology in tuyeres monitoring of blast furnace

DUAN Yifan; LIU Ran; LIU Xiaojie; LI Xin; YUAN Xuetao; L&#x000dc; Qing

doi:10.13228/j.boyuan.issn0449-749x.20230510

PDF(9366 KB)

Iron and Steel ›› 2024, Vol. 59 ›› Issue (5) : 56-70. DOI: 10.13228/j.boyuan.issn0449-749x.20230510

Raw Material and Ironmaking

Application prospects and investigation of image recognition technology in tuyeres monitoring of blast furnace

Author information +

History +

Abstract

By extracting the frame image of BF tuyeres' video data, and combining with advanced image recognition algorithm to monitor the working state of tuyeres' area, and analyzing the corresponding blast furnace parameter adjustment strategy in real time, which is conducive to reducing the air rest rate and duration, and at the same time making up for the process defects of the response lag and inaccurate results in judging tuyere's state by relying on manual experience at this stage, so as to ensure the long-term stability and smooth movement of blast furnace. Based on the tuyeres' video data of a domestic steel plant between June 1 to June 31, 2023, four common tuyere abnormalities in ironmaking process were sorted out, and main causes and countermeasures based on the principle of ironmaking were analyzed, including hanging slag, slag inflow, coal cutoff and water leakage. Then, the application route of image recognition technology in blast furnace tuyere recognition and monitoring is summarized, including image preprocessing, tuyere identification and early warning, and implantation of expert experience, and the widely used image recognition algorithms are introduced, including convolutional neural network. Transformer mechanism and graph neural network, and the latter two algorithms are affirmed and respected. Finally, based on the graph convolutional neural network, the monitoring and analysis system 1.0 of the blast furnace tuyere is developed, and its functions are briefly introduced. Adhering to the development principle of low latency and high precision, aiming to explore image recognition's application route of blast furnace tuyere in the future by combing the tuyere anomaly and image recognition algorithm, so as to provide a theoretical reference for China's steel enterprises to select reasonable tuyere monitoring technology and improve the intelligent level of tuyere identification and monitoring.

Key words

blast furnace tuyere monitoring / tuyere abnormalities / image recognition / intelligent construction / blast furnace ironmaking

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

DUAN Yifan, LIU Ran, LIU Xiaojie, et al. Application prospects and investigation of image recognition technology in tuyeres monitoring of blast furnace[J]. Iron and Steel, 2024, 59(5): 56-70 https://doi.org/10.13228/j.boyuan.issn0449-749x.20230510

References

[1] 孙永清, 杨礼平, 徐益军, 等. 湘钢四高炉风口破损原因探讨及对策[J]. 金属材料与冶金工程, 2023, 51(3):43.(SUN Y Q, YANG L P, XU Y J, et al. Discussion on the causes and countermeasures for the damage of the tuyere of No.4 BF of Xiangtan Steel[J]. Metal Materials And Metallurgy Engineering, 2023, 51(3):43.)
[2] 左俊, 尤石, 赵世丹, 等. 马钢2号高炉风口破损的应对措施[J]. 炼铁, 2023, 42(2):17.(ZUO J, YOU S, ZHAO S D, et al. Counter measures for tuyere damage in Masteel No.2 BF[J]. Ironmaking, 2023, 42(2):17.)
[3] 秦亭亭, 马力, 陈超, 等. 高炉风口喷煤流量检测方法研究[J]. 工业计量, 2015, 25(2):36.(QIN T T, MA L, CHEN C, et al. Research on flow detection method of blast furnace tuyere coal injection[J]. Industrial Metrology, 2015, 25(2):36.)
[4] 周东东. 基于图像处理的高炉风口燃烧带温度场研究及应用[D]. 北京:北京科技大学, 2018.(ZHOU D D.Research and Application of Temperature Field of Blast Furnace Combustion Zone Based on Image Processing Technology[D]. Beijing: University of Science and Technology Beijing, 2018.)
[5] SNEHAMOY C, SNEHAMOY C.Genetic algorithms for feature selection of image analysis-based quality monitoring model: An application to an iron mine[J]. Engineering Applications of Artificial Intelligence, 2011, 24(5):786.
[6] XU W G, XIAO P C, ZHU L G, et al.Classification and rating of steel scrap using deep learning[J]. Engineering Applications of Artificial Intelligence, 2023, 123:106241.
[7] 曾敏学. 新钢公司2 500 m³高炉风口摄像系统的应用实践[J]. 中国金属通报, 2022(4):144.(ZENG M X. Application practice of 2 500 m³ blast furnace air outlet camera system of Xingang Company[J]. China Metal Bulletin, 2022(4):144.)
[8] 金焱, 袁辉, 祝俊俊, 等. 高炉风口回旋区内温度分布的模拟分析[J]. 武汉科技大学学报, 2017, 40(1):1.(JIN Y, YUAN H, ZHU J J, et al. Simulation analysis of temperature distribution in raceway of blast furnace[J]. Journal of Wuhan University of Science and Technology, 2017, 40(1):1.)
[9] 李海斌, 高志军, 吕国明. 山西建龙5#高炉炉况波动快速恢复生产实践[J]. 山东冶金, 2022, 44(6):4.(LI H B, GAO Z J, LÜ G M. Practice on fluctuation treatment of furnace condition of No.5 BF in Shanxi Jianlong[J]. Shandong Metallurgy, 2022, 44(6):4.)
[10] 郭俊奎, 马铁林. 高炉风口参数的设计探讨[J]. 河南冶金, 2012, 20(4):27.(GUO J K, MA T L. Design and discussion of BF tuyere parameters[J]. Henan Metallurgy, 2012, 20(4):27.)
[11] 初云祥, 武玉, 高正. 高炉风口灌渣炉况快速恢复实践[J]. 山东冶金, 2022, 44(4):9.(CHU Y X, WU Y, GAO Z. Practice of quick recovery of blast furnace tuyere slag pouring condition[J]. Shandong Metallurgy, 2022, 44(4):9.)
[12] 荀成明. 临钢高炉风口熔损原因分析及建议[J]. 山西冶金, 2013, 36(4):69.(XUN C M. Analysis and suggestions on the causes of melting loss of Lingang blast furnace's tuyeres[J]. Shanxi Metallurgy, 2013, 36(4):69.)
[13] 张天放, 张先玲, 韩涛, 等. 人工智能图像识别技术在高炉风口监测中的应用[J]. 冶金自动化, 2021, 45(3):58.(ZHANG T F, ZHANG X L, HAN T, et al. Application of artificial intelligence image recognition technology in blast furnace tuyere monitoring[J]. Metallurgical Industry Automation, 2021, 45(3):58.)
[14] SONG C W, LI Z Y, LI Y M, et al.Research on blast furnace tuyere image anomaly detection, based on the local channel attention residual mechanism[J]. Applied Sciences, 2023, 13(2):802.
[15] 刘小杰, 邓勇, 李欣, 等. 基于大数据技术的高炉铁水硅含量预测[J]. 中国冶金, 2021, 31(2):10.(LIU X J, DENG Y, LI X, et al. Prediction of silicon content in hot molten of blast furnace based on big data technology[J]. China Metallurgy, 2021, 31(2):10.)
[16] 赵军, 李红玮, 刘小杰, 等. 基于Xgboost的高炉透气性指数预测模型[J]. 中国冶金, 2021, 31(3):22.(ZHAO J, LI H W, LIU X J, et al. Prediction model of permeability index based on XGboost[J]. China Metallurgy, 2021, 31(3):22.)
[17] 董翼宁, 曹景胜, 孙飞宇, 等. 基于OpenCV图像处理的车道线识别研究[J]. 仪器仪表与分析监测, 2023(3):29.(DONG Y N, CAO J S, SUN F Y, et al. Research on lane recognition based on OpenCV image processing[J]. Instrumentation Analysis Monitoring, 2023 (3):29.)
[18] MURPHY P M.Visual image annotation for bowel obstruction: Repeatability and agreement with manual annotation and neural networks[J]. Journal of Digital Imaging, 2023, 36:2179.
[19] 刘键涛. 图像增强算法对基于机器学习的集装箱码头设备自动化视觉应用的影响[J]. 珠江水运, 2023(15):57.(LIU J T. Impact of image enhancement algorithms on the automated visual application of container terminal equipment based on machine learning[J]. Pearl River Water Transport, 2023 (15):57.)
[20] 涂毅晗, 汪普庆. 基于多尺度局部直方图均衡化的矿井图像增强方法[J]. 工矿自动化, 2023, 49(8):94.(TU Y H, WANG P Q. Mine image enhancement method based on multi-scale local histogram equalization[J]. Journal of Mine Automation, 2023, 49(8):94.)
[21] RONG Q J, HU C H, HU X D, et al.Picking point recognition for ripe tomatoes using semantic segmentation and morphological processing[J]. Computers and Electronics in Agriculture, 2023, 210:107923.
[22] 黄健, 韩俊楠. 基于生成对抗网络的图像修复算法[J]. 计算机系统应用, 2023, 32(10):215.(HUANG J, HAN J N. Image inpainting algorithm based on generative adversarial network[J]. Computer Systems and Applications, 2023, 32(10):215.)
[23] 冯莹莹, 邱宇, 张登银. 基于色彩聚类的图像修复[J]. 计算机系统应用, 2023, 32(11):240.(FENG Y Y, QIU Y, ZHANG D Y. Image restoration based on color clustering[J]. Computer Systems and Applications, 2023, 32(11):240.)
[24] DENG Y, HUI S Q, ZHOU S P, et al.Context adaptive network for image inpainting[J]. IEEE transactions on image process, 2023, 32(20):6332.
[25] ZHANG Y F, LI H R, YANG T, et al.Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity[J]. Applied Soft Computing, 2023, 146:110675.
[26] YANG S K, ZHANG X Q, CHEN Y F, et al.UcUNet: A lightweight and precise medical image segmentation network based on efficient large kernel U-shaped convolutional module design[J]. Knowledge-Based Systems, 2023, 278:110868.
[27] 阚玉达. 基于U-Net和改进分水岭算法的露天矿爆堆矿石图像分割方法[J]. 金属矿山, 2023 (8):272.(KAN Y D. An image segmentation method for blast pile ore in open-pit mine based on U-net and improved watershed algorithm[J]. Metal Mine, 2023(8):272.)
[28] 周子懿, 熊海灵. 基于深度学习的图像描述优化策略[J]. 计算机科学, 2023, 50(8):99.(ZHOU Z Y, XIONG H L. Image captioning optimization strategy based on deep learning[J]. Computer Science, 2023, 50(8):99.)
[29] 李浩然, 佘伊伦, 王子滔. 一种基于卷积神经网络的配电网主站告警窗口的图像识别方法[J]. 电子器件, 2023, 46(3):836.(LI H R, YU Y L, WANG Z T. An image identification method for the alarm window of distribution network master station based on CNN[J]. Chinese Journal of Electron Devices, 2023, 46(3):836.)
[30] 张松兰. 基于卷积神经网络的图像识别综述[J]. 西安航空学院学报, 2023, 41(1):74.(ZHANG S L. A review of image recognition based on convolutional neural network[J]. Journal of Xi’an Aeronautical Institute, 2023, 41(1):74.)
[31] LI F, WANG L P, WANG D C, et al.Transfer multiscale adaptive convolutional neural network for few-shot and cross-domain bearing fault diagnosis[J]. Measurement Science and Technology, 2023, 34(12):125002.
[32] 史少菲. 基于卷积神经网络的图像精细识别研究[D]. 长沙: 湖南师范大学, 2018. (SHI S F.Research on the Fine-grained Image Categorization based on Convolution Neural Network[D]. Changsha: Hunan Normal University, 2018.)
[33] 张选, 胡晓娟. 基于GoogLeNet和ResNet的深度融合神经网络在脉搏波识别中的应用[J]. 计算机系统应用, 2019, 28(10):15.(ZHANG X, HU X J. Pulse wave recognition using deep hybrid neural networks based on GoogLeNet and ResNet[J]. Computer Systems and Applications, 2019, 28(10):15.)
[34] KELVIN X, JIMMY L B, RYAN K,et al.Show, attend and tell: Neural image caption generation with visual attention[J]. Computer Science, 2015, 37:2048.
[35] PAN S W, YANG B, WANG S K, et al.Oil well production prediction based on CNN-LSTM model with self-attention mechanism[J]. Energy, 2023, 284:128701.
[36] 李翔, 张涛, 张哲, 等. Transformer在计算机视觉领域的研究综述[J]. 计算机工程与应用, 2023, 59(1):1.(LI X, ZHANG T, ZHANG Z, et al. Survey of transformer research in computer vision[J]. Computer Engineering and Applications, 2023, 59(1):1.)
[37] WEI Y P, LIU H R.Convolutional long-short term memory network with multi-head attention mechanism for traffic flow prediction[J]. Sensors, 2022, 22(20):7994.
[38] YU J, LI J, YU Z, et al.Multimodal transformer with multi-view visual representation for image captioning[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2019, 30(12):1.
[39] GUO L T, LIU J, ZHU X X, et al.Normalized and geometry-aware self-attention network for image captioning[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2020:10324.
[40] WU Z H, PAN S R, CHEN F W, et al.A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1):4.
[41] TACHIBANA M, MURATA T.Semi-supervised learning on network using structure features and graph convolution[J]. Transactions of the Japanese Society for Artificial Intelligence, 2019, 34(5):1.
[42] WILLIAM L H, REX Y, JURE L.Inductive representation learning on large graphs[C]//31st Conference on Neural Information Processing Systems. Long Beach, CA, USA: Curran Associates Inc, 2017:1025.
[43] YANG B, CHEN H L.Predicting circRNA-drug sensitivity associations by learning multimodal networks using graph auto-encoders and attention mechanism[J]. Briefings in Bioinformatics, 2023, 24(1):596.
[44] CHEN Z G, ZHANG D M, LI J P, et al.Prediction of production indicators of fractured-vuggy reservoirs based on improved graph attention network[J]. Engineering Applications of Artificial Intelligence, 2024, 129:107540.
[45] ZHAO Q Q, ZHANG H, HE M Y,et al.Graph pooling via dual-view multi-level infomax[J]. Knowledge-Based Systems, 2023, 260:110089.
[46] 吴勘, 杨能惠. 基于K-means聚类的马王堆帛画色彩特征分析与应用[J]. 包装工程, 2023, 44(16):305.(WU K, YANG N H. Analysis and application of color characteristics of mawangdui silk paintings based on K-means clustering[J]. Packaging Engineering, 2023, 44(16):305.)
[47] 陈树文. 高炉专家系统在太钢高炉的应用[J]. 山西冶金, 2019, 42(6):117.(CHEN S W. Application of blast furnace expert system in TISCO[J]. Shanxi Metallurgy, 2019, 42(6):117.)
[48] 陈令坤. 基于高效冶炼的高炉智能控制系统分析[J]. 冶金自动化, 2021, 45(3):2.(CHEN L K. Analysis of intelligent control system used for high efficiency smelting in blast furnace[J]. Metallurgical Industry Automation, 2021, 45(3):2.)
[49] 胡德顺, 赵正洪, 李泽安, 等. 鞍钢朝阳钢铁2 600 m³高炉强化冶炼生产实践[J]. 鞍钢技术, 2020 (5):50.(HU D S, ZHAO Z H, LI Z A, et al. Intensive smelting and production practice of 2 600 m³ blast furnace of Angang Chaoyang Steel[J]. Angang Technology, 2020(5):50.)