| 184 | 3 | 178 |
| 下载次数 | 被引频次 | 阅读次数 |
电解温度与稀土熔盐电解槽电流效率、炉体寿命紧密相关，然而热电偶测温、红外热成像等测量方法受电解车间高温强腐蚀环境影响难以实时检测。基于YOLOv8算法对熔盐电解槽炉面温度进行预测。首先，通过高温试验炉自制温度数据集并基于YOLOv8算法训练获得温度区间分类模型；其次，采用图像灰度与温度关系式重建炉面图像温度云图；最后，基于YOLOv8-SSW算法构建了炉面温度图像识别模型，其预测准确率为93.4%，可用于电解槽炉面温度监测。
Abstract：The electrolytic temperature is closely related to the current efficiency of the rare earth molten salt electrolyzer and the life of the furnace body. However, it is difficult to detect the electrolytic temperature in real time by thermocouple measurement and infrared thermal imaging due to the high temperature and strong corrosive environment of the electrolysis workshop. The furnace surface temperature of molten salt electrolyzer was predicted based on YOLOv8 algorithm. Firstly, the temperature interval classification model was obtained through the selfmade temperature data set of high temperature test furnace and trained based on YOLOv8 algorithm. Secondly, the temperature cloud map of the furnace surface image was reconstructed using the relationship between image gray level and temperature. Finally, the image recognition model of furnace surface temperature was constructed based on YOLOv8-SSW algorithm, and its prediction accuracy is 93. 4%, which can be used to monitor the furnace surface temperature of electrolytic cell.
[1]ABBASALIZADEH A,MALFLIET A,SEETHARAMAN S,et al.Electrochemical extraction of rare earth metals in molten fluorides:conversion of rare earth oxides into rare earth fluorides using fluoride additives[J].Journal of Sustainable Metallurgy,2017,3:627-637.
[2]BASTIEN P,FRAN?OIS A,MARTIN D,et al.Error correction for temperature measurement in insulating material:application to the aluminum electrolysis cell[J].Inter national Jou r nal of Thermal Sciences,2023,195:108682.DOI:10.1016/j.ijthermalsci.2023.108682.
[3]ALLARD F,DéSILETS M,LEBREUX M,et al.Improved heat transfer modeling of the top of aluminum electrolysis cells[J].International Journal of Heat and Mass Transfer,2019,132:1262-1276.
[4]MARTINEZ I,OTAMENDI U,OLAIZOL A I G,et al.A novel method for error analysis in radiation thermometry with application to industrial furnaces[J].Measurement,2022,190:110646.DOI:10.1016/j.measurement.2021.110646.
[5]?VANTNER M,VACíKOVáP,HONNER M.Noncontact charge temperature measurement on industrial continuous furnaces and steel charge emissivity analysis[J].Infrared Physics&Technology,2013,61:20-26.
[6]邵艳明，赵书安，陈延如，等.基于多光谱测温法的转炉炉口火焰温度预测研究[J].光学学报，2015,35(11):323-329.SHAO Y M,ZHAO S A,CHEN Y R,et al.Temperature measurement of flame at converter mouth based on multi-spectral thermometry[J].Acta Optica Sinica,2015,35(11):323-329.
[7]雷雨田，王庆凯，王旭.基于动态随机森林算法的铜浮选精矿品位预测[J].矿冶，2022,31(6):110-113.LEI Y T,WANG Q K,WANG X.Grade prediction of copper flotation concentrate based on dynamic random forest algorithm[J].Mining and Metallurgy,2022,31(6):110-113.
[8]余东原，罗跃，梁大业，等.基于机器学习方法预测地浸过程中铀浸出金属量的变化[J].有色金属（冶炼部分），2024(2):92-98.YU D Y,LUO Y,LIANG D Y,et al.Predicting the variation of uranium leaching metal content in ground-leaching process based on machine learning methods[J].Nonferrous Metals(Extractive Metallurgy),2024(2):92-98.
[9]王永平，张红民，彭闯，等.基于YOLOv3的高压开关设备异常发热点目标检测方法[J].红外技术，2020,42(10):983-987.WANG Y P,ZHANG H M,PENG C,et al.The target detection method for abnormal heating point of highvoltage switchgear based on YOLOv3[J].Infrared Technology,2020,42(10):983-987.
[10]张悦，梁珊珊.基于改进Node2vec算法的锅炉温度场分割方法研究[J].电力科学与工程，2024,40(5):72-78.ZHANG Y,LIANG S S.Research on boiler temperature field segmentation method based on improved Node2vec algorithm[J].Electric Power Science and Engineering,2024,40(5):72-78.
[11]MANISH K S,AMITAVA C,DUSHYANT U,et al.Correlation and prediction of molten steel temperature in steel melting shop using reliable machine learning(RML)approach[J].Transactions of the Indian Institute of Metals,2023,76(12):3365-3377.
[12]翟乃举，周晓锋，李帅，等.基于迁移学习和知识蒸馏的加热炉温度预测[J].计算机集成制造系统，2022,28(6):1860-1869.ZHAI N J,ZHOU X F,LI S,et al.Prediction method of furnace temperature based on transfer learning and knowledge distillation[J].Computer Integrated Manufacturing Systems,2022,28(6):1860-1869.
[13]JI Z Y,TAO W H,ZHANG L X.A boiler oxygen content and furnace temperature prediction model based on honey badger algorithm optimized neural network[J].Engineering Research Express,2024,6:015083.DOI:10.1088/2631-8695/ad22be.
[14]LUO B X,KOU Z M,HAN C,et al.A“hardwarefriendly”foreign object identification method for belt conveyors based on improved YOLOv8[J].Applied Sciences,2023,13(20):11464.DOI:10.3390/app132011464.
[15]刘惠中，王志岩，姜勇，等.基于改进YOLOv5算法的锌电解阴极板剥锌残留物识别[J].有色金属工程，2023,13(10):37-45.LIU H Z,WANG Z Y,JIANG Y,et al.Recognition of zinc stripping residues in zinc electrolytic cathode plates based on improved YOLOv5 algorithm[J].Nonferrous Metals Engineering,2023,13(10):37-45.
[16]李晓磊，黄传庆，郑博，等.基于YOLO-v5的Ti-48Al-2Cr-2Nb合金高温析出相智能识别[J].有色金属工程，2023,13(9):33-41.LI X L,HUANG C Q,ZHENG B,et al.Intelligent identification of high temperature precipitated phase in Ti-48Al-2Cr-2Nb alloy based on YOLO-v5[J].Nonferrous Metals Engineering,2023,13(9):33-41.
[17]SAYDIRASULOVICH S N,MUKHIDDINOV M,DJURAEV O,et al.An improved wildfire smoke detection based on YOLOv8 and UAV images[J].Sensors,2023,23(20):8347.DOI:10.3390/s23208374.
[18]XIAO X,FENG X L.Multi-object pedestrian tracking using improved YOLOv8 and OC-SORT[J].Sensors,2023,23(20):8439.DOI:10.3390/s23208439.
[19]SOYLU E,SOYLU T.A performance comparison of YOLOv8 models for traffic sign detection in the Robotaxi-full scale autonomous vehicle competition[J].Multimedia Tools and Applications,2024,83:25005-25035.
[20]WANG Y S,HAN X B,WEI X X,et al.Instance segmentation frustum-point pillars:a lightweight fusion algorithm for camera-Li DAR perception in autonomous driving[J].Mathematics,2024,12(1):153-174.
[21]KUMAR D,MUHAMMAD N.Object detection in adverse weather for autonomous driving through data merging and YOLOv8[J].Sensors,2023,23(20):8471.DOI:10.3390/s23208471.
[22]LUO M L,XU L H,YANG Y L,et al.Laboratory flame smoke detection based on an improved YOLOXalgorithm[J].Applied Sciences,2022,12(24):12876.DOI:10.3390/app122411464.
[23]赖镜安，陈紫强，孙宗威，等.基于YOLOv5的轻量级雾天目标检测方法[J].计算机工程与应用，2024,60(6):78-88.LAI J A,CHEN Z Q,SUN Z W,et al.Lightweight foggy weather object detection method based on YOLOv5[J].Computer Engineering and Applications,2024,60(6):78-88.
[24]WANG Z W,LU H Z,JIN J L,et al.Human action recognition based on improved two-stream convolution network[J].Applied Sciences,2022,12(12):5784.DOI:10.3390/app12125784.
[25]CHEN D,PENG Q Z,LU J T,et al.PYS:a classification and extraction model of photovoltaics for providing more detailed data to support photovoltaic sustainable development[J].Sustainable Energy Technologies and Assessments,2023,60:103578.DOI:10.1016/j.seta.2023.103578.
[26]杨建辉，黄子洋，汪梅，等.机器视觉灰度化金字塔卷积模型的煤流异物识别[J].煤炭科学技术，2022,50(11):194-201.YANG J H,HUANG Z Y,WANG M,et al.Recognition of unwanted objects in coal flow based on gray pyramid convolution model of machine vision[J].Coal Science and Technology,2022,50(11):194-201.
[27]ZOU H,HUANG F Z.A novel intelligent fault diagnosis method for electrical equipment using infrared thermography[J].Infrared Physics&Technology,2015,73:29-35.
[28]戚凯旋，朱凌云.基于图像处理的燃气锅炉燃烧状态检测研究[J].自动化仪表，2021,42(11):34-38.QI K X,ZHU L Y.Research on combustion state detection of gas boiler based on image processing[J].Process Automation Instrumentation,2021,42(11):34-38.
基本信息:
DOI：10.20237/j.issn.1007-7545.2025.01.012
中图分类号:TF845
引用信息:
[1]侯伟,黄金堤,李明周,等.基于YOLOv8算法的稀土熔盐电解槽炉面温度监测研究[J].有色金属(冶炼部分),2025(01):84-91.DOI:10.20237/j.issn.1007-7545.2025.01.012.
基金信息:
高性能钢铁合金材料江西省重点实验室项目（2024SSY05041）; 江西理工大学清江优秀青年人才计划项目（JXUSTQJYX2020016）;江西理工大学科研基金（205200100517）
2024-06-17
2024
2024-07-02
2024-07-03
2024
1
2024-12-31
2024-12-31