连铸黏结漏钢发生机理及预报模型  

Mechanism and forecast model of sticker breakout in continuous casting

作　　者：王荣荣 王敏 王仲亮[3] 邢立东 艾新港 包燕平[3] WANG Rongrong;WANG Min;WANG Zhongliang;XING Lidong;AI Xingang;BAO Yanping(School of Civil and Resource Engineering,University of Science and Technology Beijing,Beijing 100083,China;HBIS Materials Technology Research Institute,Shijiazhuang 052165,Hebei,China;State Key Laboratory of Advanced Metallurgy,University of Science and Technology Beijing,Beijing 100083,China;Technical Support Center for Prevention and Control of Disastrous Accidents in Metal Smelting,University of Science and Technology Beijing,Beijing 100083,China;School of Materials and Metallurgy,University of Science and Technology Liaoning,Anshan 114051,Liaoning,China)

机构地区：[1]北京科技大学土木与资源工程学院,北京100083 [2]河钢材料技术研究院,河北石家庄052165 [3]北京科技大学钢铁冶金新技术国家重点实验室,北京100083 [4]北京科技大学金属冶炼重大事故防控技术支撑基地,北京100083 [5]辽宁科技大学材料与冶金学院,辽宁鞍山114051

出　　处：《中国冶金》2023年第11期138-150,共13页China Metallurgy

基　　金：中央引导地方科技发展资金项目(2023JH6/100100046,YDZJSX2022C028)。

摘　　要：连铸是炼钢过程非常重要的工序之一。连铸过程多发漏钢事故,其影响因素多且机理复杂,其中以黏结漏钢最为常见,约占总漏钢事故的70%。连铸漏钢事故造成钢液泄漏,容易发生灼烫、火灾甚至爆炸等安全事故,造成人员伤亡和巨大的财产损失。为解决上述问题,剖析了黏结裂口的扩展方式和黏结漏钢的形成机理;基于热电偶测温法预报黏结漏钢的原理,利用神经网络建立黏结漏钢预报模型,并运用遗传算法完成神经网络的优化,预报模型测试样本的正确报出率达到100%,预报率为97.56%;对空间网络模型进行了验证,A型空间网络模型的输出符合期望,可以实现黏结在空间裂口扩展的预报。模型具有很好的应用价值,可为连铸安全生产提供支撑。Continuous casting is one of the most important processes in the steel making process.There are many steel leakage accidents in the continuous casting process,which have many influencing factors and complex mechanisms.Among them,sticker breakout is the most common accident,accounting for about 70%of the total steel leakage.Continuous casting leakage can easily cause steel leakage,burns,fires and even explosions,resulting in casualties and huge property losses.In view of the above difficulties,the expansion of sticker fracture and the formation mechanism of sticker breakout were analyzed,the principle of forecasting sticker breakout was proposed based on thermocouple temperature measurement method and a sticker breakout forecasting model was established using neural network.The correct reporting rate of the test samples for sticker breakout forecasting model reached 100%,the forecasting rate was 97.56%.The spatial network model was verified,the output of the A-type spatial network met the expectation and could achieve the prediction of bonding in the spatial fracture expansion.The model has good application value and can provide support for the safe production of continuous casting.

关 键 词：连铸 黏结漏钢 漏钢预报 神经网络 漏钢机理 

分 类 号：TF777[冶金工程—钢铁冶金]