Build deep learning High Serious Endpoint prediction,defect detection,etc. models Secondary oxidation of steel,continuous casting Improvement from process Low Serious leakage,etc. route and operation system Small fluctuations in the amount of raw and Solving through lean High Minor auxiliary materials added,etc management Temperature measuring gun failure,spare parts Solved by routine Low Minor overdue,etc. inspection 4.总结及展提 钢铁行业的智能化当前仍处于发展初期，多数钢铁企业的智能化只是把生产工序过程数据进 行了数字化呈现和简单处理，距离完全利用数据驱动进行分析和决策尚需时甘。尽管深度学习作为 推动第四次工业革命的重要技术之一，在炼钢过程的应用极大促进钢铁工业智能化的脚步，但由于 其具有数据依赖性高、预处理难度大以及生产安全性有待验证的特点， 当前仍集中应用于简单场景， 无法全面开花。国内外各大钢铁企业及研究机构希望深度学 和大工智能可以更加致力于改善生产 环境，提高产品质量，降低人力成本，纷纷在智能化发展方向布局，见表4。 表4■内外燃铜企业细能化发晨布同 Table 4 Intelligent development layout of domestic and foreign steelmaking enterprises NO. Year Country Application companies Cooperation unit Project content 2017 Korea POSCO POSCO technical research laboratories Deep Learning Projects 2017 USA Big River Steel Noodle AI Artificial Intelligence Platform 2018 China Baowu Baidu Online Network Technology AI+Steel Quality Inspection 2018 China Kingsoft Corporation Limited Precision Steel Cloud Platform 2018 China Huawei Technologies Smart Factory Project 2018 India Tata Steel Digie-Shala department Process optimization solutions 2019 Chin nan Iron and Steel Alibaba Group Steel scrap Al grading system Magang Holding Intelligent decision-making and 2019 Tencent Company control platform 201 NIPPON STEEL NS Solutions Corporation NS-DIG Intelligent Platform 2019 Germany Thyssenkrupp Microsoft "Alfred"Artificial intelligence solution Remote intelligent grading system for 2020 China Luli Group Ramon Science and Technology steel scrap 2020 China Baowu Steel Shanghai Baosight Software Baowu Eco-Technology Platform 相信在不久的未来，以下几方面的技术发展将有助于深度学习模型在炼钢过程普及率的大幅提 升，在生产过程中给出既快速又精准的决策，如图5所示。1 High Serious Endpoint prediction, defect detection, etc. Build deep learning models 2 Low Serious Secondary oxidation of steel, continuous casting leakage, etc. Improvement from process route and operation system 3 High Minor Small fluctuations in the amount of raw and auxiliary materials added, etc. Solving through lean management 4 Low Minor Temperature measuring gun failure, spare parts overdue, etc. Solved by routine inspection 4. 总结及展望 钢铁行业的智能化当前仍处于发展初期，多数钢铁企业的智能化只是把各生产工序过程数据进 行了数字化呈现和简单处理，距离完全利用数据驱动进行分析和决策尚需时日。尽管深度学习作为 推动第四次工业革命的重要技术之一，在炼钢过程的应用极大促进钢铁工业智能化的脚步，但由于 其具有数据依赖性高、预处理难度大以及生产安全性有待验证的特点，当前仍集中应用于简单场景 ， 无法全面开花。国内外各大钢铁企业及研究机构希望深度学习和人工智能可以更加致力于改善生产 环境，提高产品质量，降低人力成本，纷纷在智能化发展方向布局，见表 4。 表 4 国内外炼钢企业智能化发展布局 Table 4 Intelligent development layout of domestic and foreign steelmaking enterprises NO. Year Country Application companies Cooperation unit Project content 1 2017 Korea POSCO POSCO technical research laboratories Deep Learning Projects 2 2017 USA Big River Steel Noodle AI Artificial Intelligence Platform 3 2018 China Baowu Steel Baidu Online Network Technology AI + Steel Quality Inspection 4 2018 China Anshan Iron and Steel Kingsoft Corporation Limited Precision Steel Cloud Platform 5 2018 China Xiangtan Iron and Steel Huawei Technologies Smart Factory Project 6 2018 India Tata Steel Tata Steel Digie-Shala department Process optimization solutions 7 2019 China Jinnan Iron and Steel Alibaba Group Steel scrap AI grading system 8 2019 China Magang Holding Company Tencent Intelligent decision-making and control platform 9 2019 Japan NIPPON STEEL NS Solutions Corporation NS-DIG Intelligent Platform 10 2019 Germany Thyssenkrupp Microsoft "Alfred" Artificial intelligence solution 11 2020 China Luli Group Ramon Science and Technology Remote intelligent grading system for steel scrap 12 2020 China Baowu Steel Shanghai Baosight Software Baowu Eco-Technology Platform 相信在不久的未来，以下几方面的技术发展将有助于深度学习模型在炼钢过程普及率的大幅提 升，在生产过程中给出既快速又精准的决策，如图 5 所示。 录用稿件，非最终出版稿