Reducing Energy Consumption and Material Loss in Steel Production Using Predictive Machine Learning

2020年，全球钢铁产量总计18.6亿吨，导致二氧化碳排放量超过30亿吨，约占所有人为温室气体排放量的8%。钢铁生产商正面临越来越大的压力，要求它们减少与钢铁生产相关的二氧化碳排放，这既来自政府，也来自工业消费者。其中一个方面是应用机器学习(ML)方法来分析钢铁厂的传感器数据，并优化工艺参数。一家钢铁厂可以有数十万个传感器，提供与大约5000多个工艺参数相关的信息。然而，运营决策通常是基于操作员的技能和经验。现在有机会采用数据驱动的方法来优化这些流程，从而提高生产率、降低能源消耗和减少浪费材料。这个项目是四个合作伙伴之间的合作：*Deep.Meta是一家成立于2021年的初创企业\。我们是由ML工程师、软件开发人员和冶金专家组成的团队。我们专注于使用ML算法生成实时洞察力，使操作员能够更新控制参数，以提高炼钢关键过程的性能。*MPI是英国领先的金属研发研究所。MPI将领导电弧炉(EAF)操作工作，利用他们的中试工厂进行32个熔炼，使Deep.Meta能够试验优化策略并衡量结果。*英国斯巴达钢铁公司是一家总部设在盖茨黑德的工业规模钢铁厂。斯巴达经营着一家热轧厂，它由四个加热炉组成，以1250°C的温度供应钢坯，然后轧制，形成建筑和桥梁建筑产品的结构钢，以及由JCB、卡特彼勒和小松生产的“黄色产品”。Deep.Meta将与斯巴达公司合作分析工艺数据，并为加热炉和轧钢厂创建算法时间表，以优化生产能力，防止材料因氧化而损失(如果钢坯在炉子中高温停留太长时间就会发生)。*Grosvenor是英国一家主要的房地产开发商。可持续建筑正在成为一个关键的差异化因素，尤其是对高端租户来说。减少制造建筑材料所排放的“具体化碳”增加了显著的价值。格罗夫纳将领导一项生命周期评估，以确定建筑行业中能源节约和资源效率提高的影响，帮助他们证明和量化选择更可持续生产的钢材的影响。

In 2020, global steel production totaled 1,860 million tonnes, leading to the emission of over 3 billion tonnes of CO2, roughly 8% of all man-made greenhouse gas emissions. Steel producers are facing increasing pressure to reduce the CO2 emissions associated with steel production, both from governments and from industrial consumers. One aspect of this is to apply machine learning (ML) methods to analyse sensor data in steel plants, and optimise the process parameters. A steelworks can have hundreds of thousands of sensors, providing information related to some 5,000+ process parameters. However, operational decisions are generally based on the skills and experience of the operators. There is an opportunity to employ data-driven approaches to optimise these processes, increasing productivity, reducing energy consumption, and reducing wasted material. This project is a collaboration between four partners:* Deep.Meta is a start-up founded in 2021\. We are a team of ML engineers, software developers and metallurgists. We focus on the use of ML algorithms to generate real-time insights enabling operators to update control parameters to improve the performance of key processes in steelmaking.* MPI is the UK's leading research institute for metals R&D. MPI will lead work on electric arc furnace (EAF) operation, carrying out 32 melts using their pilot-scale plant, enabling Deep.Meta to trial optimisation strategies and measure the results.* Spartan UK is an industrial scale steelworks based in Gateshead. Spartan operates a hot-rolling mill, which is red by four reheat furnaces, supplying steel slabs at 1250ºC for subsequently rolling to form structural steels for construction products for buildings and bridges, as well as "yellow goods" manufactured by JCB, Caterpillar and Komatsu. Deep.Meta will work with Spartan to analyse process data and create algorithmic schedules for the reheat furnaces and rolling mill that optimise throughput, and prevent material loss due to oxidation (which occurs if the steel slabs spend too long at elevated temperatures in the furnace).* Grosvenor is a major UK property developer. Sustainable buildings are becoming a key differentiator, especially for high-end tenants. Reducing "embodied carbon" emitted to create the construction materials adds significant value. Grosvenor will lead a life-cycle assessment to determine the impact of the energy savings and resource efficiency improvements in the context of the construction industry, helping them to evidence and quantify the impact of choosing more sustainably produced steels.