Scholarlink

<p>Efficient billet heating is a critical economic and environmental challenge in wire-rod steel rolling. This work presents an artificial-intelligence (AI) framework to support energy-consumption reduction in an industrial induction furnace by combining a calibrated finite-element (FE) digital twin, a deep-learning (DL) surrogate, and a deep reinforcement learning agent. The FE model, calibrated with real production data from Global Steel Wire (Spain), reproduces the outlet-temperature trends of the resulfurized billet family with RMSE &lt; 5&#xa0;°C and Pearson correlation &gt; 0.95. To enable fast surrogate-based optimization, a convolutional-recurrent surrogate was trained using real plant time series as inputs and FE-simulated outlet-temperature profiles for those same real billets as target outputs, achieving RMSE values of 5.7&#xa0;°C on the training billets and 9.85&#xa0;°C on the test billets, both within the uncertainty range of the outlet pyrometer. This surrogate was then embedded as the environment of a Deep Q-Learning (DQL) framework that searches for lower-energy heating schedules under practical operational constraints and the prescribed outlet-temperature similarity criterion. Across the evaluated resulfurized billets, the learned policy reduced surrogate-predicted energy consumption in every case while keeping the predicted exit-temperature profiles close to the prescribed 5&#xa0;°C RMSE similarity threshold to the target profile. In representative cases, the surrogate-predicted savings reached 24% and 27%. These results indicate the potential of reinforcement learning as a supervisory decision-support layer for induction-furnace energy optimization when coupled with a physically grounded and computationally efficient digital environment. However, FE re-evaluation and plant-level validation of the optimized schedules are required before industrial deployment.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimization of the energy consumption of an induction furnace for steel billets using a reinforcement learning framework applied to a finite element digital twin

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月22日

查看全文
  • Sergio Bolívar,
  • Lara Lloret,
  • José A. Sáinz-Aja,
  • Diego Ferreño,
  • Carmela Oria,
  • Estela Ruiz,
  • Miriam Cobo

摘要

Efficient billet heating is a critical economic and environmental challenge in wire-rod steel rolling. This work presents an artificial-intelligence (AI) framework to support energy-consumption reduction in an industrial induction furnace by combining a calibrated finite-element (FE) digital twin, a deep-learning (DL) surrogate, and a deep reinforcement learning agent. The FE model, calibrated with real production data from Global Steel Wire (Spain), reproduces the outlet-temperature trends of the resulfurized billet family with RMSE < 5 °C and Pearson correlation > 0.95. To enable fast surrogate-based optimization, a convolutional-recurrent surrogate was trained using real plant time series as inputs and FE-simulated outlet-temperature profiles for those same real billets as target outputs, achieving RMSE values of 5.7 °C on the training billets and 9.85 °C on the test billets, both within the uncertainty range of the outlet pyrometer. This surrogate was then embedded as the environment of a Deep Q-Learning (DQL) framework that searches for lower-energy heating schedules under practical operational constraints and the prescribed outlet-temperature similarity criterion. Across the evaluated resulfurized billets, the learned policy reduced surrogate-predicted energy consumption in every case while keeping the predicted exit-temperature profiles close to the prescribed 5 °C RMSE similarity threshold to the target profile. In representative cases, the surrogate-predicted savings reached 24% and 27%. These results indicate the potential of reinforcement learning as a supervisory decision-support layer for induction-furnace energy optimization when coupled with a physically grounded and computationally efficient digital environment. However, FE re-evaluation and plant-level validation of the optimized schedules are required before industrial deployment.