Scholarlink

<p>This study presents a comprehensive data-driven framework for predicting energy consumption in an industrial aluminum cold rolling mill. Cold rolling is one of the most energy-intensive stages of aluminum production. While traditional physics-based models are insufficient for real-time applications, existing machine learning studies have largely overlooked aluminum-specific process dynamics and the interpretability dimension. An industrial dataset consisting of 1,345 production records from 2022 was used. Physically meaningful features such as reduction ratio, thickness reduction, and specific energy consumption (SEC, kWh/ton) were derived from raw process variables. Linear regression, Ridge, and Lasso were employed as baseline models, and compared against ensemble learners including Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost. Under the random split, CatBoost achieved the best performance (<InlineEquation ID="IEq1"><EquationSource Format="TEX">\(R^2 = 0.78\)</EquationSource></InlineEquation>), whereas under the more realistic temporal split, Random Forest and Gradient Boosting emerged as the top performers (<InlineEquation ID="IEq2"><EquationSource Format="TEX">\(R^2 \approx 0.81\)</EquationSource></InlineEquation>). Linear models degraded dramatically under temporal evaluation (<InlineEquation ID="IEq3"><EquationSource Format="TEX">\(R^2 \approx 0.18\)</EquationSource></InlineEquation>). SHAP analyses revealed that CVC position and rolling speed are the dominant drivers of model predictions. The ablation study demonstrated that removing the CVC position feature group caused the <InlineEquation ID="IEq4"><EquationSource Format="TEX">\(R^2\)</EquationSource></InlineEquation> score to drop from 0.80 to 0.20. The proposed framework addresses a significant gap in the literature by jointly offering: rolling-aware energy indicator derivation, a fair comparison of ensemble model families, SHAP-based interpretability, and a CO<InlineEquation ID="IEq5"><EquationSource Format="TEX">\(_2\)</EquationSource></InlineEquation> accounting analysis grounded in SEC-based efficiency stratification.</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

Explainable energy and carbon intensity assessment for aluminum cold rolling via ensemble models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月4日

查看全文
  • Burak Ağgül,
  • Kaan Arik

摘要

This study presents a comprehensive data-driven framework for predicting energy consumption in an industrial aluminum cold rolling mill. Cold rolling is one of the most energy-intensive stages of aluminum production. While traditional physics-based models are insufficient for real-time applications, existing machine learning studies have largely overlooked aluminum-specific process dynamics and the interpretability dimension. An industrial dataset consisting of 1,345 production records from 2022 was used. Physically meaningful features such as reduction ratio, thickness reduction, and specific energy consumption (SEC, kWh/ton) were derived from raw process variables. Linear regression, Ridge, and Lasso were employed as baseline models, and compared against ensemble learners including Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost. Under the random split, CatBoost achieved the best performance (\(R^2 = 0.78\)), whereas under the more realistic temporal split, Random Forest and Gradient Boosting emerged as the top performers (\(R^2 \approx 0.81\)). Linear models degraded dramatically under temporal evaluation (\(R^2 \approx 0.18\)). SHAP analyses revealed that CVC position and rolling speed are the dominant drivers of model predictions. The ablation study demonstrated that removing the CVC position feature group caused the \(R^2\) score to drop from 0.80 to 0.20. The proposed framework addresses a significant gap in the literature by jointly offering: rolling-aware energy indicator derivation, a fair comparison of ensemble model families, SHAP-based interpretability, and a CO\(_2\) accounting analysis grounded in SEC-based efficiency stratification.