Learning When to Transfer: Reinforcement Learning for Carbon-Footprint Modeling in New Manufacturing Domains

📄 arXiv: 2610.18730v1 📥 PDF

作者: Muhammad Umar Farooq, Daniel R. Cooper

分类: cs.LG

发布日期: 2026-10-13

期刊: Farooq, M.U., Cooper, D.R. (2026). Learning When to Transfer: Reinforcement Learning for Carbon-Footprint Modeling in New Manufacturing Domains. Tackling Climate Change with Machine Learning: Workshop at NeurIPS 2026

💡 一句话要点

提出强化学习方法以优化新制造领域的碳足迹建模

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture)

关键词: 强化学习 知识转移 碳足迹建模 制造业 增材制造 温室气体排放 数据驱动

📋 核心要点

  1. 现有方法在新制造领域中，缺乏有效的知识转移机制，导致负迁移现象，影响模型预测性能。
  2. 本文提出了一种基于强化学习的选择性知识转移方法，通过奖励机制评估转移机会，避免负迁移。
  3. 实验结果表明，该方法在材料挤出增材制造中，测试均方根误差降低至5.2 g CO2e/件，较目标数据训练降低20%。

📝 摘要（中文）

制造商在获得足够的操作数据之前，常需对新材料、工艺或产品进行特征化。现有制造操作中可能包含有用知识，但不加选择地重用这些数据可能导致负迁移。本文提出了一种强化学习方法，通过奖励机制选择性地转移知识，避免负迁移并在前向预测中进行控制。该方法旨在支持碳核算及性能和质量结果的学习。通过729次实验，验证了该方法在材料挤出增材制造中的应用，显著降低了温室气体排放的预测误差。

🔬 方法详解

问题定义：本文旨在解决在新制造领域中，如何有效利用现有制造操作的数据进行知识转移的问题。现有方法在不同制造领域间的知识转移往往导致负迁移，影响模型的预测准确性。

核心思路：论文提出的强化学习方法通过奖励机制选择性地转移知识，评估每次转移的有效性，从而避免负迁移。该方法在前向预测中控制转移过程，而非事后诊断。

技术框架：整体架构包括数据输入、知识转移策略学习、预测模型选择和验证门。首先，系统接收来自新目标领域和现有源领域的数据，然后通过强化学习算法选择最佳预测器，最后通过验证门确保转移的预测优于监督学习的替代方案。

关键创新：最重要的创新在于引入了强化学习的奖励机制来评估和选择知识转移的机会，这与传统方法的无差别数据重用形成鲜明对比，显著提高了模型的预测性能。

关键设计：在模型设计中，设置了多个参数以优化奖励机制，损失函数考虑了转移的有效性，网络结构则支持多源数据的整合与处理。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，该方法在材料挤出增材制造中的应用，测试均方根误差达到5.2 g CO2e/件，较仅使用目标数据训练的模型降低了20%，而在仅有5-10%目标训练数据的情况下，降低幅度达到32.5%。与无差别源-目标数据整合相比，性能提升达10.3%。

🎯 应用场景

该研究具有广泛的应用潜力，尤其在制造业中，能够帮助企业在新材料和工艺的开发过程中，快速准确地进行碳足迹评估。这不仅有助于企业实现可持续发展目标，还能在政策制定和环境保护方面发挥重要作用，推动绿色制造的进程。

📄 摘要（原文）

Manufacturers often need to characterize a new material, process, or product before enough operating data are available to train reliable predictive models for this new, target domain. Existing manufacturing operations contain potentially useful knowledge to accelerate this characterization, but indiscriminate reuse of data from existing source domains can cause negative transfer in learning of the new, target domain when the manufacturing domains differ sufficiently. This work proposes a reinforcement-learning method for selective knowledge transfer, where its reward scores each opportunity to transfer against supervised alternatives, so negative transfer is avoided and controlled during forward prediction instead of being diagnosed afterwards. Given limited data from a new target domain, the learned policy chooses among predictors based on individual source operations, subsets of the sources, or the supervised alternatives: fully pooled sources, or target data alone. A validation gate deploys the transferred prediction only when it improves upon the supervised alternatives. The method is designed for learning variables supporting carbon accounting, as well as performance and quality outcomes. We demonstrate the approach by quantifying the embodied greenhouse-gas emissions of parts produced via material-extrusion additive manufacturing, using data from 729 experiments spanning five materials: ABS, PETG, TPU, PLA, and recycled PLA. The response combines measured fabrication electricity with polymer-specific cradle-to-gate production factors, while 22 material, process, and toolpath features characterize each experiment. In leave-one-material-out evaluation, this method achieves a mean test RMSE of 5.2 g CO2e per part, 20.00% lower than target-only training (32.5% lower when only 5-10% of the target training data are available) and 10.30% lower than indiscriminate source-target pooling.