用物理约束神经网络预测核反应堆材料疲劳寿命，更准更可靠。
Physics-informed neural network for predicting fatigue life of unirradiated and irradiated austenitic and ferritic/martensitic steels under reactor-relevant conditions
- 将物理规律嵌入损失函数，让模型学习更符合真实机制。
- 在495组数据上表现优于传统机器学习方法，预测更准确。
- 揭示了应变幅、辐照剂量和温度对寿命的反向影响，适合核电研究者使用。
本研究提出一种物理信息神经网络（PINN）框架，用于预测核反应堆中未辐照及辐照后奥氏体与铁素体/马氏体（F/M）钢在低周疲劳（LCF）条件下的寿命。这些材料在循环载荷、中子辐照和高温环境下会发生复杂退化，传统经验或纯数据驱动模型难以准确刻画。所提出的PINN将疲劳寿命的物理约束融入损失函数，实现物理一致的学习，提升预测精度、可靠性与泛化能力。模型基于495个应变控制疲劳数据点训练，涵盖辐照与未辐照条件。相比随机森林、梯度提升、极端梯度提升及常规神经网络，该模型性能更优。SHAP分析表明，应变幅、辐照剂量和测试温度是主导特征，均与疲劳寿命呈物理意义明确的负相关。单变量与多变量分析揭示合金特异性退化规律：奥氏体钢在应变、辐照与温度共同作用下呈现显著非线性耦合与疲劳劣化；而F/M钢辐照响应较稳定，具剂量饱和特性，但超过回火阈值的高温下敏感性增强。整体而言，该框架为反应堆相关疲劳评估提供了一种可靠且可解释的工具，适用于先进核能系统性能评价。
原文摘要 · Abstract (English)
This study proposes a Physics-Informed Neural Network (PINN) framework to predict the low-cycle fatigue (LCF) life of irradiated austenitic and ferritic/martensitic (F/M) steels used in nuclear reactors. These materials undergo cyclic loading, neutron irradiation, and elevated temperatures, leading to complex degradation mechanisms that are difficult to capture with conventional empirical or purely data-driven models. The proposed PINN embeds fatigue-life governing physical constraints into the loss function, enabling physically consistent learning while improving predictive accuracy, reliability, and generalizability. The model was trained on 495 strain-controlled fatigue data points spanning irradiated and unirradiated conditions. Compared with traditional machine learning approaches, including Random Forest, Gradient Boosting, eXtreme Gradient Boosting, and conventional neural networks, the PINN demonstrated superior performance. SHapley Additive exPlanations (SHAP) analysis identified strain amplitude, irradiation dose, and test temperature as the dominant features, each exhibiting physically meaningful inverse correlations with fatigue life. Univariate and multivariate analyses revealed clear alloy-specific degradation characteristics. Austenitic steels exhibited strong nonlinear coupling among strain amplitude, irradiation dose, and temperature, resulting in pronounced fatigue degradation under combined loading. In contrast, F/M steels demonstrated comparatively stable irradiation responses, including dose-saturation behavior, but showed sensitivity to elevated temperatures beyond tempering thresholds. Overall, the proposed PINN framework serves as a reliable and interpretable tool for reactor-relevant fatigue assessment, enabling performance evaluation for advanced nuclear applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。