Physics-Reinforced Deep Learning for Structural Metamodeling

用于结构元建模的物理强化深度学习

• 批准号: 2013067
• 负责人: Jerome Hajjar
• 金额: $ 59.9万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-06-01 至 2024-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2013067&HistoricalAwards=false
• 关键词: Physics; Reinforced; Deep; Learning; Structural

This research will develop new computational methods to advance modeling, analysis and assessment of civil structural systems subjected to earthquakes. Currently available simplified or reduced-order models widely used in structural analysis have severe limitations in accurately predicting the complex nonlinearities in structural response under earthquake loading (e.g., in the presence of large nonlinear drifts, damage, failure, etc.). The infusion of artificial intelligence (AI) into civil engineering offers a powerful new approach for structural modeling. However, currently large amounts of data are required to train a reliable AI model, and even with rich data, the trained models are difficult to interpret and have little physical meaning. To address these fundamental issues and to bridge the knowledge gap between AI and performance-based engineering, this project will integrate deep learning and physics principles for efficient and probabilistic modeling of nonlinear structures under earthquake hazards. This research will advance more efficient design, reliability analysis, control and optimization of engineering structures with much less computational efforts. The project will also establish an integrated research-education-outreach program that will (i) transform the fundamental understanding of machine learning grounded with domain-specific knowledge, (ii) promote participation by undergraduates, in particular, women and minorities, and (iii) inspire high school students to pursue STEM-related careers.This research will breathe novel elements of machine learning into performance-based structural engineering, opening a new avenue by leveraging deep learning integrated with physics knowledge for modeling of seismic response of structural systems. The specific research aims of this project include: (1) developing unsupervised learning-based ground motion selection for optimal generation of seismic response database, (2) establishing rigorous formulation and algorithm for an innovative, physics-reinforced deep Learning paradigm for structural metamodeling, (3) developing a neural network compression approach to prune the metamodels for efficient inference, and (4) incorporating variability for probabilistic seismic response prediction and fragility analysis. The resulting deep-learning-based metamodels will possess salient features including (i) interpretability with physical meaning, (ii) generalizability and extrapolation to unseen cases, (iii) real-time inference based on a lightweight/compressed metamodel architecture, and (iv) capability of addressing incomplete and scare data. This approach will be applicable to a wide range of nonlinear dynamical systems under complex loading conditions. This project will advance the knowledge base in multiple disciplines of nonlinear structural dynamics, computational modeling, robust and efficient machine/deep learning, optimization and uncertainty quantification.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这项研究将开发新的计算方法，以推进建模，分析和评估土木结构系统受到地震。目前广泛用于结构分析的简化或降阶模型在准确预测地震荷载下结构响应的复杂非线性方面存在严重的局限性（例如，在存在大的非线性漂移、损坏、故障等的情况下）。将人工智能（AI）注入土木工程为结构建模提供了一种强大的新方法。然而，目前需要大量的数据来训练可靠的AI模型，即使有丰富的数据，训练的模型也很难解释，并且几乎没有物理意义。为了解决这些基本问题，并弥合人工智能和基于性能的工程之间的知识差距，该项目将整合深度学习和物理原理，对地震灾害下的非线性结构进行高效和概率建模。该研究将以更少的计算工作量促进工程结构的更有效的设计、可靠性分析、控制和优化。该项目还将建立一个综合的研究-教育-推广计划，（i）以特定领域的知识为基础，转变对机器学习的基本理解，（ii）促进本科生，特别是女性和少数民族的参与，（iii）激励高中生追求STEM相关的职业。这项研究将为基于性能的结构工程注入机器学习的新元素，通过利用深度学习与物理知识相结合，为结构系统的地震响应建模开辟了一条新途径。该项目的具体研究目标包括：（1）开发基于无监督学习的地面运动选择，以优化地震响应数据库的生成，（2）为结构元建模的创新的、物理增强的深度学习范例建立严格的公式和算法，（3）开发神经网络压缩方法来修剪元模型以进行有效的推理，（4）考虑变异性进行概率地震反应预测和易损性分析。由此产生的基于深度学习的元模型将具有显著的特征，包括（i）具有物理意义的可解释性，（ii）对未知情况的可推广性和外推性，（iii）基于轻量级/压缩元模型架构的实时推理，以及（iv）解决不完整和稀缺数据的能力。这种方法将适用于各种复杂载荷条件下的非线性动力系统。该项目将推进非线性结构动力学、计算建模、稳健高效的机器/深度学习、优化和不确定性量化等多个学科的知识基础。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures

• DOI: 10.1016/j.cma.2020.113226
• 发表时间: 2020-02
• 期刊: ArXiv
• 作者: Ruiyang Zhang;Yang Liu;Hao Sun-

Forecasting of nonlinear dynamics based on symbolic invariance

基于符号不变性的非线性动力学预测

• DOI: 10.1016/j.cpc.2022.108382
• 发表时间: 2022
• 期刊: Computer Physics Communications
• 影响因子: 6.3
• 作者: Chen, Zhao;Liu, Yang;Sun, Hao
• 通讯作者: Sun, Hao

Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modeling

• DOI: 10.1016/j.engstruct.2020.110704
• 发表时间: 2020-07-15
• 期刊: ENGINEERING STRUCTURES
• 影响因子: 5.5
• 作者: Zhang, Ruiyang;Liu, Yang;Sun, Hao
• 通讯作者: Sun, Hao