MC-GRU:a Multi-Channel GRU network for generalized nonlinear structural response prediction across structures

2025-03-10

AI Summary

To address the limited generalization capability of existing AI models in cross-structural seismic response prediction and damage quantification, this paper proposes a Multi-Channel Gated Recurrent Unit (MC-GRU) network. The method innovatively encodes structural geometric and material parameters as structural features, embedding them into the candidate hidden state of the GRU, and integrates a multi-channel temporal input mechanism to enable universal modeling of nonlinear dynamic systems. Validation on single-degree-of-freedom systems, the Bouc–Wen model, and experimental data from real reinforced concrete columns demonstrates that MC-GRU significantly enhances adaptability to unseen structures. It outperforms standard GRU and LSTM in response prediction accuracy, reducing average generalization error by over 40%. This work establishes a transferable and interpretable paradigm for data-driven structural health monitoring and seismic performance assessment.

Technology Category

• Machine Learning: Structured Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate prediction of seismic responses and quantification of structural damage are critical in civil engineering. Traditional approaches such as finite element analysis could lack computational efficiency, especially for complex structural systems under extreme hazards. Recently, artificial intelligence has provided an alternative to efficiently model highly nonlinear behaviors. However, existing models face challenges in generalizing across diverse structural systems. This paper proposes a novel multi-channel gated recurrent unit (MC-GRU) network aimed at achieving generalized nonlinear structural response prediction for varying structures. The key concept lies in the integration of a multi-channel input mechanism to GRU with an extra input of structural information to the candidate hidden state, which enables the network to learn the dynamic characteristics of diverse structures and thus empower the generalizability and adaptiveness to unseen structures. The performance of the proposed MC-GRU is validated through a series of case studies, including a single-degree-of-freedom linear system, a hysteretic Bouc-Wen system, and a nonlinear reinforced concrete column from experimental testing. Results indicate that the proposed MC-GRU overcomes the major generalizability issues of existing methods, with capability of accurately inferring seismic responses of varying structures. Additionally, it demonstrates enhanced capabilities in representing nonlinear structural dynamics compared to traditional models such as GRU and LSTM.

Problem

• Generalized nonlinear structural response prediction across diverse structures
• Overcoming generalizability issues in existing AI models for seismic response
• Enhancing computational efficiency and accuracy in structural damage quantification

Innovation

• Multi-channel GRU network for structural prediction
• Enhanced generalizability across diverse structural systems
• Improved nonlinear dynamics representation over traditional models