Research on structural health monitoring database construction and intelligent diagnosis method based on a CNN–LSTM integrated model

Abstract

A structural health monitoring (SHM) framework integrating a convolutional neural network (CNN) and a long short-term memory (LSTM) network is proposed to address the identification of nonlinear, spatiotemporally varying damage features in structures under complex service conditions. From multichannel acceleration responses of a marine high-pile frame structure, time-domain statistical features, and frequency-domain features were extracted. A CNN–LSTM architecture incorporating residual units and a global attention mechanism was constructed to enhance sensitivity to key damage indicators and improve feature-extraction effectiveness. In conjunction with the International Association for Structural Control (IASC)-American Society of Civil Engineers (ASCE) benchmark frame structure, acceleration data under impact loading were obtained via finite-element simulations and scaled physical model tests to assemble an SHM dataset. The proposed CNN–LSTM model was subsequently applied to damage identification and classification. In the conducted experiments, the CNN–LSTM network achieved 100% classification accuracy across the evaluated damage scenarios and outperformed the conventional deep-learning baselines considered, indicating strong generalization within the tested settings. These findings indicate the effectiveness and reliability of the method for SHM of complex structures within the tested settings. The study presents an end-to-end solution for automated SHM and outlines its theoretical implications and potential engineering applicability.