In this study, we propose a machine-learning-based approach to identify the modal parameters of the output-only data for structural health monitoring (SHM) that makes full use of the characteristic of independence of modal responses and the principle of machine learning. By taking advantage of the independent feature of each mode, we use the principle of unsupervised learning, turning the training process of the neural network into the process of modal separation. A self-coding neural network is designed to identify the structural modal parameters from the vibration data of structures. The mixture signals, that is, the structural response data, are used as the input of the neural network. Then, we use a complex loss function to restrict the training process of the neural network, making the output of the third layer the modal responses we want, and the weights of the last two layers are mode shapes. The neural network is essentially a nonlinear objective function optimization problem. A novel loss function is proposed to constrain the independent feature with consideration of uncorrelation and non-Gaussianity to restrict the designed neural network to obtain the structural modal parameters. A numerical example of a simple structure is carried out to illustrate the modal parameter identification ability of the proposed approach considering the influence of damping ratios. Then, the proposed method is further verified by an actual SHM dataset from a cable-stayed bridge. The results show that the approach is capable of blindly extracting modal information from system responses.

Dawei Liu

Zhiyi Tang

Yuequan Bao

Hui Li

Structural Control and Health Monitoring

期刊结构控制和健康监测涵盖结构控制、结构健康监测理论和智能材料和结构的所有理论和技术方面。该期刊专注于航空航天、民用、基础设施和机械工程应用。基于分析、计算和实验方法的原创投稿主要在监测、控制、智能材料和结构三大领域征集，涵盖系统识别、健康监测等学科、健康诊断、多功能材料、信号处理、传感器技术、被动、主动和半主动控制方案和实施、形状记忆合金、压电和机电一体化。还有致动器设计、动态系统、动态稳定性、人工智能工具、数据采集、无线通信、测量、用于局部损坏检测的 MEMS/NEMS 传感器、用于健康监测的光纤传感器、监测系统的远程控制、用于移动应用的传感器-记录器组合、腐蚀传感器、冲刷指示器和实验技术。

The journal "Structural Control and Health Monitoring" covers all theoretical and technical aspects of structural control, structural health monitoring theory, and smart materials and structures. It focuses on applications in aerospace, civil, infrastructure, and mechanical engineering. We welcome original submissions based on analytical, computational, and experimental methods, primarily in the three areas of monitoring, control, and smart materials and structures. Topics include system identification, health monitoring, health diagnosis, multifunctional materials, signal processing, sensor technology, passive, active, and semi-active control schemes and implementations, shape memory alloys, piezoelectric materials, and mechatronics. Additionally, it encompasses actuator design, dynamic systems, dynamic stability, artificial intelligence tools, data acquisition, wireless communication, measurement, MEMS/NEMS sensors for local damage detection, fiber optic sensors for health monitoring, remote control of monitoring systems, sensor-recorder combinations for mobile applications, corrosion sensors, scour indicators, and experimental techniques.

《Structural Control and Health Monitoring》期刊涵盖结构控制、结构健康监测理论以及智能材料和结构的各个理论和技术方面。该期刊专注于航空航天、民用、基础设施和机械工程等应用领域。我们欢迎基于分析、计算和实验方法的原创投稿，主要集中在监测、控制、智能材料和结构三个领域，涉及系统识别、健康监测、健康诊断、多功能材料、信号处理、传感器技术、被动、主动和半主动控制方案及其实施、形状记忆合金、压电材料和机电一体化等内容。此外，还包括致动器设计、动态系统、动态稳定性、人工智能工具、数据采集、无线通信、测量、用于局部损伤检测的MEMS/NEMS传感器、用于健康监测的光纤传感器、监测系统的远程控制、用于移动应用的传感器-记录器组合、腐蚀传感器、冲刷指示器以及实验技术等。

Struct Control Health Monit

Machine‐learning‐based methods for output‐only structural modal identification

A machine‐learning‐based approach to identify the modal parameters of the output‐only data for structural health monitoring (SHM) that makes full use of the characteristic of independence of modal responses and the principle of machine learning is proposed.

Category	Quartile
工程技术	2
工程技术, 结构与建筑技术	2
工程技术, 工程土木	2
工程技术, 仪器仪表	2

Machine‐learning‐based methods for output‐only structural modal identification

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
INSTRUMENTS & INSTRUMENTATION	1