Operational Damage Identification Scheme Utilizing De-Noised Frequency Response Functions and Artificial Neural Network
- PDF / 1,947,475 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 4 Downloads / 133 Views
Operational Damage Identification Scheme Utilizing De‑Noised Frequency Response Functions and Artificial Neural Network Shilei Chen1 · Zhi Chao Ong1 · Wei Haur Lam2 · Kok‑Sing Lim3 · Khin Wee Lai4 Received: 13 April 2020 / Accepted: 11 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract A damage identification scheme combining impact-synchronous modal analysis (ISMA) and artificial neural network is developed in this study. The ISMA de-noising method makes it feasible to detect and classify the damage states with high accuracy when the machine is under operation. The feed-forward backprop network was utilized in this study. The input feature vector of the network consisted of the FRF changes in a selected vibrational mode frequency interval at several measurement points. The scheme was tested on a rectangular Perspex plate. It is proved that the trained network can successfully identify damage locations with the testing data collected by ISMA, which allows the damage detection to be carried out without shutting down the tested machine. For the plate structure in this study, an overall accuracy reached 100% when all five measurement points were used. With the input features optimized by mode shape assessment, 100% accuracy was also achieved with only two measurement points. Keywords Artificial neural network · Frequency response function · Impact-synchronous modal analysis · Structural health monitoring · Vibration
1 Introduction Mechanical machines face structural damage problems during their service life. Structural damage can severely affect safety and functionality of the structure and lead to significant economic loss. Structural health monitoring (SHM) is an important tool for identifying the presence of possible damage and insuring the reliability of in-service mechanical structures. Vibration-based damage detection techniques are very popular in the field of SHM. The fundamental principle * Zhi Chao Ong [email protected]; [email protected] 1
Department of Mechanical Engineering, Faculty of Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia
2
State Key Laboratory of Hydraulic Engineering Simulation and Safety, Tianjin University, Tianjin 300350, People’s Republic of China
3
Photonics Research Centre, University of Malaya, 50603 Kuala Lumpur, Malaysia
4
Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia
is that damage leads to alterations in the physical properties of the structure, such as stiffness and damping. Consequently, the changes in modal parameters of the system can be observed. Hence, damage can be recognized by analyzing the variations of these parameters of the structure [1]. During the past decades, efforts have been made to develop damage identification methods based on various modal parameters, e.g., natural frequency, mode shape, modal strain energy etc. [1–5]. However, the natural frequency cannot always indicate the specific location of damage [6] and is no
Data Loading...
