پذیرفته شده برای ارائه شفاهی

کد مقاله : 1089-ISAV (R1)

¹دانش آموخته دانشگاه سمنان

²School of Mechatronics Engineering, Harbin Institute of Technology, Harbin, China

³Department of Construction Science, Lund University, Lund, Sweden

As Machine Learning (ML) techniques have been modified, the applications of these techniques are sharply increasing in many scientific and industrial fields. Although vibration-based structure identification techniques have been improved to diagnose failure symptoms or identify system parameters, new methods based on machine learning have been studied to increase their performances. This research aims to present an innovative application of machine learning in structure identification. An aluminum cantilever beam that is randomly ex-cited by using an electrodynamic shaker was selected as the case study example to prove the methodology experimentally. By using a combination of ML-based regression and classification techniques, the vibration responses are measured at different points to identify the beam natural frequencies. The estimated results are validated using the Fast Fourier Transform (FFT) and Frequency Domain Decomposition (FDD) methods. The results show that using the proposed ML-based technique can present a new output-only identification method to identify the system accurately.

system identification؛ machine learning؛ Time Domain Response

Acoustic signal processing (equipment and techniques)