Analysis of FFT and K-Means Clustering for Structural Health Monitoring

Structural Health Monitoring (SHM) is crucial for maintaining the safety and longevity of civil infrastructures such as bridges. Traditional SHM methods, which often rely on manual inspections, can be time-consuming and error-prone. This paper explores the application of Fast Fourier Transform (FFT) and K-Means clustering in SHM to provide a more efficient and accurate solution. The methodology involves extracting features from vibration signal data using FFT and categorizing structural conditions through K-Means clustering. Our results demonstrate the effectiveness of these techniques in identifying structural health status, achieving a clustering accuracy of approximately 70%. The integration of FFT and K-Means clustering offers a scalable and interpretable approach for automated SHM, presenting a valuable tool for the continuous monitoring and maintenance of civil structures.