Vibration Classification Of Intact And Cracked Brick Materials Using Fast Fourier Transform–Extreme Learning Machine For Structural Damage Early Detection

Structural damage in buildings is often initiated by small cracks in lightweight brick elements, which, if undetected, may compromise structural safety. This study developed a vibration-based classification system using the ADXL345 accelerometer, Fast Fourier Transform (FFT), and Extreme Learning Machine (ELM) for early detection of such damage. Vibration data were collected along three axes (X, Y, and Z) with excitation frequencies ranging from 10–50 Hz. FFT analysis revealed clear distinctions between intact and cracked bricks, where cracked samples exhibited higher amplitudes and multiple resonance peaks. These frequency-domain features were then processed by ELM classifier. ELM achieved high computational efficiency and demonstrated strong predictive capability, correctly classifying 7,855 intact and 4,548 cracked samples. However, it also produced 1,879 false positives and 5,100 false negatives, resulting in an RMSE of 0.548. While the model proved more accurate in identifying intact bricks, its sensitivity to crack detection remains a challenge. Overall, FFT–ELM framework shows promising potential as a fast, non-destructive, and scalable approach for structural health monitoring, with further refinements needed to improve detection accuracy of damaged materials.