Search

This paper presents a novel method of assessing structural damage in beams exposed to moving loads via acceleration signals through experimental studies. In this study, beams are supported on both ends, and their dynamic response to moving loads is assessed. The raw signal has been improved using a random decrement technique. Take measurements from different locations and calculate correlation coefficients between them, then use these as features to evaluate the structure. In order to create a reliable and potential framework for predicting damage efficiently, these features are used as input variables to the machine learning model. The proposed methodology exhibits promising results in accurately discerning and predicting damage in beam structure. It demonstrates a high level of precision to subtle changes in structural integrity when trained by machine learning on the statistical feature extracted from acceleration signals. As a result of this research, methods for detecting structural damage can be made more reliable and efficient by employing machine learning techniques. Additionally, structures operating in dynamic environments can benefit significantly from the proposed methodology.

Damage assessment in the actual operating process of the structure is a modern and exciting problem of construction engineering due to several practical knowledge about the current condition of the inspected structures. However, the problem faced is the difficulty in controlling the excitation in structures. Therefore, the output-based structural damage identification method is becoming attractive because of its potential to be applied to an actual application without being constrained by the collection of the information excitation source. An approach of damage assessment based on supervised Machine Learning is introduced in this study by using the correlation of spectral signal as an input feature for artificial neural network (ANN) and decision tree. The output of machine learning algorithms consists of the appearance of new cuts, the level of cutting and the cutting position. A supported beam model was constructed as an experiment to determine if the method is reasonable for engineering structures. Two machine learning algorithms have been applied to check the relevance of the proposed feature from vibration data. This study contributes a standard in the damage identification problem based on spectral correlation. [ABSTRACT FROM AUTHOR]