Multiclass Supervised Machine Learning Algorithms Applied to Damage and Assessment Using Beam Dynamic Response

Abstract

Purpose: Structural damage can significantly alter a system's local flexibility, leading to undesirable displacements and vibrations. Analysing the dynamic structure feature through statistical analysis enables us to discriminate the current structural condition and predict its short- or long-term lifespan. By directly affecting the system's vibration, cracks and discontinuities can be detected, and their severity quantified using the DI. Two damage indexes (DI) are used to build a dataset from the beam's natural frequency and frequency response function (FRF) under both undamaged and damaged conditions, and numerical and experimental tests provided the data-driven. Methods: In this paper, we present the methodology based on machine learning (ML) to monitor the structural integrity of a beam-like structure. The performance of six ML algorithms, including k-nearest neighbors (kNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Naive Bayes (NB) are investigated. Results: The paper discusses the challenges of implementing each technique and assesses their performance in accurately classifying the dataset and indicating the beam's integrity. Conclusion: The structural monitoring performed with the ML algorithm achieved excellent metrics when inputting the simulation-generated dataset, up to 100%, and up to 95% having as input dataset provided from experimental tests. Demonstrating that the ML algorithm could correctly classify the health condition of the structure.