PyMLDA: A Python open-source code for Machine Learning Damage Assessment

• Published in: Software impacts Vol. 19; p. 100628
• Main Authors: Coelho, Jefferson da Silva, Machado, Marcela Rodrigues, de Sousa, Amanda Aryda S.R.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.03.2024
• Subjects: Damage detection; Damage Index; Raw signal; Structural health monitoring; Vibration signal; Structural health monitoring; Damage detection; Raw signal; Damage Index; Vibration signal
• ISSN: 2665-9638; 2665-9638
• DOI: 10.1016/j.simpa.2024.100628

The PyMLDA-Machine Learning for Damage Assessment is an open-source software developed for damage pattern recognition, detection, and quantification that uses the system’s vibration signatures as input. The software automatically evaluates the structure or system integrity by detecting and assessing structural damage by combining supervised, unsupervised, and regression Machine Learning (ML) algorithms. It employs different damage index techniques based on the system’s dynamic response, such as natural or frequency response frequency, to normalise the dataset input of the software. The classification ML route effectively identifies and categorises the damage, even when the integrity condition of the structure is unknown. The regression algorithm quantifies the damage levels, considering the uncertainty quantification in the estimation. The PyMLDA employs a range of validation and cross-validation metrics to evaluate the effectiveness and accuracy of these ML algorithms in detecting and diagnosing structural damage. •PyMLDA is an open-source code combining ML-SHM for pattern recognition and damage assessment.•PyMLDA assists the entire SHM process, from data acquisition to system integrity prognosis.•Integrating data-driven with preprocessing, feature selection, and pattern recognition.•System’s dynamic reposnse and damge index are the PyMLDA.•PyMLDA uses unsupervised-supervised and regression ML for enhanced dataset analysis and SHM.•Broader contributions include operational diagnoses, management, and decision-making.