An SHM approach using machine learning and statistical indicators extracted from raw dynamic measurements

• Published in: Latin American Journal of Solids and Structures Vol. 16; no. 2
• Main Authors: Finotti, Rafaelle Piazzaroli, Cury, Alexandre Abrahão, Barbosa, Flávio de Souza
• Format: Journal Article
• Language: English
• Published: Latin American Journal of Solids and Structures 01.01.2019; Associação Brasileira de Ciências Mecânicas
• Subjects: ENGINEERING, CIVIL; ENGINEERING, MECHANICAL; Failure mode and effects analysis; Machine learning; Measurement; MECHANICS; Methods; Statistical methods; Structural analysis (Engineering); Structural dynamics; Technology application; Structural Health Monitoring; Computational Intelligence; Dynamic Measurement; Damage Identification; Vibration Monitoring; Structural Dynamic
• ISSN: 1679-7817; 1679-7825; 1679-7825
• DOI: 10.1590/1679-78254942

Structural Health Monitoring using raw dynamic measurements is the subject of several studies aimed at identifying structural modifications or, more specifically, focused on damage assessment. Traditional damage detection methods associate structural modal deviations to damage. Nevertheless, the process used to determine modal characteristics can influence the results of such methods, which could lead to additional uncertainties. Thus, techniques combining machine learning and statistical analysis applied directly to raw measurements are being discussed in recent researches. The purpose of this paper is to investigate statistical indicators, little explored in damage identification methods, to characterize acceleration measurements directly in the time domain. Hence, the present work compares two machine learning algorithms to identify structural changes using statistics obtained from raw dynamic data. The algorithms are based on Artificial Neural Networks and Support Vector Machines. They are initially evaluated through numerical simulations using a simply supported beam model. Then, they are assessed through experimental tests performed on a laboratory beam structure and an actual railway bridge, in France. For all cases, different damage scenarios were considered. The obtained results encourage the development of computational tools using statistical indicators of acceleration measurements for structural alteration assessment.