Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network

Within the domain of Structural Health Monitoring (SHM), conventional approaches generally are complicated, destructive, and time-consuming. It also necessitates an extensive array of sensors to effectively evaluate and monitor the structural integrity. In this research work, we present a novel, non-destructive SHM framework based on machine learning (ML) for the accurate detection and localisation of structural cracks. This approach leverages a minimal number of strain gauge sensors linked via Bluetooth Low Energy (BLE) communication. The framework is validated through empirical data collected from 3D carbon fibre-reinforced composites, including three distinct specimens, ranging from crack-free samples to specimens with up to ten cracks of varying lengths and depths. The methodology integrates an analytical examination of the Shewhart chart, Grubbs’ test (GT), and hierarchical clustering (HC) algorithm, tailored towards the metrics of fracture measurement and classification. Our novel ML framework allows one to replace exhausting laboratory procedures with a modern and quick mechanism for the material, with unprecedented properties that could provide potential applications in the composites industry.