Monitoring of Damage in Composite Structures Using an Optimized Sensor Network: A Data-Driven Experimental Approach

Abstract

Due to the complexity of the fracture mechanisms in composites, monitoring damage using a vibration-based structural response remains a challenging task. This is also complex when considering the physical implementation of a health monitoring system with its numerous uncertainties and constraints, including the presence of measurement noise, changes in boundary and environmental conditions of a tested object, etc. Finally, to balance such a system in terms of efficiency and cost, the sensor network needs to be optimized. The main aim of this study is to develop a cost- and performance-effective data-driven approach to monitor damage in composite structures and validate this approach through tests performed on a physically implemented structural health monitoring (SHM) system. In this study, we combined the mentioned research problems to develop and implement an SHM system to monitor delamination in composite plates using data combined from finite element models and laboratory experiments to ensure robustness to measurement noise with a simultaneous lack of necessity to perform multiple physical experiments. The developed approach allows the implementation of a cost-effective SHM system with validated predictive performance.

Genetic Multi-Objective Optimization of Sensor Placement for SHM of Composite Structures

“…The lower limit of 2 sensors requires the use of at least one sensor in every X or Y direction. The upper boundary has been selected based on the limited number of channels in our measurement path presented in [8]. The number of modes was also selected according to the number of modes used in previous research [7].…”

“…Next, individual strain maps of selected modes are normalized from 0 to 1, assigning 1 to the highest strain value. Then, the sum of the strains of selected modes is performed, and the strain values in the x and y direction are organized separately as vectors of values in descending order [7,8]. Afterwards, based on this order, the sensors are sequentially placed in the coordinates, which corresponds to the highest value in the mentioned vector, taking into account other requirements such as maintaining the required distance between sensors, etc.…”

“…Next, individual strain maps of selected modes are normalized from 0 to 1, assigning 1 to the highest strain value. Then, the sum of the strains of selected modes is performed, and the strain values in the x and y direction are organized separately as vectors of values in descending order [7,8]. In this study, the sensor network obtained using the above algorithm is mainly evaluated using the prepared classifier, which is validated using k-fold cross-validation.…”

“…It is especially important in the case of SHM systems based on modal analysis, one of the oldest and most widely used approaches in both civil and mechanical engineering [6]. Recent studies of the authors [7,8] demonstrated the need for the application of an advanced machine-learning approach for this task to find a balance between the performance and cost of an SHM system.…”

“…The outcomes are presented as Pareto solutions which, linked to design variables, allow the user to obtain required performance and costs of an SHM system. This is an ongoing study within a series of previously performed studies [7,8] with a general focus on development of a customizable SHM system with a trade-off between performance and cost effectiveness.…”