Localized Damage Identification of Plate-Like Structures With Time-Delayed Binary Data From a Self-Powered Sensor Network

Recent advances in energy harvesting technologies have led to the development of self-powered monitoring techniques that are energy-efficient. This study presents an intelligent damage identification strategy for plate-like structures based on the data provided by a network of self-powered sensors that communicate through a pulse switching protocol, which has been demonstrated as an effective means for minimizing communication energy demands. The energy-aware pulse switching communication architecture uses single pulses instead of multi-bit packets for information delivery, resulting in discrete binary data. A system employing such an energy-efficient technology requires dealing with power budgets for sensing and communication of binary data, which leads to time delay constraints. In this paper, a novel machine learning framework incorporating low-rank matrix decomposition, pattern recognition, and a statistical approach is proposed to overcome challenges inherent in algorithm design for damage identification using time-delayed binary data. Performance and effectiveness of the proposed energy-aware damage identification strategy was examined for the case of a dynamically loaded plate. Damage states were simulated on a finite element model by reducing stiffness in a region of the plate. Results show that the presence and location of the damage can be effectively identified even with noisy features and missing data. The performance and applicability of the proposed localized damage detection strategy for plate-like structures using discrete time-delayed binary data from a novel wireless sensor network is thus demonstrated.