Structure-Crack Detection and Digital Twin Demonstration Based on Triboelectric Nanogenerator for Intelligent Maintenance

Abstract

The accomplishment of condition monitoring and intelligent maintenance for cantilever structure-based energy harvesting devices remains a challenge. Here, to tackle the problems, a novel cantilever-structure freestanding triboelectric nanogenerator (CSF-TENG) is proposed, which can capture ambient energy or transmit sensory information. First, with and without a crack in cantilevers, the simulations are carried out. According to simulation results, the maximum change ratios of natural frequency and amplitude are 1.1% and 2.2%, causing difficulties in identifying defects by these variations. Thus, based on Gramian angular field and convolutional neural network, a defect detection model is established to achieve the condition monitoring of the CSF-TENG, and the experimental result manifests that the accuracy of the model is 99.2%. Besides, the relation between the deflection of cantilevers and the output voltages of the CSF-TENG is first built, and then the defect identification digital twin system is successfully created. Consequently, the system is capable of duplicating the operation of the CSF-TENG in a real environment, and displaying defect recognition results, so the intelligent maintenance of the CSF-TENG can be realized.