Localization of low velocity impacts on CFRP laminates based on FBG sensors and BP neural networks

Abstract

Carbon fiber reinforced plastic (CFRP) structures are vulnerable to low-speed impacts, which will lead to almost invisible impact damage. Therefore, the timely localization of impact is of great significance to damage detection and maintenance of the structure. In this article, a low velocity impact supervisory and testing system based on fiber Bragg grating (FBG) sensors was built up for CFRP laminates to obtain the low velocity impact strain sensitivity model. Meanwhile, genetic algorithm was applied to optimize the configuration of the FBG sensing network. The eigenvectors of the impact signals were extracted by applying fast Fourier transform (FFT) transform and principal component analysis (PCA) technology used as the input of the back propagation (BP) neural network model, while the corresponding impact coordinates were used as the output, to train the model. After training, the impact position prediction model based on BP neural network was obtained, thereby achieving the impact localization for CFRP laminates successfully with an average localization error of 2.1 cm.

Keywords:

• localization
• impact
• BP neural network
• FBG sensor
• CFRP laminates
• sensing network configuration
• principal component analysis

Disclosure statement

Xianglong Wen: Conceptualization, Methodology, Funding acquisition. Quanzhi Sun: Investigation, Writing – Review & Editing. Wenhu Li: Software, Validation, Formal analysis, Writing – Original Draft. Guoping Ding: Resources, Visualization, Supervision. Chunsheng Song: Data Curation. Jinguang Zhang: Project administration.

Additional information

Funding

This research was supported by National Natural Science Foundation of China (No. 51775400, No. 51879209 and No. 51975435), Hubei Provincial Key Science and Technology Innovation Project (Project No. 2014AAA005), and The Fundamental Research Funds for the Central Universities (WUT: 2017III044).