Journal of Shanghai Jiao Tong University ›› 2021, Vol. 55 ›› Issue (5): 527-535.doi: 10.16183/j.cnki.jsjtu.2020.095

Special Issue: 《上海交通大学学报》2021年“交通运输工程”专题 《上海交通大学学报》2021年12期专题汇总专辑

Previous Articles     Next Articles

Method for Plate Crack Damage Detection Based on Long Short-Term Memory Neural Network

ZHANG Songlin, MA Dongliang, WANG Deyu()   

  1. Collaborative Innovation Center for Advanced Ship and Deep-Sea Exploration, Shanghai Jiao Tong University, Shanghai 200240, China
  • Received:2020-04-01 Online:2021-05-28 Published:2021-06-01
  • Contact: WANG Deyu


Aimed at the problem of intelligent classification of crack damage in different positions of the plate, a method for plate crack damage detection based on long short-term memory (LSTM) neural network is proposed. The Abaqus secondary development is used to build the plate crack damage model and calculate the acceleration response of the plate under Gaussian white noise excitation. The data set is generated by data augmentation, and the influence of noise on damage detection is considered. An intelligent crack detection model based on LSTM is established, which directly takes the acceleration response of the plate as the input and does not require additional damage feature extraction. With the goal of minimizing prediction error, the hyperparameter of the model is selected and the model configuration is optimized. The comparison of the multi-layer perceptron model and the multi-layer perceptron model based on wavelet packet transform shows that the LSTM model proposed in this paper has a higher damage location accuracy and a better applicability in plate crack detection.

Key words: damage detection, long short-term memory (LSTM) neural network, plate crack, noise

CLC Number: