Study on Prediction of Compression Performance of Composite Laminates After Impact Based on Convolutional Neural Networks

被引：1
作者：
Fengyang Jiang
Zhidong Guan
Xiaodong Wang
Zengshan Li
Riming Tan
Cheng Qiu
机构：
[1] Beihang University,School of Aeronautic Science and Engineering
[2] Hong Kong University of Science and Technology,Department of Mechanical and Aerospace Engineering
来源：
Applied Composite Materials | 2021年 / 28卷
关键词：
Damage tolerance; Non-destructive testing; Machine learning; Convolutional neural networks;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
This paper proposed a method for predicting composite laminates’ compressive residual strength after impact based on convolutional neural networks. Laminates made by M21E/IMA prepreg were used to introduce low-velocity impact damage and construct a non-destructive testing image dataset. The dataset images characterized the impact damage details, including dents, delamination, and matrix cracking. The convolution kernel automatically extracted and identified these complex features that could be used for classification. The model took the images as input and compressive residual strength labels as output for iterative training, and the final prediction accuracy reached more than 90%, the highest 96%. This method introduced overall damage into the model in the form of images utilizing convolution, which can quickly and accurately predicted laminates’ compression performance after impact.
引用
收藏
页码：1153 / 1173
页数：20
相关论文
共 141 条
  • [31] Sun W(2020)A Novel Method to Improve Temperature Uniformity in Polymer Composites Microwave Curing Process through Deep Learning with Historical Data Appl. Compos. Mater. 27 1-307
  • [32] Guan Z(2013)Prediction of Damage Factor in end Milling of Glass Fibre Reinforced Plastic Composites Using Artificial Neural Network Appl. Compos. Mater. 20 517-114
  • [33] Tan R(2020)Prediction of composite microstructure stress-strain curves using convolutional neural networks Mater. Des. 189 108509-E713
  • [34] He W(2011)Damage Detection in a Composite Plate Using Modal Analysis and Artificial Intelligence Appl. Compos. Mater. 18 513-1709
  • [35] Guan Z(2019)Damage mode identification of adhesive composite joints under hygrothermal environment using acoustic emission and machine learning Compos. Struct. 211 351-874
  • [36] Li X(2020)A modified transmissibility indicator and Artificial Neural Network for damage identification and quantification in laminated composite structures Compos. Struct. 248 112497-undefined
  • [37] Liu D(2019)Prediction and optimization of mechanical properties of composites using convolutional neural networks Compos. Struct. 227 111264-undefined
  • [38] Aoki Y(2019)Predicting the effective thermal conductivity of composites from cross sections images using deep learning methods Compos. Sci. Technol. 184 107861-undefined
  • [39] Suemasu H(2020)Defect identification in composite materials via thermography and deep learning techniques Compos. Struct. 246 112405-undefined
  • [40] Ishikawa T(2018)Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning Genet Program Evolvable Mach. 19 305-undefined
12345678910