A Fully Convolutional Neural Network and Corresponding Mesostructure Recognition Method

Abstract

A fully convolutional neural network and corresponding mesostructure recognition method, through the comprehensive use of the method of maximum pooling index connection and channel connection in the network, the two methods are serially processed, making full use of the shallow low-level edge information of the encoder and Decoder deep semantic information and achieve better results. In the process of enlarging the image resolution, only upsampling is used, which reduces the consumption of video memory and the time of network training. By adopting batch regularization through cross symmetry, the original distribution state of the feature map after convolution is guaranteed as much as possible, which further enhances the expressive ability of convolutional neural network, realizes the semantic segmentation of XCT slices of CMCs preforms, and improves the accuracy of mesostructure recognition. Accuracy. The same fully convolutional neural network is used to identify the mesoscopic structure of the braided structure of different ceramic matrix composite prefabricated bodies, and the use of different fully convolutional neural network weight files for different braided structures is abandoned, which simplifies the identification operation.

Description

technical field [0001] The invention belongs to the field of mesoscopic structure recognition of prefabricated ceramic matrix composite materials, and in particular relates to a fully convolutional neural network for semantic segmentation of XCT slices of woven ceramic matrix composite materials. Background technique [0002] Ceramic matrix composites (CMCs, Ceramic Material Composites) usually use continuous ceramic fibers as the reinforcement phase, which is a material that can be applied under extreme conditions, and has the advantages of high temperature resistance, corrosion resistance, low density, and wear resistance. [0003] The skeleton composed of continuous ceramic fibers is called a complex preform, and its weaving structure includes plain weave, 2.5D, three-dimensional four-way, etc. The preparation process of CMCs includes chemical vapor deposition (CVI), precursor impregnation cracking (PIP), reaction melting (MI) and other methods. Usually, CMCs are prepare...

AI Technical Summary

Problems solved by technology

[0012] Aiming at the deficiencies in the prior art, the present invention provides a fully convolutional neural network and a corresponding mesostructure recognition method for the mesostructure recognition of XCT slices of ceramic matrix composite material preforms, because it is applied in the field of CMC, so Called CMCs_Net, it solves the problem of large memory usage and long training time of the full convolutional neural network, and further improves the accuracy of the network

Images