Fracture toughness evaluation of silicon nitride from microstructures via convolutional neural network. Issue 2 (5th October 2022)

• Record Type: Journal Article
• Authors: Furushima, Ryoichi; Maruyama, Yutaka; Nakashima, Yuki; Ngo, Minh Chu; Ohji, Tatsuki; Fukushima, Manabu
• Is Part Of: Journal of the American Ceramic Society. Volume 106:Issue 2(2023)
• Page Start: 817
• Page End: 821
• Publication Date: 2022-10-05
• Subjects: convolutional neural network -- deep learning -- fracture toughness -- microstructure -- silicon nitride; Ceramics -- Periodicals; 620.1405
• DOI: 10.1111/jace.18795
• Languages: English
• ISSNs: 0002-7820

Abstract

Abstract: The fracture toughness of silicon nitride (Si3 N4 ) ceramics was evaluated directly from their microstructures via deep learning using convolutional neural network models. Totally 156 data sets containing microstructural images and relative densities were prepared from 45 types of Si3 N4 samples as input feature quantities (IFQs) and were correlated to the fracture toughness as an objective variable. The data sets were divided into two groups. One was used for training, resulting in the creation of regression models for two kinds of IFQs: the microstructures only and a combination of the microstructures and the relative densities. The other group was used for testing the validity of the created models. As a result, the determination coefficient was approximately 0.8 even when using only the microstructures as the IFQs and was further improved when adding the relative densities. It was revealed that the fracture toughness of Si3 N4 ceramics was well evaluated from their microstructures.