Deep-learning-based pyramid-transformer for localized porosity analysis of hot-press sintered ceramic paste

• Published in: PloS one Vol. 19; no. 9; p. e0306385
• Main Authors: Xia, Zhongyi, Wu, Boqi, Chan, C Y, Wu, Tianzhao, Zhou, Man, Kong, Ling Bing
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 04.09.2024; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Aluminum oxide; Aluminum Oxide - chemistry; Analysis; Ceramic materials; Ceramic tools; Ceramics; Ceramics - chemistry; Datasets; Deep Learning; Dielectric properties; Entropy; Feature maps; Grain boundaries; Grain size; High temperature; Hot pressing; Hot Temperature; Image enhancement; Image processing; Image segmentation; Laser sintering; Machine learning; Methods; Microscopy, Electron, Scanning; Morphology; Neural networks; Noise reduction; Physical Sciences; Porosity; Properties; Research and Analysis Methods; Scanning electron microscopy; Semantic segmentation; Semantics; Similarity; Sintering; Sintering (powder metallurgy); Social Sciences; Transformers; Yttrium oxide; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0306385

Scanning Electron Microscope (SEM) is a crucial tool for studying microstructures of ceramic materials. However, the current practice heavily relies on manual efforts to extract porosity from SEM images. To address this issue, we propose PSTNet (Pyramid Segmentation Transformer Net) for grain and pore segmentation in SEM images, which merges multi-scale feature maps through operations like recombination and upsampling to predict and generate segmentation maps. These maps are used to predict the corresponding porosity at ceramic grain boundaries. To increase segmentation accuracy and minimize loss, we employ several strategies. (1) We train the micro-pore detection and segmentation model using publicly available Al2O3 and custom Y2O3 ceramic SEM images. We calculate the pixel percentage of segmented pores in SEM images to determine the surface porosity at the corresponding locations. (2) Utilizing high-temperature hot pressing sintering, we prepared and captured scanning electron microscope images of Y2O3 ceramics, with which a Y2O3 ceramic dataset was constructed through preprocessing and annotation. (3) We employed segmentation penalty cross-entropy loss, smooth L1 loss, and structural similarity (SSIM) loss as the constituent terms of a joint loss function. The segmentation penalty cross-entropy loss helps suppress segmentation loss bias, smooth L1 loss is utilized to reduce noise in images, and incorporating structural similarity into the loss function computation guides the model to better learn structural features of images, significantly improving the accuracy and robustness of semantic segmentation. (4) In the decoder stage, we utilized an improved version of the multi-head attention mechanism (MHA) for feature fusion, leading to a significant enhancement in model performance. Our model training is based on publicly available laser-sintered Al2O3 ceramic datasets and self-made high-temperature hot-pressed sintered Y2O3 ceramic datasets, and validation has been completed. Our Pix Acc score improves over the baseline by 12.2%, 86.52 vs. 76.01, and the mIoU score improves from by 25.5%, 69.10 vs. 51.49. The average relative errors on datasets Y2O3 and Al2O3 were 6.9% and 6.36%, respectively.