Two kinds of advanced image processing were applied to multi-phase microstructures. One is evolutional image processing where optimized filter set was suggested by genetic programing. Another is trainable WEKA segment...
详细信息
Two kinds of advanced image processing were applied to multi-phase microstructures. One is evolutional image processing where optimized filter set was suggested by genetic programing. Another is trainable WEKA segmentation where features are extracted by many kinds of filters, followed by machine learning for classification. Once an optimized filter set is determined, efficiency of image processing for new data set is improved remarkably in comparison with a case of manual image processing.
Fly ash-based geopolymer, regarded as a eco-friendly cementitious material instead of ordinary Portland cement, has been rapidly developed and applied in practical engineering practice. Previous researches demonstrate...
详细信息
Fly ash-based geopolymer, regarded as a eco-friendly cementitious material instead of ordinary Portland cement, has been rapidly developed and applied in practical engineering practice. Previous researches demonstrated that calcium component produces distinct effect on the formation of polymer gel products, and therefore influencing the macroscopic mechanical behaviors and microstructure of geopolymers. However, the influence mechanism of calcium component on the formation of gels product is still not clear. In this study, different content of Ca (OH)(2) were adopted to prepare calcium containing geopolymers. The compressive strength and hydrochloric-acid attack tests were conducted to evaluate the effect of calcium content on the macro-performances. Then, scanning electron microscopy-energy spectrum test (SEM-EDS) was carried out to accesses the morphology and elemental components of the prepared composites. Thereafter, the microstructure of gels product was probed through Fourier transform infrared (FTIR) spectroscopy and Si-29 nuclear magnetic resonance (NMR) spectroscopy. The critical value of elemental ratio (Na + K + Ca)/Al to characterize the gel product was specified. Two kinds of fly ash and two alkali-activated solutions were adopted to verify the results. The geopolymerization products will be calcium-containing geopolymer gels (C,N-A-S-H) when (Na + K + Ca)/Al <= 0.95, while be coexist form of C-S-H and N-A-S-H gels when (Na + K + Ca)/Al > 0.95. The results provide experimental basis and references for the application of calcium-containing solid wastes in geopolymer materials.
This review explores the applications, challenges, and prospects of deep learning in the microstructure analysis of alloy materials. First, it introduces the significance of alloy materials in modern industry, along w...
详细信息
This review explores the applications, challenges, and prospects of deep learning in the microstructure analysis of alloy materials. First, it introduces the significance of alloy materials in modern industry, along with the continuous advancements in microscopy techniques and deep learning. Next, it briefly outlines the fundamental concepts and workflow of deep learning. In the critical section of this review, it elucidates how deep learning, through learning and training, can extract features from a large volume of alloy microstructure data and accurately classify these microstructures. Furthermore, deep learning can also be applied to tasks such as image segmentation in alloy microstructure images, including object detection and instance segmentation, facilitating the extraction of pertinent information from complex images. This, in turn, allows the establishment of the "microstructure-performance" relationship for effective performance prediction. Finally, it summarizes the prospects of deep learning in alloy material applications and the challenges related to data acquisition, model training,and performance optimization.
暂无评论