PDF
Full
Outline
Many types of defects are produced during the drilling of holes in carbon fiber reinforced composites, and of all the defects delamination has the most serious effect on the material. Therefore, it is crucial to develop an effective model that can accurately predict delamination in laminated materials. However, materials domain data is characterized by small samples, high latitude and complex relationships, which makes it necessary and feasible to use empirical knowledge to enhance the effectiveness of machine learning modeling. A knowledge-guided machine learning(KGML) model that integrates empirical knowledge and data-driven modeling is used to predict laminated material delamination, the fact that empirical knowledge is incorporated into the loss function as an adaptive weighting in order to enforce physical constraints during the training process. Finally, by comparing the prediction performance of the model without knowledge and the model with knowledge, the R2 of the model with knowledge was improved from 0.79 to 0.91, which successfully demonstrated the advantages of empirical knowledge-based machine learning, and provide a generalized approach for delamination prediction to reduce the experimentation time and cost for researchers.
PDF
231
115
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
