Deep Learning Model to Predict Ice Crystal Growth
Abstract The demand for highly specific and complex materials has made the development of controllable manufacturing processes crucial. Among the numerous manufacturing methods, casting is important because it is economical and highly flexible regarding the geometry of manufactured parts. Since soli...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-07-01
|
| Series: | Advanced Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/advs.202207731 |
| _version_ | 1827891498221305856 |
|---|---|
| author | Bor‐Yann Tseng Chen‐Wei Conan Guo Yu‐Chen Chien Jyn‐Ping Wang Chi‐Hua Yu |
| author_facet | Bor‐Yann Tseng Chen‐Wei Conan Guo Yu‐Chen Chien Jyn‐Ping Wang Chi‐Hua Yu |
| author_sort | Bor‐Yann Tseng |
| collection | DOAJ |
| description | Abstract The demand for highly specific and complex materials has made the development of controllable manufacturing processes crucial. Among the numerous manufacturing methods, casting is important because it is economical and highly flexible regarding the geometry of manufactured parts. Since solidification is an important stage in the casting process that influences the properties of the final product, the development of a controllable solidification process using modeling methods is necessary to create superior structural properties. However, traditional modeling methods are computationally expensive and require sophisticated mathematical schemes. Therefore, a deep learning model is proposed to predict the morphology of the dendritic crystal growth solidification process, along with a reinforcement learning model to control the solidification process. By training the deep learning model with data generated using the phase field method, the solidification process can be successfully predicted. The crystal growth structures are designed to be altered by adjusting the degree of supercooling in the deep learning model while implementing reinforcement learning to control the dendritic arteries. This research opens new avenues for applying artificial intelligence to the optimization of casting processes, with the potential to utilize it in the processing of advanced materials and to improve the target properties of material design. |
| first_indexed | 2024-03-12T21:26:43Z |
| format | Article |
| id | doaj.art-91144f270fea44f2bf38be56bd46587e |
| institution | Directory Open Access Journal |
| issn | 2198-3844 |
| language | English |
| last_indexed | 2024-03-12T21:26:43Z |
| publishDate | 2023-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Science |
| spelling | doaj.art-91144f270fea44f2bf38be56bd46587e2023-07-28T06:53:01ZengWileyAdvanced Science2198-38442023-07-011021n/an/a10.1002/advs.202207731Deep Learning Model to Predict Ice Crystal GrowthBor‐Yann Tseng0Chen‐Wei Conan Guo1Yu‐Chen Chien2Jyn‐Ping Wang3Chi‐Hua Yu4Department of Engineering Science National Cheng Kung University No. 1, University Rd. Tainan 701 TaiwanDepartment of Engineering Science National Cheng Kung University No. 1, University Rd. Tainan 701 TaiwanDepartment of Engineering Science National Cheng Kung University No. 1, University Rd. Tainan 701 TaiwanDepartment of Engineering Science National Cheng Kung University No. 1, University Rd. Tainan 701 TaiwanDepartment of Engineering Science National Cheng Kung University No. 1, University Rd. Tainan 701 TaiwanAbstract The demand for highly specific and complex materials has made the development of controllable manufacturing processes crucial. Among the numerous manufacturing methods, casting is important because it is economical and highly flexible regarding the geometry of manufactured parts. Since solidification is an important stage in the casting process that influences the properties of the final product, the development of a controllable solidification process using modeling methods is necessary to create superior structural properties. However, traditional modeling methods are computationally expensive and require sophisticated mathematical schemes. Therefore, a deep learning model is proposed to predict the morphology of the dendritic crystal growth solidification process, along with a reinforcement learning model to control the solidification process. By training the deep learning model with data generated using the phase field method, the solidification process can be successfully predicted. The crystal growth structures are designed to be altered by adjusting the degree of supercooling in the deep learning model while implementing reinforcement learning to control the dendritic arteries. This research opens new avenues for applying artificial intelligence to the optimization of casting processes, with the potential to utilize it in the processing of advanced materials and to improve the target properties of material design.https://doi.org/10.1002/advs.202207731castingdendritic structuregenerative model materialreinforcement learningsolidification |
| spellingShingle | Bor‐Yann Tseng Chen‐Wei Conan Guo Yu‐Chen Chien Jyn‐Ping Wang Chi‐Hua Yu Deep Learning Model to Predict Ice Crystal Growth Advanced Science casting dendritic structure generative model material reinforcement learning solidification |
| title | Deep Learning Model to Predict Ice Crystal Growth |
| title_full | Deep Learning Model to Predict Ice Crystal Growth |
| title_fullStr | Deep Learning Model to Predict Ice Crystal Growth |
| title_full_unstemmed | Deep Learning Model to Predict Ice Crystal Growth |
| title_short | Deep Learning Model to Predict Ice Crystal Growth |
| title_sort | deep learning model to predict ice crystal growth |
| topic | casting dendritic structure generative model material reinforcement learning solidification |
| url | https://doi.org/10.1002/advs.202207731 |
| work_keys_str_mv | AT boryanntseng deeplearningmodeltopredicticecrystalgrowth AT chenweiconanguo deeplearningmodeltopredicticecrystalgrowth AT yuchenchien deeplearningmodeltopredicticecrystalgrowth AT jynpingwang deeplearningmodeltopredicticecrystalgrowth AT chihuayu deeplearningmodeltopredicticecrystalgrowth |