Precision glass thermoforming assisted by neural networks
Many glass products require thermoformed geometry with high precision. However, the traditional approach of developing a thermoforming process through trials and errors can cause a large waste of time and resources and often fails to produce successful outcomes. Hence, there is a need to develop an...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827025000842 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849469404659580928 |
|---|---|
| author | Yuzhou Zhang Mohan Hua Jinan Liu Haihui Ruan |
| author_facet | Yuzhou Zhang Mohan Hua Jinan Liu Haihui Ruan |
| author_sort | Yuzhou Zhang |
| collection | DOAJ |
| description | Many glass products require thermoformed geometry with high precision. However, the traditional approach of developing a thermoforming process through trials and errors can cause a large waste of time and resources and often fails to produce successful outcomes. Hence, there is a need to develop an efficient predictive model, replacing the costly simulations or experiments, to assist the design of precision glass thermoforming. In this work, we report a surrogate model, based on a dimensionless back-propagation neural network (BPNN), that can adequately predict the form errors and thus compensate for these errors in mold design using geometric features and process parameters as inputs. Our trials with simulation and industrial data indicate that the surrogate model can predict forming errors with adequate accuracy. Although perception errors (mold designers’ decisions) and mold fabrication errors make the industrial training data less reliable than simulation data, our preliminary training and testing results still achieved a reasonable consistency with industrial data, suggesting that the surrogate models are directly implementable in the glass-manufacturing industry. |
| format | Article |
| id | doaj-art-aebda15656704dfba35138dd5f830703 |
| institution | Kabale University |
| issn | 2666-8270 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj-art-aebda15656704dfba35138dd5f8307032025-08-20T03:25:29ZengElsevierMachine Learning with Applications2666-82702025-09-012110070110.1016/j.mlwa.2025.100701Precision glass thermoforming assisted by neural networksYuzhou Zhang0Mohan Hua1Jinan Liu2Haihui Ruan3Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Mechanical Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaBiel Crystal (HK) Manufactory Ltd., Hong Kong, ChinaDepartment of Mechanical Engineering, The Hong Kong Polytechnic University, Hong Kong, China; PolyU-Daya Bay Technology and Innovation Research Institute, Huizhou, Guangdong, China; Corresponding author.Many glass products require thermoformed geometry with high precision. However, the traditional approach of developing a thermoforming process through trials and errors can cause a large waste of time and resources and often fails to produce successful outcomes. Hence, there is a need to develop an efficient predictive model, replacing the costly simulations or experiments, to assist the design of precision glass thermoforming. In this work, we report a surrogate model, based on a dimensionless back-propagation neural network (BPNN), that can adequately predict the form errors and thus compensate for these errors in mold design using geometric features and process parameters as inputs. Our trials with simulation and industrial data indicate that the surrogate model can predict forming errors with adequate accuracy. Although perception errors (mold designers’ decisions) and mold fabrication errors make the industrial training data less reliable than simulation data, our preliminary training and testing results still achieved a reasonable consistency with industrial data, suggesting that the surrogate models are directly implementable in the glass-manufacturing industry.http://www.sciencedirect.com/science/article/pii/S2666827025000842Glass productsPrecision thermoformingError compensationNeural networkBPNN |
| spellingShingle | Yuzhou Zhang Mohan Hua Jinan Liu Haihui Ruan Precision glass thermoforming assisted by neural networks Machine Learning with Applications Glass products Precision thermoforming Error compensation Neural network BPNN |
| title | Precision glass thermoforming assisted by neural networks |
| title_full | Precision glass thermoforming assisted by neural networks |
| title_fullStr | Precision glass thermoforming assisted by neural networks |
| title_full_unstemmed | Precision glass thermoforming assisted by neural networks |
| title_short | Precision glass thermoforming assisted by neural networks |
| title_sort | precision glass thermoforming assisted by neural networks |
| topic | Glass products Precision thermoforming Error compensation Neural network BPNN |
| url | http://www.sciencedirect.com/science/article/pii/S2666827025000842 |
| work_keys_str_mv | AT yuzhouzhang precisionglassthermoformingassistedbyneuralnetworks AT mohanhua precisionglassthermoformingassistedbyneuralnetworks AT jinanliu precisionglassthermoformingassistedbyneuralnetworks AT haihuiruan precisionglassthermoformingassistedbyneuralnetworks |