An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNN
The moisture content of tobacco is a critical quality indicator in the tobacco processing, it is essential to control the moisture content of the tobacco within an appropriate range through the drying process. However, production often faces large delays in moisture measurement, leading to the diffi...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10843206/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586861064749056 |
|---|---|
| author | Wencai Wang Chen Yang Wenwei Niu Sidi Lin Qiang Gao Zhe Cao Jianning Chen Jianzhong Li Zhengkui Li |
| author_facet | Wencai Wang Chen Yang Wenwei Niu Sidi Lin Qiang Gao Zhe Cao Jianning Chen Jianzhong Li Zhengkui Li |
| author_sort | Wencai Wang |
| collection | DOAJ |
| description | The moisture content of tobacco is a critical quality indicator in the tobacco processing, it is essential to control the moisture content of the tobacco within an appropriate range through the drying process. However, production often faces large delays in moisture measurement, leading to the difficulty of anomaly detection and moisture control. This paper proposes a novel approach combining Correlation Graph and multi-scale Temporal Neural Networks(CGTNN) for real-time moisture prediction. The model transforms the raw data into graph data based on correlation coefficients, extracting the features in the production data from both spatial and temporal perspectives according to the strength of the relationships between different production processes. In addition, to address the risks posed by the uninterpretability of deep learning models,shapley values are used for interpretability analysis, aligning predictions with production experience. Experiments with production data show that the model accurately predicts moisture content with a Mean Absolute Error (MAE) of 0.016%, Root Mean Squared Error (RMSE) of 0.024%, and an Explainable variance (R2) of 0.987, outperforming other models. This approach significantly reduces delays and errors in moisture monitoring, enhancing accuracy and reliability in practical applications. |
| format | Article |
| id | doaj-art-65b610cc4226423691cf77f98d9f323f |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-65b610cc4226423691cf77f98d9f323f2025-01-25T00:00:52ZengIEEEIEEE Access2169-35362025-01-0113130521306910.1109/ACCESS.2025.352999210843206An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNNWencai Wang0https://orcid.org/0009-0006-2152-5051Chen Yang1https://orcid.org/0009-0004-0047-7308Wenwei Niu2Sidi Lin3Qiang Gao4Zhe Cao5Jianning Chen6Jianzhong Li7Zhengkui Li8Kunming Cigarette Factory, Hongyun Honghe Tobacco (Group) Company Ltd., Kunming, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, ChinaKunming Cigarette Factory, Hongyun Honghe Tobacco (Group) Company Ltd., Kunming, ChinaKunming Cigarette Factory, Hongyun Honghe Tobacco (Group) Company Ltd., Kunming, ChinaKunming Cigarette Factory, Hongyun Honghe Tobacco (Group) Company Ltd., Kunming, ChinaKunming Cigarette Factory, Hongyun Honghe Tobacco (Group) Company Ltd., Kunming, ChinaKunming Cigarette Factory, Hongyun Honghe Tobacco (Group) Company Ltd., Kunming, ChinaKunming Cigarette Factory, Hongyun Honghe Tobacco (Group) Company Ltd., Kunming, ChinaKunming Cigarette Factory, Hongyun Honghe Tobacco (Group) Company Ltd., Kunming, ChinaThe moisture content of tobacco is a critical quality indicator in the tobacco processing, it is essential to control the moisture content of the tobacco within an appropriate range through the drying process. However, production often faces large delays in moisture measurement, leading to the difficulty of anomaly detection and moisture control. This paper proposes a novel approach combining Correlation Graph and multi-scale Temporal Neural Networks(CGTNN) for real-time moisture prediction. The model transforms the raw data into graph data based on correlation coefficients, extracting the features in the production data from both spatial and temporal perspectives according to the strength of the relationships between different production processes. In addition, to address the risks posed by the uninterpretability of deep learning models,shapley values are used for interpretability analysis, aligning predictions with production experience. Experiments with production data show that the model accurately predicts moisture content with a Mean Absolute Error (MAE) of 0.016%, Root Mean Squared Error (RMSE) of 0.024%, and an Explainable variance (R2) of 0.987, outperforming other models. This approach significantly reduces delays and errors in moisture monitoring, enhancing accuracy and reliability in practical applications.https://ieeexplore.ieee.org/document/10843206/Tobacco dryinggraph neural networkscorrelation analysisspatial and temporal analysisdeep learning interpretability |
| spellingShingle | Wencai Wang Chen Yang Wenwei Niu Sidi Lin Qiang Gao Zhe Cao Jianning Chen Jianzhong Li Zhengkui Li An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNN IEEE Access Tobacco drying graph neural networks correlation analysis spatial and temporal analysis deep learning interpretability |
| title | An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNN |
| title_full | An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNN |
| title_fullStr | An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNN |
| title_full_unstemmed | An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNN |
| title_short | An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNN |
| title_sort | interpretable prediction method for tobacco drying process based on cgtnn |
| topic | Tobacco drying graph neural networks correlation analysis spatial and temporal analysis deep learning interpretability |
| url | https://ieeexplore.ieee.org/document/10843206/ |
| work_keys_str_mv | AT wencaiwang aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT chenyang aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT wenweiniu aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT sidilin aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT qianggao aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT zhecao aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT jianningchen aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT jianzhongli aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT zhengkuili aninterpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT wencaiwang interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT chenyang interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT wenweiniu interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT sidilin interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT qianggao interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT zhecao interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT jianningchen interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT jianzhongli interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn AT zhengkuili interpretablepredictionmethodfortobaccodryingprocessbasedoncgtnn |