Prediction of Slag Characteristics Based on Artificial Neural Network for Molten Gasification of Hazardous Wastes
Molten gasification is considered as a promising technology for the processing and safe disposal of hazardous wastes. During this process, the organic components are completely converted while the hazardous materials are safely embedded in slag via the fusion-solidification-vitrification transformat...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/19/5115 |
| _version_ | 1797551986518786048 |
|---|---|
| author | Xiongchao Lin Wenshuai Xi Jinze Dai Caihong Wang Yonggang Wang |
| author_facet | Xiongchao Lin Wenshuai Xi Jinze Dai Caihong Wang Yonggang Wang |
| author_sort | Xiongchao Lin |
| collection | DOAJ |
| description | Molten gasification is considered as a promising technology for the processing and safe disposal of hazardous wastes. During this process, the organic components are completely converted while the hazardous materials are safely embedded in slag via the fusion-solidification-vitrification transformation. Ideally, the slag should be glassy with low viscosity to ensure the effective immobilization and steady discharge of hazardous materials. However, it is very difficult to predict the characteristics of slag using existing empirical equations or conventional mathematical methods, due to the complex non-linear relationship among the phase transformation, vitrification transition and chemical composition of slag. Equipped with a strong nonlinear mapping ability, an artificial neural network may be able to predict the properties of slags if a large amount of data is available for training. In this work, over 10,000 experimental data points were used to train and develop a slag classification model (glassy vs. non-glassy) based on a neural network. The optimal structure of the neural network was figured out and validated. The results suggest that the classification accuracy for the independent test samples reached 93.3%. Using 1 and 0 as model inputs to represent mildly reducing and inert atmospheres, a double hidden layer structure in the neural network enabled the accurate classification of slags under various atmospheres. Furthermore, the neural network for the prediction of glassy slag viscosity was optimized; it featured a double hidden layer structure. Under a mildly reducing atmosphere, the absolute error from the independent test data was generally within 4 Pa·s. By adding a gas atmosphere into the input of the neural network using a simple normalization method, a multi-atmosphere slag viscosity prediction model was developed. Said model is much more accurate than its counterpart that does not consider the effect of the atmosphere. In summary, the artificial neural network proved to be an effective approach to predicting the slag properties under different atmospheres. The data-driven models developed in this work are expected to facilitate the commercial deployment of molten gasification technology. |
| first_indexed | 2024-03-10T15:53:38Z |
| format | Article |
| id | doaj.art-23e5d59dad39410595c37f4ae2406605 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T15:53:38Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-23e5d59dad39410595c37f4ae24066052023-11-20T15:48:30ZengMDPI AGEnergies1996-10732020-10-011319511510.3390/en13195115Prediction of Slag Characteristics Based on Artificial Neural Network for Molten Gasification of Hazardous WastesXiongchao Lin0Wenshuai Xi1Jinze Dai2Caihong Wang3Yonggang Wang4School of Chemical & Environmental Engineering, China University of Mining and Technology (Beijing), D11 Xueyuan Road, Haidian District, Beijing 100083, ChinaSchool of Chemical & Environmental Engineering, China University of Mining and Technology (Beijing), D11 Xueyuan Road, Haidian District, Beijing 100083, ChinaDepartment of Chemical Engineering, The University of Utah, 50 South Central Campus Drive, MEB Room 3290, Salt Lake City, UT 84112, USASchool of Chemical & Environmental Engineering, China University of Mining and Technology (Beijing), D11 Xueyuan Road, Haidian District, Beijing 100083, ChinaSchool of Chemical & Environmental Engineering, China University of Mining and Technology (Beijing), D11 Xueyuan Road, Haidian District, Beijing 100083, ChinaMolten gasification is considered as a promising technology for the processing and safe disposal of hazardous wastes. During this process, the organic components are completely converted while the hazardous materials are safely embedded in slag via the fusion-solidification-vitrification transformation. Ideally, the slag should be glassy with low viscosity to ensure the effective immobilization and steady discharge of hazardous materials. However, it is very difficult to predict the characteristics of slag using existing empirical equations or conventional mathematical methods, due to the complex non-linear relationship among the phase transformation, vitrification transition and chemical composition of slag. Equipped with a strong nonlinear mapping ability, an artificial neural network may be able to predict the properties of slags if a large amount of data is available for training. In this work, over 10,000 experimental data points were used to train and develop a slag classification model (glassy vs. non-glassy) based on a neural network. The optimal structure of the neural network was figured out and validated. The results suggest that the classification accuracy for the independent test samples reached 93.3%. Using 1 and 0 as model inputs to represent mildly reducing and inert atmospheres, a double hidden layer structure in the neural network enabled the accurate classification of slags under various atmospheres. Furthermore, the neural network for the prediction of glassy slag viscosity was optimized; it featured a double hidden layer structure. Under a mildly reducing atmosphere, the absolute error from the independent test data was generally within 4 Pa·s. By adding a gas atmosphere into the input of the neural network using a simple normalization method, a multi-atmosphere slag viscosity prediction model was developed. Said model is much more accurate than its counterpart that does not consider the effect of the atmosphere. In summary, the artificial neural network proved to be an effective approach to predicting the slag properties under different atmospheres. The data-driven models developed in this work are expected to facilitate the commercial deployment of molten gasification technology.https://www.mdpi.com/1996-1073/13/19/5115artificial neural networkhazardous wastesmolten gasificationslagviscosity |
| spellingShingle | Xiongchao Lin Wenshuai Xi Jinze Dai Caihong Wang Yonggang Wang Prediction of Slag Characteristics Based on Artificial Neural Network for Molten Gasification of Hazardous Wastes Energies artificial neural network hazardous wastes molten gasification slag viscosity |
| title | Prediction of Slag Characteristics Based on Artificial Neural Network for Molten Gasification of Hazardous Wastes |
| title_full | Prediction of Slag Characteristics Based on Artificial Neural Network for Molten Gasification of Hazardous Wastes |
| title_fullStr | Prediction of Slag Characteristics Based on Artificial Neural Network for Molten Gasification of Hazardous Wastes |
| title_full_unstemmed | Prediction of Slag Characteristics Based on Artificial Neural Network for Molten Gasification of Hazardous Wastes |
| title_short | Prediction of Slag Characteristics Based on Artificial Neural Network for Molten Gasification of Hazardous Wastes |
| title_sort | prediction of slag characteristics based on artificial neural network for molten gasification of hazardous wastes |
| topic | artificial neural network hazardous wastes molten gasification slag viscosity |
| url | https://www.mdpi.com/1996-1073/13/19/5115 |
| work_keys_str_mv | AT xiongchaolin predictionofslagcharacteristicsbasedonartificialneuralnetworkformoltengasificationofhazardouswastes AT wenshuaixi predictionofslagcharacteristicsbasedonartificialneuralnetworkformoltengasificationofhazardouswastes AT jinzedai predictionofslagcharacteristicsbasedonartificialneuralnetworkformoltengasificationofhazardouswastes AT caihongwang predictionofslagcharacteristicsbasedonartificialneuralnetworkformoltengasificationofhazardouswastes AT yonggangwang predictionofslagcharacteristicsbasedonartificialneuralnetworkformoltengasificationofhazardouswastes |