Model for Predicting CO<sub>2</sub> Adsorption in Coal Left in Goaf Based on Backpropagation Neural Network
Injecting power plant flue gas into a goaf stores CO<sub>2</sub> in the flue gas and effectively prevents the spontaneous combustion of the coal remaining in the goaf. Here, we investigated the adsorption behavior of three types of coal at normal temperature and pressure using a self-dev...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/9/3760 |
| _version_ | 1797602685201940480 |
|---|---|
| author | Fei Gao Peng Wang Dapeng Wang Yulong Yang Xun Zhang Gang Bai |
| author_facet | Fei Gao Peng Wang Dapeng Wang Yulong Yang Xun Zhang Gang Bai |
| author_sort | Fei Gao |
| collection | DOAJ |
| description | Injecting power plant flue gas into a goaf stores CO<sub>2</sub> in the flue gas and effectively prevents the spontaneous combustion of the coal remaining in the goaf. Here, we investigated the adsorption behavior of three types of coal at normal temperature and pressure using a self-developed adsorption experimental device. We used a specific surface area and porosity analyzer to study the effects of pore structure, mineral content, and moisture content on CO<sub>2</sub> adsorption in coal. Based on the experimental data, we designed a multifactor CO<sub>2</sub> adsorption prediction model based on a backpropagation (BP) neural network. The results indicated that the pore size of most micropores in coal was in the range of 0.5–0.7 and 0.8–0.9 nm. The specific surface area and pore volume were positively correlated with the CO<sub>2</sub>-saturated adsorption capacity, whereas the mean pore diameter, mineral content, and moisture content were inversely associated with the CO<sub>2</sub>-saturated adsorption amount. The accuracy of the multifactor BP neural network prediction model was satisfactory: the determination coefficients (<i>R</i><sup>2</sup>) of the training and test sets were both above 0.98, the root mean square error (RMSE) and mean absolute error (MAE) of the test set were both less than 0.1, and the prediction results satisfied the requirements. To optimize the prediction performance of the model, we used the random forest algorithm to calculate the importance of each factor. The sum of the importance weights of the specific surface area, moisture content, and pore volume was 91.6%, which was much higher than that of the other two factors. Therefore, we constructed an optimization model with specific surface area, moisture content, and pore volume as input variables. The <i>R</i><sup>2</sup> values of the training and test sets in the simplified model were improved compared with those of the multifactor model, the RMSE and MAE were reduced, and the fitting effect was ideal. The prediction model of CO<sub>2</sub> adsorption in coal based on the BP neural network can predict the CO<sub>2</sub> adsorption capacity of coal under different physical and chemical conditions, thereby providing theoretical support for the application of CO<sub>2</sub> storage technology in goafs. |
| first_indexed | 2024-03-11T04:20:05Z |
| format | Article |
| id | doaj.art-5ff91677d0294a19a4130816c3fc6214 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T04:20:05Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-5ff91677d0294a19a4130816c3fc62142023-11-17T22:51:22ZengMDPI AGEnergies1996-10732023-04-01169376010.3390/en16093760Model for Predicting CO<sub>2</sub> Adsorption in Coal Left in Goaf Based on Backpropagation Neural NetworkFei Gao0Peng Wang1Dapeng Wang2Yulong Yang3Xun Zhang4Gang Bai5School of Safety Science and Engineering, Liaoning Technical University, Fuxin 123008, ChinaSchool of Safety Science and Engineering, Liaoning Technical University, Fuxin 123008, ChinaShanxi Jinshen Energy Co., Ltd., Xinzhou 034000, ChinaShanxi Hequ Jinshen Ciyaogou Coal Industry Co., Ltd., Xinzhou 036500, ChinaCollege of Mining, Liaoning Technical University, Fuxin 123008, ChinaSchool of Safety Science and Engineering, Liaoning Technical University, Fuxin 123008, ChinaInjecting power plant flue gas into a goaf stores CO<sub>2</sub> in the flue gas and effectively prevents the spontaneous combustion of the coal remaining in the goaf. Here, we investigated the adsorption behavior of three types of coal at normal temperature and pressure using a self-developed adsorption experimental device. We used a specific surface area and porosity analyzer to study the effects of pore structure, mineral content, and moisture content on CO<sub>2</sub> adsorption in coal. Based on the experimental data, we designed a multifactor CO<sub>2</sub> adsorption prediction model based on a backpropagation (BP) neural network. The results indicated that the pore size of most micropores in coal was in the range of 0.5–0.7 and 0.8–0.9 nm. The specific surface area and pore volume were positively correlated with the CO<sub>2</sub>-saturated adsorption capacity, whereas the mean pore diameter, mineral content, and moisture content were inversely associated with the CO<sub>2</sub>-saturated adsorption amount. The accuracy of the multifactor BP neural network prediction model was satisfactory: the determination coefficients (<i>R</i><sup>2</sup>) of the training and test sets were both above 0.98, the root mean square error (RMSE) and mean absolute error (MAE) of the test set were both less than 0.1, and the prediction results satisfied the requirements. To optimize the prediction performance of the model, we used the random forest algorithm to calculate the importance of each factor. The sum of the importance weights of the specific surface area, moisture content, and pore volume was 91.6%, which was much higher than that of the other two factors. Therefore, we constructed an optimization model with specific surface area, moisture content, and pore volume as input variables. The <i>R</i><sup>2</sup> values of the training and test sets in the simplified model were improved compared with those of the multifactor model, the RMSE and MAE were reduced, and the fitting effect was ideal. The prediction model of CO<sub>2</sub> adsorption in coal based on the BP neural network can predict the CO<sub>2</sub> adsorption capacity of coal under different physical and chemical conditions, thereby providing theoretical support for the application of CO<sub>2</sub> storage technology in goafs.https://www.mdpi.com/1996-1073/16/9/3760coalpore structureCO<sub>2</sub> sequestrationinfluence factorsmachine learning |
| spellingShingle | Fei Gao Peng Wang Dapeng Wang Yulong Yang Xun Zhang Gang Bai Model for Predicting CO<sub>2</sub> Adsorption in Coal Left in Goaf Based on Backpropagation Neural Network Energies coal pore structure CO<sub>2</sub> sequestration influence factors machine learning |
| title | Model for Predicting CO<sub>2</sub> Adsorption in Coal Left in Goaf Based on Backpropagation Neural Network |
| title_full | Model for Predicting CO<sub>2</sub> Adsorption in Coal Left in Goaf Based on Backpropagation Neural Network |
| title_fullStr | Model for Predicting CO<sub>2</sub> Adsorption in Coal Left in Goaf Based on Backpropagation Neural Network |
| title_full_unstemmed | Model for Predicting CO<sub>2</sub> Adsorption in Coal Left in Goaf Based on Backpropagation Neural Network |
| title_short | Model for Predicting CO<sub>2</sub> Adsorption in Coal Left in Goaf Based on Backpropagation Neural Network |
| title_sort | model for predicting co sub 2 sub adsorption in coal left in goaf based on backpropagation neural network |
| topic | coal pore structure CO<sub>2</sub> sequestration influence factors machine learning |
| url | https://www.mdpi.com/1996-1073/16/9/3760 |
| work_keys_str_mv | AT feigao modelforpredictingcosub2subadsorptionincoalleftingoafbasedonbackpropagationneuralnetwork AT pengwang modelforpredictingcosub2subadsorptionincoalleftingoafbasedonbackpropagationneuralnetwork AT dapengwang modelforpredictingcosub2subadsorptionincoalleftingoafbasedonbackpropagationneuralnetwork AT yulongyang modelforpredictingcosub2subadsorptionincoalleftingoafbasedonbackpropagationneuralnetwork AT xunzhang modelforpredictingcosub2subadsorptionincoalleftingoafbasedonbackpropagationneuralnetwork AT gangbai modelforpredictingcosub2subadsorptionincoalleftingoafbasedonbackpropagationneuralnetwork |