A temperature prediction model for coal spontaneous combustion based on PSO-SRU deep artificial neural networks
Traditional temperature prediction models for coal spontaneous combustion typically have low generality and robustness. This paper improves them by proposing a coal spontaneous combustion temperature prediction model based on particle swarm optimization and simple recurrent unit(PSO-SRU). It firstly...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Industry and Mine Automation
2022-04-01
|
| Series: | Gong-kuang zidonghua |
| Subjects: | |
| Online Access: | http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2021090047 |
| _version_ | 1827988542160109568 |
|---|---|
| author | JIA Pengtao LIN Kaiyi GUO Fengjing |
| author_facet | JIA Pengtao LIN Kaiyi GUO Fengjing |
| author_sort | JIA Pengtao |
| collection | DOAJ |
| description | Traditional temperature prediction models for coal spontaneous combustion typically have low generality and robustness. This paper improves them by proposing a coal spontaneous combustion temperature prediction model based on particle swarm optimization and simple recurrent unit(PSO-SRU). It firstly pre-processes the gas concentration data collected from temperature programmed oxidation tests, selects the concentration data of O2, CO, CO2, CH4, C2H4 that highly relate to the coal temperature as the prediction indicators, and further separates the indicators into training and testing data sets. Then, a SRU based prediction model over the training data set is trained to learn the nonlinear relationship between the coal spontaneous combustion temperature and the indicators. Mean absolute error(MAE) forms the fitness function and PSO algorithms are involved to optimize the SRU prediction model's parameters. Finally, the PSO-SRU model with optimized parameters are applied over the testing data set to predict the coal spontaneous combustion temperature. Experiments show the PSO-SRU model can improve the prediction accuracy, as the model's MAE and root mean square error(RMSE), comparing with those generated by support vector regression(SVR), random forest(RF), and back propagation(BP), decreases by 12.58, 7.65, 5.91 ℃, and 22.65, 17.45, 8.94 ℃ respectively. The PSO-SRU model also demonstrates a good generality and robustness, as the difference of determination coefficient (R2) of the model over the training and testing data sets is only 0.03. |
| first_indexed | 2024-04-10T00:05:16Z |
| format | Article |
| id | doaj.art-2042391a7cb843b3abbd928c32291dfa |
| institution | Directory Open Access Journal |
| issn | 1671-251X |
| language | zho |
| last_indexed | 2024-04-10T00:05:16Z |
| publishDate | 2022-04-01 |
| publisher | Editorial Department of Industry and Mine Automation |
| record_format | Article |
| series | Gong-kuang zidonghua |
| spelling | doaj.art-2042391a7cb843b3abbd928c32291dfa2023-03-17T01:02:52ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2022-04-0148410511310.13272/j.issn.1671-251x.2021090047A temperature prediction model for coal spontaneous combustion based on PSO-SRU deep artificial neural networksJIA Pengtao0LIN Kaiyi1GUO Fengjing2College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054, ChinaCollege of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054, ChinaShaanxi Jianxin Coal Chemical Co., Ltd., Huangling 727300, ChinaTraditional temperature prediction models for coal spontaneous combustion typically have low generality and robustness. This paper improves them by proposing a coal spontaneous combustion temperature prediction model based on particle swarm optimization and simple recurrent unit(PSO-SRU). It firstly pre-processes the gas concentration data collected from temperature programmed oxidation tests, selects the concentration data of O2, CO, CO2, CH4, C2H4 that highly relate to the coal temperature as the prediction indicators, and further separates the indicators into training and testing data sets. Then, a SRU based prediction model over the training data set is trained to learn the nonlinear relationship between the coal spontaneous combustion temperature and the indicators. Mean absolute error(MAE) forms the fitness function and PSO algorithms are involved to optimize the SRU prediction model's parameters. Finally, the PSO-SRU model with optimized parameters are applied over the testing data set to predict the coal spontaneous combustion temperature. Experiments show the PSO-SRU model can improve the prediction accuracy, as the model's MAE and root mean square error(RMSE), comparing with those generated by support vector regression(SVR), random forest(RF), and back propagation(BP), decreases by 12.58, 7.65, 5.91 ℃, and 22.65, 17.45, 8.94 ℃ respectively. The PSO-SRU model also demonstrates a good generality and robustness, as the difference of determination coefficient (R2) of the model over the training and testing data sets is only 0.03.http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2021090047temperature prediction of coal spontaneous combustiongas indicatordeep artificial neural networkrecurrent neural networksimple recurrent unitparticle swarm optimization |
| spellingShingle | JIA Pengtao LIN Kaiyi GUO Fengjing A temperature prediction model for coal spontaneous combustion based on PSO-SRU deep artificial neural networks Gong-kuang zidonghua temperature prediction of coal spontaneous combustion gas indicator deep artificial neural network recurrent neural network simple recurrent unit particle swarm optimization |
| title | A temperature prediction model for coal spontaneous combustion based on PSO-SRU deep artificial neural networks |
| title_full | A temperature prediction model for coal spontaneous combustion based on PSO-SRU deep artificial neural networks |
| title_fullStr | A temperature prediction model for coal spontaneous combustion based on PSO-SRU deep artificial neural networks |
| title_full_unstemmed | A temperature prediction model for coal spontaneous combustion based on PSO-SRU deep artificial neural networks |
| title_short | A temperature prediction model for coal spontaneous combustion based on PSO-SRU deep artificial neural networks |
| title_sort | temperature prediction model for coal spontaneous combustion based on pso sru deep artificial neural networks |
| topic | temperature prediction of coal spontaneous combustion gas indicator deep artificial neural network recurrent neural network simple recurrent unit particle swarm optimization |
| url | http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2021090047 |
| work_keys_str_mv | AT jiapengtao atemperaturepredictionmodelforcoalspontaneouscombustionbasedonpsosrudeepartificialneuralnetworks AT linkaiyi atemperaturepredictionmodelforcoalspontaneouscombustionbasedonpsosrudeepartificialneuralnetworks AT guofengjing atemperaturepredictionmodelforcoalspontaneouscombustionbasedonpsosrudeepartificialneuralnetworks AT jiapengtao temperaturepredictionmodelforcoalspontaneouscombustionbasedonpsosrudeepartificialneuralnetworks AT linkaiyi temperaturepredictionmodelforcoalspontaneouscombustionbasedonpsosrudeepartificialneuralnetworks AT guofengjing temperaturepredictionmodelforcoalspontaneouscombustionbasedonpsosrudeepartificialneuralnetworks |