Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selection
A posterior probability and intra-cluster feature weight online dynamic feature selection algorithm is proposed to address the issues of high dimensionality and high volatility of data in the basic oxygen furnace (BOF) steelmaking production process. First, a genetic algorithm with fixed feature spa...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2025-01-01
|
| Series: | High Temperature Materials and Processes |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/htmp-2024-0067 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832593696860667904 |
|---|---|
| author | Wang Haodong Liu Hui Chen FuGang Li Heng Xue XiaoJun |
| author_facet | Wang Haodong Liu Hui Chen FuGang Li Heng Xue XiaoJun |
| author_sort | Wang Haodong |
| collection | DOAJ |
| description | A posterior probability and intra-cluster feature weight online dynamic feature selection algorithm is proposed to address the issues of high dimensionality and high volatility of data in the basic oxygen furnace (BOF) steelmaking production process. First, a genetic algorithm with fixed feature space dimensions is introduced, which narrows the solution space by predefining the number of selected features, thereby enhancing the stability of feature selection. Second, the posterior probability of samples and intra-cluster feature weights are used to weigh and calculate the feature importance of the current sample, obtaining the optimal features that align with the current operating conditions. Finally, the dynamically selected features are used in a regression model to predict the carbon content and temperature of the BOF steelmaking process data. Simulations of actual BOF steelmaking process data showed that the prediction accuracy was 86% within a carbon content error range of 0.02, and 88% within a temperature error range of 10°C. |
| format | Article |
| id | doaj-art-b3774a3293aa4570a16bdf1d4dd56c76 |
| institution | Kabale University |
| issn | 2191-0324 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | High Temperature Materials and Processes |
| spelling | doaj-art-b3774a3293aa4570a16bdf1d4dd56c762025-01-20T11:08:40ZengDe GruyterHigh Temperature Materials and Processes2191-03242025-01-01441pp. 31610.1515/htmp-2024-0067Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selectionWang Haodong0Liu Hui1Chen FuGang2Li Heng3Xue XiaoJun4Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, ChinaYunnan Kungang Electronic and Information Science Ltd, Kunming, 650302, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, ChinaA posterior probability and intra-cluster feature weight online dynamic feature selection algorithm is proposed to address the issues of high dimensionality and high volatility of data in the basic oxygen furnace (BOF) steelmaking production process. First, a genetic algorithm with fixed feature space dimensions is introduced, which narrows the solution space by predefining the number of selected features, thereby enhancing the stability of feature selection. Second, the posterior probability of samples and intra-cluster feature weights are used to weigh and calculate the feature importance of the current sample, obtaining the optimal features that align with the current operating conditions. Finally, the dynamically selected features are used in a regression model to predict the carbon content and temperature of the BOF steelmaking process data. Simulations of actual BOF steelmaking process data showed that the prediction accuracy was 86% within a carbon content error range of 0.02, and 88% within a temperature error range of 10°C.https://doi.org/10.1515/htmp-2024-0067bof steelmakingsoft sensoronline dynamic feature selection algorithmgenetic algorithm |
| spellingShingle | Wang Haodong Liu Hui Chen FuGang Li Heng Xue XiaoJun Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selection High Temperature Materials and Processes bof steelmaking soft sensor online dynamic feature selection algorithm genetic algorithm |
| title | Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selection |
| title_full | Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selection |
| title_fullStr | Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selection |
| title_full_unstemmed | Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selection |
| title_short | Endpoint carbon content and temperature prediction model in BOF steelmaking based on posterior probability and intra-cluster feature weight online dynamic feature selection |
| title_sort | endpoint carbon content and temperature prediction model in bof steelmaking based on posterior probability and intra cluster feature weight online dynamic feature selection |
| topic | bof steelmaking soft sensor online dynamic feature selection algorithm genetic algorithm |
| url | https://doi.org/10.1515/htmp-2024-0067 |
| work_keys_str_mv | AT wanghaodong endpointcarboncontentandtemperaturepredictionmodelinbofsteelmakingbasedonposteriorprobabilityandintraclusterfeatureweightonlinedynamicfeatureselection AT liuhui endpointcarboncontentandtemperaturepredictionmodelinbofsteelmakingbasedonposteriorprobabilityandintraclusterfeatureweightonlinedynamicfeatureselection AT chenfugang endpointcarboncontentandtemperaturepredictionmodelinbofsteelmakingbasedonposteriorprobabilityandintraclusterfeatureweightonlinedynamicfeatureselection AT liheng endpointcarboncontentandtemperaturepredictionmodelinbofsteelmakingbasedonposteriorprobabilityandintraclusterfeatureweightonlinedynamicfeatureselection AT xuexiaojun endpointcarboncontentandtemperaturepredictionmodelinbofsteelmakingbasedonposteriorprobabilityandintraclusterfeatureweightonlinedynamicfeatureselection |