Neural Network Prediction Model for Sinter Mixture Water Content Based on KPCA-GA Optimization
The design and optimization of a sinter mixture moisture controlling system usually require complex process mechanisms and time-consuming field experimental simulations. Based on BP neural networks, a new KPCA-GA optimization method is proposed to predict the mixture moisture content sequential valu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/12/8/1287 |
| _version_ | 1797408950927228928 |
|---|---|
| author | Yuqian Ren Chuanqi Huang Yushan Jiang Zhaoxia Wu |
| author_facet | Yuqian Ren Chuanqi Huang Yushan Jiang Zhaoxia Wu |
| author_sort | Yuqian Ren |
| collection | DOAJ |
| description | The design and optimization of a sinter mixture moisture controlling system usually require complex process mechanisms and time-consuming field experimental simulations. Based on BP neural networks, a new KPCA-GA optimization method is proposed to predict the mixture moisture content sequential values with time more accurately so as to derive the optimal water addition to meet industrial requirements. Firstly, the normalized input variables affecting the output were dimensionalized using kernel principal component analysis (KPCA), and the contribution rates of the factors affecting the water content were analyzed. Then, a BP neural network model was established. In order to get rid of the randomness of the initial threshold and weights on the prediction accuracy of the model, a genetic algorithm is proposed to preferentially find the optimal initial threshold and weights for the model. Then, statistical indicators, such as the root mean square error, were used to evaluate the fit and prediction accuracy of the training and test data sets, respectively. The available experimental data show that the KPCA-GA model has high fitting and prediction accuracy, and the method has significant advantages over traditional neural network modeling methods when dealing with data sets with complex nonlinear characteristics, such as those from the sintering process. |
| first_indexed | 2024-03-09T04:06:06Z |
| format | Article |
| id | doaj.art-ec3652e5b5af40968edd3d57fc2c93f8 |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-09T04:06:06Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-ec3652e5b5af40968edd3d57fc2c93f82023-12-03T14:06:45ZengMDPI AGMetals2075-47012022-07-01128128710.3390/met12081287Neural Network Prediction Model for Sinter Mixture Water Content Based on KPCA-GA OptimizationYuqian Ren0Chuanqi Huang1Yushan Jiang2Zhaoxia Wu3College of Information Science and Engineering, Northeastern University, Qinhuangdao 066003, ChinaCollege of Information Science and Engineering, Northeastern University, Qinhuangdao 066003, ChinaInstitute of Data Analysis and Intelligence Computing, Northeastern University, Qinhuangdao 066003, ChinaInstitute of Data Analysis and Intelligence Computing, Northeastern University, Qinhuangdao 066003, ChinaThe design and optimization of a sinter mixture moisture controlling system usually require complex process mechanisms and time-consuming field experimental simulations. Based on BP neural networks, a new KPCA-GA optimization method is proposed to predict the mixture moisture content sequential values with time more accurately so as to derive the optimal water addition to meet industrial requirements. Firstly, the normalized input variables affecting the output were dimensionalized using kernel principal component analysis (KPCA), and the contribution rates of the factors affecting the water content were analyzed. Then, a BP neural network model was established. In order to get rid of the randomness of the initial threshold and weights on the prediction accuracy of the model, a genetic algorithm is proposed to preferentially find the optimal initial threshold and weights for the model. Then, statistical indicators, such as the root mean square error, were used to evaluate the fit and prediction accuracy of the training and test data sets, respectively. The available experimental data show that the KPCA-GA model has high fitting and prediction accuracy, and the method has significant advantages over traditional neural network modeling methods when dealing with data sets with complex nonlinear characteristics, such as those from the sintering process.https://www.mdpi.com/2075-4701/12/8/1287sinteringmoisture content predictionKPCAGA-BP hybrid prediction model |
| spellingShingle | Yuqian Ren Chuanqi Huang Yushan Jiang Zhaoxia Wu Neural Network Prediction Model for Sinter Mixture Water Content Based on KPCA-GA Optimization Metals sintering moisture content prediction KPCA GA-BP hybrid prediction model |
| title | Neural Network Prediction Model for Sinter Mixture Water Content Based on KPCA-GA Optimization |
| title_full | Neural Network Prediction Model for Sinter Mixture Water Content Based on KPCA-GA Optimization |
| title_fullStr | Neural Network Prediction Model for Sinter Mixture Water Content Based on KPCA-GA Optimization |
| title_full_unstemmed | Neural Network Prediction Model for Sinter Mixture Water Content Based on KPCA-GA Optimization |
| title_short | Neural Network Prediction Model for Sinter Mixture Water Content Based on KPCA-GA Optimization |
| title_sort | neural network prediction model for sinter mixture water content based on kpca ga optimization |
| topic | sintering moisture content prediction KPCA GA-BP hybrid prediction model |
| url | https://www.mdpi.com/2075-4701/12/8/1287 |
| work_keys_str_mv | AT yuqianren neuralnetworkpredictionmodelforsintermixturewatercontentbasedonkpcagaoptimization AT chuanqihuang neuralnetworkpredictionmodelforsintermixturewatercontentbasedonkpcagaoptimization AT yushanjiang neuralnetworkpredictionmodelforsintermixturewatercontentbasedonkpcagaoptimization AT zhaoxiawu neuralnetworkpredictionmodelforsintermixturewatercontentbasedonkpcagaoptimization |