A weighted SVM ensemble predictor based on AdaBoost for blast furnace Ironmaking process
| Autor: | Zian Dai, Ling Jian, Hongyi Chen, Tianxin Chen, Shihua Luo |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Blast furnace
Computer science business.industry Pattern recognition 02 engineering and technology Support vector machine ComputingMethodologies_PATTERNRECOGNITION Binary classification Artificial Intelligence 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing AdaBoost Artificial intelligence business Classifier (UML) |
| Zdroj: | Applied Intelligence. 50:1997-2008 |
| ISSN: | 1573-7497 0924-669X |
| DOI: | 10.1007/s10489-020-01662-y |
| Popis: | As one of the most complex industrial reactors, there remain some urgent issues for blast furnace (BF), such as BF automation, prediction of the inner thermal state, etc. In this work, the prediction of BF inner thermal state, which is represented by the silicon content in BF hot metal, is taken as an imbalanced binary classification problem and a Weighted Support Vector Machine (W-SVM) ensemble predictor based on AdaBoost is presented for the prediction task. Compared with the traditional W-SVM algorithm, the proposed predictor dynamically adjusts the weight distribution of training samples according to the performance of weak classifier, in this way to mine information lurked in the samples. The prediction can act as a guide to aid the operators for judging the thermal state of BF in time. Experiments results on five benchmark datasets and two real-world BFs datasets demonstrate the efficiency of the proposed W-SVM ensemble predictor. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink