控制理论与应用2024，Vol.41Issue(3)：436-446,11.DOI:10.7641/CTA.2022.20190
基于稀疏表示剪枝集成建模的烧结终点位置智能预测
Intelligent prediction of burning through point based on sparse representation pruning ensemble modeling
摘要
Abstract
The burning through point(BTP)is a crucial parameter in sintering process,which directly determines the quality of the final sinter.Since the BTP is difficult to directly detect online,it is of great significance to realize the online prediction of BTP through intelligent learning modeling and adjust the operating parameters on this basis to improve the quality of sinter.Aiming at this practical engineering problem,a Wrapper feature selection method based on the genetic algorithm is firstly proposed in this paper,which can select the feature combination that optimizes the subsequent predictive modeling performance as much as possible.Secondly,in order to solve the problem of easy overfitting in intelligent modeling of a single learner,a sparse representation pruning(SRP)ensemble modeling algorithm based on the random vector functional-link networks(RVFLNs)is proposed,namely SRP-ERVFLNs.The proposed method uses RVFLNs with fast modeling speed and good generalization performance as individual base learners,and perturbs the parameters of the base learner to increase the difference between the ensemble learning sub-models.At the same time,in order to further improve the generalization performance and computational efficiency of the ensemble model,a sparse representation pruning algorithm is introduced to achieve effective pruning of the ensemble model.Finally,the proposed SRP-ERVFLNs algorithm is used for prediction modeling of the BTP in the sintering process.Experiments using industrial data show that the proposed method has better prediction accuracy,generalization performance and computational efficiency than other methods.关键词
智能预测/特征选择/集成学习/稀疏表示/剪枝/烧结终点位置/随机权神经网络(RVFLNs)Key words
intelligent prediction/feature selection/ensemble learning/sparse representation/pruning/burning through point(BTP)/random vector functional-link networks(RVFLNs)引用本文复制引用
周平,吴忠卫,张瑞垚,吴永建..基于稀疏表示剪枝集成建模的烧结终点位置智能预测[J].控制理论与应用,2024,41(3):436-446,11.基金项目
国家自然科学基金项目(U22A2049,61890934),兴辽英才项目(XLYC1907132)资助.Supported by the National Natural Science Foundation of China(U22A2049,61890934)and the Liaoning Revitalization Talents Program(XLYC1907132). （U22A2049,61890934）
