基于更新样本智能识别算法的自适应集成建模  

Adaptive Ensemble Modelling Approach Based on Updating Sample Intelligent Identification

作　　者：汤健[1,2] 柴天佑[2] 刘卓[2] 余文 周晓杰[2] 

机构地区：[1]北方交通大学计算所 [2]东北大学流程工业综合自动化国家重点实验室 [3]墨西哥国立理工大学高级研究中心(CINVESTAV-IPN),墨西哥墨西哥07360

出　　处：《自动化学报》2016年第7期1040-1052,共13页Acta Automatica Sinica

基　　金：国家高技术研究发展计划(863计划)(2015AA043802);国家自然科学基金(61573364;61273177;61305029;61503066;61573249);中国博士后科学基金(2013M532118;2015T81082;2015M581355);流程工业综合自动化国家重点实验室开放课题基金资助项目(PAL-N201504);江苏高校优势学科建设工程资助项目;江苏省大气环境与装备技术协同创新中心资助~~

摘　　要：选择表征建模对象特性漂移的新样本对软测量模型进行自适应更新,能够降低模型复杂度和运行消耗,提高模型可解释性和预测精度.针对新样本近似线性依靠程度(Approximate linear dependence,ALD)和预测误差(Prediction error,PE)等指标只能片面反映建模对象的漂移程度,领域专家结合具体工业过程需要依据上述指标和自身积累经验进行更新样本的有效识别等问题,本文提出了基于更新样本智能识别算法的自适应集成建模策略.首先,基于历史数据离线建立基于改进随机向量泛函连接网络(Improved random vector functional-link networks,IRVFL)的选择性集成模型;然后,基于集成子模型对新样本进行预测输出后采用在线自适应加权算法(On-line adaptive weighting fusion,OLAWF)对集成子模型权重进行更新,实现在线测量阶段对建模对象特性变化的动态自适应;接着基于领域专家知识构建模糊推理模型对新样本相对ALD(Relative ALD,RALD)值和相对PE(Relative PE,RPE)值进行融合,实现更新样本智能识别,构建新的建模样本库;最后实现集成模型的在线自适应更新.采用合成数据仿真验证了所提算法的合理性和有效性.Some new samples can represent concept drift of the modeling plant. Adaptive updating soft sensor model with these new samples can reduce model complexity and running consumption, improve model interpretation and prediction performance. Concept drift embodies on both approximate linear dependence （ALD） and prediction error （PE）. In industrial practice, whether to update the old soft measuring models should be decided by the domain experts. Aimmed at these problems, a new online ensemble modeling approach based on updating sample intelligent identification is proposed in this paper. At first, the offiine ensemble model based on improved random vector functional-link networks （IRVFL） algorithm is used for online prediction using the new sample. Then, relative ALD （RALD） and relative PE （RPE） values of the new sample are fed into the fuzzy inference model based on domain expert＇s knowledge, whose output is used to identify whether this new sample is taken to updating the model. At last, the ensemble model is updated with the re-training strategy. Simulation results based on synthetic data show that the proposed method is valid and effective.

关 键 词：集成学习 更新样本识别 模糊推理 近似线性依靠 预测误差 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]