摘要
针对化工过程软测量模型的多样性,提出基于一种加权模糊聚类方法的多模型建模方法。将输入向量与输出的相关性作为加权系数,构建加权模糊聚类算法,对样本空间的输入数据进行聚类,然后用与输入变量对应的子模型进行输出估计,子模型输出作为系统模型的最终输出。该方法能够实现对输入数据更加合理的划分,提高软测量模型的精度。将该方法应用于双酚A生产过程的质量指标软测量建模,仿真结果表明了该方法的可行性和有效性。
According to the diversity of multi-model soft-sensor,a multi-model modeling method based on weighted fuzzy clustering was presented.By using the correlation of input and output as weighted coefficient of fuzzy clustering algorithm,it was employed to cluster the input data of sample space.Then,the corresponding sub-model was used to estimate output,and final output was determined by the corresponding sub-model output.This method can achieve a more rational division of the input data to improve the accuracy of soft-sensor model.The multi-model is applied to a soft sensor in production process of Bisphenol A to estimate the quality performance,and the simulation results show that the feasibility and effectiveness.
出处
《化工自动化及仪表》
CAS
北大核心
2010年第5期6-8,12,共4页
Control and Instruments in Chemical Industry
基金
国家自然科学基金资助项目(60674092)
江苏省高技术研究项目(BG20060010)
江南大学创新团队发展计划资助项目
关键词
加权模糊聚类
子模型
软测量
多模型
weighted fuzzy clustering
sub-model
soft-sensor
multi-model
