CIESC Journal ›› 2018, Vol. 69 ›› Issue (3): 1149-1157.DOI: 10.11949/j.issn.0438-1157.20171188

Previous Articles     Next Articles

Multi-delay identification by trend-similarity analysis and its application to hydrocracking process

WANG Yalin, XIA Haibing, YUAN Xiaofeng, GUI Weihua   

  1. School of Information Science and Engineering, Central South University, Changsha 410083, Hunan, China
  • Received:2017-08-24 Revised:2017-09-05 Online:2018-03-05 Published:2018-03-05
  • Supported by:

    supported by the National Natural Science Foundation of China (61590921), the National Natural Science Foundation of China (61703440) and the Fundamental Research Funds for the Central Universities of Central South University (2017zzts488).

基于趋势相似度分析的多重时滞辨识及其在加氢裂化流程中的应用

王雅琳, 夏海兵, 袁小锋, 桂卫华   

  1. 中南大学信息科学与工程学院, 湖南 长沙 410083
  • 通讯作者: 袁小锋
  • 基金资助:

    国家自然科学基金重大项目(61590921);国家自然科学基金青年项目(61703440);中南大学中央高校基本科研业务费专项资金资助项目(2017zzts488)。

Abstract:

Multi-delays exist largely in variables between production units of complex industrial processes and are difficult to detect. A trend-similarity analysis was proposed to identify such multi-delays. The trend-similarity was defined via data of variable derivatives after a polynomial least square fitting on key variables with strong correlation between production units. Multi-delay identification was described by minimizing trend-similarity after sampling delay translation. L2 norm was used to quantify trend-similarity vector and thus multi-delay identification was transformed into L2 norm minimization. The optimal sampling delays on variables were determined by fast optimization with improved adaptive particle-swarm algorithm. The proposed method was applied to identify variable sampling delays in a hydrocracking process. Based on these identified sampling delays, a prediction model for flash point of diesel fuel was established with assistance of local weighted kernel principal component regression. The experimental results show that the multi-delay prediction model improves accuracy by 19.05%, which verifies effectiveness of the proposed multi-delay-identification method.

Key words: trend-similarity analysis, multi-delay identification, adaptive particle-swarm algorithm, hydrogenation, cracking, diesel-fuel flash-point, prediction, model

摘要:

针对复杂工业流程生产单元间变量存在多重时滞且检测困难,提出一种基于趋势相似度分析的多重时滞辨识方法。选取单元间相关性强的关键变量,利用多项式最小二乘拟合后的变量导数数据定义趋势相似度,以经采样时滞平移后的趋势相似度最小,描述多重时滞辨识问题;用L2范数量化趋势相似度向量,将多重时滞辨识问题转化成L2范数最小化问题;并用改进的自适应粒子群算法快速寻优,确定各变量的最优采样时滞。所提方法被应用于加氢裂化流程中,辨识出各变量的实际采样时滞,由此建立了基于局部加权核主元回归的柴油闪点预测模型。实验结果表明:考虑多重时滞的预测模型准确率提高了19.05%,验证了所提时滞辨识方法的有效性。

关键词: 趋势相似度分析, 多重时滞辨识, 自适应粒子群算法, 加氢, 裂化, 柴油闪点, 预测, 模型

CLC Number: