李荣雨,徐宏宇.平行堆栈式自编码器及其在过程建模中的应用[J].电子测量与仪器学报,2017,31(2):264-271
平行堆栈式自编码器及其在过程建模中的应用
Parallel stacked autoencoder and its application in process modeling
  
DOI:10.13382/j.jemi.2017.02.015
中文关键词:  深度学习  自动编码器  加氢裂化  预测
英文关键词:deep learning  autoencoder  hydrocracking  prediction
基金项目:江苏省高校自然科学基金(12KJB510007)资助项目
作者单位
李荣雨 南京工业大学计算机科学与技术学院南京211816 
徐宏宇 南京工业大学计算机科学与技术学院南京211816 
AuthorInstitution
Li Rongyu School of Computer Science and Technology,Nanjing Tech University, Nanjing 211816, China 
Xu Hongyu School of Computer Science and Technology,Nanjing Tech University, Nanjing 211816, China 
摘要点击次数: 369
全文下载次数: 300
中文摘要:
      在面对流程工业存在的多参数、强非线性和富含复杂机理等问题时浅层算法的学习能力有限,故将深度学习理论引入过程工业预测建模中。而针对单个深层网络对多样性数据的特征挖掘困难,本文提出一种改进的堆栈式自编码器。该方法首先通过聚类算法对输入数据属性进行聚类,按结果将数据分类后输入并行的稀疏自编码器中进行特征的模块式提取,并行输出经整合后输入至叠加的深度网络中,联合这些特征再进行逐层学习得到拟合结果。为减轻过拟合带来的预测误差,将“dropout”方法引入网络训练中。在加氢裂化的预测建模研究中,所提出的算法具有比其他方法更好的预测水平和泛化能力。
英文摘要:
      The problem of multiparameter, nonlinearity and complex mechanism in process industry limits the performance of shallow algorithm, and therefore the deep learning is introduced into the processing industry predictive modeling. However, feature mining is insufficient for diversity data by single deep network, so an improved stacked autoencoder is proposed. Firstly, attribute of input is divided into several classes by clustering algorithm, and then the parallel sparse autoencoder is entered to detect feature locally. The parallel output is integrated into the following deep networks to extract feature layer by layer and get the fitting results. To overcome predictive error due to the overfitting, the “dropout” technique is introduced. In the prediction modeling of hydrocracking, the presented algorithm has better prediction level and generalization ability.
查看全文  查看/发表评论  下载PDF阅读器