AGGREGATE VOLUMETRIC ESTIMATION BASED ON PCA AND MOMENTUM-ENHANCED BP NEURAL NETWORK  

作　　者：Chen Ken Zhao Pan Batur Celal Zhang Yun 

机构地区：[1]College of Information Science and Engineering, Ningbo University, Ningbo 315211, China [2]College of Engineering, The University of Akron, Ohio 44325, USA

出　　处：《Journal of Electronics(China)》2009年第5期637-643,共7页电子科学学刊（英文版）

基　　金：Funded by Ningbo Natural Science Foundation (No. 2006A610016);Foundation of National Education Ministry for Returned Overseas Chinese Students & Scholars (SRF for ROCS, SEM. No.2006699)

摘　　要：This paper proposes a Back Propagation (BP) neural network with momentum enhancement aiming to achieving the smooth convergence for aggregate volumetric estimation purpose. Network inputs are first selected by optically measuring the eight geometry-related parameters from the given particle image. To simplify the network structure, principal component analysis technique is applied to reduce the input dimension. The specific network structure is finalized based on both empirical expertise and analysis on selecting the appropriate number of neurons in hidden layer. The network is trained using the finite number of randomly-picked particles. The training and test results suggest that, compared to the generic BP network, the training duration of the proposed neural network is greatly attenuated, the complexity of the network structure is largely reduced, and the estimation precision is within 2%, being sufficiently up to technical satisfaction.This paper proposes a Back Propagation （BP） neural network with momentum enhancement aiming to achieving the smooth convergence for aggregate volumetric estimation purpose. Network inputs are first selected by optically measuring the eight geometry-related parameters from the given particle image. To simplify the network structure, principal component analysis technique is applied to reduce the input dimension. The specific network structure is finalized based on both empirical expertise and analysis on selecting the appropriate number of neurons in hidden layer. The network is trained using the finite number of randomly-picked particles. The training and test results suggest that, compared to the generic BP network, the training duration of the proposed neural network is greatly attenuated, the complexity of the network structure is largely reduced, and the estimation precision is within 2%, being sufficiently up to technical satisfaction.

关 键 词：Aggregate volume Back Propagation （BP） neural network MOMENTUM Volume estimate Principal Component Analysis （PCA） 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TN911[自动化与计算机技术—控制科学与工程]