Abstract
In granule processing industries, acquisition of particle size and shape parameters is a common procedure, and volumetric measurement is of great importance in dealing with particle sizing and gradation. To eradicate the major drawbacks with manual gauge, this paper proposes an optical approach using Back Propagation (BP) neural network to estimate the particle volume based on the two-Dimensional (2D) image information. To achieve the better network efficiency and structure simplicity, Principal Component Analysis (PCA) is adopted to reduce the dimensions of network inputs. To overcome the shortcomings of generic BP network for being slow to converge and vulnerable to being trapped in local minimum, Levenberg-Marquardt (LM) algorithm is applied to achieve a higher speed and a lower error rate. The real particle data is utilized in training and testing the presented network. The experimental result suggests that the proposed neural network is capable of estimating aggregate volume with satisfactory precision and superior to the generic BP network in terms of performance capacity.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Wang Weixing. Computer vision system of aggregates. Nonferrous Metals (Mining), 54(2002)6, 16–19, 33 (in Chinese). 王卫星. 岩石颗粒计算机视觉系统. 有色金属(矿山部 分), 54(2002)6, 16–19 转33.
Chetana Rao and Erol Tutumluer. A new image analysis approach for determination of volume of aggregates. Transportation Research Board, 79th Annual Meeting, Washington, D.C., January 9–13, 2000, 73–80.
VDG-40 Measurement of particle size distribution of granular mixtures. Commercial Catalogue for Laboratory Central Des Ponts and Chaussees (LCPC); also in VDG 40 Technical Bulletin, Ministere de I’Equipment, July 1995.
N. H. Maerz and W. Zhou. Flat and elongated: advances using digital image analysis. Proceedings of the 7th Annual ICAR Symposium, International Center for Aggregates Research, University of Texas at Austin, USA, April 19–21, 1999, B1-4-1 to B1-4-12.
Yan Pingfan and Zhang Changshui. Artificial neural networks and simulated evolutionary computation. Beijing, Tsinghua University Press, 2001, Ch. 14 (in Chinese). 阎平凡, 张长水著. 人工神经网络与模拟进化计算. 北 京, 清华大学出版社, 2001, 第14 章.
Martin T. Hagan, Howard B. Demuth, and Mark Beale. Neural network design. Beijing, China Machine Press, 2002, 12–19 (in Chinese). Martin T. Hagan, Howard B. Demuth, Mark Beale. 神经网络设计. 北京, 机械工业出版社, 2002, 12–19.
Gao Xuepeng and Cong Shuang. Comparative study on fast learning algorithms of BP networks. Control and decision, 16(2001)2, 167–171 (in Chinese). 高雪鹏, 丛 爽. BP 网络改进算法的性能对比研究. 控 制与决策, 16(2001)2, 167–171.
Ken Cheng. Optical gradation of crushed limestones aggregates. [Ph.D. Dissertation]. West Virginia University, USA, 2001, Ch.6.
Chen Ken, Larry E. Banta, and Jiang Gangyi. 2-D Image-based volumetric modeling for particle of random shape. Journal of Electronics (China), 23 (2006)6, 877–881.
Chen Ken and Larry E. Banta. Image profile area calculation based on circular sample measurement calibration. Journal of Electronics (China), 22(2005)5, 528–533.
Chen Ken, Zhao Pan, and Yang Rener. A linear approach to metric circumference computation for digitized convex shapes. Journal of Electronics (China), 25(2008)4, 572–575.
Wu Mengda, Li Bin, and Wang Wenhao. Advanced engineering mathematics. Beijing, Science Press, 2004, Ch. 5 (in Chinese). 吴孟达, 李兵, 汪文浩著. 高等工程数学. 北京, 科学 出版社, 2004, 第5 章.
Fan Jixiang, Zhang Hong, Li Hui and Wang Bintuan. Applicaton of BP neural network and multi-variable linear regression in rate prediction. Computer Engineering and Applications, 43(2007)23, 203–204 (in Chinese). 樊纪香, 张宏, 李辉, 王兵团. BP 网络和多元线性回归 在产量预测中的应用.计算机工程与应用, 43(2007)23, 203–204.
Liu Yanfang and Jiao Limin. The application of BP networks to land suitability evaluation. Geo-spatial Information Science (Quarterly), 5(2002)1, 55–61.
Ji Chengjun and Liu Hongchao. The applying of BP network in forecasting the demand and its growth rate for coal. Journal of Coal Science & Engineering (China), 7(2001)1, 102–107.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by Ningbo Natural Science Foundation (No. 2006A610016), and Foundation of Ministry of Education for Returned Overseas Students & Scholars (SRF for ROCS, SEM. No. 2006699).
Communication author: Zhao Pan, born in 1983, male, Master.
About this article
Cite this article
Zhao, P., Chen, K., Wang, Y. et al. Estimation of rock-aggregate volume based on PCA and LM-optimized neural network. J. Electron.(China) 26, 825–830 (2009). https://doi.org/10.1007/s11767-008-0114-8
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11767-008-0114-8