Abstract
The industrial dust emission is characterized by scattered emission points with accurate emission parameters difficult to be obtained. The soft-sensing system for industrial dust emissions based on the B/S and C/S mixed mode was studied in terms of the topological network structure, logical structure and a series of key technologies. The network system was constructed with a data flow model, which is based on signal acquisition layer, data acquisition layer, and the area management and central management layers. The user/client cluster is constituted with area client, center client and mobile client. Interanet/Internet was employed to build up a visualization platform for environmental monitoring. Algorithm for the identification of industrial dust concentrations and emissions is proposed on the basis of image processing and Support Vector Machine (SVM). With the help of the characteristic parameters of dust image, vectors to be detected was constructed and normalized to get the real-time concentration and emissions from the SVM. The actual running situation showed that the System not only provided real-time visual monitoring and the accurate concentration of emissions data, but also simple and reliable for end-users and excellent in system scalability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fengbin, M., Liping, S., Na, Z.: Study of Measurement for Concentration and Granularity of Dust Using Extinction. Journal of Transcluction Technology 6, 289–292 (2004)
Yijun, L.: Research on testing for particles concentration and flowing rate. Journal of Transducer Technology 23(8), 27–29 (2004)
Jinhao, S., Dezhong, Z.: Neural Network and the Intelligent Measurement System of the Concentration of Flue-dust Emission. China Instrmentation 2, 10–12 (2002)
Linfeng, L., Lei, Z., Lei, D., et al.: Experimental Study of the Concentration of Soot Based on the Method of Optical Back-Scattering. Acta Photonica Sinica 35(6), 915–917 (2004)
Weidong, B., Jianhua, Y., Zengyi, M., et al.: Method of Flame Identification Based on Support Vector Machine. Power Engingeering 24(4), 548–551
Fenlan, L., Kexin, X.: An algorithm applied in frontal-view face images for automatically localizing eyes. Optics and Precision Engineering 14, 320–326 (2006)
Bin, W., Jigui, Z., Xueyou, Y., et al.: Study on the Key Technologies of 3D Digital Measurement. Chinese Journal of Mechanical Engineering 40, 159–161 (2004)
Qingkun, L., Peiwen, Q., Huawei, G., et al.: Support Vector Machine and Chaos-genetic Optimization Based Ultrasonic Flaw Identification. China Mechanical Engineering 17(1), 9–12 (2006)
Zhengping, H., Ye, Z.: Accurate image segmentation based on support vector region growing and active contour model. Optical Technique 32(3), 410–415 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, X., Yang, B., Xie, Zj. (2009). SVM-Based Soft-Monitoring Network System for Industrial Dust Emissions. In: Cao, B., Li, TF., Zhang, CY. (eds) Fuzzy Information and Engineering Volume 2. Advances in Intelligent and Soft Computing, vol 62. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03664-4_33
Download citation
DOI: https://doi.org/10.1007/978-3-642-03664-4_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03663-7
Online ISBN: 978-3-642-03664-4
eBook Packages: EngineeringEngineering (R0)