Classification of Defects in Sewer Pipes Using Neural Networks
Publication: Journal of Infrastructure Systems
Volume 6, Issue 3
Abstract
Deterioration of underground infrastructure facilities such as sewer pipes poses a serious problem to most developed urban centers today. As distribution piping networks age, they deteriorate and may ultimately fail to fulfill their intended functions. To ensure continuity of services and protect the investment made in these networks, municipalities check their conditions regularly. The current practice that is being followed in those checkup programs is usually time consuming, tedious, and expensive. This paper presents an automated system designed for detecting defects in underground sewer pipes and focuses primarily on the application of neural networks in the classification of those defects. A three-layer (i.e., one hidden layer) neural network has been developed and trained using a back-propagation algorithm to classify four categories of defects, namely cracks, joint displacements, reduction of cross-sectional area, and spalling. A total of 1,096 patterns were used in developing the neural network. An example application is described to demonstrate the use and capabilities of the developed system.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Anderson, J. (1995). An introduction to neural networks, MIT Press, Cambridge, U.K.
2.
Fausett, L. (1994). Fundamentals of neural networks, architecture, algorithms and applications, Prentice-Hall, Englewood Cliffs, N.J.
3.
Flood, I., and Kartam, N. (1994a). “Neural networks in civil engineering. I: Principles and understanding.”J. Comp. in Civ. Engrg., ASCE, 8(2), 131–148.
4.
Flood, I., and Kartam, N. (1994b). “Neural networks in civil engineering. II: Systems and applications.”J. Comp. in Civ. Engrg., ASCE 8(2), 149–162.
5.
Hegazy, T., Fazio, P., and Moselhi, O. (1994). “Developing practical neural network applications using back-propagation.” Microcomp. Civ. Engrg., Cambridge, U.K. 9(2), 145–159.
6.
Kaseco, M., and Ritchie, S. (1994). “Comparison of traditional and neural classification for pavement-crack detection.”J. Transp. Engrg., ASCE, 120(4), 552–569.
7.
Looney, C. (1997). Pattern recognition using neural networks, Oxford University Press, New York.
8.
Mashford, J. (1995). “A neural network image classification system for automatic inspection.” Proc., IEEE Int. Neural Networks Conf., Institute of Electrical and Electronics Engineers, New York, 2, 713–717.
9.
McKim, R. (1997). “Selection methods for trenchless technologies.”J. Infrastruct. Sys., ASCE, 3(3), 119–125.
10.
Morici, P. (1997). “Small cameras: diagnosing sewer lateral quickly and easily.” Trenchless Technol., 6(10), 40–45.
11.
Moselhi, O. (1998). “Neural networks and their applications in civil engineering.” Proc., 1st Int. Conf. on New Information Technol. for Decision Making in Civ. Engrg., Ecole de Technologie Superieure, Montreal, 1, 17–27.
12.
Moselhi, O., Hegazy, T., and Fazio, P. (1991). “Neural networks as tools in construction.”J. Constr. Engrg. and Mgmt., ASCE, 117(4), 606–625.
13.
Moselhi, O., Hegazy, T., and Fazio, P. (1992). “Potential applications of neural networks in construction.” Can. J. Civ. Engrg., Ottawa, 19(3), 521–529.
14.
Moselhi, O., and Shehab-Eldden, T. (1999). “Automated detection of defects in underground sewer and water pipes.” Automation in Constr., 8(5), 581–588.
15.
Nekovei, R., and Sun, Y. (1995). “Back-propagation networks configuration for blood vessels detection in angiograms.” IEEE Trans. on Neural Networks, 6(1), 64–72.
16.
NeuroShell-2 reference manual. (1996). Ward Systems Group, Inc., Frederick, Md.
17.
Ritchie, S. (1990). “Digital image concepts and application in pavement management.”J. Transp. Engrg., ASCE, 116(3), 287–298.
18.
Ritchie, S., Kaseko, M., and Bavarian, B. (1991). “Development of an intelligent system for automated pavement evaluation.” Transp. Res. Rec. 1311, Transportation Research Board, Washington, D.C., 112–119.
19.
Simpson, P. (1996). Neural networks theory, technology, and applications, Institute of Electrical and Electronics Engineers, New York.
20.
Tamura, S., and Tateishi, M. (1997). “Capabilities of four-layered feedforward neural networks: four layers versus three.” IEEE Trans. on Neural Networks, 8(2), 251–255.
21.
Zhao, J., Ivan, J., and DeWolf, J. (1998). “Structural damage detection using artificial neural networks.”J. Infrastruct. Sys., ASCE, 4(3), 93–101.
Information & Authors
Information
Published In
History
Received: Apr 22, 1999
Published online: Sep 1, 2000
Published in print: Sep 2000
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.