OPEN ACCESS
In this paper, artificial neural networks (ANNs) were used to assess the performance of flow meters used in industrial water supply. These flow meters are susceptible to drift, a condition causing them to give erroneous readings that are inconsistent with the actual flow. A simulation of industrial water flow to the industrial consumers was made. This simulation contained both healthy and drifting flow meter readings. ANN was built and trained on the simulated data. At the time of testing, the ANN developed was correct 89.52% of the time in determining the status of the flow recorded by a flow meter.
artificial neural network, flow meter drift, industrial water supply, statistical process control
[1] Ben Salamah, M., et al., The detection of fl ow meter drift by using statistical process control.International Journal of Sustainable Development and Planning, To be published.
[2] Cheng, C.S., A multi-layer neural network model for detecting changes in the process mean. Computers & Industrial Engineering, 28(1), pp. 51–61, 1995. doi:http://dx.doi.org/10.1016/0360-8352(94)00024-H
[3] Cheng, C.S., A neural network approach for the analysis of control chart patterns. International Journal of Production Research, 35(3), pp. 667–697, 1997. doi:http://dx.doi.org/10.1080/002075497195650
[4] Friedman, M. & Kandel A., Introduction to pattern recognition: statistical, structural, neural and fuzzy logic approaches. 1 edn. Series in Machine Perception and Artifi cial Intelligence, eds H. Bunke & P.S.P. Wang., World Scientifi c: London, 32, p. 329, 1999.
[5] Bishop, C.M., Neural Networks for Pattern Recognition, Oxford: Oxford University Press, 482, 2005
[6] Anagun, A.S., A neural network applied to pattern recognition in statistical process control. Computers & Industrial Engineering, 35(1–2), pp. 185–188, 1998. doi:http://dx.doi.org/10.1016/S0360-8352(98)00057-6
[7] Hassan, A., et al., Improved SPC chart pattern recognition using statistical features. International Journal of Production Research, 41(7), pp. 1587–1603, 2003.
[8] Pacella, M., Semeraro, Q. & Anglani, A., Manufacturing quality control by means of a Fuzzy ART network trained on natural process data. Engineering Applications of Artifi cial Intelligence, 17(1), pp. 83–96, 2004. doi:http://dx.doi.org/10.1016/j.engappai.2003.11.005
[9] Koutras, M.V., Bersimis, S. & Maravelakis, P.E., Statistical process control using Shewhart control charts with supplementary runs rule. Methodology and Computing in Applied Probability, 9(2), pp. 207–224, 2007. doi:http://dx.doi.org/10.1007/s11009-007-9016-8
[10] Yasui, S., Ojima, Y. & Suzuki, T., Generalization of the Run Rules for the Shewhart Control Charts in Frontiers in Statistical Quality Control 8, eds H.J. Lenz & P.T. Wilrich, Physica-Verlag: New York. pp. 207–219, 2006.
[11] Bowerman, B.L., O’Connell, R.T. & Koehler, A.B., Forecasting, Time Series and Regression An Applied Approach. Thomson Broks/Cole. p. 686, 2005.
[12] Norton, M., A Quick Course In Statistical Process Control. Technology Skills., Upper Saddle River, New Jersey: Pearson Prentice Hall. p. 56, 2005.