A neural network is applied to sensor signal processing in a novel ap proach to the determination of copper in reservoir water. The neural network performed well in determining the correct total of copper concentration in water when provided with only pH and copper(II) ion-selective electrode experimental data. This task followed an initial period of network exposure to a set of experimental data triplets, which were used as examples of the required input/output data mapping.
References
1.
Bos, M., A. Bos and W. E. van der Linden. 1990. "Processing of Signals from an Ion-Selective Electrode Array by a Neural Network", Anal. Chim. Acta, 233:31- 39.
Iupac, compiled by E. Hogfeldt 1982. "Stability Constants of Metal-Ion Complexes, Part A", Inorganic Ligands . Oxford, England. Pergamon Press , p. 44.
4.
Junqueira, L.C., J. Carneiro and J.A. Long. 1986. Basic Histology, Fifth Edition. CT: Appleton-Century-Crofts, pp. 166-200.
5.
Kohonen, T.1989. Self-Organisation and Associative Memory, Third Edition. Berlin- Springer-Verlag, pp. 210-230.
6.
Minsky, M.L. and S. Papert. 1969. Perceptrons. Cambndge, MA: MIT Press.
7.
Orion Research.1982. Handbook of Electrode Technology. Cambndge, MA. Orion Research Incorporated, pp. C-10-C-11.
8.
Rumelhart, D.E., G.E. Hinton and R.J. Williams1986. "Learning Internal Representations by Error Propagation ", in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1, D. E. Rumelhart and J. L. McClelland, eds., Cambridge, MA: MIT Press, pp. 318- 362.
9.
Westall, J.C., J.L. Zachary and F.M.M. Morel. 1976 "MINEQL, a Computer Program for the Calculation of Chemical Equilibrium Composition of Aqueous Systems", Technical Note 18, Ralph M. Parsons Water Quality Laboratory, Cambridge, MA: MIT.
