Neural Network Based Decision Support System
The research investigates the applicability of neural networks for the implementation of decision support (DS) systems
in operational control of industrial processes.
The prototype DS system was validated in the context of monitoring and control of water distribution networks.
The computational challenge of this application stems from the non-linearity and large-scale of models as well as the
uncertainty associated with the system parameters and the non-metered water consumptions. The insights derived from this research
are applicable to other public utilities or road traffic systems.
Decision support has two distinct but interrelated aspects: optimisation based
on mathematical modelling of physical plants and processes, and the fuzzy
information processing by human operators. This research
builds on our previous research contributions concerning computation using analogue neural networks and
fuzzy sets and systems. A diagrammatic representation of the various components of the project
and their interrelationship is presented below.
The operation of a water distribution system can be described by an overdetermined set
of nonlinear equations expressing the physical laws of hydro-dynamics.
Since, in general, there is no unique solution to this set of equations
the optimization problem is formulated in order to find the state estimates which are
optimal according to some suitable optimisation criterion (e.g. minimum sum of squares
of discrepancies between the measured and the estimated pressures and flows in the water
The solution to this nonlinear optimization problem utilised the
Newton-Raphson iterative method. This method has been widely and successfully
used in the context of water distribution systems. The state estimates are found by
iteratively solving a system of linear equations and adjusting the state vector values.
The novel contribution of this research was the mapping of the state
estimation method onto appropriate analog neural network.
Several neural networks and the associated optimisation criteria (Least Mean
Squares(LMS), Least Absolute Value (LAV) and MinMax (Chebyshev) have been
implemented and assessed for their efficiency and robustness. Our solution
based on the recurrent neural network
[Gabrys, Bargiela, 1995],
[Gabrys, Bargiela, 1996],
[Cichocki, Bargiela, 1997]
has proven itself to offer superior computational efficiency which allows
for what-if study of system control scenarios in real time.
The network is represented in the diagram below.
- Gabrys B., Bargiela A., Neural Networks Based Decision Support in Presence of Uncertainties, ASCE Journal of Water Reasources Planning and Management , Vol. 125, No. 5, 1999, pp. 272-280, doi:10.1061/(ASCE)0733-9496(1999)125:5(272), PDF
- Gabrys B., Bargiela A., Analysis of Uncertainties in Water Systems Using Neural Networks, Measurement and Control , Vol. 32, No. 5, June 1999, pp.145-147
- Hartley J., Bargiela A., Parallel State Estimation with Confidence Limit Analysis, Parallel Algorithms and Applications , Vol. 11, No.1-2, 1997, pp. 155-167, PDF
- Cichocki A., Bargiela A., Neural Networks for Solving Linear Inequality Systems, Parallel Computing , Vol.22, No.11, Jan. 1997, pp.1455-1475, PDF
- Bargiela A., Hartley J.K., Orthogonal linear regression algorithm based on augmented matrix formulation, Computers and Operations Research , Vol. 20, No. 8, 1993, pp. 829-836, PDF
- Bargiela A., Hainsworth G., Pressure and flow uncertainty in water systems, ASCE Journal of Water Resources Planning and Management , Vol. 115, 2, March 1989, pp. 212-229, doi: 10.1061/(ASCE)0733-9496(1989)115:2(212), PDF
- Bargiela A., An algorithm for observability determination in water-system state estimation, IEE Proceedings Part D , 132, Nov. 1985, pp. 245-249,
- Sterling M., Bargiela A., Leakage reduction by optimised control of valves in water networks, Transactions of Inst. Measurement and Control. , Vol. 6, Oct. 1984, pp. 293-298, PDF
- Sterling M., Bargiela A., Minimum norm state estimation for computer control of water distribution systems, IEE Proceedings Part D , 131, March 1984, pp. 57-63, PDF
- Gabrys B., Bargiela A., Simulation of Water Distribution Networks, Proc. European Simulation Symposium ESS-98, Oct. 1998, ISBN 1-56555-147-8, pp.273-277
- Hartley J., Bargiela A., Probabilistic Simulation of Large-scale Water Distribution Systems, Proceedings of European Simulation Symposium ESS-96, Genoa, October 1996, ISBN 1-565555-099-4 (Vol.2), pp.403-407
- Gabrys B., Bargiela A., Integrated Neural Based System for State Estimation and Confidence Limit Analysis in Water Networks, Proceedings of European Simulation Symposium ESS-96, Genoa, 1996, ISBN 1-565555-099-4, pp.398-402
- Bargiela A., High performance neural optimisation for real-time pressure control, Proc. of High Performance Computing Conference, HPC Asia 1995, Taipei, Sept. 1995, Chap. AL34, pp. 1-8
- Gabrys B., Bargiela A., Neural simulation of water systems for efficient state estimation, Proc. of Modelling and Simulation Conference ESM-95, Prague, June 1995, ISBN 1-56555-080-3, pp. 775-779
- Hartley J., Bargiela A., Cant R., Parallel simulation of large scale water distribution systems, Proceedings of Modelling and Simulation Conference ESM-95, Prague, June 1995, ISBN 1-56555-080-3, pp. 723-727
- Bargiela A., Managing uncertainty in operational control of water distribution systems, Int. Conf. On Computing and Control in Water Industry, Leicester, 1993
- Hartley J.K., Bargiela A., Utilisation of smoothing formulae for describing hydraulic relationships in water networks, Int. Conf. On Computing and Control in Water Industry, Leicester, 1993
- Bargiela A., A graphical interactive software tool for confidence limit analysis, Proc. of AWWA Conference on Computers and Automation in the Water Industry, Denver, CO, 2-4 April 1989, pp. 193-204
- Hainsworth G., Bargiela A., Optimal telemetry system for water networks, Proc. of Int. Symposium on Optimal Modelling of Water Distribution Systems, Lexington, K.Y., May 1988, pp. 181-200.
- Bargiela A., Hainsworth G., Telemetry design with TCLAS software in Computer Applications in Water Supply, Proc. Int. Conf. on Computer Applications for Water Supply and Distribution, Leicester, 1987
- Bargiela A., Hainsworth G., Confidence limit analysis in water systems, , Proc. Int. Conf. on Computer Applications for Water Supply and Distribution, Leicester, 1987
- Bargiela A., Sterling M., Detection of water leakage and measurement errors in distribution networks, Proc. of Computer Applications for Water Supply and Distribution Conference, Leicester, Sept. 1983.
Last update: 19/04/1996