Application of Adaptive Neuro-Fuzzy Inference Systems (ANFIS) in Modeling the Effects of Selected Input Variables on the Period of Oscillation in an Unsteady Flow Through Surge Chamber
[1]
Ilaboya, I. R., University of Benin; Department of Civil Engineering, Faculty of Engineering, PMB 1154, Benin City, Nigeria.
[2]
Oti, E. O., University of Benin; Department of Civil Engineering, Faculty of Engineering, PMB 1154, Benin City, Nigeria.
[3]
Atikpo E., Department of Civil Engineering, Igbinedion University, Okada, Edo State, Nigeria.
[4]
Enamuotor, B. O., Department of Civil Engineering, Delta State University, Abraka, Nigeria.
[5]
Umukoro, L. O., Department of Civil Engineering, Igbinedion University, Okada, Edo State, Nigeria.
In this research paper, an attempt was made to model the significant effects and the interactions of some selected input variables on the period of oscillation in an unsteady flow through surge chambers using adaptive neuro-fuzzy techniques. The choice of adaptive neuro-fuzzy technique is based on the fact that, it is a hybrid modeling algorithm that combines both neural network and fuzzy logic to obtain better result. The inlet valve to the reservoir was opened and adjusted to give a steady level of discharge from an overflow weir for a predetermined period of time. The flow rate of the water was thereafter computed using the volume against time relationship. A surge was then initiated following a sudden closure of the valve and the dynamics of flow behaviour was studied based on the period of oscillation. Statistical studies on the effects of selected input variables such as surge tower diameter, time of flow, velocity of flow, and rate of flow on the operational dynamics of unsteady flow in surge chambers was done using design of experiment (DOE) employing the 2-level factorial design with 3 central points’ and one replication. Results obtained were then modeled using Adaptive Neuro-Fuzzy Inference Technique (ANFIS) incorporated into MATLAB in fuzzy logic toolbox to determine the input variable (s) that possess the highest significant effects on the response variable (period of oscillation) and also to develop a Fuzzy Inference Systems (FIS) structure which can be employed to study the adequacy of results from similar experiment. Results obtained from the modeling shows that surge tower diameter with a root mean square error of 0.7360 appears to be the single variable with the highest significant effects on the amplitude of displacement. More also, for the combine variable effects, surge (tower diameter and velocity of flow) having a combine root mean square error of 0.4410 were seen to possess the highest significant effects on the amplitude of displacement.
Period of Oscillation, Design of Experiment, 2-Level Factorial Design, Unsteady Flow, and Adaptive Neuro-Fuzzy Technique
[1]
Axworthy, D. H., Ghidaoui, M. S., and McInnis, D. A., (2000), Extended Thermodynamics Derivation of Energy Dissipation in Unsteady Pipe Flow, J. Hydraul. Eng. 126 (4), pp. 276–287.
[2]
Bergant, A. and Simpson, A. R., (1994), Estimating Unsteady Friction in Transient Cavitating Pipe Flow, Proc. 2nd Int. Conf. on Water Pipeline Systems, Edinburgh, UK, May 24–26, BHRA Group Conf. Series Publ. No. 110, pp. 3–15.
[3]
Brunone, B., Karney, B. W., Mecarelli, M., and Ferrante, M., (2000), Velocity Profiles and Unsteady Pipe Friction in Transient Flow, J. Water Resources Planning and Management. 126 (4), pp. 236–244.
[4]
Carstens, M. R., and Roller, J. E., (1959), Boundary-Shear Stress in Unsteady Turbulent Pipe Flow,’’ J. Hydraul. Div., Am. Soc. Civ. Eng. 85 (HY2), pp. 67–81.
[5]
Ghidaoui, M. S., (2001), Fundamental Theory of Water-hammer, Special Issue of the Urban Water J. ~Special Issue on Transients, Guest Editor: B. W. Karney, 1(2), pp. 71–83.
[6]
Ghidaoui, M. S., and Kolyshkin, A. A., (2001), Stability Analysis of Velocity Profiles in Water-Hammer Flows, J. Hydraul. Eng. 127 (6), pp. 499–512.
[7]
Ghidaoui, M. S., Mansour, S. G. S., and Zhao, M., 2002, ‘‘Applicability of Quasi Steady and Axisymmetric Turbulence Models in Water Hammer,’’ J. Hydraul. Eng. 128 (10), pp. 917–924.
[8]
Jang, J. R., (1993), ANFIS: Adaptive-network-based fuzzy inference systems," IEEE Transactions on Systems, Man and Cybernetic Vol. 23, No. 3, pp; 2889-2892
[9]
Jang, J. S. R. and Sun, C. T., (1997), Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice Hall.
[10]
Mohdeb, N., and Mekideche, M.R., (2010), Determination of the Relative Magnetic Permeability by Using an Adaptive Neuro-Fuzzy Inference System and 2d-Fem, Progress in Electromagnetics Research B, Vol. 22, pp; 237-255,
[11]
Pezzinga, G., (1999), Quasi-2D Model for Unsteady Flow in Pipe Networks, J. Hydraul. Eng. 125 (7), pp. 676–685.
[12]
Silva-Araya, W. F., and Chaudhry, M. H., (1997), Computation of Energy Dissipation in Transient Flow, J. Hydraul. Eng. 123 (2), pp.108–115.
[13]
Vardy, A. E., and Hwang, K. L., (1991), A Characteristic Model of Transient Friction in Pipes, J. Hydraul. Res. 29 (5), pp. 669–685.
[14]
Vardy, A. E. and Brown, J, M., (1996), On Turbulent, Unsteady, Smooth-Pipe Friction, Pressure Surges and Fluid Transient, BHR Group, London, pp. 289–311.
[15]
Walker, J. S., (1975), Perturbation Solutions for Steady One- Dimensional Water-hammer Waves, ASME J. Fluids Eng. 6, pp. 260–262.
[16]
Watters, G. Z., (1984), Analysis and Control of Unsteady Flow in Pipelines, Butterworth, Stoneham, Ma.
[17]
Wylie, E. B. and Streeter, V. L (1984), Fluid Transients, FEB Press, Ann Arbor.
[18]
Zanchettin, C., Leandro, L.M., Teresa, B.L., (2010), Design of Experiments in Neuro-Fuzzy Systems, International Journal of Computational Intelligence and Applications, Vol. 9, No. 2, pp; 137–152.
