0
TECHNICAL PAPERS: Porous Media, Particles, and Droplets

Adaptive Neurocontrol of Heat Exchangers

[+] Author and Article Information
Gerardo Dı́az, Mihir Sen, K. T. Yang, Rodney L. McClain

Hydronics Laboratory, Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN 46556

J. Heat Transfer 123(3), 556-562 (Jan 08, 2001) (7 pages) doi:10.1115/1.1370512 History: Received March 20, 2000; Revised January 08, 2001
Copyright © 2001 by ASME
Your Session has timed out. Please sign back in to continue.

References

Sen, M., and Yang, K. T., 2000, “Applications of Artificial Neural Networks and Genetic Algorithms in Thermal Engineering,” CRC Handbook of Thermal Engineering, section 4.24, F. Kreith, ed., pp. 620–661.
Dı́az,  G., Sen,  M., Yang,  K. T., and McClain,  R. L., 1999, “Simulation of Heat Exchanger Performance by Artificial Neural Networks,” HVAC&R Research Journal, 5, No. 3, pp. 195–208.
Kays, W. M., and London, A. L., 1984, Compact Heat Exchangers, 3rd ed., McGraw-Hill, New York.
Sundén, B., and Faghri, M., (eds.), 1998, Computer Simulations in Compact Heat Exchangers, Computational Mechanics Publications, Boston, MA.
Dı́az,  G., Sen,  M., Yang,  K. T., and McClain,  R. L., 2001, “Dynamic Prediction and Control of Heat Exchangers Using Artificial Neural Networks,” International Journal of Heat and Mass Transfer, 44, pp. 1671–1679.
Marwah,  M., Li,  Y., and Mahajan,  R. L., 1996, “Integrated Neural Network Modeling for Electronic Manufacturing,” J. Electron. Manuf., 6, No. 2, pp. 79–91.
Blazina, A., and Bolf, N., 1997, “Neural Network-Based Feedforward Control of Two-Stage Heat Exchange Process,” Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 1 , pp. 25–29.
Ayoubi. M. 1997, “Dynamic Multi-Layer Perceptron Networks: Application to the Nonlinear Identification and Predictive Control of a Heat Exchanger,”Applications of Neural Adaptive Control Technology, World Scientific Series in Robotics and Intelligent Systems, 17 , pp. 205–230.
Nahas,  E. P., Henson,  M. A., and Seborg,  D. E., 1992, “Nonlinear Internal Model Control Strategy for Neural Network Models,” Comput. Chem. Eng., 16, No. 12, pp. 1039–1057.
Chen,  C. T., Hwu,  J., and Chang,  W. D., 1999, “Nonlinear Process Control Based on Using an Adaptive Single Neuron,” J. Chin. Inst. Chem. Eng., 30, No. 2, pp. 141–149.
Haykin, S., 1994, Neural Networks, A Comprehensive Foundation, Macmillan College Publ. Co., New York.
Dı́az, G., Sen, M., Yang, K. T., and McClain, R. L., 2001, “Stabilization of Thermal Neurocontrollers,” International Journal of Heat and Mass Transfer, in press.
Hunt,  K. J., Sbarbaro,  D., Zbikowski,  R., and Gawthrop,  P. J., 1992, “Neural Networks for Control Systems—A Survey,” Automatica, 28, No. 6, pp. 1083–1112.
Landau, I. D., Lozano, R., and M’Saad, M., 1998, Adaptive Control, Springer-Verlag, London.
Zhao, X., 1995, “Performance of a Single-Row Heat Exchanger at Low In-Tube Flow Rates,” M.S. thesis, Department of Aerospace and Mechanical Engineering, University of Notre Dame, IN.

Figures

Grahic Jump Location
IMC with integral control
Grahic Jump Location
Simultaneous optimization criteria; training curve is continuous line, path of dynamical system is shown with +
Grahic Jump Location
x,y, and z versus discrete time index
Grahic Jump Location
Schematic of test facility: (a) wind tunnel; (b) heat exchanger connections
Grahic Jump Location
Response to change in the Touta set point
Grahic Jump Location
Response to water-side disturbance
Grahic Jump Location
Response to air-side disturbance; gradual reduction of the inlet air area
Grahic Jump Location
Response to air-side disturbance; sudden reduction of the inlet air area
Grahic Jump Location
Energy consumption surface E(va,ṁw)
Grahic Jump Location
Application of energy minimization routine. ṁw is reduced to consume less energy and as a consequence, ṁa is also reduced.
Grahic Jump Location
Controllers: (a) non-adaptive, (b) adaptive
Grahic Jump Location
Tracking of a dynamical system by an ANN; (a) adaptation for target error ≥5 percent; (b) adaptation for target error ≥1 percent; — numerical solution; –– ANN prediction
Grahic Jump Location
Result of using a 2-4-1 ANN as an iterated map; i is the time index and yi+1 is the output

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In