Neural network adaptive modeling of battery discharge behavior
Dynamic processes are often influenced by external conditions. We expand the neural network approximation capability to behavior modeling within an original hierarchical master-slave relation. Unlike the control theory paradigm, neural weights will replace “state variables” that may be impossible to measure. An application aiming at predicting the end of discharge for rechargeable batteries is fully described. This new battery management tool leads to accurate predictions (mean error is about 3 %) and its implementation into a portable equipment demonstrates that neural networks could be useful even for small size products. The system is further improved by on-line adaptation to actual conditions and individual behavior. This improvement reduces the error prediction to a low 1.5 %.
Unable to display preview. Download preview PDF.
- 1.O. Gérard and J. N. Patillon. Une procédure d'optimisation des pentes dans un réseau de neurones. VALGO, 96(1), 1996.Google Scholar
- 2.O. Gérard, J.N. Patillon, and F. d'Alché Buc. Discharge prediction of rechargeable batteries with neural network. International Journal of Integrated Computer-Aided Engineering, 1997. to appear.Google Scholar
- 3.K. Hornik, M. Stinchcombe, and H. White. Multilayer feedforward networks are universal estimators. Neural Networks, 2:359–366, 1989.Google Scholar
- 4.A. Lapedes and Farber. Programming a massively parallel, computation universal system: Static behavior. In J.S. Denker, editor, Snowbird 1986, pages 283–298. American Institute of Physics, New York, 1986.Google Scholar
- 5.D. Linden, editor. Handbook of batteries. McGraw-Hill, NY, 1995.Google Scholar
- 6.J.-N. Patillon, O. Gérard, F. d'Alché Buc, S. Gourrier, and J.-P. NadaL Smart battery management. 1995 LEP Annual Review, pages 52–54, 1996.Google Scholar
- 7.N. Pican. Intrinsic and parallel performances of the OWE neural network architecture. In ICANN'96, pages 755–760, 1996.Google Scholar