Estimation of Residual Traveling Distance for Power Wheelchair Using Neural Network
The residual traveling distance of a power wheelchair is difficult to estimate due to the unknown factors of user manipulation behavior and journey characteristics of wheelchair. A virtual residual energy estimation system for power wheelchair based on neural network is proposed to estimate virtual residual energy which could be transformed into residual traveling distance. Two types of estimation systems with three training processes are presented. The estimated results are provided and compared. The results indicate that type-A estimation system with adaptive learning rate is a feasible solution based on economic factor and estimated performance.
KeywordsResidual traveling distance Residual energy Power wheelchair
This chapter is supported by Ministry of Science and Technology of the Republic of China under the grant number MOST 103-2221-E-218-013.
- 1.Haykin, S.: Neural Networks—A Comprehensive Foundation, 2nd edn. Prentice-Hall, Inc., Upped Saddle River, NJ (1998)Google Scholar
- 2.Ham, F.M., Kostanic, I.: Principles of Neurocomputing for Science and Engineering. McGraw-Hill, New York (2000)Google Scholar
- 3.Grewal, S., Grant, D.A.: A novel technique for modeling the state of charge of lithium ion batteries using artificial neural networks. In: INTELEC 2001, pp. 174–179 ( 2001)Google Scholar
- 5.Ting, C.H., Tsai, C.S., Fang, Y.L.: Estimating the residual travel distance of an electrical scooter. In: 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, pp. 1348–1352 (2009)Google Scholar
- 6.Chen, P.C., Koh, Y.F.: Residual traveling distance estimation of an electric wheelchair. In: BMEI 2012, pp. 790–794 (2012)Google Scholar