DocumentCode
690989
Title
Study of Driving In-Wheel Motor of Micro-electric Vehicle Based on Improvement of BP Algorithm
Author
Huang Xingshou
Author_Institution
Dept. of Comput. & Inf. Sci., Hechi Univ., Yizhou, China
fYear
2013
fDate
21-23 Sept. 2013
Firstpage
158
Lastpage
160
Abstract
A spatial 3-D nonlinear correction technique is put forward to correct the nonlinearity errors of the PSD in long distance laser collimating measurement. An automatic calibration system is developed to measure the nonlinearity of a 2-D PSD in 3-D space. The nonlinear characteristic of 2-D PSD is checked in a long collimating distance of 78 meters. The experimental results show that the nonlinearity of 2-D PSD is different evidently when the PSD element is at different position from the laser head. The spatial 3-D mapping relationship between the actual displacements of the incident light and the coordinates of 2-D PSD outputs is established by using a multilayer feed forward neural network and the nonlinear errors are corrected with this map. The readout errors of the PSD after correction are shown as random and no more than±0.012 mm in the whole measuring distance.
Keywords
backpropagation; brushless DC motors; electric vehicles; feedforward neural nets; optimisation; 2D PSD; 3D space; BP algorithm; PSD element; automatic calibration system; collimating distance; driving in-wheel motor; incident light; laser head; long distance laser collimating measurement; microelectric vehicle; multilayer feed forward neural network; nonlinear characteristic; nonlinear errors; nonlinearity errors; readout errors; spatial 3D mapping relationship; spatial 3D nonlinear correction technique; Algorithm design and analysis; Biological neural networks; Brushless DC motors; Optimization; Permanent magnet motors; improvement of BP algorithm; in-wheel motor; micro-electric vehicle; optimization design;
fLanguage
English
Publisher
ieee
Conference_Titel
Instrumentation, Measurement, Computer, Communication and Control (IMCCC), 2013 Third International Conference on
Conference_Location
Shenyang
Type
conf
DOI
10.1109/IMCCC.2013.40
Filename
6840429
Link To Document