Modeling FOG Drift Using Back-Propagation Neural Network Optimized by Artificial Fish Swarm Algorithm

Based on the temperature drift characteristic of fiber optic gyroscope (FOG), a novel modeling and compensation method which integrated the artificial fish swarm algorithm (AFSA) and back-propagation (BP) neural network is proposed to improve the output accuracy of FOG and the precision of inertial navigation system. In this paper, AFSA is used to optimize the weights and threshold of BP neural network which determine precision of the model directly. In order to verify the effectiveness of the proposed algorithm, the predicted results of BP optimized by genetic algorithm (GA) and AFSA are compared and a quantitative evaluation of compensation results is analyzed by Allan variance. The comparison result illustrated the main error sources and the sinusoidal noises in the FOG output signal are reduced by about 50%. Therefore, the proposed modeling method can be used to improve the FOG precision.

[1]  Deng Zheng-long.  Overview on modeling and compensation of FOG temperature drift , 2009 .

[2]  Xuyou Li,et al.  Temperature errors of IFOG and its compensation in engineering application , 2009, 2009 9th International Conference on Electronic Measurement & Instruments.

[3]  Stéphane Solve,et al.  Allan Variance Analysis of Josephson Voltage Standard Comparison for Data Taken at Unequal Time Intervals , 2011, IEEE Transactions on Instrumentation and Measurement.

[4]  Weifeng Tian,et al.  Temperature drift modelling of fibre optic gyroscopes based on a grey radial basis function neural network , 2004 .

[5]  Juntao Fei,et al.  Adaptive Sliding Mode Control of MEMS Gyroscope Based on Neural Network Approximation , 2014, J. Appl. Math..

[6]  Yanhua Zhang,et al.  A novel intelligent strategy for improving measurement precision of FOG , 2000, IEEE Trans. Instrum. Meas..

[7]  Hervé Lefevre,et al.  The Fiber-Optic Gyroscope , 1992 .

[8]  Yanbin Gao,et al.  Optimal artificial fish swarm algorithm for the field calibration on marine navigation , 2014 .

[9]  Li Xiao,et al.  An Optimizing Method Based on Autonomous Animats: Fish-swarm Algorithm , 2002 .

[10]  Tao Ma,et al.  Research on FOG Random Errors Modeling Based on AFSA , 2012, 2012 International Conference on Industrial Control and Electronics Engineering.

[11]  Liu Xi-yu.  Back-propagation neural network training based on particle swarm optimization with best influential partical , 2007 .

[12]  D. Shupe,et al.  Thermally induced nonreciprocity in the fiber-optic interferometer. , 1980, Applied optics.

[13]  Chong Shen,et al.  Study on temperature error processing technique for fiber optic gyroscope , 2013 .

[14]  Adel Nadjaran Toosi,et al.  Color Quantization Using Modified Artificial Fish Swarm Algorithm , 2011, Australasian Conference on Artificial Intelligence.

[15]  Weifeng Tian,et al.  Temperature drift modelling and compensation for a dynamically tuned gyroscope by combining WT and SVM method , 2007 .

[16]  Jin Jing.  Research on Modeling and Compensation Technology for Temperature Errors of FOG , 2006 .