Prediction of Calibration Value for Inertial Instrument Based on Genetic Neural Network

Abstract:

Based on the former calibration data of error coefficient of inertial navigation instrumentation and environment parameters, a three-layer BP neural network is founded to predict the calibration value in current circumstances. To confirm the structure of neural network, genetic algorithm is used to seek the optimal solution, and hence the concept of genetic neural network is introduced. Also since the calibration data has small-sample characteristics; Bayes regularization method is adopted to improve the network generalization ability and predicted performance. In the end the simulated results show that it is reasonable and effective to accomplish the prediction in genetic neural network.

• Periodical: Applied Mechanics and Materials (Volumes 241-244)
• Pages: 433-438
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.241-244.433
• Online since: December 2012
• Authors: Zheng Dong Hu*, Tao Yang, Yue Ping Wang, Xue Mei Tang
• Keywords: Bayes Regularization, BP Neural Network (BPNN), Calibration, Error Coefficient of Inertial Instrumentation, Generalization, Genetic Algorithm (GA), Genetic Neural Network, Predicted Performance

References

[1] X. Z. Guo, in: Theory of Gyroscopes in Inertial Navigation System. Beijing: National Defence Industry Press, (1996).

[2] The Fei Sike technology R & D center. In: Neural Network Theory and its MATLAB realization. Beijing: Electronic Industry Press, (2005).

[3] G. L. Chen, WANG X F. Method of Genetic Algorithm and its Application. Beijing: People's Posts and Telecommunications Press, (1996).

[4] L. M. Zhang, in: Artificial neural network model and its application. Shanghai: Fudan University Press, (1993).