Angular Velocity Prediction of GFSINS Based on BP Neural Network

Abstract:

Aiming at low precision for traditional angular velocity algorithms in GFSINS, a BP neural network algorithm without complex mathematic computation is put forward to calculate angular velocity. Based on a ten-accelerometer configuration scheme, the accelerometer output, sample interval and fixed position are chosen as input, angular velocity got by lognormal algorithm is chosen as output, and 5000 sample data is trained in the several conditions with different hiding layers, neural cells and training steps. Then a three-layer BP network model with 30 hiding layer neural cells is built. Finally, the angular velocity is predicted in real time by the model. Results show that network has strong adaptive capability and real time, and compared with lognormal algorithm, prediction time is almost equal, but prediction precision of angular velocity is nearly improved by three times.

• Periodical: Advanced Materials Research (Volumes 452-453)
• Pages: 846-852
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.452-453.846
• Online since: January 2012
• Authors: Hai Qing Duan, Qi Dan Zhu
• Keywords: Angular Velocity Prediction, BP Neural Network (BPNN), GFSINS, Lognormal Algorithm

References

[1] WANG Xiao-xu, XUE Hong-xiang, XIA Quan-xi, et al. Design and simulation analysis of gyroscope-free inertial measurement unit. Journal of Chinese Inertial Technology, 16: 154-158(2008).

[2] CHEN Mu-qing, XU Jiang-ning, LIU Qiang. Design of algebra-based attitude angular velocity algorithm for GFSINS. Journal of Naval University of Engineering, 20: 19-22(2008).

[3] Kirill. S. Mostov. Design of Accelerometer-based Gyro-Free Navigation Systems. Berkeley: University of California, (2000).

[4] CAO Yong-hong, ZHANG Hui, MA Tie-hua, et al. Attitude forecast of gyroscope-free SINS based on neural network. Journal of Chinese Inertial Technology, 16: 159-161(2008).

[5] CHEN Mu-qing, ZHAO Guo-rong, QU Jun-wu. Design of dual attitude angular-rates combined scheme in GFSINS. Journal of Chinese Inertial Technology, 14: 15-19(2006).

[6] Wilamowski B M，Iplikci S，Kaynak 0，et a1．An algorithm for fast convergence in training neural networks．IEEE Transactions on Neural Networks, 3: 1778-1782(2001).

DOI: 10.1109/ijcnn.2001.938431

[7] Blackwell William J．A neural network technique for atmospheric compensation and temperature/emissivity separation using LWIR/MWIR hyperspectral data．Algorithms and Technologies for Multispectral, 604-615(2004).

DOI: 10.1117/12.543616

[8] CAI Zi-xing, XU Guang-you. Artificial Intelligence and neural network. Tsinghua University Press, Beijing (2004).

[9] Chin Woo Tan, Sungsu Park. Design of accelerometer-based inertial navigation systems. IEEE Transactions on Instrumentation and Measurement. 54: 2520-2530(2005).

DOI: 10.1109/tim.2005.858129

[10] MENG Song, ZHANG Zhi-jie, FAN Jin-biao, et al. An BP ANN forecast model for aerocraft attitude. Journal of Projectiles, Rockets, Missiles and Guidance. 28: 138-142(2008).

[11] Xiaoyuan Li, Bin Qi, Lu Wang. A new improved BP neural network algorithm. International Conference on Intelligent Computing Technology and Automation. China, 19-22(2009).

DOI: 10.1109/icicta.2009.12

[12] Wen Jinwei, Zhao Jiali, Luo Siwei. The improvements of BP neural network learning algorithm. Proceedings of the 2000 International Conference on Signal Processing. 1647-1649(2000).

DOI: 10.1109/icosp.2000.893423

[13] Cooper, G.R. Spinning projectile with an inviscid liquid payload impregnating porous medi. AIAA Journal. 46: 783-787(2008).

DOI: 10.2514/1.30481

[14] Yan Q.W., Zhang W., Wu L.F., et al. Measurement of rotation and angular vibration frequencies of spinning projectile in coning motion by a silicon micromachined gyro. IEEE International Conference on Information and Automation. 1018-1022(2009).

DOI: 10.1109/icinfa.2009.5205067

[15] A.D. Doulamis, N.D. Doulamis, S.D. Kollias. On-line retrainable neural networks: improving the performance of neural networks in image analysis problems. IEEE Transactions on Neural Networks. 11: 137-155(2000).

DOI: 10.1109/72.822517

[16] Zhen Shi, Di Wang, Changqing Li. A kind of gyroscope free strapdown inertial navigation system using six accelerometers. International Workshop on Modern Science and Technology. Japan, 121-12(2002).