An Improved BP Algorithm Based on Global Revision Factor and Its Application to PID Control
To improve BP algorithm in overcoming the local minimum problem and accelerating the convergence speed, a new improved algorithm based on global revision factor of BP neural network is presented in this paper. The basic principle is to improve the formula of weight adjusting used momentum back propagation. A global revision factor is added in the weight value adjusting formula of momentum BP. Faster learning speed is obtained by adaptive adjusting this factor. The new BP algorithm is compared with other improved BP algorithms on many aspects. Simulation and applications for complex nonlinear function approximation, neural PID parameter tuning indicates that it has better training speed and precision than momentum back propagation and adaptive learning rate.
KeywordsHide Layer Hide Layer Node Adaptive Adjust Local Minimum Problem Adaptive Learning Rate
Unable to display preview. Download preview PDF.
- 1.Yan, P., Zhang, C.: Artificial Neural Network and Evolution Simulation Calculation, pp. 124–148. Tsinghua Publication House, Beijing (2000)Google Scholar
- 3.Yildirim, S., Sukkar, M.F., Demirci, R., Aslantas, V.: Design of Adaptive NNs-Robust-PID Controller for A Robot Control. In: Proceedings of IEEE International Symposium on Intelligent Control, pp. 508–513 (1996)Google Scholar
- 4.Li, J., Li, Y., Xun, J., Zhang, J.: Parallel Training Algorithm of BP Neural Algorithms. In: Proc. of the 3rd World Congress on Intelligent Control and Automation, vol. 2, pp. 872–876 (2000)Google Scholar
- 5.Wen, J., Zhao, J., Wei, L., Zhen, H.: The Improvement of BP Neural Network Learning Algorithm. In: Signal Processing Proceedings. WCCC_ICSP 2000. 5th International Conference, pp. 1647–1649 (2000)Google Scholar
- 6.Cheng, C., Tang, Y.: To Improve The Training Time of BP Neural Networks. In: 2001 International Conferences on Info-tech and Info-net, vol. 3, pp. 473–479 (2001)Google Scholar