Research on Prediction Model for Icing Thickness of Transmission Lines Based on BP Neural Network Optimized with Improved Fruit Fly Algorithm

Research on Prediction Model for Icing Thickness of Transmission Lines Based on BP Neural Network Optimized with Improved Fruit Fly Algorithm

J. Zhou B.G. Tang X.W. Ren

School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China

Information and Technology, State Grid Shanxi Electric Power Company, Taiyuan, 030001, China

Huada Tianyuan (Beijing) Electric Power Technology Co., Ltd., Beijing 102206, China

Corresponding Author Email:,,
15 March 2017
15 April 2017
31 March 2017
| Citation



Icing of transmission line has seriously impacted on the safe operation of power grid. Therefore, after analyzing meteorological factors which influence icing thickness, we proposed to construct an icing thickness prediction model based on a 3-layer BP neural network in this article. In order to solve problems that BP neural network converges slowly and is prone to local minimum values, the prediction speed and accuracy have been increased by using improved fruit fly algorithm to optimize BP neural network. Taking icing historical data on 500kV transmission line of Shenxin Line I in China as an example, the rationality and accuracy of this model have been proved, and the analyzing results could be provided to instruct the operation and maintenance of transmission lines.


Transmission lines, icing, BP neural network, fruit fly algorithm

1. Introduction
2. Prediction Model Based on A Bp Neural Network Optimized with An Improved Fruit Fly Algorithm
3. Study on Cases
4. Discussion
5. Conclusion

[1] S. F. Yin, Research on data integration method applied to predict ice thickness of transmission lines, 2013, Kunming University of Science and Technology, Kunming, China.

[2] L. Peng, L. Qimao, C. Min, Time series prediction for icing process of overhead power transmission line based on BP neural networks, 2011, Control Conference (CCC), 2011 30th Chinese, IEEE, pp.5315-5318

[3] S. E. Yu, Li M. Y. Li, H. K. H. Leon, Model construction of option pricing based on fuzzy theory, 2011, Journal of Marine Science and Technology, vol.19, no.5, pp.460-469.

[4] J. L. Deng, Introduction to grey system theory, 1989, The Journal of grey system, vol.1, no.1, pp.1-24.

[5] D. E. Ilea, P. F. Whelan, Image segmentation based on the integration of colour-texture descriptors-A review, 2011, Pattern Recognition, vol. 44, no.10, pp.2479-2501.

[6] W. C. Pan, Fruit fly optimization algorithm, 2011, Tsang Hai Publishing, Taipei, China, pp.10-12.

[7] H. Li, S. Guo, C. Li, A hybrid annual power load forecasting model based on generalized regression neural network with fly optimization algorithm, 2013, Knowledge-Based Systems, no.37, pp.378-387.

[8] X. Zheng, L. Wang, S. Wang, A novel fly optimization algorithm for the semiconductor final testing scheduling problem, 2014, Knowledge-Based Systems, no.57, pp.95-103.

[9] W. T. Pan, A new fly optimization algorithm: taking the financial distress model as an example, 2012, Knowledge-Based Systems, no.26, pp.69-74.

[10] M. S. Li, T. Y. Ji, W. J. Tang, Bacterial foraging algorithm with varying population, 2010, Biosystems, vol.100, no.3, pp.285-297.

[11] S. S. Mohamed, N. M. Tahir, R. Adnan, Background modeling and back-ground subtraction performance for object detection, 2010, Signal processing and its applications (CSPA), 2010 6th International Colloquium on. IEEE, pp.1-6.

[12] Z. W. Ren, Y. San, Improved adaptive genetic algorithm and its application research in parameter identification, 2006, Journal of System Simulation, vol.18, no.1, pp.41-43.

[13] J. Y. Han, C. Z. Liu, Fly optimization algorithm with adaptive mutation, 2013, Application Research of Computers, vol.30, no.9, pp.2641-2644.

[14] J. P. Ning, B. Wang, H. R. Li, B. H. Xu, Research on an application of diminishing step fly optimization algorithm, 2014, Journal of Shenzhen University Science and Engineering, vol.31, no.4, pp.367-373.