An Obstacle Recognition Method Based on Improved PSO-WNN for Deicing Robot on Voltage Transmission Line

Abstract:

An intelligent obstacle recognition method based on improved particle swarm optimization wavelet neural network (IPSO-WNN) for deicing robot on voltage transmission line is presented because traditional obstacle recognition methods often have errors due to structural constraints. Firstly, the improved PSO algorithm is proposed by introduce idea of probabilistic leap in simulated annealing. Secondly , the improved algorithm is used to optimize the parameters of the wavelet network. Finally, the trained IPSO-WNN is used to recognize and classify the wavelet moments of the obstacle edged images of robot. Experimental results show that compared with PSO-WNN this method have quicker convergence rate and higher classification precision and improve obviously recognition function of obstacle on transmission line.

• Periodical: Applied Mechanics and Materials (Volume 160)
• Pages: 53-58
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.160.53
• Online since: March 2012
• Authors: Su Wei Zhang, Wei Sun, Si Yi Miao
• Keywords: Deicing Robot, Obstacle Recognition, Particle Swarm Optimization (PSO), Wavelet Moments, Wavelet Neural Network (WNN)

References

[1] Peng Meng: Mobile robot obstacle detection research based on multi senor fusion. Master thesis of Central South University(2007).

[2] Junhai Zhai, Xizhao: Rough-Neural Image Classification Using Wavelet Transform. In: Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, H.K. Vol. 3045-3050(2007).

DOI: 10.1109/icmlc.2007.4370671

[3] Dickhaus H, Heinrich H: Classifying biosignals with wavelet networks. IEEE Eng in Medicine and Biology. Vol. 103-111 (1996), p.5.

DOI: 10.1109/51.537066

[4] Engelbrecht A P , Ismail : Training product unit neural networks . Stability and Control . Vol. 59-74 (1999), p.2.

[5] Van den Bergh F, Engelbrecht A P: Cooperative learning in neural networks using particle swarm optimization. South African Computer Journal. Vol. 84-90(2000), p.26.

[6] Wang Y H, Yan W L: Adaptive Simulated Annealing for the Optimal Design of Electromagnetic Devices. IEEE Transactions on magnetics. Vol. 1214-1217(1996), p.32.

DOI: 10.1109/20.497462

[7] Sriboonruang Y, Kumhom P, Chamnongthai K: Hand Posture Classification Using Wavelet Moment Invariant, In: IEEE International Conference on Virtual Environments, USA(2004).

DOI: 10.1109/vecims.2004.1397192

[8] Miao Siyi, Sun Wei, Zhang Haixia: Intelligent Visual Method Based on Wavelet Moments for Obstacle Recognition of High Voltage Transmission Line Deicer Robot. robot . Vol. 425-431(2010), p.3.

DOI: 10.3724/sp.j.1218.2010.00425