Parameter Optimization Method of Screw Axis with Variable Diameters and Different Pitches Based on PSO-BP NN

Abstract:

Parameter optimization of screw axis with variable diameters and different pitches is very important to improve the performance of material conveying equipment. But it is a trouble thing with classic theory modeling because of the complexity of material fluidity and screw structure. A PSO-trained BP algorithm is applied to establish the screw axis parameter optimization neural network (NN) model.Taking asphalt transfer vehicle as an example, PSO-BP NN is applied to set up the relationship between input parameters and aim parameter. Practical example shows that the PSO-BP NN has faster convergence and higher computational precision than the other three investigated algorithms, and it provides a powerful parameter optimization approach for screw axis with variable diameters and different pitches.

• Periodical: Advanced Materials Research (Volumes 1006-1007)
• Pages: 403-406
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1006-1007.403
• Online since: August 2014
• Authors: Zhang Ping You*, Wen Hui Zhang, Xiao Ping Ye
• Keywords: Neural Network (NN), Optimization Design, Particle Swarm Optimization (PSO), Screw Axis

References

[1] Q. Zhu, Z. Li. Improvement on Paver Auger and Application. Construction Machinery and Equipment, pages 41-43. September (2007).

[2] A. Qiu, S. Gong, G. Xie, and L. Xu. Parametric Model and Performance Simulation on the Screw Conveyor of Variable Diameters and Variable Pitches, Chinese Journal of Mechanical Engineering, pages 131-136. May (2008).

DOI: 10.3901/jme.2008.05.131

[3] D. Katherasan, Jiju V. Elias, P. Sathiya, A. Haq. Simulation and parameter optimization of flux cored arc welding using artificial neural network and particle swarm optimization algorithm. Journal of Intelligent Manufacturing, v 25, n 1, pp.67-76, February (2014).

DOI: 10.1007/s10845-012-0675-0

[4] J. Kennedy, R. Eberhart. Particle swarm optimization. In: Proceedings of the IEEE International Conference on Neural Networks, vol. 4. Perth, Australia, pp.1942-1948. (1995).

[5] R. Poli, J. Kennedy, and T. Blackwell, Particle swarm optimization an overview. Swarm Intelligence 1, 33-57. (2007).

DOI: 10.1007/s11721-007-0002-0

[6] S. Masoud, ELMekkawy, Y. Tarek. Multi-objective optimal design of hybrid renewable energy systems using PSO-simulation based approach. Renewable Energy, v68, pp.67-79, Jan (2014).

DOI: 10.1016/j.renene.2014.01.011

[7] Z. Wu, Q. Zhen, Y. Shi, etc. Optimization design of the dual throat fluidic thrust vectoring nozzle based on RBF and PSO. Tuijin Jishu/Journal of Propulsion Technology, v 34, n 4, pp.451-456, April (2013).

[8] B. Li, Z. He, and Z. Li. Experimental research on bituminous mixture conveyor model, China Journal of Highway and Transport, 16(3): 120-123. (2003).