Skip to Main Content
Skip Nav Destination
ASME Press Select Proceedings
International Conference on Advanced Computer Theory and Engineering (ICACTE 2009)
By
Xie Yi
Xie Yi
Search for other works by this author on:
ISBN:
9780791802977
No. of Pages:
2012
Publisher:
ASME Press
Publication date:
2009

To analyze agitation characteristic of screw shaft in Bituminous Mixture Transfer Vehicle (BMTV), a Neural Network (NN) model was established, based on helical blade radius, pitch and rotational speed of screw shaft used as input vector, while asphalt mixture segregation rate used as output vector. To solve the problems of the slow convergence rate and easily falling into local minimum in BP algorithm, PSO algorithm combined with Levenberg-Marquardt algorithm was employed as learning algorithm of the NN. Model of BMTV was designed and manufactured, and model experiment data was applied to simulation experiment of the screw shaft NN model. Simulation and experiment results indicate that the proposed approach not only can overcome the drawbacks of BP algorithm, but also has faster convergence and higher computational precision than original PSO. It also can be applied to building model for agitation characteristics of screw shaft in BMTV, and it is effective.

Abstract
Key Words
1 Introduction
2. FNN Model of Screw Shaft in BMTV
3 Learning Algorithm for FNN Model
4. Model Experiment of BMTV
5. Simulation Experiment with FNN Model
6. Summaries
References
This content is only available via PDF.
You do not currently have access to this chapter.
Close Modal

or Create an Account

Close Modal
Close Modal