Research on Intelligent Shift Control Strategy of The Loader Based on Radial Basis Function Neural Network

One of the key issue of the automatic shift control of the loader is how to find the best gear for the current conditions according to certain mapping relation, but this complex and non-linear mapping is difficult to express by mathematical relation. However, to solve such non-linear problems, RBF n...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series Vol. 1550; no. 6; pp. 62003 - 62006
Main Authors: Wu, Guanghua, Ma, Wenxing, You, Lipeng
Format: Journal Article
Language:English
Published: Bristol IOP Publishing 01.05.2020
Subjects:
Automatic control
Construction equipment
Genetic algorithms
Loaders
Mapping
Mathematical analysis
Neural networks
Radial basis function
Thermal expansion
ISSN:1742-6588, 1742-6596
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One of the key issue of the automatic shift control of the loader is how to find the best gear for the current conditions according to certain mapping relation, but this complex and non-linear mapping is difficult to express by mathematical relation. However, to solve such non-linear problems, RBF neural network is the very choice. This paper presents an RBF neural network intelligent shift control strategy method based on improved genetic algorithm. The genetic algorithm's global search ability is improved by adaptively adjusting the crossover probability and mutation probability. The genetic algorithm is used to optimize the RBF neural network expansion coefficient and reduce the tediousness of adjusting parameters during the network learning process. The feasibility of this method was validated by the bench test of the intelligent shift test system for loader automatic shift control. The theory was provided for the development of intelligent automatic shift control for construction machinery. The basis has high engineering application value.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1550/6/062003