Open AccessResearch on Intelligent Shift Control Strategy of The Loader Based on Radial Basis Function Neural Network
Author(s) -
Guanghua Wu,
Wenxing Ma,
Li-peng You
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1550/6/062003
Subject(s) - loader , artificial neural network , crossover , computer science , intelligent control , radial basis function , relation (database) , genetic algorithm , process (computing) , artificial intelligence , key (lock) , radial basis function network , function (biology) , control engineering , machine learning , engineering , data mining , computer security , evolutionary biology , biology , operating system
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.