An Intelligent Transportation Scheduling Management Method Based on Neural Network Genetic Algorithm

Abstract

The invention discloses an intelligent transportation scheduling management method based on a neural network genetic algorithm, comprising the following steps: A1, establishing a data module according to the transportation scheduling management system; A2, generating an initial population G; the initial population includes N chromosomes; Chromosomes encode the material M (Ma and / or Mb) according to any length according to the needs; construct the neural network; the delivery point is the input node of the neural network, the receiving point is the output node, and the transfer station is the hidden layer; A4, Start iterating. The neural network algorithm is added to the genetic algorithm to avoid the disadvantages of low computational efficiency, easy to fall into local optimum, and difficult convergence in the genetic algorithm, and avoid premature convergence or a large number of iterative recalculations. The fitness evaluation function is evaluated from two opposite angles of economical applicability e and time length t, and the two opposite functions balance each other to realize a fast and economical logistics scheduling scheme.

Description

technical field [0001] The invention relates to the technical field of transportation pipelines, in particular to a high-pressure hydrogenation large-diameter super-thick seamless tee pipe fitting. Background technique [0002] The genetic algorithm is based on the principle of survival of the fittest in self-science, and was later cited in the optimization algorithm. The genetic operations performed in the evolution process include coding, selection, crossover, mutation, and survival of the fittest. There is no need for function derivatives and requirements The function is continuous. It simulates the phenomena of reproduction, crossover and gene mutation in the process of natural selection and natural inheritance. In each iteration, a group of candidate solutions is reserved, and a better individual is selected from the solution group according to a certain index. Genetic operators (selection, crossover and mutation) combine these individuals to generate a new generation o...

AI Technical Summary

Problems solved by technology

The fitness function is similar to the role of the environment in the evolution of organisms. Individuals with high fitness will produce more offspring in the reproduction process from generation to generation, while individuals with low fitness will gradually die out; but the computational efficiency of genetic algorithm Low, easy to fall into local optimum, difficult convergence and other deficiencies, which will cause premature convergence, or a large number of iterative recalculations. In the modern logistics industry, the logistics volume is increasing, which is very consistent with the basic coding of genetic algorithms, and from disorder However, how to dispatch vehicles quickly and efficiently with as few dispatch vehicles as possible is obviously a difficult problem, which cannot be solved by genetic algorithms

Images