Transition resistance prediction method based on BP neural network

Abstract

The invention discloses a transition resistance prediction method based on a BP neural network, and the method comprises the specific steps: step 1, collecting the original data of a subway as a dataset, and enabling the original data to be five types of data: the polarization voltage, the rail structure voltage, the offset, the natural ontology, and the transition resistance measurement value ofthe subway; step 2, preprocessing the data in the data set; dividing the preprocessed data set into a training set and a test set; step 3, constructing a transition resistance prediction model basedon the BP neural network; step 4, training a transition resistance prediction model based on the BP neural network by adopting the training set; and step 5, selecting a group of data from the test set, and testing the training set by using the trained transition resistance prediction model based on the BP neural network to obtain a predicted value of the transition resistance. According to the invention, the problem that the measurement of the transition resistance is tedious and difficult to predict in the prior art is solved.

Description

technical field [0001] The invention belongs to the technical field of machine learning and relates to a transition resistance prediction method based on BP neural network. Background technique [0002] With the continuous development of my country's economy, the construction of urbanization infrastructure is also getting faster and faster, and the convenience and rapidity of citizens' travel needs have risen sharply, among which the construction of urban rail transit is particularly important. Because of its convenient travel characteristics, urban subway has become the first choice for citizens to travel. Metro DC traction system plays a very important role in urban economic development and alleviating traffic congestion. The subway DC traction system will generate a harmful stray current during operation. The stray current will cause a harmful chemical corrosion to the buried wires, communication pipelines and metal pipelines around the system, which may cause the loss of...

AI Technical Summary

Problems solved by technology

[0013] The purpose of the present invention is to provide a kind of transition resistance prediction method based on BP neural network, the present invention solves the comparatively loaded down with trivial details and difficulty of measuring transition resistance existing in the prior art problem of prediction

Images