Unlock instant, AI-driven research and patent intelligence for your innovation.

Calculation method of train traction energy consumption based on machine learning

A machine learning and train technology, applied in energy-saving calculation, computing, computer parts, etc., can solve the problems of train error, uncalculated train traction energy consumption, etc.

Active Publication Date: 2020-10-09
BEIJING JIAOTONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the field application process, there is often a certain error between the actual energy consumption of the train and the theoretical calculation
[0004] At present, there is no effective method for calculating train traction energy consumption in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Calculation method of train traction energy consumption based on machine learning
  • Calculation method of train traction energy consumption based on machine learning
  • Calculation method of train traction energy consumption based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] With the rapid development of theories such as big data, machine learning, artificial intelligence and deep learning, mining the potential information of data, using data modeling optimization, and showing good results in various applications. At the same time, the high-quality data of the running state of the train can also be obtained completely. The present invention is based on this, hoping to apply the data drive to the energy saving of train traction. Using the state data (running curve) of trains running between stations, a new method for data-driven calculation of train running energy consumption is established.

[0056] The present invention provides a method for calculating the energy consumption of train traction based on machine learning, which can be based on the recorded speed, time, and displacement data of the train running state and the corresponding net energy consumption of the train traction (excluding the energy consumption of other equipment), As t...

Embodiment 2

[0091] The processing steps of a machine learning-based calculation method for train traction energy consumption provided by this embodiment include:

[0092] Step1: Establish a data-driven model for machine learning to calculate train traction energy consumption.

[0093] Step1-1: The assumption of the model is that within the small time unit interval ▽t (0.1s level) obtained from the original train running speed curve, the running state of the train between each speed point is a process of uniform acceleration.

[0094] Step1-2: discretize the train speed curve (displacement speed curve) into a series of speed data points at different displacements {v 1 -s 1},{v 2 -s 2}.......,{v i -s i},.....{v n -s n}, {v i -s i} is the velocity-displacement point. The simplified speed point sequence represents a speed curve, and each speed point is also the decision variable of the model.

[0095] Step1-3: From a data-driven perspective, traction energy consumption E under a fi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An embodiment of the present invention provides a method for calculating train traction energy consumption based on machine learning. The method includes: establishing a discretized train traction energy consumption calculation model; selecting and processing existing data to form a discretized data set; dividing the data set into a training set and a test set, and using the training set to train and calibrate random forest regression The optimal parameters of the machine learning algorithm are regressed with the support vector machine, and the test set is used to verify its effect for calculating traction energy consumption. The new method of machine learning algorithm random forest regression and support vector machine regression is used to calculate the energy consumption of the train traction speed curve, and the random forest regression can also obtain the importance ranking of the speed at a certain displacement of the curve. The machine learning method calculates the energy consumption of train traction, the calculation process is simple, the calculation accuracy is high, and the calculation cost is low.

Description

technical field [0001] The invention relates to the technical field of train traction energy calculation, in particular to a method for calculating train traction energy consumption based on machine learning. Background technique [0002] At this stage, the main measure to solve the traffic congestion problem in the world's major cities is to guide the development of public transportation, and urban rail transit, which is the backbone of urban public transportation, has been vigorously developed. The continuous increase in the operating mileage of urban rail transit is accompanied by a continuous increase in operational energy consumption, and the corresponding carbon emissions have also risen sharply. The country and the environmental protection department also attach great importance to this; the cost of energy consumption is also increasing. Larger, the base of energy consumption becomes larger, which also puts forward higher requirements for energy conservation. [0003...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/15G06F30/27G06F16/2458G06K9/62
CPCG06F30/15G06F18/24323Y02D10/00
Inventor 杨欣黄康吴建军高自友尹浩东屈云超
Owner BEIJING JIAOTONG UNIV