Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Data cleaning and forecasting method and mobile power bank system for electric vehicle

A prediction method and data cleaning technology, applied in electric vehicle charging technology, electric vehicles, forecasting, etc., can solve problems such as abnormal data problems, remaining power, inaccurate predictions, and the failure of trams to reach their destinations

Pending Publication Date: 2018-04-06
深圳华源技术实业有限公司
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the defects or deficiencies in the prior art, the technical problem to be solved by the present invention is: to provide a technical problem in the prior art that can solve the problem that the electric car cannot drive to the destination due to an emergency or failure of the battery of the electric vehicle. A mobile charging treasure system for electric vehicles, and a method for clearing abnormal data and predicting data of a mobile charging treasure that can solve the technical problem of abnormal data in the charging and discharging process of the mobile charging treasure and the inaccurate prediction of remaining power 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
  • Data cleaning and forecasting method and mobile power bank system for electric vehicle
  • Data cleaning and forecasting method and mobile power bank system for electric vehicle
  • Data cleaning and forecasting method and mobile power bank system for electric vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0093] Example 1, such as figure 1 As shown, the present invention provides a mobile power bank system for electric vehicles, including a battery module, a discharge module, a charging module, and a display screen, and is characterized in that it also includes an insulation monitoring module, a data acquisition array module, and an intelligent monitoring and management module; The battery modules are respectively connected to the discharge module, the charging module, the insulation monitoring module and the data acquisition array; the intelligent monitoring management module is connected to the data acquisition array and the display screen; the insulation monitoring module is respectively connected to the The positive and negative poles of the battery module are electrically connected, and are also electrically connected to the casing; the intelligent monitoring and management module includes a battery management unit, an embedded database processing unit, and a PWM signal con...

Embodiment 2

[0107] Example 2, such as Figure 2-4 As shown, based on the above-mentioned embodiments, the present invention also provides a data cleaning and prediction method, wherein, cleaning of abnormal data: errors in the voltage, current, temperature and resistance data of the single battery during the charging and discharging process collected , Inconsistent abnormal data, so it is necessary to clean the abnormal data of the embedded large database, in order to analyze the performance of the system through more correct data, so as to ensure that the mobile power bank system makes a correct response during the charging and discharging process. The data cleaning and prediction method includes the following steps:

[0108] S1. Perform cluster analysis on the data in the database, and obtain data that is not classified into any category as abnormal data, that is, data to be cleaned; specifically, in step S1, perform cluster analysis on the data in the database based on the DBSCAN clust...

Embodiment 3

[0180] Embodiment 3. Based on the above embodiments, the present invention provides a data cleaning and prediction method, including, in the step S4, the method of predicting the SOC value of the single battery is the same as the method of predicting the data vacancy value in the step S3.

[0181] Wherein, the input layer of the wavelet neural network used to predict the SOC value of the single battery when training the neural network: the temperature of the single battery collected by the data acquisition array module and processed by the data cleaning and prediction method in Example 2 Data and voltage data, as well as the discharged value of the single battery, and store them in the database; the SOC value stored in the database is the input layer.

[0182] The present invention also uses the historical data of cyclic charging and discharging under the synergistic effect of the data acquisition sensor array, embedded database, and intelligent monitoring and management module...

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

The invention relates to a data cleaning and forecasting method which comprises the following steps: S1, performing cluster analysis on data in a database to obtain abnormal data which is not classified, namely the data to be cleaned; S2, deleting the abnormal data; S3, forecasting and filling the data vacancy after the abnormal data is cleaned by a wavelet neural network and a combination forecasting method; and S4, forecasting the SOC value of a single battery. The invention also relates to a mobile charge system for an electric vehicle. The mobile charge system comprises a battery module, adischarge module, a charge module and a display screen and is characterized by also comprising an insulation monitoring module, a data acquisition array module and an intelligent monitoring management module. The method provided by the invention has the advantages that the intelligent monitoring management module is adopted for cleaning the abnormal data of the single battery acquired by the dataacquisition array in the charge and discharge processes, and the wavelet neural network and the combination forecasting method are adopted for accurately forecasting the value of the data vacancy ofthe cleaned abnormal data and the SOC value of the single battery so as to ensure the reliability and stability of the system.

Description

technical field [0001] The invention relates to a mobile power supply, in particular to a data cleaning and prediction method and a mobile charging treasure system for electric vehicles. Background technique [0002] With the development of electric vehicle technology, the concept of green and environmental protection is deeply rooted in the hearts of the people, and more and more consumers pay attention to electric vehicles. However, the backwardness of electric vehicle charging technology and the imperfection of charging facilities make the cruising range of electric vehicles always a big problem and become the main factor restricting the development of electric vehicles. At present, most electric vehicle charging infrastructures are mainly fixed and cannot be flexibly moved. In the actual use of electric vehicles, due to negligence or equipment failure, sometimes the electric vehicles on the way cannot drive to the charging station in time because of the exhaustion of el...

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
IPC IPC(8): B60L11/18G06Q10/04G06K9/62
CPCG06Q10/04B60L53/20B60L53/60G06F18/23G06F18/10Y02T10/70Y02T90/12Y02T10/7072Y02T90/14
Inventor 潘海锋陈亚欢
Owner 深圳华源技术实业有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com