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

Construction of vehicle fault identification model, identification method and device, and management system

A vehicle fault and identification model technology, which is applied in the field of vehicle fault identification, can solve the problem of inconsistency in the cross-border area of ​​each parking area, and achieve the effects of precise maintenance and improved availability

Active Publication Date: 2021-07-02
SHANGHAI JUNZHENG NETWORK TECH CO LTD
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is the problem caused by the possible inconsistency of the cross-border area of ​​each parking area in the identification process of the existing parking area, and aims to provide a precise maintenance of the vehicle that is beneficial to operation and maintenance. , improve user experience, avoid vehicle failure identification model construction, identification method and device, and management system for potential safety hazards of vehicles in failure

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
  • Construction of vehicle fault identification model, identification method and device, and management system
  • Construction of vehicle fault identification model, identification method and device, and management system
  • Construction of vehicle fault identification model, identification method and device, and management system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as figure 1 As shown, Embodiment 1 provides a method for building a vehicle fault identification model, including:

[0055] S1: extract sample data of a sample vehicle, the sample data includes multi-dimensional data related to the state of the sample vehicle, and a fault label for marking the faulty vehicle;

[0056] S2: Analyze data: Analyze the data difference between the faulty vehicle and the non-faulty vehicle according to the sample data, and obtain the analysis result. Representation information of data in each dimension;

[0057] S3: Extracting sample data features: extracting data features from the analysis results obtained in S2, and establishing a vehicle portrait according to the data features;

[0058] S4: Weight the vehicle portrait processed by the machine learning model and its corresponding fault label to obtain a fault identification model.

[0059] In S1, the data of the vehicle riding dimension, vehicle geographic location dimension, vehicle...

Embodiment 2

[0072] Such as figure 2 As shown, embodiment 2 provides a device for constructing a vehicle fault recognition model, which includes:

[0073] A sample data extraction unit 10, the sample data extraction unit 10 is used to extract sample data of a sample vehicle, the sample data includes multi-dimensional data related to the state of the sample vehicle, and a fault label for marking a fault vehicle;

[0074] Data analysis unit 20, which is connected to the sample data extraction unit 10, the data analysis unit 20 is used to analyze the data difference between the faulty vehicle and the non-faulty vehicle according to the sample data, and obtain an analysis result, the analysis result includes Relevant data that are likely to cause failures mined from the sample data and characterization information of faulty vehicles in various dimensions;

[0075] A sample data feature extraction unit 30, which is connected to the data analysis unit 20, and the sample data feature extraction...

Embodiment 3

[0085] In order to reduce the number of faulty bicycles in operation, to repair the faulty vehicles in a timely manner, and to actively identify the faulty conditions of single bicycles is the direct purpose of this technology. Therefore, Embodiment 3 also provides a vehicle fault identification method, including:

[0086] S5: extracting characteristic parameters of the vehicle to be identified;

[0087] S6: Input the characteristic parameters into the fault recognition model to obtain the probability of the fault of the vehicle to be recognized.

[0088] In S5, the characteristic parameters of the vehicle to be identified are extracted, including the characteristic parameters of the above-mentioned vehicle riding dimension, vehicle geographic location dimension, vehicle attribute dimension, vehicle history fault and maintenance dimension, and vehicle history riding dimension, excluding the above-mentioned fault label .

[0089] In S6, the characteristic parameters are input...

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

This case provides a vehicle fault identification model construction, identification method, device, and management system, including: extracting sample data of sample vehicles; analyzing data: analyzing the data differences between faulty vehicles and non-faulty vehicles according to the sample data, and obtaining Get the analysis result, the analysis result includes the relevant data that is easy to cause failure and the characterization information of the faulty vehicle in each dimension dimension data mined from the sample data; extracting sample data features: extracting data features from the analysis results, Establish a vehicle portrait according to the data characteristics; weight the vehicle portrait processed by the machine learning model and its corresponding fault label to obtain a fault recognition model. Through this case, it is possible to build a vehicle fault identification model, and use this model to perform fault judgments on new vehicle samples to obtain the probability of failure of the vehicle to be identified, provide assistance for vehicle operation, and improve the availability of operating vehicles.

Description

technical field [0001] The invention relates to the technical field of vehicle fault identification, and is a method for determining vehicle performance characteristics through data mining, thereby establishing a vehicle fault identification system and identifying faulty vehicles. Background technique [0002] With the development of the concept of Internet sharing, the number of shared bicycles has further increased in cities across the country. However, after the number of bicycles reaches a certain level, with the increase in the number and time of bicycle use, the failure rate of bicycles also begins to rise. To a certain extent, it brings a large workload to the operation and maintenance personnel, and at the same time, it also produces a bad experience for the riders, and even has potential safety hazards. [0003] For the above problems, it is very meaningful to actively identify the failure of bicycles in operation, which can facilitate the precise maintenance of bic...

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): G05B23/02G06N20/00
CPCG05B23/0243G05B2219/24065G06N20/00
Inventor 杨磊余涵
Owner SHANGHAI JUNZHENG NETWORK TECH CO LTD
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