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

Motor fault knowledge extraction system and method

A technology of knowledge extraction and faults, applied in computer parts, electrical digital data processing, character and pattern recognition, etc., can solve problems such as difficulties in motor fault knowledge extraction

Pending Publication Date: 2020-11-27
哈电发电设备国家工程研究中心有限公司
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] In order to solve the problems in the prior art that the motor fault knowledge is difficult to extract due to the various types of motor faults, the present invention proposes a motor fault knowledge extraction system and method, and the technical scheme is as follows:

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
  • Motor fault knowledge extraction system and method
  • Motor fault knowledge extraction system and method
  • Motor fault knowledge extraction system and method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0095] Specific embodiment one: a kind of motor fault knowledge extraction system and method steps of this embodiment are as follows:

[0096] Step 1, in the data collection module, the user and the administrator register their information through the registration information module, and the user uploads personal information or answers to the questionnaire to the user data collection module for the administrator to complete. Processing, the data in the document data acquisition module selects the data as the training model support of the system;

[0097] Step 2, in the described data preprocessing module, the text format conversion module carries out unified processing with the text format of different types of motor faults, and the described text encoding conversion module carries out uniform encoding with different types of text encodings, and the described text The normalization module annotates the text with labels and processes it through the auxiliary training tool modul...

specific Embodiment approach 2

[0108] Specific implementation mode two: according to specific implementation mode one step one, the system also includes two parts, the mobile terminal and the PC terminal:

[0109] The PC terminal provides an interface for the mobile terminal. After the administrator configures the relevant basic information on the PC terminal, a standard questionnaire is formed at the same time. These preliminary preparations can be used at the same time. Although the administrator can only configure on the PC side, the configuration results can be used in both parts at the same time, so the business logic of the two is similar.

[0110] All users' answers need to be confirmed by the administrator, and all users will receive a notification from the administrator. After answering the questionnaire on any platform, it will be saved, uploaded, and submitted to the background, so users only need to choose a platform to answer only once That is, after answering, it will be handed over to the adm...

specific Embodiment approach 3

[0115] Embodiment 3: In addition to the document data collection module described in Embodiment 1, Step 1, it also includes crawling related articles. The design of the crawler tool in the module is mainly aimed at the position of journals on HowNet. Place it under a fixed label, and crawl according to the relevant requirements of HowNet. Before crawling, you need to obtain the crawling permission, and set the access speed per second. After the relevant settings are completed, crawl the periodicals of the magazine in recent years ;

[0116] The flow chart of document crawling is as follows: Figure 5 shown.

[0117] A total of more than 300 articles were obtained by crawling the articles in the "Journal of Large Electric Machine Technology", and a part of them was selected as a training set for training. The trained model uses Google's new BERT model, which has a high accuracy and recall rate. At the same time, the task of named entity recognition is used for training, and a...

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 discloses a motor fault knowledge extraction system and method, and particularly relates to the technical field of motor fault judgment by a neural network model. The objective of the invention is to solve the problem of difficult extraction of motor fault knowledge of related personnel caused by various motor faults in the prior art. According to the invention, a BERT model is applied to construct a software system, the system comprises a data acquisition module, a data preprocessing module, an auxiliary training tool module, a model training module and a knowledge fusion module. A user and an administrator use the motor fault knowledge extraction system. More scientific technical support and generator fault knowledge extraction are provided for user motor fault maintenanceservice, and the purpose of the invention is to construct a fault knowledge base, so that a user can conveniently and quickly solve faults in a motor, the operation is more convenient and accurate, the level of related business personnel can be improved, and the motor fault solving efficiency is greatly improved.

Description

technical field [0001] The invention relates to a motor fault knowledge extraction system and method, in particular to the technical field of motor fault judgment by a neural network model. Background technique [0002] Based on the research and analysis of domestic and foreign large-scale equipment fault diagnosis technology and application status, in order to provide customers with better technical support. In order to ensure that customers' problems can be solved quickly, the motor fault knowledge extraction system is launched. Customers can ask questions according to their own motor problems and get responses, and solve customer problems in the shortest time, ensuring the safety and stable operation of the motor. , Reduce losses due to motor failure. In the above background, combined with the current popular natural language processing technology, Google's newly proposed Bert model, and other related technologies to develop a "motor fault knowledge extraction system". ...

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): G06F16/332G06F16/35G06F40/279G06K9/62
CPCG06F16/3329G06F16/35G06F40/279G06F18/2415Y02D10/00
Inventor 王克剑毛静轩苗东旭姜漫利曲晓峰赵明傅磊张德阳
Owner 哈电发电设备国家工程研究中心有限公司
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