Fault prediction method based on machine learning

A fault prediction and machine learning technology, applied in machine learning, prediction, instruments, etc., can solve problems such as excess, waste of resources, excess maintenance, etc., to reduce costs, reduce maintenance costs, and improve efficiency.

Inactive Publication Date: 2018-07-20
CHINA NAT SOFTWARE & SERVICE
View PDF3 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, high-speed rail is routinely inspected every day, cars are maintained every few months, and aircraft are maintai

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
  • Fault prediction method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In order to facilitate those skilled in the art to understand the technical content of the present invention, the content of the present invention will be further explained below in conjunction with the accompanying drawings.

[0027] Data is the foundation of machine learning to solve problems. If the data is not selected correctly, the problem cannot be solved. First, the data is divided into two parts, one part is mainly the basic technical parameters of the equipment, operating index data, and known data of past failures. The specific parameters involve equipment temperature, heat, rotation speed, displacement, process parameters and vibration. The other part is the time series data of the above parameters of equipment operation. This type of data is to install sensors in the required prediction object (such as equipment or system) to collect real-time data of the operation of the prediction object, and perform the characteristic analysis of the above two parts of da...

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 fault prediction method based on machine learning, which comprises the steps of 1) collecting set running index data of an object to be predicted, obtaining time series dataof each set running index, and collecting historical fault data of the object to be predicted; 2) respectively performing feature extraction on the data collected in the step 1), and inputting the extracted features into a machine learning system for training to obtain a basic fault prediction model; and 3) collecting real-time data of the set running indexes of the object to be predicted in running, performing feature extraction on the real-time data, inputting the extracted features into the basic fault prediction model, and predicting whether the object to be predicted has a fault or not atpresent. According to the method, the safe operation efficiency of equipment is improved, the maintenance time is shortened, the maintenance cost is reduced, the service life of the equipment is prolonged, and influences caused by the failure of some equipment are reduced or avoided.

Description

technical field [0001] The invention belongs to the field of artificial intelligence machine learning and relates to a maintenance method, in particular to a fault prediction method based on machine learning. Background technique [0002] At present, in people's real life, the dependence on systems and machines has exceeded people's imagination. Daily travel involves driving, taking elevators, taking high-speed rail or airplanes, etc., and in the manufacturing and production of enterprises, machines have liberated workers, but these machines or systems will fail, some failures are just inconvenience, while some failures are a matter of life and death. [0003] When the stakes are high, routine maintenance of the system is required. Because the cost of failure is much higher than the cost of appearance. For example, high-speed rail is routinely inspected every day, cars are maintained every few months, and aircraft are maintained once a day. This method will lead to a serio...

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): G06Q10/00G06Q10/04G06Q10/06G06N99/00
CPCG06N20/00G06Q10/04G06Q10/0635G06Q10/20
Inventor 乔立中
Owner CHINA NAT SOFTWARE & SERVICE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap