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

Multi-parameter Life Prediction Method of Three-phase AC Asynchronous Motor Based on Neural Network

A neural network and life prediction technology, applied in neural learning methods, biological neural network models, motor generator testing, etc., can solve problems such as high safety risks, poor utilization of motors, and inability to accurately detect the life of industrial motors in real time

Active Publication Date: 2021-05-11
CHINA UNIV OF PETROLEUM (EAST CHINA) +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to solve the problems that the existing technology cannot accurately detect the service life of industrial motors in real time, the utilization rate of each motor is poor, and the safety risk is high, the present invention provides a method of recording information using the state parameters and protection event parameters of the microcomputer relay protector, combined with the depth A method of learning network to realize multi-parameter life prediction of electric motor

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
  • Multi-parameter Life Prediction Method of Three-phase AC Asynchronous Motor Based on Neural Network
  • Multi-parameter Life Prediction Method of Three-phase AC Asynchronous Motor Based on Neural Network
  • Multi-parameter Life Prediction Method of Three-phase AC Asynchronous Motor Based on Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] A neural network-based multi-parameter life prediction method for three-phase AC asynchronous motors, the prediction steps include:

[0040] 1) Construct a neural network training set:

[0041] a) Constructing a total loss training subset: in the background management software of the existing motor protector, for each motor that has failed and needs to be replaced, extract the operating state parameters during fault maintenance, standardize these data, and construct a neural network input vector I k ;Since these motors are faulty / maintenance motors, mark their service life as 100%;

[0042] b) Construct half-life training subset: in the background management software of the existing motor protector, for each motor that has failed and needs to be replaced, extract the operating state parameters at half of its service life, standardize these data, and Enter the neural network input vector I k ; Since the extracted parameters are half of the service life of the faulty m...

Embodiment 2

[0059] In this embodiment, the method steps described in Embodiment 1 are used to construct a neural network training set, which is sent to the neural network for training and correction of the neural network, and for testing. The difference is that

[0060] In step 1), if figure 1 As shown in Table 1, the operating state parameters also include the total start-up time i 1 , the total number of starts and stops i 3 , total thermal overload trip time i 4 , total jam trip time i 5 , total three-phase unbalance trip time i 6 , total energy consumption i 7 and motor rated power i 13 There are 7 types, and the corresponding k=(1,...,13).

[0061] In step 2), the 13 normalized parameters of the above-mentioned 10 faulty motors are sent to the neural network as a training set for training, and the input layer of the neural network has the same input nodes as k value number h Number, corresponding to each input data of the above-mentioned state parameters, the output obtained b...

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 multi-parameter life prediction method for a three-phase AC asynchronous motor based on a neural network, which belongs to the field of industrial motor security inspection systems. The state parameters and protection event parameters of a microcomputer relay protector are used to record information, combined with a deep learning network, to realize multiple motors. The method for parameter life prediction, the prediction steps include: constructing a neural network training set, a half life training subset and a 10% loss training subset, sending the above training set into the neural network for training, using the error back propagation algorithm to correct network parameters, Obtain the network's parametric description of the service life of the motor, build a motor loss test set and input it into the built neural network and predict it; avoid the complicated modeling process, improve the accuracy of prediction, eliminate the safety hazard of abnormal shutdown of the factory process, and reduce Risks of economic losses and casualties caused by safety accidents.

Description

technical field [0001] The invention belongs to the field of industrial motor safety inspection systems, and in particular relates to a method for predicting the life of a three-phase AC asynchronous motor. Background technique [0002] With the rapid development of the economy, the society has a strong demand for electric energy, which makes the capacity of the power system continue to expand and the scale of development is rapid. Among them, three-phase AC asynchronous motors are widely used in industrial production. For example, in the field of petroleum and petrochemical, a chemical plant often needs to run hundreds or even thousands of three-phase AC asynchronous motors at the same time. These asynchronous motors are responsible for pumping or pressurizing materials and are the most energy-consuming equipment in the chemical industry. [0003] In particular, the replacement of the main and backup motors at some key production process nodes requires a large-scale produc...

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): G06F30/20G06N3/04G06N3/08G01R31/34G06F119/04
CPCG06N3/084G01R31/34G06N3/045
Inventor 郭亮姜文聪王祥业张超来安政昂宫礼坤李政哲宋立景张秀龙
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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