Unlock instant, AI-driven research and patent intelligence for your innovation.

A Multi-fault Diagnosis Method Based on Capsule Network for Three-phase Induction Motor under Variable Working Conditions

A technology of induction motor and diagnosis method, applied in neural learning method, motor generator test, biological neural network model, etc., can solve the problems of decreased detection accuracy and increased measurement cost.

Active Publication Date: 2021-08-20
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art, to provide a capsule network-based three-phase induction motor multi-fault diagnosis method under variable working conditions, by analyzing the three-phase current of the motor, and then detect a variety of common motor faults, thereby It solves the characteristics of the traditional motor fault detection method that the detection accuracy is greatly reduced when the motor working condition changes, and the traditional fault detection needs to install additional sensors to increase the measurement cost.

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
  • A Multi-fault Diagnosis Method Based on Capsule Network for Three-phase Induction Motor under Variable Working Conditions
  • A Multi-fault Diagnosis Method Based on Capsule Network for Three-phase Induction Motor under Variable Working Conditions
  • A Multi-fault Diagnosis Method Based on Capsule Network for Three-phase Induction Motor under Variable Working Conditions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] figure 1 It is a flow chart of the capsule network-based multi-fault diagnosis method for a three-phase induction motor under variable working conditions in the present invention.

[0041] In this example, if figure 1 As shown, a capsule network-based multi-fault diagnosis method for three-phase induction motors in the present invention comprises the following steps:

[0042] S1. Data collection

[0043] Collect the current data of the three-phase induction motor under different working conditions, and the motor health status under the corresponding current, denoted as I j [state m ]; wherein, j=1,2,3,...,j represents the motor in different working conditions; m=1,2,...,7m represents the health status of the motor, and the present invention has collected current data under 5 working conditions , are the motor current under the five load conditions of 72, 70, 68, 45 and 40Nm, and the normal working state and six fault states. Lost load, rotor dynamic eccentricity an...

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 capsule network-based multi-fault diagnosis method for three-phase induction motors under variable working conditions. By collecting three-phase current data of various motor health states under different working conditions, performing data preprocessing, and then using the processed The fault diagnosis model based on the capsule network is built based on the data, and the model is trained to obtain a fault diagnosis model that can quickly and accurately detect various faults of the three-phase induction motor, and then used for real-time detection of the three-phase induction motor. It not only reduces the measurement cost and time cost, but also improves the efficiency of motor fault diagnosis and improves the safety of the motor system.

Description

technical field [0001] The invention belongs to the technical field of intelligent fault detection of three-phase induction motors, and more specifically relates to a capsule network-based multi-fault diagnosis method for three-phase induction motors under variable working conditions. Background technique [0002] In modern industrial manufacturing, electric motors are widely used in power generation, fans, machine tools, compressors, mechanical arms and other fields. With the development of renewable energy, electric motors also play an important role in wind power generation and electric vehicles. As one of the most basic components in modern industry, motors often work in harsh environments and changing working conditions, and various emergency failures often occur, causing serious accidents and huge economic losses. At the same time, with the wide application of motors in production and life, in order to ensure the economical and reliable operation of mechanical equipme...

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): G01R31/34G06N3/04G06N3/08
CPCG01R31/34G06N3/08G06N3/045
Inventor 胡维昊李坚黄琦陈健军曹迪张真源井实易建波许潇蒙怡帆
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA