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

One-class impact fault diagnosis based on small sample deep learning

A deep learning and fault diagnosis technology, applied in the computer field, can solve the problems of low diagnostic accuracy and high cost, achieve the effect of improving accuracy and efficiency, and improving the ability to migrate under variable load conditions

Pending Publication Date: 2021-11-26
BEIJING BOHUA XINZHI SCI & TECH
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, in the detection process of equipment failure, it is mainly through manual investigation, such as the observation of the engineer's human eyes, or the experience of the engineer to diagnose whether the equipment is faulty, which makes the diagnosis accuracy low and the cost high

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
  • One-class impact fault diagnosis based on small sample deep learning
  • One-class impact fault diagnosis based on small sample deep learning
  • One-class impact fault diagnosis based on small sample deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the related application, not to limit the application. It should also be noted that, for the convenience of description, only the parts related to the application are shown in the drawings.

[0027] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0028] It can be understood that in the faulty equipment diagnosis scenario, it is necessary to detect equipment failures in time to strengthen equipment maintenance and repair, such as grasping the fault conditions of a type of impact to ensure the normal operation of equipment.

...

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 one-class impact fault diagnosis method based on small sample deep learning, and the method comprises the steps: obtaining migration features corresponding to equipment monitoring data, and obtaining a migration feature set; reconstructing the migration feature set to obtain a training set of the equipment, the training set including real frequency domain data and virtual frequency domain data of the equipment; and based on machine learning, training the training set, and constructing a fault diagnosis model of the equipment, the fault diagnosis model being used for identifying whether the equipment has a fault. According to the embodiment of the invention, the appropriate migration features are selected according to the fault mechanism of the equipment, the migration feature set is reconstructed to generate the rich training set, finally the model of the generated training set is trained, and the fault diagnosis model of the equipment is constructed, so that whether the equipment has a fault can be accurately diagnosed by using the constructed fault diagnosis model. The accuracy and efficiency of equipment fault diagnosis are improved, and the method has good variable load working condition migration capability.

Description

technical field [0001] This application generally relates to the field of computer technology, and specifically relates to a type of impact fault diagnosis method based on small-sample deep learning. Background technique [0002] During the use of the equipment, due to friction, external force, stress and chemical reaction, the parts will always be gradually worn, corroded, broken and shut down due to failure. In order to prevent economic losses caused by downtime due to failures, it is necessary to detect equipment failures in time to strengthen equipment maintenance. If the wear and tear of parts is known, repairs and replacements can be carried out before the parts enter the stage of severe wear and tear. [0003] At present, in the detection process of equipment failure, it is mainly through manual inspection, such as the observation of the engineer's eyes, or the experience of the engineer to diagnose whether the equipment is faulty, which makes the diagnosis accuracy l...

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 Applications(China)
IPC IPC(8): G06F30/27G06N3/04G06N3/08G06N20/00G01M7/08
CPCG06F30/27G06N3/08G06N20/00G01M7/08G06N3/045
Inventor 高晖赵大力刘锦南王牮
Owner BEIJING BOHUA XINZHI SCI & TECH