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

Fault diagnosis and test method based on proportional valve shaft controller

A technology of fault diagnosis and testing method, applied in the fields of instruments, character and pattern recognition, computer parts, etc., which can solve the problems of limited experimental data of proportional valve shaft controller and overfitting of proportional valve shaft controller fault classification.

Pending Publication Date: 2021-07-06
NANJING CHENGUANG GRP
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the experimental data of the proportional valve shaft controller is limited, and in the case of small samples, the fault classification of the proportional valve shaft controller is prone to overfitting.

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 diagnosis and test method based on proportional valve shaft controller
  • Fault diagnosis and test method based on proportional valve shaft controller
  • Fault diagnosis and test method based on proportional valve shaft controller

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0022] The invention provides a fault diagnosis and testing method based on a proportional valve axis controller. Firstly, the slow feature analysis algorithm is used to extract the slowly changing information in the proportional valve fault, and the slow feature is weighted through the spatial attention weighting mechanism to improve the importance of fault discrimination. The weight of the feature weakens the weight of non-important features for fault discrimination, and re-calibrates the slow features to obtain new slow features weighted based on the spatial attention mechanism. Finally, the random forest algorithm is used to realize the fault diagnosis of the proportional valve. The overall algorithm principle flow process of the present invention is as figure 1 As shown, the specific steps are as follows:

[0023] Step 1: Collect the test ...

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 diagnosis and test method based on a proportional valve shaft controller. The method comprises the following steps: collecting test data of different types of proportional valves in different states; extracting slow features of the test data of the proportional valve; generating a plurality of training sample subsets according to the newly calibrated slow features of the test data of the proportional valve; training different random forest models for different types of proportional valves; fault diagnosis of a proportional valve shaft controller: after the model of the proportional valve is determined, inputting the slow data characteristics of the proportional valve to be detected into the random forest model of the corresponding model, and outputting a fault type label of the proportional valve; and optimizing the random forest model on line. The fault of the proportional valve shaft controller is judged after the proportional valve flow characteristic experiment, the proportional valve threshold characteristic experiment and the proportional valve pressure gain experiment are combined and subjected to characteristic fusion, and the fault recognition rate is higher than the fault recognition precision of the proportional valve shaft controller of a single experiment.

Description

technical field [0001] The invention relates to the field of proportional valve fault diagnosis, in particular to a fault diagnosis and testing method based on a proportional valve shaft controller. Background technique [0002] Proportional valves are widely used in the fields of metallurgy, aerospace, ships, weapons and petrochemicals. Fault identification of proportional valve shaft controllers is an important direction in the field of proportional valves. Once a proportional valve shaft controller fails, it will generate immeasurable damage. Therefore, improving the proportional valve axis controller is a research hotspot in the field of proportional valves. The essence of the detection problem of proportional valve shaft controller is the fault mode recognition problem of proportional valve shaft controller, in which the feature extraction of data and the design of classification model are the key points of pattern recognition. [0003] Normally, the failure types of t...

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): G06K9/62G06K9/00
CPCG06F2218/08G06F18/24323G06F18/214
Inventor 孙家庆赵旭东王俊霞翟丽娟韩宁黄璞
Owner NANJING CHENGUANG GRP
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