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

Early diagnosis method for faults of strip steel tension sensor

A technology of tension sensor and early diagnosis, which is applied in the direction of instruments, special data processing applications, electrical digital data processing, etc., and can solve the problems that time domain analysis cannot effectively detect fault characteristics, etc.

Active Publication Date: 2014-01-22
武汉钢铁有限公司
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The frequency components of the output signal of the tension sensor are relatively rich, and the fault characteristics cannot be effectively detected by simple time-domain analysis or frequency-domain analysis.
Although wavelet transform can be used for time-frequency analysis, it is necessary to set the wavelet basis function in advance with the help of prior knowledge

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
  • Early diagnosis method for faults of strip steel tension sensor
  • Early diagnosis method for faults of strip steel tension sensor
  • Early diagnosis method for faults of strip steel tension sensor

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0039] The experimental data used in this embodiment is obtained by on-site collection and simulation program simulation, and the specific process is as follows:

[0040]1. The normal data is collected from the on-site tension measurement system under normal working conditions. A total of 100 strip tension sequences are collected from certain characteristic data of the tension sensor, and the data length of each strip tension sequence is 300.

[0041] 2. Randomly select a position in the length interval from 1 / 3 to 1 / 2 of each normal data sequence (ie [100,150]), so that the sequence value after the random position is a constant value (the constant value of each piece of data is a random value within a certain range), to simulate the failure data of the tension sensor.

[0042] (3) Randomly select a position on the length interval from 1 / 3 to 1 / 2 of each normal data sequence (ie [100,150]), and add or subtract a constant value to the sequence value after the random position (e...

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 an early diagnosis method for faults of a strip steel tension sensor. The early diagnosis method comprises the following steps: (1) obtaining strip steel tension sequence data and standardizing; (2) carrying out adaptive EMD (empirical mode decomposition) on the standardized strip steel tension sequence data; (3) carrying out multi-feature extraction and combination on the strip steel tension sequence data, namely calculating multiple feature vectors of each decomposition amount of the strip steel tension sequence data, combining the feature vectors, and describing the global feature of a strip steel tension time sequence in multi-scale adaptive decomposition; (4) carrying out SVM (support vector machine) classifier training, namely selecting part of global feature data as a training set for SVM classifier learning to obtain an SVM classifier model used for identifying a state of the tension sensor; (5) carrying out offline test and online application. The early diagnosis method can be used for timely finding and removing the early faults of the tension sensor to guarantee normal running of a strip steel tension measurement and control system, and can be widely applied in the technical field of strip steel production.

Description

technical field [0001] The invention relates to the technical field of strip steel production, in particular to an early fault diagnosis method for a strip tension sensor. Background technique [0002] In strip steel production, proper strip steel tension is one of the important conditions to ensure high-speed operation of strip steel, prevent strip deviation and buckling, and obtain good strip steel shape. The fluctuation of strip steel tension will not only affect the quality of strip steel products, but also lead to strip steel breakage and stacking accidents in severe cases, resulting in the shutdown of the unit. Therefore, it is an important means to improve the quality and output of strip steel products by timely and correctly grasping the dynamic characteristics of the strip steel tension and ensuring that the strip steel has a suitable and stable tension in the production process. [0003] From the perspective of production process, strip thickness or unevenness of ...

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): G06K9/66G06F19/00
Inventor 杨先发刘毅敏裴云徐望明代向红梁柏华江淼李富强易钊罗君
Owner 武汉钢铁有限公司
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