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

Fault diagnosis method based on multi-period segmented sliding window standard deviation

A technology of sliding window and fault diagnosis, which is applied to the generation of response errors, complex mathematical operations, and special data processing applications. It can solve problems such as difficulty in obtaining abnormal data and long training model time, and achieve the effect of simple and effective algorithms

Active Publication Date: 2021-03-16
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, equipment fault diagnosis and early warning are generally based on artificial intelligence algorithms; or machine learning algorithms, or deep learning algorithms. For some expensive equipment, it is extremely difficult to obtain abnormal data

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 method based on multi-period segmented sliding window standard deviation
  • Fault diagnosis method based on multi-period segmented sliding window standard deviation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0021] like figure 1 As shown, a fault diagnosis method based on the standard deviation of the multi-period segmented sliding window includes the following steps:

[0022] 1. Collect An period of current amplitude data during normal operation of an electrical equipment A as sample data, and normalize the maximum and minimum values ​​of the sample data of each period to the [0,1] interval;

[0023] 2. Convert the sample data into two-dimensional matrix data, that is, the complete data of a certain period in the horizontal direction, and the corresponding point data in each period in the vertical direction, such as figure 2 As shown; the specific operation is: initialize the two-dimensional array Array[x][y], x represents the number of acquisition cycles of the sample data, y represents the number of data points in a single cycle, fill the sample data into the two-dimensional array, initialize the list L, Ln , Lm, set the size of the sliding window as m*n, the sliding step as ...

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 method based on a multi-period segmented sliding window standard deviation, and the method comprises the steps: carrying out the convolution pooling of segmented multi-parameter indexes of current amplitude data of a continuous period, obtaining a data feature value list of the period, and determining a fluctuation range P of equipment operation through calculating the standard deviation of the feature data list; and matching the standard deviation of the measured data after sliding window processing with P, so that equipment fault prediction is carried out, the algorithm is simple and effective, and fault diagnosis of electrical equipment is facilitated.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of electrical equipment under a non-invasive monitoring system, in particular to a fault diagnosis method based on the standard deviation of multi-period segmented sliding windows. Background technique [0002] At present, various electrical appliances are used in the production and operation of enterprises, and electrical appliances may fail during operation, and once a failure occurs, it may cause huge economic losses to the production and operation of the enterprise, and more seriously, it may cause safety hazards . Therefore, producers and operators will think about how to obtain data about equipment failure in advance, give early warning, and achieve the purpose of reducing losses. [0003] At present, equipment fault diagnosis and early warning are generally based on artificial intelligence algorithms; or machine learning algorithms, or deep learning algorithms. For some expensive ...

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): G06F11/07G06F17/16G06F17/15G06F17/18
CPCG06F11/079G06F17/16G06F17/153G06F17/18
Inventor 何金辉宋佶聪王浩磊李哲
Owner SICHUAN CHANGHONG ELECTRIC CO LTD