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

Cable insulation online monitoring method based on KPCA-NSVDD

A cable insulation and cable technology, applied in the field of KPCA-NSVDD-based cable insulation on-line monitoring, can solve problems such as inability to detect cable insulation status, achieve the effect of reducing risks and improving accuracy

Inactive Publication Date: 2021-09-28
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For XLPE cables, the common on-line monitoring methods include partial discharge monitoring, sheath current monitoring, temperature monitoring, etc., but the above methods usually cannot accurately detect the overall insulation state of the cable with a single variable

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
  • Cable insulation online monitoring method based on KPCA-NSVDD
  • Cable insulation online monitoring method based on KPCA-NSVDD
  • Cable insulation online monitoring method based on KPCA-NSVDD

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0062] figure 1 A KPCA-NSVDD-based cable insulation online monitoring method is shown, the overall steps are:

[0063] Step 1: Get the original cable sample data X, X∈R N×M , N represents the number of samples, M represents the number of process variables; including n + positive samples (normal samples) and n - Heterogeneous samples (failure samples), and record the sliding window width as ω - =n + +n - , and the sliding step is s.

[0064] Step 2: Use the KPCA algorithm to perform feature dimensionality reduction and nonlinear principal component extraction on the original cable data;

[0065] Step 3: Use the current window sample after reduction to train the NSVDD model, and find the center a and radius R of the hypersphere to complete the division of the hypersphere space;

[0066] Step 4: Perform data processing on the s s...

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 cable insulation online monitoring method based on KPCA-NSVDD. The cable insulation on-line monitoring method comprises the following steps: firstly, acquiring cable insulation historical data including a small number of fault samples as an original training data set; secondly, in order to solve the problem that high-dimensional data is difficult to process, using kernel principal component analysis (KPCA) for carrying out dimension reduction processing on the data; and then establishing an NSVDD (support vector data description with fault samples) training model by using the training sample, and reflecting the real-time state of cable insulation by using the absolute distance between the real-time sample and the constructed NSVDD hypersphere center. The sliding window mechanism is introduced, the training model can be updated in real time, and the anomaly recognition accuracy is improved. The established model can accurately grasp the behavior rule of normal work of the unit, and the operation state of the overhead line is monitored on line through the established model, so that timely early warning of abnormity is realized.

Description

technical field [0001] The invention relates to the field of cable operation monitoring, in particular to a method for on-line monitoring of cable insulation based on KPCA-NSVDD Background technique [0002] The cross-linked polyethylene (XLPE) cables that are widely used at this stage will have insulation defects due to various abnormal factors such as external mechanical stress damage, environmental corrosion, and internal overvoltage during operation. Therefore, in order to improve the reliability of cable operation, it is necessary to know the cable insulation state in time to discover the deterioration degree of the cable insulation performance. [0003] At this stage, planned maintenance and post-accident maintenance are mainly used for the detection and diagnosis of actual cables and their accessories in operation. However, there are problems such as "excessive" or "not timely" in this detection mode, and the online monitoring method can effectively make up for it. d...

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): G06K9/62G06N20/00
CPCG06N20/00G06F18/213G06F18/2135G06F18/214
Inventor 刘奕玹夏向阳刘雄
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com