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

A Feature Extraction Method Based on Fractional Hilbert Cepstrum

A feature extraction and fractional-order technology, applied to pattern recognition in signals, spectral analysis/Fourier analysis, instruments, etc., can solve problems such as no research and no recognition effect, and achieve high recognition rate and good recognition effect, the effect of improving the recognition accuracy

Active Publication Date: 2022-07-26
NANJING INST OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the characteristics of the electric load are similar, it cannot bring the ideal recognition effect
[0003] Title of prior art document: A non-intrusive load monitoring method based on cepstrum analysis Published to: ("Electronic Technology", 2018, discloses the use of traditional cepstrum analysis to monitor the load of multiple electrical appliances and a single electrical appliance when they are running separately identification, but there is no research on the identification of loads with similar power

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
  • A Feature Extraction Method Based on Fractional Hilbert Cepstrum
  • A Feature Extraction Method Based on Fractional Hilbert Cepstrum
  • A Feature Extraction Method Based on Fractional Hilbert Cepstrum

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be described in detail below with reference to the accompanying drawings.

[0055] as attached figure 1 As shown, a feature extraction method based on fractional Hilbert cepstrum is characterized in that: it comprises the following steps:

[0056] Step 1: Use the preset sampling frequency and sampling time to collect the current data of N different target electricity loads when they operate alone to form a sample set {X 1 ,X 2 ....,X N }, where X is a vector composed of the current data of the target electricity load corresponding to the subscript.

[0057] Step 2: Perform windowing preprocessing on the collected current data of each target power consumption load respectively.

[0058] Step 3: Perform fractional Hilbert transformation on the current data collected by each load on the current data after windowing processing, and map the data of all target loads to the same fractional space; the specific steps include the following:

[0059...

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 specifically relates to a feature extraction method based on fractional Hilbert cepstrum, which includes S1, collecting current data when different electricity loads operate independently; S2, performing windowing preprocessing on the collected current data respectively; S3, pairing The processed current data are respectively subjected to fractional Hilbert transform to map the data to the fractional space; S4, the order of fractional Hilbert transform is optimized to determine the optimal order; S5, under the optimal order, different calculation results are obtained. Cepstral features of the electricity load; S6. Substitute the fractional-order cepstrum features of different electricity loads under the optimal order into the support vector machine for load identification, and obtain the recognition rates of different electricity loads. The fractional-order cepstral feature proposed by the invention effectively improves the identification rate of different electricity loads, and has a better classification effect when the load features are similar.

Description

technical field [0001] The invention relates to a non-invasive load feature extraction method, in particular to a feature extraction method based on fractional Hilbert cepstrum. Background technique [0002] Non-intrusive Load Monitoring (NILM) technology can obtain refined user internal load category and usage status data by decomposing and identifying the user's total load data, which is an effective way to solve the problem of intelligent power load monitoring. way. Non-intrusive load monitoring does not require the installation of load monitoring devices on the user side or a substantial upgrade and transformation of smart meters. It relies on the data acquisition device and communication network of the existing electricity consumption information acquisition system, and adopts advanced data communication technology to obtain refined user data. Electric load data, and then use the powerful data processing capability of the power cloud platform to run a more complex and ...

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 Patents(China)
IPC IPC(8): G06K9/00G06N3/00G01R23/16
CPCG06N3/006G01R23/16G06F2218/10
Inventor 邵琪包永强姜家辉陆志文贾成宇景凌啸
Owner NANJING INST OF TECH