Data-driven power sensor error online evaluation closed-loop improvement method, system and medium

A power sensor and data-driven technology, applied in the direction of measuring electrical variables, instruments, measuring devices, etc., can solve the problems of poor generalization of deduction methods and inaccurate deduction results, so as to improve the accuracy of deduction results and achieve efficient methods Safety, generalization-enhancing effects

Active Publication Date: 2022-03-11
STATE GRID HUNAN ELECTRIC POWER +2
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Technical problem to be solved by the present invention: Aiming at the deficiencies of the existing open-loop measurement error deduction technology, a data-driven closed-loop improvement method, system and medium for online evaluation of electric quantity sensor errors are provided. The present invention adopts a closed-loop operation method to realize electric quantity Online sensor error evaluation does not require on-site testing, does not need to change the topology of the physical system, does not affect the physical operation, and at the same time can solve the problem of poor generalization of the open-loop measurement error deduction method and inaccurate deduction results to a certain extent. Effectively improve the accuracy of the deduction results, improve the generalization of the deduction model, and have the advantages of efficient and safe implementation methods without affecting the physical system

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
  • Data-driven power sensor error online evaluation closed-loop improvement method, system and medium
  • Data-driven power sensor error online evaluation closed-loop improvement method, system and medium
  • Data-driven power sensor error online evaluation closed-loop improvement method, system and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] like figure 1 As shown, the implementation steps of the data-driven online evaluation closed-loop improvement method for electric quantity sensor error in this embodiment include:

[0049] 1) Initialize the number of iterations n and the number of error deduction Q;

[0050] 2) Create the sensor data correction model set S of the nth iteration n ;

[0051] 3) Synchronously collect the sensing data of the power sensor group according to the time series and generate the sensing data set DATA;

[0052] 4) Correct the model set S according to the sensing data of the nth iteration n Generating the sensor data correction coefficient set A after the nth iteration n , modify the coefficient set A according to the sensing data n Generate correction data set DATA'(n) with sensing data set DATA;

[0053] 5) Update the value of the error derivation times Q, and perform power sensor error deduction on the corrected data set DATA'(n) according to the open-loop data-driven algor...

Embodiment 2

[0106] This embodiment is basically the same as Embodiment 1, and the main difference is that the sensing data correction model in this embodiment is a PID-like correction model, and its function expression is shown in the following formula:

[0107]

[0108] In the above formula, S Ln Represents the PID-like correction model of the nth iteration of any L-th power sensor, E Ln E L(n-1) It is the result of the n-1th error deduction model implemented by the Lth power sensor error deduction model, K a 、K b 、K c is the PID coefficient, n is the number of iterations, and m is the iterative evolution scale of the modified model. In this embodiment, the PID-like coefficient K is set a =5,K b =0.1,K c = 0.5. In particular, when n=0, S Ln =1. image 3 For this embodiment, based on the PID-like correction model, the closed-loop iterative derivation of the gradual change process of the measurement error, image 3 It can also be seen that the more the number of iterations, t...

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 data-driven electric quantity sensor error online evaluation closed-loop improvement method, system and medium. The invention includes creating an n-th iterative electric quantity sensing data correction model set; collecting electric quantity sensing data to generate a sensing data set; According to the power sensor data correction model set, the power sensor data correction coefficient set after the nth iteration is generated, and the power sensor data set is corrected to generate a correction data set; the power sensor error will be carried out on the correction data set according to the open-loop data-driven algorithm Deduction forms the deduction result; if the end condition is not satisfied, update the number of iterations n and the power sensor data correction model, and continue to iterate after accumulating the power sensor data correction coefficient set; otherwise, output the iteration result. The invention does not require on-site tests, does not need to change the topology of the physical system, does not affect the physical operation, can effectively improve the accuracy of the deduction results, improve the generalization of the deduction model, achieve high efficiency and safety, and does not affect the physical system.

Description

technical field [0001] The invention relates to an error evaluation method for an electric quantity sensor during operation, in particular to a data-driven electric quantity sensor error online evaluation closed-loop improvement method, system and medium. Background technique [0002] Sensors are an important device for measuring physical parameters and a key medium connecting the physical world and the information world. With the continuous development and wide application of big data, the Internet of Things, and 5G communication technologies, the demand for cyber-physical fusion is increasing, and the role of the basic structure of sensor networks is becoming more and more important. Its reliability and accuracy directly determine the effectiveness of the cyber-physical fusion process. , need to carry out error evaluation. Especially for power sensors, which involve trade settlement, safety protection and other purposes, they are measuring instruments that are mandatory f...

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): G01R35/04
CPCG01R35/04
Inventor 李恺陈向群谈丛谭海波解玉满杨方黄红桥周宇烨卜文彬王海元
Owner STATE GRID HUNAN ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap