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

AGC system identification method based on big data and Bayesian neural network

A neural network and system identification technology, applied in the field of AGC system identification based on big data and Bayesian neural network, can solve the problems of big data and retrograde intelligent identification without giving practical guidance, so as to improve the level of automatic control and achieve better results. Recognition accuracy, the effect of improving speed and accuracy

Inactive Publication Date: 2018-12-11
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although there have been studies on neural network and other intelligent algorithm modeling for AGC systems, there is still no practical guidance on how to fully combine power plant big data and retrograde intelligent identification

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
  • AGC system identification method based on big data and Bayesian neural network
  • AGC system identification method based on big data and Bayesian neural network
  • AGC system identification method based on big data and Bayesian neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0082] In order to verify that the AGC system identification method proposed in this application has high identification accuracy and fast convergence speed, the historical operation data of a 1000MW ultra-supercritical unit was collected, and the high-profile gate valve position, feedwater flow rate and total fuel volume were selected as model inputs The actual power, the temperature at the middle point and the main steam pressure are used as the output of the model. 16381 sets of data have been collected, and the sampling interval is 0.01s. The observed input and output curves are as follows: Figure 2-7 shown.

[0083] According to the identification method proposed in this application, after zero initialization, data denoising, normalization and other preprocessing are performed on all data, 1000 sets of data are selected as sample data by using the nearest neighbor method, and the selected sample data curve is as follows Figures 8 to 13 shown. The sampling data other th...

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 relates to an AGC system identification method based on big data and a Bayesian neural network. The method includes: 1, collecting historical data of an AGC system, and obtaining sampledata after preprocessing; 2, initializing a Bayesian neural network; 3, calculating that input and output of each neuron in a hidden layer and an output layer, calculating the difference between the actual output and the output of the Bayesian neural network, and calculating the error according to the MSE standard; 4, judging whether that error meet the requirement or not, if so, carrying out step6, otherwise, correcting the weights and threshold between the output layer and the hidden layer, correcting the weights and thresholds between the input layer and the hidden layer, updating the connection weights, and increasing the learning times by 1; 5, repeating that steps 3 to 4 until the error requirement or the maximum learn times are met; 6, computing the Bayesian neural network and obtaining a mathematical model of identification. Compared with a classic BP neural network identification method, the method has better identification accuracy and faster convergence speed.

Description

technical field [0001] The invention relates to the technical field of information control, in particular to an AGC system identification method based on big data and a Bayesian neural network. Background technique [0002] As of the end of 2017, my country's installed power generation capacity was 1.77 billion kilowatts, and thermal power installed capacity accounted for 62.2% of the total installed capacity. Thermal power is still the main form of power generation in my country. Constraints, the thermal power industry is facing an increasingly severe situation. AGC is an advanced technology in power grid dispatching. Its main task is to realize the closed-loop control between the power grid dispatching automatic energy management system (Energy Management System, referred to as EMS) and the generator set coordination control system (abbreviated as CCS). The rapid development of UHV power grid, AC-DC transmission technology and new energy has increased the complexity of pow...

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): G06K9/62G06N3/08G06Q50/06
CPCG06N3/084G06Q50/06G06F18/24155G06F18/214
Inventor 彭道刚赵慧荣田园园苏烨何钧高升孙宇贞梅兰
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
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