Comprehensive energy system fault risk early warning method based on RelieF-softmax algorithm

A technology that integrates energy systems and failure risks, applied in computing, resources, computer components, etc., can solve problems that threaten the safe and stable operation of electrical systems, the possibility of system failures, and the reduction of gas units, so as to improve classification performance and correlate The effect of small sex and cost reduction

Pending Publication Date: 2022-04-26
国网浙江省电力有限公司平阳县供电公司 +5
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the integrated energy system is the same as the distribution network. The grid structure is complex, the coverage is wide, and the types of equipment are various and miscellaneous. The factors affecting its stable operation will increase, and the possibility of system failure will also increase.
Taking the gas grid system as an example, after the large-scale introduction of natural gas into the system, the coupling between the electrical and gas systems has been enhanced, and at the same time, the reliability of the system has become increasingly prominent.
For example, random failures such as leakage of natural gas pipelines and interruption of gas source supply may lead to a rapid reduction in the output of gas-fired units due to insufficient supply of natural gas, thereby threatening the safe and stable operation of the electrical 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
  • Comprehensive energy system fault risk early warning method based on RelieF-softmax algorithm
  • Comprehensive energy system fault risk early warning method based on RelieF-softmax algorithm
  • Comprehensive energy system fault risk early warning method based on RelieF-softmax algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The present invention will be further described below in conjunction with the accompanying drawings.

[0066] refer to Figure 1 to Figure 4 , a comprehensive energy system failure risk early warning method based on the RelieF-softmax algorithm, the method comprising the following steps:

[0067] S1: Build an integrated energy system model.

[0068] S2: Preprocessing the fault characteristic data, data preprocessing includes 4 steps of data cleaning, data transformation, data integration and abnormal sample data elimination.

[0069] S3: Use the improved RelieF algorithm to filter features according to their ability to distinguish distance between samples, select some features from the original data set to construct an optimal feature subset, so that it can describe the original sample space.

[0070] S4: The basis for the failure risk level of the integrated energy system mainly includes two parts: the frequency of failures (failure rate per 100 kilometers) and the c...

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 an integrated energy system fault risk early warning method based on a RelieF-softmax algorithm. The method comprises the following steps: constructing an integrated energy system model; preprocessing the fault feature data; utilizing a RelieF algorithm to screen features according to the far-near distinguishing capability of the features to sample distances; fault risk grade prediction is carried out by taking the fault occurrence frequency and the number and range of residents influenced by the fault occurrence as the basis of fault risk grade division; and adopting a RelieF-softmax algorithm to carry out fault risk early warning on the integrated energy system. According to the method, serious consequences caused by misclassification high-risk faults can be effectively avoided, and the cost caused by prediction error bands is reduced.

Description

technical field [0001] The invention relates to a comprehensive energy system fault risk early warning method based on the RelieF-softmax algorithm. Background technique [0002] In recent years, in order to solve the problems of shortage of non-renewable energy such as oil and coal traditionally used for power generation, serious environmental pollution, etc., and realize my country's strategic goal of "carbon peaking and carbon neutrality" as soon as possible, many scholars have successively proposed the concept of integrated energy system . The integrated energy system optimizes the combination of different energy systems such as traditional power grids, natural gas grids, and heat grids, and uses advanced information network technology and communication technology to realize the coupling of multiple energy systems and promote the efficient use of energy and equipment. [0003] However, the integrated energy system is the same as the distribution network. The grid structu...

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): G06Q10/06G06Q50/06G06K9/62
CPCG06Q10/0635G06Q50/06G06F18/23213G06F18/2415
Inventor 叶清泉林厚飞金建新廖鸿图冯昌森施亦治林达支秉忠陈伟章玮姜衍张扬洪彬峰邓宝华龚瑛王万焕
Owner 国网浙江省电力有限公司平阳县供电公司
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