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

Comprehensive energy supply service station oil gas recovery system fault detection method oriented to data scarce scene

An oil and gas recovery system, data-oriented technology, applied in data processing applications, neural learning methods, instruments, etc., can solve the problems of lack of historical fault samples, inability to detect timely and effectively, insufficient sample size of a single oil gun system for modeling, etc. , to achieve the effect of improving accuracy and ensuring safe and reliable operation

Pending Publication Date: 2022-06-07
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the scenarios where the oil and gas recovery system of the comprehensive energy supply service station lacks historical fault samples in the daily operation process, the sample size of a single oil gun system is not enough to model, and the traditional instrument monitoring method cannot timely and effectively detect A fault detection method for the oil and gas recovery system of an integrated energy supply service station is proposed for data-scarce scenarios.

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 supply service station oil gas recovery system fault detection method oriented to data scarce scene
  • Comprehensive energy supply service station oil gas recovery system fault detection method oriented to data scarce scene
  • Comprehensive energy supply service station oil gas recovery system fault detection method oriented to data scarce scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention provides a fault detection method for an oil and gas recovery system of a comprehensive energy supply service station oriented to a data scarcity scenario, the method comprising the following steps:

[0033] Collect the variable data of the oil and gas recovery process of the oil and gas recovery system of the integrated energy supply service station;

[0034] Calculate the membership degrees of the current oil and gas recovery process variable data to K categories; the K categories are obtained by dividing the oil and gas recovery process variable data set based on the historical normal operation of the oil and gas recovery system of the comprehensive energy supply service station;

[0035] Based on the K trained unsupervised anomaly detection models, the anomaly scores of the current oil and gas recovery process variable data for each category are calculated; the K unsupervised anomaly detection models are based on the historical normal operation ...

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 scarcity scene-oriented comprehensive energy supply service station oil gas recovery system fault detection method. In order to solve the data scarcity problems of no historical fault samples, unbalanced samples among multiple devices and the like in an oil gas recovery system of a comprehensive energy supply service station, firstly, a clustering method is used for clustering normal data with similar distribution in all the devices into the same sample cluster, so that a small number of modeling samples of the original single device are expanded; the problem of sample imbalance among multiple devices is effectively solved; and then an unsupervised fault detection model is established based on each sample cluster, and a reconstruction error of a fault sample can be amplified in combination with an auto-encoder and a generative adversarial thought, so that the fault detection precision and sensitivity are effectively improved under the condition of no historical fault data. According to the method, the fault detection precision and sensitivity can be effectively enhanced under the scene of sample imbalance among multiple devices and no historical fault data, and a foundation is laid for safe and reliable operation and intelligent operation and maintenance of an oil gas recovery system of an energy supply station.

Description

technical field [0001] The invention belongs to the field of industrial process fault detection, and is oriented to industrial scenarios with scarce data such as no historical fault samples and unbalanced samples among multiple devices, especially for fault detection of an oil and gas recovery system of an integrated energy supply service station. Background technique [0002] The comprehensive energy supply service station is a new type of all-round, multi-functional and intelligent public infrastructure service facilities for transportation and energy. Cultural publicity, information consultation and other public services. It has the characteristics of many access devices, a wide range of service objects, and a large amount of information. Therefore, it is of great significance to develop comprehensive energy intelligent operation and maintenance and fault early warning and diagnosis technology and build a safety assessment model for key equipment at the site to improve s...

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): G06K9/62G06N3/04G06N3/08G06Q10/00G06Q50/06
CPCG06N3/088G06Q10/20G06Q10/30G06Q50/06G06N3/045G06F18/23213G06F18/2431Y02P90/82
Inventor 赵春晖王应龙常树超
Owner ZHEJIANG UNIV
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