Anomaly detection method for marine nuclear power based on logical distance to characterize safe operation domain

A technology for safe operation and abnormal detection, applied in complex mathematical operations, structured data retrieval, digital data information retrieval, etc., can solve problems such as variable operating conditions, narrow space of ship nuclear power systems, and complex mission profiles, etc. Achieve the effects of adjustable detection strength, good reliability and interpretability, strong pertinence and applicability

Active Publication Date: 2021-09-07
NAVAL UNIV OF ENG PLA
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] Unlike land-based nuclear facilities, marine nuclear power systems have the characteristics of complex mission profiles, variable operating conditions, small space for ship nuclear power systems, and relatively simple safety facilities. The ability to deal with accidents is relatively weak. The reliance on the operator's experience judgment and on-the-spot disposal is also greater. These factors increase the operational safety risk of the marine nuclear power system, and also add additional mental pressure and workload to the operating personnel.

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
  • Anomaly detection method for marine nuclear power based on logical distance to characterize safe operation domain
  • Anomaly detection method for marine nuclear power based on logical distance to characterize safe operation domain
  • Anomaly detection method for marine nuclear power based on logical distance to characterize safe operation domain

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0144] Aiming at the problem of rare and incomplete fault samples in the online detection technology of marine nuclear power system, based on the concept of data-driven, starting from the normal operation data of the system, combined with the characteristics of marine reactors, an anomaly detection algorithm based on the safe operation domain of the system is designed , and based on the logical distance calculation, a system safe operation domain representation function is designed, which is used to monitor the abnormality of the marine nuclear power system online. Finally, the algorithm is verified by numerical experiments under the common operating conditions of the system. The results show that the designed algorithm can effectively detect system anomalies and faults, has good reliability and explainability, and its detection strength can be adjusted.

[0145] Algorithm system design mainly includes five main contents: operation state representation vector design, nuclear po...

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 belongs to the technical field of nuclear power system anomaly detection, and discloses a method for detecting marine nuclear power anomalies based on logical distances to characterize the safe operation domain. By analyzing historical operation data of nuclear power systems, data samples of typical operating conditions of the system are retrieved; construction standards The operating condition sample library selects the characteristic parameters that characterize the operating state; constructs a logical distance calculation function; conducts training and learning, simulation calculations, or inspection and verification of abnormal data samples collected through historical operating data to determine the logical distance threshold for judging system abnormalities, that is, the safety zone Attribution threshold, online detection of system anomalies or retrieval of anomalies in historical system operating data. The invention constructs an abnormality detection model directly from the operating state data of the target nuclear power plant, which is close to the actual system, and has stronger pertinence and applicability than other algorithms from the perspective of mechanism, and has the advantages of strong interpretability, detection strength and adjustment.

Description

technical field [0001] The invention belongs to the technical field of nuclear power system anomaly detection, and in particular relates to a marine nuclear power anomaly detection method based on a logical distance to represent a safe operation domain. Background technique [0002] At present, the automatic detection technology of the abnormal state of the nuclear power system is the front-end entry program module of the system fault diagnosis technology, and it is also the servo technology module to assist the operator on duty. The existing domestic and foreign research on abnormal detection and fault diagnosis technology of nuclear power system can be roughly divided into two categories: mechanism analysis method and data-driven method. [0003] 1) Mechanism analysis anomaly detection method. The mechanism analysis method was developed earlier and is more popular. It is the traditional mainstream method for anomaly detection and fault diagnosis of the current nuclear 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/2458G06F16/28G06F17/15G06F17/16
CPCG06F17/15G06F17/16G06F16/2465G06F16/285
Inventor 王晓龙张永发王昕晔陈玲蔡琦刘忠蒋立志刘小丫
Owner NAVAL UNIV OF ENG PLA
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