Nuclear power plant fault diagnosis method and device and medium thereof

A technology for fault diagnosis and nuclear power plants, applied to instruments, biological neural network models, character and pattern recognition, etc., can solve problems such as inaccurate judgment of fault problems, and achieve the effects of avoiding human errors, accurate fault diagnosis, and ensuring safety

Pending Publication Date: 2022-04-08
NANHUA UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of this application is to provide a nuclear power plant fault diagnosis method, device and its medium, so as to solve the problem that human

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
  • Nuclear power plant fault diagnosis method and device and medium thereof
  • Nuclear power plant fault diagnosis method and device and medium thereof
  • Nuclear power plant fault diagnosis method and device and medium thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0078] In the above description, there is a step of judging whether the established diagnostic model meets the initial requirements. If the diagnostic model does not meet the initial conditions, the diagnostic model needs to be re-established. As for how to judge whether the diagnostic model meets the initial requirements, this embodiment A preferred embodiment is provided, including:

[0079] According to the accuracy of the prediction results of the diagnosis model on the test set data, the cross-entropy loss function and the prediction confusion matrix graph, it is judged whether the diagnosis model meets the initial requirements.

[0080] The calculation method of the accuracy is shown in the following formula:

[0081]

[0082] Among them, acc means accuracy, n 1 Indicates the number of correctly predicted samples, and n indicates the total number of samples.

[0083] The calculation method of the cross-entropy loss function is shown in the following formula:

[008...

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 nuclear power plant fault diagnosis method, a nuclear power plant fault diagnosis device and a medium, and provides a nuclear power plant fault diagnosis method for solving the problems that human errors cannot be avoided by adopting an expert system to assist manual monitoring at present and the judgment on the fault problem which does not occur before is inaccurate, and the method comprises the following steps: obtaining actual working condition data of a nuclear power plant; inputting the actual working condition data into a pre-established diagnosis model; and obtaining a diagnosis result output by the diagnosis model. As the diagnosis result is returned by the diagnosis model after the actual working condition data is input into the diagnosis model, manual participation is not needed, and human errors caused by manual monitoring are avoided. And the accuracy verification is performed on each LSTM model trained by the training set data through the verification set data, and the LSTM model with the highest accuracy is selected as the diagnosis model, so that the diagnosis model also has accuracy guarantee for the unseen data, and the fault diagnosis is more accurate compared with an expert system completely depending on previous artificial experience.

Description

technical field [0001] The present application relates to the technical field of nuclear power plant fault diagnosis, in particular to a nuclear power plant fault diagnosis method, device and medium thereof. Background technique [0002] A nuclear power plant is a complex and huge system consisting of many subsystems, which include many different devices. At the same time, the nuclear power plant has extremely strict safety requirements. Determining the type of failure at one time to take remedial measures, or wrongly judging the type of failure when an accident occurs, may lead to a serious risk of radioactive leakage, which will have a major impact on the physical and mental health of the public. In order to fully grasp the operating status of each system equipment of the nuclear power plant, a large number of sensors are arranged in the entire system equipment to measure parameters such as temperature, pressure, water level, etc., and the manual monitoring is assisted by ...

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): G06K9/62G06N3/04G06N3/12
Inventor 雷济充于涛陈珍平谢金森倪梓宁张华健任长安李卫
Owner NANHUA UNIV
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