Nuclear power plant fault diagnosis method and device and medium thereof

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 ...

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 errors cannot be avoided and the faults that have not occurred before are not judged accurately in the current method of expert system assisted manual monitoring

Images