A method for detecting sensor anomalies in nuclear power plants
By combining principal component analysis with Bayesian long short-term memory neural networks, the accuracy and reliability issues of sensor anomaly detection in nuclear power plants have been resolved. This has enabled efficient anomaly detection, reduced false alarms and missed alarms, and improved the accuracy and reliability of sensor detection in nuclear power plants.
CN122087628APending Publication Date: 2026-05-26SUZHOU NUCLEAR POWER RES INST CO LTD
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SUZHOU NUCLEAR POWER RES INST CO LTD
- Filing Date
- 2025-12-16
- Publication Date
- 2026-05-26
Smart Images
Figure CN122087628A_ABST
Abstract
This invention provides a method for detecting sensor anomalies in nuclear power plants. The method includes: constructing a principal component analysis model, calculating the Q-statistic, and determining a first threshold; training a Bayesian long short-term memory neural network model and calibrating its prediction interval; calculating a second and third threshold based on the predicted value and uncertainty output by the calibrated model; inputting test data into the two models to obtain the Q-statistic, predicted value, and uncertainty, and comparing them with the corresponding thresholds to obtain three judgment results; and making a final judgment on the three results using a logical judgment table. This invention integrates spatiotemporal characteristics and uncertainty assessment, achieving high-precision and high-reliability sensor anomaly detection with only normal operating data, exhibiting high reliability and robustness.
Need to check novelty before this filing date? Find Prior Art