摘要详情

ID / 提交时间

4 / 2024-05-11 11:08:50

标题

Research on Nuclear Power Sensor Failure Detection Method Based on Autoencoder and Random Forest

关键字

Nuclear Power Sensor; Failure Detection; KPCA; Autoencoder; Random Forest

主题及专题

TRACK 2: OPERATION & PERFORMANCE

状态

终稿

作者

Jiarong Gao / Harbin Engineering University

Yongkuo Liu / Harbin Engineering University

Xin Ai / Harbin Engineering University

Longfei Shan / Harbin Engineering University

Qiang Zhao / Harbin Engineering University

摘要

Sensors are essential detection components in nuclear power instrumentation and control systems. Their proper functioning plays a crucial role in the operation of nuclear power systems and equipment. Sensor failures may lead to inaccurate detection data and delayed identification of nuclear system or equipment malfunctions. Based on this premise, this paper conducts research on the failure detection method of nuclear power sensors. Firstly, using the simulation platform of the PCtran, historical operational data of sensors under both steady-state and transient conditions are collected to establish a dataset for sensor failure detection. Then, based on this dataset, the SPE statistical contribution rate of the autoencoder, and the fault detection and final location result is obtained. Finally, the random forest algorithm is used to diagnose the fault type of the sensor. Experimental analysis demonstrates that the proposed method effectively detects nuclear power sensor failures with high accuracy.