Abstract
Owing to the fact that large-scale peak-load-regulation nuclear power turbine units’ thermal signal is greatly influenced by background noise and has non-stationary and nonlinear characteristics, this paper proposes a new fault diagnosis method for thermal sensors based on an improved independent component analysis (Improved-ICA) algorithm and random forest (RF) algorithm. This method is based on independent component analysis (ICA), which is not capable of extracting components independently. Therefore, we propose the use of the maximum approximate information negative entropy optimization model in order to improve the ICA algorithm’s independent principal component extraction ability and obtain better non-Gaussian physical source signal separation results. The improved ICA algorithm is used for the blind source separation of the thermal parameters of peak-load-regulation nuclear power units. A series of stationary physical source functions and a series of non-stationary noise signals are obtained. Then, according to the specific signal format and data volume of the nuclear power parameter signal, the network parameters of the random forest algorithm are determined, giving rise to the fault diagnosis model. Finally, the real-time operation data of an 1121 MW nuclear power unit are used to complete the training and fault diagnosis of the random forest network and analyze the diagnosis results. The results indicate that the model can effectively mine the abnormal sample points of thermal parameters and classify the fault type of the thermal sensor during peak load operation of the nuclear power unit. The accuracy rate is found to be at the threshold of 99%.
Highlights
China, in recent years, has witnessed the growth of the number of nuclear power units put into operation and their share of power generation
We studied the thermal sensor fault of a large-scale peak-load-regulation nuclear power turbine generator set and propose a new thermal sensor fault diagnosis method based on an improved independent component analysis algorithm and the random forest algorithm
After blind source separation and feature extraction using improved independent component analysis (ICA), the correct rate of the ICA-KNN algorithm for peak load operation increased to 99.8%, while the accuracy rate of data drift fault diagnosis was improved to 100%
Summary
In recent years, has witnessed the growth of the number of nuclear power units put into operation and their share of power generation. In nuclear power units that participate in peak load regulation, their operating parameters deviate from the design values, and the stress, thermal expansion, and thermal deformation of each component of the unit will change. The traditional data mining technology finds it difficult to analyze this kind of data effectively, which impedes the extraction, analysis and diagnosis of fault information. Research on the signal separation technology and feature extraction technology used for the thermal signals of nuclear power units, and obtaining accurate abnormal signals from the monitoring signals, are the basis of sensor fault diagnosis in thermal systems. A recent serious accident was caused by the failure of a thermal sensor. The thermal sensor had a serious precision degradation fault, but
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
