Online and Offline Fault Detection and Diagnostics in a Nuclear
Power Plant Condenser
Ark Ifeanyi
1
, and Jamie Coble
2
1,2
University of Tennessee-Knoxville, Knoxville, TN, 37996, USA
aifeanyi@vols.utk.edu
jamie@utk.edu
ABSTRACT
Nuclear power plants (NPPs) face significant financial pres-
sures due to operational and maintenance costs. This research
investigates Fault Detection and Diagnostics (FDD) techniques
to optimize maintenance schedules and reduce expenses. The
NPP condenser plays a critical role in converting turbine ex-
haust steam back into water for reuse. Condenser tube foul-
ing, a prevalent fault mode, impedes heat transfer efficiency
and can lead to decreased plant efficiency and safety risks.
This study proposes an FDD framework that leverages raw
signal analyses from temperature and pressure monitoring to
detect and diagnose condenser tube fouling in both online and
offline settings. The online approach facilitates close-to-real-
time predictions, enabling proactive maintenance strategies.
Additionally, the framework explores incorporating a con-
denser’s maintenance history for enhanced diagnostics. We
employ a dataset obtained from a simulated nuclear power
plant condenser using the Asherah Nuclear Power Plant Sim-
ulator (ANS). ANS replicates the operational dynamics of
a pressurized water reactor (PWR) type NPP. The proposed
methodology utilizes an encoder-decoder (E-D) structured 1D-
CNN model to analyze the raw signals. The research demon-
strates consistent and accurate fault detection and diagnostics
for condenser tube fouling in both online and offline scenar-
ios. A high potential for generalization to unseen conditions
was observed. However, online detection using small data
windows necessitates caution due to potential false alarms
around the transition points. Our findings pave the way for
further exploration of robust diagnostics by accommodating
a wider spectrum of fouling rates within degradation classes
using ANS. This combined online and offline FDD approach
offers a promising solution for promoting operational safety,
efficiency, and cost-effectiveness in NPP condensers.
Ark Ifeanyi et al. This is an open-access article distributed under the terms of
the Creative Commons Attribution 3.0 United States License, which permits
unrestricted use, distribution, and reproduction in any medium, provided the
original author and source are credited.
1. INTRODUCTION
Fault detection and diagnostics (FDD) are critical compo-
nents of ensuring the safe and efficient operation of complex
systems (Abid et al., 2021). FDD involves the continuous
monitoring and analysis of system parameters to identify de-
viations from normal operating conditions, pinpoint potential
faults, and diagnose their root causes (Ifeanyi, Dos Santos,
et al., 2024). By enabling proactive maintenance and mini-
mizing downtime, FDD plays a pivotal role in enhancing the
reliability and performance of energy systems (Ma & Jiang,
2011).
In the context of a nuclear power plant (NPP), the associated
operational and maintenance expenses represent a significant
financial burden. Even with extended operating licenses, re-
actors are being decommissioned due to their lack of compet-
itiveness against alternative energy sources, leading to early
closures despite their strong safety track record (Walker et
al., 2021). Thus, it is crucial to implement cost-saving mea-
sures to avert these premature shutdowns. The NPP con-
denser stands out as a key component where the implemen-
tation of FDD holds significant implications. The condenser
serves the vital function of converting the steam exiting the
turbine into water for reuse in the steam cycle (Attia, 2015).
Any faults or inefficiencies in the condenser can have cascad-
ing effects on the entire power generation process, leading
to decreased efficiency, increased operational costs, and po-
tential safety risks (Webb, 2011a). One prevalent fault mode
in condenser systems is condenser tube fouling, which oc-
curs when contaminants such as dirt, debris, or biological
growth accumulate on the inner surfaces of the condenser
tubes. Fouling impedes heat transfer efficiency, reducing con-
denser performance and potentially leading to increased tur-
bine backpressure and reduced plant efficiency (Ibrahim &
Attia, 2015).
The objectives of this research include leveraging raw signal
analyses to detect and diagnose faults in the condenser, with a
focus on making close to real-time predictions. Additionally,
this research will investigate the potential of incorporating
1
