Search

The conditions of various nuclear power plant facilities are regularly examined through manual inspections. Remote visual inspection is commonly applied and requires engineers to watch lengthy inspection footage and seek anomaly features therein. This is a labor-intensive process as anomaly features of interest usually only appear in very short segments of the original whole video. Therefore, an automated anomaly detection system is preferred to lessen the intensive labor cost in the inspection process. The detection process could also benefit from useful information that could potentially contribute to addressing reasoning traceability. With a well-prepared training data set of the anomaly feature, a convolutional neural network (CNN) can be developed to automatically detect anomaly indications in the inspection video. However, false-positive detections may occur and can be difficult to remove without seeking manual verification. To overcome this problem, we present a new automated video-level anomaly detection framework that utilizes the latency mechanism to effectively lessen false-positive occurrences, and therefore, increase detection accuracy. In this framework, a CNN-based anomaly classifier first performs initial scanning of the anomaly type of interest in every region of the sampled frames. Then our latency mechanism is applied to refine the initial scanning results by flagging up a region as an "anomaly" indication only when "anomaly" is detected by CNN in the current frame and also in a sequence of previous consecutive frames of the same region. We present a case study of crack feature detection in superheater inspection videos to illustrate the performance of the proposed framework. The results show that the latency mechanism can effectively remove the original false-positive detections seen in the initial scanning. In order to provide a primary exploration of suggesting possible formats for addressing reasoning traceability, knowledge graphs of the reasoning process in the video-level detection framework are built to provide a better understanding of why a specific section of the video is flagged as anomaly contents by the video-level detection framework. [ABSTRACT FROM AUTHOR]

Periodic manual inspection by trained specialists is an important element of asset management in the nuclear industry. Detection of cracks caused by stress corrosion is an important element of remote visual inspection (RVI) in power plant steam generator components such as boilers, superheaters and reheaters. Challenges exist in the interpretation of RVI footage, such as high degree of concentration for reviewing lengthy and disorienting footage due to narrow field of view offered by endoscope. Deep learning is considered useful to automate crack detection process for improved efficiency and accuracy, and has enjoyed success in related applications. This article utilises a new application of automated crack feature detection in steam cycle components to demonstrate a transferrable data-driven framework for a variety of anomaly inspections in such structures. Specifically, a case study of superheater (a type of reactor pressure vessel head) anomaly inspection is presented to automatically detect regions of crack-like features in inspection footage with a good accuracy of 92.97 % using convolutional neural network (CNN), even in challenging cases. Due to the black-box nature of the CNN classification, the explicability of the classification results is discussed to enhance the trustworthiness of the detection system. • Deep learning is useful to support remote visual inspection of pressure vessels at nuclear power plants. • Automated anomaly detection in steam cycle components is showcased through crack-feature inspection in superheaters. • The presented data-driven framework is transferrable for various anomaly inspections in pressure vessel structures. [ABSTRACT FROM AUTHOR]

Gas circulator (GC) units are an important rotating asset used in the advanced gas-cooled reactor design, facilitating the flow of CO$_2$ gas through the reactor core. The ongoing maintenance and examination of these machines are important for operators in order to maintain safe and economic generation. GCs experience a dynamic duty cycle with periods of nonsteady state behavior at regular refueling intervals, posing a unique analysis problem for reliability engineers. In line with the increased data volumes and sophistication of available technologies, the investigation of predictive and prognostic measurements has become a central interest in rotating asset condition monitoring. However, many of the state-of-the-art approaches finding success deal with the extrapolation of stationary time series feeds, with little to no consideration of more complex but expected events in the data. In this paper, we demonstrate a novel modeling approach for examining refueling behaviors in GCs, with a focus on estimating their health state from vibration data. A machine learning model was constructed using the operational history of a unit experiencing an eventual inspection-based failure. This new approach to examining GC condition is shown to correspond well with explicit remaining useful life measurements of the case study, improving on the existing rudimentary extrapolation methods often employed in rotating machinery health monitoring. [ABSTRACT FROM PUBLISHER]

Highlights: [•] Combining laboratory model outputs with operational data. [•] Isolation of single component from noisy data. [•] Better understanding of the health of graphite cores. [•] Extended plant operation through leveraging existing data sources. [ABSTRACT FROM AUTHOR]

This paper presents a self-tuning framework for the diagnosis of routine alarms in steam turbine generators utilizing a combination of inductive machine learning and knowledge-based heuristics. The techniques provide a novel basis for initializing and updating time series feature extraction parameters used in the automated decision support of vibration events due to operational transients. The data-driven nature of the algorithms allows for machine-specific characteristics of individual turbines to be learned and reasoned about. The paper provides a case study illustrating the routine alarm paradigm, and the applicability of systems using self-tuning techniques. The approaches discussed throughout are presented to provide useful diagnosis tools for the reliability and maintenance analysis of steam turbine generators. [ABSTRACT FROM PUBLISHER]

Abstract: A major life-limiting factor of the UK''s Advanced Gas-Cooled Reactors (AGRs) is the condition of the graphite core. Installation of new measurement equipment is difficult and expensive, therefore maximizing the information gained from existing equipment is highly desirable. The main approach to determining the health of an AGR core is through periodic inspections undertaken during planned outages. However, there is the desire to supplement this inspection activity through the analysis of data gathered as part of routine plant operation. One such source of data is measurements taken during refueling and this paper describes knowledge-directed characterization of this refueling data, both spatially across the reactor core and temporally across the operational lifetime of the core. Characterization provides information relating to the current condition of the reactor core and allows suspected ageing trends to be visualized and confirmed. A standard approach for characterizing reactor core data is presented and applied to a variety of different reactor core parameters. The benefit of this approach is that it allows engineers to distill large volumes of refueling data into a readily understandable format in a short period of time. It also allows hypothesized trends relating to the ageing process within the core to be tested and provides supporting evidence for these hypotheses. The trending data is also valuable as it can form the basis of a predictive model of ageing of the reactor core. The ageing process of nuclear graphite is understood from theoretical and experimental viewpoints and this empirical data, gathered from operating reactors, further supports this understanding. This paper represents the initial exploration of using refueling data to construct a predictive model of AGR reactor core ageing. [Copyright &y& Elsevier]

Unplanned outages can be especially costly for generation companies operating nuclear facilities. Early detection of deviations from expected performance through condition monitoring can allow a more proactive and managed approach to dealing with ageing plant. This paper proposes an anomaly detection framework incorporating the use of the Hidden Markov Model (HMM) to support the analysis of nuclear reactor core condition monitoring data. Fuel Grab Load Trace (FGLT) data gathered within the UK during routine refueling operations has been seen to provide information relating to the condition of the graphite bricks that comprise the core. Although manual analysis of this data is time consuming and requires considerable expertise, this paper demonstrates how techniques such as the HMM can provide analysis support by providing a benchmark model of expected behavior against which future refueling events may be compared. The presence of anomalous behavior in candidate traces is inferred through the underlying statistical foundation of the HMM which gives an observation likelihood averaged along the length of the input sequence. Using this likelihood measure, the engineer can be alerted to anomalous behaviour, indicating data which might require further detailed examination. It is proposed that this data analysis technique is used in conjunction with other intelligent analysis techniques currently employed to analyse FGLT to provide a greater confidence measure in detecting anomalous behaviour from FGLT data. [ABSTRACT FROM AUTHOR]

A critical component of an advanced-gas cooled reactor (AGR) station is the graphite core. As a station ages, the graphite bricks that comprise the core can distort and may eventually crack. As the core cannot be replaced the core integrity ultimately determines the station life. Monitoring these distortions is usually restricted to the routine outages, which occur every few years, as this is the only time that the reactor core can be accessed by external sensing equipment. However, during weekly refueling activities measurements are taken from the core for protection and control purposes. It is shown in this paper that these measurements may be interpreted for condition monitoring purposes, thus potentially providing information relating to core condition on a more frequent basis. This paper describes the data-mining approach adopted to analyze this data and also describes a software system designed and implemented to support this process. The use of this software to develop a model of expected behavior based on historical data, which may highlight events containing unusual features possibly indicative of brick cracking, is also described. Finally, the implementation of this newly acquired understanding in an automated analysis system is described. [ABSTRACT FROM AUTHOR]

AbstractIn high-dose radiological environments, where precision and safety are of utmost importance, the ability to acquire accurate and clear visual information is of paramount importance for ensuring safety and reliability in critical industrial processes. However, these environments inherently introduce significant challenges due to the adverse effects of radiation on imaging equipment. As a consequence, inspection videos captured within such high-radiation environments often contain a significant amount of noise. This noise substantially complicates the task of identifying and assessing potential defects in vital components. It also diverts attention and resources toward investigating false positives created by noise, leading to inefficiencies, and for industrial processes on the critical path, this can further prolong the outage. Addressing this noise is essential not only for precision, but also for ensuring safety, reliability, and efficiency in critical industrial processes.In this paper, we present a custom-designed filter utilizing a priori information about camera position and trajectory to remove the noise from the inspection videos, making the defects easier to manually identify. As the camera movement is in one direction at a constant speed, the proposed approach uses this temporal and spatial information to accurately remove the noise. This approach applies to a subset of visual inspection problems throughout the nuclear industry, as well as many other industries where there is knowledge available about the camera speed and direction of travel. The proposed approach is compared with three accepted/well-known approaches, median filtering, bilateral filtering, and fast nonlocal means denoising, and an additional state-of-the-art deep learning model is also used for comparison. It was found that the proposed approach produces the most accurate video denoising in terms of visual quality and the retainment of the defect features throughout the videos tested. [ABSTRACT FROM AUTHOR]

• Automated detection of physical features of interest in fuel channels can save time and reduce the time taken for inspection outages • Automated techniques are robust and repeatable for a given problem removing human subjectivity • Frameworks work very well for both detecting defects and accurately measuring trepanned hole dimensions • Generalisation was shown by testing both frameworks on data sets with imagery recorded from multiple reactors Remote Visual Inspection (RVI) of reactors in nuclear power plants allows station operators to assess the health and condition of their plant. In the UK, most nuclear stations are of the Advanced Gas-cooled Reactor (AGR) design. During planned periodic outages, a representative portion of each AGR core is inspected using specialist tools equipped with various sensors including a video camera for RVI. If cracks are observed in the core during data capture, a stitched image of the region needs to be created so that the crack can be analysed and sentenced (classifying the crack morphology, location, orientation and size) before the station is returned to service, provided return to service is justified. Currently, the crack analysis and sizing activities are conducted manually by expert analysts in a laborious process. In this paper, we present a new image processing approach capable of automating aspects of the crack analysis process. Specifically, we describe a set of techniques for quickly and accurately detecting the presence of cracks in AGR fuel channel inspection images. We also present a method for detecting circular channel features known as trepanned holes whose dimensions are known and can thus be used for scaling. The results of applying the proposed techniques are evaluated on image data from real AGR fuel channels and are shown to produce comparable results to those obtained manually. The advantage of the proposed approach is that it is fast, robust and more repeatable than the existing manual approach. [ABSTRACT FROM AUTHOR]

• Dimensional changes in fuel channels can potentially show signs of defects. • Understanding defects in fuel channels helps support the safety case. • Estimations of dimensional changes can be produced using monitoring data. • Generalization and improved performance was shown using data from multiple reactors. One of the major life-limiting factors of an Advanced Gas-cooled Reactor (AGR) nuclear power station is the graphite core as it cannot be repaired or replaced and therefore detailed information about the health of the core is vital for continued safe operation. The graphite bricks that comprise the core experience gradual degradation during operation as a result of irradiation. Routine physical inspection of the graphite core fuel channels is performed by specialist inspection equipment during outages every 12 months to 3 years. It has also been shown to be advantageous to supplement this periodic inspection information with analysis of operational data which can provide additional insights into the core health. One such approach is through the use of online monitoring data called the Fuel Grab Load Trace (FGLT). An FGLT is a measure of the perceived load of the fuel assembly with contributions from aerodynamic forces and frictional forces, which is related to bore diameter. This paper describes enhancements to existing analysis of FGLT data which, to date, has focussed solely on using data from a single reactor at a time to build bore estimation models, by considering data from multiple reactors to produce a generalised model of bore estimation. This paper initially describes the process of producing a bore estimation from an FGLT by isolating the contribution that relates to the fuel channel bore and then discusses the limitations with the existing bore estimation model. Improvements are then proposed for the bore estimation model and a detailed assessment is undertaken to understand the effect of each of these proposed improvements. In addition, the effect of introducing non-linear regression models to further enhance the bore estimation is explored. The existing model is trained on data from one reactor in the UK and therefore the results produced from it are only applicable to this reactor. However, out of the remaining 13 nuclear reactors currently in operation, 3 also have a similar construction to the reactor the model is trained on, and these should all produce similar FGLT data. Therefore, a generalised model is proposed that produces bore estimations for four AGRs stations reactors, compared with one previously. It is shown that this approach offers an improved overall bore estimation model. [ABSTRACT FROM AUTHOR]