Graeme West

An SQL-based approach to similarity assessment within a relational database

A common issue with case-based reasoning (CBR) systems, particularly those that are distributed over a network, is the time required to determine the closest match to the current case. Research has been carried out in this area to try to improve the situation by distributing some of the calculation to the client side thereby reducing the burden on the server. In CBR applications, the case library is stored in some format such as a relational database or flat files that the software interprets in order to perform similarity assessment between the current case and each case in the database. In this paper a novel approach is proposed where the retrieval of the case information and the calculation of the similarity values are performed in one action. This does not incur the same burden upon the server in terms of calculation, as all that is required is a larger database lookup via SQL. As the case base needs to be queried regardless of the CBR technique used to obtain the case information, it is proposed that a combined similarity assessment and case retrieval would provide a fast method of case retrieval.

Data mining reactor fuel grab load trace data to support nuclear core condition monitoring

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.

Industrial implementation of intelligent system techniques for nuclear power plant condition monitoring

As the nuclear power plants within the UK age, there is an increased requirement for condition monitoring to ensure that the plants are still be able to operate safely. This paper describes the novel application of Intelligent Systems (IS) techniques to provide decision support to the condition monitoring of Nuclear Power Plant (NPP) reactor cores within the UK. The resulting system, BETA (British Energy Trace Analysis) is deployed within the UKs nuclear operator and provides automated decision support for the analysis of refuelling data, a lead indicator of the health of AGR (Advanced Gas-cooled Reactor) nuclear power plant cores. The key contribution of this work is the improvement of existing manual, labour-intensive analysis through the application of IS techniques to provide decision support to NPP reactor core condition monitoring. This enables an existing source of condition monitoring data to be analysed in a rapid and repeatable manner, providing additional information relating to core health on a more regular basis than routine inspection data allows. The application of IS techniques addresses two issues with the existing manual interpretation of the data, namely the limited availability of expertise and the variability of assessment between different experts. Decision support is provided by four applications of intelligent systems techniques. Two instances of a rule-based expert system are deployed, the first to automatically identify key features within the refuelling data and the second to classify specific types of anomaly. Clustering techniques are applied to support the definition of benchmark behaviour, which is used to detect the presence of anomalies within the refuelling data. Finally data mining techniques are used to track the evolution of the normal benchmark behaviour over time. This results in a system that not only provides support for analysing new refuelling events but also provides the platform to allow future events to be analysed. The BETA system has been deployed within the nuclear operator in the UK and is used at both the engineering offices and on station to support the analysis of refuelling events from two AGR stations, with a view to expanding it to the rest of the fleet in the near future.

The Use of Hidden Markov Models for Anomaly Detection in Nuclear Core Condition Monitoring

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.

Distributed Data and Information Fusion for Nuclear Reactor Condition Monitoring

An increasing number of civil nuclear reactors world wide are approaching, and have in many cases exceeded, their original design lives. In order to satisfy regulatory requirements and ensure that the reactors are safe to operate, whilst maximizing availability and ensuring economic viability, the volume of installed condition monitoring has increased significantly in recent years. Due to the age of many stations however, there is often the lack of a modern, integrated IT infrastructure with many, often overlapping, data sources of varying measurement types and sample rates. This paper describes a method for the distributed condition monitoring of nuclear reactors using intelligent software agents, which by means of a common ontology can autonomously collect and analyze data from multiple locations. The use of data and information fusion to derive more detailed condition monitoring results is shown to be a task well suited to agent based condition monitoring and a prototype system designed along these principles is described. Case studies are presented of the application of the prototype system to condition monitoring analysis of real data sets from nuclear reactors in the UK.

Machine Learning Model for Event-Based Prognostics in Gas Circulator Condition Monitoring

Gas circulator (GC) units are an important rotating asset used in the advanced gas-cooled reactor design, facilitating the flow of CO

Self-Tuning Routine Alarm Analysis of Vibration Signals in Steam Turbine Generators

_2

Increasing the adoption of prognostic systems for heath management in the power industry

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.

The Influence of the Spatial Distribution of 2-D Features on Pose Estimation for a Visual Pipe Mapping Sensor

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.

A novel visual pipework inspection system

Effective asset management benefits from accurate information about the current health and expected future health of each asset. This information can be supplied by diagnostic and prognostic systems respectively, utilizing data from condition monitoring systems and inspections to derive status and likely future behavior. However, new prognostic techniques can face difficulties when transitioning from research tool to industrial deployment. Within the power industry there are two main drivers to improve asset management. First, the safety of personnel and members of the public may be compromised by a failure in service, so maintenance aims to pre-empt such failures. Secondly, more accurate prediction of future degradation can feed into a more efficient maintenance program, reducing costs through appropriate delay of repair and replacement. These drivers prompt a cautious interest in prognostic tools, countered by some reticence within traditional utilities to adopt new and relatively unproven technologies. This paper identifies issues which may hinder the deployment of prognostic techniques within the power industry. It considers two examples of diagnostic systems (for rotating plant within nuclear stations, and for power transformers) which progressed past the research prototype stage to deployed demonstrator systems, and one example of a prognostic system (for HV circuit breakers) which has not yet made that transition. Drawing lessons from these experiences, the paper extracts key factors which link the deployed systems, but are missing from the third. The paper concludes that structural issues are the main differentiators, including automated access to data, clear and concise user interfaces, and working with the engineers who will ultimately use the system. Trust in the algorithm is also important, and the paper outlines the techniques selected for the case study applications, with discussion of selected results. Once engineers are able to integrate prognostics into their processes, it naturally contributes to asset management strategy.