Data-driven Sensor Recalibration and Fault Diagnosis in Nuclear Power Plants
Data-driven Sensor Recalibration and Fault Diagnosis in Nuclear Power Plants

Author: Wenqing Yao

Publisher:

Published: 2019

Total Pages:

ISBN-13:

DOWNLOAD EBOOK

This dissertation explores techniques for online monitoring of nuclear power plants, especially pressurized water reactor (PWR) plants, which must have the capabilities to examine and diagnose the health of instrumentation and component, recalibrate faulty sensor measurements, and send maintenance request to the control room. Such techniques will enhance the functionality and reliability of the control and monitoring system and reduce the instrumentation maintenance labor requirement and cost.Two data-driven methods are introduced for sensor recalibration. The first method is recursive adaptive filtering that estimates the plant state parameters from a set of redundant sensor measurements. It corrects the redundant measurements based on the principle of best linear least-squares estimation and also detects and isolates anomalous measurements by adjusting their weights, in real time, based on a sequential log likelihood ratio test of sensor data. The second method is autoregressive support vector regression that is a virtual sensing technique; it predicts unknown measurements without the sensor redundancy. A support vector machine is built by learning from historical time series measurements and uses measurements from other sensors from previous time instants to estimate the current unknown. The feasibility of both approaches is validated with simulation and experimental data for PWR applications.From these perspectives, an online monitoring scheme is proposed to expand the monitoring capabilities for prognosis of sensor and component degradation. A symbolic dynamics modeling method is used to extract statistical features of time series data at the fast time scale and detect sensor and component degradation when the measurements have not shown observable anomalies at a slow time scale. The extracted features have been shown to produce distinguishable patterns between normal and faulty temperature sensor measurements. This dissertation contains detailed descriptions of the proposed algorithms, theoretical evaluations, pertinent results, and an outlook of how the research will be applied in real plants.

Development of a Data Driven Multiple Observer and Causal Graph Approach for Fault Diagnosis of Nuclear Power Plant Sensors and Field Devices
Development of a Data Driven Multiple Observer and Causal Graph Approach for Fault Diagnosis of Nuclear Power Plant Sensors and Field Devices

Author: Ke Zhao

Publisher:

Published: 2002

Total Pages:

ISBN-13:

DOWNLOAD EBOOK

Data driven multiple observer and causal graph approach to fault detection and isolation is developed for nuclear power plant sensors and actuators. It can be integrated into the advanced instrumentation and control system for the next generation nuclear power plants. The developed approach is based on analytical redundancy principle of fault diagnosis. Some analytical models are built to generate the residuals between measured values and expected values. Any significant residuals are used for fault detection and the residual patterns are analyzed for fault isolation. Advanced data driven modeling methods such as Principal Component Analysis and Adaptive Network Fuzzy Inference System are used to achieve on-line accurate and consistent models. As compared with most current data-driven modeling, it is emphasized that the best choice of model structure should be obtained from physical study on a system. Multiple observer approach realizes strong fault isolation through designing appropriate residual structures. Even if one of the residuals is corrupted, the approach is able to indicate an unknown fault instead of a misleading fault. Multiple observers are designed through making full use of the redundant relationships implied in a process when predicting one variable. Data-driven causal graph is developed as a generic approach to fault diagnosis for nuclear power plants where limited fault information is available. It has the potential of combining the reasoning capability of qualitative diagnostic method and the strength of quantitative diagnostic method in fault resolution. A data-driven causal graph consists of individual nodes representing plant variables connected with adaptive quantitative models. With the causal graph, fault detection is fulfilled by monitoring the residual of each model. Fault isolation is achieved by testing the possible assumptions involved in each model. Conservatism is implied in the approach since a faulty sensor or a fault actuator signal is isolated only when their reconstructions can fully explain all the abnormal behavior of the system. The developed approaches have been applied to nuclear steam generator system of a pressurized water reactor and a simulation code has been developed to show its performance. The results show that both single and dual sensor faults and actuator faults can be detected and isolated correctly independent of fault magnitudes and initial power level during early fault transient.

Advanced methods for fault diagnosis and fault-tolerant control
Advanced methods for fault diagnosis and fault-tolerant control

Author: Steven X. Ding

Publisher: Springer Nature

Published: 2020-11-24

Total Pages: 664

ISBN-13: 3662620049

DOWNLOAD EBOOK

The major objective of this book is to introduce advanced design and (online) optimization methods for fault diagnosis and fault-tolerant control from different aspects. Under the aspect of system types, fault diagnosis and fault-tolerant issues are dealt with for linear time-invariant and time-varying systems as well as for nonlinear and distributed (including networked) systems. From the methodological point of view, both model-based and data-driven schemes are investigated.To allow for a self-contained study and enable an easy implementation in real applications, the necessary knowledge as well as tools in mathematics and control theory are included in this book. The main results with the fault diagnosis and fault-tolerant schemes are presented in form of algorithms and demonstrated by means of benchmark case studies. The intended audience of this book are process and control engineers, engineering students and researchers with control engineering background.

NUREG/CR.
NUREG/CR.

Author: U.S. Nuclear Regulatory Commission

Publisher:

Published: 1977

Total Pages: 144

ISBN-13:

DOWNLOAD EBOOK

Data-Driven Design of Fault Diagnosis Systems
Data-Driven Design of Fault Diagnosis Systems

Author: Adel Haghani Abandan Sari

Publisher: Springer Science & Business

Published: 2014-04-22

Total Pages: 149

ISBN-13: 3658058072

DOWNLOAD EBOOK

In many industrial applications early detection and diagnosis of abnormal behavior of the plant is of great importance. During the last decades, the complexity of process plants has been drastically increased, which imposes great challenges in development of model-based monitoring approaches and it sometimes becomes unrealistic for modern large-scale processes. The main objective of Adel Haghani Abandan Sari is to study efficient fault diagnosis techniques for complex industrial systems using process historical data and considering the nonlinear behavior of the process. To this end, different methods are presented to solve the fault diagnosis problem based on the overall behavior of the process and its dynamics. Moreover, a novel technique is proposed for fault isolation and determination of the root-cause of the faults in the system, based on the fault impacts on the process measurements.

Data-Driven Fault Detection and Reasoning for Industrial Monitoring
Data-Driven Fault Detection and Reasoning for Industrial Monitoring

Author: Jing Wang

Publisher: Springer Nature

Published: 2022-01-03

Total Pages: 277

ISBN-13: 9811680442

DOWNLOAD EBOOK

This open access book assesses the potential of data-driven methods in industrial process monitoring engineering. The process modeling, fault detection, classification, isolation, and reasoning are studied in detail. These methods can be used to improve the safety and reliability of industrial processes. Fault diagnosis, including fault detection and reasoning, has attracted engineers and scientists from various fields such as control, machinery, mathematics, and automation engineering. Combining the diagnosis algorithms and application cases, this book establishes a basic framework for this topic and implements various statistical analysis methods for process monitoring. This book is intended for senior undergraduate and graduate students who are interested in fault diagnosis technology, researchers investigating automation and industrial security, professional practitioners and engineers working on engineering modeling and data processing applications. This is an open access book.

Fault Detection and Diagnosis in Industrial Systems
Fault Detection and Diagnosis in Industrial Systems

Author: L.H. Chiang

Publisher: Springer Science & Business Media

Published: 2012-12-06

Total Pages: 281

ISBN-13: 1447103475

DOWNLOAD EBOOK

Early and accurate fault detection and diagnosis for modern chemical plants can minimize downtime, increase the safety of plant operations, and reduce manufacturing costs. This book presents the theoretical background and practical techniques for data-driven process monitoring. It demonstrates the application of all the data-driven process monitoring techniques to the Tennessee Eastman plant simulator, and looks at the strengths and weaknesses of each approach in detail. A plant simulator and problems allow readers to apply process monitoring techniques.

Data-driven Methods for Fault Detection and Diagnosis in Chemical Processes
Data-driven Methods for Fault Detection and Diagnosis in Chemical Processes

Author: Evan L. Russell

Publisher: Springer Science & Business Media

Published: 2012-12-06

Total Pages: 193

ISBN-13: 1447104099

DOWNLOAD EBOOK

Early and accurate fault detection and diagnosis for modern chemical plants can minimise downtime, increase the safety of plant operations, and reduce manufacturing costs. The process-monitoring techniques that have been most effective in practice are based on models constructed almost entirely from process data. The goal of the book is to present the theoretical background and practical techniques for data-driven process monitoring. Process-monitoring techniques presented include: Principal component analysis; Fisher discriminant analysis; Partial least squares; Canonical variate analysis. The text demonstrates the application of all of the data-driven process monitoring techniques to the Tennessee Eastman plant simulator - demonstrating the strengths and weaknesses of each approach in detail. This aids the reader in selecting the right method for his process application. Plant simulator and homework problems in which students apply the process-monitoring techniques to a nontrivial simulated process, and can compare their performance with that obtained in the case studies in the text are included. A number of additional homework problems encourage the reader to implement and obtain a deeper understanding of the techniques. The reader will obtain a background in data-driven techniques for fault detection and diagnosis, including the ability to implement the techniques and to know how to select the right technique for a particular application.

Dynamic Modeling, Sensor Placement Design, and Fault Diagnosis of Nuclear Desalination Systems
Dynamic Modeling, Sensor Placement Design, and Fault Diagnosis of Nuclear Desalination Systems

Author: Fan Li

Publisher:

Published: 2011

Total Pages: 266

ISBN-13:

DOWNLOAD EBOOK

Fault diagnosis of sensors, devices, and equipment is an important topic in the nuclear industry for effective and continuous operation of nuclear power plants. All the fault diagnostic approaches depend critically on the sensors that measure important process variables. Whenever a process encounters a fault, the effect of the fault is propagated to some or all the process variables. The ability of the sensor network to detect and isolate failure modes and anomalous conditions is crucial for the effectiveness of a fault detection and isolation (FDI) system. However, the emphasis of most fault diagnostic approaches found in the literature is primarily on the procedures for performing FDI using a given set of sensors. Little attention has been given to actual sensor allocation for achieving the efficient FDI performance. This dissertation presents a graph-based approach that serves as a solution for the optimization of sensor placement to ensure the observability of faults, as well as the fault resolution to a maximum possible extent. This would potentially facilitate an automated sensor allocation procedure. Principal component analysis (PCA), a multivariate data-driven technique, is used to capture the relationships in the data, and to fit a hyper-plane to the data. The fault directions for different fault scenarios are obtained from the prediction errors, and fault isolation is then accomplished using new projections on these fault directions. The effectiveness of the use of an optimal sensor set versus a reduced set for fault detection and isolation is demonstrated using this technique. Among a variety of desalination technologies, the multi-stage flash (MSF) processes contribute substantially to the desalinating capacity in the world. In this dissertation, both steady-state and dynamic simulation models of a MSF desalination plant are developed. The dynamic MSF model is coupled with a previously developed International Reactor Innovative and Secure (IRIS) model in the SIMULINK environment. The developed sensor placement design and fault diagnostic methods are illustrated with application to the coupled nuclear desalination system. The results demonstrate the effectiveness of the newly developed integrated approach to performance monitoring and fault diagnosis with optimized sensor placement for large industrial systems.