Cover -- Supervision and Safety of Complex Systems -- Title Page -- Copyright Page -- Table of Contents -- Foreword -- Foreword -- Introduction -- PART 1. INDUSTRIAL ISSUES -- Chapter 1. Safety and Performance of Electricity Production Facilities -- Chapter 2. Monitoring of Radioactive Waste Disposal Cells in Deep Geological Formation -- 2.1. Context -- 2.2. Monitoring of the environment -- 2.3. Monitoring of geological repository structures -- 2.4. Conclusion and perspectives -- Chapter 3. Towards Fourth-generation Nuclear Reactors -- 3.1. Context -- 3.2. Surveillance and acoustic detection -- 3.3. Inspection during operation -- 3.3.1. The case of acoustic measurements -- 3.4. Conclusion -- PART 2. SUPERVISION AND MODELING OF COMPLEX SYSTEMS -- Chapter 4. Fault-tolerant Data-fusion Method: Application on Platoon Vehicle Localization -- 4.1. Introduction -- 4.2. Review -- 4.3. Bayesian network for data fusion -- 4.3.1. Bayesian network and Kalman filter -- 4.4. Localization of a single vehicle: multisensor data fusion with a dynamic Bayesian network -- 4.4.1. Presentation of the approach developed -- 4.4.2. Inference in switching Kalman filter -- 4.4.3. Detailed synopsis of the method based on Bayesian networks -- 4.4.4. Example of management of multi-hypotheses by a Bayesian network -- 4.4.5. Illustration of the map localization method using SKF -- 4.5. Multi-vehicle localization -- 4.5.1. The problem studied -- 4.5.2. Communication within the convoy -- 4.5.3. Sensors used on each vehicle in the convoy -- 4.5.4. Bayesian network for the localization of a chain of vehicles -- 4.5.5. Extension of the approach: modeling and localization of a chain of vehicles -- 4.5.6. The issue with this model -- 4.5.7. New model for the localization of a chain of vehicles -- 4.5.8. Proportional commands -- 4.5.9. Functional analysis of models of the convoy.

4.6. Conclusions and perspectives -- 4.7. Bibliography -- Chapter 5 Damage and Forecast Modeling -- 5.1. Introduction -- 5.1.1. Operational level -- 5.1.2. Strategic level -- 5.2. Preliminary study of data -- 5.2.1. Structure of the database -- 5.2.2. Performance criterion for the prognostic -- 5.2.3. Definition of a deterioration indicator -- 5.3. Construction of the deterioration indicator -- 5.3.1. Study of the failure space with PCA -- 5.3.2. Damage indicator defined as a distance -- 5.4. Estimation of the residual life span (RUL) -- 5.4.1. Simple approach based on the life span -- 5.4.2. Stochastic deterioration model -- 5.5. Conclusion -- 5.6. Bibliography -- Chapter 6. Diagnosis of Systems with Multiple Operating Modes -- 6.1. Introduction -- 6.2. Detection of faults for a class of switching systems -- 6.2.1. Introduction -- 6.2.2. Structure of the residual generator and observer design -- 6.2.3. Simulation and results -- 6.2.4. Conclusions -- 6.3. Analytical method to obtain a multiple model -- 6.3.1. Introduction -- 6.3.2. Setting the problem -- 6.3.3. Transformation in multiple-model form -- 6.3.4. Conclusion -- 6.4. Detection of switching and operating mode recognition without the explicituse of model parameters -- 6.4.1. Introduction -- 6.4.2. Diagnosis of SSs with linear modes -- 6.4.3. Diagnosis of a switching system with uncertain nonlinear modes -- 6.4.4. Conclusions -- 6.5. Modeling, observation and monitoring of switching systems: application toa multicellular converter -- 6.5.1. Introduction -- 6.5.2. Multicellular converter with two arms or four quadrants -- 6.5.3. Diagnosing faults in the four quadrant converter -- 6.5.4. Experimental benchmark for validation -- 6.6. Bibliography -- Chapter 7. Multitask Learning for the Diagnosis of Machine Fleet -- 7.1. Introduction -- 7.2. Single-task learning of one-class SVM classifier.

7.3. Multitask learning of 1-SVM classifiers -- 7.3.1. Formulation of the problem -- 7.3.2. Dual problem -- 7.4. Experimental results -- 7.4.1. Academic nonlinear example -- 7.4.2. Analysis of textured images -- 7.5. Conclusion -- 7.6. Acknowledgments -- 7.7. Bibliography -- Chapter 8. The APPRODYN Project: Dynamic Reliability Approaches to Modeling Critical Systems -- 8.1.Context and aims -- 8.1.1.Context -- 8.1.2. Objectives -- 8.2. Brief overview of the test case -- 8.2.1. General remarks -- 8.2.2. Functional description -- 8.2.3. Modeling the process -- 8.2.4. Modeling command logic -- 8.2.5. Reliability data and state graphs -- 8.2.6. Ageing -- 8.2.7. Sensors -- 8.3. Modeling using a stochastic hybrid automaton approach -- 8.3.1. Main concepts and references -- 8.3.2. What is a stochastic hybrid automaton? -- 8.3.3. Structuring and synchronization approach -- 8.3.4. Modeling the case study -- 8.3.5. Qualitative and quantitative results -- 8.3.6. Conclusion and perspectives for the stochastic hybrid automaton approach -- 8.4. Modeling using piecewise deterministic Markov processes -- 8.4.1. Principles and references -- 8.4.2. What is a piecewise deterministic Markov process? -- 8.4.3. Modeling the test case -- 8.4.4. Modeling the VVP -- 8.4.5. Modeling CEX -- 8.4.6. Qualitative and quantitative results -- 8.4.7. Conclusion and perspectives for the piecewise deterministic Markov processes and simulation approach -- 8.5. Modeling using stochastic Petri nets -- 8.5.1. Principles and references -- 8.5.2. What is a stochastic Petri net? -- 8.5.3. Modeling framework -- 8.5.4. Qualitative and quantitative results -- 8.5.5. SPN approach: conclusions and perspectives -- 8.6. Preliminary conclusion and perspectives -- 8.7. Bibliography.

PART 3. CHARACTERIZING BACKGROUND NOISE, IDENTIFYING CHARACTERISTIC SIGNATURES IN TEST CASES AND DETECTING NOISE REACTORS -- Chapter 9. Aims, Context and Type of Signals Studied -- Chapter 10. Detection/Classification of Argon and Water Injections into Sodium into an SG of a Fast Neutron Reactor -- 10.1. Context and aims -- 10.2. Data -- 10.3. Online (sequential) detection-isolation -- 10.3.1. Formulating the practical problem -- 10.3.2. Formulating the statistical problem -- 10.3.3. Non-recursive approach -- 10.3.4. Recursive approach -- 10.3.5. Practical algorithm -- 10.3.6. Experimental results -- 10.4. Offline classification (non-sequential) -- 10.4.1. Characterization and approach used -- 10.4.2. Initial characterization -- 10.4.3. Effective features -- 10.4.4. Classification -- 10.4.5. Performance evaluation -- 10.4.6. Experimental results -- 10.5. Results and comments -- 10.6. Conclusion -- 10.7. Bibliography -- Chapter 11. A Dynamic Learning-based Approach to the Surveillance and Monitoring of Steam Generators in Prototype Fast Reactors -- 11.1. Introduction -- 11.2. Proposed method for the surveillance and monitoring of a steam generator -- 11.2.1. Learning and classification -- 11.2.2. Detecting the evolution of a class -- 11.2.3. Adapting a class after validating its evolution and creating a new class -- 11.2.4. Validating classes -- 11.2.5. Defining the parameters of the SS-DFKNN method -- 11.3. Results -- 11.3.1. Data analysis -- 11.3.2. Classification results -- 11.3.3. Designing an automaton to improve classification rates -- 11.4. Conclusion and perspectives -- 11.5. Bibliography -- Chapter 12. SVM Time-Frequency Classification for the Detection of Injection States -- 12.1. Introduction -- 12.2. Preliminary examination of the data -- 12.2.1. Approach -- 12.2.2. Spectral analysis of the data -- 12.2.3. Class visualization.

12.3. Detection algorithm -- 12.3.1. SVM implementation -- 12.3.2. Algorithm calibration -- 12.4. Role of sensors -- 12.5. Experimental results -- 12.6. Bibliography -- Chapter 13. Time and Frequency Domain Approaches for the Characterization of Injection States -- 13.1. Introduction -- 13.1.1. Framework of the study -- 13.1.2. Processing recordings -- 13.1.3. Identifying the injection zones -- 13.1.4. Extraction of "non-injection" zones -- 13.2. Analyzing the statistical properties of spectral power densities -- 13.2.1. Methodology -- 13.2.2. Results -- 13.2.3. Exploring implementation in a new installation -- 13.3. Analysis of the filtering characteristics -- 13.3.1. Estimating filtering characteristics using an AR model -- 13.3.2. Comparing filtering characteristics -- 13.3.3. A leak detection algorithm -- 13.3.4. Conclusions on the autoregressive signal modeling-based approach -- 13.4. Conclusion on frequential and temporal approaches -- 13.5. Bibliography -- PART 4. HUMAN, ORGANIZATIONAL AND ENVIRONMENTAL FACTORS IN RISK ANALYSIS -- Chapter 14. Risk Analysis and Management in Systems Integrating Technical, Human, Organizational and Environmental Aspects -- 14.1. Aims of the project -- 14.2. State of the art -- 14.2.1. Context of the study -- 14.2.2. Towards an "integrated" approach to risk: combining several specialist disciplines -- 14.3. Integrated risk analysis -- 14.3.1. Concepts -- 14.3.2. A description of the approach -- 14.4. Accounting for uncertainty in risk analysis -- 14.4.1. Different kinds and sources of uncertainty -- 14.4.2. Frameworks for modeling uncertainty -- 14.5. Modeling risk for a quantitative assessment of risk -- 14.5.1. Bayesian networks -- 14.5.2. Evaluating risk beyond a probabilistic framework -- 14.6. Conclusions and future perspectives -- 14.7. Bibliography.

Chapter 15. Integrating Human and Organizational Factors into the BCD Risk Analysis Model: An Influence Diagram-based Approach.