TY - CHAP A1 - Weidl, Galia T1 - ADAPTIVE RISK ASSESSMENT IN COMPLEX LARGE SCALE PROCESSES WITH REDUCED COMPUTATIONAL COMPLEXITY T2 - 9th International Conference on Industrial Engineering Theory, Applications & Practice, November 27-30, 2004 N2 - We have developed a methodology that targets risk assessment for process operation. It includes both abnormality prediction and evaluation of its development, provided no corrective actions are taken, as well as a possibility to examine the impact of intended actions. It handles the uncertainties in the domain and the big number of influences on the effect variables by utilizing causal probabilistic modeling. The process is modeled by Hidden Markov Models (HMM), and object oriented dynamic Bayesian networks (OOBNs). Various modeling techniques and assumptions have been used to reduce the computational complexity and ensure fast inference. The methodology is applied in a case study. KW - Adaptive Risk Management KW - Hidden Markov Models KW - HMM KW - OOBN KW - Bayesian Networks KW - Prozessmodell Y1 - 2004 UR - http://www.orsnz.org.nz/conf39/ProgramSummary.pdf ER - TY - CHAP A1 - Weidl, Galia A1 - Madsen, Anders L. A1 - Dahlquist, Erik T1 - Applications of object-oriented Bayesian networks for causal analysis of process disturbances T2 - SIMS'2003 (44th International Conference of the Scandinavian Simulation Society) N2 - We discuss a hybrid approach for causal analysis of disturbances in industrial process operation. It represents a combination of OOBN with first level diagnostic packages and physical models serving as agents in the system design and providing evidence for automated reasoning on abnormality in process operation. The aim is causal analysis of non-measurable disturbances as a decision advice complement to the distributed control system (DCS). The approach includes prediction of signals' level-trend development, risk assessment for disturbance analysis and predictive maintenance on demand. The methodology has been applied on a screening process with a pressure-flow network in a Pulp Mil. KW - OOBN KW - DCS KW - Bayesian Networks KW - Prozessmodell KW - Prozesssteuerung Y1 - 2003 UR - https://www.researchgate.net/publication/228679172_Applications_of_object-oriented_Bayesian_networks_for_causal_analysis_of_process_disturbances#fullTextFileContent ER - TY - CHAP A1 - Weidl, Galia A1 - Madsen, Anders L. A1 - Dahlquist, Erik T1 - Object Oriented Bayesian Networks for Industrial Process Operation T2 - Proceedings of the first Bayesian Application Modeling Workshop at the 19th Conference in Uncertainty in Artificial Intelligence, 2003 N2 - We present an application, where extensions of existing methods for decision-theoretic troubleshooting are used for industrial process operation and asset management. The extension includes expected average cost of asset management actions, prediction of signals' level-trend development, risk assessment for disturbance analysis and predictive maintenance on demand. KW - Bayesian Networks KW - OOBN KW - Prozesssteuerung Y1 - 2003 UR - https://www.researchgate.net/publication/2942492_Object_Oriented_Bayesian_Networks_for_Industrial_Process_Operation#fullTextFileContent ER - TY - JOUR A1 - Weidl, Galia A1 - Madsen, Anders L. A1 - Dahlquist, Erik T1 - Condition Monitoring, Root Cause Analysis and Decision Support on Urgency of Actions JF - Book Series FAIA (Frontiers in Artificial Intelligence and Applications), Soft Computing Systems - Design, Management and Applications N2 - We discuss the use of a hybrid system utilizing Object Oriented Bayesian networks and influence diagrams for probabilistic reasoning under uncertainties in industrial process operations. The Bayesian networks are used for condition monitoring and root cause analysis of process operation. The recommended decision sequence of corrective actions and observations is obtained following the "myopic" approach. The BN inference on most probable root cause is used in an influence diagram for taking decisions on urgency of corrective actions vs. delivery deadline. The build-in chain of causality from root cause to process faults can provide the user with explanation facility and a simulation tool of the effect of intended actions. KW - OOBN KW - Bayesian Networks KW - Prozesssteuerung KW - Prozessanalyse Y1 - 2002 UR - https://www.researchgate.net/publication/228719447_Condition_Monitoring_Root_Cause_Analysis_and_Decision_Support_on_Urgency_of_Actions#fullTextFileContent VL - 2002 IS - 87 SP - 221 EP - 230 ER -