1.
Genoa – Italy – July 16-19, 2012 Centre de recherche sur les Risques et les Crises Integration of a Bayesian network for response planning in a maritime piracy risk management system - Xavier CHAZE - Amal BOUEJLA, Aldo NAPOLI, Franck GUARNIERI Mines ParisTech – CRCIntegration of a Bayesian network for response planning in a maritime piracy risk management system 1/20
2.
French engineering school Research centre (since 2008) French research association (since 1783) (Team created in 1998) (since 1967) Research & training Centre for research on Business creation Risks and Industrial partnerships Strong industrial contacts Crisis Science for engineers, 47 people: 8 Researchers, Management science, 25 PhD Students, Psychology, 3 Engineers + support Computer science, Geography, Law. Develop research, teaching activities, methods and tools. Contribute to strengthen organisations and territories against disturbances.Integration of a Bayesian network for response planning in a maritime piracy risk management system 2/24
3.
Introduction Problem definition Method Results ConclusionSummary Problem definition Issues and context Operational needs Contribution of the SARGOS project Method The Bayesian networks Methodological approach The SARGOS Bayesian network Results Attack scenario case study Integration of the Bayesian Network into the SARGOS systemIntegration of a Bayesian network for response planning in a maritime piracy risk management system 3/20
4.
Introduction Problem definition Method Results ConclusionIntegration of a Bayesian network for response planning in a maritime piracy risk management system 4/20
5.
Introduction Problem definition Method Results ConclusionIssues and context Operational needs Contribution of the SARGOS project • Offshore oil industry represents: • Offshore oil production over 30% of the oil world production 1000 meters from coasts: 27% of the gas world production Mexico Gulf Guinea Gulf • Piracy cost is estimated between 7 and 12 Brasil billiards of US dollars per year. It is mainly due to: Ransom payments • Geographical expansion of Insurance premiums pirate attacks: 2005-2011 Cost of trials and judiciary pursuits Installation of security equipment Source : IFP Énergies Nouvelles • Political issues are also important. Serenity of a whole region can be disturbed: Conflicts between nations when the rig is located in a one country while the company operating the platform is located in another. The legal status of oil rig, the heterogeneity of applicable regulations and the limits of laws and conventions etablished for the fight against piracy.Integration of a Bayesian network for response planning in a maritime piracy risk management system 5/20
6.
Introduction Problem definition Method Results ConclusionIssues and context Operational needs Contribution of the SARGOS project Threat Existing anti-piracy Benefits DIsadvantages treatment tools process Detection of • Poor performance against small targets in medium and large a sea clutter. RADAR systems cooperative vessels • Relatively slow to scan a wide field. Detection of the threat Long-range detection • Disturbed by problems of solar reflectance Optronics surveillance of small targets of the sea. system • Sensitive to the meteorological conditions. Automatic exchange • Messages exchange in a restricted Automatic Identification of messages geographical area. System (AIS) Response against the Intervention towards • Uncertainty of the intervention depending threat Surety and security attackers on the distance between threat and vessel. vessel • Imbalance of arms between attackers and security officers. The solution is to develop a system that can manage the safety of oil fields and provide both suitable protection and effective crisis management.Integration of a Bayesian network for response planning in a maritime piracy risk management system 6/20
7.
Introduction Problem definition Method Results ConclusionIssues and context Operational needs Contribution of the SARGOS project • The SARGOS system (Graduated OffShore Response Alert System) aims to design and develop a comprehensive system that takes into account the whole threat treatment process: Detection of a potential threat Edition of an alert report that lists the significant parameters of threat and target Definition of the response by the planning module of reactions Formalization and implementation of the reaction by the publication of a response plan Fundings Approvements ConsortiumIntegration of a Bayesian network for response planning in a maritime piracy risk management system 7/20
8.
Introduction Problem definition Method Results ConclusionIssues and context Operational needs Contribution of the SARGOS project • Functional outline of the SARGOS system The SARGOS system responds to an alert report with a response plan, which is the result of an intelligent analysis of the alert report.Integration of a Bayesian network for response planning in a maritime piracy risk management system 8/20
9.
Introduction Problem definition Method Results ConclusionThe Bayesian networks Methodological approach The SARGOS Bayesian network Interest • The problem of the response planning against a threat to offshore oil fields exhibits strong constraints: Coordination between the different available counter-attack devices on the field Real-time gradation of the threat and the response adaptation depending on its increase Inherent uncertainty of threat parameters Automatization of the whole process Choice of using the Bayesian networks • A Bayesian network is a model that represents knowledge, and makes it possible to calculate conditional probabilities and provide solutions to various types of problemsIntegration of a Bayesian network for response planning in a maritime piracy risk management system 9/20
10.
Introduction Problem definition Method Results ConclusionThe Bayesian networks Methodological approach The SARGOS Bayesian network Definition & example • Bayesian networks are based on Thomas Bayes theorem (1702-1761) : • Supposed that you live in London and according to your experience, during winter, it rains 50% of the time and it is cloudy 80% of the time. You know, of course, that if it rains, so it is also cloudy. • What is the chance of rain knowing that there are clouds ? • Where: Pl : it rains N : it is cloudy Thus, 62.5% of the time in London during the winter, if it is cloudy, then it is rainyIntegration of a Bayesian network for response planning in a maritime piracy risk management system 10/20
11.
Introduction Problem definition Method Results ConclusionThe Bayesian networks Methodological approach The SARGOS Bayesian network How to construct a bayesian network? • The construction proceeds in 4 steps: Define variables of the problem (nodes) Set the modalities which describe all possible values for each variable Define the connections of the system (links between nodes) Specify the conditional probabilities resulting by the created linksIntegration of a Bayesian network for response planning in a maritime piracy risk management system 11/20
12.
Introduction Problem definition Method Results ConclusionThe Bayesian networks Methodological approach The SARGOS Bayesian network The application to SARGOS Realisation of aaBayesian network Realisation of Bayesian network Datamining learning Brainstorming learning Database of the Expert knowledge from the maritime International Maritime Organisation and safety domains (IMO)Integration of a Bayesian network for response planning in a maritime piracy risk management system 12/20
13.
Introduction Problem definition Method Results ConclusionThe Bayesian networks Methodological approach The SARGOS Bayesian network • Founded the 6th of march 1948, the International Maritime Organization is a specialized institution of United Nations. • On the 15th of July 2011, the database contained 5502 recordings of piracy attacks or armed robbery. • The database contains more information about: The name and the type of the attacked target, Longitude and latitude of the attack location, A textual description of the sequence of events … The Bayesian network constructed from IMO dataIntegration of a Bayesian network for response planning in a maritime piracy risk management system 13/20
14.
Introduction Problem definition Method Results ConclusionThe Bayesian networks Methodological approach The SARGOS Bayesian network • The Bayesian network created from the IMO data made it possible to define: The main tools and protection measures used by a crew, and their effectiveness The probability distributions of using the reactions These results will be integrated into the Bayesian network constructed from the marine community expert knowledge • The construction of the Bayesian network was based on the expert knowledge during many brainstorming sessions. • The prototype was tested and improved by an iterative process to refine the conditional probabilities of the nodes. Expert bayesian network architectureIntegration of a Bayesian network for response planning in a maritime piracy risk management system 14/20
15.
Introduction Problem definition Method Results ConclusionThe Bayesian networks Methodological approach The SARGOS Bayesian network SARGOS Bayesian networkIntegration of a Bayesian network for response planning in a maritime piracy risk management system 15/20
16.
Introduction Problem definition Method Results ConclusionAttack scenario case study Integration of the Bayesian Network into the SARGOS system Attack by an unknown vessel Diagnosis The high-manoeuvrability vessel is now identified against a Floating Production Storage improvement as hostile. The threat is located less than 300 and Offloading unit (FPSO). seconds and 50 metres from the target. T1 T1+t time Increase in the level overall danger Response graduation and adaptationIntegration of a Bayesian network for response planning in a maritime piracy risk management system 16/20
17.
Introduction Problem definition Method Results ConclusionAttack scenario case study Integration of the Bayesian Network into the SARGOS system • The SARGOS reactions planning results in the generation of a response planning report from the intelligent processing of the last issued alert report. Alert Planning Report Bayesian Report (XML) module (XML) • The response plan gathers the necessary information for the physical and chronological execution of the reaction • The interface between the bayesian module and the SARGOS system is completed thanks to JAVA scripts: Input - Identification of a new alert report (XML file) - Extraction of useful information Execution of bayesian module (API BayesiaEngine) -Supply of the Bayesian network (set the observations of source nodes) Output - Export of modalities and resulting probabilities of the Bayesian network - Generation of the graduated suitable response planning report (XML file)Integration of a Bayesian network for response planning in a maritime piracy risk management system 17/20
18.
Introduction Problem definition Method Results ConclusionAttack scenario case study Integration of the Bayesian Network into the SARGOS system • Human-Computer interface of the SARGOS system: once the countermeasures have been selected, they are displayed in the response plan in a specific order.Integration of a Bayesian network for response planning in a maritime piracy risk management system 18/20
19.
Introduction Problem definition Method Results Conclusion • The use of a Bayesian network for the planning of the response is a major asset of the SARGOS system as this network can: Define a graduated response adaptated to the identified threat Take into account the uncertainty of some parameters Manage the real-time situation evolution • Finally, the network is able to integrate feedback from attacks that has previously been used to administer and can therefore evolve. Consequently the planning module can be modified and improved iteratively.Integration of a Bayesian network for response planning in a maritime piracy risk management system 19/20
20.
Thank you for your attention Questions ? Xavier.Chaze@mines-paristech.frIntegration of a Bayesian network for response planning in a maritime piracy risk management system 20/20
Views
Actions
Embeds 0
Report content