Download presentation
Presentation is loading. Please wait.
Published byElmer Flynn Modified over 9 years ago
1
DDRE/DTU AUGUST 2007 1 Decision Support System for Fighter Pilots Lars Rosenberg Randleff Danish Defence Research Establishment / Technical University of Denmark
2
DDRE/DTU AUGUST 2007 2 Agenda Project Description The Four Approaches Prolog Bayesian Net Integer Programming Metaheuristics Comparing Approaches Conclusion
3
DDRE/DTU AUGUST 2007 3 Agenda Project Description The Four Approaches Prolog Bayesian Net Integer Programming Metaheuristics Comparing Approaches Conclusion
4
DDRE/DTU AUGUST 2007 4 Hostile Environment
5
DDRE/DTU AUGUST 2007 5 Project Description To explorer a number of technologies within AI and OR that may be used in designing a DSS for fighter pilots. The DSS is to be used in finding a response to ground based threats.
6
DDRE/DTU AUGUST 2007 6 Requirements Real-time Hardware Updateable Trustworthy Useful User Interface
7
DDRE/DTU AUGUST 2007 7 Agenda Project Description The Four Approaches Prolog Bayesian Net Integer Programming Metaheuristics Comparing Approaches Conclusion
8
DDRE/DTU AUGUST 2007 8 A Prolog Example %----------------- % Find appropriate countermeasures. %----------------- proper_cm(Angle, jammer) :- ( warning(rwr, (Angle, _)), warning(mws, (Angle, _)), jammer_mode(auto) );( warning(rwr, (Angle, _)), warning(mws, (DiffAngle, _)), Angle \== DiffAngle );( warning(rwr, (Angle, _)), not(warning(mws, (_, _))) ). ”When the jammer is jamming it may influence the RWR and jammers of other aircraft.” “When the jammer is in 'auto' mode, it will jam the RF sources detected.” If the MWS indicates a missile in a given direction, and the RWR does not, the missile is IR guided.
9
DDRE/DTU AUGUST 2007 9 Some Results ”Use flares, chaff, jammer, or towed decoy. Do not use chaff to counter SA-5 and SA-10. Use jammer in auto mode.”
10
DDRE/DTU AUGUST 2007 10 Agenda Project Description The Four Approaches Prolog Bayesian Net Integer Programming Metaheuristics Comparing Approaches Conclusion
11
DDRE/DTU AUGUST 2007 11 The Bayesian Net
12
DDRE/DTU AUGUST 2007 12 Semi-automatic Population Excel MATLAB desc. MATLAB prog. HUGIN Text file
13
DDRE/DTU AUGUST 2007 13 Structural Learning Fly-In HUGIN (SL) Text file Log file Perl Text file
14
DDRE/DTU AUGUST 2007 14 Some Results
15
DDRE/DTU AUGUST 2007 15 Agenda Project Description The Four Approaches Prolog Bayesian Net Integer Programming Metaheuristics Comparing Approaches Conclusion
16
DDRE/DTU AUGUST 2007 16 Parameters α ρ
17
DDRE/DTU AUGUST 2007 17 Lethality ScenarioLethality
18
DDRE/DTU AUGUST 2007 18 Deployment Scheme Jammer Decoy Chaff
19
DDRE/DTU AUGUST 2007 19 Reduction of Lethality (α)
20
DDRE/DTU AUGUST 2007 20 Reduction of Lethality (ρ)
21
DDRE/DTU AUGUST 2007 21 Deployment Phases IIIIIIIVV Time OtOt AtAt
22
DDRE/DTU AUGUST 2007 22 Constraints I Time OtOt AtAt Ot’Ot’ O t ’’ T start T end
23
DDRE/DTU AUGUST 2007 23 Constraints II Time AtAt T start OtOt CtCt
24
DDRE/DTU AUGUST 2007 24 Constraints III Time OtOt AtAt Ot’Ot’ O t ’’ T start T end
25
DDRE/DTU AUGUST 2007 25 Scenarios sc1sc2sc3sc4sc5sc6
26
DDRE/DTU AUGUST 2007 26 Running Time
27
DDRE/DTU AUGUST 2007 27 Results
28
DDRE/DTU AUGUST 2007 28 Agenda Project Description The Four Approaches Prolog Bayesian Net Integer Programming Metaheuristics Comparing Approaches Conclusion
29
DDRE/DTU AUGUST 2007 29 Three Metaheuristics Steepest Ascent Local Search Simulated Annealing
30
DDRE/DTU AUGUST 2007 30 Parameters in SA Algorithm Cooling Schedule Start Temperature End Temperature Acceptance Stopping Criteria Objective Function Neighbourhood Initial Solution
31
DDRE/DTU AUGUST 2007 31
32
DDRE/DTU AUGUST 2007 32 Results
33
DDRE/DTU AUGUST 2007 33 Comparing Metaheuristics
34
DDRE/DTU AUGUST 2007 34 Agenda Project Description The Four Approaches Prolog Bayesian Net Integer Programming Metaheuristics Comparing Approaches Conclusion
35
DDRE/DTU AUGUST 2007 35 Comparing Approaches I Prolog is easy to use, and easy to model BN is not categorical; it treats probabilities IP ensures the optimal solutions; but is too slow for a real-time DSS A metaheuristic will not necessarily give an optimal solution; but it will find a solution fast
36
DDRE/DTU AUGUST 2007 36 Comparing Approaches II Prolog Bayesian Net Mathematical Model Metaheuristic
37
DDRE/DTU AUGUST 2007 37 Agenda Project Description The Four Approaches Prolog Bayesian Net Integer Programming Metaheuristics Comparing Approaches Conclusion
38
DDRE/DTU AUGUST 2007 38 Conclusion Four approaches to a DSS for fighter pilots have been implemented All approaches have pros and cons None of the approaches fulfil all requirements More research may find the best technology for developing a DSS for fighter pilots
39
DDRE/DTU AUGUST 2007 39 Decision Support System for Fighter Pilots Lars Rosenberg Randleff Danish Defence Research Establishment / Technical University of Denmark
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.