project participants
DESCRIPTION
Lessons Learned and Flight Results from the F-15 Intelligent Flight Control System Project John Bosworth Project Chief Engineer February 2006 NASA, Dryden Flight Research Center. Nasa Dryden Flight Research Center Responsible test organization for the flight experiment - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/1.jpg)
1John T. Bosworth – Project Chief Engineer
Lessons Learned and
Flight Results from the
F-15 Intelligent Flight Control System Project John Bosworth
Project Chief Engineer
February 2006NASA, Dryden Flight Research Center
![Page 2: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/2.jpg)
2John T. Bosworth – Project Chief Engineer
Project Participants
• Nasa Dryden Flight Research Center– Responsible test organization for the flight experiment
• Flight, range and ground safety• Mission success
• Nasa Ames Research Center– Development of the concepts
• Boeing STL Phantom Works– Primary flight control system software (Conventional mode)– Research flight control system software (Enhanced mode)
• Institute for Scientific Research – Neural Network adaptive software
• Academia – West Virginia University– Georgia Tech– Texas A&M
![Page 3: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/3.jpg)
3John T. Bosworth – Project Chief Engineer
F-15 IFCS Project Goals
• Demonstrate Revolutionary Control Approaches that can Efficiently Optimize Aircraft Performance in both Normal and Failure Conditions
• Advance Neural Network-Based Flight Control Technology for New Aerospace Systems Designs
![Page 4: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/4.jpg)
4John T. Bosworth – Project Chief Engineer
4
Motivation
These are survivable accidents
IFCS has potential to reduce the amount of skill and luck required for survival
![Page 5: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/5.jpg)
5John T. Bosworth – Project Chief Engineer
IFCS Approach
• Implemented on NASA F-15 #837 (SMTD and ACTIVE projects)
• Use Existing Reversionary Research System
• Limited Flight Envelope
• Failures Simulated by Frozen Surface Command (Stab) or Gain Modification on the Angle of Attack to Canard Feedback
![Page 6: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/6.jpg)
6John T. Bosworth – Project Chief Engineer
Production design P/Y thrust vectoring nozzles
Canards
F100-PW-229 IPE engines with IDEECs
Quad digital flight control computers with research processors and quad digital electronic throttles
ARTS II computer for high computation research control laws
Electronic air inlet controllers
•No mechanical or analog backup•Digital fly-by-wire actuators•Four hydraulic systems
NASA F-15 #837 Aircraft Description
![Page 7: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/7.jpg)
7John T. Bosworth – Project Chief Engineer
Flight Envelope
For Gen 2 Mach < 0.95
![Page 8: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/8.jpg)
8John T. Bosworth – Project Chief Engineer
Limited Authority System• Adaptation algorithm
implemented in separate processor– Class B software– Autocoded directly from
Simulink block diagram– Many configurable settings
• Learning rates• Weight limits• Thresholds, etc.
• Control laws programmed in Class A, quad-redundant system
• Protection provided by floating limiter on adaptation signals
AdaptiveAlgorithm
SafetyLimits
Research Controller4 Channel 68040
Single Channel 400 Mhz
Conventional Controller
![Page 9: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/9.jpg)
9John T. Bosworth – Project Chief Engineer
Max persistence ctr,downmode
NN Floating Limiter
Upper range limit (down mode)
Lower range limit (down mode)
Floating limiter
Rate limit drift, start persistence
counter
Tunable metrics Window delta Drift rate Persistence limiter Range limits
Window size
Sigma pi cmd (pqr)
Black – sigma pi cmdGreen – floating limiter boundaryOrange – limited command (fl_drift_flag)Red – down mode condition (fl_dmode_flag
![Page 10: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/10.jpg)
10John T. Bosworth – Project Chief Engineer
Flight Experiment
• Assess handling qualities of Gen II controller without adaptation
• Activate adaptation and assess changes in handling qualities
• Introduce simulated failures– Control surface locked (“B matrix failure”)– Angle of attack to canard feedback gain change (“A matrix
failure”)• Re-assess handling qualities with simulated failures and
adaptation.• Report on “Real World” experience with a neural network
based flight control system
![Page 11: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/11.jpg)
11John T. Bosworth – Project Chief Engineer
Adaptation Goals
• Ability to suppress initial transient due to failure– Trade-off between high learning rate and stability of
system• Ability to re-establish model following
performance • Ability to suppress cross coupling between axes
– No existing criteria
![Page 12: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/12.jpg)
12John T. Bosworth – Project Chief Engineer
Handling Qualities Performance Metric
• Grey Region:– Based on model-to-
be-followed – Maximum noticeable
dynamics (LOES)
![Page 13: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/13.jpg)
13John T. Bosworth – Project Chief Engineer
Project Phases• Funded
– Gen 1 Indirect adaptive system• Identify changes to “plant”• Adapt controls based on changes• LQR model based controller (online Ricatti solver)
– Gen 2 Direct adaptive• Feedback error drives adaptation changes• Dynamic inversion based controller with explicit model following
• Future Potential– Gen 2+ Different Neural Network approaches
• Single hidden layer, radial basis, etc
– Gen 3 adaptive mixer and adaptive critic
![Page 14: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/14.jpg)
14John T. Bosworth – Project Chief Engineer
Generation 1
Indirect Adaptive System
![Page 15: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/15.jpg)
15John T. Bosworth – Project Chief Engineer
Indirect Adaptive Control Architecture
Pretrained Neural Network
SCE-3SCSI
Sensors
ControlCommands
PilotInputs
PTNNDerivatives
DCSDerivatives
DCSNeuralNetwork
PIDDerivativeEstimation
DerivativeEstimates
DerivativeErrors
+
ARTS II
OpenLoopLearning
ClosedLoopLearning
DerivativeBias
+
+
![Page 16: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/16.jpg)
16John T. Bosworth – Project Chief Engineer
Indirect AdaptiveExperience and Lessons Learned
• System flown in 2003 – Open loop only
• Gain calculation sensitive to identified derivatives– Uncertainty in estimated derivative too high
• Difficult to estimate derivatives from pilot excitation– Normally correlated surfaces – Better estimation available with forced excitation
• Many derivatives required for full plant estimation However more are required when LatDir couples with Long
• No immediate adaptation with failure– Requires period of time before new plant can be identified
• Indirect adaptive might be more suited for clearance of new vehicles rather than failure adaptation
![Page 17: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/17.jpg)
17John T. Bosworth – Project Chief Engineer
Generation 2
Direct Adaptive System
![Page 18: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/18.jpg)
18John T. Bosworth – Project Chief Engineer
pilotinputs
Sensors
ModelFollowing
ControlAllocation
Research Controller
-
Direct AdaptiveNeural Network
+
Gen II Direct Adaptive Control Architecture(Adaptive)
FeedbackError
![Page 19: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/19.jpg)
19John T. Bosworth – Project Chief Engineer
Current Status
• Gen 2 – Currently in flight test phase– Simplified Sigma-Pi neural network
• No higher order terms• Limits on Weights
Qdot_c = Q_err*Kpq*[1 – W1 – W2] + Q_err_int*Kiq*[1 - W1 – W3]
+ Q_err_dot*Kqd*[1 – W1]
![Page 20: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/20.jpg)
20John T. Bosworth – Project Chief Engineer
Effect of Canard Multiplier
A/C Plant
AoACanard
Apparent Plant
Control System
Sym. Stab
Can.Mult.
![Page 21: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/21.jpg)
21John T. Bosworth – Project Chief Engineer
Simulated Canard Failure Stab Open Loop
![Page 22: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/22.jpg)
22John T. Bosworth – Project Chief Engineer
Canard Multiplier EffectClosed Loop Freq. Resp.
![Page 23: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/23.jpg)
23John T. Bosworth – Project Chief Engineer
Simulated Canard Failure Stab Open Loop with Adaptation
![Page 24: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/24.jpg)
24John T. Bosworth – Project Chief Engineer
Canard Multiplier EffectClosed Loop with Adaptation
![Page 25: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/25.jpg)
25John T. Bosworth – Project Chief Engineer-0.5 canard multiplier at flight condition 1; with & without neural networks
![Page 26: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/26.jpg)
26John T. Bosworth – Project Chief Engineer
0 10 20 30 40 50 60 70 80 90 100-1
-0.5
0
0.5
1R
oll A
xis
NN Weights (normalized)-0.5 canard: basic maneuvering card
0 10 20 30 40 50 60 70 80 90 100-1
-0.5
0
0.5
1
Pitc
h A
xis
0 10 20 30 40 50 60 70 80 90 100-1
-0.5
0
0.5
1
Yaw
Axi
s
Gen 2 NN Wts from Simulation
![Page 27: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/27.jpg)
27John T. Bosworth – Project Chief Engineer
Direct AdaptiveExperience and Lessons Learned
• Initial simulation model had high bandwidth– Majority of system performance achieved by the dynamic inversion
controller– Direct adaptive NN played minor role
• Dynamic Inversion gains reduced to meet ASE attenuation requirements – Much harder to achieve desired performance– NN contribution increased
• Initial performance objective emphasized transient reduction and achieving model following after failure– Piloted simulation results showed that reducing cross coupling was
more important objective• Explicit cross terms in NN required for failure cases
– Relying on disturbance rejection alone doesn’t work (also finding of Gen 1)
![Page 28: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/28.jpg)
28John T. Bosworth – Project Chief Engineer
Direct AdaptiveExperience and Lessons Learned
• Liapunov proof of bounded stability– Necessary but not sufficient proof of stability– Many cases of limit cycle behavior observed– Other analytic methods required for ensuring global stability
• Dynamic Inversion controller contributes significantly to cross coupled response in presence of surface failure (locked)– Redesigned yaw loop using classical techniques
• NN’s require careful selection of inputs– Presence of transient errors “normal” for abrupt inputs in non-
adaptive systems– Existence of transient errors tend to drive NN’s to “high gain” trying
to achieve impossible• Significant amount of “tuning” required for to achieve robust full
envelope performance– Contradicts claim of robustness to unforeseen failures– Piloted nonlinear simulation required
![Page 29: Project Participants](https://reader035.vdocument.in/reader035/viewer/2022062315/56815cbc550346895dcabdfe/html5/thumbnails/29.jpg)
29John T. Bosworth – Project Chief Engineer
Conclusions
• Adaptive controls status– Currently collecting “real world” flight experience– Interactions with structure biggest challenge– Fruitful area for future research
• F-15 IFCS project is providing valuable research to promote adaptive control technology to a higher readiness level