"IGF::OT::IGF" ARTIFICIAL INTELLIGENCE BASED CONTROL POWER OPTIMIZATION ON TAILLESS AIRCRAFT 1 SCOPE THIS P…

Public award description

"IGF::OT::IGF" ARTIFICIAL INTELLIGENCE BASED CONTROL POWER OPTIMIZATION ON TAILLESS AIRCRAFT 1 SCOPE THIS PROJECT INVESTIGATES THE POTENTIAL OF APPLYING ARTIFICIAL INTELLIGENCE METHODS LIKE NEUROCOMPUTING TO THE CONTROL ALLOCATION OPTIMIZATION PROBLEM OF HYBRID WING BODY (HWB) AIRCRAFT CONCEPTS. RESEARCHERS FROM NASA LANGLEY, VIRGINIA TECH, AND BOEING RESEARCH AND TECHNOLOGY WILL EXPLORE THE USE OF ARTIFICIAL NEURAL NETWORKS TO DEVELOP INNOVATIVE CONTROL ALGORITHMS MINIMIZING CONTROL POWER, HINGE MOMENTS, AND ACTUATOR FORCES TO KEEP SYSTEM WEIGHTS WITHIN ACCEPTABLE LIMITS. 2 OBJECTIVES HWB PLATFORMS FEATURE MULTIPLE CONTROL SURFACES, WITH LARGE CONTROL SURFACE GEOMETRIES LEADING TO LARGE HINGE MOMENTS AND HIGH CONTROL POWER DEMANDS. DUE TO THE LARGE NUMBER OF CONTROL SURFACES ON AN HWB, THERE IS NO UNIQUE RELATIONSHIP BETWEEN CONTROL INPUTS AND RESULTING AIRCRAFT RESPONSE, I.E. DIFFERENT COMBINATIONS OF FLAP DEFLECTIONS MAY RESULT IN THE SAME MANEUVER, BUT WITH LARGE DIFFERENCES IN CONTROL POWER. TRADITIONAL METHODS OF CONTROL ALLOCATION OPTIMIZATION HAVE SHOWN DIFFICULTIES IN EXPLOITING THE FULL POTENTIAL OF CONTROLLING A LARGE ARRAY OF CONTROL DEVICES. ARTIFICIAL NEUTRAL NETWORKS (ANN) ARE INSPIRED BY BIOLOGICAL NERVOUS SYSTEMS AND NEUROCOMPUTING HAS SUCCESSFULLY BEEN APPLIED TO A VARIETY OF COMPLEX OPTIMIZATION PROBLEMS. THIS PROJECT WILL EMPLOY A FINITE ELEMENT BASED AEROELASTIC HWB MODEL, BOEING X-48B WIND TUNNEL AND FLIGHT TEST DATA TO DEVELOP A DATABASE THAT CAN BE USED TO DEVELOP AN ARTIFICIAL NEURAL NETWORK (ANN) TO PERFORM CONTROL ALLOCATION OPTIMIZATION FOR TAILLESS AIRCRAFT AT THE CONCEPTUAL DESIGN LEVEL. 3 TASKS 3.1 CONTROL POWER OPTIMIZATION METHODOLOGY BOEING R&T SHALL WORK WITH NASA AND THE PROJECT TEAM TO DEVELOP A METHODOLOGY FOR CONTROL POWER OPTIMIZATION ON TAILLESS AIRCRAFT USING ARTIFICIAL INTELLIGENCE METHODS LIKE NEURAL NETWORKS. IN COLLABORATION WITH THE OTHER MEMBERS OF THE TEAM, BOEING R&T SHALL SUPPORT THE DEVELOPMENT OF AN AEROSERVOELASTIC FINITE ELEMENT REPRESENTATION OF AN HWB SUITABLE FOR CONTROL EFFECTIVENESS ASSESSMENT. 3.2 AEROELASTIC FINITE ELEMENT MODEL BOEING R&T SHALL SUPPORT THE EXTENSION OF THE BASELINE AEROELASTIC FEM MODEL TO A FULL AEROSERVOELASTIC MODEL BY PROVIDING TRAILING EDGE CONTROL SURFACE GEOMETRIES, ACTUATOR DYNAMICS (E.G. STIFFNESS, DAMPING ETC.), MASS PROPERTIES, AND STIFFNESS DISTRIBUTIONS. BOEING R&T SHALL SUPPORT THE DEVELOPMENT OF A BASELINE CONTROL SURFACE DEFLECTION SCHEDULE SUITABLE TO GENERATE A CONTROL SURFACE EFFECTIVENESS DATABASE FOR NEURAL NETWORK TRAINING. 3.3 CALIBRATION AND VALIDATION DATA BOEING R&T SHALL PROVIDE EXPERIMENTAL CONTROL SURFACE EFFECTIVENESS DATA BASED ON WIND TUNNEL OR FLIGHT TESTING TO CALIBRATE AND VALIDATE THE AEROSERVOELASTIC FINITE ELEMENT MODEL. 3.4 DOCUMENTATION AND FEEDBACK BOEING R&T SHALL PROVIDE TECHNICAL EXPERTISE AND ADVISORY FEEDBACK ON THE ENGINEERING APPROACH, MODELING AND ANALYSIS EFFORT, AND FEASIBILITY OF THE OVERALL PROCESS. BOEING R&T SHALL COLLABORATE WITH NASA AND THE OTHER MEMBERS OF THE PROJECT ON WRITING REPORTS AND PRESENTING PAPERS AT APPROPRIATE CONFERENCES AND WORKSHOPS. 3.5 REGULAR STATUS UPDATES BOEING R&T SHALL PARTICIPATE IN REGULAR TELECONFERENCES TO DISCUSS THE STATUS OF ONGOING WORK WITH THE COTR AND OTHER TEAM MEMBERS. THE TELECONFERENCES WILL BE SCHEDULED AS NEEDED. 4 DELIVERABLES THE CONTRACTOR SHALL PROVIDE THE FOLLOWING DELIVERABLES AS OUTLINED IN TABLE 1. THE SPECIFIC WORK ADDRESSED BY EACH DELIVERABLE IS IDENTIFIED BY STATEMENT OF WORK (SOW) PARAGRAPH NUMBER.