Tatiana Kichkaylowith Dave Barnhart and Lucy HoagUSC .ppt

《Tatiana Kichkaylowith Dave Barnhart and Lucy HoagUSC .ppt》由会员分享，可在线阅读，更多相关《Tatiana Kichkaylowith Dave Barnhart and Lucy HoagUSC .ppt（13页珍藏版）》请在麦多课文档分享上搜索。

1、Engineering Design with SPIDR,Tatiana Kichkaylo with Dave Barnhart and Lucy Hoag USC Information Sciences Institute,Background,Funded as ISI Inter-divisional seedlingSpace Engineering Research Center + Artificial Intelligence= Spacecraft Portal for Integrated Design in Real timeDriven by user needs

2、SERC is building satellites, fast, cheap, with student power (“teaching hospital“ model) SPIDR is there to help,Systems Platform for Integrated Design in Real time,Design problem,Spacecraft missions are typically “one-off” designs, requiring high degree of non-recurring engineering between even simi

3、lar design states Spacecraft design is highly interdisciplinary, and follows many sets of constraints and rules dictated by environment, payload and mission setsComponents and design approaches can be reused Engineering knowledge can be encoded to automate many design choices and analysis steps “Pap

4、erless“ design helps directly and also provides basis for further automationUltimately want to let individual engineers bounce ideas of a computer system, leading to faster, cheaper and better designs,Design,Geometry/mass,Power,Thermal,Launch,Orbit,Flight software,Mission goals,Vibration,Component p

5、roviders,Export regulations,Delivery schedules,Manufacturing capabilities,Validation and testing (software and hardware),Payload,What does it take to build a spacecraft?,Bigger picture,Collaborative design Information sharing and clash detection Optimization of parameters Limited number of parameter

6、s but with high fidelity Project management Schedules and resourcesSPIDR Automate roll out and propagation of dependencies Optimize over structures given high-level specification Very lightweight and driven by project needs,Idea: Use planning,AI planning is about finding a sequence (DAG) of actions

7、that achieve a goal Methods have preconditions Methods expand parts of the planDesign is about finding a set of recipes that convert a specification into a complete design Recipes have applicability conditions Recipes modify (expand) designBoth methods and recipes have parameters Both plans and desi

8、gns have constraints Constraints in design are often represented as models,User revises requirements and metrics as needed,Reusable knowledge base of engineering rules,Mission requirements, orbit,N best designs (component lists and system budgets),Reusable component database,Optimization metrics,SPI

9、DR,Reusable data,Mission-specific data,Automated design synthesis,Design loop,Rule example,Semantic entities,Query engine,Variables and constraints,Constraint propagation,Tokens and rules,Planner,Semantic layer,Constraint layer,Planning layer,Data representation,Algorithms,Optimization engine,User i

10、nterface,Implementation,SPIDR meets real world,Nanosatellite project at USC ISI Low costs Unusual constraintsReality alters trajectory Initial “vision“ for SPIDR Single optimization tool with models in the loop Actual use Run every several days with design files (XML etc.) posted online Got several

11、extensions, model tweaked constantly Useful for dealing with ripple effects and ensuring consistency Users want more,Observations,No way to close all loops Extended to dynamic models (e.g., power profile) Stuck on thermal and geometry due to Lack of APIs Licensing issues Need for user interactionOne

12、 shot is not enough need Living Design Feed back from out-of-the-loop models, version control Side-by-side designs Project structure and scheduling roll out Still want the optimization loop,Observations (2),Rule design is not easy Engineers understand the concept Tools help: Eclipse plug-in Crossing

13、 domain boundary is hard Tweaks and overrides encourage local thinking SPIDR Lite to study the knowledge engineering problemOther applications: Trade space studies and tools for acquisition SPIDR-Energy for undersea surveillance (DARPA),Last slide,SPIDR is about rolling out engineering recipes and o

14、ptimizing over high-level structures Glue for collaborative design, optimization, and project management SPIDR is driven by real project(s) Some ambitions got scaled down New extensions and ideas emerged Next steps New engineering domains New applications More users (students?),Tatiana Kichkaylo tatianaisi.edu,