%0 Journal Article %1 Matthews:2006:AIEDAM %A Matthews, Peter C. %A Standingford, David W. F. %A Holden, Carren M. E. %A Wallace, Ken M. %D 2006 %I Cambridge University Press %J Artificial Intelligence for Engineering Design, Analysis and Manufacturing %K Data Design Elicitation, GP-HEM, Induction, Knowledge Metamodels Mining, Model SVM, algorithms, demes genetic programming, %P 1--18 %R doi:10.10170S089006040606001X %T Learning inexpensive parametric design models using an augmented genetic programming technique %V 20 %X Previous applications of genetic programming (GP) have been restricted to searching for algebraic approximations mapping the design parameters e.g., geometrical parameters, to a single design objective e.g., weight. In addition, these algebraic expressions tend to be highly complex. By adding a simple extension to the GP technique, a powerful design data analysis tool is developed. This paper significantly extends the analysis capabilities of GP by searching for multiple simple models within a single population by splitting the population into multiple islands according to the design variables used by individual members. Where members from different islands 'cooperate', simple design models can be extracted from this cooperation. This relatively simple extension to GP is shown to have powerful implications to extracting design models that can be readily interpreted and exploited by human designers. The full analysis method, GP heuristics extraction method, is described and illustrated by means of a design case study.

@article{Matthews:2006:AIEDAM, abstract = {Previous applications of genetic programming (GP) have been restricted to searching for algebraic approximations mapping the design parameters e.g., geometrical parameters, to a single design objective e.g., weight. In addition, these algebraic expressions tend to be highly complex. By adding a simple extension to the GP technique, a powerful design data analysis tool is developed. This paper significantly extends the analysis capabilities of GP by searching for multiple simple models within a single population by splitting the population into multiple islands according to the design variables used by individual members. Where members from different islands 'cooperate', simple design models can be extracted from this cooperation. This relatively simple extension to GP is shown to have powerful implications to extracting design models that can be readily interpreted and exploited by human designers. The full analysis method, GP heuristics extraction method, is described and illustrated by means of a design case study.}, added-at = {2008-06-19T17:35:00.000+0200}, author = {Matthews, Peter C. and Standingford, David W. F. and Holden, Carren M. E. and Wallace, Ken M.}, biburl = {https://www.bibsonomy.org/bibtex/2b791a20285e194c8e76ae8b970c00e72/brazovayeye}, doi = {doi:10.10170S089006040606001X}, interhash = {39a0f8f5bc7b504c2333d3d5719fa107}, intrahash = {b791a20285e194c8e76ae8b970c00e72}, journal = {Artificial Intelligence for Engineering Design, Analysis and Manufacturing}, keywords = {Data Design Elicitation, GP-HEM, Induction, Knowledge Metamodels Mining, Model SVM, algorithms, demes genetic programming,}, notes = {School of Engineering, University of Durham, Durham, United Kingdom BAE Systems, Advanced Technology Centre, Filton, Bristol, United Kingdom Aerodynamic Methods and Tools, Airbus UK, Filton, Bristol, United Kingdom Engineering Design Centre, Engineering Department, University of Cambridge, Cambridge, United Kingdom Flat screen design.}, pages = {1--18}, publisher = {Cambridge University Press}, size = {18 pages}, timestamp = {2008-06-19T17:46:28.000+0200}, title = {Learning inexpensive parametric design models using an augmented genetic programming technique}, volume = 20, year = 2006 }