The frequent use of past experience by human engineers when solving ne
w problems has led to an interest in the use of case based reasoning (
CBR) to help automate engineering design. In engineering design it oft
en occurs that many past experiences must be combined to solve a new p
roblem, and thus the process of case based adaptation must efficiently
and systematically combine information from many sources. We have dev
eloped a constraint based methodology for case combination that allows
its application across a wide range of problems. We have shown that o
ur approach provides an efficient adaptation methodology that ensures
convergence upon a solution if one exists, provides a uniform represen
tation of cases, and is generalizable beyond just one domain. Our tech
nique is implemented in a case based reasoning system called COMPOSER,
which has been tested in two design domains: assembly sequence design
and configuration design.