Evolutionary and Adaptive Synthesis Methods

Lee, Cin-Young; Ma, Lin; Antonsson, Erik K.

doi:10.1017/cbo9780511529627.011

Cited by 8 publications

(2 citation statements)

References 127 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by nature's evolution process, genetic algorithm (Goldberg, 1989) and genetic programming (Koza, 1992) have been established to model problems using bit string (genetic algorithm) or functional tree (genetic programming) genes and to solve problems by evolving the best solution(s) from a population through reproduction, mutation, recombination, natural selection, and survival of fitness. This approach has been taken to solve various engineering problems, including design optimization, configuration design, and design automation (Koza, 1992; Fogel et al, 1996; Parmee, 1997; Bentley, 1999; Koza et al, 1999; Bonnie & Malaga, 2000; Lee et al, 2001; Maher, 2001; Vajna & Clement, 2002; Fan et al, 2003). In addition to direct encoding where genotype codes map to the phenotypes directly, recently researchers have explored indirect coding method, called computational embryogeny (Kumar & Bentley, 2000), to evolve rules that build or develop corresponding phenotypes (Yogev & Antonsson, 2007).…”

Section: Related Workmentioning

confidence: 99%

Cellular self-organizing systems: A field-based behavior regulation approach

Jin

Chen

2014

AIEDAM

View full text Add to dashboard Cite

Multiagent systems have been considered as a potential solution for developing adaptive systems. In this research, a cellular self-organizing (CSO) approach is proposed for developing such multiagent adaptive systems. The design of CSO systems however is difficult because the global effect emerges from local actions and interactions that are often hard to specify and control. In order to achieve high-level flexible and robustness of CSO systems and retain the capability of specifying desired global effects, we propose a field-based regulative control mechanism, called field-based behavior regulation (FBR). FBR is a real-time, dynamical, distributed mechanism that regulates the emergence process for CSO systems to self-organize and self-reconfigure in complex operation environments. FBR characterizes the task environment in terms of “fields” and extends the system flexibility and robustness without imposing global control over local cells or agents. This paper describes the model of CSO systems and FBR, and demonstrates their effectiveness through simulation-based case studies.

show abstract

Section: Related Workmentioning

confidence: 99%

Cellular self-organizing systems: A field-based behavior regulation approach

Jin

Chen

2014

AIEDAM

View full text Add to dashboard Cite

show abstract

“…Broadly, the existing approaches to conceptual design focus on formulating a set of design rules that need to be satisfied [1,2], on interactive (and iterative) specialized design approaches, such as knowledge-based reasoning, and on applying various search techniques -typically "analysis in the loop" type approaches based on generate and test paradigms -to find a single feasible solution for the design problem [3]. While the more recent solution search techniques, such as "path finding", "constraint satisfaction", "simulated annealing", "genetic algorithms" and various shape optimization techniques [4,5], are becoming more popular, they typically lead to single designs with fully specified geometries. Configuration spaces (C-spaces) have been shown to be a convenient representation of the design space for parts moving in contact because the C-spaces explicitly capture the motion constraints imposed by the relative motion, as discussed, for example, in [6,7,8,9].…”

Section: Motivationmentioning

confidence: 99%

Equivalence Classes for Shape Synthesis of Moving Mechanical Parts

Ilieş

Shapiro

2004

Journal of Computing and Information Science in Engineering

View full text Add to dashboard Cite

Moving parts in contact have been traditionally synthesized through specialized techniques that focus on completely specified nominal shapes. Given that the functionality does not completely constrain the geometry of any given part, the design process leads to arbitrarily specified portions of geometry, without providing support for systematic generation of alternative shapes satisfying identical or altered functionalities. Hence the design cycle of a product is forced to go into numerous and often redundant iterative stages that directly impact its effectiveness.We argue that the shape synthesis of mechanical parts is more efficient and less error prone if it is based on techniques that identify the functional surfaces of the part without imposing arbitrary restrictions on its geometry. We demonstrate that such techniques can be formally defined for parts moving in contact through equivalence classes of mechanical parts that satisfy a given functionality. We show here that by replacing the completely specified geometry of the traditional approaches with partial geometry and functional specification, we can formally define classes of mechanical parts that are equivalent, in the sense that all members of the class satisfy the same functional specifications. Moreover, these classes of functionally equivalent parts are computable, may be represented unambiguously by maximal elements in each class, and contain all other functional designs that perform the same function.

show abstract

Artificial intelligence for design process improvement

Brown

2005

Design Process Improvement

View full text Add to dashboard Cite

Evolutionary and Adaptive Synthesis Methods

Cited by 8 publications

References 127 publications

Cellular self-organizing systems: A field-based behavior regulation approach

Cellular self-organizing systems: A field-based behavior regulation approach

Equivalence Classes for Shape Synthesis of Moving Mechanical Parts

Artificial intelligence for design process improvement

Contact Info

Product

Resources

About