MEMS design synthesis: integrating case-based reasoning and multi-objective genetic algorithms

Cobb, Corie L.; Ying, Zhang; Agogino, Alice M.

doi:10.1117/12.695609

Cited by 10 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These include but are not restricted to: conceptual design [64], component based design [22], classical shape [35], sizing [56,60] and topological [57,62] design optimisation, multi-disciplinary [65], multi-objective [21,22], and multi-level design optimisation [14,27], hybrid genetic algorithms [62], robust design [60], interactive evolutionary algorithms [57], and case-based reasoning [61]. The bulk of work performed on MEMS through natural computing has focused on, predominantly, multi-objective evolutionary algorithms [21,22].…”

Section: Evolutionary Design Optimisationmentioning

confidence: 99%

An efficient evolutionary multi-objective framework for MEMS design optimisation: validation, comparison and analysis

et al. 2011

View full text Add to dashboard Cite

The application of multi objective evolutionary algorithms (MOEA) in the design optimisation of microelectromechanical systems (MEMS) is of particular interest in this research. MOEA is a class of soft computing techniques of biologically inspired stochastic algorithms, which have proved to outperform their conventional counterparts in many design optimisation tasks. MEMS designers can utilise a variety of multi-disciplinary design tools that explore a complex design search space, however, still follow the traditional trial and error approaches. The paper proposes a novel framework, which couples both modelling and analysis tools to the most referenced MOEAs (NSGA-II and MOGA-II). The framework is validated and evaluated through a number of case studies of increasing complexity. The research presented in this paper unprecedentedly attempts to compare the performances of the mentioned algorithms in the application domain. The comparative study shows significant insights into the behaviour of both of the algorithms in the design optimisation of MEMS. The paper provides extended discussions and analysis of the results showing, overall, that MOGA-II outperforms NSGA-II, for the selected case studies.

show abstract

Section: Evolutionary Design Optimisationmentioning

confidence: 99%

An efficient evolutionary multi-objective framework for MEMS design optimisation: validation, comparison and analysis

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Drawing from the MEMS design component library, an initial valid design or a set of designs is loaded into the MOGA process. The initial design(s) can be provided by the designer (Zhang et al, 2005) or recommended by a MEMS case-based reasoning tool (Cobb et al, 2006). MOGA then makes many strongly mutated copies of the initial design(s) to produce the first generation for the GA process.…”

Section: Mogas For Mems Designmentioning

confidence: 99%

Hierarchical component-based representations for evolving microelectromechanical systems designs

Ying

Agogino

2010

AIEDAM

Self Cite

View full text Add to dashboard Cite

In this paper we present a genotype representation method for improving the performance of genetic-algorithm-based optimal design and synthesis of microelectromechanical systems. The genetic algorithm uses a hierarchical component-based genotype representation, which incorporates specific engineering knowledge into the design optimization process. Each microelectromechanical system component is represented by a gene with its own parameters defining its geometry and the way it can be modified from one generation to the next. The object-oriented genotype structures efficiently describe the hierarchical nature typical of engineering designs. They also encode knowledge-based constraints that prevent the genetic algorithm from wasting time exploring inappropriate regions of the search space. The efficiency of the hierarchical component-based genotype representation is demonstrated with surface-micromachined resonator designs.

show abstract

“…Previous work [8] has shown that the integration of a CBR knowledge base with a multi-objective genetic algorithm (MOGA) can increase the number of optimal solutions generated for a given MEMS design problem. CBR is used to help select the best candidates to be evolved in an evolutionary process such as MOGA.…”

Section: B Purpose Of Resonance and Vibrationmentioning

confidence: 99%

“…In one experiment [8], for each MOGA synthesis run, we used a population of 400 for 50 generations. Each constraint case of (1) no symmetry, (2) ysymmetry, and (3) xy-symmetry had 5 runs of the MOGA process in order to see a good spread of designs.…”

Section: A Creating Evolutionary Linkage With Cbrmentioning

confidence: 99%

“…Zhang et al [5], [6] implemented a hierarchical MEMS synthesis and optimization architecture, using a component-based genotype representation and two levels of optimization: global genetic algorithms (GA) and local gradient-based refinement. Cobb et al [7] created a case-based reasoning (CBR) tool to serve as an automated knowledge base for the synthesis of MEMS resonant structures, integrating CBR with MOGA [8] to select promising initial designs for MOGA and to increase the number of optimal design concepts presented to MEMS designers.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Case-based reasoning and object-oriented data structures exploit biological analogs to generate virtual evolutionary linkages

Cobb

Zhang

Agogino

et al. 2007

2007 IEEE Congress on Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

Multiobjective Genetic Algorithms (MOGA) andCase-based Reasoning (CBR) have proven successful in the design of MEMS (Microelectromechanical Systems) suspension systems. Object-oriented data structures of primitive and complex genetic algorithm (GA) elements have been developed to restrict genetic operations to produce feasible design combinations as required by physical limitations or practical constraints. Thus, virtual linkage between genes and chromosomes are coded into the properties of pre-defined GA objects. A new design problem requires selecting the right primitive elements, associated data structures, and linkages that promise to produce the best gene pool for new functional requirements. In this paper, biomimetics is proposed as a means to examine and classify functional requirements so that case-based reasoning algorithms can be used to map design requirements to promising initial conceptual designs and appropriate GA primitives. The concept is demonstrated using micro-mechanical resonators.

show abstract

MEMS design synthesis: integrating case-based reasoning and multi-objective genetic algorithms

Cited by 10 publications

References 10 publications

An efficient evolutionary multi-objective framework for MEMS design optimisation: validation, comparison and analysis

An efficient evolutionary multi-objective framework for MEMS design optimisation: validation, comparison and analysis

Hierarchical component-based representations for evolving microelectromechanical systems designs

Case-based reasoning and object-oriented data structures exploit biological analogs to generate virtual evolutionary linkages

Contact Info

Product

Resources

About