Domain-specific initial population strategy for compliant mechanisms using customized genetic algorithm

Sharma, Deepak; Deb, Kalyanmoy; Kishore, Nanda

doi:10.1007/s00158-010-0575-x

Cited by 40 publications

(22 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The global search and optimization is done using NSGA-II [27]. These algorithms have successfully been used for structure topology optimization earlier [12,14,15,17,25]. The flow chart of the hybrid NSGA-II algorithm is shown in Fig.…”

Section: Hybrid Genetic Algorithmmentioning

confidence: 99%

“…In this methodology, a closeness between the paths cannot be ensured and may find a solution generating its actual path far from the desired path. This problem leads to the motivation to develop a formulation wherein a constraint is imposed at each precision point such that a gap between the paths can be controlled [12].…”

Section: Minimizementioning

confidence: 99%

“…Most of the above studies combine the multiple objectives into a single objective optimization problem. On the other hand, solving single objective optimization problem as multi-objective optimization can introduce adequate diversity in GA, thereby enhancing the chance of finding good new solutions with generations [12,25,26].…”

Section: Introductionmentioning

confidence: 99%

“…The major drawback of GA is large computation time. But, it can be reduced by performing function evaluations in parallel [12,13].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Generation of Compliant Mechanisms using Hybrid Genetic Algorithm

Sharma

Deb

2014

J. Inst. Eng. India Ser. C

View full text Add to dashboard Cite

Compliant mechanism is a single piece elastic structure which can deform to perform the assigned task. In this work, compliant mechanisms are evolved using a constraint based bi-objective optimization formulation which requires one user defined parameter (g). This user defined parameter limits a gap between a desired path and an actual path traced by the compliant mechanism. The non-linear and discrete optimization problems are solved using the hybrid Genetic Algorithm (GA) wherein domain specific initialization, two-dimensional crossover operator and repairing techniques are adopted. A bit-wise local search method is used with elitist non-dominated sorting genetic algorithm to further refine the compliant mechanisms. Parallel computations are performed on the masterslave architecture to reduce the computation time. A parametric study is carried out for g value which suggests a range to evolve topologically different compliant mechanisms. The applied and boundary conditions to the compliant mechanisms are considered the variables that are evolved by the hybrid GA. The post-analysis of results unveils that the complaint mechanisms are always supported at unique location that can evolve the non-dominated solutions.

show abstract

Section: Hybrid Genetic Algorithmmentioning

confidence: 99%

Section: Minimizementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The major drawback of GA is large computation time. But, it can be reduced by performing function evaluations in parallel [12,13].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Generation of Compliant Mechanisms using Hybrid Genetic Algorithm

Sharma

Deb

2014

J. Inst. Eng. India Ser. C

View full text Add to dashboard Cite

show abstract

“…The biggest advantages of intelligent optimization algorithms are algorithmic simplicity, multi-point parallel computing capability, strong global search capability, and objective function and constraint conditions with possibly no derivatives [2,3]. In recent years, intelligent optimization algorithms have been rapidly expanding and successfully applied in the fields of system control, production scheduling, artificial intelligence, pattern recognition, path planning and so on [4,5]. Most commonly used intelligent optimization algorithms are genetic algorithm, particle swarm optimization, ant colony algorithm, simulated annealing, tabu search algorithm, particle swarm optimization, and predatory search algorithm [6,7].…”

Section: Introductionmentioning

confidence: 99%

A Method of Initial Population Generation of Intelligent Optimization Algorithms for Constrained Global Optimization

Wang¹,

Ersoy²,

Chen³

et al. 2017

IJHIT

View full text Add to dashboard Cite

show abstract

From Bioinspiration to Computer Generation: Developments in Autonomous Soft Robot Design

Pinskier

Howard

2021

Advanced Intelligent Systems

View full text Add to dashboard Cite

The emerging field of soft robotics presents a new paradigm for robot design in which “precision through rigidity” is replaced by “cognition through compliance.” Lightweight and flexible, soft robots have vast potential to interact with fragile objects and navigate unstructured environments. Like octopuses and worms in nature, soft robots’ flexible bodies conform to hard objects and reconfigure for different tasks, delegating the burden of control from brain to body through embodied cognition. However, because of the lack of efficient modeling and simulation tools, soft robots are primarily designed by hand. Typically, hard components from rigid robots or living creatures are heuristically substituted for comparable soft ones. Autonomous design and manufacturing methodologies are urgently required to produce bespoke, high‐performing robots. Currently, design methodologies exist between simple but realistic parametric optimizations, and evolutionary algorithms which simulate morphology and control coevolution. To find high‐performing designs, novel high‐fidelity simulators and high‐throughput manufacturing and testing processes are required to explore the complex soft material, morphology and control landscape, blending simulation, and experimental data. This article reviews the state of the art in autonomous soft robotic design. Existing manual and automated designs are surveyed and future directions to automate soft robot design and manufacturing are presented.

show abstract

Domain-specific initial population strategy for compliant mechanisms using customized genetic algorithm

Cited by 40 publications

References 42 publications

Generation of Compliant Mechanisms using Hybrid Genetic Algorithm

Generation of Compliant Mechanisms using Hybrid Genetic Algorithm

A Method of Initial Population Generation of Intelligent Optimization Algorithms for Constrained Global Optimization

From Bioinspiration to Computer Generation: Developments in Autonomous Soft Robot Design

Contact Info

Product

Resources

About