Novel Strategies for Data-Driven Evolutionary Optimization

Roy, Swagata; Chakraborti, Nirupam

doi:10.1007/978-3-030-70787-3_2

Cited by 5 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset created in this way served as input for evolutionary deep neural nets (EvoDN2) algorithm 21 which created a surrogate model for each objective by using a multi-objective evolutionary algorithm on a population of mutually connected subnets, where the final convergence is obtained using a linear least square (LLSQ) algorithm. 22 The surrogate models were run through the constrained reference vector evolutionary algorithm (cRVEA) optimization module which is very efficient for multicriteria optimization task and is detailed elsewhere. 23,24 The multicriteria optimization task described by equation (16) leads to Pareto-optimal solution.…”

Section: Optimizationmentioning

confidence: 99%

Analysis and optimization of junction between cylindrical part and end dome of filament wound pressure vessels using data driven evolutionary algorithms

Vondráček

Padovec

Mareš

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

Self Cite

View full text Add to dashboard Cite

The junction between cylindrical part and end dome is the most critical place of the filament wound composite pressure vessels because the shear forces and bending moments occur in this area. The strength analyses of junction between cylindrical part and different types of known end domes based on influence coefficients method were performed for filament wound composite pressure vessels manufactured using glass-epoxy and carbon-epoxy composites. Four known end domes were considered that is, a spherical shell, a geodesic-isotensoid shell, a shell based on minimizing of the Tsai-Hill’s strength criterion and shell designed in authors’ previous work (Hoffman 1 shell). Moreover, the study is also dealing with design of optimal end dome shape which takes account to the junction area. Finding of optimal end dome shape was based on data-driven evolutionary algorithms. Using input dataset from the analytical simulation surrogate models were created using Evolutionary Deep Neural Nets (EvoDN2) algorithm. The multicriterial optimization procedure was performed using Constrained Reference Vector Algorithm (cRVEA) optimization algorithm. Results indicates that the optimal end dome shape highly depend on material properties.

show abstract

Section: Optimizationmentioning

confidence: 99%

Analysis and optimization of junction between cylindrical part and end dome of filament wound pressure vessels using data driven evolutionary algorithms

Vondráček

Padovec

Mareš

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

Self Cite

View full text Add to dashboard Cite

show abstract

“…A population of ANNs can be created by stacking together these new 2-D matrices. A neural network with many hidden layers and various numbers of nodes in each layer is created using EvoDN (Roy & Chakraborti, 2022). Each layer typically has a varied number of connections; hence they can't be expressed by identically sized 2-D matrices.…”

Section: Hybridization Of ML Using Evolutionary Algorithmsmentioning

confidence: 99%

Computational intelligence based design of biomaterials

Arulraj¹,

Datta²

2022

cmms

View full text Add to dashboard Cite

This paper presents an overview of the applications of computational intelligence techniques, viz. artificial neural networks, fuzzy inference systems, and genetic algorithms, for the design of biomaterials with improved performance. These techniques are basically used for developing data-driven models and for optimization. The paper introduces the domain of biomaterials and how they can be designed using computational intelligence techniques. Then a brief description of the tools is made, followed by the applications of the tools in various domains of biomaterials. The applications range in all classes of materials ranging from alloys to composites. There are examples of applications for the surface treatment of biomaterials, materials for drug delivery systems, materials for scaffolds and even in implant design. It is found the tools can be effectively used for designing new and improved biomaterials.

show abstract