Hybrid genetic algorithm for fast electromagnetic synthesis

Boriskin, Artem; Sauleau, Ronan

doi:10.1109/msmw.2010.5546134

Cited by 5 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here genetic algorithm (GA) performs an exhaustive global exploration and the gradient-based SDG algorithm is used for the straight-forward down-hill local search in the neighborhood of the most promising solution found by GA. Such a two-step strategy enables us to significantly reduce the GA stagnation period observed at the later stage of optimization and was found to be very effective when dealing with multi-parameter and multi-extremum functions typical for electromagnetic synthesis [17,18]. Merging HGA with MBIE/MAR solver enabled us to build full-wave synthesis-oriented software capable of fast and reliable optimization of arbitrary-shaped dielectric scatterers.…”

Section: Methods Of Analysismentioning

confidence: 99%

Numerical Investigation Into the Design of Shaped Dielectric Lens Antennas With Improved Angular Characteristics

Boriskin¹,

Sauleau

2011

PIER B

View full text Add to dashboard Cite

Abstract-The feasibility of designing a compact-size beam-switching dielectric lens antenna (DLA) with improved angular (scanning) characteristics is investigated numerically using in-house software based on the Muller boundary integral equations and hybrid genetic algorithm. It is demonstrated that joint optimization of the lens shape and feeding array parameters enables one to minimize the directivity degradation for off-axis feeds which is a well-known drawback of conventional extended hemielliptic DLAs fed by focal arrays. The key to success is found in proper shaping the lens profile and using arrays of non-identical feeds.

show abstract

Section: Methods Of Analysismentioning

confidence: 99%

Numerical Investigation Into the Design of Shaped Dielectric Lens Antennas With Improved Angular Characteristics

Boriskin¹,

Sauleau

2011

PIER B

View full text Add to dashboard Cite

show abstract

“…It operates by detecting a hyper-plane in the space of all possible inputs to split the positive samples from the negative samples. With a given data set {(x i , y i ), i = 1, 2…n} where xi ЄR n and y i is either 1 or -1, the dividing hyper-plane can be expressed as: (2) where the weight vector w is perpendicular to the splitting hyper-plane. The bias b controls the separation parameter increment.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

“…In the machinery environment, a variety of diagnosis approaches that is based on computational intelligence techniques, has been proposed in literature [1,2,3,3,5,6]. These approaches have gone through tremendous reported progress with verified achievements.…”

Section: Introductionmentioning

confidence: 99%

A Dual Soft-Computing Based on Genetic Algorithm and Fuzzy Logic Defect Recognition for Gearbox and Motors: Attempts Toward Optimal Performance

et al. 2022

View full text Add to dashboard Cite

Motor and gearbox are considered the main components in various machines related to its supplying power and transmitting motion role. Operating machines acquire vibration signal that ere continuously monitoring by sensors placing close to vibration source. This for processing and identify the mechine'componentsstetus.Breekdownofthe rotating machine causes significant losses and costs, so the analysis of its vibration signals proved literately avoiding these drawbacks with effective faults diagnosis. This paper proposing two models for gearbox and motor faults identification as an attempt towards finding the optimal performance: The first developed model is a fuzzy logic based model and the other is genetic algorithm based model. The intended output of both models reduce time and cost of maintenance. It also indirectly increases the mechinecomponent's life. ydditioneddy , t he computational results showed that, in terms of execution time and accuracy effectiveness; and with Fuzzy logic meaningful and powerful representation for measurement of uncertainties; the fuzzy logic is reliable, however it presented lower classification accuracy (96% for gear box faults and 93% for motor faults) and lower generalization schema. Yet, the second proposed strategy which combines genetic algorithm and SVM recorded high performances in optimization and higher classification capabilities (97% for both gear box and motors faults). These factors illustrate the effectiveness and optimal performance of the genetic based model.

show abstract