Empirically-Derived Population Size and Mutation Rate Guidelines for a Genetic Algorithm with Uniform Crossover

Williams, Edwin A.; Crossley, William A.

doi:10.1007/978-1-4471-0427-8_18

Cited by 57 publications

(22 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The chromosome string length for this communication satellite problem is 41 bits (the sum of all the bits representing the 27 design variables shown in Table 1). A constant population size of 164 (4 chromosome length) individuals is used as suggested by previous empirical studies [35]. The implemented mutation probability is 0.3% [41 1= 2 164 41]; this is again suggested by empirical studies [35].…”

Section: A Monte Carlo Sampling Approachmentioning

confidence: 99%

Spacecraft Reliability-Based Design Optimization Under Uncertainty Including Discrete Variables

Hassan

Crossley

2008

Journal of Spacecraft and Rockets

View full text Add to dashboard Cite

High reliability is a primary design goal in commercial communication satellite systems because they require large capital investment and are inaccessible after launch. Spacecraft system reliability is typically computed using standard parallel-series combination techniques based upon component and subsystem failure rates provided by suppliers. Component failure rates are empirically determined and, as such, are nondeterministic parameters. Treating these failure rates as uncertain parameters in spacecraft design may avoid unnecessary high redundancy. However, probabilistic methods in reliability evaluation are often ignored because handling uncertain parameters associated with discrete or categorical design variables, such as technology choices and redundancy levels, requires computationally expensive sampling techniques. The computational cost of optimization approaches becomes prohibitive when considering discrete technology and redundancy choices as variables. This work presents a genetic algorithm with Monte Carlo sampling for probabilistic reliability-based design optimization of satellite systems. In this approach, confidence-level constraints ensure that system reliability requirements are met with high probability. The genetic algorithm-Monte Carlo sampling approach is compared to a deterministic margin-based approach that enforces margins or safety factors on the reliability of individual components. The comparison shows that the genetic algorithm-Monte Carlo sampling approach produces satellite designs that have low launch mass (a surrogate for cost) while achieving reliability requirements at specified high confidence levels, while the genetic algorithmdeterministic margin-based approach produces heavy satellite designs with excessive redundancy. Based on this work, extensions of a genetic algorithm-based approach for discrete optimization under uncertainty that may require less computational effort appear possible. Nomenclature c = penalty multiplier E = expected value of f = fitness function G = uncertain inequality constraint g = inequality constraint M = mass N samples = number of samples P = probability of R = reliability x = design vector = failure rate = mean = uncertain parameters vector = standard deviation = Gaussian probability density function = objective function

show abstract

Section: A Monte Carlo Sampling Approachmentioning

confidence: 99%

Spacecraft Reliability-Based Design Optimization Under Uncertainty Including Discrete Variables

Hassan

Crossley

2008

Journal of Spacecraft and Rockets

View full text Add to dashboard Cite

show abstract

“…Throughout this work, a genetic algorithm-based procedure previously created and used to predict the correct R-line and vibronic sideband peak positions of polycrystalline alumina 29 was implemented on the unprocessed, experimental data. This Matlab-based, genetic algorithm method was preferred over gradient-based methods, as it has the capability of global optimization 30,31 and performs four main functions to optimize the R-lines: baseline removal, cropping, separation and recombination. The fitting procedure used two pseudo-Voigt functions [32][33][34] to obtain the following design variables for each of the R1 and R2 curves: area, line-widths, peak positions and shape factors (describing the Gaussian and Lorentzian characteristics).…”

Section: Deconvolution and Curve Fitting Of Spectral Datamentioning

confidence: 99%

Characterization of particle dispersion and volume fraction in alumina-filled epoxy nanocomposites using photo-stimulated luminescence spectroscopy

Stevenson

Jones

Raghavan

2011

Polym J

View full text Add to dashboard Cite

A novel method is presented to validate the dispersion of a-alumina nanoparticles within a polymer matrix, as well as to create a calibration for filler particle volume fraction identification. Using photo-stimulated luminescence spectroscopy (PSLS), spectral information from a-alumina-filled epoxy nanocomposites consisting of varying volume fraction quantities of alumina nanoparticles was collected and analyzed. Surface contour maps of each nanocomposite were created by comparing integrated intensity data from the R1 curve of a-alumina throughout each specimen. These maps show satisfactory dispersion of alumina in the 5 and 25% volume fraction composites, whereas agglomerations were detected in various regions of the 38% nanocomposite, establishing the capability of this method to characterize photo-luminescent particle dispersion. This new approach also provides high spatial resolution, which can be used to determine the exact locations of voids, inclusions and/or agglomerations, while also predicting the volume percentage of photo-luminescent particle content within a specimen, lending itself as a quality control method in the manufacturing of these composites. Keywords: alumina nanocomposites; nanoparticle dispersion; photo-stimulated luminescence spectroscopy INTRODUCTIONThermosetting polymers, such as epoxy resins, are currently being used in aerospace applications because of the ease for which their molecular structure can be modified, as well as their ability to sufficiently bond with various filler materials. 1 Typically, un-reinforced epoxies show poor resistance to crack initiation and propagation. 2 As a result, epoxies are commonly reinforced with filler particles, or modifiers, that alter their molecular structure by increasing the already dense cross-linked network structure of the epoxy, resulting in improved mechanical properties, such as strength, stiffness and toughness.Recent research has indicated that using nano-sized particles improves the stiffness, strength and toughness of a polymer without sacrificing the thermomechanical properties. 2,3 In addition, nanoparticles have a higher specific surface area than micron-sized particles, as more of these particles can be integrated within a specific volume, enabling an overall increase in the mechanical properties of the matrix. 1,4,5 Commonly embedded nanoparticles include aluminum oxide, 6-8 , calcium silicate 6 and titanium oxide. 6,9 With the improvement in mechanical properties, these nanocomposites have applications as ballistic materials with high-impact resistance. 10,11 Owing to a high dielectric strength, alumina-filled epoxy composites are also used in high-voltage applications, such as the encapsulation of ferroelectric elements for shock depoling. 12

show abstract

“…As such, most GA e orts depend on sizing rules that are often ad hoc, based on experience or empirically derived for the problem at hand [22][23][24][25][26]. In general, however, the e ective population size is highly dependent on the string length.…”

Section: Adaptive Population Sizementioning

confidence: 99%

Knowledge‐based algorithms in fixed‐grid GA shape optimization

Woon

Tong

Querin

et al. 2003

Numerical Meth Engineering

View full text Add to dashboard Cite

SUMMARYShape optimization through a genetic algorithm (GA) using discrete boundary steps and the ÿxed-grid (FG) ÿnite-element analysis (FEA) concept was recently introduced by the authors. In this paper, algorithms based on knowledge speciÿc to the FG method with the GA-based shape optimization (FGGA) method are introduced that greatly increase its computational e ciency. These knowledge-based algorithms exploit the information inherent in the system at any given instance in the evolution such as string structure and ÿtness gradient to self-adapt the string length, population size and step magnitude. Other non-adaptive algorithms such as string grouping and deterministic local searches are also introduced to reduce the number of FEA calls. These algorithms were applied to two examples and their e ects quantiÿed. The examples show that these algorithms are highly e ective in reducing the number of FEA calls required hence signiÿcantly improving the computational e ciency of the FGGA shape optimization method.

show abstract

Empirically-Derived Population Size and Mutation Rate Guidelines for a Genetic Algorithm with Uniform Crossover

Cited by 57 publications

References 2 publications

Spacecraft Reliability-Based Design Optimization Under Uncertainty Including Discrete Variables

Spacecraft Reliability-Based Design Optimization Under Uncertainty Including Discrete Variables

Characterization of particle dispersion and volume fraction in alumina-filled epoxy nanocomposites using photo-stimulated luminescence spectroscopy

Knowledge‐based algorithms in fixed‐grid GA shape optimization

Contact Info

Product

Resources

About