Using dynamic mutation rates in gene-set genetic algorithms

Hong, Tzung-Pei; Wu, Min-Thai; Lee, Yeong-Chyi

doi:10.1109/icsmc.2010.5642209

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the objective function, the effectiveness of the GAs relies on the selection of its control parameters (initial population, population size, generation size, crossover, and mutation) that interact in a complex way. 31…”

Section: Airfoil Optimizationmentioning

confidence: 99%

Utilizing artificial intelligence to develop an advanced compressor airfoil family for industrial, aero-derivative, and heavy-duty gas turbines

Farahani

Mohammadi

Alizadeh

2023

Proceedings of the Institution of Mechanical Engineers, Part A:

View full text Add to dashboard Cite

This paper describes the procedure for developing a new airfoil family. This airfoil family applies to heavy-duty, industrial, and aero-derivative gas turbine compressors ranging from subsonic to transonic flow regimes. The airfoil family is generated by filling a database with optimized airfoil geometries. This database is structured in six dimensions, called design space parameters, including inlet Mach number, inlet flow angle, outlet flow angle, axial velocity density ratio, maximum thickness to chord ratio, and solidity. This six-dimensional space includes all compressor blades used in stationary gas turbine compressors. Each set of these design space parameters is related to an optimal geometry produced by the optimization system. The optimization system includes a parametrized airfoil generator, an accurate, fast blade-to-blade flow solver, and an evolutionary optimization algorithm. Airfoils of different stationary gas turbine compressor types are investigated to cover the required design space. Four hundred thirty airfoils, denoted as reference airfoils, are used to define design space borders. Comparing the newly optimized airfoils with reference airfoils revealed superior performance throughout the entire design space. They incorporate these optimized airfoils into a surrogate model, resulting in a fast, optimized airfoil generator (airfoil family). The transonic rotor of the existing multistage compressor has been redesigned according to the developed airfoil family. 3D computational fluid dynamics showed a 2% efficiency improvement for optimized blade row over the original design. Integrating this airfoil family and a streamline curvature code as part of a compressor design system is the main application of this advanced airfoil family.

show abstract

Section: Airfoil Optimizationmentioning

confidence: 99%

Utilizing artificial intelligence to develop an advanced compressor airfoil family for industrial, aero-derivative, and heavy-duty gas turbines

Farahani

Mohammadi

Alizadeh

2023

Proceedings of the Institution of Mechanical Engineers, Part A:

View full text Add to dashboard Cite

show abstract

“…Beginning with the initial generation in each iteration, an offspring is generated through randomly selecting and modifying the parent gene values [5] [14]. In this experiment, single gene mutation and dynamic gene mutation are separately performed.…”

Section: B Mutationmentioning

confidence: 99%

Circuit design optimisation using a modified genetic algorithm and device layout motifs

Xiao

Walker

Bale

et al. 2014

2014 IEEE International Conference on Evolvable Systems

View full text Add to dashboard Cite

Circuit performance optimisation such as increasing speed and minimizing power consumption is the most important design goal for circuit designers next to correct functionality. This is generally also a very complex problem where, in order to solve it, several factors such as device characteristics, circuit topology, and circuit functionality must be considered. Particularly, as technology has scaled to the atomistic level, the resulting uncertainty factors further affect circuit performance. In this paper, we propose combining a modified genetic algorithm with dynamic gene mutation and device layout motif selection for circuit performance improvement. We explore novel device layout motifs (O shape device) to exploit effects of device layout at the atomistic level in order to improve characteristics of circuits and combine them with a modified GA for automatic circuit optimisation. Additionally, in order to overcome local optima and premature convergence, a dynamic gene mutation rate is performed within the GA. The experimental results show that this methodology can achieve more than 30% delay reduction through mixed combinations of O shape devices and regular devices in a circuit, compared to circuits built of only regular devices. At the same time, the local optima are also reliably avoided due to the dynamic gene mutation.

show abstract

Generation of Pairwise Test Sets Using a Genetic Algorithm

McCaffrey

2009

2009 33rd Annual IEEE International Computer Software and Applications Conference

View full text Add to dashboard Cite

Using dynamic mutation rates in gene-set genetic algorithms

Cited by 5 publications

References 13 publications

Utilizing artificial intelligence to develop an advanced compressor airfoil family for industrial, aero-derivative, and heavy-duty gas turbines

Utilizing artificial intelligence to develop an advanced compressor airfoil family for industrial, aero-derivative, and heavy-duty gas turbines

Circuit design optimisation using a modified genetic algorithm and device layout motifs

Generation of Pairwise Test Sets Using a Genetic Algorithm

Contact Info

Product

Resources

About