Niche Genetic Algorithms Research Articles

Application of an Improved Ridgelet Process Neural Network for Predicting the Temperature Rise of Rotor Structure Optimization

To solve the negative-sequence temperature-rise problem of large equipment under asymmetric operating conditions, this paper optimizes the structure of the main components and adopts an improved process neural network to conduct online analysis and calculate the operating data, achieving the accurate prediction of the equipment heating status. Firstly, taking a 300 MW generator that urgently needs equipment improvement as the research object, the typical asymmetric accident characteristics that have occurred in recent years and the main influencing factors of negative-sequence heating of the rotor are analyzed. The influence of the rotor damping structure and shaft length on the temperature-rise change is explored. Secondly, a tent map is introduced to enhance the distribution uniformity of the population in the search space to enhance the global convergence of niche genetic algorithms. Numerical experiments and field experiments show that the improved algorithm, which is applied to optimize the parameters of the ridgelet process neural network, has good temperature-rise prediction performance. Finally, the influence of the rotor length and number of pole damping bars on the negative-sequence heating problem under different negative-sequence component ratios is examined, which provides useful references for the structural optimization and asymmetric operation state prediction of large equipment.

Sensitivity Analysis of a Species Conserving Genetic Algorithm's Parameters for Addressing the Niche Radius Problem

Niche Genetic Algorithms (NGA) are a special category of Genetic Algorithms (GA) that solve problems with multiple optima. These algorithms preserve genetic diversity and prevent the GA from converging on a single optima. Many NGAs suffer from the Niche Radius Problem (NRP), which is the problem of correctly setting a radius parameter for optimal results. While the selection of the radius value has been widely researched, the effects of other GA parameters on genetic diversity is not well known. This research is a parameter sensitivity analysis on the other parameters in a GA, namely mutation rate, number of individuals and number of generations.

Evolutionary Design of Adjustable Six-Linkage Bar Manufacturing Mechanisms Using Niche Genetic Algorithms

This paper studies the optimal synthesis design of adjustable six-linkage mechanisms in metal-mold die-casting systems. The synthesis process is extremely complex because of higher order structures, collision-free constraints, and multiple loci in the solution space. Therefore, a twin-space crowding genetic algorithm was used to solve the design problem with the multiplicity of solutions. To verify the effectiveness of the proposed approach, this paper first studied the function generation problems for adjustable four linkage-bar structures in the literature, and compared these with a numerical local optimization method. From the comparison result, multiple and more precise design solutions can be obtained with the proposed approach. The synthesis design problem for collision-free adjustable six-linkage bars was then solved and discussed. The simulated experiments demonstrated the promising result of the proposed approach.

Niche Genetic Algorithms are better than traditional Genetic Algorithms for de novo Protein Folding

Here we demonstrate that Niche Genetic Algorithms (NGA) are better at computing de novo protein folding than traditional Genetic Algorithms (GA). Previous research has shown that proteins can fold into their active forms in a limited number of ways; however, predicting how a set of amino acids will fold starting from the primary structure is still a mystery. GAs have a unique ability to solve these types of scientific problems because of their computational efficiency. Unfortunately, GAs are generally quite poor at solving problems with multiple optima. However, there is a special group of GAs called Niche Genetic Algorithms (NGA) that are quite good at solving problems with multiple optima. In this study, we use a specific NGA: the Dynamic-radius Species-conserving Genetic Algorithm (DSGA), and show that DSGA is very adept at predicting the folded state of proteins, and that DSGA is better than a traditional GA in deriving the correct folding pattern of a protein.

DSGA and GA from 'Niche Genetic Algorithms are better than traditional Genetic Algorithms for de novo Protein Folding '

DSGA and GA from 'Niche Genetic Algorithms are better than traditional Genetic Algorithms for de novo Protein Folding '

Research on Satellite Formation Establishing in Elliptical Orbits Based on Two-Impulse Control

In order to solving the establishment problem of satellites formation establishing in elliptical orbits, the problem of Lambert transfer based on two-impulse control with unfixed time and initial position is studied. The Niche Genetic Algorithms (NGA) is used to locating the optimal transfer orbit, and the transfer time and initial position are coded into genetic algorithms, as well as the fitness functions are designed to total coasting. The results show that the NGA can solve the optimization problem of two-impulse control effectively, furthermore, the performance of NGA is more effective than the traditional genetic algorithm. The research provides a way for satellites formation establishing based on two-impulse control.

Optimized Analysis of the Hollow Floor Based on the Niche Genetic Algorithms

Nowadays, the hollow floor is widely used due to its excellent mechanical property and economic benefit.However, its related specification is absence of evaluation in geometric parameters. The optimized analysis aimed at the hollow floor under vertical load, the total cost of the hollow floor is considered as a objective function, the maximum deflection and the threshold value of the geometric parameters are considered as constrain conditions. The program, which introduces the section design and compiled by the python script, based on the niche genetic algorithms is used to analyze the optimization of a hollow floor. Comparing to the global optimal solution, the program achieves good results. It indicates that the niche genetic algorithms is efficient and suited for the optimization analysis of hollow floor. The above mentioned conclusions will be conducive to engineering design and further research in this field.

Study on Hull Form Optimization for Minimum Resistance Based on Niche Genetic Algorithms

The Niche Genetic Algorithms (NGAs) can overcome the deficiency of Genetic Algo-rithms (GAs), such as premature convergence and low ability of local search. The NGA can maintain the diversity of the individual in groups. Meanwhile, it has a high ability of globally searching and a rapid convergence rate. To get the hull form with minimum resistance, an optimization design of the hull form with NGA method, which is combined with CAD technology based on the Rankine source method, is proposed. The total resistance is taken as objective function in the optimization process, study on the optimization of the fore-body of hull is proposed, with the parameter of hull form modification function as design variables, with an appropriate displacement as the basic constraint. Initially, the Series60 hull was selected as the base for the optimized calculation. Comparison between the optimized results of the NGAs and GAs shows that the hull based on the optimized NGA are valid and effective.

Study on Hull Form Optimization for Minimum Resistance Based on Niche Genetic Algorithms

Study on Hull Form Optimization for Minimum Resistance Based on Niche Genetic Algorithms

Damage Detection Method for Composite Structures Based on a Combined Technique of Cross Modal Strain Energy and Niche Genetic Algorithms

This paper presents an effective method for structural damage detection using the combined technique of the up-to-date cross modal strain energy (CMSE) and niche genetic algorithms (GAs). The traditional modal strain energy method is not convenient for structural damage detection because it needs to compare the modal information between the same modes of the baseline and damaged structures, and also requires the analytical and measured modes to be consistent in scale, or to be normalized, but no such constraint is required for the CMSE method. However, the current CMSE method is still deficient because it cannot effectively determine the locations of structural damage. In order to overcome the shortcoming of the CMSE method in structural damage detection, a combined method of the CMSE with the niche GAs is proposed in this paper to enhance the capability of identifying structural damage location. Numerical studies of damage detection for the case of a model of an airfoil of composite material are given, and the obtained results show that the method proposed in this paper is successful to detect the damage of complex structures.

The Skeleton‐Relaxed Model for Poroviscoelastic Media

AbstractBased on Biot theory, the relaxation effect of the solid skeleton is considered in a porous media. We introduce the three parameters of P wave quality factor, S wave quality factor and diffusion quality factor to describe the poroviscoelastic wave equations. A pseudo‐spectral method is used in wavefield forward modeling. Simulation results show that the skeleton‐relaxed model not only works for the fluid saturated porous media in ultrasonic band. It can also be used for the explanation of elastic waves' high attenuation in seismic band, to approximate the solid particles' relaxation effect in a mesoscopic scale. Niche Genetic Algorithms are introduced in the inversion for 24 parameters of a three‐layer model. Inversion results of the wavefield without noise hold high precision. But if white noise is added, the parameters whose true values are near singularity will get larger errors. Finally, actual shot gather sections from some district in east China are processed. The solid bulk modulus, the solid density and the quality factors of the shallow layers are estimated.

Niche pseudo-parallel genetic algorithms for path optimization of autonomous mobile robot

A new genetic algorithm named niche pseudo-parallel genetic algorithm (NPPGA) is presented for path evolution and genetic optimization of autonomous mobile robot. The NPPGA is an effective improvement to maintain the population diversity as well for the sake of avoiding premature and strengthen parallelism of the population to accelerate the search process combined with niche genetic algorithms and pseudo-parallel genetic algorithms. The proposed approach is evaluated by robotic path optimization, which is a specific application of traveler salesman problem (TSP). Experimental results indicated that a shortest path could be obtained in the practical traveling salesman problem named “Robot tour around Pekin”, and the performance conducted by NPPGA is better than simple genetic algorithm (SGA) and distributed paralell genetic algorithms (DPGA).

P-Wave Traveltime Analysis and Thomsen Parameters Inversion in Orthorhombic Media

An orthorhombic (ORT) model is the simplest azimuthally anisotropic model used to describe realistic fractured reservoirs (e.g., vertical cracks embedded in an anisotropic background media or orthogonal fracture systems in purely isotropic matrix). In this paper, we calculate the omnidirectional reflection traveltime of P-wave in single orthorhombic media with horizontal interface by using the ray trace method. The reflection Pwave traveltime-distance curves show strong azimuthal anisotropy. Using the Niche Genetic Algorithms (NGA), inversion of reflection traveltime of three common-midpoint (CMP) lines provides us with a good estimation of azimuth, P- wave vertical velocity and Thomsen anisotropic parameters.

The feature extraction of nonparametric curves based on niche genetic algorithms and multi-population competition

This research presents an approach utilizing niche genetic algorithms (NGA) other than Hough transform (HT) in detecting nonparametric curves or undefined shapes in a binary image. The optimum curve can be concluded from the evolutions of two populations, which are separately coded along columns and rows, or from multi-population competition. In order to extract the most probable curve as human visualization does, the fitness function based on the human visual tradition model is introduced for the fitness evaluation. The NGA-based curve feature extraction approach has many unique characteristics compared with the HT method, such as the ability to obtain the trajectory and length of nonparametric curves, high convergence speed, and implicit parallelism. For NGA-based curve extraction, this paper offers detailed analysis in the construction of fitness function, NGA, multi-population competition, population reservation, and comparison with Hough transform.

Inversion of Reservoir Parameters Based on the BISQ Model in Partially Saturated Porous Medium

AbstractThe Biot‐flow mechanism and the squirt‐flow mechanism are the two most important mechanisms of pore fluids in a fluid‐saturated porous medium. Based on the BISQ model including the two mechanisms simultaneously, we perform the inversion of reservoir parameters (e.g., porosity, permeability, and saturation) by using Niche Genetic Algorithms (NGA). Numerical experiments indicate that during the process of reservoir parametric inversion the convergence of objective function is fast, and our present algorithms have the property of strongly protecting the noises of observation. The results of reservoir parametric inversion are very precise while the errors of observation are less than 5%. Finally, applying to the practical inversion of experimental data proves that our present algorithms are effective in inverse problems of wave propagation in partially saturated reservoir media affected simultaneously by the Biot and squirt‐flow mechanisms.