Design Of Genetic Algorithm Research Articles

License Plate Localization Using Genetic Algorithm including Color Feature Extraction

This paper contains a concept which is the combination of image processing and genetic algorithms. Here is a proposal for a design of a new genetic algorithm, which is introduced to detect the license plate location. It is done by converting the taken image into binary format from gray-scale image. Also connected component analysis is implemented to detect the candidate objects in that given image. A new genetic algorithm is proposed to find out the location of license plate number in the given image. Two new crossover operators, based on sorting, are introduced, which greatly improve the performance of the system. The genetic algorithm phase also takes the color feature extraction of the input color image in calculating the fitness function. The system is implemented using MATLAB and various image samples are experimented with to verify the distinction of the proposed system with the existing methods. More than 100 input images are tested by this proposed method.

Design and Comparison of Genetic Algorithms for Mixed-Model Assembly Line Balancing Problem with Original Task Times of Models

Assembly line balancing is a key for organizational productivity in terms of reduced number of workstations for a given production volume per shift. Mixed-model assembly line balancing is a reality in many organizations. The mixed-model assembly line balancing problem comes under combinatorial category. So, in this paper, an attempt has been made to develop three genetic algorithms for the mixed-model assembly line balancing problem such that the combined balancing efficiency is maximized, where the combined balancing efficiency is the average of the balancing efficiencies of the individual models. At the end, these three algorithms and another algorithm in literature are compared in terms of balancing efficiency using a randomly generated set of problems through a complete factorial experiment, in which “Algorithm”, “Problem Size” and “Cycle Time” are used as factors with two replications under each of the experimental combinations to draw inferences and to identify the best of the four algorithms. Then, through another set of randomly generated small and medium size data, the results of the best algorithm are compared with the optimal results obtained using a mathematical model. It is found that best algorithm gives the optimal solution for all the problems in the second set of data, except for one problem which cannot be solved using the model. This observation supports the fact that the best algorithm identified in this paper gives superior results.

Genetic algorithm design of a soil–structure–damper system

This paper reports on an investigation into the optimum design for a passive tuned mass damper system which takes account of soil–structure interaction. A multi-objective optimisation approach for minimising the displacement, velocity and acceleration of the structure is adopted. Three-dimensional structural models of five-, ten- and 15-storey buildings resting on soils with different shear wave velocities are used. Damper parameters are calculated using three different approaches. In the first, the damper is tuned to the fundamental frequency of the fixed-base structure; the second approach employs modified design parameters based on ASCE 7-10, and in the third the damper is optimally designed using a multi-objective genetic algorithm optimiser. The results indicate that taking the effects of soil–structure interaction into account leads to performance improvements of the damper. On the other hand, the maximum value of the displacement of soil–structure–damper system founded on soft soil reduces by a considerable extent (about 30%) using the genetic algorithm approach. Therefore the simplicity and efficiency of using the real coded genetic algorithm method in the optimal design of tuned mass dampers compared to the other two approaches is demonstrated.

Multi-level optimization of building design, energy system sizing and operation

Multi-level optimisation divides a problem into sections such that each can be addressed using the most appropriate evaluation and optimisation processes. A methodology is proposed to address the design and operation of a building and its energy system, split into three levels: building design, system design and system operation. The optimisation techniques used are a multi-objective genetic algorithm (design) and mixed-integer linear programming (operation); the evaluation methods used are the building energy simulation program EnergyPlus (building level) and the ‘energy hub’ model (system level). The objective functions used here were annual carbon emissions and initial capital cost (for the multi-objective design problem) and annual running costs (for the single objective operational problem).The methods used are described in detail, and the proposed methodology is applied to a case study concerning an office building. The detailed results presented include the trade-off front of optimal design-level solutions, the convergence of the optimisation, trends in the associated design variable values, derived properties of each solution, the operational variable values, and the run-times of the operational optimisation. Conclusions are drawn regarding the case study and the overall approach, and future directions are suggested.

Design of an efficient genetic algorithm for resource-constrained unrelated parallel machine scheduling problem with machine eligibility restrictions

This study addresses a resource-constrained unrelated parallel machine scheduling problem with machine eligibility restrictions. Majority of the traditional scheduling problems in parallel machine environment deal with machine as the only resource. However, other resources such as labors, tools, jigs, fixtures, pallets, dies, and industrial robots are not only required for processing jobs but also are often restricted. Considering other resources makes the scheduling problems more realistic and practical to implement in manufacturing environments. First, an integer mathematical programming model with the objective of minimizing makespan is developed for this problem. Noteworthy, due to NP-hardness of the considered problem, application of meta-heuristic is avoidable. Furthermore, two new genetic algorithms including a pure genetic algorithm and a genetic algorithm along with a heuristic procedure are proposed to tackle this problem. With regard to the fact that appropriate design of the parameters has a significant effect on the performance of algorithms, hence, we calibrate the parameters of these algorithms by using the response surface method. The performance of the proposed algorithms is evaluated by a number of numerical examples. The computational results demonstrated that the proposed genetic algorithm is an effective and appropriate approach for our investigated problem.

Thermal and integral lifting analysis of a lattice shell lighting roof based on genetic algorithm and probabilistic design

The optimum analysis for Railway Station Building of Yujiapu (a shell-shaped single-layer reticulated shell structure) was conducted based on genetic algorithm. An elitist genetic algorithm was used by combining Matlab and a general finite element software ANSYS. Analysis was firstly conducted to study the influence of temperature load on support reaction force, then the optimal combination of support stiffness to minimize the effects of temperature load was derived by using GA. Subsequently, probabilistic design analysis was conducted for the integral lifting process and the key lifting points which influence the stress of lifting zone significantly was derived, at the same time the probability distribution model of lifting height difference was established and validated. Finally, the same genetic algorithm was adopted to optimize the combination of lifting height difference, the maximum stress of lifting zone will be reduced obviously by using the computed results. The efficiency and applicability of GA in optimization of complex structures were demonstrated in this paper.

Design Optimization of a Novel Doubly Fed Dual-Rotor Flux-Modulated Machine for Hybrid Electric Vehicles

The doubly fed dual-rotor flux-modulated (DFDRFM) machine is a promising electrical continuously variable transmission (E-CVT) concept for the hybrid electric vehicles as it has two mechanical ports and two electrical ports, which are highly desirable for E-CVT. In this paper, a novel DFDRFM machine is proposed. Compared with previous designs, the most prominent merits are its compactness and robustness. In addition, it is easy to manufacture. After introducing its structure and working principle, the influence of dimensions on its torque and loss is analyzed. A genetic algorithm and finite-element method-based design optimization method, which aims to increase the efficiency of the proposed machine, is presented.

Pyrolysis: A Theoretical and Experimental Study on the Conversion of Softwood Sawmill Residues to Biooil

The pyrolysis of biomass is a complex process in terms of the kinetic and mass and heat transfer phenomena, which is necessary information for process optimization and large scale modeling. In this paper, an analysis of pyrolysis of sawmill residues is performed in a lab-scale pyrolysis unit to minimize the heat and mass transfer effects. Three factors, including pyrolysis temperature, feedstock particle size, and nitrogen flow rate, in the reactor are optimized using response surface methodology. Two factor-based models (a three factor quadratic model and a quadratic model without factor interactions coefficients) and two kinetic models (one based on primary reactions only, the second including secondary reactions) are compared. The factor-based models (with and without interactions) were developed using design of experiment software and Genetic Algorithm, respectively. The results showed that the quadratic model with interactions between factors predicts the experimental data more accurately compared to the other models. However, the quadratic models are experiment specific and can only be used as a design tool. The primary kinetic model predicts the experimental data trend below 550 °C well; however, as temperature rises (>550 °C), including secondary reactions gives better predictions.

A Generic Adaptive Multi-Gene-Set Genetic Algorithm (AMGA)

Genetic algorithms have been used extensively in solving complex solution-space search problems. However, certain problems can include multiple sub-problems in which multiple searches through distinct solution-spaces are required before the final solution combining all the sub-solutions is found. This paper presents a generic design of genetic algorithms which can be used for solving complex solution-space search problems that involve multiple sub-solutions. Such problems are very difficult to solve using basic genetic algorithm designs that utilize a single gene-set per chromosome. The suggested algorithm presents a generic solution which utilizes both multi-gene-set chromosomes, and an adaptive gene mutation rate scheme. The results presented from experiments done using an automatic graphical user interface generation case study, show that the suggested algorithm is capable of producing successful solutions where the common single-gene-set design fails.

A Method Combined with the Genetic Algorithm for Design of High Efficiency Propeller

In this paper, a design method combined with the genetic algorithm is proposed to design the propeller of general aviation aircraft. The inputs of this method are the cruise speed, rotational speed, propeller diameter, number of blade, thrust, Reynolds and Mach numbers. The chord and pitch-angle angle distributions along the blade are the outputs of this method. The propeller of a kind of Li-ion battery powered aircraft is designed by the present method.

Based on the Genetic Algorithm to Optimize the QoS Routing Algorithm

This article introduce the genetic algorithm to solve the routing problem with QoS requirements, solve the traditional routing algorithms in completely the limitation of the NP problem. QoS routing optimization model is given, and the detailed design of genetic algorithm encoding scheme, fitness function, selection operator, crossover operator and mutation operator. Finally, the simulation experiment algorithm according to have better convergence and stability, in solving the problem of QoS routing is feasible.

A genetic algorithm-based decomposition approach to solve an integrated equipment-workforce-service planning problem

We develop a new genetic algorithm to solve an integrated Equipment-Workforce-Service Planning problem, which features extremely large scales and complex constraints. Compared with the canonical genetic algorithm, the new algorithm is innovative in four respects: (1) The new algorithm addresses epistasis of genes by decomposing the problem variables into evolutionary variables, which evolve with the genetic operators, and the optimization variables, which are derived by solving corresponding optimization problems. (2) The new algorithm introduces the concept of Capacity Threshold and calculates the Set of Efficient and Valid Equipment Assignments to preclude unpromising solution spaces, which allows the algorithm to search much narrowed but promising solution spaces in a more efficient way. (3) The new algorithm modifies the traditional genetic crossover and mutation operators to incorporate the gene dependency in the evolutionary procedure. (4) The new algorithm proposes a new genetic operator, self-evolution, to simulate the growth procedure of an individual in nature and use it for guided improvements of individuals. The new genetic algorithm design is proven very effective and robust in various numerical tests, compared to the integer programming algorithm and the canonical genetic algorithm. When the integer programming algorithm is unable to solve the large-scale problem instances or cannot provide good solutions in acceptable times, and the canonical genetic algorithm is incapable of handling the complex constraints of these instances, the new genetic algorithm obtains the optimal or close-to-optimal solutions within seconds for instances as large as 84 million integer variables and 82 thousand constraints.

Optimization of shell-and-tube heat exchangers using a general design approach motivated by constructal theory

A general optimization design method motivated by constructal theory is proposed for heat exchanger design in the present paper. The simplified version of this design approach is suggested and the optimization problem formulations are given. In this method, a global heat exchanger is divided into several sub heat exchangers in series-and-parallel arrangement. The shell-and-tube heat exchanger is utilized for the method application, and the Tubular Exchanger Manufacturers Association (TEMA) standards are rigorously followed for all design parameters, e.g. tube diameter, arrangement, thickness and number. The fitness function is the total cost of the shell-and-tube heat exchangers, including the investment cost for initial manufacture and the operational cost involving the power consumption to overcome the frictional pressure loss. A genetic algorithm is applied to minimize the objective function by adjusting parameters. Three case studies are considered to demonstrate that the new design approach can significantly reduce the total cost compared to the methods of original design, traditional genetic algorithm design, and old constructal design.

Genetic Algorithm Design on Scalable Data Mining of Cultural Industry

In this paper, we use the functional structural principle to extend genetic algorithm, and introduce it to the cultural industry data mining, which solves the problem of data redundancy in the data mining process, improves the data processing speed and design a computer processing system of cultural industry analysis. In order to verify the effectiveness and stability of the system, we use MATLAB numerical simulation to design the program of extension genetic algorithm data mining, and test the data mining using Simulink toolbox. Through calculation, we find with the increase of set threshold, the accuracy of data mining increases, the accuracy of extension genetic algorithm is much higher than the general genetic algorithm.

Localization of License Plate Number Using Dynamic Image Processing Techniques and Genetic Algorithms

In this research, the design of a new genetic algorithm (GA) is introduced to detect the locations of license plate (LP) symbols. An adaptive threshold method is applied to overcome the dynamic changes of illumination conditions when converting the image into binary. Connected component analysis technique (CCAT) is used to detect candidate objects inside the unknown image. A scale-invariant geometric relationship matrix is introduced to model the layout of symbols in any LP that simplifies system adaptability when applied in different countries. Moreover, two new crossover operators, based on sorting, are introduced, which greatly improve the convergence speed of the system. Most of the CCAT problems, such as touching or broken bodies, are minimized by modifying the GA to perform partial match until reaching an acceptable fitness value. The system is implemented using MATLAB and various image samples are experimented with to verify the distinction of the proposed system. Encouraging results with 98.4% overall accuracy are reported for two different datasets having variability in orientation, scaling, plate location, illumination, and complex background. Examples of distorted plate images are successfully detected due to the independency on the shape, color, or location of the plate.

Minimization of sink mark depth in injection-molded thermoplastic through design of experiments and genetic algorithm

This paper deals with minimization of sink marks occurring behind the rib in plastic injection molding. In terms of rib structure and injection processing parameters, a theoretical analysis model was created. Meanwhile, finite element flow analysis with design of experiments (DOE) and genetic algorithm (GA) was integrated. Values of sink mark depth depend on design variables and technological parameters. Out of all, the four most influential variables, viz., rib thickness, mold temperature, melt temperature, and coolant temperature, were selected for optimization. The mathematic relation between sink mark depth and variables was established by conducting a set of FE analyses at various combinations of variables based on central composite design (CCD). Furthermore, the influence incidence of each factor and interaction between each variable on sink marks were investigated. The prediction model of sink marks was effectively coupled with GA for optimization of variables to minimize the sink depth. Results of the contrast analysis indicated that the proposed methodology could be used effectively in minimizing sink mark depth and parameter optimization design.

Task Optimization Scheduling Algorithm in Embedded System Based on Internet of Things

Embedded system has been widely used in the network, server, etc., and it has a good application prospect with the development of Internet of things. In the embedded heterogeneous computing system, task scheduling is the key to deciding the system performance. For multi-task scheduling, the current scheduling algorithm is mostly based on task duplication, without a full consideration of the correlation between the predecessor task and its subsequent tasks. Based on modeling the multi-frame task scheduling problem in the heterogeneous embedded system, this paper analyzes the availability of tasks through the design of genetic algorithm, so as to verify the algorithm's feasibility, which is of important guiding significance for the multi-task scheduling in the embedded heterogeneous computing system.

VSO-Optimized Dipole-Loaded Monopole

Very Simple Optimization (VSO) is introduced as a new a new global search design and optimization algorithm that is applied to a seminal antenna optimization problem: achieving uniform hemispherical coverage in a dipole-loaded monopole. The VSOoptimized monopole's performance is compared to genetic algorithm and hill-climber designs, and VSO is tested against two suites of benchmark functions and several other algorithms.

Multi-objective robust PSSs tuning in large scale power system using particle swarm optimisation

In this paper, a multi-objective robust power system stabilisers (MORPSSs) design based on the particle swarm optimisation (PSO) technique is proposed to damp the low frequency oscillations in a large scale power system. The design problem is converted to a non-linear optimisation problem with a multi-objective function that the PSO technique which has a strong ability to find the optimistic solutions is applied to it and the optimal design parameters achieved. The robustness and performance of the newly designed stabilisers is evaluated in a New England-New York 16-machine power system subjected to the different operating conditions and different types of disturbances in comparison with the genetic algorithm and linear matrix inequality-based PSS design methods. The superiority of the proposed controller is demonstrated through the eigenvalue analysis, the non-linear time-domain simulation and some performance indices studies. The results analysis reveals that the tuned PSSs using the proposed fitness function has an excellent capability in damping power system low frequency oscillations and enhances greatly the dynamic stability of the power systems.

Optimization of shell-and-tube heat exchangers conforming to TEMA standards with designs motivated by constructal theory

A modified optimization design approach motivated by constructal theory is proposed for shell-and-tube heat exchangers in the present paper. In this method, a shell-and-tube heat exchanger is divided into several in-series heat exchangers. The Tubular Exchanger Manufacturers Association (TEMA) standards are rigorously followed for all design parameters. The total cost of the whole shell-and-tube heat exchanger is set as the objective function, including the investment cost for initial manufacture and the operational cost involving the power consumption to overcome the frictional pressure loss. A genetic algorithm is applied to minimize the cost function by adjusting parameters such as the tube and shell diameters, tube length and tube arrangement. Three cases are studied which indicate that the modified design approach can significantly reduce the total cost compared to the original design method and traditional genetic algorithm design method.