Application Of Multi-objective Genetic Algorithms Research Articles

Multiobjective optimization of transpiration cooling in hypersonic laminar flow using a genetic algorithm approach

The efficient utilization of transpiration cooling is crucial for addressing coolant consumption challenges in hypersonic vehicle design. This study focuses on optimizing the blowing ratio, a key parameter in transpiration cooling. A multiobjective genetic algorithm is employed to determine the optimal blowing ratio using an experimental correlation. The optimization objectives include average thermal effectiveness, length of cooling with thermal effectiveness greater than 0.5, and coolant reservoir volume over a 60 s duration cooling process. The results reveal that a blowing ratio of 0.108 % is the optimal point, with corresponding values for average thermal effectiveness, coolant reservoir volume, and length of cooling being 0.493, 7.093 m³, and 0.14 m, respectively. A comparison with the maximum experimental blowing ratio indicates a 56.61 % reduction in average thermal effectiveness, accompanied by a 56.68 % decrease in coolant reservoir volume. This study highlights the application of multiobjective genetic algorithms in optimizing the transpiration cooling blowing ratio for hypersonic vehicles.

Application of Artificial Neural Networks and Genetic Algorithm for optimizing Process parameters in Pocket Milling of AA7075

Received 06 October 2021; revised 23 August 2022; accepted 24 August 2022 Mould preparation is an important phase in the injection moulding process. The surface roughness of the mould affects the surface finish of the final plastic product. Quality product with a better production rate is required to meet the competition in the present market. To achieve this objective, manufacturers try to select the best combination of parameters. Multi-objective optimization is one such technique to obtain the optimal process parameters that give better quality with a good production rate. The current paper describes the application of Multi-Objective Genetic Algorithms (MOGA) on the Artificial Neural Network (ANN) model for pocket milling on AA7075. Through the application of ANN with MOGA minimum Surface Roughness (SR) is achieved with a better Material Removal Rate (MRR). From the confirmation experiments, it is evident that follow-periphery tool path gives a better surface finish with higher MRR and the percentage error observed is 1.9553 and 1.8282 respectively.

Optimal Operation of a Distributed Generation Microgrid based on the Multi-Objective Genetic Algorithms

This document describes the application of multiobjective genetic algorithms as techniques and tools to optimize generation and distribution in small microgrids. In this way, genetic algorithms have been used for the allocation of distributed generation to reduce losses and improve the voltage profile. The IEEE14 network has been taken as a study and analysis model. This smart grid has 14 nodes and integrates several generation units, both conventional and renewable, transformers, and multiple loads. In this way, a multi-objective metaheuristic algorithm is proposed with the purpose of planning the power distribution grid based on a series of conditions such as the optimal generation configuration, the minimization of power losses in the lines, power transfer capacity, the reduction of CO2 emissions, and the optimization of the benefits obtained in renewable generation. The overall purpose is the development of an intelligent microgrid management system that is capable of determining the optimal configuration, by estimating demand, energy costs, and operating costs.

Multiobjective Genetic Algorithm for Class Testing using OCL Class Contract Specifications: A Framework

It has been a software trend to build large-scale complex systems with high reliability. Due to the size of the software and the dynamic requirements of the stakeholders, it becomes hard to test those software systems manually. This may lead the software to fatal failures and cause irrecoverable catastrophic damage. To be safe, the software system must be investigated thoroughly before it is too late. Test sequence generation for Unified Modeling Language (UML) class models from their semiformal Object Constraint Language specifications can be helpful in identifying the defects in the early phase of the software life cycle. The existing approaches suffer from inherent problems of exhaustive exploration of finite state machines (infeasible paths, exponential number of test sequences, and uncertainty of completion of testing). Evolutionary algorithms can greatly help by optimizing the test sequences to get optimal coverage, minimal cost, and higher quality. The proposed approach helps us to improve the testing of Unified Modeling Language (UML) model-based software, by testing the conformance to semiformal class operation contract specifications (specified in the form of Object Management Group (OMG) standard and Object Constraint Language (OCL) semiformal language). The presented research achieved two main goals: (1) automation of testing process and conformance to standards of the current technique of test sequence generation, bridging the gap between the research and industry; (2) improvement in the state of the art approach through the application of multiobjective genetic algorithms (MOGAs). A case study along with the results achieved through the proposed technique is presented as well, clearly reflecting the significance of the proposed research.

Design optimization of broadband extreme ultraviolet polarizer in high-dimensional objective space

With the purpose of designing the extreme ultraviolet polarizer with many objectives, a combined application of multi-objective genetic algorithms is theoretically proposed. Owing to the multi-objective genetic algorithm, the relationships between different designing objectives of extreme ultraviolet polarizer have been obtained by analyzing the distribution of nondominated solutions in the four-dimensional objective space, and the optimized multilayer design can be obtained by guiding the searching in the desired region based on the multi-objective genetic algorithm with reference direction. Compared with the conventional method of multilayer design, our method has a higher probability of achieving the optimal multilayer design. Our work should be the first research in optimizing the optical multilayer designs in the high-dimensional objective space, and our results demonstrate a potential application of our method in the designs of optical thin films.

DISEÑO ÓPTIMO MULTI-OBJETIVO DE EDIFICIOS DE CONCRETO REFORZADO USANDO ALGORITMOS GENÉTICOS

Se muestra el diseño sísmico óptimo de marcos estructurales de concreto reforzado mediante la aplicación de los algoritmos genéticos multi-objetivo, considerando dos objetivos de manera simultánea. El primer objetivo consiste en controlar la distorsión máxima de entrepiso y el segundo en minimizar el costo total estructural del marco. Para ello las estructuras se analizan representando el efecto sísmico a partir de fuerzas laterales. Para lograr un diseño sísmico satisfactorio se utiliza una búsqueda de soluciones basada en algoritmos evolutivos de optimización multi-objetivo denominada Non-Dominated Sorting Genetic Algorithm (NSGA-II). Los resultados obtenidos muestran que los algoritmos genéticos son una herramienta bastante útil para encontrar soluciones de problemas de optimización estructural, y que los diseños obtenidos son adecuados en términos de desempeño sísmico y economía.

Optimum machine capabilities for reconfigurable manufacturing systems

Reconfigurable manufacturing systems constitute a new manufacturing paradigm and are considered as the future of manufacturing because of their changeable and flexible nature. In a reconfigurable manufacturing environment, basic modules can be rearranged, interchanged, or modified, to adjust the production capacity according to production requirements. Reconfigurable machine tools have modular structure comprising of basic and auxiliary modules that aid in modifying the functionality of a manufacturing system. As the product’s design and its manufacturing capabilities are closely related, the manufacturing system is desired to be customizable to cater for all the design changes. Moreover, the performance of a manufacturing system lies in a set of planning and scheduling data incorporated with the machining capabilities keeping in view the market demands. This research work is based on the co-evolution of process planning and machine configurations in which optimal machine capabilities are generated through the application of multi-objective genetic algorithms. Furthermore, based on these capabilities, the system is tested for reconfiguration in case of production changeovers. Since, in a reconfigurable environment, the same machine can be used to perform different tasks depending on the required configuration, the subject research work assigns optimum number of machines by minimizing the machining capabilities to carry out different operations in order to streamline production responses. An algorithm has also been developed and verified on a part family. As a result of the proposed methodology, an optimized reconfigurable framework can be achieved to realize optimal production of a part family. Finally, the proposed methodology was applied on a case study and respective conclusions were drawn.

Application of multi-objective genetic algorithms to interior lighting optimization

The energy consumed by artificial lighting represents a vast amount of total energy consumption of a building. LED luminaires combine many advantages and they are considered a prominent lighting technology. The utilization of miscellaneous optimization methods in lighting control has achieved a variety of benefits, such as energy savings while sustaining illuminance at the required levels. However, there is a lack of methods, which take into account the uniformity of lighting which is a significant factor that should be considered according to the EN 12464. This paper proposes a multi-objective optimization model for artificial lighting control so as to minimize energy consumption and the same time maximize uniformity of lighting while maintaining the illuminance at an appropriate level. Two objective functions have been used, the first is the summation of the dimming levels of the luminaires of an interior space and the second is the coefficient of variation of root mean square error of illuminance which is metric of the uniformity of artificial lighting. Both functions have been formulated as mathematical functions of the dimming levels of the luminaires. Constraints include the required level of illuminance and the luminaires’ dimming capabilities. The Non-Dominated Sorting Genetic Algorithm II is used to carry out the optimization. The proposed model has been implemented in an office room and the results demonstrated significant energy savings up to 22%. The proposed approach is flexible and can be applied to all types of interior spaces and is independent of the geometry and configuration of the room.

Application of multi-objective genetic algorithms for optimization of energy, economics and environmental life cycle assessment in oilseed production

In this study a multi-objective genetic algorithm (MOGA) was applied to find the best combination of mixing energy, economic and environmental indices concerning oilseed canola production. Data were collected from oilseed farming enterprises in Mazandaran province of Iran. Life cycle assessment of canola production from cradle to farm gate was investigated to calculate the environmental emissions. Econometric modelling was applied to find the relationship functions between energy inputs and three individual output parameters including environmental emissions, output energy and economic productivity. A multi-objective model was formulated in order to maximise the output energy and benefit to cost ratio, and minimise the final score of environmental emissions in order to obtain a set of Pareto frontier. When applying CML-IA methodology, multi-objective optimization resulted in a 32.1% reduction of the total environmental emissions as well as simultaneous increase of output energy and benefit cost ratio by 24.1% and 14.2%, respectively. More specifically, the reduction of chemicals by 82.2%, nitrogen by 11.1% and other chemical fertilisers by 70.7% would be beneficial from environment, energy and economic viewpoints. This work highlights the usefulness of the implementation of MOGA in agricultural production systems to find an optimized combination of mixing energy, economic and environment.

Building energy optimization in the early design stages: A simplified method

This paper presents the application of multi-objective genetic algorithms for holistic building design that considers multiple criteria; building energy use, capital cost, daylight distribution and thermal indoor environment. The optimization focus is related to building envelope parameters. To obtain relevant feedback from multi-objective optimizations in early design stages, evaluation speed is a key concern. The paper presents a fast evaluation method fit for the early design stages. It uses a combination of two different quasi-steady-state methods for energy and indoor environment evaluations, a Radiance implementation for daylight simulations and a scripted algorithm for capital cost evaluations. The application of the method is developed around an integrated dynamic model which allows visual design feedback from all evaluations to be an integrated part of the design tool experience. It is concluded, that quasi-steady-state methods implemented as part of integrated dynamic models are fast and flexible enough to support building energy-, indoor environment- and cost-optimization the early design stages.

Finite Element Analysis and Multi-Objective Optimization of the Precision Horizontal Machining Center Bed

In order to improve dynamic and static performance of the precision horizontal machining center, the method of multi-objective optimization based on the response surface model was applied for optimizing design of the bed structure. The design variables were the layout parameters of the rib plates. Sample points were obtained by the Box-Behnken design experiment, and responses of sample points were analyzed by SAMCEF. The maximum deformation of guide rails and the low-order natural frequency were extracted to fit the response surface model by least square method. The layout parameters of the rib plates were optimized through the application of multi-objective genetic algorithms. Then, relationship between the lightening holes and the performance were analyzed to determine the suitable diameter. The results verify the validity of the optimization method, and the paper provides methodological guidance for optimization of machine tool structural parts.

Application of multi-objective genetic algorithms to the mechatronic design of a four bar system with continuous and discrete variables

This paper deals with a multi-objective optimization of a mechatronic system. The objective functions to minimize are the motor torque and the fluctuation of the system velocity. These goals are achieved by simultaneously finding the best motor in a list, to drive the system and the best distribution of the inertia of the mechanical system parts. This led us to formulate a global optimization problem where all the inertia parameters of the mechanism and the different motors are considered simultaneously. The problem is then presented as a multi-objective optimization one with continuous and discrete variables. A second generation Multi-Objective-Genetic Algorithm method, called Non-dominated Sorting GA-II (NSGA-II), was used to solve this problem. The obtained solutions form what is called a “Pareto front”. They are analyzed for several different design conditions. We showed, in particular, that the proposed method, compared to electromechanical design strategy, proved to be more efficient in finding the optimal combination of the mechanical system and the driving motor besides minimizing the power consumption without the need of sophisticated controllers.

Application of multi-objective genetic algorithms to two case studies of reliability efficiency analysis and optimal expansion of electrical transmission networks

Two applications of multi-objective genetic algorithms to the analysis and optimization of electrical transmission networks are reported to show the potential of these combinatorial optimization schemes in the treatment of highly interconnected, complex systems. In a first case study, an analysis of the topological structure of an electrical power transmission system in the literature is carried out to identify the most important group of elements of different sizes in the network. The importance is quantified in terms of group closeness centrality. In the second case study, an optimization method is developed for identifying strategies of expansion of an electrical transmission network by addition of new lines of connection which are optimally identified with respect to the objective of improving the transmission reliability, while limiting the investment cost.

Calibrating a watershed simulation model involving human interference: an application of multi-objective genetic algorithms

We calibrate a storm-event distributed hydrologic model to a watershed, in which runoff is significantly affected by reservoir storage and release, using a multi-objective genetic algorithm (NSGA-II). This paper addresses the following questions: What forms of the objective (fitness) function used in the optimization model will result in a better calibration? How does the error in reservoir release caused by neglected human interference or the imprecise storage–release function affect the calibration? Reservoir release is studied as a specific (and popular) form of human interference. Two procedures for handling reservoir releases are tested and compared: (1) treating reservoir releases to be solely determined by the hydraulic structure (predefined storage or stage-discharge relations) as if perfect, a procedure usually adopted in watershed model calibration; or (2) adding reservoir releases that are determined by the storage–discharge relation to an error term. The error term encompasses a time-variant human interference and a discharge function error, and is determined through an optimization-based calibration procedure. It is found that the calibration procedure with consideration of human interference not only results in a better match of modeled and observed hydrograph, but also more reasonable model parameters in terms of their spatial distribution and the robustness of the parameter values.

A MULTI-OBJECTIVE GENETIC ALGORITHM FOR TUNING AND RULE SELECTION TO OBTAIN ACCURATE AND COMPACT LINGUISTIC FUZZY RULE-BASED SYSTEMS

This work proposes the application of Multi-Objective Genetic Algorithms to obtain Fuzzy Rule-Based Systems with a better trade-off between interpretability and accuracy in linguistic fuzzy modelling problems. To do that, we present a new post-processing method that by considering selection of rules together with tuning of membership functions gets solutions only in the Pareto zone with the highest accuracy, i.e., containing solutions with the least number of possible rules but still presenting high accuracy. This method is based on the well-known SPEA2 algorithm, applying appropriate genetic operators and including some modifications to concentrate the search in the desired Pareto zone.

Application of multi-objective genetic algorithms to multireservoir system optimization in the Han River basin

The objective of multireservoir system optimization is to achieve an optimal reservoir operating plan by the effective use of water resources. Many optimization techniques have been applied for the last decades, and researchers have recently interested in the heuristic approaches like evolutionary computation. This study proposes a methodology for applying multi-objective genetic algorithms (MOGAs) to a multireservoir system optimization in the Han River basin. The second generation evolutionary multiobjective technique, NSGA-II, is used. The simulation model is applied to the Han River basin and the performance of the model is compared with the historical reservoir operation records. Two different cases are performed to evaluate the applicability of NSGA-II. Case 1 shows the basic performance of NSGA-II as applied to multireservoir system optimization, and Case 2 presents the methodology to discriminate the critical decision variables. In addition, the alternative releases and storages by NSGA-II are compared with the historical releases and storages. Cases 1 and 2 show that NSGA-II can be applied to multireservoir system optimization, and the alternative releases and storages computed using the results from NSGA-II can be used as the possible resrvoir operating plans that supply more water resources to downstream than the historical releases.