A computational intelligence approach to system-of-systems architecting is developed using multi-objectiveoptimization. Such an approach yields a set of optimal solutions (the Pareto set) which has both advantages an...
详细信息
A computational intelligence approach to system-of-systems architecting is developed using multi-objectiveoptimization. Such an approach yields a set of optimal solutions (the Pareto set) which has both advantages and disadvantages. The primary benefit is that a set of solutions provides a picture of the optimal solution space that a single solution cannot. The primary difficulty is making use of a potentially infinite set of solutions. Therefore, a significant part of this approach is the development of a method to model the solution set with a finite number of points allowing the architect to intelligently choose a subset of optimal solutions based on criteria outside of the given objectives. The approach developed incorporates a meta-architecture, multi-objective genetic algorithm, and a corner search to identify points useful for modeling the solution space. This approach is then applied to a network centric warfare problem seeking the optimum selection of twenty systems. Finally, using the same problem, it is compared to a hybrid approach using single-objectiveoptimization with a fuzzy logic assessor to demonstrate the advantage of multi-objectiveoptimization. (C) 2015 The Authors. Published by Elsevier B.V.
In recent years, multi-objective optimization problems (MOOPs) have gained a lot of attentions from the community of evolutionary algorithm since many real-world optimizationproblems would involve multiple objective ...
详细信息
ISBN:
(纸本)9781479958252
In recent years, multi-objective optimization problems (MOOPs) have gained a lot of attentions from the community of evolutionary algorithm since many real-world optimizationproblems would involve multiple objective functions. In this paper, a species-based multi-objective genetic algorithm (SMOGA) that hybridizes a species method, which was initially designed in GA for multi-modal problems, with the algorithm mechanism of NSGA-II, which was one of well-known MOGAs, is proposed for MOOPs. In order to examine the performance of the proposed algorithm, experiments were carried out to investigate the strength and weakness of SMOGA on a series of test MOOPs in comparison with NSGA-II.
In order to solve the constrained multi-objective optimization problems effectively and find a set of Pareto solutions with uniform distribution as well as wide range, in this paper an evolutionary algorithm is propos...
详细信息
ISBN:
(纸本)9781479974344
In order to solve the constrained multi-objective optimization problems effectively and find a set of Pareto solutions with uniform distribution as well as wide range, in this paper an evolutionary algorithm is proposed based on a space-gridding search technique. Firstly, the decision space is divided into grids and a feasible ratio is defined for each grid. The mutation operations are executed according to this ratio, which can generate as more feasible individuals as possible. In addition, the objective space is also divided into grids to find non-dominated solutions, which can reduce the computation time evidently. Experimental results show that these technologies based on space-gridding can improve the efficiency of the algorithm.
A computational intelligence approach to system-of-systems architecting is developed using multi-objectiveoptimization. Such an approach yields a set of optimal solutions (the Pareto set) which has both advantages an...
详细信息
A computational intelligence approach to system-of-systems architecting is developed using multi-objectiveoptimization. Such an approach yields a set of optimal solutions (the Pareto set) which has both advantages and disadvantages. The primary benefit is that a set of solutions provides a picture of the optimal solution space that a single solution cannot. The primary difficulty is making use of a potentially infinite set of solutions. Therefore, a significant part of this approach is the development of a method to model the solution set with a finite number of points allowing the architect to intelligently choose a subset of optimal solutions based on criteria outside of the given objectives. The approach developed incorporates a meta-architecture, multi-objective genetic algorithm, and a corner search to identify points useful for modeling the solution space. This approach is then applied to a network centric warfare problem seeking the optimum selection of twenty systems. Finally, using the same problem, it is compared to a hybrid approach using single-objectiveoptimization with a fuzzy logic assessor to demonstrate the advantage of multi-objectiveoptimization.
The present paper proposes a multi-objective design approach for the c chart, considering in the optimization process of the chart parameters both the statistical and the economic objectives. In particular, the minimi...
详细信息
The present paper proposes a multi-objective design approach for the c chart, considering in the optimization process of the chart parameters both the statistical and the economic objectives. In particular, the minimization of the hourly total quality related costs is the considered objective to carry out the economic goal, whereas the statistical objective is reached by the minimization the out-of-control average run length of the chart. A mixed integer non-linear constrained mathematical model is formulated to solve the treated multi-objective optimization problem, whereas the Pareto optimal frontier is described by the epsilon-constraint method. In order to show the employment of the proposed approach, an illustrative example is developed and the related considerations are given. Finally, some sensitivity analysis is also performed to investigate the effects of operative and costs parameters on the chart performance. Copyright (c) 2013 John Wiley & Sons, Ltd.
This paper proposes a multi-objective probabilistic reactive power and voltage control in distribution networks using wind turbines, hydro turbines, fuel cells, static compensators and load tap changing transforms. Th...
详细信息
This paper proposes a multi-objective probabilistic reactive power and voltage control in distribution networks using wind turbines, hydro turbines, fuel cells, static compensators and load tap changing transforms. The objective functions are total electrical energy costs, the electrical energy losses, total emissions produced, and voltage deviations during the next day. Since the wind sources and load demand have intermittent characteristics, a probabilistic load flow based on 2m + 1 point estimated method is used to investigate the objective functions. The correlation in wind speed is considered as the distances between WTs are not large in distribution systems. Furthermore, a multi-objective modified bee swarm optimization is proposed to solve the optimizationproblem by defining a set of non-dominated points as the solutions. A fuzzy based clustering is used to control the size of the repository and a niching method is utilized to choose the best solution during the optimization process. Performance of the proposed algorithm is tested on a 69-bus distribution feeder. The results confirm the necessity of modeling the reactive power and voltage control problem in a stochastic framework. Also, the effects of wind site correlations on different objective functions are discussed completely. (c) 2014 Elsevier Ltd. All rights reserved.
In this paper, local learning is proposed to improve the speed and the accuracy of convergence performance of regularity model-based multiobjective estimation of distribution algorithm (RM-MEDA), a typical multi-objec...
详细信息
In this paper, local learning is proposed to improve the speed and the accuracy of convergence performance of regularity model-based multiobjective estimation of distribution algorithm (RM-MEDA), a typical multi-objectiveoptimization algorithm via estimation of distribution. RM-MEDA employs a model-based method to generate new solutions, however, this method is easy to generate poor solutions when the population has no obvious regularity. To overcome this drawback, our proposed method add a new solution generation strategy, local learning, to the original RM-MEDA. Local learning produces solutions by sampling some solutions from the neighborhood of elitist solutions in the parent population. As it is easy to search some promising solutions in the neighborhood of an elitist solution, local learning can get some useful solutions which help the population attain a fast and accurate convergence. The experimental results on a set of test instances with variable linkages show that the implement of local learning can accelerate convergence speed and add a more accurate convergence to the Pareto optimal.
Recently, efficient use of energy resources has become a very critical issue in most industries due to various reasons such as the high price of energy resources and environmental problems. The printed circuit board (...
详细信息
Recently, efficient use of energy resources has become a very critical issue in most industries due to various reasons such as the high price of energy resources and environmental problems. The printed circuit board (PCB) industry is known as one of the major manufacturing industries that consumes a moderately large amount of electricity. Of all PCB manufacturing processes, the photolithography process is the most complicated. The photolithography process consists of: 1) a lamination process;2) an exposure process;and, 3) a development process. Particularly, the lamination process appears to consume the most energy among the entire PCB manufacturing processes. This is due to the use of high temperatures and high pressures in that process which are required to employ photo sensitive dry film resist-coating on the panel. In addition, the PCB panel quality after the lamination process is highly dependent on conditions of three main operating parameters, temperature, pressure, and conveyor belt speed. In this research, we employ designed experiments and model-building techniques to obtain optimal settings of the three main operating parameters which will simultaneously minimize energy consumption while maximizing the probability of creating a non-defective PCB panel during the lamination process.
Seismic resistance and cost effectiveness are often two important building planning objectives for architects. However, these objectives nearly always share a negative correlation with each other, which can cause plan...
详细信息
Seismic resistance and cost effectiveness are often two important building planning objectives for architects. However, these objectives nearly always share a negative correlation with each other, which can cause planning delays and confusion. The conflict between these two is a multi-objective optimization problem (MOOP). Besides, building planning often encompasses both subjective and objective factors. However, most current efficiency evaluation methods focus on the latter and underemphasize the former. Current efficiency evaluation methods are thus not optimized for actual building planning needs. The aim of this study is to develop a new planning efficiency evaluation approach to resolve the above problems. Research methods include the indifference curve, efficient frontier and Data Envelopment Analysis (DEA). The indifference curve deduced the subjective planning preferences of architects;efficient frontier theory constructed the efficient frontier of school buildings;and DEA evaluated the efficiency of various building factors objectively. A total of 326 school buildings in Taichung City, Taiwan in an empirical study designed to illustrate proposed approach effectiveness. The results show that using only objective evaluation or subjective recognition is insufficient to explain the true nature of building planning. Findings can serve as benchmarks for inefficient school buildings at preliminary planning stage.
multi-objective optimization problems (MOPs) are commonly encountered in the study and design of complex systems. Pareto dominance is the most common relationship used to compare solutions in MOPs, however as the numb...
详细信息
multi-objective optimization problems (MOPs) are commonly encountered in the study and design of complex systems. Pareto dominance is the most common relationship used to compare solutions in MOPs, however as the number of objectives grows beyond three, Pareto dominance alone is no longer satisfactory. These problems are termed "Many-objectiveoptimizationproblems (MaOPs)". While most MaOP algorithms are modifications of common MOP algorithms, determining the impact on their computational complexity is difficult. This paper defines computational complexity measures for these algorithms and applies these measures to a multi-objective Evolutionary Algorithm (MOEA) and its MaOP counterpart. (C) 2014 The Authors. Published by Elsevier B.V.
暂无评论