Michalewicz, Z. and Dasgupta, D., Evolutionary Algorithms in Engineering Applications, Springer Verlag, 1997.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....the continuous domain is challenging for GAs. In traditional GAs, binary representation has been used for chromosomes, which evenly discretizes a real design space. Although such binary coded GAs have been successfully applied to a wide range of design optimization problems (for example, see [2] [3]) they suffer from disadvantages, when applied to the real world problems involving a large number of real design variables. Since binary substrings representing each parameter with the desired precision are concatenated to form a chromosome for the GAs, the resulting chromosome encoding a large ....

Dasgupta, D. and Michalewicz, Z. (Eds.), Evolutionary Algorithms in Engineering Applications, Springer, (1997).

....consideration ofform a processing principles, and the other a m#( intuitive operator along the lines of traditional single point crossover. Both operators are analyzed interm s of theform a that they process, and their perform7 3 is evaluated on a nontrivial test problem Several books [2,6,10,13,15] provide thorough accounts of theme3)#) cs of genetic search. Section 2 presents a brief overview ofform a related principles for the design of genetic search operators. The design of two crossover operators and a m#qx ion operator for searching over probability spaces are considered in Section ....

D. Dasgupta, Z. Michalewicz, Evolutionary Algorithm in Engineering Applications, Springer, New York, 1997.

....The main di erence between these two approaches (Powell Skolnick s and Deb s) is that the second does not require a penalty factor r, because of the pairwise comparisons performed during the selection process. However, Deb s approach requires niching to maintain diversity in the population [100]. This means that in this approach the search is focused initially on nding feasible solutions and then uses techniques to maintain diversity to approach the optimum. Another similar approach called CONGA (COnstraint based Numeric Genetic Algorithm) was proposed by Hinterding and Michalewicz ....

Z. Michalewicz, K. Deb, M. Schmidt, and Th. Stidsen. Evolutionary Algorithms for Engineering Applications. In K. Miettinen, P. Neittaanmaki, M. M. Makela, and J. Periaux, editors, Evolutionary Algorithms in Engineering and Computer Science, pages 73-94. John Wiley and Sons, Chichester, England, 1999. 43

....y described and discussed, indicating their main advantages and disadvantages. At the end, we conclude with some of the most promising paths of future research in this area. There are several other surveys on constraint handling techniques available in the specialized literature (see for example [104, 109, 103, 63, 34, 161]) but they are either too narrow (i.e. they cover a single group of constraint handling techniques) or they focus more on empirical comparisons and on the design of interesting test functions. None of these surverys attempt to focus on the discussion of the di erent aspects of each method or to ....

....role in penalizing such an individual [144] However, it is not clear how to exploit this relationship to guide the search in the most desirable direction. There are at least three main choices to de ne a relationship between an infeasible individual and the feasible region of the search space [34]: 1. an individual might be penalized just for being infeasible regardless of its amount of constraint violation (i.e. we do not use any information about how close it is from the feasible region) 2. the amount of its infeasibility can be measured and used to determine its corresponding ....

[Article contains additional citation context not shown here]

Dipankar Dasgupta and Zbigniew Michalewicz, editors. Evolutionary Algorithms in Engineering Applications. Springer-Verlag, Berlin, 1997.

....metaheuristics are applied to both continuous nonlinear MOO problems and to MOCO problems. Presently, most of the successful real life applications concern continuous nonlinear MOO problems with relatively low number of variables. Such problems are, for example, common in engineering design [28]. The main source of difficulty of such problems is not their size but their nonlinearity. MOCO problems are apparently more difficult for multiple objective metaheuristics. Although some authors claim that their methods can be applied to any kind of problems, in our opinion MOCO problems require ....

Dasgupta D., Michalewicz Z. (1997), Evolutionary Algorithms in Engineering Applications, Springer, Berlin.

.... algorithm Genetic algorithms (GAs) are a class of stochastic search algorithms that have been used widely in function optimization [5] GAs have been particularly effective in large scale NP complete combinatorial optimization problems including a wide variety of scheduling and routing problems [1]. The optimal CS search problem is a combinatorial optimization problem with an exponential search space. As long as there is some regularity in the search space, i.e. 2 1 2 , 3,4 1 4 2,3 2 3 1,4 3 4 , 1,2 1,2 3,4 1,3 2,4 1,4 2,3 (4) 3) 2) 1) ....

D. Dasgupta and Z. Michalewicz, editors. Evolutionary Algorithms in Engineering Applications. Spring-Verlag, New York, NY, 1997.

....contains all items classi ed as books. Chaos theory in the nancial markets. Applying fractals, Fuzzy logic, Genetic algorithms, Swrn Simulation the Monte Carlo Method to Manage Market, 12] Computational Intelligence for Optimization, 85] Evolutionary Algorithms in Engineering Applications, [91] Evolutionary Learning Algorithms for Neural Adaptive Control, 117] Genetic Algorithms and Grouping Problems, 92] Genetic Algorithms for Control and Signal Processing (Advances in Industrial Control) 115] Genetic Algorithms for Machine Learning, 17] Genetic Algorithms for Pattern ....

....Carlos C. 89] Collins, Robert James, 398] Colombetti, Marco, 355, 358] Cootes, T. F. 45] Cord on, Oscar, 193, 221, 232, 239, 243, 252, 275, 285, 288, 290, 292] Coveney, Peter V. 125] Crutch eld, James P. 47, 387, 388] Cziko, Gary, 41] Das, Rajarshi, 31, 47] Dasgupta, Dipankar, [91, 390, 391, 392] Deb, Kalyanmoy, 363] Delgado, M. 378] Delibasis, Konstantinos K. 66] Dexter, Terrence W. 68] Dominic, Stephen, 31] Dorigo, Marco, 355, 356, 357, 358] Dracopoulos, D. 117] Duncan, Tim, 42] Duponcheele, Georges, 194] East, Ian R. 209] Edengren, Magnus, 195] Edwards, A. D. ....

[Article contains additional citation context not shown here]

Dipankar Dasgupta and Zbigniew Michalewicz. Evolutionary Algorithms in Engineering Applications. Springer-Verlag, Berlin, 1997. ywww.amazon.com GAdigest V. 11 N. 13 /Dasgupta Key: ga97aDasgupta.

....all items classified as books. Chaos theory in the financial markets. Applying fractals, Fuzzy logic, Genetic algorithms, Swrn Simulation the Monte Carlo Method to Manage Market, 12] Computational Intelligence for Optimization, 65] Evolutionary Algorithms in Engineering Applications, [69] Genetic Algorithms and Grouping Problems, 70] Genetic Algorithms for Control and Signal Processing (Advances in Industrial Control) 77] Genetic Algorithms for Machine Learning, 16] Genetic Algorithms for Pattern Recognition, 56] Genetic Algorithms Engineering Design, 91] Learning ....

....Victor, 208] Collins, Robert James, 353] Colombetti, Marco, 310, 313] Cootes, T. F. 35] Cord on, Oscar, 152, 181, 192, 199, 203, 212, 235, 245, 248, 250, 252] Coveney, Peter V. 96] Crutchfield, James P. 168, 342, 343] Cziko, Gary, 32] Das, Rajarshi, 28, 168] Dasgupta, Dipankar, [69, 345, 346, 347] Deb, Kalyanmoy, 318] Delgado, M. 333] Delibasis, Konstantinos K. 47] Dexter, Terrence W. 49] Dominic, Stephen, 28] Dorigo, Marco, 310, 311, 312, 313] Duponcheele, Georges, 153] East, Ian R. 169] Edengren, Magnus, 154] Eiben, Agoston E. 172, 194] Ericson, Christer, 115] ....

[Article contains additional citation context not shown here]

Dipankar Dasgupta and Zbigniew Michalewicz. Evolutionary Algorithms in Engineering Applications. Springer-Verlag, Berlin, 1997. y(www.amazon.com GAdigest V. 11 N. 13 /Dasgupta) Key: ga97aDasgupta.

....be some discussion of the results obtained and the expected paths of future research. 2 PREVIOUS WORK Over the years, several approaches have been developed to handle constraints using evolutionary algorithms. Focusing only on numerical optimization, these approaches can be classified as follows [5]: ffl Rejection of infeasible individuals. ffl Maintaining a feasible population by special representations and genetic operators. ffl Separation of objectives and constraints. ffl Penalizing infeasible individuals. The rejection of infeasible individuals (also called death penalty ) is ....

....special genetic operators which guarantee to keep all chromosomes within the constrained solution space. GENOCOP assumes a feasible starting point (or feasible initial population) and since it assumes the existence of only linear constraints, it is inherently restricted to convex search spaces [5]. There are several approaches that handle constraints and objectives separately. On of them was reported by Paredis [9] and is based on a co evolutionary model in which there are two populations: the first contains the constraints to be satisfied and the second contains potential possibly ....

[Article contains additional citation context not shown here]

Dasgupta, D. and Michalewicz, Z., editors (1997). Evolutionary Algorithms in Engineering Applications . Springer-Verlag, Berlin.

....in the literature. 2 Previous Work The most common approach in the GA community to handle constraints (particularly, inequality constraints) is to use penalties. The basic approach is to define the fitness value of an individual i by extending the domain of the objective function f using [3] fitness i = f i (X) Sigma Q i (1) where Q i represents either a penalty for an infeasible individual i, or a cost for repairing such an individual (i.e. the cost for making it feasible) It is assumed that if i is feasible then Q i = 0. Ideally, the penalty should be kept as low as possible, ....

....role in penalizing such individual. However, it is not completely clear how to exploit this relationship to guide the search in the most desirable direction. There are at least three main choices to define a relationship between an infeasible individual and the feasible region of the search space [3]: 1) an individual might be penalized just for being infeasible (i.e. we do not use any information about how close it is from the feasible region) 2) the amount of its infeasibility can be measured and used to determine its corresponding penalty, or (3) the effort of repairing the ....

[Article contains additional citation context not shown here]

Dipankar Dasgupta and Zbigniew Michalewicz, editors. Evolutionary Algorithms in Engineering Applications. Springer-Verlag, Berlin, 1997.

.... simulation an modeling (Stender, Hillebrand, and Kingdon 1994) control and signal processing (Man, Tang, Kwong, and Halang 1997) and engineering design (Gen and Cheng 1997) Edited collection of papers on genetic algorithms include Davis (1987, 1991) Chambers (1995) Biethahn and Nissen (1995) Dasgupta and Michalewicz (1997), and Back, Fogel, and Michalewicz (1997) Recent work on genetic algorithms can often be found in conference proceedings, such as the International Conference on Genetic Algorithms (Back 1997) ICEC International Conference on Evolutionary Computation (IEEE 1997) the annual Genetic ....

Dasgupta, D. and Michalewicz, Z. (editors). 1997. Evolutionary Algorithms in Engineering Applications. Berlin: Springer-Verlag.

....provided, showing their advantages and disadvantages, and we will conclude with some of the most promising paths of future research. It should be mentioned that despite the fact that there are other surveys on constraint handling techniques available in the specialized literature (see for example [86, 85, 52, 23, 127]) they are either too narrow (i.e. they cover a single constraint handling technique) or they focus more on empirical comparisons and on the design of interesting test functions and do not attempt to be comprehensive as we pretend in this paper. Our main goal is to provide enough (mainly ....

....makes a clear distinction between equality and inequality constraints. 3 A Taxonomy of Approaches Focusing only on numerical optimization, particularly regarding non linear optimization problems, the constrainthandling techniques developed over the years can be roughly classified as follows [23]: ffl Use of penalty functions. ffl Maintaining a feasible population by special representations and genetic operators. ffl Separation of objectives and constraints. ffl Hybrid methods. ffl Novel approaches. 4 Use of penalty functions The most common approach in the EA (mainly with genetic ....

[Article contains additional citation context not shown here]

Dipankar Dasgupta and Zbigniew Michalewicz, editors. Evolutionary Algorithms in Engineering Applications. Springer-Verlag, Berlin, 1997.

.... Science Rutgers, The State University of New Jersey Piscataway, NJ 08855 USA davison cs.rutgers.edu November 2, 1998 1 Introduction The abundance of powerful workstations makes course grained parallelization an obvious enhancement to many optimization techniques, including genetic algorithms [Gol89, DM97]. While initial modifications have been made to GADO (Genetic Algorithm for Design Optimization [Ras98, RHG97] such changes have not been carefully analyzed for potential impacts on quality. More generally, parallelization has the potential to improve GA performance through the use of ....

Dipankar Dasgupta and Zbigniew Michalewicz, editors. Evolutionary algorithms in engineering applications. Springer-Verlag, New York, NY, 1997.

.... classes of multiple objective problems, for instance multiple objective combinatorial problems (cf. Ulungu and Teghem, 1994) This interest is raised by practical applications, e.g. in project scheduling (see e.g. Slowinski, 1989) vehicle routing (see e.g. Assad, 1988) and engineering design (Dasgupta and Michalewicz 1997). For example, solutions to vehicle routing problems are usually evaluated by e.g. total cost, distance, travel time and the number of vehicles used. In practice, it can therefore be difficult to evaluate a solution to such a problem with only a single objective. The objectives, however, are ....

Dasgupta D., Michalewicz Z. (1997). Evolutionary Algorithms in Engineering Applications. Springer Verlag.

....Evolutionary algorithms can be made ecient because they are exible, and relatively easy to hybridize with domain dependent heuristics. Those features of evolutionary computation have already been acknowledged in the eld of engineering, and many applications have been reported (see, for example, [6, 11, 34, 43]) A vast majority of engineering optimization problems are constrained problems. The presence of constraints signi cantly a ects the performance of any optimization algorithm, including evolutionary search methods [20] This paper focuses on the issue of evaluation of constraints handling ....

Dasgupta, D. and Michalewicz, Z., (Editors), Evolutionary Algorithms in Engineering Applications, Springer-Verlag, New York, 1997.

....function for the non self space: x ) max( l #R R , and l = level(R ) # 0 ) where level(R ) represent the deviation level reported by the rule R . 12 3. 3 Genetic Algorithm in Detection Rule Generation The genetic algorithm, attempts to evolve good rules [6, 7, 12] that cover the non self space. The goodness of a rule is determined by various factors: the number of normal samples that it covers, its area, and the overlapping with other rules. This is clearly a multi objective, multi modal optimization problem. We are not interested in one solution but a set ....

D. Dasgupta and Z. Michalewicz, editors. Evolutionary Algorithms in Engineering Applications. Springer-Verlag " New York, 1997. 18

....Evolutionary algorithms can be made ecient because they are exible, and relatively easy to hybridize with domain dependent heuristics. Those features of evolutionary computation have already been acknowledged in the eld of engineering, and many applications have been reported (see, for example, [6, 11, 34, 43]) A vast majority of engineering optimization problems are constrained problems. The presence of constraints signi cantly a ects the performance of any optimization algorithm, including evolutionary search methods [20] This paper focuses on the issue of evaluation of constraints handling ....

Dasgupta, D. and Michalewicz, Z., (Editors), Evolutionary Algorithms in Engineering Applications, Springer-Verlag, New York, 1997.

No context found.

Michalewicz, Z. and Dasgupta, D., Evolutionary Algorithms in Engineering Applications, Springer Verlag, 1997.

No context found.

Dasgupta D, Michalewicz Z. (eds) Evolutionary Algorithms in Engineering Applications. Springer-Verlag, New York 1997

No context found.

Dipankar Dasgupta and Zbigniew Michalewicz, editors. Evolutionary Algorithms in Engineering Applications. Springer-Verlag, Berlin, 1997. Variables This paper Gen [16] Homaifar [25] GRG [15]

No context found.

Dasgupta, D. & Michalewicz, Z. (1997). Evolutionary algorithms in Engineering Applications. Germany, Springer.

No context found.

) Dasgupta, D. and Michalewicz, Z. (eds.), Evolutionary Algorithms in Engineering Applications, Springer-Verlag, Berlin, Heidelberg,

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC