I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97--102, Plymouth, UK, 1994. University of Plymouth.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....is that it does not requiere a fine tuning of penalty factors or any other additional parameter. The main drawback of COMOGA is that it requires several extra parameters, although its authors argue that the technique is not particularly sensitive to their values [24] 3. 2 VEGA Parmee Purchase [18] proposed to use VEGA [23] to guide the search of an evolutionary algorithm to the feasible region of an optimal gas turbine design problem with a heavily constrained search space. After having a feasible point, they generated an optimal hypercube around it in order to avoid leaving the feasible ....

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97--102, Plymouth, UK, 1994. University of Plymouth, University of Plymouth.

....of solutions. Select a P cost proportion of parents based on tness and the remaining 1 P cost based on constraint ranking. Apply genetic operators Adjust P cost : Decreasing it favors feasible solutions; Increasing it favors lower cost solutions (high tness) 3. 7 VEGA Parmee Purchase [34] proposed to use VEGA [40] to guide the search of an evolutionary algorithm to the feasible region of an optimal gas turbine design problem with a heavily constrained search space. After having a feasible point, they generated an optimal hypercube around it in order to avoid leaving the feasible ....

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97-102, Plymouth, UK, 1994. University of Plymouth.

....called COMOGA, the population was ranked based on constraint violations (counting the number of individuals dominated by each solution) Then, one portion of the population was selected based on constraint ranking, and the rest based on real cost ( tness) of the individuals. Parmee and Purchase [129] implemented a version of VEGA [151] that handled the constraints of a gas turbine problem as objectives to allow an EA to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and instead Parmee ....

....a version of VEGA [151] that handled the constraints of a gas turbine problem as objectives to allow an EA to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and instead Parmee and Purchase [129] opted to use specialized operators that would create a variable size hypercube around each feasible point to help the EA to remain within the feasible region at all times. Camponogara Talukdar [16] proposed the use of a procedure based on an evolutionary multiobjective optimization technique. ....

[Article contains additional citation context not shown here]

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97-102, Plymouth, UK, 1994. University of Plymouth.

....; m) as elements of a vector and apply multi objective techniques to minimize all components of the vector. For example, in [38] Vector Evaluated Genetic Algorithm (VEGA) selects 1= m 1) of the population based on each of the objectives. Such an approach was incorporated by Parmee and Purchase [33] in the development of techniques for constrained design spaces. On the other hand, in the approach by [43] all members of the population are ranked on the basis of constraint violation. Such rank r, together with 2 However, as observed by Davis [7] the requirement that all solutions in F ....

Parmee, I. and G. Purchase (1994). The development of directed genetic search technique for heavily constrained design spaces. In Proceedings of the Conference on Adaptive Computing in Engineering Design and Control, pp. 97-102. University of Plymouth.

....but the results achieved were not better than those found with a penalty function [50] It should be added that COMOGA [50] required several extra parameters, although its authors argue [50] that the technique is not particularly sensitive to the values of such parameters. Parmee and Purchase [37] implemented a version of the Vector Evaluated Genetic Algorithm (VEGA) 43] that handled the constraints of a gas turbine problem as objectives to allow a genetic algorithm to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to ....

....[43] that handled the constraints of a gas turbine problem as objectives to allow a genetic algorithm to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and instead Parmee and Purchase [37] opted to use specialized operators that would create a variable size 3 hypercube around each feasible point to help the genetic algorithm to remain within the feasible region at all times. This approach was specially developed for a heavily constrained search space and it proved to be ....

[Article contains additional citation context not shown here]

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97--102, Plymouth, UK, 1994. University of Plymouth. 25

....Onder, H. H. 657, 659] O Neill, A. W. 642] O Neill, Mark A. 220] Orero, S. O. 260] Ouazar, Driss, 215] Ozdemir, E, 383] Ozdemir, E. 447, 462] Paechter, Ben, 68] Paechter, B. 127, 341] Pan, J. S. 229, 418] Parks, G. T. 664] Parmee, I. C. 308, 463] Parmee, Ian C. [69, 128, 147, 155, 158, 162, 165, 167, 278, 385, 419, 427, 443, 448, 454, 456, 461, 465, 649, 650, 651, 652, 653, 654, 655, 656] Patel, Mukesh J. 129, 703] Patiakin, O. V. 486] Paton, R. 26] Patrick, T. A. 70] Patton, R. J. 71, 342] Payne, A. W. R. 552] Pearce, R. 261] Peggs, T. 262] Perry, R. 263] Petriuc, Mihai, 68] Pham, D. T. 72, 130, 195, 312, 657, 658, 659, 660, 661, 662] Pipe, A. G. ....

.... 650, 661, 382] aerospace, 550, 30, 71, 74, 78, 111, 132, 201, 261, 410] automobile, 616] biotechnology, 96] chemical, 638, 489, 98, 352] civil, 656, 167, 215, 247, 262, 349] communal, 610, 31, 38, 89] computer, 176] construction, 597, 202, 413] control, 510, 511, 37] design, [654, 655, 69, 128, 147, 155, 158, 162, 165, 167] electronic, 183] environment, 351] hydraulics, 357] machine, 207] marine, 431] mechanical, 614, 615, 616, 660, 188, 194, 200, 311, 315] mine, 29] nuclear, 663, 664] petroleum, 79, 411] pipes, 610, 18, 89] power, 664, 494, 599, 667, 32, 53, 75, 120, 121, 142, 145, 160, 192, ....

[Article contains additional citation context not shown here]

Ian C. Parmee. The development of a directed genetic search technique for heavily constrained design spaces. In ?, editor, Proceedings of Adaptive Computing in Engineering Design and Control, page ?, University of Plymouth (UK), 21.-22. September 1994. ? y(Plymouth) ga94dParmee.

....[404] Ost, Alexander, 444] Ouh Young, Ming, 224] Oyman, A. Iirfan, 232] Ozdemir, E. 354, 378, 386, 390, 391] Pak, W. H. 161, 162] Pakzad, S. 218] Palmer, Charles Campbell, 258] Pan, Tzong Shii, 178] Pao, Yoh Han, 457] Paris, William D. 399] Parkinson, B. W. 22] Parmee, Ian C. [233, 259, 266, 269, 272, 274, 275, 276, 298, 63, 334, 369, 379, 86, 163, 164, 165, 166, 438, 167] Parodi, R. 461] Parry, S. 439] Parsaei, Hamid R. 67] Patel, J. H. 337] Pathak, Rakesh M. 67] Patnaik, L. M. 295, 57, 91] Pearce, R. 53] Peng, Pei Yuan, 221] P eriaux, J. 466] Pfister, Gerd, 15] Authors 17 Pham, D. T. 168, 169, 170] Pollard, T. 210] Poloni, Carlo, ....

.... 113, 127, 149, 170] engineering aerospace, 171, 106, 116, 136, 493, 12, 22, 459, 26, 43, 288, 46, 464, 53, 466, 467, 468, 303, 471, 472, 473, 476, 335, 478, 479, 353, 359, 75, 80, 84] CAD, 132] chemical, 71] civil, 167, 248, 276, 284, 45, 317, 326] construction, 419, 420, 242, 462] design, [400, 166, 438, 206, 212, 219, 233, 242, 246, 249, 259, 266, 267, 269, 272, 274, 275, 276, 298] design theory, 318, 349] electric power, 114] electrical, 159] electronic, 279] electronics, 207, 252, 387] machine, 481] mechanical, 143, 23, 242, 25, 246, 267, 480, 482] mining, 107, 41] petroleum, 367] pipes, 9] plastics, 27] power, 122, 87, 89, 90, 95, 225, 51, 59, 477, 480, ....

[Article contains additional citation context not shown here]

Ian C. Parmee. The development of a directed genetic search technique for heavily constrained design spaces. In ?, editor, Proceedings of Adaptive Computing in Engineering Design and Control, page ?, University of Plymouth (UK), 21.-22. September 1994. ? y(Plymouth) ga94dParmee.

....called COMOGA, the population was ranked based on constraint violations (counting the number of individuals dominated by each solution) Then, one portion of the population was selected based on constraint ranking, and the rest based on real cost (fitness) of the individuals. Parmee and Purchase [18] implemented a version of VEGA [22] that handled the constraints of a gas turbine problem as objectives to allow a genetic algorithm to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and ....

....VEGA [22] that handled the constraints of a gas turbine problem as objectives to allow a genetic algorithm to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and instead Parmee and Purchase [18] opted to use specialized operators that would create a variable size hypercube around each feasible point to help the genetic algorithm to remain within the feasible region at all times. Camponogara Talukdar [1] proposed the use of a procedure based on an evolutionary multiobjective ....

[Article contains additional citation context not shown here]

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97--102, Plymouth, UK, 1994. University of Plymouth.

.... function [25] It should be added that COMOGA [25] required several extra parameters, from which the so called p cost was the most important (this parameter regulates the proportion of feasible and infeasible individuals that will exist in the population at any given time) Parmee and Purchase [28] implemented a version of VEGA [27] that handled the constraints of a gas turbine problem as objectives to allow the GA to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and instead Parmee ....

....a version of VEGA [27] that handled the constraints of a gas turbine problem as objectives to allow the GA to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and instead Parmee and Purchase [28] opted to use specialized operators that would create a variablesize hypercube around each feasible point to help the GA to remain within the feasible region at all times. 3.1 Description of the new approach The main idea behind the approach proposed in this paper is to use a population based ....

[Article contains additional citation context not shown here]

Parmee, I. C. and Purchase, G. (1994). The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94 , pages 97--102. University of Plymouth, University of Plymouth, Plymouth, UK.

....# 1# # # # # m# as elements of a vector and apply multi#objective techniques to minimize all components of the vector. For example# in #Scha#er# 1985## Vector Evaluated Genetic Algorithm #VEGA# selects 1##m#1# of the population based on each of the objectives. Such an approach was incorporated by Parmee and Purchase #1994# in the development of techniques for constrained design spaces. On the other hand# in the approach by #Surry et al.# 1995## all members of the population are ranked on the basis of constraint violation. Such rank r# together with the value of the objective function f # leads to the two#objective ....

Parmee# I. and G. Purchase #1994#. The development of directed genetic search technique for heavily constrained design spaces. In Proceedings of the Conference on Adaptive Computing in Engineer# ing Design and Control# pp. 97#102. University of Plymouth.

....called COMOGA, the population was ranked based on constraint violations (counting the number of individuals dominated by each solution) Then one portion of the population was selected based on constraint ranking, and the rest based on real cost (fitness) of the individuals. Parmee and Purchase [107] implemented a version of VEGA [119] that handled the constraints of a gas turbine problem as objectives to allow the GA to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and instead Parmee ....

....a version of VEGA [119] that handled the constraints of a gas turbine problem as objectives to allow the GA to locate a feasible region within the highly constrained search space of this application. However, VEGA was not used to further explore the feasible region, and instead Parmee and Purchase [107] opted to use specialized operators that would create a variable size hypercube around each feasible point to help the GA to remain within the feasible region at all times. Camponogara Talukdar [12] proposed the use of a procedure based on an evolutionary multiobjective optimization technique. ....

[Article contains additional citation context not shown here]

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97--102, Plymouth, UK, 1994. University of Plymouth, University of Plymouth.

.... are normally generated by trial and error, although their definition may severely affect the results produced by the GA [9] The idea of using multiobjective optimization techniques to handle constraints is not new, since there are at least three approaches reported in the literature since 1994 [7, 11, 2]. The main idea is to redefine the single objective optimization of f as a multiobjective optimization problem in which we will have m 1 objectives, where m is the number of constraints. Then, we can apply any multiobjec Please send all correspondence to: PO Box 60326 394, Houston, Texas ....

....the sub population allocated (whose number depends on the number of constraints) depending on the feasibility of the individuals contained within each of them. This is easier to implement, does not require special operators to preserve feasiblity (like in the case of Parmee and Purchase s approach [7]) makes unnecessary the use of a sharing function to preserve diversity (like with traditional multiobjective optimization techniques) and does not require extra parameters to control the mixture of fea sible and infeasible individuals (like in the case of COMOGA [11] Although VEGA is known ....

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97--102, Plymouth, UK, 1994. University of Plymouth, University of Plymouth.

....= 1; m) as elements of a vector and apply multi objective techniques to minimize all components of the vector. For example, Schaffer s (1985) Vector Evaluated Genetic Algorithm (VEGA) selects 1= m 1) of the population based on each of the objectives. Such an approach was incorporated by Parmee and Purchase (1994) in the development of techniques for constrained design spaces. On the other hand, in the approach by Surry et al. 1995) all members of the population are ranked on the basis of constraint violation. Such rank r, together with the value of the objective function f , leads to the two objective ....

Parmee, I. and G. Purchase (1994). The development of directed genetic search technique for heavily constrained design spaces. In Proceedings of the Conference on Adaptive Computing in Engineering Design and Control, pp. 97--102. University of Plymouth.

....an evaluation vector and apply multi objective techniques to minimise all components of the vector. For example, Schaffer s [20] Vector Evaluated Genetic Algorithm (VEGA) selects 1= m 1) of the population based on each of the objectives. Such an approach was incorporated by Parmee and Purchase [16] in the development of techniques for constrained design spaces. On the other hand, in the approach by Surry et al. 25] all members of the population are ranked on the basis of constraint violation. Such rank r, together with the value of the objective function f , leads to the two objective ....

Parmee, I. and G. Purchase (1994). The development of directed genetic search technique for heavily constrained design spaces. In Proceedings of the Conference on Adaptive Computing in Engineering Design and Control, pp. 97--102. University of Plymouth.

....the sub population allocated (whose number depends on the number of constraints) depending on the feasibility of the individuals contained within each of them. This is easier to implement, does not require special operators to preserve feasiblity (like in the case of Parmee and Purchase s approach [5]) makes unnecessary the use of a sharing function to preserve diversity (like with traditional multiobjective optimization techniques) and does not require extra parameters to control the mixture of feasible and infeasible individuals (like in the case of COMOGA [3] It is interesting to ....

Parmee, I. C. and Purchase, G. (1994). The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94 , pp. 97--102. University of Plymouth, UK.

.... problem, which is solved using Fonseca s MOGA [17] This approach was used by Surry et al. to optimize gas supply networks [89] Fonseca and Fleming [19] also proposed to handle constraints as objectives, and applied their approach to the design of a gas turbine [20] Parmee and Purchase [67] implemented a version of VEGA [83] to handle constraints relating to a gas turbine design problem as objectives to allow the GA to locate a feasible region within the highly constrained search space of this application. Having identified a feasible point region, specialized operators were ....

....to allow the GA to locate a feasible region within the highly constrained search space of this application. Having identified a feasible point region, specialized operators were introduced to create a variable size hypercube around each feasible point in an attempt to define the feasible region [67]. Finally, Stanley and Mudge [88] used also Pareto ranking to handle constraints treated as objectives in a combinatorial optimization problem (microprocessor design) With no doubt, the number of applications of evolutionary multiobjective optimization techniques to real world problems will ....

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97--102, Plymouth, UK, 1994. University of Plymouth, University of Plymouth.

No context found.

I. C. Parmee and G. Purchase. The development of a directed genetic search technique for heavily constrained design spaces. In I. C. Parmee, editor, Adaptive Computing in Engineering Design and Control-'94, pages 97--102, Plymouth, UK, 1994. University of Plymouth.

No context found.

Parmee, I. and G. Purchase (1994). The development of directed genetic search technique for heavily constrained design spaces. In Proceedings of the Conference on Adaptive Computing in Engineering Design and Control, pp. 97--102. University of Plymouth.

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