Evolutionary algorithms with goal and priority information for multi-objective optimization

Tan, Kay Chen; Lee, T.H.; Khor, E. F.

doi:10.1109/cec.1999.781914

Cited by 36 publications

(42 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To examine the relationships among the different trajectory, multi-objective optimisation is necessary such that a set of trade-off models could be obtained and visualised before final determination of a model based upon the on-hand situation. Unlike conventional gradient-guided optimisation techniques, evolutionary algorithm can be easily extended for multi-objective optimisation in view of its parallel-based evolution feature (Fonseca, 1995;Tan et al, 1999). A multi-objective evolutionary algorithm is capable to approximate the set of non-dominated solutions known as Pareto optimal set, where each objective component of any model along the Pareto front can only be improved by degrading at least one of its other objective components.…”

Section: Trade-offs Among the Trajectorymentioning

confidence: 99%

Grey-box model identification via evolutionary computing

Tan

2002

Control Engineering Practice

Self Cite

View full text Add to dashboard Cite

This paper presents an evolutionary grey-box model identification methodology that makes the best use of a-priori knowledge on a clear-box model with a global structural representation of the physical system under study, whilst incorporating accurate black-box models for immeasurable and local nonlinearities of a practical system. The evolutionary technique is applied to building dominant structural identification with local parametric tuning without the need of a differentiable performance index in the presence of noisy data. It is shown that the evolutionary technique provides an excellent fitting performance and is capable of accommodating multiple objectives such as to examine the relationships between model complexity and fitting accuracy during the model building process. Validation results show that the proposed method offers robust, uncluttered and accurate models for two practical systems. It is expected that this type of grey-box models will accommodate many practical engineering systems for a better modelling accuracy.

show abstract

Section: Trade-offs Among the Trajectorymentioning

confidence: 99%

Grey-box model identification via evolutionary computing

Tan

2002

Control Engineering Practice

Self Cite

View full text Add to dashboard Cite

show abstract

“…2), MOEA and IMOEA have the highest RNI on almost all the test problems (except test problem 2) as compared to others. This clearly indicates their abilities to provide more nondominated solutions from a given size of population based on the incorporation of switching preserved strategy (SPS) (Tan et al, 1999) where all the non-dominated individuals are preserved for the next generation. The RNI for SPEA and EMOEA are mainly depending on the ratio of the size of secondary (best-found) population to the size of main population.…”

Section: Performance Comparisonsmentioning

confidence: 99%

“…In order to guarantee a fair comparison, all algorithms considered are implemented with the same coding scheme, crossover and mutation. Note that each parameter is represented by 3-digit decimal and concatenated to form the chromosomes, which gives a shorter chromosome length and avoids the Hamming-cliff effect as encountered in traditional binarybased coding scheme (Tan et al, 1999). In all cases, standard mutation with a probability of 0.01 and standard crossover with two-point crossover and a probability of 0.7 are used.…”

Section: Performance Comparisonsmentioning

confidence: 99%

“…The sharing distance for HLGA, NPGA, MOGA, NSGA as well as the performance measure of UD for all methods are set as 0.01 in the normalized space. Since dynamic sharing (Tan et al, 1999) was used for both MOEA and IMOEA, the sharing distance is computed dynamically at each generation, whereas no distance parameter is needed for SPEA and EMOEA as proposed by (Zitzler and Thiele, 1999) and (Tan et al, 2001). Tournament selection scheme with tournament size of 2 is used in MOGA, SPEA, MOEA IMOEA and EMOEA as suggested in their respective literatures.…”

Section: Performance Comparisonsmentioning

confidence: 99%

“…The MO evolutionary optimization methods under studied include VEGA from (Schaffer, 1985), MIMOGA from (Murata and Ishibuchi, 1995), HLGA from (Hajela and Lin, 1992), NPGA from (Horn et al, 1994), MOGA from (Fonseca and Fleming, 1993), NSGA from (Srinivas and Deb, 1994), SPEA from (Zitzler and Thiele, 1999), MOEA from (Tan et al, 1999), IMOEA from (Tan et al, 2000) and EMOEA from (Tan et al, 2001). Most of the these methods have often been applied or taken as reference in literature for comparing different population-based multi-objective evolutionary algorithms, and hence they are chosen here for the study.…”

Section: Performance Comparisonsmentioning

confidence: 99%

See 2 more Smart Citations

Evolutionary algorithms for multi-objective optimization: performance assessments and comparisons

Tan

Lee

Khor

Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546)

Self Cite

105

120

View full text Add to dashboard Cite

Abstract-The rapid advances of evolutionary methods for multi-objective (MO) optimization poses the difficulty of keeping track of the developments in this field as well as selecting an appropriate evolutionary approach that best suits the problem in-hand. This paper aims to analyze the strength and weakness of different evolutionary methods proposed in literatures. For this purpose, ten existing well-known evolutionary MO approaches have been experimented and compared exte nsively on two benchmark problems with different MO optimization difficulties and characteristics. Besides considering the usual two important aspects of MO performance, i.e., the spread across the Pareto-optimal front as well as the ability to attain the global optimum or final trade -offs, this paper also proposes a few useful performance measures for better and comprehensive examination of each approach both quantitatively and qualitatively. Simulation results for the comparisons are commented and summarized.

show abstract