In this paper the CNC machining of St52 was modeled using an artificial neural network(ANN)in the form of a four-layer multi-layer perceptron(MLP).The cutting parameters used in the model were cutting fluid flow,feed ...In this paper the CNC machining of St52 was modeled using an artificial neural network(ANN)in the form of a four-layer multi-layer perceptron(MLP).The cutting parameters used in the model were cutting fluid flow,feed rate,spindle speed and the depth of cut and the model output was the tool life.For obtaining more accuracy and spending less time Taguchi design of experiment(DOE)has been used and correlation between the output of the ANN and the experimental results was 96%.Further optimization process has been done by use of a genetic algorithm(GA).After optimization process tool life was increased about 8%equal to 33 min and was corroborated by experimental tests.This demonstrates that the coupling of an ANN with the GA optimization technique is a valid and useful approach to use.展开更多
Aims Phenotypic optimality models neglect genetics.However,especially when heterozygous genotypes are fittest,evolving allele,genotype and phenotype frequencies may not correspond to predicted optima.This was not prev...Aims Phenotypic optimality models neglect genetics.However,especially when heterozygous genotypes are fittest,evolving allele,genotype and phenotype frequencies may not correspond to predicted optima.This was not previously addressed for organisms with complex life histories.Methods Therefore,we modelled the evolution of a fitness-relevant trait of clonal plants,stolon internode length.We explored the likely case of an asymmetric unimodal fitness profile with three model types.In constant selection models(CSMs),which are gametic,but not spatially explicit,evolving allele frequencies in the one-locus and fiveloci cases did not correspond to optimum stolon internode length predicted by the spatially explicit,but not gametic,phenotypic model.This deviation was due to the asymmetry of the fitness profile.Gametic,spatially explicit individual-based(SEIB)modeling allowed us relaxing the CSM assumptions of constant selection with exclusively sexual reproduction.Important findings For entirely vegetative or sexual reproduction,predictions of the gametic SEIB model were close to the ones of spatially explicit nongametic phenotypic models,but for mixed modes of reproduction they approximated those of gametic,not spatially explicit CSMs.Thus,in contrast to gametic SEIB models,phenotypic models and,especially for few loci,also CSMs can be very misleading.We conclude that the evolution of traits governed by few quantitative trait loci appears hardly predictable by simple models,that genetic algorithms aiming at technical optimization may actually miss the optimum and that selection may lead to loci with smaller effects in derived compared with ancestral lines.展开更多
文摘In this paper the CNC machining of St52 was modeled using an artificial neural network(ANN)in the form of a four-layer multi-layer perceptron(MLP).The cutting parameters used in the model were cutting fluid flow,feed rate,spindle speed and the depth of cut and the model output was the tool life.For obtaining more accuracy and spending less time Taguchi design of experiment(DOE)has been used and correlation between the output of the ANN and the experimental results was 96%.Further optimization process has been done by use of a genetic algorithm(GA).After optimization process tool life was increased about 8%equal to 33 min and was corroborated by experimental tests.This demonstrates that the coupling of an ANN with the GA optimization technique is a valid and useful approach to use.
文摘Aims Phenotypic optimality models neglect genetics.However,especially when heterozygous genotypes are fittest,evolving allele,genotype and phenotype frequencies may not correspond to predicted optima.This was not previously addressed for organisms with complex life histories.Methods Therefore,we modelled the evolution of a fitness-relevant trait of clonal plants,stolon internode length.We explored the likely case of an asymmetric unimodal fitness profile with three model types.In constant selection models(CSMs),which are gametic,but not spatially explicit,evolving allele frequencies in the one-locus and fiveloci cases did not correspond to optimum stolon internode length predicted by the spatially explicit,but not gametic,phenotypic model.This deviation was due to the asymmetry of the fitness profile.Gametic,spatially explicit individual-based(SEIB)modeling allowed us relaxing the CSM assumptions of constant selection with exclusively sexual reproduction.Important findings For entirely vegetative or sexual reproduction,predictions of the gametic SEIB model were close to the ones of spatially explicit nongametic phenotypic models,but for mixed modes of reproduction they approximated those of gametic,not spatially explicit CSMs.Thus,in contrast to gametic SEIB models,phenotypic models and,especially for few loci,also CSMs can be very misleading.We conclude that the evolution of traits governed by few quantitative trait loci appears hardly predictable by simple models,that genetic algorithms aiming at technical optimization may actually miss the optimum and that selection may lead to loci with smaller effects in derived compared with ancestral lines.
