Aiming at the phenomenon of discrete variables whic h generally exists in engineering structural optimization, a novel hybrid genetic algorithm (HGA) is proposed to directly search the optimal solution in this pape r....Aiming at the phenomenon of discrete variables whic h generally exists in engineering structural optimization, a novel hybrid genetic algorithm (HGA) is proposed to directly search the optimal solution in this pape r. The imitative full-stress design method (IFS) was presented for discrete struct ural optimum design subjected to multi-constraints. To reach the imitative full -stress state for dangerous members was the target of IFS through iteration. IF S is integrated in the GA. The basic idea of HGA is to divide the optimization t ask into two complementary parts. The coarse, global optimization is done by the GA while local refinement is done by IFS. For instance, every K generations, th e population is doped with a locally optimal individual obtained from IFS. Both methods run in parallel. All or some of individuals are continuously used as initial values for IFS. The locally optimized individuals are re-implanted into the current generation in the GA. From some numeral examples, hybridizatio n has been discovered as enormous potential for improvement of genetic algorit hm. Selection is the component which guides the HGA to the solution by preferring in dividuals with high fitness over low-fitted ones. Selection can be deterministi c operation, but in most implementations it has random components. "Elite surviv al" is introduced to avoid that the observed best-fitted individual dies out, j ust by selecting it for the next generation without any random experiments. The individuals of population are competitive only in the same generation. There exists no competition among different generations. So HGA may be permitted to h ave different evaluation criteria for different generations. Multi-Selectio n schemes are adopted to avoid slow refinement since the individuals have si milar fitness values in the end phase of HGA. The feasibility of this method is tested with examples of engineering design wit h discrete variables. Results demonstrate the validity of HGA.展开更多
A newly isolated strain EL31410, producing elastase (E.C3.4.4.7) with h igh elastolytic activity was identified as Bacillus sp. In the medium opt imizat ion, it was found that wheat bran and soybean flour hydrosate we...A newly isolated strain EL31410, producing elastase (E.C3.4.4.7) with h igh elastolytic activity was identified as Bacillus sp. In the medium opt imizat ion, it was found that wheat bran and soybean flour hydrosate were the best crud e carbon and nitrogen source for enzyme production, respectively. Addition of co rn steep flour can affect the bacterium growth and elastase production. A fracti onal factorial design was applied to study the main factors that affect the enzy me production, and central composite experimental design and response surface me thodology were adopted to derive a statistical model for the effect of wheat bra n and soybean flour hydrosate on elastase production. The experimental results s howed that wheat bran had positive effect but soybean flour hydrosate had neg ative effect, on enzyme production. An initial concentration of 3.4%(w/v) wh eat b ran and 9.4%(v/v) soybean flour hydrosate were found to be optimal for enzyme pr oduction in batch culture. The time course of elastase production in the optimiz ed medium composition was also described.展开更多
文摘Aiming at the phenomenon of discrete variables whic h generally exists in engineering structural optimization, a novel hybrid genetic algorithm (HGA) is proposed to directly search the optimal solution in this pape r. The imitative full-stress design method (IFS) was presented for discrete struct ural optimum design subjected to multi-constraints. To reach the imitative full -stress state for dangerous members was the target of IFS through iteration. IF S is integrated in the GA. The basic idea of HGA is to divide the optimization t ask into two complementary parts. The coarse, global optimization is done by the GA while local refinement is done by IFS. For instance, every K generations, th e population is doped with a locally optimal individual obtained from IFS. Both methods run in parallel. All or some of individuals are continuously used as initial values for IFS. The locally optimized individuals are re-implanted into the current generation in the GA. From some numeral examples, hybridizatio n has been discovered as enormous potential for improvement of genetic algorit hm. Selection is the component which guides the HGA to the solution by preferring in dividuals with high fitness over low-fitted ones. Selection can be deterministi c operation, but in most implementations it has random components. "Elite surviv al" is introduced to avoid that the observed best-fitted individual dies out, j ust by selecting it for the next generation without any random experiments. The individuals of population are competitive only in the same generation. There exists no competition among different generations. So HGA may be permitted to h ave different evaluation criteria for different generations. Multi-Selectio n schemes are adopted to avoid slow refinement since the individuals have si milar fitness values in the end phase of HGA. The feasibility of this method is tested with examples of engineering design wit h discrete variables. Results demonstrate the validity of HGA.
文摘A newly isolated strain EL31410, producing elastase (E.C3.4.4.7) with h igh elastolytic activity was identified as Bacillus sp. In the medium opt imizat ion, it was found that wheat bran and soybean flour hydrosate were the best crud e carbon and nitrogen source for enzyme production, respectively. Addition of co rn steep flour can affect the bacterium growth and elastase production. A fracti onal factorial design was applied to study the main factors that affect the enzy me production, and central composite experimental design and response surface me thodology were adopted to derive a statistical model for the effect of wheat bra n and soybean flour hydrosate on elastase production. The experimental results s howed that wheat bran had positive effect but soybean flour hydrosate had neg ative effect, on enzyme production. An initial concentration of 3.4%(w/v) wh eat b ran and 9.4%(v/v) soybean flour hydrosate were found to be optimal for enzyme pr oduction in batch culture. The time course of elastase production in the optimiz ed medium composition was also described.
