Temperature-constrained cascade correlation networks(TCCCNs) were applied to the identification of the powder pharmaceutical samples of metronidazole based on near infrared(NIR) diffuse reflectance spectra. This work ...Temperature-constrained cascade correlation networks(TCCCNs) were applied to the identification of the powder pharmaceutical samples of metronidazole based on near infrared(NIR) diffuse reflectance spectra. This work focused on the comparison of performances of the uni-output TCCCN(Uni-TCCCN) to multi-output TCCCN(Multi-TCCCN) by using near infrared diffuse reflectance spectra of metronidazole. The TCCCN models were verified with independent prediction samples by using the "cross-validation" method. The networks were used to discriminate qualified, un-qualified and counterfeit metronidazole pharmaceutical powders. The results showed that multiple outputs network generally worked better than the single output networks. With proper network parameters the pharmaceutical powders can be classified at a rate of 100% in this work. Also, the effects of neural network parameters including number of candidate nodes, type of transfer functions(linear, sigmoid functions and temperature-constrained sigmoid function, respectively) on classification were discussed.展开更多
Due to the limitation of Edlen Equation to compensate for air refractivity in ordinary air pressure, an experiment to study the relationship between air refractivity and temperature, along with its pressure, is design...Due to the limitation of Edlen Equation to compensate for air refractivity in ordinary air pressure, an experiment to study the relationship between air refractivity and temperature, along with its pressure, is designed and carried out from ordinary pressure to low pressure. The expansion of Edlen Equation is achieved by using the cascade-Correlation learning method, and a neural network architecture model. The applied accuracy of neural network is the same as that of Edlen Equation in an ordinary pressure zone.展开更多
This study proposed a design and optimization strategy for a tandem arranged cascade using the Non-dominated Sorting Genetic Algorithm(NSGA) Ⅱ multi-objective optimization algorithm and Back Propagation(BP) neural ne...This study proposed a design and optimization strategy for a tandem arranged cascade using the Non-dominated Sorting Genetic Algorithm(NSGA) Ⅱ multi-objective optimization algorithm and Back Propagation(BP) neural network technology. The NASA Stage 35 was employed as the initial bench mark in the present study and five geometric control parameters were working as the optimization parameters aiming to enhance the aerodynamic performance in terms of total pressure rise and efficiency. Results showed that the feasibility and capability of the proposed optimization strategy was successfully examined. In view of the fact that the initial tandem cascade(directly scaling down from NASA Stage 35) cannot guarantee the aerodynamic performance, first optimization trial was conducted to optimize the initial design. Results showed that the optimum can improve the flow quality whereas the separation on the blade is decayed or even eliminated particularly at the tip and root regions. However, compared with the initial tandem design, the enhancement in total pressure ratio(0.47%) and efficiency(1%) are too small to be noticed. Second investigation was particularly emphasizing on a high turning tandem compressor with an increment by 28°. The pressure rise and efficiency were augmented by 1.44% and 2.34%(compared to the initial tandem design), respectively. An important conclusion can be drawn that the optimization strategy is worthy to be used in high turning compressors with a considerable performance improvement.展开更多
文摘Temperature-constrained cascade correlation networks(TCCCNs) were applied to the identification of the powder pharmaceutical samples of metronidazole based on near infrared(NIR) diffuse reflectance spectra. This work focused on the comparison of performances of the uni-output TCCCN(Uni-TCCCN) to multi-output TCCCN(Multi-TCCCN) by using near infrared diffuse reflectance spectra of metronidazole. The TCCCN models were verified with independent prediction samples by using the "cross-validation" method. The networks were used to discriminate qualified, un-qualified and counterfeit metronidazole pharmaceutical powders. The results showed that multiple outputs network generally worked better than the single output networks. With proper network parameters the pharmaceutical powders can be classified at a rate of 100% in this work. Also, the effects of neural network parameters including number of candidate nodes, type of transfer functions(linear, sigmoid functions and temperature-constrained sigmoid function, respectively) on classification were discussed.
文摘Due to the limitation of Edlen Equation to compensate for air refractivity in ordinary air pressure, an experiment to study the relationship between air refractivity and temperature, along with its pressure, is designed and carried out from ordinary pressure to low pressure. The expansion of Edlen Equation is achieved by using the cascade-Correlation learning method, and a neural network architecture model. The applied accuracy of neural network is the same as that of Edlen Equation in an ordinary pressure zone.
基金financially supported by the National Natural Science Foundation of China(No.51376150)
文摘This study proposed a design and optimization strategy for a tandem arranged cascade using the Non-dominated Sorting Genetic Algorithm(NSGA) Ⅱ multi-objective optimization algorithm and Back Propagation(BP) neural network technology. The NASA Stage 35 was employed as the initial bench mark in the present study and five geometric control parameters were working as the optimization parameters aiming to enhance the aerodynamic performance in terms of total pressure rise and efficiency. Results showed that the feasibility and capability of the proposed optimization strategy was successfully examined. In view of the fact that the initial tandem cascade(directly scaling down from NASA Stage 35) cannot guarantee the aerodynamic performance, first optimization trial was conducted to optimize the initial design. Results showed that the optimum can improve the flow quality whereas the separation on the blade is decayed or even eliminated particularly at the tip and root regions. However, compared with the initial tandem design, the enhancement in total pressure ratio(0.47%) and efficiency(1%) are too small to be noticed. Second investigation was particularly emphasizing on a high turning tandem compressor with an increment by 28°. The pressure rise and efficiency were augmented by 1.44% and 2.34%(compared to the initial tandem design), respectively. An important conclusion can be drawn that the optimization strategy is worthy to be used in high turning compressors with a considerable performance improvement.
