Two artificial intelligence techniques, artificial neural network and genetic algorithm, were applied to optimize the fermentation medium for improving the nitrite oxidization rate of nitrite oxidizing bacteria. Exper...Two artificial intelligence techniques, artificial neural network and genetic algorithm, were applied to optimize the fermentation medium for improving the nitrite oxidization rate of nitrite oxidizing bacteria. Experiments were conducted with the composition of medium components obtained by genetic algorithm, and the experimental data were used to build a BP (back propagation) neural network model. The concentrations of six medium components were used as input vectors, and the nitrite oxidization rate was used as output vector of the model. The BP neural network model was used as the objective function of genetic algorithm to find the optimum medium composition for the maximum nitrite oxidization rate. The maximum nitrite oxidization rate was 0.952 g 2 NO-2-N·(g MLSS)-1·d-1 , obtained at the genetic algorithm optimized concentration of medium components (g·L-1 ): NaCl 0.58, MgSO 4 ·7H 2 O 0.14, FeSO 4 ·7H 2 O 0.141, KH 2 PO 4 0.8485, NaNO 2 2.52, and NaHCO 3 3.613. Validation experiments suggest that the experimental results are consistent with the best result predicted by the model. A scale-up experiment shows that the nitrite degraded completely after 34 h when cultured in the optimum medium, which is 10 h less than that cultured in the initial medium.展开更多
Aiming at the disadvantages of BP model in artificial neural networks applied to intelligent fault diagnosis, neural network fault diagnosis optimization method with rough sets and genetic algorithms are presented. Th...Aiming at the disadvantages of BP model in artificial neural networks applied to intelligent fault diagnosis, neural network fault diagnosis optimization method with rough sets and genetic algorithms are presented. The neural network nodes of the input layer can be calculated and simplified through rough sets theory; The neural network nodes of the middle layer are designed through genetic algorithms training; the neural network bottom-up weights and bias are obtained finally through the combination of genetic algorithms and BP algorithms. The analysis in this paper illustrates that the optimization method can improve the performance of the neural network fault diagnosis method greatly.展开更多
Although time series are frequently nonlinear in reality, people tend to use linear models to fit them under some assumptJLons unnecessarily in accordance with the truth, which unsurprisingly leads to unsatisfactory p...Although time series are frequently nonlinear in reality, people tend to use linear models to fit them under some assumptJLons unnecessarily in accordance with the truth, which unsurprisingly leads to unsatisfactory performance. This paper proposes a forecast method: Genetic programming based on least square method (GP-LSM). Inheriting the advantages of genetic algorithm (GA), without relying on the particular distribution of the data, this method can improve the prediction accuracy because of its ability of fitting nonlinear models, and raise the convergence speed benefitting from the least square method (LSM). In order to verify the vMidity of this method, the authors compare this method with seasonal auto regression integrated moving average (SARIMA) and back propagation artificial neural networks (BP-ANN). The results of empirical analysis show that forecast accuracy and direction prediction accuracy of GP-LSM are obviously better than those of the others.展开更多
Minipump is widely used in microfluidics system, active cooling system, etc. But building a high efficiency minipump is still a challenging problem. In this paper, a systematic method was developed to design, characte...Minipump is widely used in microfluidics system, active cooling system, etc. But building a high efficiency minipump is still a challenging problem. In this paper, a systematic method was developed to design, characterize and optimize a particular mechanical minipump. The optimization work was conducted to cope with the conflict between pressure head and hydraulic efficiency by an improved back-propagation neural network (BPNN) with the non-dominated sorting genetic algorithm-II (NSGA-II). The improved BPNN was utilized to predicate hydraulic performance and, moreover, was modified to improve the prediction accuracy. The NSGA-II was processed for minipump multi-objective optimization which is dominated by four impeller dimensions. During hydraulic optimization, the processing feasibility was also taken into consideration. Experiments were conducted to validate the above optimization methods. It was proved that the optimized minipump was improved by about 24 % in pressure head and 4.75 % in hydraulic efficiency compared to the original designed prototype. Meanwhile, the sensitivity test was used to analyze the influence of the four impeller dimensions. It was found that the blade outlet angle β2 and the impeller inlet diameter Do significantly influence the pressure head H and the hydraulic efficiency η, respec- tively. Detailed internal flow fields showed that the optimum model can relieve the impeller wake and improve both the pressure distribution and flow orientation.展开更多
基金Supported by the National Natural Science Foundation of China (21076090)
文摘Two artificial intelligence techniques, artificial neural network and genetic algorithm, were applied to optimize the fermentation medium for improving the nitrite oxidization rate of nitrite oxidizing bacteria. Experiments were conducted with the composition of medium components obtained by genetic algorithm, and the experimental data were used to build a BP (back propagation) neural network model. The concentrations of six medium components were used as input vectors, and the nitrite oxidization rate was used as output vector of the model. The BP neural network model was used as the objective function of genetic algorithm to find the optimum medium composition for the maximum nitrite oxidization rate. The maximum nitrite oxidization rate was 0.952 g 2 NO-2-N·(g MLSS)-1·d-1 , obtained at the genetic algorithm optimized concentration of medium components (g·L-1 ): NaCl 0.58, MgSO 4 ·7H 2 O 0.14, FeSO 4 ·7H 2 O 0.141, KH 2 PO 4 0.8485, NaNO 2 2.52, and NaHCO 3 3.613. Validation experiments suggest that the experimental results are consistent with the best result predicted by the model. A scale-up experiment shows that the nitrite degraded completely after 34 h when cultured in the optimum medium, which is 10 h less than that cultured in the initial medium.
文摘Aiming at the disadvantages of BP model in artificial neural networks applied to intelligent fault diagnosis, neural network fault diagnosis optimization method with rough sets and genetic algorithms are presented. The neural network nodes of the input layer can be calculated and simplified through rough sets theory; The neural network nodes of the middle layer are designed through genetic algorithms training; the neural network bottom-up weights and bias are obtained finally through the combination of genetic algorithms and BP algorithms. The analysis in this paper illustrates that the optimization method can improve the performance of the neural network fault diagnosis method greatly.
基金supported by the National Natural Science Foundation of China under Grant Nos.71171011 and 91224001Program for New Century Excellent Talents in University(NCET-12-0756)
文摘Although time series are frequently nonlinear in reality, people tend to use linear models to fit them under some assumptJLons unnecessarily in accordance with the truth, which unsurprisingly leads to unsatisfactory performance. This paper proposes a forecast method: Genetic programming based on least square method (GP-LSM). Inheriting the advantages of genetic algorithm (GA), without relying on the particular distribution of the data, this method can improve the prediction accuracy because of its ability of fitting nonlinear models, and raise the convergence speed benefitting from the least square method (LSM). In order to verify the vMidity of this method, the authors compare this method with seasonal auto regression integrated moving average (SARIMA) and back propagation artificial neural networks (BP-ANN). The results of empirical analysis show that forecast accuracy and direction prediction accuracy of GP-LSM are obviously better than those of the others.
文摘Minipump is widely used in microfluidics system, active cooling system, etc. But building a high efficiency minipump is still a challenging problem. In this paper, a systematic method was developed to design, characterize and optimize a particular mechanical minipump. The optimization work was conducted to cope with the conflict between pressure head and hydraulic efficiency by an improved back-propagation neural network (BPNN) with the non-dominated sorting genetic algorithm-II (NSGA-II). The improved BPNN was utilized to predicate hydraulic performance and, moreover, was modified to improve the prediction accuracy. The NSGA-II was processed for minipump multi-objective optimization which is dominated by four impeller dimensions. During hydraulic optimization, the processing feasibility was also taken into consideration. Experiments were conducted to validate the above optimization methods. It was proved that the optimized minipump was improved by about 24 % in pressure head and 4.75 % in hydraulic efficiency compared to the original designed prototype. Meanwhile, the sensitivity test was used to analyze the influence of the four impeller dimensions. It was found that the blade outlet angle β2 and the impeller inlet diameter Do significantly influence the pressure head H and the hydraulic efficiency η, respec- tively. Detailed internal flow fields showed that the optimum model can relieve the impeller wake and improve both the pressure distribution and flow orientation.