Hilbert-Huang transformation has been applied to extract eigenvectors from the pressure fluctuation signals in the spouted bed. According on these eigenvectors, the flow regimes in the spouted bed could be classified ...
详细信息
Hilbert-Huang transformation has been applied to extract eigenvectors from the pressure fluctuation signals in the spouted bed. According on these eigenvectors, the flow regimes in the spouted bed could be classified into 4 clusters including 'packed bed', 'stable spouting', 'bubbling fluidized bed' and 'slugging bed' by chaos optimized fuzzy c-means clustering algorithm. The Elman neural network was used to recognize these four flow regimes, and the parameters in the Elman neural network were optimized by adaptive fuzzy particle swarm optimizationalgorithm. The recognition accuracies of 'packed bed', 'stable spouting', 'bubbling fluidized bed' and 'slugging bed' can reach 85%, 90%, 85% and 80% respectively. (C) 2010 Elsevier B.V. All rights reserved.
Initial water rights allocation in the watershed is a typical multidimensional, nonlinear, nonnormal decision problem, and it is difficult for traditional methods to determine weights and solve the decision problem. I...
详细信息
Initial water rights allocation in the watershed is a typical multidimensional, nonlinear, nonnormal decision problem, and it is difficult for traditional methods to determine weights and solve the decision problem. In this study, a new coupled chaosoptimization-projection pursuit model is established, in which projection pursuit is adopted to reduce the dimensions of the decision problem and chaos optimization algorithm is presented to search the optimal projection direction. The model is directly driven by the sample data, and the optimal values of various schemes are calculated according to the optimal projection direction. In the coupled model, the difficulty that the objective functions and constraints must be continuous and differential can be avoided and the calculation efficiency is greatly enhanced, and the calculation of weights is objective and fair. The model proposed in this study provides a new method for initial water rights allocation in the watershed. Finally, the rationality and validity of this model is verified by a case study of initial water rights allocation in Fuhuan River.
In order to overcome the inefficiency shortcoming of traditional step-based searching method for extremum seeking in two-dimensional fractional Fourier domain, the chaosoptimization method is introduced and applied s...
详细信息
ISBN:
(纸本)9780769539607
In order to overcome the inefficiency shortcoming of traditional step-based searching method for extremum seeking in two-dimensional fractional Fourier domain, the chaosoptimization method is introduced and applied successfully in fractional Fourier transform. To accelerate the convergence further, two improved chaosoptimization methods are proposed. The performances of the proposed optimization methods are verified by comparing with step-based method and other intelligent optimization methods such as genetic algorithms, continuous ant colony algorithm and particle swarm optimization based on simulation. Results show that the second presented chaos optimization algorithm is more preferable considering computation efficiency, precision and resolution.
Experiments to investigate the jet penetration depth were carried out. The jet penetration depth increases with the increase of spouting gas velocity, spouting nozzle diameter and carrier gas density, but decreases wi...
详细信息
Experiments to investigate the jet penetration depth were carried out. The jet penetration depth increases with the increase of spouting gas velocity, spouting nozzle diameter and carrier gas density, but decreases with the rise of the static bed height, particle density, particle diameter and fluidized gas rate. The intelligent model to predict the jet penetration depth has been established based on least square support vector machine and adaptive mutative scale chaos optimization algorithm. The prediction performance of the intelligent model is better than empirical correlations and neural network. (C) 2010 Elsevier B.V. All rights reserved.
In this paper, the problem of single reservoir operation optimization is studied. Firstly, the background and mathematic model of single reservoir operation optimization are given. Then modified ant colony optimizatio...
详细信息
ISBN:
(纸本)9781424467129
In this paper, the problem of single reservoir operation optimization is studied. Firstly, the background and mathematic model of single reservoir operation optimization are given. Then modified ant colony optimization (MACO) is presented. According to the ergodicity, stochastic property and regularity of chaos, search and optimization are carried out using the chaos variables. Population entropy is introduced to judge whether the algorithm falls in local peak or not, and catastrophe operation is also adopted. Then detailed solving steps of reservoir operation optimization based on MACO are given. Lastly, an instance is given. By calculations of the instance and comparison with other algorithms, it proves the algorithm has much stronger ability of local search and better search efficiency. It also can find better solution and certifies that this method is feasible and valid.
The hybrid algorithm based on the chaos optimization algorithm and ant colony algorithm is proposed in this paper. It is an approach to solve the optimal operation issue of a reservoir. According to the randomness and...
详细信息
ISBN:
(纸本)9780769538655
The hybrid algorithm based on the chaos optimization algorithm and ant colony algorithm is proposed in this paper. It is an approach to solve the optimal operation issue of a reservoir. According to the randomness and ergodicity of chaos, by searching all the chaos variables and walking all the statuses, the hybrid algorithm can effectively increase the computing efficiency, is easy to improve the stagnation and could not fall into the local optimization. And by using the advantage of positive feedback information of the ant colony algorithm, the researching efficiency is enhanced. The result showed that the algorithm is very efficient and can rind the global optimization.
To solve the disadvantage that BP neural network is liable to get into the local minimum, a novel learning algorithm that new chaos optimizer BP neural network is proposed. By the use of the properties of ergodicity a...
详细信息
ISBN:
(纸本)9781424420957
To solve the disadvantage that BP neural network is liable to get into the local minimum, a novel learning algorithm that new chaos optimizer BP neural network is proposed. By the use of the properties of ergodicity and randomness of chaosalgorithms, and combining global rough search and local elaborate search of chaotic variable, get the global optimization weight values of neural network. By the simulation of Direct Torque Control (DTC) system based on new chaos neural network, the simulation results show that the rotor speed identification has high approximation precision and good generalization capability, and provides a new plan for the speed-sensorless DTC system.
Test selection is a problem of NP-hard solution. Genetic algorithm (GA) is a method of global searching strategy and can be used to solve the problem above. But there are several drawbacks of GA, such as bad initial g...
详细信息
ISBN:
(纸本)9787506292207
Test selection is a problem of NP-hard solution. Genetic algorithm (GA) is a method of global searching strategy and can be used to solve the problem above. But there are several drawbacks of GA, such as bad initial group, slowly searching in final phase. In order to overcome these drawbacks of GA and improve the efficiency of searching, we apply chaos optimization algorithm to GA to improve it. The basic idea of improving is that we use chaosalgorithm to produce better initial group, and apply chaos to optimize the individual of group which has been optimized though genetic operating with certain probability. Finally, we realize it though software of MATLAB and use an example to demonstrate it. Though optimizing by this improved chaos Genetic algorithm, we get better result. This has proved that this improved algorithm is efficient for solving for the problem of test selection.
<正>Test selection is a problem of NP-hard solution. Genetic algorithm (GA) is a method of global searching strategy and can be used to solve the problem *** there are several drawbacks of GA,such as bad initial g...
详细信息
<正>Test selection is a problem of NP-hard solution. Genetic algorithm (GA) is a method of global searching strategy and can be used to solve the problem *** there are several drawbacks of GA,such as bad initial group,slowly searching in final *** order to overcome these drawbacks of GA and improve the efficiency of searching,we apply chaos optimization algorithm to GA to improve *** basic idea of improving is that we use chaosalgorithm to produce better initial group,and apply chaos to optimize the individual of group which has been optimized though genetic operating with certain ***,we realize it though software of MATLAB and use an example to demonstrate *** optimizing by this improved chaos Genetic algorithm,we get better *** has proved that this improved algorithm is efficient for solving for the problem of test selection.
To solve the disadvantage that BP neural network is liable to get into the local minimum, a novel learning algorithm that new chaos optimizer BP neural network is proposed. By the use of the properties of ergodicity a...
详细信息
To solve the disadvantage that BP neural network is liable to get into the local minimum, a novel learning algorithm that new chaos optimizer BP neural network is proposed. By the use of the properties of ergodicity and randomness of chaosalgorithms, and combining global rough search and local elaborate search of chaotic variable, get the global optimization weight values of neural network. By the simulation of Direct Torque Control (DTC) system based on new chaos neural network, the simulation results show that the rotor speed identification has high approximation precision and good generalization capability, and provides a new plan for the speed-sensorless DTC system.
暂无评论