Firstly, particleswarmoptimization fuzzy neural network (PSOFNN) is proposed and the algorithm How of PSOFNN are given in this ***, PSOFNN is applied in soft-sensor modeling of acrylonitrile *** new method assumes t...
详细信息
Firstly, particleswarmoptimization fuzzy neural network (PSOFNN) is proposed and the algorithm How of PSOFNN are given in this ***, PSOFNN is applied in soft-sensor modeling of acrylonitrile *** new method assumes that fuzzy neural network (FNN) is used to construct the soft-sensor model of acrylonitrile yield and particle swarm optimization algorithm (PSO) is employed to optimize parameters of ***, how to choose the auxiliary variables of soft-sensor is studied *** results show that the model based on PSOFNN has higher precision and better performance than the model based on *** method proposed by this paper is feasible and effective in soft-sensor of acrylonitrile yield.
An online speciality store is a kind of small retail shop on the internet that specializes in some merchandise of the same brand or with the similar function. Putting low prices on some special items is a special pric...
详细信息
ISBN:
(纸本)9781424408849
An online speciality store is a kind of small retail shop on the internet that specializes in some merchandise of the same brand or with the similar function. Putting low prices on some special items is a special pricing strategy in online speciality store, which will increase the flow of the web site and accelerate the sales of other products. The phenomenon that there is positive sale association among different items is called as size effect in this paper. A multi-objective model was built and a particle swarm optimization algorithm was proposed to solve this holistic pricing problem. Maximum of the gross profits and sales was the objective of the model. Simulation results reveal that the model can help online speciality store get more gross profits and more sales.
In high bit rate optical fiber communication systems, Polarization mode dispersion (PMD) is one of the main factors to signal distortion and needs to be compensated. PMD monitoring system is the key integral part of a...
详细信息
ISBN:
(纸本)9783540725893
In high bit rate optical fiber communication systems, Polarization mode dispersion (PMD) is one of the main factors to signal distortion and needs to be compensated. PMD monitoring system is the key integral part of an adaptive PMD compensator. The degree of polarization (DOP) ellipsoid obtained by using a polarization scrambler can be used as a feedback signal for automatic PMD compensation. Generally, more than several thousands of sampling data of states of polarization (SOP) must be collected to insure getting a correct DOP ellipsoid. This would result in an unacceptable time consuming for adaptive PMD compensation. In this paper, we introduce the particleswarmoptimization (PSO) algorithm in determining the real-time DOP ellipsoid with high precision, requiring only 100 sampling data of SOPs. Experimental results confirm that the PSO algorithm is effective for ellipsoid data fitting with high precision within 250ms using our hardware environment.
This paper presents the study of clutch magnet actuators. Two topologies, considering different magnetic constraints of saturation are designed in order to generate powerful engaging force in a limited volume. The mag...
详细信息
ISBN:
(纸本)9781424412600
This paper presents the study of clutch magnet actuators. Two topologies, considering different magnetic constraints of saturation are designed in order to generate powerful engaging force in a limited volume. The magnetic models are based on a reluctance equivalent magnetic circuit considering the magnet flux leakages. The model results are then compared and validated with finite element computations and measurements on different built actuators. Finally, the validated analytical models are coupled to a particle swarm optimization algorithm in order to maximize the transmitted torque or the torque to volume ratio. The study shows that a reluctance circuit model validated by some experimentation and coupled to a particleswarmalgorithm gives a solid and efficient basis for the design and the optimization of clutch magnet actuators.
Mechanic property prediction of hot rolled strip has enormous economic benefits and vast applied *** neural network is used almost in Mechanic property prediction of hot rolled strip in *** BP has local infinitesimal ...
详细信息
ISBN:
(纸本)9780972147903
Mechanic property prediction of hot rolled strip has enormous economic benefits and vast applied *** neural network is used almost in Mechanic property prediction of hot rolled strip in *** BP has local infinitesimal *** with PSO(particleswarmoptimization) global optimizationalgorithm,a new PSO-BP neural network is *** PSO-BP algorithm takes on advantages of global optimization ability,the rapid constringency of BP rapid training algorithm,the ability of nonlinear approach of multilayer feedforward network,and improves the performance of Neural ***-BP neural network model has good application foreground.
A new support vector machine (SVM) optimized by an improved particleswarmoptimization (PSO) combined with simulated annealing algorithm (SA) was proposed. By incorporating with the simulated annealing method, ...
详细信息
A new support vector machine (SVM) optimized by an improved particleswarmoptimization (PSO) combined with simulated annealing algorithm (SA) was proposed. By incorporating with the simulated annealing method, the global searching capacity of the particleswarmoptimization(SAPSO) was enchanced, and the searching capacity of the particleswarmoptimization was studied. Then, the improyed particle swarm optimization algorithm was used to optimize the parameters of SVM (c,σ and ε). Based on the operational data provided by a regional power grid in north China, the method was used in the actual short term load forecasting. The results show that compared to the PSO-SVM and the traditional SVM, the average time of the proposed method in the experimental process reduces by 11.6 s and 31.1 s, and the precision of the proposed method increases by 1.24% and 3.18%, respectively. So, the improved method is better than the PSO-SVM and the traditional SVM.
In this paper we investigate the application of the particleswarmoptimization (PSO) technique for solving the Hardware/Software partitioning problem. The PSO is attractive for the Hardware/Software partitioning prob...
详细信息
ISBN:
(纸本)9781424408986
In this paper we investigate the application of the particleswarmoptimization (PSO) technique for solving the Hardware/Software partitioning problem. The PSO is attractive for the Hardware/Software partitioning problem as it offers reasonable coverage of the design space together with O(n) main loop's execution time, where n is the number of proposed solutions that will evolve to provide the final solution. We carried out several tests on a hypothetical, relatively-large Hardware/Software partitioning problem using the PSO algorithm as well as the Genetic algorithm (GA), which is another evolutionary technique. We found that PSO outperforms GA in the cost function and the execution time. For the case of unconstrained design problem, we tested several hybrid combinations of PSO and GA algorithms;including PSO then GA, GA then PSO, GA followed by GA, and finally PSO followed by PSO. We found that a PSO followed by GA algorithm gives small or no improvement at all, while a GA then PSO algorithm gives the same results as the PSO alone. The PSO algorithm followed by another PSO round gave the best result as it allows another round of domain exploration. The second PSO round assign new randomized velocities to the particles, while keeping best particle positions obtained in the first round. We propose to name this successive PSO algorithm as the Re-excited PSO algorithm.
To solve the problem of network expansion, an improved particle swarm optimization algorithm (PSO) is proposed in this paper. This method initialized the particleswarm according to borderline search mind, made the in...
详细信息
ISBN:
(纸本)1424400600
To solve the problem of network expansion, an improved particle swarm optimization algorithm (PSO) is proposed in this paper. This method initialized the particleswarm according to borderline search mind, made the initialized particle near the safety line, overcome the defect of the uncertainty in the rational distribution of particle initialization, optimizing the range of the initialization. Numerical simulation results of power transmission network planning demonstrate the feasibility and efficiency of this method, and shed new light on the further improving of PSO.
As far as the impact of tropospheric ozone (O-3) On human heath and plant life are concerned, forecasting its daily maximum level is of great importance in Hong Kong as well as other metropolises in the world. This pa...
详细信息
As far as the impact of tropospheric ozone (O-3) On human heath and plant life are concerned, forecasting its daily maximum level is of great importance in Hong Kong as well as other metropolises in the world. This paper proposed a multi-layer perceptron (MLP) model with a novel hybrid training method to perform the forecasting task. The training method synergistically couples a stochastic particleswarmoptimization (PSO) algorithm and a deterministic Levenberg-Marquardt (LM) algorithm, which aims at exploiting the advantage of both. The performance of such a hybrid model is further compared with ones obtained by the MLP model trained individually by these two training methods mentioned above. Based on original data collected from two typical monitoring sites with different O-3 formation and transportation mechanism, the simulation results show that the hybrid model is more robust and efficient than the other two models by not only producing good results during non-episodes but also providing better consistency with the original data during episodes. (c) 2005 Elsevier Ltd. All rights reserved.
The paper introduces an intelligent decision-making model which is based on the application of artificial neural networks (ANN) and swarm intelligence technologies. The proposed model is used to generate one-step forw...
详细信息
The paper introduces an intelligent decision-making model which is based on the application of artificial neural networks (ANN) and swarm intelligence technologies. The proposed model is used to generate one-step forward investment decisions for stock markets. The ANN are used to make the analysis of daily stock returns and to calculate one day forward decision for purchase of the stocks. Subsequently the particleswarmoptimization (PSO) algorithm is applied in order to select the "the best" ANN for the future investment decisions and to adapt the weights of other networks towards the weights of the best network. The experimental investigations were made considering different forms of decision-making model: different number of ANN, ANN inputs, sliding windows, and commission fees. The paper introduces the decision-making model, its evaluation results and discusses its application possibilities.
暂无评论