On the basis of analyzing the particleswarmoptimization (PSO) algorithm and support vector machine (SVM), this paper applies the PSO algorithm with last out mechanism to optimize the parameters of SVM. Then, the PSO...
详细信息
On the basis of analyzing the particleswarmoptimization (PSO) algorithm and support vector machine (SVM), this paper applies the PSO algorithm with last out mechanism to optimize the parameters of SVM. Then, the PSO-SVM model about a practical soft-sensor of gasoline endpoint of delayed coking plant is constructed. The method takes advantages of the minimum structure risk of SVM and the quickly globally optimizing ability of PSO for soft sensor modeling. The simulation results show that the model has effective generalization performance and higher precision.
In order to extract features for Brillouin scattering spectrum of distributed sensing systems with high accuracy, a novel fitting algorithm, using a hybrid algorithm based on particle swarm optimization algorithm and ...
详细信息
In order to extract features for Brillouin scattering spectrum of distributed sensing systems with high accuracy, a novel fitting algorithm, using a hybrid algorithm based on particle swarm optimization algorithm and Levenberg-Marquardt algorithm to optimize the optimization process of radial basis function networks, is explanatorily proposed. Compared the proposed algorithm with traditional BP neural networks, the five times polynomial curve and piecewise cubic spline interpolation in fitting the simulative And experimental spectrum, respectively, the evaluation parameter is relatively better than other three algorithms under the same experiment with different pulse widths. The numerical and experimental results showed that modified RBFN networks have some referential roles, which can guarantee the accurate measurement of Brillouin scattering spectrum. (C) 2012 Elsevier GmbH. All rights reserved.
Harmony search (HS) algorithm is a good meta-heuristic intelligent optimization method and it does depend on imitating the music improvisation process to generate a perfect state of harmony. However, intelligent optim...
详细信息
ISBN:
(纸本)9783037857816
Harmony search (HS) algorithm is a good meta-heuristic intelligent optimization method and it does depend on imitating the music improvisation process to generate a perfect state of harmony. However, intelligent optimization methods is easily trapped into local optimal, HS is no exception. In order to modify the optimization performance of HS, a new variant of harmony search algorithm is proposed in this paper. The variant integrate the position updating of the particle swarm optimization algorithm with pitch adjustment operation, and dynamically adjust the key parameter pitch adjusting rate (PAR) and bandwidth (BW). Several standard benchmarks are to be tested. The numerical results demonstrated the superiority of the proposed method to the HS and recently developed variants (HIS, and GHS).
The fatigue life prognosis of concrete is becoming more important with the development for demanding higher quality and safety in industrial. However, effective methods for this prognosis are still in need now, due to...
详细信息
ISBN:
(纸本)9783037855911
The fatigue life prognosis of concrete is becoming more important with the development for demanding higher quality and safety in industrial. However, effective methods for this prognosis are still in need now, due to the feature of concrete. This paper proposes the extended grey Markov model (i.e. EGMM) for fatigue life prognosis of concrete. Firstly, the GM (1, 1, lambda(1), lambda(2)) (i.e. EGM) is proposed by integrating the particle swarm optimization algorithm (PSOA) with GM (1, 1) (i.e. GM). Then the Markov model is integrated with EGM and a novel prognosis method of the extended grey Markov model is proposed. The EGMM is used to combine the health states and transition probability. And a real case study is used to demonstrate the implementation and potential applications of the proposed fatigue life prognosis approach on concrete.
In this paper, a detailed research about aeroengine small perturbation State Variable Model (SVM) has been carried out. The small perturbation SVM was obtained by using partial derivative method and the particleswarm...
详细信息
ISBN:
(纸本)9781479903337
In this paper, a detailed research about aeroengine small perturbation State Variable Model (SVM) has been carried out. The small perturbation SVM was obtained by using partial derivative method and the particleswarmoptimization (PSO) algorithm was selected to optimize parameter matrices. On the basis of comparison, the calculation results of the SVM have quite remarkable consistency with those results calculated by the nonlinear model. In order to better verify the accuracy and efficiency of this method, a real-time piecewise linear dynamic model (RPLDM) was constructed;and a transient simulation on sea-level condition was carried out. The results showed that the proposed approach to establishing the small perturbation SVM and the RPLDM was highly rated in validity and applicability.
There have many problems such as multi-interference factors, large delay and difficult to establish accurate mathematical model in temperature control system of water-coal-mixture gasifier. The gasifier temperature co...
详细信息
ISBN:
(纸本)9781479913909
There have many problems such as multi-interference factors, large delay and difficult to establish accurate mathematical model in temperature control system of water-coal-mixture gasifier. The gasifier temperature control is general realized by fuzzy controller in traditional method, however, the temperature control effect is not very good because the performance of fuzzy controller is affected by many factors. Considering that particleswarmoptimization(PSO) algorithm has simple operation and fast convergence, the coding of fuzzy rules are completed by defining an equivalent probability matrix, the appropriate objective function is selected as particle fitness function. particles with higher fitness degree are obtained by iterative optimization, as the fuzzy control rule, which is applied to the gasifier temperature control. The results of application show the optimized control effect is much better than the original fuzzy controller in the rapidity despite the loss in the stability, to achieve optimal control.
Due to the complex relations among the various factors, the nonlinear calculation of aircraft fuel consumption is very difficult. The purpose of this paper is to present a simplified method to estimate aircraft fuel c...
详细信息
ISBN:
(纸本)9783037856932
Due to the complex relations among the various factors, the nonlinear calculation of aircraft fuel consumption is very difficult. The purpose of this paper is to present a simplified method to estimate aircraft fuel consumption using a novel particleswarm neural network. Fuel consumption information obtained directly from QAR recorded flight data is trained by the neural network. The method can avoid the high cost of flight testing and wind tunnel testing. An improved particle swarm optimization algorithm embeds neural network topology to replace the network BP learning algorithm. The experimental results demonstrate that the proposed method integrates a new particleswarm neural network system, and significantly improves the system's learning ability and prediction of evolutionary effects.
Based on the probabilistic loss model of distribution network and the improved hybrid particleswarmalgorithm, a reactive power optimizationalgorithm is presented, which encompasses the effects of stochastic wind sp...
详细信息
ISBN:
(纸本)9783037856680
Based on the probabilistic loss model of distribution network and the improved hybrid particleswarmalgorithm, a reactive power optimizationalgorithm is presented, which encompasses the effects of stochastic wind speed and load. Firstly, with the control vector dimension's length augmented and with the probabilistic loss method built, the reactive power optimization model is presented. Secondly, with the Niche operations embedded into the original PSO, an improved hybrid PSO algorithm is presented. Lastly, the corresponding software system program is developed in VC++ language and on basis of SQL SERVER platform. While this software system being supplied into a case, the experimental data have proved that this algorithm possesses more adaptability. At the same time, compared with the RTS algorithm, the calculating process is speeded.
RBF neural network with the parameters randomly selected may have unstabilized error. hi this paper on this problem we improve the RBFNN by introducing particle swarm optimization algorithm, and use the algorithm of s...
详细信息
ISBN:
(纸本)9783037856529
RBF neural network with the parameters randomly selected may have unstabilized error. hi this paper on this problem we improve the RBFNN by introducing particle swarm optimization algorithm, and use the algorithm of searching optimization process to adjust the three parameters of RBFNN. Through simulating four groups of test data by improved PSO-RBFNN network, we get optimal parameters. The simulation shows that the error of the improved network is smaller.
Harmony search (HS) algorithm is a good meta-heuristic intelligent optimization method and it does depend on imitating the music improvisation process to generate a perfect state of harmony. However, intelligent optim...
详细信息
ISBN:
(纸本)9783037858653
Harmony search (HS) algorithm is a good meta-heuristic intelligent optimization method and it does depend on imitating the music improvisation process to generate a perfect state of harmony. However, intelligent optimization methods is easily trapped into local optimal, HS is no exception. In order to improve the performance of HS, a new variant of harmony search algorithm is proposed in this paper. The variant introduce a new crossover operation into HS, and design a strategy to adjust parameter pitch adjusting rate (PAR) and bandwidth (BW). Several standard benchmarks carried out to be tested. The numerical results demonstrated that the superiority of the proposed method to the HS and recently developed variants (IHS, and GHS).
暂无评论