The heat transfer mechanism of thermal radiation is directly related to either the emission and propagation of electromagnetic waves or the transport of photons. Depending on the participation of the medium in space, ...
详细信息
The heat transfer mechanism of thermal radiation is directly related to either the emission and propagation of electromagnetic waves or the transport of photons. Depending on the participation of the medium in space, thermal radiation can be classified into two forms, which are surface and gas radiation, respectively. In the present study, unknown surface radiation properties are estimated by an inverse analysis for a surface radiation in an axisymmetric cylindrical enclosure. For efficiency, the repulsive particleswarmoptimization (RPSO) algorithm, which showed an outstanding effectiveness in the previous inverse gas radiation problem, is adopted as an inverse solver. By comparing the convergence rates of an objective function and the estimated accuracies with the results of the hybrid genetic algorithm (HGA) and the particleswarmoptimization (PSO) method, the performance of the RPSO algorithm is verified to be quite an efficient method as the inverse solver when applied to the retrieval of unknown properties of the surface radiation problem. (C) 2015 Elsevier Ltd. All rights reserved.
A novel Quantum-behaved particle swarm optimization algorithm with probability(P-QPSO) is introduced to improve the global convergence property of QPSO. In the proposed algorithm, all the particles keep the original e...
详细信息
A novel Quantum-behaved particle swarm optimization algorithm with probability(P-QPSO) is introduced to improve the global convergence property of QPSO. In the proposed algorithm, all the particles keep the original evolution with large probability, and do not update the position of particles with small probability, and re-initialize the position of particles with small probability. Seven benchmark functions are used to test the performance of P-QPSO. The results of experiment show that the proposed technique can increase diversity of population and converge more rapidly than other evolutionary computation methods.
Keeping particleswarm alive support vector machine optimized algorithm network traffic forecasting model(EPSO-SVM) is proposed. First, building support vector machine learning sample by calculating the delay time and...
详细信息
Keeping particleswarm alive support vector machine optimized algorithm network traffic forecasting model(EPSO-SVM) is proposed. First, building support vector machine learning sample by calculating the delay time and embedding dimension, second, learning network flow training set by using the maintaining the vitality of particleswarmoptimization support vector machine, at last, validating performance EPSO-SVM's by using set of the network traffic tests. The results showed that the proposed model can improve the forecasting precision of network traffic. It has great practical application value.
A cloud adaptive chaos particle swarm optimization algorithm is proposed for economic load dispatch problems of power system,which has the characteristics of nonlinear,non-convex and *** cloud generator was used to ad...
详细信息
ISBN:
(纸本)9781510806474
A cloud adaptive chaos particle swarm optimization algorithm is proposed for economic load dispatch problems of power system,which has the characteristics of nonlinear,non-convex and *** cloud generator was used to adaptively adjust the inertia weight of each particles,so as to optimize their optimization direction and improve the convergence speed of the algorithm;and the chaotic variation operation was introduced to adjust the particle's positions,so as to improve the diversity of the solution and avoid falling into local *** of 6 unit system demonstrates that the proposed algorithm has high accuracy and quick speed used in economic load dispatch of power system.
A novel Quantum-behaved particle swarm optimization algorithm with probability(P-QPSO)is introduced to improve the global convergence property of *** the proposed algorithm,all the particles keep the original evolutio...
详细信息
ISBN:
(纸本)9781467365949
A novel Quantum-behaved particle swarm optimization algorithm with probability(P-QPSO)is introduced to improve the global convergence property of *** the proposed algorithm,all the particles keep the original evolution with large probability,and do not update the position of particles with small probability,and re-initialize the position of particles with small *** benchmark functions are used to test the performance of *** results of experiment show that the proposed technique can increase diversity of population and converge more rapidly than other evolutionary computation methods.
In order to solve the problem of insufficient adaptive ability of the network intrusion detection model, the large-scale fast search capability of the particleswarmoptimization (PSO) algorithm is introduced into the...
详细信息
ISBN:
(纸本)9798331532109;9798331532093
In order to solve the problem of insufficient adaptive ability of the network intrusion detection model, the large-scale fast search capability of the particleswarmoptimization (PSO) algorithm is introduced into the intrusion detection model. In order to solve the problem that PSO is easy to fall into local optimality, the genetic algorithm (GA) is introduced. An improved particleswarmoptimization (GAPSO) algorithm based on genetic algorithm is proposed. This algorithm optimizes the parameters that are difficult to adjust in the lightweight gradient boosting machine (LightGBM) algorithm, so that the PSO algorithm can quickly converge while ensuring the optimization accuracy, and obtain the optimal network intrusion detection model. Experimental results show that GAPSO is more effective than the basic PSO algorithm when dealing with high-dimensional, complex structure optimization problems.
Atomic-scale simulations are important tools for microscopic phenomena study and material design, especially the cost-effective and large-scale reactive force field (ReaxFF). However, the poor transferability and tedi...
详细信息
Atomic-scale simulations are important tools for microscopic phenomena study and material design, especially the cost-effective and large-scale reactive force field (ReaxFF). However, the poor transferability and tedious training process of ReaxFF parameters constrain its accuracy and application, urgently requiring more efficient automatic optimization methods. In this study, we propose a multi-objective optimization method that combines simulated annealing algorithm (SA) and particle swarm optimization algorithm (PSO) to optimize the ReaxFF parameters. Moreover, we innovatively introduce a concentrated attention mechanism (CAM) to improve the accuracy of parameter optimization. Finally, this study selects the H/S system as the testing target to evaluate the accuracy and efficiency of the above algorithm. It is found that our algorithm is faster and more accurate than traditional metaheuristic methods. Our automated optimization scheme efficiently optimizes ReaxFF parameters, providing crucial support for atomic-scale simulations.
In the present study, an artificial neural network (ANN) together with a heuristic algorithm, called particleswarmoptimization (PSO), was used to set up a methodology for selecting the optimal process parameters for...
详细信息
In the present study, an artificial neural network (ANN) together with a heuristic algorithm, called particleswarmoptimization (PSO), was used to set up a methodology for selecting the optimal process parameters for the mu EDM process. The developed methodology is characterized by a double direction functionality responding to different industry needs. Usually, in the industrial scenario, the operators are bound by the project specifications or by the limited availability of time. For this reason, a methodology tested only on a specific workpiece material, that involves limited input parameters or developed for the optimization of a single performance is limiting. The developed 2-steps model leaves operators free to establish which factors to impose for the optimization and allows to define the best solution for the production of a part. The validation of the model shows a good fit between predicted and experimental results.
The aim of this work is to present an adaptive maximum power point tracking (MPPT) approach for photovoltaic (PV) power generation system. Integrating the extension theory as well as the conventional perturb and obser...
详细信息
The aim of this work is to present an adaptive maximum power point tracking (MPPT) approach for photovoltaic (PV) power generation system. Integrating the extension theory as well as the conventional perturb and observe method, an maximum power point (MPP) tracker is made able to automatically tune tracking step size by way of the category recognition along a P-V characteristic curve. Accordingly, the transient and steady state performances in tracking process are improved. Furthermore, an optimization approach is proposed on the basis of a particleswarmoptimization (PSO) algorithm for the complexity reduction in the determination of weighting values. At the end of this work, a simulated improvement in the tracking performance is experimentally validated by an MPP tracker with a programmable system-on-chip (PSoC) based controller. (C) 2014 Elsevier Ltd. All rights reserved.
Loss circulation is a common problem in drilling industry that causes high expenditure on drilling companies. Nowadays minimizing of loss circulation is a main goal and preference for drilling engineers. Artificial in...
详细信息
Loss circulation is a common problem in drilling industry that causes high expenditure on drilling companies. Nowadays minimizing of loss circulation is a main goal and preference for drilling engineers. Artificial intelligence (Al) is a new method of solving engineering problems that has the ability to consider all effective parameters simultaneously. Moreover, it has generalization and the ability to learn directly from field data. In this paper, two models were designed using Al and data of 38 wells located in Maroun oil field. Both models were developed by modular neural network, to predict loss circulation in quality and quantity. Then, the particle swarm optimization algorithm was used to minimize loss circulation. The accuracy of two models in predicting loss circulation quantitatively and qualitatively is 0.94 and 0.98 %, respectively.
暂无评论