In the paper, Radial Basis Function(RBF) neural network optimized by particle swarm optimization algorithm is proposed to fault diagnosis for embedded system. The parameters of Radial Basis Function(RBF) neural networ...
详细信息
In the paper, Radial Basis Function(RBF) neural network optimized by particle swarm optimization algorithm is proposed to fault diagnosis for embedded system. The parameters of Radial Basis Function(RBF) neural network are selected by particle swarm optimization algorithm to solve the problem of the parameters selection of Radial Basis Function(RBF) neural network. In order to testify the superiority of Radial Basis Function(RBF) neural network optimized by particle swarm optimization algorithm in fault diagnosis for embedded system, traditional Radial Basis Function(RBF) neural network and Back Propagation(BP) neural network are applied to compare with the proposed Radial Basis Function(RBF) neural network optimized by particle swarm optimization algorithm. The comparison results show that the diagnosis accuracy of Radial Basis Function(RBF) neural network optimized by particle swarm optimization algorithm is the best methods among traditional Radial Basis Function(RBF) neural network, Back Propagation(BP) neural network and Radial Basis Function(RBF) neural network optimized by particle swarm optimization algorithm.
With the rapid development of urban rail transit, the problem of energy consumption is drawing more and more attentions. Based on the utilization of regenerative braking energy among trains, this paper studies the ene...
详细信息
ISBN:
(纸本)9781467365970
With the rapid development of urban rail transit, the problem of energy consumption is drawing more and more attentions. Based on the utilization of regenerative braking energy among trains, this paper studies the energy-efficient operation method. We propose an utilization strategy of regenerative energy among trains. Based on the proposed strategy, we set up the energy-saving model which optimizes the timetable and speed profile of trains simultaneously. Based on the particle swarm optimization algorithm, taking Beijing Yizhuang subway line and Changping subway line as examples of short section and long section for simulation, we verify the effectiveness of the proposed method. It is showed that the energy consumption of Yizhuang line and Changping line can be reduced by 3.2% and 5.5%, respectively, through improving the utilization of regenerative energy.
An energy storage system (ESS) can provide regulation and reserve capacities for the power system, and hence alleviate the negative impacts of renewable energy such as wind power. Nonetheless, challenges remain as to ...
详细信息
ISBN:
(纸本)9781510830059
An energy storage system (ESS) can provide regulation and reserve capacities for the power system, and hence alleviate the negative impacts of renewable energy such as wind power. Nonetheless, challenges remain as to how the operation of wind farms and ESSs can be coordinated efficiently, and how transmission system expansion planning will be impacted. This paper addresses these challenges by: (1) examining the correlation between the cost of ESS and its cycle life, exampled with a Natrium Sulfur (NaS) ESS; (2) investigating the integrated operation of a wind farm and an ESS taking into account both the cost of ESSs and their smoothing effect of wind power fluctuations; (3) developing a transmission system expansion planning model with particular reference to both the investment cost of the transmission system concerned and the operating costs of wind farms and ESSs; and (4) solving the developed planning formulation using an improved particle swarm optimization algorithm. The proposed planning method is illustrated through its applications to two sample systems.
Iron ore is the main raw material of the production in iron and steel enterprises in China. It is a non-renewable resource and with limited reserves. In this paper, in combination with the practical situation of the m...
详细信息
Iron ore is the main raw material of the production in iron and steel enterprises in China. It is a non-renewable resource and with limited reserves. In this paper, in combination with the practical situation of the mine, an integer linear programming model of a strip mining block scheduling problem is established with the scientific, reasonable, and economical principle. The maximization of mining profit is set as the goal under the precedence constraints and production capacity constraints. This paper designs an improved particle swarm optimization algorithm to solve the problem and compares with results with CPLEX optimizing software. According to the results of different scale experiment, the improved particle swarm optimization algorithm has better performance.
This study was developed in the context of new challenges imposed by the recast of the Energy Performance of Buildings Directive 2010/31/EU (EPBD) and its supplementing regulation. The aim is to find the cost-optimal ...
详细信息
This study was developed in the context of new challenges imposed by the recast of the Energy Performance of Buildings Directive 2010/31/EU (EPBD) and its supplementing regulation. The aim is to find the cost-optimal level for the French single-family building typology, while providing an effective method to deal with a huge number of simulations corresponding to a large number of building configurations. The method combines the use of TRNSYS, dynamic energy simulation software, with GenOpt, Generic optimization program. The building that was taken as a reference is a real low-consumption house located in Amberieu-en-Bugey, Rhone-Alpes, France. The model was created and calibrated in TRNSYS and the energy efficiency measures, concerning different technologies for envelope systems and technical systems, were set up as parameters in GenOpt. After a research on the French market, a cost function was created for each parameter and the global cost function (EN15459 Standard) was taken as objective function for the optimization. The particle swarm optimization algorithm was used to minimize the objective function and find the cost-optimal building configuration within the current regulatory framework. (C) 2014 Elsevier B.V. All rights reserved.
In this work, a method for the single-objective optimization of material distribution of simply supported functionally graded isotropic plates is presented. The material composition is assumed to vary only in the thic...
详细信息
In this work, a method for the single-objective optimization of material distribution of simply supported functionally graded isotropic plates is presented. The material composition is assumed to vary only in the thickness direction. Piecewise cubic interpolation of volume fractions are used to calculate volume fractions of constituent material phases at a point;these fractions are defined at a limited number of evenly spaced control points. The effective material properties of the plate are obtained by applying linear rule of mixtures. Behavior of functionally graded plate is predicted by the assumptions of the third-order shear deformation theory of Reddy. Exact solutions for deflections and stresses of simply supported plates are presented by using Navier type solution technique. Those volume fractions at control points that are selected as decision variables are optimized by two evolutionary algorithms: (1) Real-coded genetic algorithm and (2) particle swarm optimization algorithm. Three models are optimized as primary goal to verify the capability and efficiency of the proposed model with flexibility and stress constraints under various transverse loads. Secondary goal of this article is survey accuracy and convergence of two algorithms aforementioned. The proposed framework for designing functionally graded plates under pure mechanical conditions has been furnished by the founded results. (C) 2013 Elsevier Ltd. All rights reserved.
By introducing the fractional-order difference into the updating formulas of the velocity and position,fractional-order particle swarm optimization algorithm is proposed. The effects on the convergence rate and accura...
详细信息
By introducing the fractional-order difference into the updating formulas of the velocity and position,fractional-order particle swarm optimization algorithm is proposed. The effects on the convergence rate and accuracy are analyzed, by introducing fractional-orders in the updating formulas for the velocity and position. Moreover, the linear increasing methods to adjust the fractional-orders are proposed. Compared with the standard particle swarm optimization algorithm, the higher convergence rate is achieving to improve the accuracy of the optimal result. Finally, five standard functions are tested, and the results of the numerical experiments illustrate the effectiveness of the fractional-order particleswarmoptimization
The transport line used in a terahertz FEL device has to transport electron beam through the entire system efficiently and meet the requirements of the beam parameters at the undulator entrance. Due to space limitatio...
详细信息
The transport line used in a terahertz FEL device has to transport electron beam through the entire system efficiently and meet the requirements of the beam parameters at the undulator entrance. Due to space limitations, the size of the magnets (five quadrupoles and two bending magnets) employed in the transport line was limited, and some devices were densely packed. In this paper, analyses of the effect of fringe fields and magnetic interference of magnets are presented. 3D models of these magnets are built and their linear optical properties are compared with those obtained by hard edge models. The results indicated that the effects of these factors are significant and they would cause a mismatch of the beam at the exit of the transport line under the preliminary lattice design. To solve this problem, the beam was re-matched using the particle swarm optimization algorithm. (C) 2014 Elsevier B.V. All rights reserved.
To ensure security during the excavation process of an earth pressure balance shield, this paper presents an optimal control method that accounts for the tunnel face's stability. The tunnel face is controlled by a...
详细信息
To ensure security during the excavation process of an earth pressure balance shield, this paper presents an optimal control method that accounts for the tunnel face's stability. The tunnel face is controlled by an optimal screw conveyor speed derived from the particle swarm optimization algorithm for a designed stable normal vector angle range on the distribution surface of the chamber pressure field. These normal vector angles can be computed online by measuring the changes to the earth pressure in the shield's chamber using a BP neural network model of the chamber pressure field distribution. An experimental example that uses excavation data from an actual EPB shield is given to illustrate the effectiveness of the proposed method. (C) 2014 Elsevier B.V. All rights reserved.
In this article, the numerical techniques are presented for the solution of Troesch's problem based on neural networks optimized with three different methods including particleswarmoptimization (PSO), active set...
详细信息
In this article, the numerical techniques are presented for the solution of Troesch's problem based on neural networks optimized with three different methods including particleswarmoptimization (PSO), active set (AS) and PSO hybridized with AS (PSO-AS) algorithms. The variable transformation is applied in order to convert the original problem to a transformed problem which is relatively less stiff to solve. Feed-forward artificial neural networks are used to model the transformed problem. Learning of adjustable parameters is made with PSO, AS and PSO-AS algorithms. The proposed methodologies are applied to a number of cases for stiff and non-stiff boundary value problems. The comparative analyses are carried out with other standard numerical solutions, as well as approximate analytical solver. (C) 2014 Elsevier Inc. All rights reserved.
暂无评论