The present study is to improve the volume flow rate of an axial fan through optimizing the blade shape under the demand for a specified static pressure. Fourteen design variables were selected to control the blade ca...The present study is to improve the volume flow rate of an axial fan through optimizing the blade shape under the demand for a specified static pressure. Fourteen design variables were selected to control the blade camber lines and the stacking line and the values of these variables were determined by using the experimental design method of the Latin Hypercube Sampling (LHS) to generate forty designs. The optimization was carried out using the genetic algorithm (GA) coupled with the artificial neural network (ANN) to increase the volume flow rate of the axial fan under the constraint of a specific motor power and a required static pressure. Differences in the aerodynamic performance and the flow characteristics between the original model and the optimal model were analyzed in detail. The results showed that the volume flow rate of the optimal model increased by 33%. The chord length, the installation angle and the cascade turning angle changed considerably. The forward leaned blade was beneficial to improve the volume flow rate of the axial fan. The axial velocity distribution and the static pressure distribution on the blade surface were improved after optimization.展开更多
This paper chooses passenger flow data of some stations in China from January 2015 to March 2016, and the time series prediction model of BP neural network for railway passenger flow is established. But because of its...This paper chooses passenger flow data of some stations in China from January 2015 to March 2016, and the time series prediction model of BP neural network for railway passenger flow is established. But because of its slow convergence speed and easily falling into local optimal solution of the problem, we propose to improve the time series model of BP neural network by genetic algorithm to predict railway passenger flow. Experimental results show that the improved method has higher prediction accuracy and better nonlinear fitting ability.展开更多
For the great significance of the prediction of control parameters selected for hot-rolling and the evaluation of hot-rolling quality for the analysis of prod uction problems and production management, the selection o...For the great significance of the prediction of control parameters selected for hot-rolling and the evaluation of hot-rolling quality for the analysis of prod uction problems and production management, the selection of hot-rolling control parameters was studied for microalloy steel by following the neural network principle. An experimental scheme was first worked out for acquisition of sample data, in which a gleeble-1500 thermal simolator was used to obtain rolling temperature, strain, stain rate, and stress-strain curves. And consequently the aust enite grain sizes was obtained through microscopic observation. The experimental data was then processed through regression. By using the training network of BP algorithm, the mapping relationship between the hotrooling control parameters (rolling temperature, stain, and strain rate) and the microstructural paramete rs (austenite grain in size and flow stress) of microalloy steel was function appro ached for the establishment of a neural network-based model of the austeuite grain size and flow stress of microalloy steel. From the results of estimation made with the neural network based model, the hot-rolling control parameters can be effectively predicted.展开更多
In the multiple protocol label-switched (MPLS) networks, the commodities are transmitted by the label-switched paths (LSPs). For the sake of reducing the total cost and strengthening the central management, the MPLS n...In the multiple protocol label-switched (MPLS) networks, the commodities are transmitted by the label-switched paths (LSPs). For the sake of reducing the total cost and strengthening the central management, the MPLS networks restrict the number of paths that a commodity can use, for maintaining the quality of service (QoS) of the users, the demand of each commodity must be satisfied. Under the above conditions, some links in the network may be too much loaded, affecting the performance of the whole network drastically. For this problem, in [1], we proposed two mathematical models to describe it and a heuristic algorithm which quickly finds transmitting paths for each commodity are also presented. In this paper, we propose a new heuristic algorithm which finds a feasible path set for each commodity, and then select some paths from the path set through a mixed integer linear programming to transmit the demand of each commodity. This strategy reduces the scale of the original problem to a large extent. We test 50 instances and the results show the effectiveness of the new heuristic algorithm.展开更多
Most of the existing opportunistic network routing protocols are based on some type of utility function that is directly or indirectly dependent on the past behavior of devices. The past behavior or history of a devic...Most of the existing opportunistic network routing protocols are based on some type of utility function that is directly or indirectly dependent on the past behavior of devices. The past behavior or history of a device is usually referred to as contacts that the device had in the past. Whatever may be the metric of history, most of these routing protocols work on the realistic premise that node mobility is not truly random. In contrast, there are several oracles based methods where such oracles assist these methods to gain access to information that is unrealistic in the real world. Although, such oracles are unrealistic, they can help to understand the nature and behavior of underlying networks. In this paper, we have analyzed the gap between these two extremes. We have performed max-flow computations on three different opportunistic networks and then compared the results by performing max-flow computations on history generated by the respective networks. We have found that the correctness of the history based prediction of history is dependent on the dense nature of the underlying network. Moreover, the history based prediction can deliver correct paths but cannot guarantee their absolute reliability.展开更多
In this paper, two new sandwich algorithms for the convex curve approximation are introduced. The proofs of the linear convergence property of the first method and the quadratic convergence property of the second meth...In this paper, two new sandwich algorithms for the convex curve approximation are introduced. The proofs of the linear convergence property of the first method and the quadratic convergence property of the second method are given. The methods are applied to approximate the efficient frontier of the stochastic minimum cost flow problem with the moment bicriterion. Two numerical examples including the comparison of the proposed algorithms with two other literature derivative free methods are given.展开更多
Network calculus is an evolving new methodology for backlog and delay analysis of packet-switching networks. With network calculus we are able to compute tight bounds on delays,backlogs,and effective bandwidths in a l...Network calculus is an evolving new methodology for backlog and delay analysis of packet-switching networks. With network calculus we are able to compute tight bounds on delays,backlogs,and effective bandwidths in a lossless setting applicable to packet-switching networks and better understand some physical properties of networks. In this paper,the basic network calculus concepts of arrival curves and service curves are introduced.Then we provide the approach for modeling leaky-bucket,generic cell rate algorithm(GCRA),constant bit rate(CBR)flow, variable bit rate(VBR) flow with arrival curve.It is shown that all rate-based packet schedulers can be by a simple rate latency service curve.And by applying these fundamental rules of network calculus,bounds on delay, buffer,effective bandwidth for leaky bucket,GCRA,CBR and VBR can be derived and some practical examples are given.Finally,we compare all the results obtained and conclude this paper.展开更多
文摘The present study is to improve the volume flow rate of an axial fan through optimizing the blade shape under the demand for a specified static pressure. Fourteen design variables were selected to control the blade camber lines and the stacking line and the values of these variables were determined by using the experimental design method of the Latin Hypercube Sampling (LHS) to generate forty designs. The optimization was carried out using the genetic algorithm (GA) coupled with the artificial neural network (ANN) to increase the volume flow rate of the axial fan under the constraint of a specific motor power and a required static pressure. Differences in the aerodynamic performance and the flow characteristics between the original model and the optimal model were analyzed in detail. The results showed that the volume flow rate of the optimal model increased by 33%. The chord length, the installation angle and the cascade turning angle changed considerably. The forward leaned blade was beneficial to improve the volume flow rate of the axial fan. The axial velocity distribution and the static pressure distribution on the blade surface were improved after optimization.
文摘This paper chooses passenger flow data of some stations in China from January 2015 to March 2016, and the time series prediction model of BP neural network for railway passenger flow is established. But because of its slow convergence speed and easily falling into local optimal solution of the problem, we propose to improve the time series model of BP neural network by genetic algorithm to predict railway passenger flow. Experimental results show that the improved method has higher prediction accuracy and better nonlinear fitting ability.
文摘For the great significance of the prediction of control parameters selected for hot-rolling and the evaluation of hot-rolling quality for the analysis of prod uction problems and production management, the selection of hot-rolling control parameters was studied for microalloy steel by following the neural network principle. An experimental scheme was first worked out for acquisition of sample data, in which a gleeble-1500 thermal simolator was used to obtain rolling temperature, strain, stain rate, and stress-strain curves. And consequently the aust enite grain sizes was obtained through microscopic observation. The experimental data was then processed through regression. By using the training network of BP algorithm, the mapping relationship between the hotrooling control parameters (rolling temperature, stain, and strain rate) and the microstructural paramete rs (austenite grain in size and flow stress) of microalloy steel was function appro ached for the establishment of a neural network-based model of the austeuite grain size and flow stress of microalloy steel. From the results of estimation made with the neural network based model, the hot-rolling control parameters can be effectively predicted.
文摘In the multiple protocol label-switched (MPLS) networks, the commodities are transmitted by the label-switched paths (LSPs). For the sake of reducing the total cost and strengthening the central management, the MPLS networks restrict the number of paths that a commodity can use, for maintaining the quality of service (QoS) of the users, the demand of each commodity must be satisfied. Under the above conditions, some links in the network may be too much loaded, affecting the performance of the whole network drastically. For this problem, in [1], we proposed two mathematical models to describe it and a heuristic algorithm which quickly finds transmitting paths for each commodity are also presented. In this paper, we propose a new heuristic algorithm which finds a feasible path set for each commodity, and then select some paths from the path set through a mixed integer linear programming to transmit the demand of each commodity. This strategy reduces the scale of the original problem to a large extent. We test 50 instances and the results show the effectiveness of the new heuristic algorithm.
文摘Most of the existing opportunistic network routing protocols are based on some type of utility function that is directly or indirectly dependent on the past behavior of devices. The past behavior or history of a device is usually referred to as contacts that the device had in the past. Whatever may be the metric of history, most of these routing protocols work on the realistic premise that node mobility is not truly random. In contrast, there are several oracles based methods where such oracles assist these methods to gain access to information that is unrealistic in the real world. Although, such oracles are unrealistic, they can help to understand the nature and behavior of underlying networks. In this paper, we have analyzed the gap between these two extremes. We have performed max-flow computations on three different opportunistic networks and then compared the results by performing max-flow computations on history generated by the respective networks. We have found that the correctness of the history based prediction of history is dependent on the dense nature of the underlying network. Moreover, the history based prediction can deliver correct paths but cannot guarantee their absolute reliability.
文摘In this paper, two new sandwich algorithms for the convex curve approximation are introduced. The proofs of the linear convergence property of the first method and the quadratic convergence property of the second method are given. The methods are applied to approximate the efficient frontier of the stochastic minimum cost flow problem with the moment bicriterion. Two numerical examples including the comparison of the proposed algorithms with two other literature derivative free methods are given.
基金supported in part by the development Foundation of Southwest Jiaotong Universitythe National Natural Science Foundation of China under Grant No.60572143
文摘Network calculus is an evolving new methodology for backlog and delay analysis of packet-switching networks. With network calculus we are able to compute tight bounds on delays,backlogs,and effective bandwidths in a lossless setting applicable to packet-switching networks and better understand some physical properties of networks. In this paper,the basic network calculus concepts of arrival curves and service curves are introduced.Then we provide the approach for modeling leaky-bucket,generic cell rate algorithm(GCRA),constant bit rate(CBR)flow, variable bit rate(VBR) flow with arrival curve.It is shown that all rate-based packet schedulers can be by a simple rate latency service curve.And by applying these fundamental rules of network calculus,bounds on delay, buffer,effective bandwidth for leaky bucket,GCRA,CBR and VBR can be derived and some practical examples are given.Finally,we compare all the results obtained and conclude this paper.
