The detection of foreign object intrusion is crucial for ensuring the safety of railway operations.To address challenges such as low efficiency,suboptimal detection accuracy,and slow detection speed inherent in conven...The detection of foreign object intrusion is crucial for ensuring the safety of railway operations.To address challenges such as low efficiency,suboptimal detection accuracy,and slow detection speed inherent in conventional comprehensive video monitoring systems for railways,a railway foreign object intrusion recognition and detection system is conceived and implemented using edge computing and deep learning technologies.In a bid to raise detection accuracy,the convolutional block attention module(CBAM),including spatial and channel attention modules,is seamlessly integrated into the YOLOv5 model,giving rise to the CBAM-YOLOv5 model.Furthermore,the distance intersection-over-union_non-maximum suppression(DIo U_NMS)algorithm is employed in lieu of the weighted nonmaximum suppression algorithm,resulting in improved detection performance for intrusive targets.To accelerate detection speed,the model undergoes pruning based on the batch normalization(BN)layer,and Tensor RT inference acceleration techniques are employed,culminating in the successful deployment of the algorithm on edge devices.The CBAM-YOLOv5 model exhibits a notable 2.1%enhancement in detection accuracy when evaluated on a selfconstructed railway dataset,achieving 95.0%for mean average precision(m AP).Furthermore,the inference speed on edge devices attains a commendable 15 frame/s.展开更多
To provide the supplier with the minimizum vehicle travel distance in the distribution process of goods in three situations of new customer demand,customer cancellation service,and change of customer delivery address,...To provide the supplier with the minimizum vehicle travel distance in the distribution process of goods in three situations of new customer demand,customer cancellation service,and change of customer delivery address,based on the ideas of pre-optimization and real-time optimization,a two-stage planning model of dynamic demand based vehicle routing problem with time windows was established.At the pre-optimization stage,an improved genetic algorithm was used to obtain the pre-optimized distribution route,a large-scale neighborhood search method was integrated into the mutation operation to improve the local optimization performance of the genetic algorithm,and a variety of operators were introduced to expand the search space of neighborhood solutions;At the real-time optimization stage,a periodic optimization strategy was adopted to transform a complex dynamic problem into several static problems,and four neighborhood search operators were used to quickly adjust the route.Two different scale examples were designed for experiments.It is proved that the algorithm can plan the better route,and adjust the distribution route in time under the real-time constraints.Therefore,the proposed algorithm can provide theoretical guidance for suppliers to solve the dynamic demand based vehicle routing problem.展开更多
A 3-D topology architeeture based on Spidergon and its generation method are proposed. Aiming at establishing relationships between the topology architecture and the latency, the 3-D topology latency model based on pr...A 3-D topology architeeture based on Spidergon and its generation method are proposed. Aiming at establishing relationships between the topology architecture and the latency, the 3-D topology latency model based on prototype is proposed, and then the optimization topology structure with minimum latency is determined based on it. Meanwhile, in accordance with the structure, the adaptive routing algorithm is designed. The algorithm sets longitudinal direction priority to adaptively searching the equivalent minimum path between the source nodes and the destination nodes in order to increase network throughput. Simulation shows that in case of approximate saturation network, compared with the same scale 3-D mesh structure, 3-D Spidergon has 17% less latency and 16.7% more network throughput.展开更多
In order to decrease the calculation complexity of connectivity reliability of road networks, an improved recursive decomposition arithmetic is proposed. First, the basic theory of recursive decomposition arithmetic i...In order to decrease the calculation complexity of connectivity reliability of road networks, an improved recursive decomposition arithmetic is proposed. First, the basic theory of recursive decomposition arithmetic is reviewed. Then the characteristics of road networks, which are different from general networks, are analyzed. Under this condition, an improved recursive decomposition arithmetic is put forward which fits road networks better. Furthermore, detailed calculation steps are presented which are convenient for the computer, and the advantage of the approximate arithmetic is analyzed based on this improved arithmetic. This improved recursive decomposition arithmetic directly produces disjoint minipaths and avoids the non-polynomial increasing problems. And because the characteristics of road networks are considered, this arithmetic is greatly simplified. Finally, an example is given to prove its validity.展开更多
In order to estimate circuit power at the early design stage,a rapid analysis method is presented to calculate the RTL power of combinational modules.By building the power library with Monte Carlo simulation,the powe...In order to estimate circuit power at the early design stage,a rapid analysis method is presented to calculate the RTL power of combinational modules.By building the power library with Monte Carlo simulation,the power dissipation of a certain module of any input vector can be obtained.This method uses Taylor's expansion to establish an equation based model.The simulation results for ISCAS85 circuit show that the method has error within 5%.展开更多
An efficient parallel global router using random optimization that is independent of net ordering is proposed.Parallel approaches are described and strategies guaranteeing the routing quality are discussed.The wire le...An efficient parallel global router using random optimization that is independent of net ordering is proposed.Parallel approaches are described and strategies guaranteeing the routing quality are discussed.The wire length model is implemented on multiprocessor,which enables the algorithm to approach feasibility of large scale problems.Timing driven model on multiprocessor and wire length model on distributed processors are also presented.The parallel algorithm greatly reduces the run time of routing.The experimental results show good speedups with no degradation of the routing quality.展开更多
Due to the diversified demands of quality of service（QoS） in volume multimedia application, QoS routings for multiservice are becoming a research hotspot in low earth orbit（LEO） satellite networks. A novel QoS sat...Due to the diversified demands of quality of service（QoS） in volume multimedia application, QoS routings for multiservice are becoming a research hotspot in low earth orbit（LEO） satellite networks. A novel QoS satellite routing algorithm for multi-class traffic is proposed. The goal of the routing algorithm is to provide the distinct QoS for different traffic classes and improve the utilization of network resources. Traffic is classified into three classes and allocated priorities based on their QoS requirements, respectively. A priority queuing mechanism guarantees the algorithm to work better for high-priority classes. In order to control the congestion, a blocking probability analysis model is built up based on the Markov process theory. Finally, according to the classification link-cost metrics, routings for different classes are calculated with the distinct QoS requirments and the status of network resource. Simulations verify the performance of the routing algorithm at different time and in different regions, and results demonstrate that the algorithm has great advantages in terms of the average delay and the blocking probability. Meanwhile, the robustness issue is also discussed.展开更多
A new partitioning methodology is presented to accelerate 130nm and beyond large scale alternating phase shift mask(Alt PSM) design flow.This method deals with granularity self adaptively.Phas...A new partitioning methodology is presented to accelerate 130nm and beyond large scale alternating phase shift mask(Alt PSM) design flow.This method deals with granularity self adaptively.Phase conflicts resolution approaches are described and strategies guaranteeing phase compatible during layout compaction are also discussed.An efficient CAD prototype for dark field Alt PSM based on these algorithms is implemented.The experimental results on several industry layouts show that the tool can successfully cope with the rapid growth of phase conflicts with good quality and satisfy lower resource consumption with different requirements of precision and speedup.展开更多
The dynanaic model of a novel electric power steering（EPS） system integrated with active front steer- ing function and the three-freedom steering model are built. Based on these models, the concepts and the quanti- ...The dynanaic model of a novel electric power steering（EPS） system integrated with active front steer- ing function and the three-freedom steering model are built. Based on these models, the concepts and the quanti- tative expressions of road feel, sensitivity, and operation stability of the steering are introduced. Then, according to constrained optimization features of multi-variable function, a genetic algorithm is designed. Making the road feel of the steering as optimization objective, and operation stability and sensitivity of the steering as constraints, the system parameters are optimized by the genetic and the coordinate rotation algorithms. Simulation results show that the optimization of the novel EPS system by the genetic algorithm can effectively improve the road feel, thus providing a theoretical basis for the design and optimization of the novel EPS system.展开更多
The problem of path planning is studied for t he case for a mobile robot moving in a known environment. An aggressive algorith m using a description of the obstacles based on a neural network is proposed. Th e algorit...The problem of path planning is studied for t he case for a mobile robot moving in a known environment. An aggressive algorith m using a description of the obstacles based on a neural network is proposed. Th e algorithm allows to construct an optimal path which is piecewise linear with c hanging directions of the obstacles and the calculation speed for the proposed a lgorithm is comparatively fast. Simulation results and an application to a car_l ike robot 'Khepera' show the effectiveness of the proposed algorithm.展开更多
基金supported in part by the Science and Technology Innovation Project of CHN Energy Shuo Huang Railway Development Company Ltd(No.SHTL-22-28)the Beijing Natural Science Foundation Fengtai Urban Rail Transit Frontier Research Joint Fund(No.L231002)the Major Project of China State Railway Group Co.,Ltd.(No.K2023T003)。
文摘The detection of foreign object intrusion is crucial for ensuring the safety of railway operations.To address challenges such as low efficiency,suboptimal detection accuracy,and slow detection speed inherent in conventional comprehensive video monitoring systems for railways,a railway foreign object intrusion recognition and detection system is conceived and implemented using edge computing and deep learning technologies.In a bid to raise detection accuracy,the convolutional block attention module(CBAM),including spatial and channel attention modules,is seamlessly integrated into the YOLOv5 model,giving rise to the CBAM-YOLOv5 model.Furthermore,the distance intersection-over-union_non-maximum suppression(DIo U_NMS)algorithm is employed in lieu of the weighted nonmaximum suppression algorithm,resulting in improved detection performance for intrusive targets.To accelerate detection speed,the model undergoes pruning based on the batch normalization(BN)layer,and Tensor RT inference acceleration techniques are employed,culminating in the successful deployment of the algorithm on edge devices.The CBAM-YOLOv5 model exhibits a notable 2.1%enhancement in detection accuracy when evaluated on a selfconstructed railway dataset,achieving 95.0%for mean average precision(m AP).Furthermore,the inference speed on edge devices attains a commendable 15 frame/s.
基金supported by Natural Science Foundation Project of Gansu Provincial Science and Technology Department(No.1506RJZA084)Gansu Provincial Education Department Scientific Research Fund Grant Project(No.1204-13).
文摘To provide the supplier with the minimizum vehicle travel distance in the distribution process of goods in three situations of new customer demand,customer cancellation service,and change of customer delivery address,based on the ideas of pre-optimization and real-time optimization,a two-stage planning model of dynamic demand based vehicle routing problem with time windows was established.At the pre-optimization stage,an improved genetic algorithm was used to obtain the pre-optimized distribution route,a large-scale neighborhood search method was integrated into the mutation operation to improve the local optimization performance of the genetic algorithm,and a variety of operators were introduced to expand the search space of neighborhood solutions;At the real-time optimization stage,a periodic optimization strategy was adopted to transform a complex dynamic problem into several static problems,and four neighborhood search operators were used to quickly adjust the route.Two different scale examples were designed for experiments.It is proved that the algorithm can plan the better route,and adjust the distribution route in time under the real-time constraints.Therefore,the proposed algorithm can provide theoretical guidance for suppliers to solve the dynamic demand based vehicle routing problem.
基金Supported by the National Nature Science Foundation of China(61076019)the Aviation Science Foundation(20115552031)the Science and Technology Support Program of Jiangsu Province(BE2010003)~~
文摘A 3-D topology architeeture based on Spidergon and its generation method are proposed. Aiming at establishing relationships between the topology architecture and the latency, the 3-D topology latency model based on prototype is proposed, and then the optimization topology structure with minimum latency is determined based on it. Meanwhile, in accordance with the structure, the adaptive routing algorithm is designed. The algorithm sets longitudinal direction priority to adaptively searching the equivalent minimum path between the source nodes and the destination nodes in order to increase network throughput. Simulation shows that in case of approximate saturation network, compared with the same scale 3-D mesh structure, 3-D Spidergon has 17% less latency and 16.7% more network throughput.
基金The National Key Technology R& D Program of Chinaduring the 11th Five-Year Plan Period (No.2006BAJ18B03).
文摘In order to decrease the calculation complexity of connectivity reliability of road networks, an improved recursive decomposition arithmetic is proposed. First, the basic theory of recursive decomposition arithmetic is reviewed. Then the characteristics of road networks, which are different from general networks, are analyzed. Under this condition, an improved recursive decomposition arithmetic is put forward which fits road networks better. Furthermore, detailed calculation steps are presented which are convenient for the computer, and the advantage of the approximate arithmetic is analyzed based on this improved arithmetic. This improved recursive decomposition arithmetic directly produces disjoint minipaths and avoids the non-polynomial increasing problems. And because the characteristics of road networks are considered, this arithmetic is greatly simplified. Finally, an example is given to prove its validity.
文摘In order to estimate circuit power at the early design stage,a rapid analysis method is presented to calculate the RTL power of combinational modules.By building the power library with Monte Carlo simulation,the power dissipation of a certain module of any input vector can be obtained.This method uses Taylor's expansion to establish an equation based model.The simulation results for ISCAS85 circuit show that the method has error within 5%.
文摘An efficient parallel global router using random optimization that is independent of net ordering is proposed.Parallel approaches are described and strategies guaranteeing the routing quality are discussed.The wire length model is implemented on multiprocessor,which enables the algorithm to approach feasibility of large scale problems.Timing driven model on multiprocessor and wire length model on distributed processors are also presented.The parallel algorithm greatly reduces the run time of routing.The experimental results show good speedups with no degradation of the routing quality.
基金Supported by the National High Technology Research and Development Program of China(″863″Program)(2010AAxxx404)~~
文摘Due to the diversified demands of quality of service（QoS） in volume multimedia application, QoS routings for multiservice are becoming a research hotspot in low earth orbit（LEO） satellite networks. A novel QoS satellite routing algorithm for multi-class traffic is proposed. The goal of the routing algorithm is to provide the distinct QoS for different traffic classes and improve the utilization of network resources. Traffic is classified into three classes and allocated priorities based on their QoS requirements, respectively. A priority queuing mechanism guarantees the algorithm to work better for high-priority classes. In order to control the congestion, a blocking probability analysis model is built up based on the Markov process theory. Finally, according to the classification link-cost metrics, routings for different classes are calculated with the distinct QoS requirments and the status of network resource. Simulations verify the performance of the routing algorithm at different time and in different regions, and results demonstrate that the algorithm has great advantages in terms of the average delay and the blocking probability. Meanwhile, the robustness issue is also discussed.
文摘A new partitioning methodology is presented to accelerate 130nm and beyond large scale alternating phase shift mask(Alt PSM) design flow.This method deals with granularity self adaptively.Phase conflicts resolution approaches are described and strategies guaranteeing phase compatible during layout compaction are also discussed.An efficient CAD prototype for dark field Alt PSM based on these algorithms is implemented.The experimental results on several industry layouts show that the tool can successfully cope with the rapid growth of phase conflicts with good quality and satisfy lower resource consumption with different requirements of precision and speedup.
基金Supported by the National Natural Science Foundation of China(51005115)the Risiting Scholar Foundation of the State Key Lab of Mechanical Transmission in Chongqing University(SKLMT-KFKT-201105)theScience Fund of State Key Laboratory of Automotive Satefy and Energy in Tsinghua University(KF11202)~~
文摘The dynanaic model of a novel electric power steering（EPS） system integrated with active front steer- ing function and the three-freedom steering model are built. Based on these models, the concepts and the quanti- tative expressions of road feel, sensitivity, and operation stability of the steering are introduced. Then, according to constrained optimization features of multi-variable function, a genetic algorithm is designed. Making the road feel of the steering as optimization objective, and operation stability and sensitivity of the steering as constraints, the system parameters are optimized by the genetic and the coordinate rotation algorithms. Simulation results show that the optimization of the novel EPS system by the genetic algorithm can effectively improve the road feel, thus providing a theoretical basis for the design and optimization of the novel EPS system.
文摘The problem of path planning is studied for t he case for a mobile robot moving in a known environment. An aggressive algorith m using a description of the obstacles based on a neural network is proposed. Th e algorithm allows to construct an optimal path which is piecewise linear with c hanging directions of the obstacles and the calculation speed for the proposed a lgorithm is comparatively fast. Simulation results and an application to a car_l ike robot 'Khepera' show the effectiveness of the proposed algorithm.
