The back propagation (BP)-based artificial neural nets (ANN) can identify complicated relationships among dissolved gas contents in transformer oil and corresponding fault types, using the highly nonlinear mapping nat...The back propagation (BP)-based artificial neural nets (ANN) can identify complicated relationships among dissolved gas contents in transformer oil and corresponding fault types, using the highly nonlinear mapping nature of the neural nets. An efficient BP-ALM (BP with Adaptive Learning Rate and Momentum coefficient) algorithm is proposed to reduce the training time and avoid being trapped into local minima, where the learning rate and the momentum coefficient are altered at iterations. We developed a system of transformer fault diagnosis based on Dissolved Gases Analysis (DGA) with a BP-ALM algorithm. Training patterns were selected from the results of a Refined Three-Ratio method (RTR). Test results show that the system has a better ability of quick learning and global convergence than other methods and a superior performance in fault diagnosis compared to convectional BP-based neural networks and RTR.展开更多
Traffic jam in large signalized road network presents a complex nature.In order to reveal the jam characteristics,two indexes,SVS(speed of virtual signal) and VOS(velocity of spillover),were proposed respectively.SVS ...Traffic jam in large signalized road network presents a complex nature.In order to reveal the jam characteristics,two indexes,SVS(speed of virtual signal) and VOS(velocity of spillover),were proposed respectively.SVS described the propagation of queue within a link while VOS reflected the spillover velocity of vehicle queue.Based on the two indexes,network jam simulation was carried out on a regular signalized road network.The simulation results show that:1) The propagation of traffic congestion on a signalized road network can be classified into two stages:virtual split driven stage and flow rate driven stage.The former stage is characterized by decreasing virtual split while the latter only depends on flow rate; 2) The jam propagation rate and direction are dependent on traffic demand distribution and other network parameters.The direction with higher demand gets more chance to be jammed.Our findings can serve as the basis of the prevention of the formation and propagation of network traffic jam.展开更多
Artificial neural network (ANN) has a great capability of self learning. The application of neural network to flight controller design can get good result. This paper studies the method of choosing controller paramet...Artificial neural network (ANN) has a great capability of self learning. The application of neural network to flight controller design can get good result. This paper studies the method of choosing controller parameters using neural network with Back Propagation (B P) algorithm. Design and simulation results show that this method can be used in flight control system design.展开更多
文摘The back propagation (BP)-based artificial neural nets (ANN) can identify complicated relationships among dissolved gas contents in transformer oil and corresponding fault types, using the highly nonlinear mapping nature of the neural nets. An efficient BP-ALM (BP with Adaptive Learning Rate and Momentum coefficient) algorithm is proposed to reduce the training time and avoid being trapped into local minima, where the learning rate and the momentum coefficient are altered at iterations. We developed a system of transformer fault diagnosis based on Dissolved Gases Analysis (DGA) with a BP-ALM algorithm. Training patterns were selected from the results of a Refined Three-Ratio method (RTR). Test results show that the system has a better ability of quick learning and global convergence than other methods and a superior performance in fault diagnosis compared to convectional BP-based neural networks and RTR.
基金Project(2012CB725402)supported by the State Key Development Program for Basic Research of ChinaProject(2012MS21175)supported by the National Science Foundation for Post-doctoral Scientists of ChinaProject(Bsh1202056)supported by the Excellent Postdoctoral Science Foundation of Zhejiang Province,China
文摘Traffic jam in large signalized road network presents a complex nature.In order to reveal the jam characteristics,two indexes,SVS(speed of virtual signal) and VOS(velocity of spillover),were proposed respectively.SVS described the propagation of queue within a link while VOS reflected the spillover velocity of vehicle queue.Based on the two indexes,network jam simulation was carried out on a regular signalized road network.The simulation results show that:1) The propagation of traffic congestion on a signalized road network can be classified into two stages:virtual split driven stage and flow rate driven stage.The former stage is characterized by decreasing virtual split while the latter only depends on flow rate; 2) The jam propagation rate and direction are dependent on traffic demand distribution and other network parameters.The direction with higher demand gets more chance to be jammed.Our findings can serve as the basis of the prevention of the formation and propagation of network traffic jam.
文摘Artificial neural network (ANN) has a great capability of self learning. The application of neural network to flight controller design can get good result. This paper studies the method of choosing controller parameters using neural network with Back Propagation (B P) algorithm. Design and simulation results show that this method can be used in flight control system design.
