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
There are many kinds of fires occurring under different conditions. For a specific site, it is difficult to collect sufficient data for analyzing the fire risk. In this paper, we suggest an information diffusion techn...There are many kinds of fires occurring under different conditions. For a specific site, it is difficult to collect sufficient data for analyzing the fire risk. In this paper, we suggest an information diffusion technique to analyze fire risk with a small sample. The information distribution method is applied to change crisp observations into fuzzy sets, and then to effectively construct a fuzzy relationship between fire and surroundings. With the data of Shanghai in winter, we show how to use the technique to analyze the fire risk.展开更多
In this paper, we describe an SIS epidemic model where both the disease transmission rate and treatment function are considered in saturated forms. The dynamical behavior of the system is analyzed. The system is custo...In this paper, we describe an SIS epidemic model where both the disease transmission rate and treatment function are considered in saturated forms. The dynamical behavior of the system is analyzed. The system is customized by considering the disease trans- mission rate and treatment control as fuzzy numbers and then fuzzy expected value of the infected individuals is determined. The fuzzy basic reproduction number is investi- gated and a threshold condition of pathogen is derived at which the system undergoes a backward bifurcation.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.
文摘There are many kinds of fires occurring under different conditions. For a specific site, it is difficult to collect sufficient data for analyzing the fire risk. In this paper, we suggest an information diffusion technique to analyze fire risk with a small sample. The information distribution method is applied to change crisp observations into fuzzy sets, and then to effectively construct a fuzzy relationship between fire and surroundings. With the data of Shanghai in winter, we show how to use the technique to analyze the fire risk.
文摘In this paper, we describe an SIS epidemic model where both the disease transmission rate and treatment function are considered in saturated forms. The dynamical behavior of the system is analyzed. The system is customized by considering the disease trans- mission rate and treatment control as fuzzy numbers and then fuzzy expected value of the infected individuals is determined. The fuzzy basic reproduction number is investi- gated and a threshold condition of pathogen is derived at which the system undergoes a backward bifurcation.
