Aiming at the problem of incomplete information and uncertainties in the diagnosis of complex system by using single parameter, a new method of multi-sensor information fusion fault diagnosis based on BP neural networ...Aiming at the problem of incomplete information and uncertainties in the diagnosis of complex system by using single parameter, a new method of multi-sensor information fusion fault diagnosis based on BP neural network and D-S evidence theory is proposed. In order to simplify the structure of BP neural network, two parallel BP neural networks are used to diagnose the fault data at first; and then, using the evidence theory to fuse the local diagnostic results, the accurate inference of the inaccurate information is realized, and the accurate diagnosis resuh is obtained. The method is applied to the fault diagnosis of the hydraulic driven servo system （HDSS） in a certain type of rocket launcher, which realizes the fault location and diagnosis of the main components of the hydraulic driven servo system, and effectively improves the reliability of the system.展开更多
The estimation of key rate is an important aspect of the quantum key distribution process, especially in the use of dead time. In this paper, we demonstrate a numerical simulation to estimate the average detection pro...The estimation of key rate is an important aspect of the quantum key distribution process, especially in the use of dead time. In this paper, we demonstrate a numerical simulation to estimate the average detection probability and the key rate. Using our method, the estimated average detection probability is better than the previous result. Besides, we can easily find the best dead time, especially when considering the impact of after pulse.展开更多
基金supported by the military scientific research plan(wj2015cj020001)
文摘Aiming at the problem of incomplete information and uncertainties in the diagnosis of complex system by using single parameter, a new method of multi-sensor information fusion fault diagnosis based on BP neural network and D-S evidence theory is proposed. In order to simplify the structure of BP neural network, two parallel BP neural networks are used to diagnose the fault data at first; and then, using the evidence theory to fuse the local diagnostic results, the accurate inference of the inaccurate information is realized, and the accurate diagnosis resuh is obtained. The method is applied to the fault diagnosis of the hydraulic driven servo system （HDSS） in a certain type of rocket launcher, which realizes the fault location and diagnosis of the main components of the hydraulic driven servo system, and effectively improves the reliability of the system.
基金Project supported by the National High Technology Research and Development Program of China (863 Program) (GrantNo. 2009AA01A349)
文摘The estimation of key rate is an important aspect of the quantum key distribution process, especially in the use of dead time. In this paper, we demonstrate a numerical simulation to estimate the average detection probability and the key rate. Using our method, the estimated average detection probability is better than the previous result. Besides, we can easily find the best dead time, especially when considering the impact of after pulse.
