Fiber reinforced polymers (FRPs), unlike steel, are corrosion-resistant and therefore are of interest;however, their use is hindered because their brittle shear is formulated in most specifications using limited data ...Fiber reinforced polymers (FRPs), unlike steel, are corrosion-resistant and therefore are of interest;however, their use is hindered because their brittle shear is formulated in most specifications using limited data available at the time. We aimed to predict the shear strength of concrete beams reinforced with FRP bars and without stirrups by compiling a relatively large database of 198 previously published test results (available in appendix). To model shear strength, an artificial neural network was trained by an ensemble of Levenberg-Marquardt and imperialist competitive algorithms. The results suggested superior accuracy of model compared to equations available in specifications and literature.展开更多
In view of some distinctive characteristics of the early-stage flame image, a corresponding method of characteristic extraction is presented. Also introduced is the application of the improved BP algorithm based on th...In view of some distinctive characteristics of the early-stage flame image, a corresponding method of characteristic extraction is presented. Also introduced is the application of the improved BP algorithm based on the optimization theory to identifying fire image characteristics. First the optimization of BP neural network adopting Levenberg-Marquardt algorithm with the property of quadratic convergence is discussed, and then a new system of fire image identification is devised. Plenty of experiments and field tests have proved that this system can detect the early-stage fire flame quickly and reliably.展开更多
The algorithm of autonomous orbit determination for the probe around small body is studied. In the algorithm, first, the observed images of the body are compared with its pre-computed model of the body to obtain the l...The algorithm of autonomous orbit determination for the probe around small body is studied. In the algorithm, first, the observed images of the body are compared with its pre-computed model of the body to obtain the location of the limb features of the body in the inertial coordinate. Second, the information of the images and features in utilized to obtain the position of the probe using the Levenberg-Marquardt algorithm. The position is then input to an extended Kalman filter which determines the real time orbit of the probe. Finally, considering the effective of the irregular small body shape perturbation and the small body model parameter error on the orbit determination precise, the procedure of autonomous orbit determination is validated using digital simulation.展开更多
文摘Fiber reinforced polymers (FRPs), unlike steel, are corrosion-resistant and therefore are of interest;however, their use is hindered because their brittle shear is formulated in most specifications using limited data available at the time. We aimed to predict the shear strength of concrete beams reinforced with FRP bars and without stirrups by compiling a relatively large database of 198 previously published test results (available in appendix). To model shear strength, an artificial neural network was trained by an ensemble of Levenberg-Marquardt and imperialist competitive algorithms. The results suggested superior accuracy of model compared to equations available in specifications and literature.
文摘In view of some distinctive characteristics of the early-stage flame image, a corresponding method of characteristic extraction is presented. Also introduced is the application of the improved BP algorithm based on the optimization theory to identifying fire image characteristics. First the optimization of BP neural network adopting Levenberg-Marquardt algorithm with the property of quadratic convergence is discussed, and then a new system of fire image identification is devised. Plenty of experiments and field tests have proved that this system can detect the early-stage fire flame quickly and reliably.
基金This project was supported by the 15th Plan National Defence Science & Tehnology and Civil Space Previous Study Project.
文摘The algorithm of autonomous orbit determination for the probe around small body is studied. In the algorithm, first, the observed images of the body are compared with its pre-computed model of the body to obtain the location of the limb features of the body in the inertial coordinate. Second, the information of the images and features in utilized to obtain the position of the probe using the Levenberg-Marquardt algorithm. The position is then input to an extended Kalman filter which determines the real time orbit of the probe. Finally, considering the effective of the irregular small body shape perturbation and the small body model parameter error on the orbit determination precise, the procedure of autonomous orbit determination is validated using digital simulation.
