中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共3条，第1-3条

帮助

条数/页：排序方式：
	Research on AUV Obstacle Avoidance Based on BP Neural Network 会议论文 OAI收割 2017 The 2nd International Conference on Robotics, Control and Automation (ICRCA 2017), Kitakyushu, Japan, September 15-18, 2017 作者: Dong LY(董凌艳); Xu HL(徐红丽) \| 收藏 \| 浏览/下载：32/0 \| 提交时间：2017/12/21 obstacle avoidance AUV BP neural network.
	Design of controlling system in multi-function durability testing device for vehicle vacuum booster with brake master cylinder (EI CONFERENCE) 会议论文 OAI收割 2012 International Conference on Mechanical and Electronic Engineering, ICMEE 2012, June 23, 2012 - June 24, 2012, Hefei, China Hao X.; Zhang R.; Li X.; Wang M. 收藏 \| 浏览/下载：63/0 \| 提交时间：2013/03/25 The quality of vehicle vacuum booster with brake master cylinder is related to the safe of drivers and automobiles. The testing experiment must be executed strictly before leaving factory based on the national standards.The paper introduces the controlling system of multi-function durability testing device which is designed for doing durable testing experiments and Anti-lock braking system (ABS) performance experiments. The structure and theory of device is presented. The controlling system is illuminated in detail. To test the dynamic property this system was identified by a recursive BP neural network. According to the character of a great deal of sensors and actuators the high precision capabilities and reliability the distributed control mode (DCS) including the computer and PLC by RS-485 bus is utilized. The four channels testing experiments are achieved at the same time. The test data is directly memorized into the computer. The results of general endurance and ABS endurance testing experiments are shown to demonstrate the excellent performance of the testing device. 2012 Springer-Verlag Berlin Heidelberg.
	An object recognition method based on fuzzy theory and BP networks (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China Chuan W.; Ming Z.; Dong Y. 收藏 \| 浏览/下载：29/0 \| 提交时间：2013/03/25 It is difficult to choose eigenvectors when neural network recognizes object. It is possible that the different object eigenvectors is similar or the same object eigenvectors is different under scaling shifting rotation if eigenvectors can not be chosen appropriately. In order to solve this problem the image is edged the membership function is reconstructed and a new threshold segmentation method based on fuzzy theory is proposed to get the binary image. Moment invariant of binary image is extracted and normalized. Some time moment invariant is too small to calculate effectively so logarithm of moment invariant is taken as input eigenvectors of BP network. The experimental results demonstrate that the proposed approach could recognize the object effectively correctly and quickly.