No abstract

A new method is proposed in which three images of the same field of view under different lighting conditions were analysed comprehensively. On the basis of pretreatment of debris digital image and extraction of characteristic parameter of debrises, the debrises were recognized by establishing the BP neural network model. The results showed that the recognition accuracy of debrises could reach 85.6% with this method.

Class_A surface reconstruction is a key part in the design of automotive body external panel. Traditional methods of Class_A surface reconstruction have some disadvantages such as low efficiency, bad flexibility and low surface quality in complicated surface reconstruction. In this paper, a method of Class_A surface reconstruction from point clouds based on NURBS patch was presented, which made surface design more flexible and direct, besides, the reconstruction efficiency and surface quality were improved.

In order to solve some problems existing in the process of shift for automatic mechanical transmission vehicles such as great shift impact, engine noise and low shift success ratio between gears which have large speed ratio differences, a new method used to determine shift schedule was put forward in this paper. In this method, shift schedule and shift quality were synthetically considered, the downshift schedule was obtained based on the same optimization target with upshift schedule and proper downshift delay with shift impact and shift time controlled in a predetermined range. An optimal power shift schedule was developed with this method, and the performance of the automatic mechanical transmission vehicle controlled by this method was compared with that of controlled by skilled driver. The results indicate that the former obviously improved the performance of the vehicle with the shift quality controlled in a predetermined range.