The torus is a promisingly potential alternative to traditionally cylindrical pressure vessels due to its capability to store more hydrogen energy within limited space. Constant angle winding is widely used in practical filament winding. Hence, it is necessary to study constant angle winding on the torus. This paper presents constant winding angle curve on torus, a new winding trajectory, and gives a sufficient and necessary condition that makes it nonslip and non-bridging, and a computational formula for determining the lower bound of the winding angle of stable constant winding angle curve. By combining with semi-geodesics, we propose an integration design method for winding pattern and develop a computer aided path design system for filament winding torus, which can design constant angle winding pattern or approximate equilibrium winding for toroidal composite pressure vessels. Since our approach uses constant winding angle curve and integration trajectories besides semi-geodesics, our method has more design space for optimizing fiber path, and outperforms the existing methods.

The traditionally diameter-varying tube is a combination part of cylinder and cone with unsmooth transition region, which is usually a weak link. Using spline technique, we present a smooth diameter-varying tube consisting of cylinder and revolution surface with interpolation spline as meridian, and study the stability of three categories of typical curves used for filament winding, geodesics, semi-geodesics, and constant winding angle curve. A sufficient condition that makes fiber path non-bridging is introduced by analyzing normal curvature, and furthermore there is a sufficient and necessary condition of non-bridging geodesics. For constant angle winding, an efficient algorithm for determining whether constant winding angle curve is stable or not is presented by investigating its slippage coefficient , and a novel winding pattern design metthod is proposed for filament winding diameter-varying tube. These methods have been applied to our computer aided filament winding software. The experimental and simulation results show that our method can design winding pattern of uniformly covering the mandrel, and efficiently shortens the design time.

In the process of garment production, obtaining and identifying garment illustrations, transforming them into the required information, and then implementing the information into automated production can improve the production efficiency to a great extent. However, the research on recognition of garment illustration and pattern image is mostly based on category classification, but very little on the identification of parts and details. The Inception module in the GoogleNet Inception and its improvement development models enhance parameter utilization, accelerate computation, and have no special requirements for hardware. The Mask R-CNN, a convolutional neural network, is a modified model from based on Faster R-CNN for instance splitting tasks. Based on these two models, this paper proposes a method to identify garment illustrations using a self-built database. The experimental results show that this method outperforms the related algorithms.