Equipment maintenance is essential for ensuring the longevity and optimal performance throughout the product lifecycle. The augmented reality technology is used to replace traditional paper manuals for maintenance, leading to enhanced efficiency and accuracy. However, the current development of augmented reality maintenance procedures primarily depends on the product's process manual. This approach only reduces the user's operation time, but still requires developers to invest significant time and effort. In this article, we propose automating the planning of product disassembly sequences based on the product's CAD model in order to improve the automation process of augmented reality maintenance applications. We propose a novel selective disassembly sequences method for maintaining faulty components based on product and disassembly levels. We utilize this method as the input for our developed Guided Information Generation System (GIGS). We conduct a rapid maintenance process for experimental equipment to validate the feasibility and potential practical application of our method.

Virtual-to-real registration is a crucial aspect of 3D registration, which presents a more challenging multimodal 3D registration problem due to the different data structures between virtual and real models. In this paper, we utilize point cloud registration algorithm to align virtual and real models, transforming the multimodal 3D registration problem into a cross-source point cloud registration problem. We propose a method for extracting macro and micro structures to represent the shared features of virtual and real models, combined with a multi-constraint registration algorithm, to achieve high-accuracy virtual-to-real registration tasks. This method can register unseen 3D objects using virtual prior knowledge, and allow partial point cloud registration without the need for a 360-degree scan of the model. Our approach can effectively resist interference from typical cross-source point cloud registration problems such as varying densities, missing data, and distribution changes. Furthermore, by processing only 0.2% of the original number of point clouds through downsampling, we can effectively diminish the effects of noise and outlier, as well as significantly decrease time consuming. Experimental results show that our algorithm outperforms other advanced point cloud registration algorithms in cross-source point cloud registration for virtual-to-real registration.