1. This paper studies the use of a multi-view convolutional neural network (MVCNN) algorithm enhanced by the addition of engineering metadata, for classification and retrieval of 3D computer-aided design (CAD) models.
2. The proposed algorithm (MVCNN++) builds on the MVCNN algorithm with the addition of part dimension data, improving its efficacy for manufacturing part classification and yielding an improvement in classification accuracy of 5.8% over the original version.
3. DNNs can be used to search and discover relevant 3D engineering models in large public repositories, making 3D models accessible to the community.
The article is generally reliable and trustworthy as it provides evidence for its claims through experiments conducted on datasets and provides detailed descriptions of the methodology used in these experiments. The authors also provide references to other related works which adds to the credibility of their work. However, there are some potential biases that should be noted such as a lack of discussion on possible risks associated with using deep learning algorithms for CAD model shape classification and retrieval, as well as a lack of exploration into counterarguments or alternative approaches that could be taken when dealing with this problem. Additionally, there is no discussion on how this approach could be applied to other domains or industries outside of mechanical design which could limit its applicability in certain contexts.