Yenan Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yenan Shi has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Guolei Zheng
School of Mechanical Engineering and Automation, Beihang University, Beijing, China
2 shared publications - Jingchen Hu1 shared publication
Latest Publications
- 24 June 2019
- Published by U-turn Press LLC
A Visual-cognition-inspired Model for Machining Feature Recognition
Artificial neural network (ANN) is a successful implementation of imitating biological neural network. Feature recognition is a key technology in CAD/CAM. Using ANN to identify machining features is a significant interdisciplinary research direction of feature recognition, and has received considerable results. The method mainly performs pre-processing and assigns features based on B-rep information or voxel representation, and then inputs them into the ANN for calculation. Several popular ANN structures are employed, including Convolutional Neural Network (CNN), Back Propagation (BP) Neural Network and Self-organizing Feature Map (SOFM). The advantages of the ANN recognition method are that ANNs have the ability to learn and generalize, and process faster. However, the recognition process of ANNs is opaque. Moreover, ANNs can only process numerical input and perform arithmetic operations, not logical operations, which restricts the application of ANNs in the field of CAD machining feature recognition. Therefore, it is essential to research and establish a new and more practical network structure. The contribution of this paper is that a new Visual-cognition-inspired Model (VCIM) for machining feature recognition especially in aircraft structural parts is established by imitating the visual cognition process of the human brain and related neural mechanisms.
- 24 June 2019
- Published by U-turn Press LLC
A Visual-cognition-inspired Model for Machining Feature Recognition
Artificial neural network (ANN) is a successful implementation of imitating biological neural network. Feature recognition is a key technology in CAD/CAM. Using ANN to identify machining features is a significant interdisciplinary research direction of feature recognition, and has received considerable results. The method mainly performs pre-processing and assigns features based on B-rep information or voxel representation, and then inputs them into the ANN for calculation. Several popular ANN structures are employed, including Convolutional Neural Network (CNN), Back Propagation (BP) Neural Network and Self-organizing Feature Map (SOFM). The advantages of the ANN recognition method are that ANNs have the ability to learn and generalize, and process faster. However, the recognition process of ANNs is opaque. Moreover, ANNs can only process numerical input and perform arithmetic operations, not logical operations, which restricts the application of ANNs in the field of CAD machining feature recognition. Therefore, it is essential to research and establish a new and more practical network structure. The contribution of this paper is that a new Visual-cognition-inspired Model (VCIM) for machining feature recognition especially in aircraft structural parts is established by imitating the visual cognition process of the human brain and related neural mechanisms.
- 29 December 2016
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 91 (5-8) , 2059-2075
The algorithm of layering calculation for corner plunge milling tool path
- 29 December 2016
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 91 (5-8) , 2059-2075
The algorithm of layering calculation for corner plunge milling tool path