Modares Mechanical Engineering

Modares Mechanical Engineering

Automatic Machining Features Extraction from Two-Dimensional Image of Mechanical Parts with the Help of Artificial Intelligence

Document Type : Original Research

Abstract
Extracting the required information from the design file is one of the main steps in the computer aided process planning. In previous methods of extracting machining features, various methods such as graph-based method, volume analysis method, logic rules method and other methods have been used. In all the previous methods, whether traditional methods or methods based on artificial intelligence, the input data to the machine feature identification system is the output information of a computer-aided design system. Converting the output information of a computer-aided design system to input data of a machining feature identification system is faced with limitations such as the variety of format and type of data arrangement, deleting some data from the design file due to geometric interference of features, slow extraction of features due to extensive information in the design file and the limitation of identifying different types of machining features by a unity feature identification system. In the present study, using artificial intelligence techniques based on deep learning, machining features are extracted directly from the two-dimensional image of a workpiece. The image may be prepared by a computer-aided design file, or it can be taken by a camera.
Keywords
Machining Feature Recognition
Computer-Aided Process Planning
Artificial Intelligence Depth Learning

Subjects

"1-Babic B, Nesic N, Miljkovic Z. A review of automated feature recognition with rule-based pattern recognition. Computers in industry. 2008; 59(4):321-37.
2- Kyprianou LK. Shape classification in computer-aided design (Doctoral dissertation, University of Cambridge).
3- Vandenbrande JH, Requicha AA. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1993;15(12):1269-85.
4- Parvaz H, Nategh MJ. A multi-TAD framework for recognizing machining features using hint based recognition algorithm. InAdvanced Materials Research 2012 (Vol. 445, pp. 905-910). Trans Tech Publications Ltd.
5- Joshi S, Chang TC. Graph-based heuristics for recognition of machined features from a 3D solid model. Computer-Aided Design. 1988; 20(2):58-66.
6- Henderson MR, Anderson DC. Computer recognition and extraction of form features: a CAD/CAM link. Computers in industry. 1984; 5(4):329-39.
7- Han J, Pratt M, Regli WC. Manufacturing feature recognition from solid models: a status report. IEEE transactions on robotics and automation. 2000;16(6):782-96.
8- Babic BR, Nesic N, Miljkovic Z. Automatic feature recognition using artificial neural networks to integrate design and manufacturing: Review of automatic feature recognition systems. Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AI EDAM. 2011; 25(3):289.
9- Ding L, Matthews J. A contemporary study into the application of neural network techniques employed to automate CAD/CAM integration for die manufacture. Computers & Industrial Engineering. 2009; 57(4):1457-71.
10- Yue Y, Ding L, Ahmet K, Painter J, Walters M. Study of neural network techniques for computer integrated manufacturing. Engineering Computations. 2002.
11- Babic BR, Nesic N, Miljkovic Z. Automatic feature recognition using artificial neural networks to integrate design and manufacturing: Review of automatic feature recognition systems. Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AI EDAM. 2011; 25(3):289.
12- Zhang Z, Jaiswal P, Rai R. Featurenet: Machining feature recognition based on 3d convolution neural network. Computer-Aided Design. 2018; 101:12-22.
13- Shi P, Qi Q, Qin Y, Scott PJ, Jiang X. A novel learning-based feature recognition method using multiple sectional view representation. Journal of Intelligent Manufacturing. 2020:1-9."
Modares Mechanical Engineering
Volume 22, Issue 10
October 2022
Pages 173-179