In EDS ansehen

Feature Extraction and CNC Code Generation for Prismatic Parts.

Gespeichert in:
Bibliographische Detailangaben
Titel: Feature Extraction and CNC Code Generation for Prismatic Parts.
Autoren: Patil, Sumant S., Rawandale, Shitalkumar A., Kale, Kishor B., Gupta, Ravi Kumar, Patil, Rutuja S.
Quelle: Journal of Mines, Metals & Fuels; Dec2025, Vol. 73 Issue 12, p3795-3804, 10p
Schlagwörter: FEATURE extraction, PRINCIPAL components analysis, LOGISTIC regression analysis, MANUFACTURING process automation, COMPUTER-aided process planning, PRODUCT design software, NUMERICAL control of machine tools, THREE-dimensional modeling
Firma/Körperschaft: DASSAULT Systemes SolidWorks Corp.
Abstract: Introduction: In general, a designer creates a product based on their logic, incorporating certain constraints and assumptions. On the other hand, manufacturers interpret the design data based on their own logic, often making modifications during the production process. This disconnect between design intent and manufacturing execution leads to a gap in understanding, resulting in inconsistencies and inefficiencies. Currently, designers have no direct control over manufacturing process parameters, which limits the alignment between design and production. Ideally, the relationship between designer and manufacturer should be such that the manufacturing process accurately reflects the designer’s intent. This would allow designers to directly control the manufacturing parameters, reducing human intervention and minimizing errors. Methods: This paper proposes a novel methodology that enables automatic part feature extraction and CNC code generation for individualized product manufacturing. The aim is to optimize Computer-Aided Process Planning (CAPP) at the designer stage itself. Prismatic models are created using SolidWorks, and Principal Component Analysis (PCA) is applied to extract important features of these parts. Results: The PCA implementation is enhanced using logistic regression with hyperparameter tuning in Python. Automated feature extraction is achieved through specially designed algorithms that process signals without human involvement. Conclusion: By integrating feature extraction with decision-making algorithms, CNC codes can be generated automatically. This intelligent system streamlines the process, reducing product manufacturing errors, production time, and time-to-market. Major Findings: This study proposes an automated methodology for part feature extraction and CNC code generation to bridge the gap between design and manufacturing. PCA and logistic regression with hyperparameter tuning are used to enhance feature recognition from SolidWorks models. The approach enables real-time CAPP, reducing errors, production time, and aligning manufacturing with design intent. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Mines, Metals & Fuels is the property of Books & Journal Private Ltd. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Datenbank: Complementary Index
Beschreibung
Abstract:Introduction: In general, a designer creates a product based on their logic, incorporating certain constraints and assumptions. On the other hand, manufacturers interpret the design data based on their own logic, often making modifications during the production process. This disconnect between design intent and manufacturing execution leads to a gap in understanding, resulting in inconsistencies and inefficiencies. Currently, designers have no direct control over manufacturing process parameters, which limits the alignment between design and production. Ideally, the relationship between designer and manufacturer should be such that the manufacturing process accurately reflects the designer’s intent. This would allow designers to directly control the manufacturing parameters, reducing human intervention and minimizing errors. Methods: This paper proposes a novel methodology that enables automatic part feature extraction and CNC code generation for individualized product manufacturing. The aim is to optimize Computer-Aided Process Planning (CAPP) at the designer stage itself. Prismatic models are created using SolidWorks, and Principal Component Analysis (PCA) is applied to extract important features of these parts. Results: The PCA implementation is enhanced using logistic regression with hyperparameter tuning in Python. Automated feature extraction is achieved through specially designed algorithms that process signals without human involvement. Conclusion: By integrating feature extraction with decision-making algorithms, CNC codes can be generated automatically. This intelligent system streamlines the process, reducing product manufacturing errors, production time, and time-to-market. Major Findings: This study proposes an automated methodology for part feature extraction and CNC code generation to bridge the gap between design and manufacturing. PCA and logistic regression with hyperparameter tuning are used to enhance feature recognition from SolidWorks models. The approach enables real-time CAPP, reducing errors, production time, and aligning manufacturing with design intent. [ABSTRACT FROM AUTHOR]
ISSN:00222755
DOI:10.18311/jmmf/2025/50383