View in EDS PDF Full Text

Improving the Stability of CNC Machine Tools Based on Artificial Intelligence.

Saved in:
Bibliographic Details
Title: Improving the Stability of CNC Machine Tools Based on Artificial Intelligence.
Authors: JunGuo1, Long, Shuangyan1 ShuangyanLong@outlook.com, ShiyunMo1
Source: Jordan Journal of Mechanical & Industrial Engineering. Apr2026, Vol. 20 Issue 2, p273-281. 9p.
Subjects: Artificial intelligence, Numerical control of machine tools, Machine learning, Machining, Deep learning, Inspection & review
Abstract (English): The stability of machining accuracy in CNC machine tools is often affected by multiple factors such as fixture conditions, tool wear, ambient temperature, and vibration, which can easily cause the actual machining trajectory to deviate from the theoretical path. To suppress such errors and improve machining stability, it is necessary to dynamically correct the machining process through real time compensation parameters. For this purpose, this paper proposes an artificial intelligence model that integrates deep learning and machine learning, aiming to provide a real time, adaptive, and high precision dynamic parameter compensation scheme for lathes during machining. In terms of data modeling, the aforementioned influencing factors are quantified into feature variables, each associated with a set of adjustable compensation parameters. Each data sample consists of a feature vector, a compensation parameter vector, and the corresponding measured machining accuracy value, thereby constructing a structured dataset for error compensation. In terms of methodology implementation, first, based on this dataset, a deep learning framework is employed to build an error compensation model, achieving real time optimization of machining parameters and enhancement of accuracy. Second, by collecting a large number of image samples of qualified and unqualified workpieces, a machine learning based visual inspection model is trained to automatically discriminate the quality of workpieces after compensation. Simulation experiments show that the proposed error compensation model improves machining accuracy on the training set and test set from 0.66 to 0.98 and from 0.65 to 0.967, respectively; the visual inspection model achieves fully accurate recognition on both types of datasets. In practical machining verification, after intelligent compensation machining of 50 gears, all were judged as qualified by the visual inspection system. The results indicate that the artificial intelligence model constructed in this paper can significantly enhance the machining accuracy and product qualification rate of CNC machine tools. [ABSTRACT FROM AUTHOR]
Abstract (Arabic): يركز المقال على تحسين استقرار ودقة أدوات الماكينات ذات التحكم الرقمي بالحاسوب (CNC) باستخدام نهج الذكاء الاصطناعي الذي يدمج التعلم العميق والتعلم الآلي. يقدم نموذج تعويض ديناميكي للأخطاء يقوم بتحويل العوامل المؤثرة على دقة التشغيل—مثل ظروف التثبيت، تآكل الأدوات، درجة حرارة البيئة، والاهتزاز—إلى متغيرات مميزة مرتبطة بمعاملات التعويض. يتنبأ نموذج التعلم العميق بمعاملات التعويض في الوقت الحقيقي لتعزيز دقة التشغيل، بينما يقوم نموذج الفحص البصري المعتمد على التعلم الآلي بتقييم جودة القطع المصنعة تلقائيًا. تُظهر المحاكاة والاختبارات العملية تحسنات كبيرة في دقة التشغيل ومعدلات تأهيل المنتجات، حيث حقق نظام الذكاء الاصطناعي دقة تصل إلى 0.98 على بيانات التدريب ومعدل تأهيل 100% على 50 ترسًا تم اختبارها. تسلط الدراسة الضوء على إمكانيات دمج خوارزميات الذكاء الاصطناعي مع البيانات الصناعية الضخمة لتعويض الأخطاء بشكل تكيفي تحت ظروف عمل متغيرة، مما يعزز استقرار وموثوقية تشغيل ماكينات CNC. [Extracted from the article]
Copyright of Jordan Journal of Mechanical & Industrial Engineering is the property of Hashemite University 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.)
Database: Engineering Source
Description
Abstract:The stability of machining accuracy in CNC machine tools is often affected by multiple factors such as fixture conditions, tool wear, ambient temperature, and vibration, which can easily cause the actual machining trajectory to deviate from the theoretical path. To suppress such errors and improve machining stability, it is necessary to dynamically correct the machining process through real time compensation parameters. For this purpose, this paper proposes an artificial intelligence model that integrates deep learning and machine learning, aiming to provide a real time, adaptive, and high precision dynamic parameter compensation scheme for lathes during machining. In terms of data modeling, the aforementioned influencing factors are quantified into feature variables, each associated with a set of adjustable compensation parameters. Each data sample consists of a feature vector, a compensation parameter vector, and the corresponding measured machining accuracy value, thereby constructing a structured dataset for error compensation. In terms of methodology implementation, first, based on this dataset, a deep learning framework is employed to build an error compensation model, achieving real time optimization of machining parameters and enhancement of accuracy. Second, by collecting a large number of image samples of qualified and unqualified workpieces, a machine learning based visual inspection model is trained to automatically discriminate the quality of workpieces after compensation. Simulation experiments show that the proposed error compensation model improves machining accuracy on the training set and test set from 0.66 to 0.98 and from 0.65 to 0.967, respectively; the visual inspection model achieves fully accurate recognition on both types of datasets. In practical machining verification, after intelligent compensation machining of 50 gears, all were judged as qualified by the visual inspection system. The results indicate that the artificial intelligence model constructed in this paper can significantly enhance the machining accuracy and product qualification rate of CNC machine tools. [ABSTRACT FROM AUTHOR]
ISSN:19956665
DOI:10.59038/jjmie/200213