Time-Bound Optimal Planning in CNC Machine Considering Machining Safety DOI
Jianxin Guo, Mingyong Zhao, Lixian Zhang

et al.

IEEE Transactions on Automation Science and Engineering, Journal Year: 2023, Volume and Issue: 21(4), P. 6358 - 6370

Published: Oct. 23, 2023

In this paper, we propose a time-bound optimal planning model to reconcile the dilemma between cutting efficiency and security. Unlike traditional method, consider bound of kinematic constraints be flexible in form fuzzy set. It is reasonable use such an expression considering that safety computer numerical control (CNC) machine susceptible potential disturbance process. A optimization method used obtain compromise aiming balance The original problem can reduced into convex some weak conditions, for which interesting results are proved also solve it. proposed algorithm experimented on our self-designed CNC machine. We verify effectiveness through air-cutting milling process with two respect experiment, by comparing open-loop strategies. Note Practitioners —The starting point article improve performance under premise ensuring machining, but applicable other robot arm path design. boundary existing speed cannot guarantee machining process, blindly reducing will greatly sacrifice processing efficiency. This paper proposes new based programming determine boundary, completely realized manner, avoiding risks reorganization. mathematically describe conditions forming boundaries, then resolve fast-solvable series transformations. perform formed paths, incorporate them CAD system or carry out pocket tests production. Preliminary physical experiments show feasible has unique advantages over methods. future research, give more accurate estimate security membership function extend higher-order kinematically constrained problems.

Language: Английский

Improving generalisation and accuracy of on-line milling chatter detection via a novel hybrid deep convolutional neural network DOI Creative Commons
Pengfei Zhang, Dong Gao, Dongbo Hong

et al.

Mechanical Systems and Signal Processing, Journal Year: 2023, Volume and Issue: 193, P. 110241 - 110241

Published: March 4, 2023

Unstable chatter seriously reduces the quality of machined workpiece and machining efficiency. In order to improve productivity, on-line detection has attracted much interest in past decades. Nevertheless, traditional methods are inevitably flawed due manually extracted features. Deep learning possess outstanding feature classification capabilities, but generalisation accuracy severely affected by labelling training data. To address this, this paper proposed a novel hybrid deep convolutional neural network method combining an Inception module Squeeze-and-Excitation ResNet block (SR-block), namely ISR-CNN. The can automatically extract multi-scale features cutting force signal enrich map. SR-block assign weights different channels, thus suppressing useless maps improving model accuracy. Meanwhile, introduction also risk gradient disappearance speeds up network. is guaranteed two modules without with transition state Milling tests were carried out on wedge-shaped using parameters tool overhang lengths verify generalisability method. results showed that outperforms other achieving validation test sets 100% 97.8%, respectively. comparison existing methods, correctly identify each state, including states. Furthermore, identifies onset earlier than which beneficial for suppression.

Language: Английский

Citations

30
A new intelligent approach of surface roughness measurement in sustainable machining of AM-316L stainless steel with deep learning models DOI
Nimel Sworna Ross, Peter Madindwa Mashinini, C. Sherin Shibi

et al.

Measurement, Journal Year: 2024, Volume and Issue: 230, P. 114515 - 114515

Published: March 15, 2024

Language: Английский

Citations

16
Health monitoring of CNC machining processes using machine learning and wavelet packet transform DOI

Abbas Hussain,

Taha Al Muhammadee Janjua,

Anjum Naeem Malik

et al.

Mechanical Systems and Signal Processing, Journal Year: 2024, Volume and Issue: 212, P. 111326 - 111326

Published: March 12, 2024

Language: Английский

Citations

9
Novel Framework for Quality Control in Vibration Monitoring of CNC Machining DOI Creative Commons
Georgia Apostolou,

Myrsini Ntemi,

Spyridon Paraschos

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(1), P. 307 - 307

Published: Jan. 4, 2024

Vibrations are a common issue in the machining and metal-cutting sector, which spindle vibration is primarily responsible for poor surface quality of workpieces. The consequences range from need to manually finish metal surfaces, resulting time-consuming costly operations, high scrap rates, with corresponding waste time resources. main problem conventional solutions that they address suppression machine vibrations separately control process. In this novel proposed framework, we combine advanced vibration-monitoring methods AI-driven prediction indicators problem, increasing quality, productivity, efficiency evaluation shows number rejected parts, devoted reworking manual finishing, costs reduced considerably. framework adopts generalized methodology tackle condition monitoring processes. This allows broader adaptation different CNC machines unique setups configurations, challenge other data-driven approaches literature have found difficult overcome.

Language: Английский

Citations

5
Research and application of simulation and optimization for CNC machine tool machining process under data semantic model reconstruction DOI

Fei Hu,

Xiumin Zou,

Hongmei Hao

et al.

The International Journal of Advanced Manufacturing Technology, Journal Year: 2024, Volume and Issue: 132(1-2), P. 801 - 819

Published: March 16, 2024

Language: Английский

Citations

5
Time series prediction for production quality in a machining system using spatial-temporal multi-task graph learning DOI
Pei Wang,

Qianle Zhang,

Hai Qu

et al.

Journal of Manufacturing Systems, Journal Year: 2024, Volume and Issue: 74, P. 157 - 179

Published: March 19, 2024

Language: Английский

Citations

4
Online tool wear prediction based on cutting force coefficients identification using neural network DOI

Guicheng Wang,

Min Wang, Peng Gao

et al.

The International Journal of Advanced Manufacturing Technology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 8, 2025

Language: Английский

Citations

0
A Signal Pattern Extraction Method Useful for Monitoring the Condition of Actuated Mechanical Systems Operating in Steady State Regimes DOI Creative Commons

Adriana Munteanu,

Mihaiță Horodincă,

Neculai-Eduard Bumbu

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(4), P. 1119 - 1119

Published: Feb. 12, 2025

The aim of this paper is to present an approach condition monitoring actuated mechanical system operating in a steady-state regime. state signals generated by the sensors placed on (a lathe headstock gearbox) regime contain sum periodic components, sometimes mixed with small amount noise. It assumed that rotating part inside can be characterized shape component within signal. This proposes method find time domain description for significant components these signals, as patterns, based arithmetic averaging signal samples selected at constant regular intervals. has same effect numerical filter multiple narrow pass bands. availability been fully demonstrated experimentally. applied three different signals: active electrical power absorbed asynchronous AC electric motor driving gearbox, vibration and instantaneous angular speed output spindle. presents some relevant patterns describing behavior parts extracted from signals.

Language: Английский

Citations

0
Acoustic-Based Machine Main State Monitoring for High-Speed CNC Drilling DOI Creative Commons

Pimolkan Piankitrungreang,

Kantawatchr Chaiprabha,

Worathris Chungsangsatiporn

et al.

Machines, Journal Year: 2025, Volume and Issue: 13(5), P. 372 - 372

Published: April 29, 2025

This paper introduces an acoustic-based monitoring system for high-speed CNC drilling, aimed at optimizing processes and enabling real-time machine state detection. High-fidelity acoustic sensors capture sound signals during drilling operations, allowing the identification of critical events such as tool engagement, material breakthrough, withdrawal. Advanced signal processing techniques, including spectrogram analysis Fast Fourier Transform, extract dominant frequencies patterns, while learning algorithms like DBSCAN clustering classify operational states cutting, returning. Experimental studies on materials acrylic, PTFE, hardwood reveal distinct profiles influenced by properties conditions. Smoother patterns lower characterize PTFE whereas produces higher rougher due to its density resistance. These findings demonstrate correlation between emissions machining dynamics, non-invasive predictive maintenance. As AI power increases, it is expected in-situ process information achieve resolution, enhancing precision in data interpretation decision-making. A key contribution this project creation open library processes, fostering collaboration innovation intelligent manufacturing. By integrating big concepts algorithms, supports continuous monitoring, anomaly detection, optimization. AI-ready hardware enhances accuracy efficiency improving quality, reducing wear, minimizing downtime. The research establishes a transformative approach advancing manufacturing systems.

Language: Английский

Citations

0
Deep-learning-assisted online surface roughness monitoring in ultraprecision fly cutting DOI
Adeel Shehzad, Xiaoting Rui,

Yuanyuan Ding

et al.

Science China Technological Sciences, Journal Year: 2024, Volume and Issue: 67(5), P. 1482 - 1497

Published: April 25, 2024

Language: Английский

Citations

3