Témakiírások
Advancing Machining Processes through Real-Time Monitoring and Predictive Modeling
témakiírás címe
Advancing Machining Processes through Real-Time Monitoring and Predictive Modeling
intézmény
doktori iskola
témakiíró
társtémakiíró
tudományág
témakiírás leírása
Background and Motivation
The increasing global population and the depletion of natural resources necessitate a transformation in industrial production practices. Industries are now required to optimize their production systems to reduce material consumption, improve efficiency, and deliver high-quality products at competitive prices. Achieving these objectives demands the adoption of innovative technologies that reduce costs while maintaining superior product standards.
Modernizing outdated equipment, integrating versatile machinery, and incorporating emerging technologies such as 3D printing are critical strategies to meet these demands. However, technologies like 3D printing are still in their early stages of development and cannot yet serve as comprehensive solutions. Another significant challenge is the integration of disruptive innovations that bridge the digital and physical realms. Emerging technologies such as the Internet of Things, Industry 4.0, robotics, big data, cloud manufacturing, and augmented reality are reshaping production systems and work environments. This new industrial paradigm has the potential to transform production processes, create new business models, and improve overall productivity.
Research Problem
This research focuses on developing methodologies to measure surface roughness directly on machine tools during machining operations and exploring how this data can be effectively utilized to enhance production processes. The study aims to create a predictive model capable of continuously estimating surface roughness in real-time, aligning with modern manufacturing requirements for smarter and more efficient processes.
Research Objectives
1. Develop a Predictive AI-Based Model:
Design an artificial intelligence-based model to continuously estimate surface roughness during machining by utilizing multiple process characteristics.
2. Investigate Real-Time Measurement Feasibility:
Assess the possibility of reliably measuring surface roughness during machining operations across different methods.
3. Analyze Cutting Force and Vibration Relationships:
Explore the relationship between cutting forces and vibrations in the Machine Tool-Tooling-Workpiece system, using both simulation data and experimental validation.
Methodology
AI Model Development:
• Utilize machine learning techniques to develop a model that predicts surface roughness based on real-time data collected during machining, incorporating factors such as cutting forces, tool wear, and vibration.
Data Collection and Validation:
• Employ advanced sensors and measurement systems to gather data on surface roughness during machining. Validate the reliability and accuracy of these measurements across various machining methods.
Experimental Analysis:
• Conduct cutting experiments to study the impact of cutting forces and vibrations on surface quality. Use cutting force data from simulations and validate findings through physical experimentation.
Expected Outcomes
• A reliable and robust AI-based predictive model for real-time surface roughness estimation.
• Enhanced methodologies for measuring surface roughness during machining operations.
• A comprehensive understanding of the interplay between cutting forces, vibrations, and surface quality, enabling better process optimization.
Significance
This research aims to contribute to the development of smarter manufacturing systems by integrating real-time monitoring and predictive modeling. The findings are expected to help industries achieve higher efficiency, reduce production costs, and improve the quality of machined products.
References: [1–4]
1. Namboodri, T.; Felh, C.; Sztankovics, I. Optimization of Machining Parameters for Improved Surface Integrity in Chromium–Nickel Alloy Steel Turning Using TOPSIS and GRA. Applied Sciences 2025, Vol. 15, Page 8895 2025, 15, 8895, doi:10.3390/APP15168895.
2. Namboodri, T.; Felhő, C. AI FOR QUALITY OPTIMIZATION IN TURNING: A SHORT REVIEW. MM Science Journal 2025, 2025, 8338–8352, doi:10.17973/MMSJ.2025_06_2025033.
3. Felhő, C.; Namboodri, T. Statistical Analysis of Cutting Force and Vibration in Turning X5CrNi18-10 Steel. Applied Sciences 2024, 15, 54, doi:10.3390/APP15010054.
4. Felhő, C.; Namboodri, T.; Sisodia, R.P.S. Taguchi’s L18 Design of Experiments for Investigating the Effects of Cutting Parameters on Surface Integrity in X5CrNi18-10 Turning. Designs 2025, Vol. 9, Page 59 2025, 9, 59, doi:10.3390/DESIGNS9030059.
The increasing global population and the depletion of natural resources necessitate a transformation in industrial production practices. Industries are now required to optimize their production systems to reduce material consumption, improve efficiency, and deliver high-quality products at competitive prices. Achieving these objectives demands the adoption of innovative technologies that reduce costs while maintaining superior product standards.
Modernizing outdated equipment, integrating versatile machinery, and incorporating emerging technologies such as 3D printing are critical strategies to meet these demands. However, technologies like 3D printing are still in their early stages of development and cannot yet serve as comprehensive solutions. Another significant challenge is the integration of disruptive innovations that bridge the digital and physical realms. Emerging technologies such as the Internet of Things, Industry 4.0, robotics, big data, cloud manufacturing, and augmented reality are reshaping production systems and work environments. This new industrial paradigm has the potential to transform production processes, create new business models, and improve overall productivity.
Research Problem
This research focuses on developing methodologies to measure surface roughness directly on machine tools during machining operations and exploring how this data can be effectively utilized to enhance production processes. The study aims to create a predictive model capable of continuously estimating surface roughness in real-time, aligning with modern manufacturing requirements for smarter and more efficient processes.
Research Objectives
1. Develop a Predictive AI-Based Model:
Design an artificial intelligence-based model to continuously estimate surface roughness during machining by utilizing multiple process characteristics.
2. Investigate Real-Time Measurement Feasibility:
Assess the possibility of reliably measuring surface roughness during machining operations across different methods.
3. Analyze Cutting Force and Vibration Relationships:
Explore the relationship between cutting forces and vibrations in the Machine Tool-Tooling-Workpiece system, using both simulation data and experimental validation.
Methodology
AI Model Development:
• Utilize machine learning techniques to develop a model that predicts surface roughness based on real-time data collected during machining, incorporating factors such as cutting forces, tool wear, and vibration.
Data Collection and Validation:
• Employ advanced sensors and measurement systems to gather data on surface roughness during machining. Validate the reliability and accuracy of these measurements across various machining methods.
Experimental Analysis:
• Conduct cutting experiments to study the impact of cutting forces and vibrations on surface quality. Use cutting force data from simulations and validate findings through physical experimentation.
Expected Outcomes
• A reliable and robust AI-based predictive model for real-time surface roughness estimation.
• Enhanced methodologies for measuring surface roughness during machining operations.
• A comprehensive understanding of the interplay between cutting forces, vibrations, and surface quality, enabling better process optimization.
Significance
This research aims to contribute to the development of smarter manufacturing systems by integrating real-time monitoring and predictive modeling. The findings are expected to help industries achieve higher efficiency, reduce production costs, and improve the quality of machined products.
References: [1–4]
1. Namboodri, T.; Felh, C.; Sztankovics, I. Optimization of Machining Parameters for Improved Surface Integrity in Chromium–Nickel Alloy Steel Turning Using TOPSIS and GRA. Applied Sciences 2025, Vol. 15, Page 8895 2025, 15, 8895, doi:10.3390/APP15168895.
2. Namboodri, T.; Felhő, C. AI FOR QUALITY OPTIMIZATION IN TURNING: A SHORT REVIEW. MM Science Journal 2025, 2025, 8338–8352, doi:10.17973/MMSJ.2025_06_2025033.
3. Felhő, C.; Namboodri, T. Statistical Analysis of Cutting Force and Vibration in Turning X5CrNi18-10 Steel. Applied Sciences 2024, 15, 54, doi:10.3390/APP15010054.
4. Felhő, C.; Namboodri, T.; Sisodia, R.P.S. Taguchi’s L18 Design of Experiments for Investigating the Effects of Cutting Parameters on Surface Integrity in X5CrNi18-10 Turning. Designs 2025, Vol. 9, Page 59 2025, 9, 59, doi:10.3390/DESIGNS9030059.
felvehető hallgatók száma
1 fő
helyszín
Institute of Manufacturing Science
jelentkezési határidő
2025-12-31