Sustainable machining of Inconel 718 using minimum quantity lubrication: Artificial intelligence-based process...

Area of Science:

• Manufacturing Engineering
• Artificial Intelligence
• Sustainable Manufacturing

Background:

• Industries face pressure to reduce carbon emissions and energy consumption.
• CNC machining energy demand is often linked to production lot sizes.
• Existing analytical models for machining energy demand lack integration capabilities.

Purpose of the Study:

• To develop and implement an artificial intelligence-based power reduction strategy for CNC machining.
• To evaluate machine learning algorithms for predicting power consumption in machining processes.
• To optimize energy-aware strategies for sustainable manufacturing.

Main Methods:

• Implementation of an AI-based power reduction strategy on Inconel 718 material.
• Investigation of four control parameters: cutting speed, feed rate, depth of cut, and flow rate.
• Comparison of four machine learning algorithms (K-Nearest Neighbor, Gaussian Regression, Decision Tree, Logistic Regression) for power consumption prediction.
• Evaluation using Minimum Quantity Lubrication (MQL) and Nanofluid-MQL (NF-MQL) sub-systems.

Main Results:

• The Decision Tree algorithm demonstrated the highest accuracy in predicting power consumption (Pc).
• Optimal performance for the Decision Tree model was achieved with a max_depth of 2.
• The Decision Tree model yielded R-squared values of 0.915 for Pc MQL and 0.931 for Pc NF-MQL.

Conclusions:

• The Decision Tree model is the most effective predictor for CNC machining power consumption.
• AI-driven strategies can significantly contribute to energy reduction in manufacturing.
• Energy-aware machining processes are crucial for achieving sustainable industrial practices.