Estimation and Optimization of Tool Wear in Conventional Turning of 709M40 Alloy Steel Using Support Vector Machine...

Area of Science:

• Manufacturing Engineering
• Materials Science
• Artificial Intelligence

Background:

• Cutting tool wear negatively impacts product quality and increases manufacturing costs.
• Optimizing machining parameters and tool life is crucial for resource conservation and production efficiency.

Purpose of the Study:

• To introduce a computational approach for estimating tool wear in the turning process using artificial intelligence.
• To determine the effectiveness of Support Vector Machines (SVM) with Bayesian optimization for predicting tool wear based on machining parameters.

Main Methods:

• Utilized a coated insert carbide tool (2025) for turning tests on 709M40 alloy steel.
• Collected experimental data on feed rate, depth of cut, and cutting speed.
• Employed Support Vector Machines (SVM) for regression, optimized with Bayesian methods, to estimate tool wear.
• Measured tool wear using a scanning electron microscope (SEM) and trained the SVM model on 162 data points.

Main Results:

• The SVM model with Bayesian optimization achieved high accuracy in tool wear estimation.
• Reported a mean absolute percentage error (MAPE) of 6.13% and a root mean square error (RMSE) of 2.29% for the model's predictions.
• Validated the model's performance by estimating experimental testing data points.

Conclusions:

• Artificial intelligence methods, specifically SVM with Bayesian optimization, are feasible for estimating machining parameters and tool wear.
• Adopting AI can significantly reduce manufacturing time and costs.
• This approach contributes to more sustainable manufacturing processes through optimized resource utilization and waste reduction.