Optimization of wear parameters for ECAP-processed ZK30 alloy using response surface and machine learning approaches:...

Area of Science:

• Materials Science
• Mechanical Engineering
• Tribology

Background:

• ZK30 alloy wear behavior is critical for engineering applications.
• Equal Channel Angular Pressing (ECAP) is a severe plastic deformation technique used to enhance material properties.
• Predicting and optimizing wear parameters is essential for material performance.

Purpose of the Study:

• To predict and optimize processing parameters for ZK30 alloy wear behavior using statistical analysis and machine learning (ML).
• To investigate the effect of ECAP passes on wear responses (volume loss and coefficient of friction).
• To validate ML and regression models for wear prediction.

Main Methods:

• Equal Channel Angular Pressing (ECAP) applied to ZK30 alloy (as-annealed, 1-pass, 4-passes).
• Design of Experiments (DOE) to study wear responses (Volume Loss - VL, Coefficient of Friction - COF) under varying load (P) and speed (V).
• Statistical analysis (ANOVA), ML, and Genetic Algorithms (GA) for prediction and optimization.

Main Results:

• ECAP processing (4 passes) reduced grain size by 92.7% and improved VL by 99.8% compared to as-annealed.
• ML and regression models showed high correlation between predicted and experimental data (70-99.7% accuracy).
• Minimal VL occurred at highest wear test conditions; minimal COF at maximum load, with optimal speed decreasing with ECAP passes.

Conclusions:

• ECAP significantly enhances wear resistance of ZK30 alloy.
• Statistical and ML models effectively predict and optimize wear behavior.
• Optimized processing and wear parameters are crucial for maximizing ZK30 alloy performance.