An Improved Multi-Objective Grey Wolf Optimizer for Bi-Objective Parameter Optimization in Single Point Incremental...

Area of Science:

• Materials Science and Engineering
• Manufacturing Processes
• Computational Mechanics

Background:

• Single Point Incremental Forming (SPIF) is a flexible manufacturing process for sheet metals.
• Excessive sheet thinning and geometric deviation are critical challenges in SPIF.
• Optimizing SPIF process parameters is essential for achieving high-quality components.

Purpose of the Study:

• To develop a bi-objective process parameter optimization framework for Al1060 sheets in SPIF.
• To minimize sheet thinning and geometric deviation simultaneously.
• To enhance the prediction accuracy and efficiency of forming quality.

Main Methods:

• Utilized multilayer perceptron (MLP) as a surrogate model for rapid prediction of forming quality.
• Employed an improved multi-objective grey wolf optimization (IMOGWO) algorithm for efficient Pareto optimal solution searching.
• Incorporated Spm chaotic mapping, enhanced convergence coefficient updates, and associative learning within IMOGWO.
• Applied entropy-weighted TOPSIS for selecting optimal parameters from the Pareto front.

Main Results:

• The proposed framework effectively reduced sheet thinning and geometric deviation in SPIF.
• MLP surrogate model enabled rapid and accurate prediction of forming quality.
• IMOGWO algorithm efficiently identified Pareto optimal solutions for bi-objective optimization.
• Experimental validation confirmed the simulation results with low relative errors (0.58% for thinning, 3.10% for deviation).

Conclusions:

• The developed optimization framework is feasible and effective for improving SPIF quality.
• The combination of MLP and IMOGWO offers a powerful approach for complex manufacturing process optimization.
• The findings have practical potential for enhancing the precision and reliability of SPIF components.