Prediction of formation force during single-point incremental sheet metal forming using artificial intelligence...

Area of Science:

• Manufacturing Engineering
• Materials Science
• Computational Intelligence

Background:

• Single-point incremental forming (SPIF) offers a flexible and economical method for complex part manufacturing from sheet materials.
• Accurate measurement and prediction of forming forces in SPIF are crucial for process optimization, failure prevention, and implementing real-time control systems.

Purpose of the Study:

• To experimentally investigate the influence of key process parameters on the maximum forming force during SPIF.
• To develop and evaluate an efficient force predictive model using an adaptive neuro-fuzzy inference system (ANFIS).

Main Methods:

• Conducted experimental studies on SPIF, systematically varying parameters: step size, tool diameter, sheet thickness, and feed rate.
• Developed and compared predictive models for forming force, including an artificial neural network (ANN), a regression model, and an ANFIS model.

Main Results:

• The experimental results demonstrated the impact of process parameters on the maximum forming force.
• All developed models showed good agreement between predicted and experimental forces.
• The ANFIS model achieved superior performance, fully leveraging the capabilities of the ANN model for force prediction.

Conclusions:

• The study successfully identified key parameters influencing SPIF forming forces.
• ANFIS is a highly effective tool for developing accurate force predictive models in SPIF.
• The findings contribute to the advancement of process control and optimization in incremental manufacturing.