Analysis and Prediction of Melt Pool Geometry in Rectangular Spot Laser Cladding Based on Ant Colony...

Area of Science:

• Materials Science and Engineering
• Manufacturing Technology
• Additive Manufacturing

Background:

• Rectangular spot laser cladding offers high efficiency but can compromise melt pool stability and cladding quality.
• Accurate prediction of melt pool morphology is crucial for controlling quality in wide beam laser cladding.

Purpose of the Study:

• To develop a melt pool monitoring system for real-time prediction of melt pool morphology and size during rectangular spot laser cladding.
• To establish an accurate prediction model for melt pool width and area using Support Vector Regression (SVR) optimized with Ant Colony Optimization (ACO).

Main Methods:

• Real-time monitoring of melt pool morphology using a developed system.
• Image processing techniques to extract melt pool width and area.
• Development and optimization of a Support Vector Regression (SVR) model using Ant Colony Optimization (ACO) with laser power, scanning speed, and powder feed rate as inputs.

Main Results:

• The Ant Colony Optimization-Support Vector Regression (ACO-SVR) model accurately predicted melt pool width with a relative error below 2.2%.
• The ACO-SVR model achieved a relative error of less than 9.13% in predicting melt pool area.
• The developed system and model enable precise control over melt pool dimensions in laser cladding.

Conclusions:

• The ACO-SVR model provides a reliable method for predicting melt pool dimensions in rectangular spot laser cladding.
• The melt pool monitoring system and predictive model contribute to enhanced quality control in high-efficiency laser cladding processes.
• Accurate prediction of melt pool width and area is achievable, addressing challenges associated with melt pool stability.