Study on parameter optimization of laser cladding Fe60 based on GA-BP neural network

Abstract

Laser cladding is an emerging surface modification technology, which can effectively improve the wear and corrosion resistance of the workpiece surface. It is widely used in aviation, aerospace, iron and steel metallurgy and other fields. The parameters of the cladding process directly affect the performance and quality of the cladding layer. Optimizing process parameters is significant to prepare high-quality cladding layers. In this study, a three-dimensional numerical model of C45 laser cladding Fe60 powder was established, and the transient evolution law of the cladding temperature, flow rate and thermal stress was revealed. On this basis, the parameters of the cladding process were changed to perform multiple sets of numerical calculations and obtain sample data. A GA-BP neural network model was established to determine the optimal parameters of the cladding process. The cladding temperature was tracked and observed with the thermal imager, and the cladding morphology was observed by the scanning electron microscope, which verified the effectiveness of the numerical model. Calculations show that the maximum temperature of the molten pool reaches 3240 K at 2.5 s, and the isotherm shows a ‘comet tail’ distribution. The maximum flow rate of the molten pool is 0.33 m/s, and the thermal stress in cladding reaches 367 MPa. Based on the optimized process parameters determined by the GA-BP neural network, the laser power is 1076.41 W, the spot radius is 2.61 mm, and the scanning speed is 6.05 mm/s. This research provides a significant theoretical basis for effectively improving the cladding quality.

Keywords:

• Laser cladding
• Fe60
• GA-BP neural network
• process parameter optimization

Ethical approval

All analyses were based on previously published studies; thus, no ethical approval and patient consent are required.

Disclosure statement

All authors agree with the participation and publication of this article. All authors declare that they do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.

Additional information

Funding

This work was supported by the Innovation Talent Support Plan Program of Higher Education Institutions of Liaoning Province [20201020], National Key R&D Program Advanced Structures and Composite Materials of China [2021YFB3702002].