Multi-dimensional data fusion and quantitative modeling method for metal additive manufacturing process system

Abstract

The invention discloses a multi-dimensional data fusion and quantitative modeling method for a metal additive manufacturing process system, and the method comprises the steps: obtaining diversified multivariate multi-dimensional discrete strong coupling original data related to the metal additive manufacturing process system, and carrying out preprocessing of the data, and obtaining the metal additive manufacturing process data; carrying out distribution state evaluation, classification screening, feature extraction and normalization processing on the metal additive manufacturing process data to obtain normalized structural data of the metal additive manufacturing process system. Aiming at normalized structural data of the metal additive manufacturing process system, according to a process system modeling framework, a neural network structure is designed, model training parameters are set, calculation training is carried out, model structure and parameter optimization is carried out through training result analysis, and a process system quantification model is obtained. According to the invention, the problems of analysis, application and visualization of multi-dimensional diversified data of different equipment, different materials and different process methods are solved.

Description

technical field [0001] The present invention relates to the field of data processing, in particular to a method for multi-dimensional data fusion and quantitative modeling of a metal additive manufacturing process system. Background technique [0002] Metal additive manufacturing (Additive Manufacturing, AM) or 3D printing is the most cutting-edge and most potential additive manufacturing technology, and it is a potentially disruptive technology in important fields such as aerospace, biomedicine, and energy transportation. This technology uses heat sources such as laser beams, electron beams or arcs to melt metal powder or wire, and builds metal parts layer by layer through solidification of the molten pool, which can improve design freedom and manufacturing flexibility, thereby realizing complex structure molding and increasing product quality. Customization and reduced time-to-market while removing the constraints of traditional economies of scale. [0003] However, the m...

AI Technical Summary

Problems solved by technology

[0003] However, the metal additive manufacturing process system is a complex selective continuous melting and casting system involving complex physical effects such as arc heat, force, sound, light, electricity, and magnetism, material melting, molten pool flow, melt solidification, and matrix solid-state phase transition. Among them, the coupling effect of physical fields such as energy field, temperature field, flow field, phase field, and stress field is strong, and the heat and mass transfer process of the rapid transition of solid, liquid, and plasma in metal materials is extremely complicated, resulting in plasma morphology, droplet Significant changes and differences in transition, cladding forming, alloying element distribution, microstructure state, and component strength and toughness can cause defects such as pores, cracks, humps, lack of fusion, and slag inclusions, which seriously affect the stability of the additive manufacturing process and components. Comprehensive performance, but due to the large number of parameters, strong coupling, complex process and high nonlinearity, it is difficult to quantitatively represent and systematically model and analyze. Low, weak generalization ability, no self-learning ability and other limitations make it difficult to work and have low practicability

[0004] In view of the metal additive manufacturing industry's ultimate pursuit of full parametric design, precise process control and efficient intelligent manufacturing, but lack of effective systematic modeling and analysis methods, a multi-dimensional data fusion of metal additive manufacturing process system was developed. and quantitative modeling methods have become a top priority

Images