Scholarlink

Metal additive manufacturing (MAM) is a series of production methods that use 3D modeling data to join materials to build components in layers. MAM is a promising method for complicated parts with several functionalities and is revolutionizing product development in the aerospace, automotive, and medical industries. Technology is maturing in design, process, and production as more organizations use MAM to make final items. Controlling all components of a MAM approach determines its precision. However, major issues include construction consistency, printing errors, and material property incompatibilities. In recent years, design for metal additive manufacturing (DFMAM) and neural networks (NN) have evolved into the most preferred technologies for addressing these essential concerns. DFMAM uses NN for healthcare, image processing, prediction, learning, and several other applications due to the growing availability of data. These applications maximize manufacturing efficiency and reduce expenses. This review introduces NN-integrated DFMAM, which uses NN’s ability to grasp the complex connections among design domains and performance areas. Considering that NN’s biggest benefit is its ability to simulate input and output relationships in both directions. Additionally, the NNs most often utilized for MAM are analyzed and examined with detailed comparison.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrated Design Using Physic-Based Machine Learning that Utilizes Neural Network for Metal Additive Manufacturing: A Review

  • 章节

  • 发表日期：

    2026年

查看全文
  • Onuchukwu Godwin Chike,
  • Norhayati Binti Ahmad,
  • Wan Fahmin Faiz Wan Ali

摘要

Metal additive manufacturing (MAM) is a series of production methods that use 3D modeling data to join materials to build components in layers. MAM is a promising method for complicated parts with several functionalities and is revolutionizing product development in the aerospace, automotive, and medical industries. Technology is maturing in design, process, and production as more organizations use MAM to make final items. Controlling all components of a MAM approach determines its precision. However, major issues include construction consistency, printing errors, and material property incompatibilities. In recent years, design for metal additive manufacturing (DFMAM) and neural networks (NN) have evolved into the most preferred technologies for addressing these essential concerns. DFMAM uses NN for healthcare, image processing, prediction, learning, and several other applications due to the growing availability of data. These applications maximize manufacturing efficiency and reduce expenses. This review introduces NN-integrated DFMAM, which uses NN’s ability to grasp the complex connections among design domains and performance areas. Considering that NN’s biggest benefit is its ability to simulate input and output relationships in both directions. Additionally, the NNs most often utilized for MAM are analyzed and examined with detailed comparison.