Sanae Tajalli’s scientific contributions

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (1)


The number of published papers on the application of ML in various AM methods as a function of publication year. The data was extracted according to the keywords tabulated in Table 1
Process parameters for various AM methods upon consulting Refs [6, 23, 41, 42, 43, 44, 45, 46, 47–48]. The surface roughness represents the average deviation of the surface from its mean height
Application of mechanistic models and ML in the various steps of metal AM. Both mechanistic models and ML offer a quantitative framework for understanding the characteristics of components. This figure illustrates the respective roles of ML and mechanistic models at different stages in manufacturing and analyzing elements
Three different approaches for the classification of ML
Some of the most essential ML algorithms with their description

+23

Intelligent laser-based metal additive manufacturing: A review on machine learning for process optimization and property prediction
  • Article
  • Full-text available

December 2024

·

135 Reads

The International Journal of Advanced Manufacturing Technology

Alireza Moradi

·

Sanae Tajalli

·

·

Abdollah Saboori

The utilization of metal Additive Manufacturing (AM) has led to substantial progress in the manufacturing process of metal components. Evaluating the influence of the wide variety of factors related to the material type, AM process, and the resultant microstructure and properties is not easy and accurate by traditional engineering strategies. Therefore, one of the most effective ways to improve AM performance is to employ artificial intelligence methods, such as Machine Learning (ML), to establish complex links and enhance control over systems and product quality. The integration of these powerful ML techniques presents an emerging opportunity to revolutionize manufacturing processes, tackle production challenges, and optimize resource consumption. Consequently, in this review, the role of machine learning in laser-based metal additive manufacturing is explored by highlighting its applications in process optimization and property prediction. Evaluation of the results reported in the literature indicates that it is possible to establish relationships between process, structure, and properties by considering inputs such as part geometry, material properties, microstructural characteristics, and AM process parameters and utilizing ML algorithms. Defect detection and in-situ monitoring are among the other applications of ML algorithms in AM procedures, enhancing the manufacturability and repeatability of metal components. For this purpose, various linkages and correlations for Directed Energy Deposition and Laser Powder Bed Fusion are outlined in this review. The advancement in hardware and software will boost the advantage of applying data-driven approaches to overcome the obstacles in metal AM.

Download