A Review of Machine Learning for Additive Manufacturing

Additively manufactured parts can present lower mechanical properties because of the anisotropy and defects. Also reliability, repeatability, durability as well as the forecast of characteristics can remain difficult. Artificial intelligence techniques can prevent these challenges. They can analyze complex design requirements and generate optimized designs. These algorithms can be applied for real-time monitoring and quality control. By analyzing high amounts of data and simulating properties with regard to material, artificial intelligence can allow describe new materials with specified features. Integrating artificial intelligence with additive manufacturing processes can lead to increased efficiency, quality, and innovation, ultimately driving advancements in manufacturing. On the other hand, artificial intelligence driven additive manufacturing may face hurdles in ensuring consistent quality, scalability, and generalization across materials and processes. These algorithms require extensive computational resources and time to find optimal solutions, limiting their applicability. In the research regarding with additive manufacturing, machine learning has become a significant field of artificial intelligence, which deals with the development of algorithms and statistical models that allow computers to operate without specific programming. This study provides a review of the recent research on machine learning methods in the additive manufacturing in terms of analysis of strengths, weaknesses, opportunities, and threats (SWOT) analysis, which is crucial in determining if a specific machine learning model suits a specific additive manufacturing process. Conducting a SWOT analysis on the integration of artificial intelligence with additive manufacturing can provide valuable insights into its potential benefits, challenges, technologic and strategic considerations.