Application of Artificial Intelligence for Surface Roughness Prediction of Additively Manufactured Components

Area of Science:

• Materials Science and Engineering
• Manufacturing Technology
• Computational Science

Background:

• Additive manufacturing (AM) offers production efficiency but struggles with consistent product quality.
• Surface roughness is a critical quality parameter impacting performance in key industries like automotive and aerospace.
• Predicting and controlling surface roughness in AM is essential for meeting industry standards.

Purpose of the Study:

• To review recent advancements in artificial intelligence (AI) and machine learning (ML) for predicting surface roughness in AM.
• To identify challenges and future directions for AI applications in AM surface quality.
• To highlight the potential of AI in improving AM productivity and competitiveness.

Main Methods:

• Review of existing research on AI and ML techniques applied to surface roughness prediction in AM.
• Analysis of deep learning and machine learning models used for surface quality assessment.
• Synthesis of findings on the effectiveness of AI in cost and time reduction.

Main Results:

• AI and ML, including deep learning, are effective in predicting surface roughness in AM components.
• These AI methods demonstrate significant potential for cost reduction and time savings.
• Successful application of AI minimizes re-processing and ensures compliance with technical specifications.

Conclusions:

• AI integration is crucial for enhancing productivity and competitiveness in additive manufacturing.
• AI-driven surface roughness prediction addresses key challenges in achieving consistent product quality.
• Future research should focus on further developing and implementing AI methodologies for advanced AM applications.