Page 43 - IJAMD-1-2

International Journal of AI for
Materials and Design
AI-driven quality assurance in AM

risk mitigation. 28,29 Moreover, proactive engagement with • Impact: Benchmarking will provide a clear
regulatory agencies, standards bodies, and customers is understanding of the strengths and limitations
critical for navigating regulatory complexities and gaining of various AI approaches, guiding practitioners
acceptance of AI-enabled AM solutions. in selecting the most suitable methods for their
specific applications.
8.3. Future directions and opportunities
(iii) Interdisciplinary collaborations
As AI-driven quality assurance continues to evolve, • Action: Foster collaborations between AI
future research directions and opportunities abound. researchers, material scientists, and AM
Advancements in data availability, model interpretability, practitioners to address complex challenges and
and integration with manufacturing workflows will enable drive innovation.
organizations to overcome technical barriers and unlock • Impact: Interdisciplinary partnerships will
new possibilities for innovation and growth. 18,28 Moreover, combine expertise from different fields, leading to
the development of hybrid AI-physical models that combine the development of more effective and practical
data-driven learning with mechanistic understanding AI-driven solutions for AM.
holds promise for improving defect prediction, process (iv) Investments in technological infrastructure
optimization, and design optimization in AM. 35,37 By • Action: Invest in advanced technological
embracing these challenges and opportunities, industry infrastructure, including high-resolution
stakeholders can realize the full potential of AI technologies sensors, edge computing devices, and specialized
in AM and drive the next wave of industrial revolution. hardware like GPUs.
• Impact: Enhanced infrastructure will support
9. Conclusion the real-time processing and integration of AI
The research on AI-driven quality assurance in AM systems, improving the overall efficiency and
processes underscores the transformative impact of AI effectiveness of quality assurance processes.
technologies on enhancing product quality, reducing (v) Focus on explainable AI
costs, and accelerating innovation in AM. By leveraging • Action: Prioritize the development of explainable
AI-driven approaches for defect detection, process AI models to ensure transparency and trust in
monitoring, predictive maintenance, and design AI-driven quality assurance systems.
optimization, organizations can achieve higher levels of • Impact: Explainable AI will help stakeholders
reliability, efficiency, and competitiveness in the rapidly understand and trust the decision-making
evolving landscape of AM. However, realizing the full processes of AI models, facilitating their
potential of AI technologies requires strategic vision, acceptance and adoption in critical manufacturing
technological investments, collaborative partnerships, environments.
and a culture of continuous improvement. By embracing
these principles and harnessing the power of AI, industry (vi) Continuous improvement and adaptation
stakeholders can position themselves for success in the • Action: Cultivate a culture of continuous
digital era of AM. improvement and adaptation to incorporate
new AI advancements and address emerging
To fully realize the potential of AI technologies in AM, challenges in AM.
several actionable recommendations and future research • Impact: A commitment to continuous
directions should be considered: improvement will ensure that AI-driven quality
(i) Development of standardized datasets assurance systems remain up-to-date and effective
• Action: Establish standardized datasets for in a dynamic technological landscape.
various AM processes and materials to facilitate
the training and benchmarking of AI models. By implementing these recommendations and
• Impact: Standardized datasets will ensure harnessing the power of AI, industry stakeholders can
position themselves for success in the digital era of AM.
consistency and comparability across studies, Future research should focus on refining AI techniques,
accelerating the development and deployment of improving data quality, and developing comprehensive
robust AI models.
frameworks for integrating AI into AM processes.
(ii) Benchmarking methodologies Through strategic vision, technological investments, and
• Action: Develop and adopt benchmarking collaborative efforts, the full potential of AI-driven quality
methodologies to evaluate the performance of assurance in AM can be realized, driving the industry
different AI techniques in AM quality assurance. toward a more innovative and efficient future.

Volume 1 Issue 2 (2024) 37 doi: 10.36922/ijamd.3455