Page 42 - IJAMD-1-2

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

existing AM workflows is essential for maximizing architectures, modular designs, and cloud-based
efficiency and effectiveness. 11,13,17 Cross-functional platforms can facilitate scalability, adaptability, and cost-
teams comprising engineers, data scientists, and effectiveness in deploying AI technologies across diverse
manufacturing experts should collaborate to design manufacturing environments.
and implement integrated solutions that complement In summary, embracing AI-driven quality assurance
existing processes and systems. in AM processes entails strategic vision, technological
(v) Data management and governance: Organizations investments, collaborative partnerships, and a culture
must establish robust data management practices of continuous improvement. 1,3,7,18,21,22,32 By leveraging AI
and governance frameworks to ensure the quality, technologies effectively and responsibly, organizations
security, and integrity of data used in AI-driven can enhance product quality, reduce costs, and drive
quality assurance. 34,35 Data collection, storage, and innovation, positioning them for success in the rapidly
processing protocols should comply with relevant evolving landscape of AM.
regulatory requirements and industry standards to
mitigate privacy and security risks. 8. Discussion
(vi) Continuous improvement and iteration: Continuous
monitoring, evaluation, and iteration of AI-driven The present research sheds light on the transformative
quality assurance systems are necessary to adapt potential of AI in revolutionizing quality assurance
to evolving manufacturing requirements and practices within AM processes. 14,15 Through an exploration
technological advancements. 36,37 Feedback loops of AI-driven approaches such as defect detection,
should be established to gather insights from process monitoring, predictive maintenance, and design
production data, user feedback, and performance optimization, this research underscores the critical role
metrics, enabling continuous improvement and that AI technologies play in enhancing the reliability,
optimization of AI models and algorithms. efficiency, and consistency of AM operations.
(vii) Risk management and contingency planning: 8.1. Advancements in quality assurance
Organizations should proactively identify and mitigate
risks associated with AI-driven quality assurance, The integration of AI algorithms, ML techniques,
including algorithmic bias, model overfitting, and and computer vision systems has enabled significant
system failures. 19,20 Contingency plans and risk advancements in quality assurance across various stages of
mitigation strategies should be developed to address the AM process. 14,18,28 AI-driven defect detection systems
potential disruptions and ensure business continuity can identify and classify defects with high accuracy, enabling
in the event of AI-related issues or failures. real-time quality control and non-destructive testing.
(viii) Regulatory compliance and certification: Compliance Process monitoring and predictive maintenance systems
with regulatory standards and certification leverage AI to track key process parameters, anticipate
requirements is critical for gaining approval and equipment failures, and optimize production workflows,
acceptance of AI-driven quality assurance solutions thereby minimizing defects and maximizing operational
in safety-critical industries. 9,10 Organizations efficiency. 14,28 Additionally, AI-driven generative design
should proactively engage with regulatory agencies, tools empower engineers to explore innovative design
standards bodies, and industry stakeholders alternatives and optimize part geometries for enhanced
to navigate regulatory complexities and obtain performance and manufacturability.
necessary certifications and approvals.
(ix) Customer education and communication: Educating 8.2. Implications for industry
customers and stakeholders about the benefits, The implications of AI-driven quality assurance in AM
capabilities, and limitations of AI-driven quality extend beyond technological advancements to strategic,
assurance in AM is essential for building trust and operational, and organizational dimensions. Industry
confidence. Transparent communication channels stakeholders must recognize the strategic importance
7,8
should be established to address customer inquiries, of AI technologies in AM and invest in talent, expertise,
concerns, and expectations regarding the use of AI and collaborative partnerships to drive innovation
technologies in quality assurance. and competitiveness. 11,14,19,28 Seamless integration of
(x) Scalability and sustainability: Scalability and sustainability AI-driven quality assurance tools into existing workflows,
considerations should be factored into the design and coupled with robust data management and governance
implementation of AI-driven quality assurance solutions practices, is essential for maximizing the benefits of AI
to support long-term growth and expansion. 16,17 Flexible technologies while ensuring regulatory compliance and

Volume 1 Issue 2 (2024) 36 doi: 10.36922/ijamd.3455