Qua²ntum: Quality Management System for AI in Regulated Markets with Data-Driven Interpretability and Robustness through Real and Synthetic Data

BMBF / KI4KMU Project / May 1, 2024

Quality Assurance with AI in Production

Aimino is proud to be part of the groundbreaking “Qua²ntum” project, aimed at enhancing quality management systems (QMS) for AI in the highly regulated pharmaceutical industry. This project focuses on leveraging real and synthetic data to ensure interpretability and robustness of AI systems, thereby maintaining consistent, efficient, and resource-saving production.

Quality² – Ensuring Quality with and for AI

The “Qua²ntum” project aims to enable the use of AI systems for quality assurance in the pharmaceutical sector. To comply with stringent regulatory requirements and ensure transparency in decision-making processes, a dedicated management system is essential for controlling and monitoring AI systems.

Development of a Comprehensive QMS

The primary objective of the “Qua²ntum” project is to develop a comprehensive QMS tailored to the specific needs of AI systems. This system will define processes, responsibilities, and documentation during the development of AI systems, ensuring traceability, transparency, and robustness in AI methodologies, and thus, the accountability of decisions made by these systems.

AI Quality Management in the Pharmaceutical Industry

Initially, the project will identify requirements and thoroughly research the relevant regulations. Based on this, both the AI-QMS and AI algorithms will be developed. The effectiveness of the system will be demonstrated through three use cases in the pharmaceutical industry: inspecting empty bottles, bottle necks, and crimp caps. Specifically, the system will check for particles in empty bottles, ensure the integrity of bottle necks, and verify the correct positioning of crimp caps on filled bottles. These use cases not only demonstrate the functionality of the QMS but also the practical applicability and effectiveness of the AI methods.

Building Trust and Ensuring Reliability

By enhancing transparency in AI decision-making, the project aims to strengthen trust in these systems and ensure that they reliably and transparently perform their designated tasks. This initiative will improve production quality in regulated markets and ensure the safety and efficacy of products that impact millions of people worldwide.

Funding

The “Qua²ntum” project is funded by the German Federal Ministry of Education and Research (BMBF) under the “KI4KMU” directive, which supports research, development, and use of AI methods in small and medium-sized enterprises (SMEs).

Project Partners

  • Fraunhofer Institute for Production Technology IPT, Aachen
  • OCTUM GmbH, Ilsfeld
  • Aimino Tech GmbH, Karlsruhe
  • Sartorius AG, Göttingen
  • Groninger Holding GmbH & Co. KG, Crailsheim
  • ROTZINGER PharmaPack, Waiblingen