Short Title: PdM in the Pharmaceutical Industry

 

Long title: Evolution of Prescriptive Maintenance in the Pharmaceutical Industry - Design and Evaluation of a Novel Data-Driven Maintenance Strategy for the Example of a Chromatography Machine

 

Assignment to our (IMW) research priorities:

  • Predictive Maintenance
  • Machine Learning
  • Production

Sponsor: Takeda

Duration: 01.01.2022-31.12.2023

Abstract:

The pharmaceutical industry has evolved significantly, transitioning from manual processing of simple drug preparations to large-scale production of complex drug products. This shift in the production process has led to changing demands in terms of machine availability and lead time. Therefore, this project aims to propose a prescriptive maintenance strategy specifically designed for the 24-hour pharmaceutical industry. The objectives and research questions are as follows:

Objective 2: Identify state-of-the-art strategies suitable for the pharmaceutical industry and assess their potential for optimizing key performance indicators (KPIs). This will be achieved through a systematic literature review and the application of findings to the industry context. The corresponding research question 1 focuses on identifying effective strategies and evaluating their impact in the pharmaceutical industry.

Objective 2: Determine the data requirements for a data management layer that can support knowledge-based maintenance strategies in the pharmaceutical industry. This includes identifying the necessary data inputs for predictive data models. The answer to research question 2 involves describing the design of the data management layer, specifying data requirements, and providing an overview of different predictive data models.

Objective 3: Develop a conceptual framework for a prescriptive maintenance strategy in the pharmaceutical industry that addresses the unique demands of 24-hour production. Research question 3 will be addressed by presenting the conceptual framework and demonstrating its applicability and performance using a chromatography machine as an example within the pharmaceutical industry's 24-hour production setting.

Resultate:

The project is expected to yield the following results: identification of state-of-the-art maintenance strategies and associated key performance indicators (KPIs) for improvement in the pharmaceutical industry; determination of data requirements for an effective data management layer supporting predictive models in the industry; and development of a prescriptive maintenance concept tailored to 24-hour production, demonstrated through a specific use case example. These results will showcase the enhanced maintenance practices and operational efficiency achievable in the pharmaceutical industry.

Partners:

Research Group of Production- and Maintenance Management (Management)

Takeda Pharma Ges.m.b.H., opens an external URL in a new window

Projectmanagement:

Dipl.-Ing. Linus Kohl

Telephone: +43 1 58801-33048

Email: linus.kohl@tuwien.ac.at