Master Thesis - Data - driven Optimization Of Maintenance In Manufacturing Operations

Master Thesis - Data-Driven Optimization of Maintenance in Manufacturing Operations

Maintenance plays a critical role in ensuring operational efficiency, equipment reliability, and cost control in manufacturing. With increasing digitalization, companies now have access to vast amounts of data — including failure history, operational costs, inventory levels, and equipment complexity. However, leveraging this data effectively to optimize maintenance strategies remains a challenge. This project aims to explore how maintenance can be improved using available data and identify gaps that hinder effective decision-making.

To investigate how maintenance activities in a manufacturing environment can be optimized using historical failure data, cost metrics, inventory records, and equipment complexity. The project will combine theoretical frameworks, industry best practices, and practical data from Tetra Pak to develop actionable insights and recommendations.

Key components of the project:

• Literature Review: Study existing models and strategies for maintenance optimization (e.g., RCM, TPM, predictive maintenance).
• Industry Benchmarking: Analyze how leading manufacturing companies use data to drive maintenance decisions.
• Data Analysis: Examine Tetra Pak's available maintenance data (failure logs, cost reports, inventory usage, etc.).
• Gap Identification: Determine if critical data is missing or insufficient for building effective models.
• Modeling & Simulation: Propose conceptual models or decision-support tools based on available data.
• Recommendations: Suggest improvements in data collection, integration, and maintenance strategy.

Expected outcome:

• A detailed report outlining current maintenance practices and optimization opportunities.
• Identification of key data sources and missing elements.
• Conceptual framework or prototype model for data-driven maintenance planning.
• Recommendations for improving data infrastructure and maintenance strategy.

Timeframe and schedule:

Full time work one semester. The project requires knowledge and studies in Industrial Manufacturing. Selection is made continuously.