The Project Organization

The PrimaVera project is structured in six technical work packages and two concerning dissemination and management. The chain wide communication and management are considered crucial components in this project. The consortium contains 13 partners: 6 academic partners, and 10 industrial or societal partners.

 

Interaction of the different Workpackages

 

WP1 – DATA ACQUISITION

Lead: Wouter Teeuw – Saxion University of Applied Sciences

Goal: Discover the knowledge and the information in the data by 1) determining what to measure and how to measure it so as to optimize the quality of the collected data for the purpose of PM; 2) investigating novel sources of data and information collection; 3) creating a decision support system.

 

WP2 – DATA PROCESSING AND DIAGNOSIS

Lead: Alessandro Di Bucchianico – Eindhoven University of Technology

Goal: The main goal of WP2 is the transfer of raw sensor data into actionable information relevant for maintenance. WP2 will develop novel automated methods for real-time data validation and correction, building upon probabilistic and statistical techniques for missing value imputation and outlier detection. These methods will take care to exclude effects of changing operational conditions on the measurements and isolate these from the effects caused by failures. 

 

WP3 – PROGNOSTIC ALGORITHMS

Lead: Tiedo Tinga – University of Twente

Goal: The goal of WP3 is to develop scalable and accurate prognostics, i.e. algorithms to predict the future failure behaviour of components and systems. WP3 will quantify relevant key performance indicators, such as the remaining useful life (RUL), time to first failure, availability, and reliability, etc. Thus, WP3 turns the diagnostic information developed in WP2 into useful indicators needed by WP4 to take optimal maintenance decisions. 

 

WP4 – MAINTENANCE AND LOGISTICS OPTIMIZATION

Lead: Rob Basten – Eindhoven University of Technology

Goal: The goal of WP4 is to develop accurate, efficient, effective, and robust methods for large-scale maintenance optimization and simultaneous service logistics control. The novelty of the suggested maintenance plans lies in 1) the incorporation of the key performance indicators (developed in WP3); 2) the combination of maintenance and service logistics planning; and 3) the adaptability and robustness of the underlying algorithms.

 

WP5 – ORGANIZATIONAL BEHAVIOR AND HUMAN DECISION MAKING

Lead: Phillipe van de Calseyde – Eindhoven University of Technology

Goal: The goal of WP5 is to develop a fundamental understanding of the user requirements and design principles for developing effective decision support tools in the domain of predictive maintenance. These insights will be used to design novel, user-centered maintenance tools that make the user-system interaction more effective and efficient. In a similar vein, developing advanced maintenance techniques is useless unless they are well-integrated into the organization’s overall business processes. As such, WP5 will develop new procedures for the effective implementation of data-driven maintenance systems within organizations.

 

WP6 – PREDICTIVE MAINTENANCE DEMONSTRATORS

Lead: Frank Grooteman – NLR/Netherlands Aerospace Centre

Goal: The consortium will build three demonstrators, integrating the knowledge, insights, methods and models developed in the WPs 1–5, each delivering a generic building block. Combining the building blocks will translate these into tangible tools that demonstrate the added value of the research to industrial applications, thereby providing a window for dissemination and exploitation.

 

WP7 – DISSEMINATION AND KNOWLEDGE UTILIZATION

Lead: Nils Jansen – Radboud University

 

WP8 – MANAGEMENT

Lead: Anna Hermelink – University of Twente