Data Analytics in Maintenance Planning (DAIMP)
Purpose and goal
DAIMP aimed at higher productivity and reduced environmental impact in production, the main goals of FFI Sustainable Production. They were achieved through WP1 to 4 by focusing on different parts of maintenance decision making. WP1 developed capability framework; WP2 developed descriptive, predictive & prescriptive algorithms for bottleneck detection, WP3 developed data-driven machine criticality framework; WP4 developed component classification to design PM programs; WP5 developed test-beds.
Expected results and effects
DAIMP project showed that maintenance have a key role in enabling industrial digitalization. The project put the maintenance research back on the national agenda. Main effects: producing world-leading level in MES data analytics research; showing the link between maintenance and productivity increase, thereby changing narrow-focused view of maintenance organizations to achieve system perspective; showing how to work with component level problems to working with vendors and end-users.
Planned approach and implementation
The overall goals of the project were divided into specific goals. 5 WPs were designed to achieve those specific goals and WP6 managed the entire project. All the 5 WPs were executed in parallel with academic partners leading them. The industry partners contributed to different WPs throughout the project. In addition to strong individual WP focus, some WPs collaborated to maximize research potentials. As part of WP6, an international evaluation was conducted by inviting two visiting professors.