Product and Production Development

DAIMP- Data analysis in maintenance planning

The DAIMP project connects data collection from a detailed machine level to system level analysis. Reaching a system level is necessary to detect critical equipment, differentiate maintenance planning and prioritize the most important equipment in real-time. Maintenance organizations will also be supported in moving from descriptive statistics of historical data to predictive and prescriptive analytics, forecasting failures and proposing actions before disturbances even occur.

Project manager at MDU

No partial template found

Description of the project

Modern maintenance is a necessity for the implementation of Industrie 4.0 and similar digitalization concepts. A substantial increase in systems availability is crucial to enable the expected levels of automation and autonomy in future production. A main challenge is to go from experiences and guesses in maintenance planning to Big Data analysis and data-driven decision support. The current lack of maintenance-oriented research, based on empirical data, is hindering an increased use of engineering methods within the area.

The project will deliver methods and algorithms for maintenance engineers. The use of data-driven decision support in maintenance planning will enable more resource efficient production, both in terms of productivity and ecologic sustainability, e.g. reduced energy consumption in failure and idle machine states. The project goals are focused on increasing systems availability and specifically on increasing OEE in critical equipment to world-class levels above 85%. Predictive and prescriptive analytics aim to enable more preventive maintenance activities compared to reactive. This will lead to more efficient and robust systems, which in turn reduces the ramp-up time of new products and production systems.

The research approach is based on a unique set of evaluation and demonstration cases. One of the cases will follow the implementation of a completely new production line with new car models at Volvo Cars Torslanda. This case study enables investigation of solutions for getting the data collection system right from start and using the data for various types of data-driven analysis in maintenance planning. Two other cases at AB Volvo and Chalmers Smart Industry Lab will provide further research opportunities and possibilities to demonstrate the DAIMP results and connections to Industrie 4.0 outside the consortium.

The consortium includes major automotive companies (AB Volvo, Volvo Cars and Scania) with high competence and innovative ideas in the data analysis and maintenance areas as well as VBG Group, which is a SME currently modernizing their maintenance planning. Data system vendors (IFS and Axxos) are also included to realize project results and disseminate innovative solutions outside the consortium. Chalmers University of Technology is the project leader and will collaborate with KTH and Mälardalen Universities. All three are major Swedish universities and important institutions within the international maintenance research community. The project budget is 11.9 MSEK for three (3) years with 5.95 MSEK public funding. Suggested project start is March 1st, 2016.