Data-based tool availability for series production through predictive maintenance

Key Info

Basic Information

Duration:
01.09.2017 to 31.12.2019
Organizational Unit:
Chair of Prodcution Engineering, Business Development
Funding:
Federal Ministry of Education and Research BMBF
Status:
Closed

Research partner

    • BMW AG
    • Continental Automotive GmbH
    • Krämer+Grebe GmbH & Co. KG Modellbau
    • Peter Sauer & Sohn KG
    • i2solutions GmbH
 

The toolmaking manufactures tools for the serial production of plastic or metal parts in single and small series. The availability of the manufactured tools is of outstanding importance for industrial series production and significantly determines their productivity. Currently, tool failures are unpredictable and cause sudden production failures and thus high costs. There is currently no solution for predictive and proactive maintenance to avoid tool failures in a timely and efficient manner.

The aim of the research project "WerkPriMa", funded by the Federal Ministry of Education and Research (BMBF), is to design and develop a data-based maintenance and service system to increase tool availability for series production by using production data. This also results in an increase of the availability of production facilities.

Predictive and proactive maintenance should enable the tool shop to analyse the tools used in series production for wear and potential damage in real time by recording process data. In this way, maintenance can be carried out as required and as a preventive measure. Possible problems in the process and on the tool can also be discovered even before they lead to an unplanned failure of the tool and thus of the production plant.

The steps of data generation, data acquisition, data processing and data analysis over the entire tool life cycle are decisive for the development of the approach. In series production, relevant process data must be recorded by appropriate sensor systems on the tool and on the production line. The recorded data should then be sent to a cloud in real time. By analyzing the data on the basis of cause-effect relationships, predictions can be made about the future behavior of the tool. In this way, wear and tear and an optimal maintenance time can be calculated, suggestions for the correction of production process parameters can be derived and a failure can be announced in advance.