Increase of maintenance quality through machine-specific information using the example of the paper processing industry

Theme Industry 4.0
Project title Increase of maintenance quality through machine-specific information using the example of the paper processing industry (Digitale Maschinenakte)
Project duration 01.05.2008 – 30.06.2010
The aim of the project was to increase the availability of machines in the printing and paper processing industry by developing maintenance-relevant methods. For this purpose, manufacturers, operators and service providers need extensive maintenance-relevant information e.g. in terms of the current machine status, the expected fault conditions and constructive weak points. Therefore existing static data as well as current, dynamic machine data from existing data sources is used.

Publications about the project

Production downtimes and maintenance costs affect the choice of an economic maintenance strategy. Predictive maintenance of machines promises a solution for both interests, when machine conditions can be predicted. The digital machine file supports this task by a combination of data exchange and artificial intelligence.

condition monitoring, artificial intelligence

In the project "Increase of maintenance quality through machine-specific information on the example of paper and print finishing" researchers developed methods for an improved maintenance quality by using a predictive strategy. The developed methods combine the exchange of data related to the maintenance with analysis of this data with the help of artificial intelligence. This ensures that the companies that are involved in the lifecycle of a machine gain additional information, for example about the current degree of wear of a unit.

maintenance, data mining

Condition-based maintenance of production equipment offers a better trade-off between availability and maintenance costs than other maintenance strategies. A novel approach for determining and predicting the plant condition is presented. The approach applies methods of artificial intelligence to a distributed database covering the entire life cycle of the equipment. The approach simplifies the introduction of condition-based maintenance by means of machine learning and is especially suited for equipment with unknown fault behaviour.

condition-based maintenance, condition forecast, artificial intelligence, distributed data managemen

Sponsor

This pre-competitive project was funded by the Federal Ministry for Economic Affairs and Climate Action (BMWK) with IGF funds.

Your contact person

Dr.-Ing.

Benjamin Küster

Manager production automation