IMP – Intelligent Maintance Planner & Inspection Knowledge Based Maintenance Managment Systems

Intelligent Maintenance saves Costs. Efficient planning and running of industrial maintenance saves costs and conserves resources. The required information normally already exists. It just needs to be used.

Short Description

Intelligent maintenance cycles and error-free maintenance performance are increasingly becoming the key to commercial success. Many machines and equipment are however still subject to set maintenance intervals. They are therefore rarely serviced at the optimum time. Important information is often absent too.

  • How should which component be changed?
  • Which resources are required?
  • Which experiences were already made?

The result: higher costs. In a joint project COPA-DATA, an HMI/SCADA specialist, the Salzburg University of Applied Sciences and the research company PROFACTOR developed a self-learning tool for intelligent planning and maintenance of equipment and machines. It collects information from various sources, interprets them and triggers the necessary steps. Each new service procedure increases empirical values and makes predictions more precise.

5 clear steps for every maintenance process

  1. Identifying: Maintenance demand is detected by the system. Initially on the basis of specifications, then increasingly via condition monitoring by means of analysis of machine and operating data as well as from feedback from previous maintenance tasks.
  2. Planning tasks: The tool creates specific maintenance instructions and defines the optimal timing as well as the required resources. The plans include target times, which increase in accuracy with each maintenance task.
  3. Time planning and dispatch: Using its database and the linked shift schedules the tool chooses the best qualified employee to carry out the task and informs them automatically. Production and maintenance tasks for time control are considered and optimized together.
  4. Guided performance: During operation the technician is given detailed information per augmented reality. The component to be replaced as well as its position in the machine is displayed and technical instructions are incorporated. In the case of deviations, feedback is given to the planning component.
  5. Learning: Finally, the maintenance task is qualitatively assessed. Newly gathered data and experience is adopted and used as a data basis for the next cycle.

Companies can thereby optimize running times of their machines, plan their maintenance cycles more precisely and thereby make optimal use of resources.

Project Partners

  • Ing. Punzenberger COPA-DATA GmbH
  • Fh Salzburg, Studiengang Informationstechnik und Informationsmanagement

Contact Address

Mag.(FH) Reinhard Mayr