Predictive maintenance: Anticipating problems before they occur

In the course of Industry 4.0 development, monitoring the condition of important components should eliminate the need to bring material handling systems to a standstill. "The trick is to optimize system availability continuously and to find the ideal moment - both for the provider and the customer - to execute the maintenance services," says Dr. Maximilian Beinhofer, Head of Cognitive Systems Development at TGW. "Condition monitoring and predictive maintenance, based on a 'digital twin', provide a good solution."

Dr. Maximilian Beinhofer, Head of Cognitive Systems Development at TGW.

Predictive maintenance uses sensors to monitor the condition of components and a software simulation to see whether a problem is coming up.

Using smart algorithms TGW take data that have already been provided by sensors and link and merge this data in an intelligent way that allows to make very precise statements about the condition or wear of components. It saves expenses because no additional sensors must be installed. To give an example: TGW's Rovolution picking robot measures the status of the vacuum of the gripping device.

If there is a pressure loss, due to the dust load of the environment, for example, this is immediately spotted and action can be taken. For older systems, there is always an option of installing additional sensors. Depending on the size of the system, the number of sensors required may range between just a few and several hundred.

For this reason, a cost-benefit analysis should be run on beforehand. The biggest challenge of predictive maintenance is to create maximum leverage with minimum effort. Another challenge is to use the networks of the system in such a way that the data required for the predictive maintenance software can be transmitted.

And the feedback loops are the third challenge. As a manufacturer, one has to develop intelligent methods so that feedback is output immediately and suitable for automated evaluation. Condition monitoring is already available for TGW's Rovolution picking robot.

At the same time, TGW is developing a specific cloud solution for data acquisition and processing. The goal is that all data - from mechatronics to IT - are to be recorded in the future. The digital twin is the outcome of this process.

One can either use the replay mode to analyse what has happened or view in real time what is happening. An additional step will allow it to look into the future and make predictions. TGW believes that within five or ten years all systems sold will provide predictive maintenance services.

This will also change the business model behind maintenance contracts.

The new tools and services offer multiple advantages for customers and these advantages will ultimately be visible in the Total Cost of Ownership (TCO).

Discover more on predictive maintenance on[1]


  1. ^ (