Every day, sensors in production plants collect huge amounts of data. However, companies seldom realise how valuable the correct evaluation of large amounts of data is. This creates ‘data graves’ whose potential remains undiscovered. For example, German manufacturer Heubach collects data from PID controllers in a central PIMS (production information management system) database. Production data is often stored in condensed form – in the case of PID controllers, with sampling rates of two seconds.
Full-fledged controller optimisation is probably not possible with such data. Nevertheless, experts from Heubach and Festo wondered whether the data could be put to good use. After all, PIMS databases have an invaluable advantage: they contain the data of all controllers from different systems, different manufacturers and from all connected production sites. Michael Pelz, automation & digitisation manager at Heubach, says: “Our goal would be a central controller monitoring system.” Based on the results obtained, controllers could then be specifically analysed and optimised, for example with optimisation software in the SCADA system used, and with experts on site.
Part of the solution uses the Festo Automation Experience (Festo AX) software. In the first step, Festo AX’s AI evaluated several months of baseline data and cleaned it where necessary. Experts from Heubach’s maintenance, process engineering (quality) and operations improvement management departments evaluated the initial results from the historical offline data.
In the second step, departments reported back regarding the variable batch processes and which sensitivity levels should be possible for the controllers, depending on their physical functions. For example, they assessed the relative importance of parameters such as temperature, flow and pressure. Subsequently, it was determined how the different error deviations should be prioritised.
An additional trend line of the anomaly scores should also help the departments to identify the deviations per batch. This should make AI evaluation algorithms and error scores adaptable to the experience of experts and conditions on site. It was also important to display results simply, with the aim of being able to use aggregated dashboards in the future. In the third step, the project should be portable (on-premises) and be able to lead to an online query including visualisation within existing systems, which facilitates improved data security.
RESULTS
“The results were already amazingly good after the first step of the AI analysis,” said Pelz. “It was very easy to see which controllers, for example, exhibited a strong fluctuation in the manipulated variable, and thus caused the actuators to wear out more quickly.”
The automation and digitisation manager concludes: “With this solution we have two outstanding advantages: firstly, it is cross-manufacturer and can be used globally on a central system, so that we can use the algorithm for all systems and controllers. Secondly, the Festo solution is so flexible on the IT side that it can be used and further developed from a pragmatic offline pilot project to an on-premises solution within our own IT systems to a cloud-based implementation.”