AI in practice

As early as 25 years ago, we were involved with AI in a funded project. Here, we will briefly look at how and in which products we are already using AI today and why our systems are AI-enabled. The first product was developed by our subsidiaryfirma QST and launched under the name MQFuzzy. The name was derived from the Fuzzy Pattern Classification Technology used then as now. MQFuzzy later became PQS weld, which is still used today for unsurpassed quality inspection in welding. In its successor, XPQS, QST has incorporated new AI technologies to further improve quality inspection and make it easier to use.

Resistance welding has never been so trivial that you could do without adaptive control and monitoring. That’s why we use AI-based systems in the IQR controller and the associated Q-Inspector. We rely even more heavily on the power of data in the new IQf controller and the IQ-Inspector. Here, the AI filters out those data sets, some of which number in the thousands, that are most suitable for the controller setup. In this way, we achieve optimum process stability with minimal setup effort at the same time.
We offer IQR and IQf together with the respective inspectors in the IQflex package.

However, AI goes beyond the limited use for just one process control. The potential of AI can only be fully exploited if all processes and products in networked environments are AI-enabled. To this end, suitable interfaces must be offered on the one hand, and on the other, information communicated via the interfaces must be processed internally and process flows must be beeinfluenced.
We have naturally integrated the most important interfaces in the Industrie 4.0 environment, OPC UA and MQTT, into our portfolio. AI has therefore been part of our products for a long time.

However, it is important for us to emphasize that AI is an important technology of the future, but by no means the only one. There are many other technical possibilities to further improve the welding process. The experience of the setters and operators will also continue to play a supporting and prominent role. All the hype currently surrounding AI is unfortunately all too often misused for advertising purposes and should therefore be taken with a grain of salt.