Deutsch (Germany) 
Polski (PL) 
• Artificial intelligence – a meta topic for Arburg and entire mechanical engineering industry
• High-profile experts discuss trends and specific potential applications of AI
• Group work on the topics of AutoML and TabPFN
Arburg has always been something of a trendsetter in the industry and the topic of artificial intelligence (AI) is no exception. On 26 and 27 October 2023, 33 experts came together for a two-day event at company headquarters in Lossburg in the north of the Black Forest. As part of the "AI in the forest" event, they discussed how automated machine learning (AutoML) or neural networks such as TabPFN can be used to make a data forecast in the form of a spreadsheet in industrial and academic research as well as in the industrial environment and can make day-to-day life in injection moulding easier.
The participants had come to the prestigious expert event by invitation of Werner Faulhaber, Vice President Research & Development at Arburg.
High-ranking scientists discuss trending AI topics
The thoroughly committed AI group, which meets for a regular industrial AI meeting at the initiative of the Industrial AI Podcast and Hannover Messe, was able to persuade two more luminaries from Europe in the form of Dr. Frank Hutter from the Machine Learning Lab at the Albert-Ludwig University of Freiburg and Dr. Marco Huber from the Fraunhofer IPA to hold a presentation and participate in the discussion. Arburg was represented at the event by Werner Faulhaber and Stefan Lamp, Data Analytics Development team manager.
Group work, discussion and a tour of the company
Group work on the topics of AutoML and TabPFN was carried out in a whole group session as well as in several workshops spread over the two days. As well as the inputs from the two professors, the programme included a feedback panel with information from Dr. Denis Cavallucci from the National Institute for Applied Sciences INSA in Strasbourg. Arburg made itself and its infrastructure available to the participants in the accustomed professional manner.
Following the theory parts, there was a tour of the company. One group was led by Werner Faulhaber, who informed participants about the current use of AI in production and in Arburg products. The second group was led by Dr. Thomas Walther, Director Applications Development, who responded to the many questions about company infrastructure and its increasingly autonomous production processes.
Use of AI at Arburg
The Lossburg company is researching how to combine its own smart Gestica control system with artificial intelligence and with self-learning machines in order to make the injection moulding process more intelligent and thereby open up new work options for processors of plastic. "The goal is for the control system to master not just the process, but also the three areas of machine, material and mould," explains Werner Faulhaber. Besides the control system, customers will in future be able to use the host computer system ALS and the customer portal arburgXworld in order to establish a common basis for smarter, self-optimising injection-moulding processes. In the medium term, machines will optimise themselves and also be able to learn for themselves. "'Setters and operators will be assisted in their work by AI-based assistance systems, as well as having their workload reduced. As a result, we will see more stable processes, less scrap and increased quality of workpieces," reports Stefan Lamp.
Event led to immeasurable new findings
At "AI in the forest", participants were also able to acquire an overview of new technologies such as AutoML and TabPFN. Some of the discussions were conducted at a very profound technical level and based on concrete application examples. This led to a wide range of solution options. There was, however, also a contentious discussion of the systemic limitations currently still in place: What does the EU AI Act mean for industry? How can AI and the development process be standardised? How can we build reliable AI? These ongoing questions led to exciting discussions in the workshops. This in particular resulted in positive closing feedback from the participants.
