AI is often said to open up limitless opportunities. In order to make meaningful use of AI, a realistic picture of its possibilities and limits is extremely important. A few years ago, WDS started to look for modern solutions for the confectionery industry with its own digitisation department. First ideas were developed with easily accessible tools such as ChatGPT or Microsoft Copilot.

However, Large Language models like ChatGPT are only one very general model family among thousands of other AI models.

Working together with the Fraunhofer Institute, a theoretical basis and in-company know-how was built up at WDS to begin with. WDS.gpt was developed – a tool that interacts with the WDS knowledge database and provides immediate answers to all questions during operation. Then further sources of knowledge, such as assembly reports, were evaluated intelligently and supplied in a structured way to the WDS.gpt.

The WDS.gpt for internal use makes it possible to ask questions in natural language, making it very easy to operate. The system determines the information available in the saved database and puts it together clearly in a very short time. In addition, the sources of information are indicated, so that the answers can be checked and reproduced.

In future, the knowledge gained shall not only be able to be used internally by WDS but also by their customers. Research is currently being done on the possibilities of providing knowledge specifically, meaningfully and securely.

A confectionery machine produces a large amount of data. Using a smart measuring mould such as SmartMould, process data in the mould flow can be recorded continually and evaluated using statistics methods or simple limit value analyses. However, it is still not currently possible to make efficient use of the complete data.

The quantity of data can be processed almost in real time by AI and can be linked with historic data in order to guarantee automated and continual process monitoring. Error patterns or anomalies can be recognised in good time and can often be optimised before they lead to a real problem. An AI application is thus designed to support trained personnel in making fast and goal oriented decisions.

Alongside the many conceivable possibilities, some data is less suitable for the use of AI:
• Sensitive data
• Moral decisions
• Ecological aspects
• Certain safety requirements
Risks should always be considered carefully in such cases.

An assistance chat like WDS.gpt can search for contents in many documents and sources at the same time. In future, this work would be done by a depositing assistant, which gives clear answers to questions about errors or work instructions.

AI-based assistants reliably carry out tasks such as daily OEE reports or reports in the event of deviations and generate clear dashboards, since they can understand and create source code.