Hannover Messe 2022: Achieving the goal faster with the help of AI when planning operation sequences in production

Ever shorter production life cycles and the trend towards customised products are increasing the planning effort in production. Researchers at Technische Universität Kaiserslautern (TUK) are developing an AI-supported tool that can predict the individual steps using Deep Learning in order to make it easier for companies to plan manufacturing sequences. The researchers will be presenting their tool at the Hannover Messe from 30 May to 3 June at the Rhineland-Palatinate research stand (Hall 2, Stand B40). The software is suitable for use in small and medium-sized enterprises (SMEs) - the prerequisite is, for example, that 3D CAD data of the parts to be manufactured are available.

Using the algorithm pays off especially in contract manufacturing. Customised and fast manufacturing of products or parts is an important instrument for customer loyalty in this sector.

“In this project, for example, we are working with KWS Kölle GmbH, which is active in the field of toolmaking and special production,” explains Marco Hussong, research assistant at the Institute for Manufacturing Technology and Production Systems at TUK. “Once a client contacts them, the decisive question that the planners ask themselves at the outset is what process steps and technologies are to be used and in what sequence to get from the raw part to finished product.” Thus, process planning is the link between product development and the manufacturing of a product. It determines the time, costs and quality of the manufacturing process.

Where the knowledge of experienced specialists used to determine the process, AI, in this case deep learning, can support faster achievement of the goal. On the one hand, the researchers train the algorithm with digital 3D CAD data of the parts to be manufactured. On the other hand, they also feed the algorithm implicit knowledge about production sequences from existing work plans - in other words, the company's wealth of experience. By linking all this information, the algorithm learns to predict the required manufacturing sequence. Thus, manual efforts are drastically reduced compared to existing approaches.

The aim of the project is to develop a software demonstrator that intuitively guides users through AI-supported process planning. The company does not need any special prior knowledge or IT investments for this.

At the Hannover Messe, interested companies will be able to see a presentation showing how and with which input and output variables AI-supported process planning is carried out.

The project (VorPlanML, FKZ: 01 IS 21 0 10) is funded as part of the programme „Erforschung, Entwicklung und Nutzung von Methoden der Künstlichen Intelligenz in KMU“ [Research, Development and Use of Artificial Intelligence Methods in SMEs] by the Federal Ministry of Education and Research.

Questions can be directed to:
Marco Hussong
Institute for Manufacturing Technology and Production Systems
Phone: +49 631 205 - 4305
E-mail: marco.hussong(at)mv.uni-kl.de

+++
Klaus Dosch, Department of Technology and Innovation, is organizing the presentation of the researchers of the TU Kaiserslautern at the fair. He is the contact partner for companies and, among other things, establishes contacts to science.
Contact: Klaus Dosch, Email: dosch[at]rti.uni-kl.de, Phone: +49 631 205-3001