"GenISys" project Researchers Introduce Generative AI to Plant Construction

Related Vendors

Bergische Universität

dataTec AG

Taiwan Machine Tool & Accessory Builders' Association (TMBA)

SIMTOS (Seoul International Machine Tool Show)

In the "GenISys" project, researchers from the University of Wuppertal, in collaboration with two industry partners, are developing generative AI models aimed at revolutionizing the construction of filling plants. The initiative focuses on making these plants smarter and more resource-efficient. The overarching goal is to enhance the adoption of artificial intelligence across key economic sectors, thereby driving innovation and efficiency.

Generative AI models are designed to generate new content from existing data. In many enterprise and user applications, the models are already integrated and demonstrate impressive capabilities, such as generating human-like texts. "However, in the industrial production area, the known potential and capability of generative AI approaches remain almost unused. This is partly because AI methods have not yet been adapted for areas of application with very specific requirements," explains Dr. Hasan Tercan, scientific director of the research area "Industrial Deep Learning" at the Chair for Technologies and Management of Digital Transformation at Bergische Universität.

Complex, costly, lengthy

Such a special area of application is the design and construction of industrial filling plants, for example for powdery and granular material like cement, which needs to be bagged in mass production. The elaborate, partly manual configuration process of these plants is characterized by laboratory tests to determine the properties of the material to be filled, as well as the development and multi-stage testing of a plant prototype. When new operational requirements and changing material properties occur, further necessary adaptation steps follow in the operation of the plant. "This labor-intensive character of the design process in conjunction with the recurring need to redefine parameters due to material changes emphasizes the need for a more innovative and adaptable approach to plant configuration," says Tercan.

Reduce test cycles

The scientist and his team are working in the now launched research project "GenISys" together with the software company Snap and the plant manufacturer Haver & Boecker to reduce the number of test cycles using digital technologies and the use of generative AI methods. In doing so, they not only want to push forward the implementation of innovative ideas and services in the industry—less production effort and less material use also protect the environment.

The significance of the innovation, according to the project partners, goes far beyond its immediate application in machinery and plant construction. Since the AI development and training process is carefully designed for adaptability and expandability, the application framework can later—for example in the form of a license model for an AI module kit—be seamlessly reused in different contexts, enabling integration into other industries.

Goal: Development of an AI-based, easy-to-use and interactive software application

The vision of the project is to develop an AI-based, easy-to-use and interactive software application for plant construction companies and plant operators. The starting point for "GenISys" is data and information about a customer order, on the basis of which the software to be developed should configure a new filling plant. The data consists of the material properties of the product to be filled—such as grain size and density - which were determined through laboratory investigations, and existing microscopic images of the product, which have so far been mainly produced for documentation and verification purposes. In addition, historical data from thousands of plant configurations and product properties are available for training the AI models integrated in the software.

To implement the software in a practical manner, the architecture of the AI models, training methods, modularization strategies for integration into existing business processes and automation strategies for their continuous optimization as well as concepts for integrating human feedback need to be adapted and partially redeveloped.

The project "GenISys—Intelligent system for resource-conserving plant configuration with generative AI technology" is funded as part of the innovation competition NEXT.IN.NRW by the Ministry of Economics, Industry, Climate Protection and Energy of the state of North Rhine-Westphalia and the European Union with funds from the European Regional Development Fund (ERDF program NRW 2021-2027).