Using energy more efficiently and thus reducing resource consumption and costs – digitalization and artificial intelligence (AI) methods offer a wide range of options here. However, small and medium-sized enterprises are too often unable to make full use of them, because they often lack the expertise to integrate these technologies in their own operations and the barriers to entry are high. In future, they will be able to obtain tools, knowledge and a support infrastructure via a platform. This is the aim of research in the new joint project “ecoKI” led by the BIBA – Bremen Institute for Production and Logistics at the University of Bremen.
Simplify and accelerate the step from research laboratory to operational application
The path from prototype from the research lab to the market is arduous and takes a long time. The step into the operational application especially of small and medium-sized enterprises (SMEs) is still too seldom taken. The “ecoKI” research and technology platform is intended to remove hurdles here and accelerate the processes along the way. The project focuses on the transfer of findings and developments from publicly funded research.
The goal of the partners: To gather knowledge on digitization and AI methods, especially on machine learning, and make it easily and clearly accessible, to build up further knowledge, and to network experts with users in order to enable a low-threshold and rapid introduction to the benefits of the new technologies for increasing energy efficiency.
Permanently available solutions
Permanently available, expandable solutions are to be created – with the platform itself as well as through the thus generated implementation of individual projects in the companies with the goal of increased energy efficiency. In addition, the collaborative partners expect their research to lead to new questions and further insights into the needs of industry.
A central task in the ecoKI project is the development and organisation of the platform as the basis for a long-term, functioning business model. The second essential work is the development of standard building blocks for the platform. These should serve as a knowledge base for the users and can be used for new tasks. The reusable modules implemented in the platform are intended to offer companies support in developing their processes cost-effectively and efficiently through the use of AI methods. Synergies from different use cases should be able to be used.
The economic exploitation perspectives of the project are strategically oriented in the long term and are primarily based on the improved cooperation between developers and users of innovative AI technologies in operational practice.
With CRISP-DM, rigorous models, and machine learning.
For the collection, processing and use of the data, the project partners rely on the CRISP-DM method (Cross Industry Standard Process for Data Mining). This is a proven, standardized process model that helps achieve a consistent approach to developing data mining processes to identify trends and correlations. To develop the generic building blocks for the platform, the project also deals with so-called rigorous models and – in the field of artificial intelligence – with deep learning, a subfield of machine learning.
Rigorous models map a technical mechanism with exact scientific methodology. They have the advantage of being able to understand simulated processes more precisely with their help. Machine learning, as opposed to formalized expert knowledge, deals with the automated creation of predictive models based on data alone. Especially due to the development of Deep Learning approaches and their successful applications, the use of machine learning has been experiencing rapid growth for years.
Key data on the “ecoKI” joint project
In the workshop “Increasing Energy Efficiency in Production through Digitization and AI” initiated by the BIBA – Bremen Institute for Production and Logistics with representatives of the Federal Ministry for Economic Affairs and Energy (BMWi) and the Project Management Organisation Jülich (PtJ), among others, the idea for the realisation of a research and technology platform and network structure oriented towards the issues of sustainable energy efficiency emerged. It is intended to make innovative R&D results more easily accessible, in particular to SMEs, and to promote their application.
Partners of the resulting research project “ecoKI” are, besides the BIBA as coordinator, the German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern, the Institute for Neuroinformatics (INI) of the Ruhr-University Bochum and the professorship Process Control Engineering/Workgroup Systems Process Engineering of the Technical University Dresden. The four-year project ends on 30.11.2024, is funded by the BMWi within the framework of the 7th Energy Research Programme of the Federal Government and is supervised by the Project Management Organisation Jülich (PtJ).