Data-Driven Collaborative Decision Making in Complex Industrial Systems

Category: News

Pioneering work in Causal AI for supply chain management

Conventional AI models of supply chain management provide interesting recommendations, but often no real understanding and unreliable predictions, which reduces trust in their advice. In a research project with BMW, a team around Prof. Dr.-Ing. Hendro Wicaksono, Professor of Industrial Engineering at Constructor University, PhD-Student Ishansh Gupta and Master-Student Adriana Martinez has developed a pioneering method that closes existing gaps by taking a causal approach.

In addition to data relating to the reliability of suppliers, for example, human “tribal knowledge” from the company is also incorporated into the model. This makes its recommendations more accurate, trustworthy and realizable.

In a survey at BMW, all the experts questioned favored this causal AI approach over conventional machine learning models.  “The most critical and strategic business decisions are causal questions,” says Prof Wicaksono. “Causal models try to capture the process of data generation and not just fit curves to the data. They are not a black box but can answer the question of ‘why’.”

Digital Trial: How to plan transport infrastructures more efficiently

Reduce costs, increase productivity and simplify processes: Researchers at Constructor University in Bremen are developing a digital platform for managing transport infrastructures in a more efficient way. Professor Hendro Wicaksono’s project is funded by the German Federal Ministry of Digital Affairs and Transport (BMDV).

The platform that Wicaksono and his team are setting up works with so-called “digital twins”: with digital asset counterparts of real projects, systems or infrastructures. They contain all the relevant technical information on which they are based. The digital assets are fed with real-time data and cover the entire life cycle of a form of infrastructure. With the help of these digitalization measures in the transport sector, resources can be used more efficiently and thus the management of infrastructures can be optimized.

“With such a tool, workflows and decisions can be tested and optimized in the digital world before they are transferred to the real world,” says Wicaksono, Professor of Industrial Engineering, describing one of the benefits. Another is that by integrating various data, plant operators can determine at an early stage when, for example, maintenance or servicing of a bridge is necessary.

The portal is intended to be used by the various companies involved in the construction or maintenance of an infrastructure. Small and medium-sized enterprises in particular will be involved, thus promoting cooperation between them. In the project itself, Wicaksono is the scientific coordinator and responsible for semantic data management and the development of predictive models, among other things. Here, machine learning and probability calculation are used to predict outcomes. Wicaksono designed a specific form of artificial intelligence, “Explainable AI”, which makes decisions of a machine learning model transparent and comprehensible. In addition to Constructor University, two companies – Vectorsoft AG and Concedra – are also involved in the project.

Intelligent use of green electricity in industry

The use of green electricity is a common practice for private households, but not for energy intensive industrial companies. How can they too succeed in consuming more electricity from renewable sources in the future? This is the subject of a project initiated by Hendro Wicaksono, Professor of Industrial Engineering at Jacobs University, together with SWT, the public utility company in Trier, and seven other scientific and economic partners. The three-year project is being funded by the German Federal Ministry of Economics and Energy with around 2 million euros. Around a quarter will go to Jacobs University.

A group of researchers from Jacobs University Bremen, the Karlsruhe Institute of Technology (KIT) and the Research Center for Information Technology (FZI) is scientifically supporting the project. “It presents us with interdisciplinary research challenges in the fields of energy and data management, artificial intelligence and production optimization,” explained Wicaksono, the scientific leader of the project.

The research project includes the integration and processing of data from heterogeneous sources, such as power plant, sensor, weather and production data. “Therefore, we are developing a concept of data management and data integration using semantic technologies and a service-oriented architecture,” Wicaksono described the task. Semantic technologies serve as a key technology in the use of “big data”. They help standardize different types of data, to combine and to merge them.

The public utility company SWT operates more than 50 green power plants and is coordinating the project. “We provide the market with around 170 million kilowatt hours of green electricity every year,” said Rudolf Schöller from SWT. Green electricity production depends on when the sun shines or when the wind blows, therefore it is subject to strong fluctuations. “Nevertheless, manufacturing companies need a predictable and reliable energy supply,” stressed Thorsten Zoerner, Executive Director of the green power supplier STROMDAO, which is also involved in the project.

Two small and medium-sized companies with energy-intensive production processes are also involved in the project – Kautenburger, a special machine manufacturer from Merzig, and MaTec Gummiwerk, a manufacturer of molded rubber parts for technology. “We are confident that we will succeed in producing more efficiently and sustainably in the future,” said André Henning, Managing Director of MaTec Gummiwerk. With devolo and Pumacy Technologies, two technology companies contribute to the development of technical solutions.