Research in application: Discover our projects

The Fraunhofer CCIT Technology Hub Machine Learning engages in interdisciplinary projects in diverse application areas such as production technology, quality control, process monitoring, or dialog systems and media analysis. The center cooperates with partners from business and industry as well as with universities and research centers. Discover the variety of our projects here.

Are you interested in an innovative Machine Learning solution for your company? We look forward to talking with you about individual application possibilities.

The chemical and mechanical industry is in great need of the so-called Industry 4.0 technologies in order to increase the efficiency and expand all the benefits of their processes. Particularly, the use of catalytic converters requires a predictive mode of operation, for instance in gas purification processes, with aims to minimize failures and unexpected maintenance-related downtimes due to aging.

More info

A sustainable circular economy is essential to achieve the goal of climate neutrality. To this end, the development of new innovative building materials in particular is crucial. However, this development has so far been a very laborious and lengthy process. To support and significantly accelerate this effort, experts from Fraunhofer IBP and Fraunhofer SCAI are working at the Research Center Machine Learning on new data-driven virtual materials design techniques.

More info

Linear solvers represent the numerical core of battery aging simulations and simulations in many other development applications. The different physical properties of battery cells require different solver approaches. Adapted solver strategies and parameter settings are crucial for both numerical robustness and efficient calculations. Within the project, an autonomous solver control (ASC) was developed, which performs these adaptations autonomously, based on evolutionary and surrogate learning methods. This allows the straightforward application of efficient, iterative solver procedures for different types of lithium-ion cells in battery aging simulations.

More info

Our research team has developed a test that allows accurate determination of your biological age from home. They are using Artificial Intelligence (AI) to analyze the large amount of data that is generated to investigate the underlying protein targets that change during the aging process and identify molecules that can halt or even reverse this process.

More info

More than 90% of clinical trials during drug development fail, resulting into huge economic costs for pharma companies and – indirectly – negative impact on society, because patients do not receive new medications. In addition to lack of efficacy, unwanted side effects are among the most frequent reasons for the failure of clinical studies during drug development. The aim of this project was to investigate whether modern AI-based approaches can predict potentially adverse side effects already in the preclinical phase.

More info

Noise is one of the biggest health risks for people in industrialized countries. Established methods for noise assessment are based on long-term evaluations of standard sound sources, which have hardly any relation to the real and subjectively perceived noise. Since the perception of noise is highly individual, there is a need for tools and methods to make noise situations realistically audible and experienceable. Experts for acoustics, noise control and AI from the Fraunhofer Institute IDMT and the Fraunhofer Institute LBF realized a web-based application for the simulation of noise situations (auralization) with and without reduction measures in urban living spaces.

More info

Scientists of the Research Center Machine Learning developed a custom, hybrid AI approach for an independently deployable voice assistance solution. With this solution approach, citizen services can be extended with a voice assistant, e.g., to enable filling out and submitting applications in a completely voice-based manner – for everyone, but especially beneficial for people with motoric or visual impairments.

More info

New forms of interaction with technical devices and user interfaces via gestures and speech have great potential in industry to make processes more efficient and intuitive. Voice assistants can support and simplify existing processes, such as visual inspection in quality assurance. Experts at the Research Center Machine Learning are working to combine speech recognition and gesture control into a multimodal voice assistant that can be used for defect identification and marking.

More info

Many tasks in the field of Artificial Intelligence and Machine Learning are still today, despite advanced computing power of computer systems, only solvable with immense time and computational effort. It will take a "quantum leap" to raise Artificial Intelligence and Machine Learning to a new level and make the almost unsolvable solvable. This study presents fundamental concepts and technologies of quantum computing, analyzes the current research and competence landscape, and identifies market potentials.

More info

The quality control of reflective surfaces in production pushes conventional measurement technology to its limits. Alternatives such as manual visual inspections or technically complex testing systems have disadvantages: the former are time-consuming and subjective; the latter are characterized by high costs and low flexibility. These weaknesses are addressed by our scientists in this project.

More info

Predictive maintenance plays a central role in modern industry. In the HEAD project, experts from the Research Center Machine Learning are developing interpretable AI models that predict tool wear in cutting processes from acoustic emission. The objective is to increase both the robustness of the production process and the availability of the machines – while maintaining consistently high production quality.

More info

Methods that use markers or optical features to identify components lead to problems in tracking and identification after processing. The Fraunhofer Institutes ITWM and IZFP address these weaknesses by identifying information from inside the component to extract unique features, similar to an individual fingerprint. This enables component identification even if the surface of the components is covered by paint or similar, or if the components are subjected to deformation, e.g., by quality control. This ensures an essential prerequisite for knowledge-based process-influencing decisions in production, which helps to optimize quality, productivity and costs.

More info

The handling robot presents new and sometimes sophisticated AI technologies for handling tasks by means of a simple interactive game for young and older players about sorting objects. The robot is controlled via speech recognition and is mobile, which makes it highly versatile.

More info

The scientists of the Research Center Machine Learning developed a retrofit solution for handheld tools including an intelligent sensor module that measures various parameters during work processes that are analyzed by AI algorithms to delivers process insights for worker assistance and quality assurance. The AI algorithms not only detect actions (e.g., the tightening or loosening of screws) but also the location and sequence of operations is assessed.

More info

New types of safety assessment of local rail passenger transport supported by Artificial Intelligence offer a wide range of possibilities to make processes safer. Automatic object detection enables the recognition of hazardous situations, the identification of critical conditions and the support of responsible persons in decision-making. Experts from Research Center Machine Learning combine AI-based object recognition with user-optimized presentation in an overall system that allows for the timely and accurate identification of dangerous situations in the field of public transport.

More info