Kevin Cremanns

PI Probaligence GmbH

Surrogate models based on machine learning methods have become an important part of modern engineering to replace costly computer simulations. The data used for creating a surrogate model are essential for the model accuracy and often restricted due to cost and time constraints. Adaptive sampling strategies have been shown to reduce the number of s...

Background Running is a very popular sport among both recreational and competitive athletes. However, participating in running is associated with a comparably high risk of sustaining an exercise-related injury. Due to the often multifactorial and individual reasons for running injuries, a shift in thinking is required to account for the dynamic pro...

Chemical engineering in materials science covers tasks like the synthesis of materials, formulation of raw materials to semifinished products, and the final application of these materials. Research and development in these fields requires knowledge of the property-structure relationship of the chemical compounds and physical parameters of the mater...

The following thesis deals with the development of new probabilistic machine learning models with a focus on efficiency, flexibility, applicability, scalability and high prediction accuracy. Therefore, learning tasks from the areas of regression, classification, image classification, time series as well as the representation of spatial and / or tem...

The use of artificial intelligence is currently finding its way into various industries and specialist disciplines. With the help of machine learning (ML), the experimental design, formulation, and testing of chemicals can be made significantly more efficient in both time and resource efficiency. One possible application is to create a desired colo...

FARBE UND LACK, Ausgabe 11/2019, http://www.farbeundlack.de Artikel über die Anwendung des maschinellen Lernens zur Lackformulierung, sowie effizienter Planung notwendiger Experimente auf Basis adaptiver Verfahren. Ein weiterer Aspekt stellt die Farberkennung anhand von Bildern dar.

Machine learning helps to develop new materials by implementation of appropriate algorithms and tools of theoretical chemistry. This results in huge saving of time to synthesize the new materials. The integration of new light sources such as high‐power LEDs and semiconductor lasers with line‐shaped focus emitting in the NIR between 800–1000 nm open...

Cyanines covering the absorption in the near infrared (NIR) are attractive for distinct applications. They can interact either with lasers exhibiting line‐shaped focus emitting at both 808 nm and 980 nm or bright high intensity NIR‐LEDs with 805 nm emission, respectively. This has and is drawing attention to Industry 4.0 applications. The major dea...

This work presents a robust multi-objective optimization of a labyrinth seal used in power plants steam turbines. The conflicting objectives of this optimization are to minimize the mass flow and to minimize the total enthalpy increase in order to increase the performance and to reduce the temperature, which results in elevated component utilizatio...

Renewable energies are increasingly contributing to the overall volume of the electricity grid and demand besides high efficiency , greater flexibility of the conventional fossil power plants. To optimize these objectives, extensive CFD calculations are required in most cases. For example, transient CFD calculations are only rarely combined with an...

The correlation length-scale next to the noise variance are the most used hyperparameters for the Gaussian processes. Typically, stationary covariance functions are used, which are only dependent on the distances between input points and thus invariant to the translations in the input space. The optimization of the hyperparameters is commonly done...

During the bid phase for turbine-generator retrofits the rotor dynamic design of the complete rotor train needs to be assessed. This becomes particularly challenging for turbine-generators supplied by other original equipment manufacturers where typically data such as e.g. rotor cross-sections, bearing and pedestal properties and rotor train alignm...

In this study a strategy for a 3D optimisation of the exhaust of a low pressure (LP) steam turbine is presented. The flow domain utilized consists of both the last stage and the exhaust diffuser. The optimisation is done with the help of a hybrid surrogate model for the diffuser flow. In the first part of the paper a numerical model and its validation...

The demand for energy is increasingly covered through renewable energy sources. As a consequence conventional power plants need to respond to power fluctuations in the grid much more than in the past. Additional, high loads for the steam turbines components are expected due to this new kind of energy management. Changes in steam temperature caused...

The demand for energy is increasingly covered through renewable energy sources. As a consequence, conventional power plants need to respond to power fluctuations in the grid much more frequently than in the past. Additionally, steam turbine components are expected to deal with high loads due to this new kind of energy management. Changes in steam t...

Computational simulations or experiments in engineering applications are often time and resource consuming. This is especially so when performing optimization, robustness or reliability analyses, because they need hundreds or even thousands of design evaluations. A common solution for this are surrogate models, which are mathematical approximations...

The present paper shows an approach of a multicriteria optimization and robustness evaluation of a radial compressor impeller. The objective of the optimization is to improve the fluidic and mechanical properties of a radial compressor impeller and verify its robustness. Therefore is used the software ANSYS, optiSLang and an Excel-Tool of KSPG. The...

In order to meet the requirements of rising energy demand, one goal in the design process of modern steam turbines is to achieve high efficiencies. A major gain in efficiency is expected from the optimization of the last stage and the subsequent diffuser of a low pressure turbine (LP). The aim of such optimization is to minimize the losses due to s...

A large gain in efficiency is expected from the optimization of the last stage and the following diffuser of a low pressure turbine (LP) by minimizing losses due to separations as well as inefficient blade or diffuser designs.