Open Access

Der Beitrag zeigt, wie systemisches Coaching als lösungsorientiertes Beratungsverfahren in Arbeitsweltkontexten hilfreich sein kann, um Personen und Organisationen im Umgang mit Komplexität zu begleiten. In ingenieurwissenschaftlichen Kontexten eingesetzt, unterstützt Coaching (angehende) Ingenieur*innen dabei, ein ganzheitlich-systemisches Verständnis des digitalen Wandels zu entwickeln und zentrale Kompetenzen wie Reflexionsfähigkeit zu erwerben. Im ersten Teil werden Anforderungen an eine zukunftsfähige Ingenieur*innenausbildung und deren Umsetzung an der Fakultät für Anlagen, Energie- und Maschinensysteme der TH Köln sowie Arbeitsweisen und Grundannahmen systemischen Coachings vorgestellt. Die Wirksamkeit des Einsatzes von Coaching in der Lehre wird an der Fakultät begleitend erforscht. Dazu werden im zweiten Teil zunächst Herausforderungen beim Einsatz von Coaching im Hochschulkontext und mögliche Dilemmata für Coaches benannt. Im Anschluss werden die Ergebnisse zweier Studien vorgestellt, die den Einsatz von Projektcoaching und Leadership-Coaching in projektbasierten Modulen mit großen Teilnehmer*innenzahlen an der Fakultät untersuchen. Die Forschungsergebnisse stützen zum einen die Annahme, dass das hier konzipierte Coaching die Studierenden dabei begleitet, Metakompetenzen wie Reflexionsfähigkeit und Self-Awareness zu entwickeln. Zum anderen unterstreichen die Ergebnisse das Vorgehen der Fakultät, Kompetenzen nicht nur einmalig im Studium, sondern aufeinander aufbauend durchgängig zu trainieren. Der Beitrag schließt mit einem Ausblick für Praxis und Forschung. Die Konzepte sind anschlussfähig sowohl für den Einsatz in anderen Disziplinen als auch an Beratungskonzepte für Lehrende. Fazit ist, dass eine didaktische und curriculare Verankerung von Coaching Studierende dabei unterstützen kann, eine systemische Haltung zu entwickeln und sie damit auf den digitalen Wandel sowie zukünftige Führungsaufgaben vorbereitet.

EventDetectR: An efficient Event Detection System (EDS) capable of detecting unexpected water quality conditions. This approach uses multiple algorithms to model the relationship between various multivariate water quality signals. Then the residuals of the models were utilized in constructing the event detection algorithm, which provides a continuous measure of the probability of an event at every time step. The proposed framework was tested for water contamination events with industrial data from automated water quality sensors. The results showed that the framework is reliable with better performance and is highly suitable for event detection.

Benchmark experiments are required to test, compare, tune, and understand optimization algorithms. Ideally, benchmark problems closely reflect real-world problem behavior. Yet, real-world problems are not always readily available for benchmarking. For example, evaluation costs may be too high, or resources are unavailable (e.g., software or equipment). As a solution, data from previous evaluations can be used to train surrogate models which are then used for benchmarking. The goal is to generate test functions on which the performance of an algorithm is similar to that on the real-world objective function. However, predictions from data-driven models tend to be smoother than the ground-truth from which the training data is derived. This is especially problematic when the training data becomes sparse. The resulting benchmarks may not reflect the landscape features of the ground-truth, are too easy, and may lead to biased conclusions. To resolve this, we use simulation of Gaussian processes instead of estimation (or prediction). This retains the covariance properties estimated during model training. While previous research suggested a decomposition-based approach for a small-scale, discrete problem, we show that the spectral simulation method enables simulation for continuous optimization problems. In a set of experiments with an artificial ground-truth, we demonstrate that this yields more accurate benchmarks than simply predicting with the Gaussian process model.

An important class of black-box optimization problems relies on using simulations to assess the quality of a given candidate solution. Solving such problems can be computationally expensive because each simulation is very time-consuming. We present an approach to mitigate this problem by distinguishing two factors of computational cost: the number of trials and the time needed to execute the trials. Our approach tries to keep down the number of trials by using Bayesian optimization (BO) –known to be sample efficient– and reducing wall-clock times by parallel execution of trials. We compare the performance of four parallelization methods and two model-free alternatives. Each method is evaluated on all 24 objective functions of the Black-Box-Optimization- Benchmarking (BBOB) test suite in their five, ten, and 20-dimensional versions. Additionally, their performance is investigated on six test cases in robot learning. The results show that parallelized BO outperforms the state-of-the-art CMA-ES on the BBOB test functions, especially for higher dimensions. On the robot learning tasks, the differences are less clear, but the data do support parallelized BO as the ‘best guess’, winning on some cases and never losing.

Real-world problems such as computational fluid dynamics simulations and finite element analyses are computationally expensive. A standard approach to mitigating the high computational expense is Surrogate-Based Optimization (SBO). Yet, due to the high-dimensionality of many simulation problems, SBO is not directly applicable or not efficient. Reducing the dimensionality of the search space is one method to overcome this limitation. In addition to the applicability of SBO, dimensionality reduction enables easier data handling and improved data and model interpretability. Regularization is considered as one state-of-the-art technique for dimensionality reduction. We propose a hybridization approach called Regularized-Surrogate-Optimization (RSO) aimed at overcoming difficulties related to high-dimensionality. It couples standard Kriging-based SBO with regularization techniques. The employed regularization methods are based on three adaptations of the least absolute shrinkage and selection operator (LASSO). In addition, tree-based methods are analyzed as an alternative variable selection method. An extensive study is performed on a set of artificial test functions and two real-world applications: the electrostatic precipitator problem and a multilayered composite design problem. Experiments reveal that RSO requires significantly less time than standard SBO to obtain comparable results. The pros and cons of the RSO approach are discussed, and recommendations for practitioners are presented.