Data science

F - 7 AI based design assistant für early stage bridge design

The thesis can be of different scope: (bachelor thesis), project thesis, diploma thesis or a combination. Detailing and structuring of the task will be done before the start of the project with the student depending on the individual interests. The work is integrated into the institute's internal research on the topic of "parametrization" and "artificial intelligence" in bridge design.

Generally, Bridge design is a creative process with multiple requirements and constraints. The design process is often manual and without (partially) automated support processes. Accordingly, it can be optimized and this is particularly important in times of high demand for new construc-tion and growing sustainability requirements. Bridge design takes place within given, multiple boundary conditions. In the "preliminary design" phase, a preferred variant must be found, taking into account important boundary conditions such as topography and the road profile. Methods of Artificial Intelligence (AI) and Machine Learning (ML) enable nowadays design assistance for general design methods and also for bridge design. Data from built bridges can be taken into account and new design proposals can be derived from them. However, built bridges may not always be optimized or the reasons for the design determination may be manifold and therefore not always explainable.

The aim of this work is to develop a digital design assistant for the preliminary design of a frame bridge using AI methods that suggests possible bridge variants for given boundary conditions.

The thesis is to be worked on in the following steps:

• Research and categorisation of AI methods for the design process
• Development of a parametric FEM optimisation model
• (Software: Grasshopper+Karamba+ e.g. Galapogos)
• Development of a data set of synthetic and real bridge designs of superstructures
• Analysing the synthetic database of optimised bridges for existing bridges (software: OrangeDataScience). For this purpose, a cluster analysis is to detect statical and constructive correlations. A correlation analysis should explain the correlations with the target variables for certain design parameters in more detail.

• Training of existing regression algorithms and evaluation of their reliability

Contact person:
Jakob Grave, M.Sc.
Phone: +49 30 2207-7774
E-Mail:

F - 6 Literature research on ageing phenomena in structural health monitoring systems

Metrological monitoring for infrastructure structures will play an increasingly important role in the future, as it enables continuous monitoring of the structure and the provision of information for digitalisation in the construction industry. Structures are nowadays monitored with so-called structural health monitoring systems. However, it is problematic that not only the structure but also the measuring system itself is subject to an ageing process, which reduces the measuring accuracy and thus the reliability of such systems. The difficulty lies in the fact that the measuring systems do not fail completely, but provide seemingly plausible, but faulty data.

Within the scope of a project or diploma thesis, a literature research on existing national and international research findings on ageing phenomena in measurement systems is to be carried out. Based on this, an experimental programme should be developed that takes into account different environmental influences such as temperature or humidity.

Contact person:
Jan-Hauke Bartels, M. Sc.
Phone: +49 351 463-36399
E-Mail:

F - 5 Fiber-optical sensor make quasi-continuous strain measurements with possible

Therefore, the interest in deployment of this measurement technique grows for structural health monitoring, especially for crack width monitoring. The estimation of integration limits for the crack width calculation based on dFOS data is essential for the correct calculation. Initial crack formation with isolated, solitary cracks and final crack state with seemlessly neighboring crack differ fundamentally. For the latter, approaches with good results already exist in a Python software framework. However, determination of the integration limits for solitary cracks is yet to be developed.

Goal of the thesis (Projekt- and/or Diplomarbeit/master's thesis) is the development of stable crack width integration limit determination approaches. The approaches for initial crack formation and final crack state shall be unified to work for both cases and implemented into the Python framework.

The developed algorithms should be validated by means of experiments on reinforced concrete beams. Details of the task will be refined prior and while working on the project.
Interest/experience in software development/programming is advantageous.

Contact person:
Dipl.-Ing. Bertram Richter
Phone: +49 351 463-32822
E-mail:

F - 4 Automated analysis of fibre optical sensor strain measurement data

Fibre optical sensors make it possible – in contrast to many conventional measurement methods – to measure continuous strain along the structural members with a high spatial resolution up to 0.6 mm. Therefore, the importance of of fibre optical sensor usage for structural health monitoring is rising. Important is an efficient handling of the enormous data as result of those measurements. In the future, the widths of cracks is envisioned to be calculated and assessed in real time. The implementation of functionalities into a Python software framework is scope of a thesis (Projekt- and/or Diplomarbeit/master's thesis). Possible topics are (combination possible):

• Development of real time capabilities for the analysis framework

• Influence of cyclic loading

• Influence of creep and shrinking on the crack width

• Temperature compensation

• Influence of tension stiffening on the crack width

• Analysis of fibre slip in the sensors

• Deformation analysis of specimen (1D, 2D, 3D) based on strain measurements

The developed algorithms should be validated by means of experiments on reinforced concrete beams. Details of the task will be refined prior and while working on the project. Interest/experience in software development/programming is advantageous.

Contact person:
Dipl.-Ing. Bertram Richter
Phone: +49 351 463-32822
E-Mail:

F - 3 Literature research on the digital inventory methods of large infrastructure structures (applies to project work)

In the scope of the Priority Program 2388 "Hundred plus", the Nibelungen Bridge Worms has been selected as a validation structure. Accordingly, a monitoring system will be deployed on this bridge. In addition, a digital twin is to be developed.

As the central object of a digital twin, an accurate 3D model of the structure is very important. To create the 3D model of an existing structure, there are many optical technologies such as laser scanning, infrared scanning, and digital image correlation etc. In this project work, the state of the art in this field will be investigated and summarized. In addition, the different methods will be compared regarding their advantages and disadvantages, their time consumption, and their economic expenditure.

For more information on the 100+ priority program, please follow this link:
https://tu-dresden.de/bu/bauingenieurwesen/imb/forschung/spp-2388?set_language=en

Contact person:
Dr.-Ing. Chongjie Kang
Phone: +49 351 463-37305
E-mail:

F - 2 Description of ageing processes in strain gauges in structural monitoring systems

In the course of digitalisation in the construction industry, the digital twin is taking on an increasingly important role. This virtual image of the real structure enables, in addition to dimensioning, above all monitoring during the use phase. Since this phase takes up the largest part of the building's life, information about the condition of the building must be collected continuously. Monitoring systems that guarantee a lifelong link between the real and virtual systems are suitable for this purpose. Over time, the real supporting structure will change (e.g. due to ageing). This change must be reliably recorded by monitoring and transferred to the digital twin. However, monitoring systems are also subject to an ageing process. The quality of the monitoring system deteriorates significantly over the lifetime of the real structure in terms of data quantity and quality. One difficulty is that components of the measuring system do not immediately fail completely, but the system still delivers seemingly plausible, but erroneous data.

In the course of the student work, it is to be shown how the functioning of monitoring system components (strain gauges, cables, measuring amplifiers, A/D converters) can be physically described. Which measuring system components are subject to a notable ageing process? What are useful methods for describing these ageing processes? Which signal analyses are suitable for measurement data evaluation? In order to answer these questions, different signal analysis procedures for ageing-related changes in the measured values of strain gauges are to be investigated.

Depending on the progress of the project and the interests of the students, the following subtasks can be worked on:

• Evaluation of time-independent laboratory tests with different influencing parameters such as cable length and temperature as well as the physical description of the measurement system components.
• Evaluation of time-dependent, mechanically unloaded laboratory tests with different influencing parameters such as time, cable length, humidity, etc.

Evaluation of time-dependent, mechanically loaded laboratory tests with different influencing parameters such as time, cable length, force, air humidity etc.

Contact person:
Jan-Hauke Bartels, M. Sc.
Phone: +49 351 463-36399
E-Mail:

F - 1 Damage assessment of cyclically loaded concrete structures with ultrasonic measurements

Concrete structures under a given load do not fail because they abruptly change from a "normal" state to a fracture state, but because the degradation process progresses with increasing load until material failure occurs. When subjected to mechanical loads, stresses first concentrate around material defects or interfaces at the microscale, destroying bonds between individual molecules. With increasing mechanical load, the microcracks then grow and unite, leading to the formation of macrocracks. During this process, the lattice structure of the material, which serves as a propagation medium for the stress waves of an ultrasonic pulse, is progressively changed and in this way the damage can be detected.

The objective of this thesis is to relate ultrasonic measurements of degradation evolution from concrete specimens and beams subjected to cyclic loading to hypotheses of damage accumulation. From these correlations and using concepts of robustness and redundancy, safety factors will be determined and the remaining useful life will be evaluated.

Contact person:
Raúl Enrique Beltrán Gutiérrez, M. Sc.
Phone: +49 351 463-33675
E-Mail: