Lab

Computing in Engineering

About the lab

The Chair of Computing in Engineering researches new scientific foundations for the systematic generalization of planning, calculation and simulation methods in civil engineering on the basis of innovative information and communication technology. The main focus is on the control of complex model interactions, the development of emergent and adaptive software concepts, holistic planning and simulation systems, and the formalization of expert and empirical knowledge.

Featured projects (5)

Project
The main idea of the research project is the development of an open platform for the provision of certified applications, services and catalogues in order to be able to build up integrated project-specific digital value chains for construction projects. Open and web-based API ensure that individual components can be integrated into existing systems or cloud solutions from different manufacturers.
Project
Deterministic as well as probabilistic methods are implemented for the system identification in mechanised tunnelling. In particular, different probabilistic approaches as sensitivity analysis, reliability analysis, optimal experimental design and etc. are tested on different probabilistic scenarios describing the characteristic process in tunnel excavation. The involved spatial and temporal uncertainties in the soil properties are quantified using both random variable and random field concepts. In addition, various metamodelling techniques are utilised to substitute the original FE model which is constructed based on Hardening soil constitutive model. http://sfb837.sd.rub.de/en/Projektbereiche/Projektbereich_C/Teilprojekt_C2.html http://sfb837.sd.rub.de/
Project
Goal: Automate construction payment using BIM and smart contracts. Homepage: https://bimcontracts.com/
Project
The main goal of the research project is on using AI and cloud technologies for the construction industry as key technologies in the retrodigitization of existing buildings. Information on buildings and infrastructure structures, e.g. 2D plans, images, point clouds or text documents, is to be evaluated by means of AI processes, structural and technical construction elements are generated and consistently and transparently fed into a BIM-based as-built model. Similarly, the updating of an existing as-built model is to be automated. The data and AI services will be provided in a decentralized manner using open standards and existing BIM systems based on GAIA-X. An ecosystem is created which forms a fundamental basis for BIM applications.

Featured research (12)

The majority of innovative approaches in the realm of the retrospective generation of building information models for existing structures deal with geometry extraction from point clouds or engineering drawings. However, many building-specific or object-specific attributes for the enrichment of building models cannot be inferred from these geometric and visual data sources, and thus their acquisition requires the analysis of textual building documentation. One type of such documents are structural bridge records, which include specifications regarding used material, location, structural health, modifications, and administrative data. The documents are semi-structured and hardly allow a robust information extraction based on traditional programming, since the implementation of such an approach would result in a complex nesting of conditional clauses, which is not guaranteed to remain effective for future versions of the document structure. Therefore, a data-driven approach is adopted for the information extraction. This paper demonstrates an end-to-end semantic enrichment method, taking a bridge status report as input and feeding structured object parameters directly to the building information modeling software for the enrichment of the model. The proposed method requires little user interaction and achieves production-ready accuracy. It is tested on an as-built model of an actual bridge and shows promising results.
Building Information Modeling (BIM) provides an excellent opportunity to digitally document and visually display construction projects' information throughout their whole lifecycle. Another recent technology that is fostering the digital transformation of the construction sector is blockchain-based smart contracts. In combination with BIM models, such smart contracts can be used for the automation of delivery, acceptance, and payment (DAP) processes in the construction industry. The DAP process can be modelled by using smart contracts and securely stored via a blockchain. Since smart contracts are programming codes, for stakeholders it is difficult to understand what is exactly written in the smart contracts. Therefore, it is necessary to visualize the status of the deployed smart contracts and the executed transactions. In this paper, a framework is highlighted to record and visualize the status of the DAP processes by combining BIM with smart contracts using the Business Process Model and Notation (BPMN) to develop a smart contract system. With the help of suitable visualization concepts, the individual transactions of the blockchain can be displayed in a comprehensible way. The feasibility of the framework is presented through an illustrative implementation of the smart contract system. The proposed framework can help project participants better understand the current state of a smart contract.
The construction industry is characterized by the diversity of its processes, whereby persons involved in changing project communities are confronted with a changing interplay of software applications. Therefore, planning workflows, and especially the exchange of information between stakeholders, need to be formalized. The automation and execution of these workflows go one step further to achieve added value in implementation and project management using building information modeling. For the configuration and execution of collaborative BIM workflows with compatible software products, a framework is conceived and developed that enables the modeling of project-specific workflows by linking individual software tools based on a standardized process notation. The resulting toolchains enable seamless information exchange between applications that integrate an openCDE-compliant web interface. The methodological approach in this paper is a concept implementation, including a proof of concept. For the concept development, a review of the state of the art is conducted, and requirements are analyzed. The concept development comprises data models and API descriptions and includes the concept of a central integration platform. The interaction between workflow management on the platform and the execution of tasks in the software product clients is explained. The implementation of the toolchains on the proposed platform is evaluated in a demonstrator scenario.
Digital methods such as Building Information Modeling (BIM) offer significant potential in the operation phase of a building but, therefore, require digital as-built models of the existing structures as a prerequisite. The existing building records have to be transferred into a digital model. For this retro-digitization purpose, Computer Vision (CV) and Machine learning (ML) are essential technologies. Thereby, 2D construction plans are an indispensable data basis for these methods to extract the geometry of the existing structures. The extraction requires a highly reliable detection of lines and texts. However, the performance of the CV and ML methods is highly dependent on the quality of the data. Anomalies like discolorations, stains, and fold lines can negatively affect the detection. This is especially case for old, hand-drawn paper plans, which are often the only data source available for old buildings. To integrate old plans better in the detection process by CV and ML, a quality recovery of the plans is necessary. To achieve this, we propose the use of the cycle-consistent Generative Adversarial Network (CycleGAN) that enables style transformation with unpaired data. Hereby transformation means the removal of the stated anomalies. Our results of CycleGAN improved 2D plans show that both text and edge detection methods perform better.
Modularized construction with precast concrete elements has many advantages, such as shorter construction times, higher quality, flexibility, and lower costs. These advantages are mainly due to its potential for prefabrication and series production. However, the production processes are still craftsmanship, and automation rarely occurs. Fundamental to the automation of production is digitization. In recent years, the manufacturing industry made significant progress through the intelligent networking of components, machines, and processes in the introduction of Industry 4.0. A key concept of Industry 4.0 is the digital twin, which represents both components and machines, thus creating a dynamic network in which the participants can communicate with each other. So far, BIM and digital twins in construction have focused mainly on the structure as a whole and do not consider feedback loops from production at the component level. This paper proposes a framework for a digital twin for the industrialized production of precast concrete elements in series production based on the asset administration shell (AAS) from the context of Industry 4.0. For this purpose, relevant production processes are identified, and their information requirements are derived. Data models and corresponding AAS for precast concrete parts will be created for the identified processes. The functionalities of the presented digital twin are demonstrated using the use case of quality control for a precast concrete wall element. The result shows how data can be exchanged with the digital twin and used for decision-making.

Lab head

Markus König

Members (18)

Elham Mahmoudi
  • Ruhr-Universität Bochum
Karlheinz Lehner
  • Ruhr-Universität Bochum
Ningshuang Zeng
  • Southeast University (China)
Philipp Hagedorn
  • Ruhr-Universität Bochum
Xuling Ye
  • Ruhr-Universität Bochum
Patrick Herbers
  • Ruhr-Universität Bochum
Stephan Embers
  • Ruhr-Universität Bochum
Simon Kosse
  • Ruhr-Universität Bochum

Alumni (1)

Kristina Doycheva
  • Ruhr-Universität Bochum