@unpublished{SteinerBourinetLahmer, author = {Steiner, Maria and Bourinet, Jean-Marc and Lahmer, Tom}, title = {An adaptive sampling method for global sensitivity analysis based on least-squares support vector regression}, doi = {10.25643/BAUHAUS-UNIVERSITAET.3832}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20181218-38320}, pages = {1 -- 33}, abstract = {In the field of engineering, surrogate models are commonly used for approximating the behavior of a physical phenomenon in order to reduce the computational costs. Generally, a surrogate model is created based on a set of training data, where a typical method for the statistical design is the Latin hypercube sampling (LHS). Even though a space filling distribution of the training data is reached, the sampling process takes no information on the underlying behavior of the physical phenomenon into account and new data cannot be sampled in the same distribution if the approximation quality is not sufficient. Therefore, in this study we present a novel adaptive sampling method based on a specific surrogate model, the least-squares support vector regresson. The adaptive sampling method generates training data based on the uncertainty in local prognosis capabilities of the surrogate model - areas of higher uncertainty require more sample data. The approach offers a cost efficient calculation due to the properties of the least-squares support vector regression. The opportunities of the adaptive sampling method are proven in comparison with the LHS on different analytical examples. Furthermore, the adaptive sampling method is applied to the calculation of global sensitivity values according to Sobol, where it shows faster convergence than the LHS method. With the applications in this paper it is shown that the presented adaptive sampling method improves the estimation of global sensitivity values, hence reducing the overall computational costs visibly.}, subject = {Approximation}, language = {en} } @article{LizarazuHarirchianShaiketal., author = {Lizarazu, Jorge and Harirchian, Ehsan and Shaik, Umar Arif and Shareef, Mohammed and Antoni-Zdziobek, Annie and Lahmer, Tom}, title = {Application of machine learning-based algorithms to predict the stress-strain curves of additively manufactured mild steel out of its microstructural characteristics}, series = {Results in Engineering}, volume = {2023}, journal = {Results in Engineering}, number = {Volume 20 (2023)}, publisher = {Elsevier}, address = {Amsterdam}, doi = {10.1016/j.rineng.2023.101587}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20231207-65028}, pages = {1 -- 12}, abstract = {The study presents a Machine Learning (ML)-based framework designed to forecast the stress-strain relationship of arc-direct energy deposited mild steel. Based on microstructural characteristics previously extracted using microscopy and X-ray diffraction, approximately 1000 new parameter sets are generated by applying the Latin Hypercube Sampling Method (LHSM). For each parameter set, a Representative Volume Element (RVE) is synthetically created via Voronoi Tessellation. Input raw data for ML-based algorithms comprises these parameter sets or RVE-images, while output raw data includes their corresponding stress-strain relationships calculated after a Finite Element (FE) procedure. Input data undergoes preprocessing involving standardization, feature selection, and image resizing. Similarly, the stress-strain curves, initially unsuitable for training traditional ML algorithms, are preprocessed using cubic splines and occasionally Principal Component Analysis (PCA). The later part of the study focuses on employing multiple ML algorithms, utilizing two main models. The first model predicts stress-strain curves based on microstructural parameters, while the second model does so solely from RVE images. The most accurate prediction yields a Root Mean Squared Error of around 5 MPa, approximately 1\% of the yield stress. This outcome suggests that ML models offer precise and efficient methods for characterizing dual-phase steels, establishing a framework for accurate results in material analysis.}, subject = {Maschinelles Lernen}, language = {en} } @article{HarirchianLahmerKumarietal., author = {Harirchian, Ehsan and Lahmer, Tom and Kumari, Vandana and Jadhav, Kirti}, title = {Application of Support Vector Machine Modeling for the Rapid Seismic Hazard Safety Evaluation of Existing Buildings}, series = {Energies}, volume = {2020}, journal = {Energies}, number = {volume 13, issue 13, 3340}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/en13133340}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20200707-41915}, pages = {15}, abstract = {The economic losses from earthquakes tend to hit the national economy considerably; therefore, models that are capable of estimating the vulnerability and losses of future earthquakes are highly consequential for emergency planners with the purpose of risk mitigation. This demands a mass prioritization filtering of structures to identify vulnerable buildings for retrofitting purposes. The application of advanced structural analysis on each building to study the earthquake response is impractical due to complex calculations, long computational time, and exorbitant cost. This exhibits the need for a fast, reliable, and rapid method, commonly known as Rapid Visual Screening (RVS). The method serves as a preliminary screening platform, using an optimum number of seismic parameters of the structure and predefined output damage states. In this study, the efficacy of the Machine Learning (ML) application in damage prediction through a Support Vector Machine (SVM) model as the damage classification technique has been investigated. The developed model was trained and examined based on damage data from the 1999 D{\"u}zce Earthquake in Turkey, where the building's data consists of 22 performance modifiers that have been implemented with supervised machine learning.}, subject = {Erdbeben}, language = {en} } @article{LahmerKnabeNikullaetal., author = {Lahmer, Tom and Knabe, Tina and Nikulla, Susanne and Reuter, Markus}, title = {Bewertungsmethoden f{\"u}r Modelle des konstruktiven Ingenieurbaus}, series = {Bautechnik}, journal = {Bautechnik}, pages = {60 -- 64}, abstract = {Bewertungsmethoden f{\"u}r Modelle des konstruktiven Ingenieurbaus}, subject = {Angewandte Mathematik}, language = {de} } @inproceedings{AlaladeKafleWuttkeetal., author = {Alalade, Muyiwa and Kafle, Binod and Wuttke, Frank and Lahmer, Tom}, title = {CALIBRATION OF CYCLIC CONSTITUTIVE MODELS FOR SOILS BY OSCILLATING FUNCTIONS}, series = {Digital Proceedings, International Conference on the Applications of Computer Science and Mathematics in Architecture and Civil Engineering : July 20 - 22 2015, Bauhaus-University Weimar}, booktitle = {Digital Proceedings, International Conference on the Applications of Computer Science and Mathematics in Architecture and Civil Engineering : July 20 - 22 2015, Bauhaus-University Weimar}, editor = {G{\"u}rlebeck, Klaus and Lahmer, Tom}, organization = {Bauhaus-Universit{\"a}t Weimar}, issn = {1611-4086}, doi = {10.25643/bauhaus-universitaet.2793}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20170314-27932}, pages = {6}, abstract = {In order to minimize the probability of foundation failure resulting from cyclic action on structures, researchers have developed various constitutive models to simulate the foundation response and soil interaction as a result of these complex cyclic loads. The efficiency and effectiveness of these model is majorly influenced by the cyclic constitutive parameters. Although a lot of research is being carried out on these relatively new models, little or no details exist in literature about the model based identification of the cyclic constitutive parameters. This could be attributed to the difficulties and complexities of the inverse modeling of such complex phenomena. A variety of optimization strategies are available for the solution of the sum of least-squares problems as usually done in the field of model calibration. However for the back analysis (calibration) of the soil response to oscillatory load functions, this paper gives insight into the model calibration challenges and also puts forward a method for the inverse modeling of cyclic loaded foundation response such that high quality solutions are obtained with minimum computational effort. Therefore model responses are produced which adequately describes what would otherwise be experienced in the laboratory or field.}, subject = {Angewandte Informatik}, language = {en} } @article{FaridmehrTahirLahmer, author = {Faridmehr, Iman and Tahir, Mamood Md. and Lahmer, Tom}, title = {Classification System for Semi-Rigid Beam-to-Column Connections}, series = {LATIN AMERICAN JOURNAL OF SOLIDS AND STRUCTURES 11}, journal = {LATIN AMERICAN JOURNAL OF SOLIDS AND STRUCTURES 11}, doi = {10.1590/1679-78252595}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20170401-30988}, pages = {2152 -- 2175}, abstract = {The current study attempts to recognise an adequate classification for a semi-rigid beam-to-column connection by investigating strength, stiffness and ductility. For this purpose, an experimental test was carried out to investigate the moment-rotation (M-theta) features of flush end-plate (FEP) connections including variable parameters like size and number of bolts, thickness of end-plate, and finally, size of beams and columns. The initial elastic stiffness and ultimate moment capacity of connections were determined by an extensive analytical procedure from the proposed method prescribed by ANSI/AISC 360-10, and Eurocode 3 Part 1-8 specifications. The behaviour of beams with partially restrained or semi-rigid connections were also studied by incorporating classical analysis methods. The results confirmed that thickness of the column flange and end-plate substantially govern over the initial rotational stiffness of of flush end-plate connections. The results also clearly showed that EC3 provided a more reliable classification index for flush end-plate (FEP) connections. The findings from this study make significant contributions to the current literature as the actual response characteristics of such connections are non-linear. Therefore, such semirigid behaviour should be used to for an analysis and design method.}, subject = {Tragf{\"a}higkeit}, language = {en} } @article{ReichertOlneyLahmer, author = {Reichert, Ina and Olney, Peter and Lahmer, Tom}, title = {Combined approach for optimal sensor placement and experimental verification in the context of tower-like structures}, series = {Journal of Civil Structural Health Monitoring}, volume = {2021}, journal = {Journal of Civil Structural Health Monitoring}, number = {volume 11}, publisher = {Heidelberg}, address = {Springer}, doi = {10.1007/s13349-020-00448-7}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20210804-44701}, pages = {223 -- 234}, abstract = {When it comes to monitoring of huge structures, main issues are limited time, high costs and how to deal with the big amount of data. In order to reduce and manage them, respectively, methods from the field of optimal design of experiments are useful and supportive. Having optimal experimental designs at hand before conducting any measurements is leading to a highly informative measurement concept, where the sensor positions are optimized according to minimal errors in the structures' models. For the reduction of computational time a combined approach using Fisher Information Matrix and mean-squared error in a two-step procedure is proposed under the consideration of different error types. The error descriptions contain random/aleatoric and systematic/epistemic portions. Applying this combined approach on a finite element model using artificial acceleration time measurement data with artificially added errors leads to the optimized sensor positions. These findings are compared to results from laboratory experiments on the modeled structure, which is a tower-like structure represented by a hollow pipe as the cantilever beam. Conclusively, the combined approach is leading to a sound experimental design that leads to a good estimate of the structure's behavior and model parameters without the need of preliminary measurements for model updating.}, subject = {Strukturmechanik}, language = {en} } @article{MarzbanLahmer, author = {Marzban, Samira and Lahmer, Tom}, title = {Conceptual implementation of the variance-based sensitivity analysis for the calculation of the first-order effects}, series = {Journal of Statistical Theory and Practice}, journal = {Journal of Statistical Theory and Practice}, pages = {589 -- 611}, abstract = {Conceptual implementation of the variance-based sensitivity analysis for the calculation of the first-order effects}, subject = {Angewandte Mathematik}, language = {en} } @article{Lahmer, author = {Lahmer, Tom}, title = {Crack identification in hydro-mechanical systems with applications to gravity water dams}, series = {Inverse Problems in Science and Engineering}, journal = {Inverse Problems in Science and Engineering}, pages = {1083 -- 1101}, abstract = {Crack identification in hydro-mechanical systems with applications to gravity water dams}, subject = {Angewandte Mathematik}, language = {en} } @article{AlaladeNguyenTuanWuttkeetal., author = {Alalade, Muyiwa and Nguyen-Tuan, Long and Wuttke, Frank and Lahmer, Tom}, title = {Damage identification in gravity dams using dynamic coupled hydro-mechanical XFEM}, series = {International Journal of Mechanics and Materials in Design}, journal = {International Journal of Mechanics and Materials in Design}, doi = {10.25643/bauhaus-universitaet.3596}, pages = {1 -- 19}, abstract = {Damage identification in gravity dams using dynamic coupled hydro-mechanical XFEM.}, subject = {Angewandte Mathematik}, language = {en} }