TY - GEN A1 - Villani, P. A1 - Unger, Jörg F. A1 - Weiser, M. T1 - Adaptive Gaussian Process Regression for Bayesian inverse problems T2 - arxiv.org N2 - We introduce a novel adaptive Gaussian Process Regression (GPR) methodology for efficient construction of surrogate models for Bayesian inverse problems with expensive forward model evaluations. An adaptive design strategy focuses on optimizing both the positioning and simulation accuracy of training data in order to reduce the computational cost of simulating training data without compromising the fidelity of the posterior distributions of parameters. The method interleaves a goal-oriented active learning algorithm selecting evaluation points and tolerances based on the expected impact on the Kullback-Leibler divergence of surrogated and true posterior with a Markov Chain Monte Carlo sampling of the posterior. The performance benefit of the adaptive approach is demonstrated for two simple test problems. T2 - ALGORITMY 2024 Central-European Conference on Scientific Computing CY - High Tatra Mountains, Slovakia DA - 15.03.2024 KW - Active learning KW - Bayesian inverse problems KW - Gaussian Process Regression (GPR) KW - Parameter identification KW - Surrogate models PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-600408 DO - https://doi.org/10.48550/arXiv.2404.19459 SN - 2331-8422 SP - 1 EP - 12 PB - Cornell University CY - Ithaca, NY AN - OPUS4-60040 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN A1 - Thiele, Marc A1 - Makris, Ralf T1 - Specification for high-speed tensile tests on reinforcement bar coupler systems N2 - This document presents the specification for the execution and evaluation of high-speed tensile tests on reinforcement bar coupler systems. This specification was developed at BAM - Bundesanstalt für Materialforschung und -prüfung (Federal Institute for Materials Research and Testing, Germany) - following test principles from related international standards. The present document represents the latest status of the test specification. It is noted that until 2010 the test procedure was characterised on a test velocity based on L0. In an improved test conception and after intensive investigations in cooperation with industry partners, this procedure has been updated to consider instead a test velocity based on Lr, since this warrants more comparable and meaningful results. KW - Test specification KW - Coupler systems KW - High-speed KW - Tensile test KW - Reinforcement PY - 2021 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-525075 DO - https://doi.org/10.26272/opus4-52507 SP - 1 EP - 29 PB - Bundesanstalt für Materialforschung und -prüfung (BAM) CY - Berlin ET - V01 AN - OPUS4-52507 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -