TY - RPRT A1 - Holtappels, Kai A1 - Liebner, Christian A1 - Schröder, Volkmar A1 - Schildberg, H.-P. T1 - Report on experimentally determined explosion limits, explosion pressures and rates of explosion pressure rise - Part 1: methane, hydrogen and propylene; Contract No. EVG1-CT-2002-00072 KW - Explosion indices KW - Dependence of pressure KW - Temperature KW - Ignition energy and fuel content PY - 2006 UR - http://www.morechemistry.com/SAFEKINEX/deliverables/44.Del.%20No.%208.pdf IS - 8 SP - 1 EP - 149 PB - Bundesanstalt für Materialforschung und -prüfung CY - Berlin AN - OPUS4-12434 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Junias, Josua Kondja A1 - Askar, Enis A1 - Holtappels, Kai A1 - Liebner, Christian A1 - Shaanika, Erasmus A1 - Thewis, Max T1 - Prediction of Explosion Characteristics of Hydrogen Mixtures using Machine Learning Models N2 - Explosion characteristics of hydrogen mixtures have been extensively investigated at different conditions. Due to the intensiveness of the explosion characteristics experimental determination, empirical and semi-empirical models are commonly used to predict explosion limits in dependance of conditions: temperature, pressure, and mixture composition. However, unevenly distributed, and limited empirical data and the complex non-linear relationship of these explosion characteristics’ present significant challenges to empirical explosion limits prediction methods under various mixture conditions. Moreover, some empirical models and semi-empirical models are not comprehensive and limited in scope of application. To address these issues, the present study adapts a machine learning approach for improving the hydrogen mixtures explosion characteristics prediction at different conditions, offering a fast, flexible, and comprehensive accurate prediction approach. A Multi-Layer Perceptron model was trained, validated, and tested using key input features such as flammability state, initial mixture temperature, inert gas concentration, adiabatic flame temperature, and Lewis numbers. Data augmentation techniques were conducted to supplement and improve the predictive capability of the model. The model’s performance was compared with a separate experimental dataset. This machine learning approach offers a cost-effective and robust alternative to existing empirical explosion limit prediction method, thus also reducing the experimental effort for explosion limits determination. T2 - BAM Symposium on Artificial Intelligence and Machine Learning CY - Berlin, Germany DA - 06.11.2025 KW - Machine Learning KW - Flammability Limits PY - 2025 AN - OPUS4-64706 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - RPRT A1 - Holtappels, Kai A1 - Liebner, Christian A1 - Schröder, Volkmar A1 - Pasman, H. A1 - Pekalski, A. A1 - Carson, D. A1 - Proust, C. T1 - Report on the experimental factors influencing explosion indices determination KW - SAFEKINEX KW - Explosionskenngrößen KW - Experimentelle Einflüsse KW - Nicht-atmosphärische Bedingungen PY - 2004 UR - http://www.morechemistry.com/SAFEKINEX/deliverables/02.Del.%20No.%202%20Exp.%20Factors%20Expl.%20Indices%20Det.pdf SP - 1 EP - 52 AN - OPUS4-5976 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Junias, Josua Kondja A1 - Holtappels, Kai A1 - Liebner, Christian A1 - Thewis, Max A1 - Askar, Enis A1 - Shaanika, Erasmus T1 - Hydrogen Mixtures Flammability Limits Prediction using Machine Learning Models N2 - Flammability characteristics of hydrogen mixtures have been extensively investigated at different initial conditions(temperature and pressure). Based on the available experimental datasets, empirical and semi-empirical models are commonly used to calculate flammability limits in dependance to initial conditions and mixture composition to reduce the experimental effort. However, unevenly distributed empirical data and the complex non-linear relationship characteristics of these data present significant challenges to empirical flammability limits prediction methods under various mixture initial conditions. Moreover, the empirical models and semi-empirical models only cover some influencing parameters, respectively. To address these issues, the present study adapts a machine learning (ML) approach for improving the hydrogen-air/oxygen-inert gas mixture flammability limits prediction at different conditions with a holistic approach. A Multi-Layer Perceptron (MLP) model was trained, validated, and tested using key input features such as flammability state, initial mixture temperature, equivalence ratio, inert gas concentration, adiabatic flame temperature, and Lewis numbers. Data augmentation techniques were conducted on experimental datasets to improve the predictive capability of the model. The models’ performance was compared with empirical flammability limit prediction methods. The goal is to deliver fast, reliable, and more accurate predictions across different scenarios with a single prediction model. Most importantly, the machine learning approach offers a cost-effective and robust alternative to existing empirical flammability limit prediction methods, thus also reducing the experimental effort for explosion limits determination. T2 - 11th International Conference on Hydrogen Safety (ICHS) 2025 CY - Seoul, South Korea DA - 22.09.2025 KW - Machine Learning KW - Flammability Limits PY - 2025 SN - 979 -12 -243 -0274 - 2 SP - 1389 EP - 1401 AN - OPUS4-64624 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Liebner, Christian A1 - Schröder, Volkmar A1 - Holtappels, Kai T1 - Safety characteristics of hydrogen at super ambient conditions: Lubricant contamination influencing the Auto Ignition Temperature T2 - WHEC 2006 - 16th World Hydrogen Energy Conference CY - Lyon, France DA - 2006-06-13 KW - Hydrogen KW - Safety Characteristics KW - Auto Ignition KW - Lubricant KW - Motor Oil PY - 2013 SN - 978-1-62276-540-9 SP - 7 pages (Ref 638) PB - International Association for Hydrogen Energy CY - Lyon AN - OPUS4-12508 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Liebner, Christian A1 - Holtappels, Kai A1 - Schröder, Volkmar T1 - Untersuchungsmethoden für Selbstentzündungsprozesse von Brenngasen PY - 2005 DO - https://doi.org/10.1002/cite.200590361 SN - 0009-286X SN - 1522-2640 VL - 77 IS - 8 SP - 1125 EP - 1126 PB - Wiley-VCH Verl. CY - Weinheim AN - OPUS4-11886 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Liebner, Christian A1 - Holtappels, Kai A1 - Schröder, Volkmar T1 - Selbstentzündungsprozesse bei nichtatmosphärischen Bedingungen - Die Identifizierung unerwarteter Risiken T2 - 7. Fachtagung Anlagen-, Arbeits- und Umweltsicherheit CY - Köthen, Deutschland DA - 2004-11-04 PY - 2004 PB - VDI-Verl. CY - Halle AN - OPUS4-5218 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - RPRT A1 - Liebner, Christian A1 - Holtappels, Kai A1 - Schröder, Volkmar A1 - Pasman, H. A1 - Pekalski, A. T1 - Report on experimentally determined self-ignition temperature and the ignition delay time KW - Autoignition KW - Pressure Dependency KW - Ignition Temperature KW - Cool Flame KW - Slow Combustion KW - Gases KW - n-Butane KW - Ethylene KW - Methane PY - 2005 UR - http://www.morechemistry.com/SAFEKINEX/deliverables/26.Del.%20No.%205%20SIT+IDT%20steel+quartz.pdf SP - 74 pages AN - OPUS4-5975 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Holtappels, Kai A1 - Liebner, Christian A1 - Scheid, Marc A1 - Schröder, Volkmar T1 - Volumeneinfluss auf die Explosionskenngrößen von Wasserstoff und Methan bei nicht-atmosphärischen Bedingungen KW - SAFEKINEX KW - Explosionsgrenzen KW - Explosionsdrücke KW - Raten des Druckanstiegs PY - 2005 DO - https://doi.org/10.1002/cite.200590143 SN - 0009-286X SN - 1522-2640 VL - 77 IS - 8 SP - 1141 EP - 1142 PB - Wiley-VCH Verl. CY - Weinheim AN - OPUS4-10857 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN A1 - Schröder, Volkmar A1 - Holtappels, Kai A1 - Liebner, Christian T1 - Hydrocarbon oxidation processes at non-atmospheric conditions - EC-project SAFEKINEX N2 - The project will develop test methodology for explosion indices al non-ambient conditions, a validated data base on them and on many other explosion indices as a function of pressure and temperature. Further, models will be developed, enabling prediction of behaviour of reactive systems and predicting explosion parameters. T2 - 3rd International ESMG Symposium: Process Safety and Industrial Explosion Protection CY - Nuremberg, Germany DA - 2004-03-16 KW - Gas explosion KW - Safety characteristics KW - Oxidation kinetics KW - Explosion limits KW - Self ignition PY - 2004 SN - 3-9807567-3-4 SP - 1(?) EP - 10(?) PB - European Safety Management Group CY - Hamm AN - OPUS4-5783 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -