Research Assistant at Bundesanstalt für Materials forschung und prüfung, Germany
Ranjith Nandish is a dedicated Computational Engineer and Ph.D. researcher at Technische Universität Braunschweig, specializing in Computational Fluid Dynamics (CFD), numerical modeling, and machine learning applications in fire safety. With extensive experience in fire behavior simulations, he has contributed to multiple BMBF-funded projects, including lithium-ion battery storage safety and cultural heritage fire risk assessments. His expertise includes applying Physics-Informed Neural Networks (PINNs) and Convolutional Neural Networks (CNNs) to optimize fire prediction models and improve simulation accuracy. Proficient in tools like Fire Dynamics Simulator (FDS), ANSYS, Python, and PyTorch, he integrates machine learning with engineering challenges to develop innovative safety solutions. Ranjith has presented at international conferences and published research on pyrolysis modeling and fire dynamics. His contributions to fire safety, automation, and real-time predictive modeling highlight his strong research capabilities, making him a promising candidate for prestigious awards in engineering and computational research.
Professional Profile
Education
Ranjith Nandish has a strong academic background in engineering and computational sciences. He is currently pursuing a Ph.D. at Technische Universität Braunschweig, Germany, focusing on experimental and numerical investigations of wooden fires using advanced fire modeling methodologies. He holds a Master of Science in Computational Science and Engineering from the University of Rostock, where his research centered on numerical simulation of buoyant flows in dairy cattle houses using the porous medium approach in atmospheric boundary layers. His master’s studies provided him with in-depth knowledge of computational fluid dynamics (CFD), numerical mathematics, machine learning, and high-performance computing. Prior to that, he earned a Bachelor of Mechanical Engineering from Visvesvaraya Technological University, Karnataka, India, where he developed a strong foundation in thermodynamics, mechatronics, and engineering simulations. His diverse academic experiences have equipped him with expertise in numerical modeling, fire dynamics, and computational optimization, making him a valuable researcher in his field.
Professional Experience
Ranjith Nandish is an experienced Computational Engineer and Research Associate at the Bundesanstalt für Materialforschung und -prüfung (BAM) in Berlin, Germany. He has worked on multiple BMBF-funded projects, including the BEGIN-HVS and BRAWA projects, where he performed large-scale fire simulations for lithium-ion battery storage safety and cultural heritage buildings. His expertise lies in developing numerical models for fire spread dynamics, optimizing CFD simulations, and applying machine learning techniques to enhance predictive fire safety models. Previously, he conducted research on fire safety in timber constructions, integrating thermogravimetric analysis (TGA) and cone calorimeter data for improved simulation accuracy. His professional experience also includes a Master’s research project at the Leibniz Institute for Agricultural Engineering, where he developed airflow and thermal comfort models for animal housing. Additionally, as a Project Intern at Voith GmbH, he worked on inclined centrifugal spin casting and turbine modeling, further expanding his expertise in computational modeling and optimization.
Research Interest
Ranjith Nandish’s research interests lie at the intersection of computational fluid dynamics (CFD), fire safety engineering, and machine learning. He focuses on developing advanced numerical models to simulate fire behavior, particularly in complex environments such as lithium-ion battery storage systems, cultural heritage buildings, and timber constructions. His expertise includes applying Physics-Informed Neural Networks (PINNs) and Convolutional Neural Networks (CNNs) to enhance the accuracy and efficiency of fire prediction models. Additionally, he explores time-series forecasting, parameter optimization, and automation techniques to improve real-time fire safety assessments. His research also extends to high-performance computing, thermodynamics, and multi-physics simulations, aiming to bridge the gap between experimental fire dynamics and computational modeling. By integrating artificial intelligence with engineering solutions, Ranjith seeks to develop scalable and efficient safety mechanisms that can mitigate fire hazards in various industrial and residential settings. His work contributes to the advancement of fire modeling methodologies and predictive safety strategies.
Award and Honor
Ranjith Nandish has been recognized for his contributions to fire safety engineering and computational modeling through prestigious awards and honors. Notably, he received the SFPE Foundation GCI Student Research Fellowship, a distinguished recognition awarded by the Society of Fire Protection Engineers (SFPE) for his outstanding research in fire dynamics and computational simulations. His work on numerical investigations of fire exposure and pyrolysis modeling has been acknowledged in international conferences and symposiums, where he has presented his findings on advanced fire safety strategies. His innovative approach to integrating machine learning with fire behavior simulations has positioned him as a leading researcher in the field. Through his contributions to multiple BMBF-funded projects and his pioneering research in computational fluid dynamics (CFD), he has gained recognition within the scientific community. His commitment to advancing fire safety and predictive modeling continues to be reflected in his scholarly achievements and industry collaborations.
Research Skill
Ranjith Nandish possesses a diverse and advanced set of research skills, specializing in Computational Fluid Dynamics (CFD), fire dynamics modeling, and machine learning applications. He has expertise in numerical simulations, particularly in fire behavior prediction, safety design, and optimization. His proficiency in Fire Dynamics Simulator (FDS), ANSYS Fluent, and Pyrosim enables him to conduct high-accuracy fire simulations for large-scale industrial and structural applications. Additionally, he is skilled in Physics-Informed Neural Networks (PINNs) and Convolutional Neural Networks (CNNs), integrating machine learning techniques to enhance simulation accuracy and predictive modeling. His experience in time-series forecasting, parameter optimization, and automating CFD workflows has significantly improved computational efficiency in fire safety research. Furthermore, his ability to work with high-performance computing (HPC), MATLAB, OpenFOAM, and programming languages such as Python and C++ makes him adept at developing innovative solutions for complex engineering challenges. His interdisciplinary approach ensures robust and scalable research methodologies.
Conclusion
Ranjith Nandish is a strong candidate for the Best Researcher Award due to his advanced expertise in CFD, fire safety, and machine learning, high-quality research contributions, and technical excellence in numerical modeling and AI-driven predictions. To further solidify his chances, he could focus on publishing more high-impact papers, securing additional research awards, leading research initiatives, and highlighting his real-world impact in fire safety and computational engineering.
Publication Top Noted
Title: Numerical Investigations of a Large Fire Exposure Crib Test—Presenting Different Pyrolysis Modelling Methodologies and Numerical Results
Authors: Ranjith Nandish, Christian Knaust, Jochen Zehfuß
Year: 2025
Citation: Nandish, R., Knaust, C., & Zehfuß, J. (2025). Numerical Investigations of a Large Fire Exposure Crib Test—Presenting Different Pyrolysis Modelling Methodologies and Numerical Results. Fire and Materials. DOI: 10.1002/fam.3287
