Selecting Machine Learning Models to Support the Design of Al/CuO Nanothermites

Abstract

Novel properties associated with nanothermites have attracted great interest for several applications, including lead-free primers and igniters. However, the prediction of quantitative structure-energetic performance relationships are still challenging. This study investigates machine learning methods as tools to surrogate complex physical models to design novel nanothermites with optimized burning rates chosen for energetic performance. The study focuses on Al/CuO nanolaminates, for which nine supervised regressors commonly used in ML applied to materials science are investigated. For each, a ML model is built using a database containing a set of 2,700 Al/CuO nanolaminate systems, specifically generated for this study.We demonstrate the superiority of the multilayer perceptron algorithm to surrogate conventional physical-based models and predict the Al/CuO nanolaminate microstructure-burn rate relationship with good efficiency: the burn rate is estimated with less than 1% error (0.07 m.s -1 ), which is very good for designing nanoengineered energetic materials, knowing that it typically varies from approximately 8-20 m.s -1 . In addition, the optimization of the Al/CuO nanolaminate structure for burn rate maximization through machine learning takes a few

Effects of different mass ratios on mechanical properties and impact energy release characteristics of Al/PTFE/W and Al/PTFE/CuO polymer composites

“…The reaction heat of Al/PTFE promotes the thermite reaction of Al/CuO, leading to the generation of local hot spots, and the reaction heat spreads throughout the entire specimen. The temperature of the specimen rises sharply, and a thermal explosion reaction occurs 29 . Additionally, no gaseous reactant and product is found for Al/CuO.…”

“…The temperature of the specimen rises sharply, and a thermal explosion reaction occurs. 29 Additionally, no gaseous reactant and product is found for Al/CuO. Hence, although the chemical reaction heat of Al/PTFE theoretically exceeds that of Al/CuO, the reaction is more complete for Al/CuO than for Al/PTFE, which results in a further increase in the released energy and the reaction efficiency (η) of the Al/PTFE/CuO specimens.…”

Role of Surface Tension on Heat Feedback and Power from Energetic Composites

“…Metalized energetics has emerged as a promising frontier due to their higher theoretically chemical energy density compared to the traditional CHNO energetics. − Despite the higher energy density, the relatively long diffusion length between fuel and oxidizer of traditional micrometer-scale metal energetics results in slow reaction kinetics. Modern formulations that incorporate nanoscale fuels and oxidizers aim to enhance reactivity by increasing the specific surface area and reducing the transport distances. ,,− Aluminum (Al) nanoparticles have been widely used for this purpose due to their high gravimetric and volumetric energy density (31.1 kJ·g –1 and 83.8 kJ·cm –3 , respectively), as well as ready availability. − However, agglomeration becomes prevalent with the replacement of micron scale Al with nanoscale Al. , This is because of the tendency of Al nanoparticles to aggregate, sinter, and coalesce due to either solid state diffusion or viscous flow. , The agglomeration mitigates the advantages of utilizing Al nanoparticles and decreases the energy release rate. ,, …”