Flame spray pyrolysis optimization via statistics and machine learning. (November 2020)

• Record Type: Journal Article
• Authors: Paulson, Noah H.; Libera, Joseph A.; Stan, Marius
• Is Part Of: Materials & design. Volume 196(2020)
• Publication Date: 2020-11
• Subjects: Flame spray pyrolysis -- Nanoparticle synthesis -- Latin hypercube sampling -- Bayesian optimization; Materials -- Periodicals; Engineering design -- Periodicals; Matériaux -- Périodiques; Conception technique -- Périodiques; Electronic journals; 620.11
• DOI: 10.1016/j.matdes.2020.108972
• Languages: English
• ISSNs: 0264-1275

Abstract

Abstract: Flame spray pyrolysis (FSP) is an important manufacturing process whereby nanomaterials are produced through the combustion of atomized fuel containing dissolved precursor elements. While FSP has the potential to enable the scalable production of a wide range of next generation energy materials, it also has a multi-scale, multi-physics character, and a large number of processing variables. Optimizing the process for desirable material outcomes by traditional approaches is challenging. In this work, the processing parameter space is explored via a new and efficient methodology that includes statistical methods such as Latin hypercube design of experiments, machine learning surrogate modeling, and Bayesian optimization. As a result, the FSP process is optimized for enhanced performance. Specifically, in-situ particle size measurements are used to tailor the production of silica nanoparticles for a low spread in particle diameters with respect to the mean particle diameter, resulting in an improvement of 25.5% over the baseline within 15 experimental trials. In the process, the analysis reveals distinct domains of primary particle and agglomerated particle formation. Graphical abstract: Unlabelled Image Highlights: A novel statistical workflow tuned flame spray pyrolysis to produce SiO2 nanoparticles that met the design objectives. The Latin hypercube and Bayesian optimization design strategy minimized the spread of the particle size distribution. The procedure achieved a relative improvement over the baseline relative spread of 25.5% within 15 experiments. Post analysis revealed a transition from primary to agglomerated particle formation at 0.5wt% TEOS in ethanol/methanol.