Jump to main content
Jump to site search

Flame-assisted spray pyrolysis to size-controlled LiyAlxMn2-xO4: a supervised machine learning approach


Demand for lithium manganese oxide for cathodes is growing faster than lithium cobalt oxide because of their smaller environmental footprint, lower cost, and flammability. Their capacity, cyclability, and time between charge require a precise control of the physiochemical properties including particle size distribution. We developed a novel one-step synthesis route for Al-doped LiMn2O4 by flame assisted spray pyrolysis (FASP) that controls particle size and morphology. A combination of intrinsic and extrinsic parameters governs the process with synergistic and antagonistic interactions and non-linear relationships. We identified the responses to these 10 operational factors that affect the size and specific surface area of LiyAlxMn2-xO4 powders. The surface areas of powders doped with Al double versus standard formulations, which we attribute to carbon forming on the surface. Elemental mapping of the surface shows that Al, Mn, and O, are evenly distributed in the particles. The shifts in the XRD peaks proves Al is incorporated into the structure. We trained three machine learning algorithms to predict the particle size given the experimental factors. Artificial neural networks (ANNs), support vector regression (SVR), and random forest regression (RF) adequately predict the particle size and each model accounts for 0.97, 0.86, and 0.49 of the variance (R-squared), respectively. The ANN model identifies ethanol to precursor ratio, precursor type, and fuel flow-rate as the most significant factors to account for the particle size. The RF model assigns the greatest effect to vacuum pressure, followed by precursor type, and fuel flow-rate.

Back to tab navigation

Publication details

The article was received on 21 Jun 2018, accepted on 05 Nov 2018 and first published on 06 Nov 2018

Article type: Paper
DOI: 10.1039/C8CE01026A
Citation: CrystEngComm, 2018, Accepted Manuscript
  •   Request permissions

    Flame-assisted spray pyrolysis to size-controlled LiyAlxMn2-xO4: a supervised machine learning approach

    N. Saadatkhah, S. Aghamiri, M. R. Talaie and G. S. Patience, CrystEngComm, 2018, Accepted Manuscript , DOI: 10.1039/C8CE01026A

Search articles by author