Abstract
Acoustic spectroscopy and neural networks (NNs) are applied to on-line real-time measurement of particle size distribution (PSD) during wet milling of pharmaceutical nanocrystals. A method for modeling the relationship between acoustic attenuation spectra and PSD is proposed that is based on NNs and principal component analysis (PCA). PCA reduces the dimensions of both the spectra and the PSD; then, a neural network model of 2 × 2 × 2 (input, hidden, output layer nodes) with only eight connection weights is built. Compared with previous instrument models that could require as many as 14 physical properties, the current approach does not need any prior knowledge of the system's properties. In addition, the time taken to complete a PSD measurement is reduced from minutes to seconds and it always generates a single solution, rather than possible multiple PSD solutions as in early methods. Application to hydrotalcite nanomilling found good agreement between the on-line measurements and off-line analysis.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
