In-line Self-calibrated pH Monitoring System with Hyperspectral Imaging and Deep Learning
This project aims at developing an automated system for in-line, non-invasive, self-calibrated pH and/or related DO and glucose measurement in pharmaceutical processing.
Categories
Equipment and Supplies
Process control
Project status
100% Completed
Industry Need
Current industrial practice includes frequent solution sampling and sensor probe calibration in order to monitor solution status such as pH and glucose.
Solution
Short wavelength infrared (SWIR) hyperspectral imaging has the potential to offer non-invasive and continuous monitoring solution status to cut labor cost and sampling waste in the processing lines.
Outputs/Deliverables
Show that analytical method SWIR Hyperspectral Imaging (HIS) can predict pH and glucose concentration in aqueous solutions with R2 values larger than 0.9.
An innovative system was created and experiments were conducted to gain know-how of the new probe.
Tested in lab with partner participations.
Impacts
Automated system for in-line, non-invasive, self-calibrated pH and/or related DO and glucose measurement in pharmaceutical processing.
Publications
Hevaganinge, A., Weber, C. M., Filatova, A., Musser, A., Neri, A., Conway, J., Yuan, Y., Cattaneo, M., Clyne, A. M., & Tao, Y. (2023). Fast-Training Deep Learning Algorithm for Multiplex Quantification of Mammalian Bioproduction Metabolites via Contactless Short-Wave Infrared Hyperspectral Sensing. ACS Omega, 8(16), 14774-14783. https://doi.org/10.1021/acsomega.3c00861
Additional Project Information (Members Only)
Login to the NIIMBL member portal to access more, including: