Rights statement: ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Accepted author manuscript, 1.31 MB, PDF document
Available under license: CC BY: Creative Commons Attribution 4.0 International License
Final published version
Licence: CC BY: Creative Commons Attribution 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network
AU - Li, Xiaoran
AU - Williams, Bryan
AU - May, Robert K.
AU - Evans, Michael J.
AU - Zhong, Shuncong
AU - Gladden, Lynn F.
AU - Shen, Yao chun
AU - Zeitler, J. Axel
AU - Lin, Hungyen
N1 - ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
PY - 2022/7/31
Y1 - 2022/7/31
N2 - In-line terahertz pulsed imaging (TPI) has been utilised to measure the film coating thickness of individual tablets during the coating process in a production-scale pan coater. A criteria-based waveform selection algorithm (WSA) was developed to select terahertz signals reflected from the surface of coating tablets and determine the coating thickness. Since the WSA uses many criteria thresholds to select terahertz waveforms of sufficiently high quality, it could reject some potential candidate tablet waveforms that are close but do not reach the threshold boundary. On the premise of the availability of large datasets, we aim to improve the efficiency of WSA with machine learning. This paper presents a recurrent neural network approach to optimise waveform selection. In comparison with the conventional method of WSA, our approach allows more than double the number of waveforms to be selected while maintain great agreement with off-line thickness measurement. Moreover, the processing time of waveform selection decreases so that it can be applied for real-time coating monitoring in the pharmaceutical industry, which leads more advancement on the quality control for the pharmaceutical film coating.
AB - In-line terahertz pulsed imaging (TPI) has been utilised to measure the film coating thickness of individual tablets during the coating process in a production-scale pan coater. A criteria-based waveform selection algorithm (WSA) was developed to select terahertz signals reflected from the surface of coating tablets and determine the coating thickness. Since the WSA uses many criteria thresholds to select terahertz waveforms of sufficiently high quality, it could reject some potential candidate tablet waveforms that are close but do not reach the threshold boundary. On the premise of the availability of large datasets, we aim to improve the efficiency of WSA with machine learning. This paper presents a recurrent neural network approach to optimise waveform selection. In comparison with the conventional method of WSA, our approach allows more than double the number of waveforms to be selected while maintain great agreement with off-line thickness measurement. Moreover, the processing time of waveform selection decreases so that it can be applied for real-time coating monitoring in the pharmaceutical industry, which leads more advancement on the quality control for the pharmaceutical film coating.
KW - Coatings
KW - Thickness measurement
KW - Pharmaceuticals
KW - Logic gates
KW - Terahertz wave imaging
KW - Refractive index
KW - Convolutional neural networks
U2 - 10.1109/TTHZ.2022.3164353
DO - 10.1109/TTHZ.2022.3164353
M3 - Journal article
VL - 12
SP - 392
EP - 400
JO - IEEE Transactions on Terahertz Science and Technology
JF - IEEE Transactions on Terahertz Science and Technology
SN - 2156-342X
IS - 4
ER -