Predicting the moisture content of a drug mixture based on acoustic signals during the granulation process using deep machine learning
DOI:
https://doi.org/10.58445/rars.3784Keywords:
Pharmaceutical wet granulation, Acoustic monitoring, Real-time process monitoring, Sound signal analysisAbstract
This study aims to present an acoustic method for real-time monitoring of the pharmaceutical
wet granulation process. Granulation is a widely used process in pharmaceutical production, and
the quality of the granule mass is directly related to the material and process parameters. The
aim of the study is to accurately determine the moisture content of the granule mass and the
granulation phases using machine learning tools by analyzing the sound signals recorded by the
microphone. According to the hypothesis, the acoustic emissions generated during granulation
are sensitive to phase changes, and their analysis by deep neural networks allows us to classify
each granulation phase with high accuracy. The study consisted of three main stages. In the first
stage, acoustic microphones were used to record sound signals from each granulation phase.
In the second stage, the obtained sound data was spectrally transformed and prepared as input
to a convolutional neural network. In the third stage, the model was trained and tested, and the
accuracy of granulation phase classification was assessed. The novelty of the study is that it
demonstrates an effective method for completely non-contact and real-time monitoring of the
granulation process. Data collection, pre processing, and model building were performed
completely independently. The results showed that up to 94 percent classification accuracy was
achieved using microphone data. This acoustic method is a reliable tool for process quality
control in pharmaceutical production. The proposed approach meets GMP requirements and
allows the development of real-time control systems in automated production, improving product
quality.
References
S. Ramm, R. Fulek, V. A. Eberle, C. Kiera, U. Odefey, and M. Pein-Hackelbusch,
"Compression density as an alternative to identify an optimal moisture content for high
shear wet granulation as an initial step for spheronisation," Pharmaceutics, vol. 14, no.
, 2022, doi: 10.3390/pharmaceutics14102303.
T. Reimers, J. Thies, P. Stöckel, S. Dietrich, M. Pein-Hackelbusch, and J. Quodbach,
"Implementation of real-time and in-line feedback control for a fluid bed granulation
process," Int. J. Pharm., vol. 567, p. 118452, Aug. 2019, doi:
1016/j.ijpharm.2019.118452.
R. Attota, P. P. Kavuri, H. Kang, R. Kasica, and L. Chen, "Nanoparticle size
determination using optical microscopes," Appl. Phys. Lett., vol. 105, p. 163105, Oct.
, doi: 10.1063/1.4900484.
M. Jamrógiewicz, "Application of the near-infrared spectroscopy in the pharmaceutical
technology," J. Pharm. Biomed. Anal., vol. 66, pp. 1–10, Jul. 2012, doi:
1016/j.jpba.2012.03.009.
B. Liu, J. Wang, J. Zeng, L. Zhao, Y. Wang, Y. Feng, and R. Du, "A review of high
shear wet granulation for better process understanding, control and product
development," Powder Technol., vol. 381, pp. 204–223, Mar. 2021, doi:
1016/j.powtec.2020.11.051.
M. Whitaker, G. Baker, J. Westrup, P. Goulding, R. Belchamber, and M. Collins,
"Applications of acoustic emission to the monitoring and end point determination of a high
shear granulation process," Int. J. Pharm., vol. 205, pp. 79–91, 2000, doi: 10.1016/S0378-
(00)00479-8.
L. Briens, D. Daniher, and A. Tallevi, "Monitoring high-shear granulation using sound
and vibration measurements," Int. J. Pharm., vol. 331, pp. 54–60, 2007, doi:
1016/j.ijpharm.2006.09.012.
H. Tsujimoto, T. Yokoyama, C. Huang, and I. Sekiguchi, "Monitoring particle
fluidization in a fluidized bed granulator with an acoustic emission sensor," Powder
Technol., vol. 113, pp. 88–96, 2000, doi: 10.1016/S0032-5910(00)00205-9.
D. Daniher, L. Briens, and A. Tallevi, "End-point detection in high-shear granulation
using sound and vibration signal analysis," Powder Technol., vol. 181, pp. 130–136, 2008,
doi: 10.1016/j.powtec.2006.12.003.
E. M. Hansuld, L. Briens, J. A. B. McCann, and A. Sayani, "Audible acoustics in highshear wet granulation: Application of frequency filtering," Int. J. Pharm., vol. 378, pp. 37–
, 2009, doi: 10.1016/j.ijpharm.2009.05.042.
E. Hansuld, L. Briens, A. Sayani, and J. McCann, "Monitoring quality attributes for highshear wet granulation with audible acoustic emissions," Powder Technol., vol. 215–216,
pp. 117–123, 2012, doi: 10.1016/j.powtec.2011.09.034.
H. Lou, B. Lian, and M. J. Hageman, "Applications of machine learning in solid oral
dosage form development," J. Pharm. Sci., vol. 110, pp. 3150–3165, 2021, doi:
1016/j.xphs.2021.04.013.
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, pp. 436–444,
, doi: 10.1038/nature14539.
J. Donahue, L. A. Hendricks, M. Rohrbach, S. Venugopalan, S. Guadarrama, K.
Saenko, and T. Darrell, "Long-term recurrent convolutional networks for visual
recognition and description," IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 4, pp.
–691, Apr. 2017, doi: 10.1109/TPAMI.2016.2599174.
C. N. Teague, S. Hersek, H. Toreyin, M. L. Millard-Stafford, M. L. Jones, G. F. Kogler,
M. N. Sawka, and O. T. Inan, "Novel methods for sensing acoustical emissions from the
knee for wearable joint health assessment," IEEE Trans. Biomed. Eng., vol. 63, no. 8, pp.
–1590, Aug. 2016, doi: 10.1109/TBME.2016.2543226.
S. W. Smith, Digital Signal Processing: A Practical Guide for Engineers and Scientists,
vol. 1. Oxford, UK: Newnes, 2003.
Y. Qu, X. Li, and Z. Qin, "Acoustic scene classification based on three-dimensional multichannel feature-correlated deep learning networks," Sci. Rep., vol. 12, p. 13730, 2022,
doi: 10.1038/s41598-022-17938-0.
A. Mesaros, T. Heittola, and T. Virtanen, "Acoustic scene classification: An overview of
DCASE 2017 challenge entries," in Proc. 16th Int. Workshop Acoustic Signal
Enhancement (IWAENC), Tokyo, Japan, 17–20 Sep. 2018, pp. 411–415, doi:
1109/IWAENC.2018.8586003.
T. Zhang, G. Feng, J. Liang, and T. An, "Acoustic scene classification based on Mel
spectrogram decomposition and model merging," Appl. Acoust., vol. 182, p. 108258,
, doi: 10.1016/j.apacoust.2021.108258.
B. McFee, C. Raffel, D. Liang, D. P. W. Ellis, M. McVicar, E. Battenberg, and O. Nieto,
"librosa: Audio and music signal analysis in Python," in Proc. 14th Python in Science
Conf., Austin, TX, USA, 6–12 Jul. 2015, pp. 18–25.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale
image recognition,” in Proc. Int. Conf. Learn. Representations (ICLR), San Diego, CA,
USA, May 7–9, 2015.
C. R. Harris et al., "Array programming with NumPy," Nature, vol. 585, no. 7825, pp.
–362, Sep. 2020, doi: 10.1038/s41586-020-2649-2.
M. Abadi et al., “TensorFlow: Large-Scale Machine Learning on Heterogeneous
Systems,” 2015. [Online]. Available: https://www.tensorflow.org
Downloads
Posted
Categories
License
Copyright (c) 2026 Research Archive of Rising Scholars
This work is licensed under a Creative Commons Attribution 4.0 International License.
