RESEARCH PAPER
Application of Continuous Wavelet Transform and Convolutional Neural Networks for Diagnostics of Screw Wear in Wheat Extrusion
1
Faculty of Environmental and Mechanical Engineering, Department of Biosystems Engineering, Poznań University of Life Sciences, Poland
2
Faculty of Environmental and Mechanical Engineering, Poznań University of Life Sciences, Poland
3
Faculty of Technical Sciences
Department of Vehicles and Machines, University of Warmia and Mazury in Olsztyn, Poland
4
Department of Automation and Robotic Systems, National University of Life and Environmental Sciences of Ukraine, Ukraine
5
Faculty of Agriculture, Horticulture and Biotechnology, Department of Agronomy, Poznań University of Life Sciences, Poland
Submission date: 2025-11-26
Final revision date: 2026-01-29
Acceptance date: 2026-01-29
Online publication date: 2026-02-18
Corresponding author
Karol Durczak Durczak
Faculty of Environmental and Mechanical Engineering, Department of Biosystems Engineering, Poznań University of Life Sciences, Wojska Polskiego 50, 60-627, Poznań, Poland
Faculty of Environmental and Mechanical Engineering, Department of Biosystems Engineering, Poznań University of Life Sciences, Wojska Polskiego 50, 60-627, Poznań, Poland
KEYWORDS
TOPICS
ABSTRACT
This study presents a hybrid diagnostic approach combining the Continuous Wavelet Transform (CWT) and Convolutional Neural Networks (CNN) for assessing screw wear in a single-screw extruder operating under controlled conditions. Electrical current signals from the drive motor were analyzed to identify changes associated with the degradation of working components. CWT scalograms were used as time–frequency inputs for a CNN classifier, achieving a classification accuracy of 92.3% in distinguishing between new and worn screw states. Principal Component Analysis (PCA) confirmed clear separability of operating conditions, with the first two components explaining over 99% of the total variance. The results indicate that electrical signals contain diagnostically relevant information and that their combined analysis using CWT and CNN enables automated, non-invasive condition assessment with potential applicability in predictive maintenance systems without additional sensors.
REFERENCES (20)
1.
Mościcki L., Mitrus M. (2011). Extrusion-Cooking of Starch. In: Mościcki L. (ed.) Extrusion-Cooking Techniques. Wiley-VCH. ISBN 9783527634088.
2.
Janssen L.P.B.M., Mościcki L., Mitrus M. (2002). Energy aspects in food extrusion-cooking. International Agrophysics, 16, 191–196.
3.
Ekielski A., Osiak J. (2003). Wpływ stopnia zużycia elementów ekstrudera na wybrane parametry ekstruzji. Inżynieria Rolnicza, 7(49), 39–46.
4.
Ekielski A., Żelaziński T., Durczak K. (2017). The use of wavelet analysis to assess the degree of wear of working elements of food extruders. Eksploatacja i Niezawodnosc – Maintenance and Reliability, 19(4), 560–564. https://doi.org/10.17531/ein.2....
5.
Żelaziński T., Ekielski A., Siwek A., Durczak K. (2018). By-products from brewery industry as attractive additives to the extruded cereals food. Carpathian Journal of Food Science and Technology, 10(5), 83–97.
6.
Leonard W., Zhang P., Ying D., Fang Z. (2020). Application of extrusion technology in plant food processing by-products: An overview. Comprehensive Reviews in Food Science and Food Safety, 19(1), 218–246.
7.
Ekielski A. (2006). Analiza energetyczna procesu ekstruzji z wykorzystaniem metod empirycznych. Inżynieria Rolnicza, 9(84), 45–52.
8.
Danielak M., Witaszek K., Ekielski A., Żelaziński T., Dudnyk A., Durczak K. (2023). Wear detection of extruder elements based on current signature by means of a continuous wavelet transform. Processes, 11(11), 3240. https://doi.org/10.3390/pr1111....
9.
LeCun Y., Bengio Y., Hinton G. (2015). Deep learning. Nature, 521, 436–444. https://doi.org/10.1038/nature....
10.
Zhang J., Kong X., Cheng L., Qi H., Yu M. (2023). Intelligent fault diagnosis of rolling bearings based on continuous wavelet transform–multiscale feature fusion and improved channel attention mechanism. Eksploatacja i Niezawodnosc – Maintenance and Reliability, 25(1). https://doi.org/10.17531/ein.2....
11.
Polychronopoulos N.D., Moustris K., Karakasidis T., et al. (2025). Machine learning for screw design in single-screw extrusion. Polymer Engineering and Science, 1–17. https://doi.org/10.1002/pen.27....
12.
Delvar E., Oliveira I., Brito M.S.C.A., Silva C.G., Santamaria-Echart A., Barreiro M.-F., Santos R.J. (2025). Literature Review on Single and Twin-Screw Extruders Design for Polymerization Using CFD Simulation. Fluids, 10(1), 9. https://doi.org/10.3390/fluids....
13.
Pakhomov V., Braginets S., Rudoy D. (2020). Effect of extrusion on nutritional composition of feed containing mussel meat: Experimental study results. Engineering for Rural Development, 19, 306–312. https://doi.org/10.22616/ERDev....
14.
Lachuga Y., Pakhomov V., Braginets S., Bakhchevnikov O., Rudoy D., Maltseva T. (2021). Study of extruded feed from wheat ears during early harvest. IOP Conference Series: Earth and Environmental Science, 937, 032003. https://doi.org/10.1088/1755-1....
15.
Zhang G., Sun Z., Wang T., Liu L., Zhao J., Zhang Z. (2024). Effects of extrusion on the available energy and nutrient digestibility of soybean meal and its application in weaned piglets. Animals, 14(23), 3355. https://doi.org/10.3390/ani142....
16.
Shah R., Sridharan N.V., Mahanta T.K., Muniyappa A., Vaithiyanathan S., Ramteke S.M., Marian M. (2023). Ensemble deep learning for wear particle image analysis. Lubricants, 11(11), 461. https://doi.org/10.3390/lubric....
17.
Xue Z., Yang J., Chen L. (2023). Tool wear state recognition based on one-dimensional convolutional neural networks with attention mechanism. Sensors, 23(9), 4321. https://doi.org/10.3390/s23094....
18.
Yang P., Wang H., Zhu M., Ma Y. (2020). Evaluation of extrusion temperatures, pelleting parameters, and vitamin forms on vitamin stability in feed. Animals, 10, 894. https://doi.org/10.3390/ani100....
19.
Deokar S., Lin J., Xu Y. (2025). Hybrid CNN–LSTM architecture for mechanical fault detection in rotating machinery. Journal of Industrial Information Integration, 49, 101017. https://doi.org/10.1016/j.jii.....
20.
Cho J.H., Park J.W., Lee B.J., Kim K.W., Hur S.W. (2023). Low extrusion pressure and small feed particle size improve the growth performance and digestive physiology of rockfish. Aquaculture, 566, 739199. https://doi.org/10.1016/j.aqua....
Share
RELATED ARTICLE
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
