Application of machine learning to classify wear level of multi-piston displacement pump

• Autorzy: Iwaniec Marek , Stojek Jerzy
• Języki publikacji: EN

Abstrakty

EN

This article specifies application of machine learning for the purpose of classifying wear level of multi-piston displacement pump. A diagnostic experiment that was carried out in order to acquire vibration signal matrices from selected locations within the pump body is described herein. Measured signals were subject to time and frequency analysis. Signal attributes related to time and frequency were grouped in a table in accordance with pump wear level. Subsequently, classification models for the pump wear level were developed through application of Matlab package. Assessment of their accuracy was carried out. A selected model was subject to confirmation. The article includes its summary.

Słowa kluczowe

EN

machine learning; diagnostics; signal analysis; multi-piston pump; vibrations

PL

uczenie maszynowe; diagnostyka; analiza sygnałów; pompa wielotłoczkowa; drgania

• Wydawca: Poznan University of Technology. Institute of Applied Mechanics
• Czasopismo: Vibrations in Physical Systems
• Rocznik: 2019
• Tom: Vol. 30, nr 2
• Strony: art. no. 2019222
• Opis fizyczny: Bibliogr. 5 poz., il. kolor., fot., 1 rys., wykr.

Twórcy

autor

Iwaniec Marek

• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Krakow Poland, WIMiR, Department of Process Control

autor

Stojek Jerzy

• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Krakow Poland, WIMiR, Department of Process Control

Bibliografia

• 1. I. Goodfellow, Y. Bengio, A. Courville, Deep learning: systemy uczące się, Wydawnictwo Naukowe PWN SA, 2018.
• 2. J. Kiusalaas, Numerical methods in engineering with MATLAB, Cambridge University Press, 2005.
• 3. W. Łatas, J. Sojek, Dynamic model of axial piston swash-plate pump for diagnostics of wear in elements, The Archive of Mechanical Engineering, 2 (2011) 135 - 155.
• 4. A. Sadowski, E. Miernik, J. Sobol, Length and angle metrology (in Polish), Wydawnictwa Naukowo-Techniczne, Warszawa 1978.
• 5. S. Stryczek, Hydrostatic drive (in Polish), Wydaw. Nauk.-Techniczne, Warszawa 1990.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).