Radyal Pompalarda Kavitasyon Koşulları Altında ENPY, Gürültü ve Titreşim Düzeylerinin Makine Öğrenimine Dayalı Tahmini

Öz

Kavitasyon, pompa performansını olumsuz etkileyen ve pompa ömrünü azaltan fiziksel bir olgudur ve pompa elemanlarında aşınmaya neden olabilir. Kavitasyon sürecinin başlangıcını ve tam gelişimini belirlemek için çeşitli mühendislik yöntemleri geliştirilmiştir. Bunlardan biri, sabit bir debi hızında toplam basınç düşüşü (%3 Hm) ile emmedeki net pozitif yük (ENPY) değerinin belirlenmesidir. Tarım sulaması ve endüstride yaygın olarak kullanılan radyal pompalarda, kavitasyon koşulları Hm-Q eğrisinde ani bir düşüşe yol açarak %3 Hm değer düşüşünü tespit etmeyi zorlaştırır. Bu çalışma, yapay sinir ağları (ANN), destek vektör makineleri (SVM) ve karar ağacı regresyonu (DTR) olmak üzere üç makine öğrenmesi modeli kullanarak ENPY, gürültü ve titreşim seviyelerini modellenmesiyle literatürdeki diğer çalışmalardan farklılık gösterir. En iyi performans gösteren model, %3 Hm düşüşüne karşılık gelen ENPY, gürültü ve titreşim seviyelerini tahmin eder. Bu çalışma, yatay şaftlı santrifüj pompada farklı debi hızlarında ENPY değerlerinin belirlendiği ve bu ENPY değerleri için titreşim ve gürültü seviyelerinin ölçüldüğü bir çalışmadır. ENPY, gürültü ve titreşim seviyeleri için ANN, SVM ve DTR modelleri oluşturulmuştur. Bu modellerin performansları kök ortalama kare hatası (KOKH), ortalama mutlak hata (OMH) ve ortalama mutlak yüzde hatası (OMYH) gibi kriterler kullanılarak değerlendirildi. Ayrıca Taylor ve hata kutu diyagramları oluşturulmuştur. ANN modeli ve DTR, ENPY değerleri için yüksek doğrulukta tahminler sağlamıştır (sırasıyla R2 = 0.86 ve R2 = 0.8). ANN modeli, gürültü ve titreşim seviyeleri için en iyi tahmin performansını sağlamıştır. Pompa Hm değerindeki %3 düşüş seviyesini ANN modeline harici veri girişi olarak kullanarak, ENPY3, gürültü ve titreşim seviyeleri belirlenmiştir. ANN modelleri, özellikle radyal akış pompalarında manometrik yükseklik değerlerinde %3'lük azalmaların tespit edilmesinin zor olduğu durumlarda, ENPY3, gürültü ve titreşim seviyelerini belirlemek için etkili bir şekilde kullanılabilir.

Anahtar Kelimeler

• Santrifüj pompalar
• Emmedeki net pozitif yük (ENPY)
• Titreşim
• Gürültü
• Makine öğrenimi

Machine Learning-Based Prediction of NPSH, Noise, and Vibration Levels in Radial Pumps Under Cavitation Conditions

Öz

Cavitation, a physical phenomenon that detrimentally affects pump performance and reduces pump life, can cause wear on pump elements. Various engineering methods have been developed to identify the initiation and full development of the cavitation process. One such method is the determination of the net positive suction head (NPSH) through a 3% decrease in total head (Hm) at a constant flow rate. In radial pumps, commonly used in agricultural irrigation and industry, cavitation conditions result in a sudden drop in the Hm-Q curve, making it challenging to detect the 3% Hm value drop. This study differs from others in the literature by modelling NPSH, noise, and vibration levels using three machine learning models, specifically artificial neural networks (ANN), support vector machines (SVM), and decision tree regression (DTR). The best-performing model predicts NPSH, noise, and vibration levels corresponding to a 3% decrease in Hm level. The present study determined the NPSH values of a horizontal shaft centrifugal pump at different flow rates and constant operating speed, and the vibration and noise levels were measured for these NPSH values. For each of the NPSH, noise, and vibration levels, ANN, SVM and DTR models were created. The performances of these models were evaluated using criteria such as root mean squared error (RMSE), Mean Absolute Error (MAE) and mean absolute percentage error (MAPE). In addition, Taylor and error box diagrams were created. The ANN model and DTR yielded high accuracy predictions for NPSH values (R2 = 0.86 and R2 = 0.8, respectively). The ANN model provided the best prediction performance for noise and vibration levels. By entering the level of 3% drop in the Hm value of the pump as external data input to the ANN model, NPSH3, noise, and vibration levels were determined. The ANN models can be effectively employed to determine NPSH3, noise, and vibration levels, particularly in radial flow pumps, where detecting 3% reductions in manometric height value is challenging.

Anahtar Kelimeler

• Centrifugal pumps
• Net positive suction head (NPSH)
• Vibration
• Noise
• Machine learning

Kaynakça

1. Al-Obaidi, A. and Towsyfyan, H. (2019). An experimental study on vibration signatures for detecting incipient cavitation in centrifugal pumps based on envelope spectrum analysis. Journal of Applied Fluid Mechanics, 12(6), 2057-2067.
2. Anonymous (2002). Rotodynamic Pumps-Hydraulic Performance Acceptance Tests, Class 1 and Class 2. In (Vol. TS EN ISO 9906). Turkish Standards Institute: Ankara.
3. Arendra, A., Akhmad, S. and Winarso, K. (2020). Investigating pump cavitation based on audio sound signature recognition using artificial neural network. Paper presented at the Journal of Physics: Conference Series (Vol. 1569, No. 3, p. 032044).
4. Bayram, S. and Çıtakoğlu, H. (2023). Modeling monthly reference evapotranspiration process in Turkey: application of machine learning methods. Environmental Monitoring and Assessment, 195(1): 67.
5. Bordoloi, D. and Tiwari, R. (2017). Identification of suction flow blockages and casing cavitations in centrifugal pumps by optimal support vector machine techniques. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 39(8): 2957-2968.
6. Brennen, C. E. (2011). Hydrodynamics of pumps: Cambridge University Press. Čdina, M. (2003). Detection of cavitation phenomenon in a centrifugal pump using audible sound. Mechanical Systems and Signal Processing, 17(6): 1335-1347.
7. Cho, J. H. (2020). Detection of smoking in indoor environment using machine learning. Applied Sciences, 10(24): 8912. https://doi.org/10.3390/app10248912
8. Coutier-Delgosha, O., Fortes-Patella, R., Reboud, J.-L., Hofmann, M. and Stoffel, B. (2003). Experimental and numerical studies in a centrifugal pump with two-dimensional curved blades in cavitating condition. Journal of. Fluids Engineering., 125(6): 970-978.

9. Cucit, V., Burlon, F., Fenu, G., Furlanetto, R., Pellegrino, F. A. and Simonato, M. (2018). A control system for preventing cavitation of centrifugal pumps. Energy Procedia, 148: 242-249.
10. Čudina, M. and Prezelj, J. (2008). Use of audible sound for safe operation of kinetic pumps. International Journal of Mechanical Sciences, 50(9): 1335-1343.
11. Čudina, M. and Prezelj, J. (2009). Detection of cavitation in operation of kinetic pumps. Use of discrete frequency tone in audible spectra. Applied Acoustics, 70(4): 540-546.
12. Çalışır, S., Aydım, C. and Mengeş, H. O. (2006a). Determination of Vibration Velocity and Noise Level in Deep Well Pumping Plants. Selcuk Journal of Agriculture and Food Sciences, 20(38): 49-54.
13. Çalışır, S., Eryılmaz, T., Hacıseferoğulları, H. and Mengeş, H. O. (2006b). Vibration of Centrifugal Pumps. Journal of Agricultural Machinery Science, 2(4): 345-351.
14. Çalışır, S., Eryılmaz, T., Hacıseferoğulları, H. and Mengeş, H. O. (2007). Noise in centrifugal pumps. Journal of Agricultural Machinery Science, 3(2): 105-110.
15. Delale, C. F., Ayder, E., Pasinlioğlu, Ş. and Morkoyun, U. (2020). Improvement of Simplified Cavitation Models for the Determination of Centrifugal Pump Cavitation Performance Characteristics. Tübitak (117MO72) Project Report (In Turkish).
16. Demir, V. (2022). Enhancing monthly lake levels forecasting using heuristic regression techniques with periodicity data component: application of Lake Michigan. Theoretical and Applied Climatology, 148(3-4): 915-929.
17. Dong, L., Zhao, Y. and Dai, C. (2019). Detection of inception cavitation in centrifugal pump by fluid-borne noise diagnostic. Shock and Vibration, 2019.
18. Durdu, A., Celtek, S. A. and Orhan, N. (2021). Detection of Vortex Cavitation With The Method Adaptive Neural Fuzzy Networks in the Deep Well Pumps. Journal of Tekirdag Agricultural Faculty, 18(4): 613-624.
19. Dzhurabekov, A., Rustamov, S., Nasyrova, N. and Rashidov, J. (2021). Erosion processes during non-stationary cavitation of irrigation pumps. Paper presented at the E3S Web of Conferences, (Vol. 264, p. 03016). EDP Sciences.
20. El Guabassi, I., Bousalem, Z., Marah, R. and Qazdar, A. (2021). A Recommender System for Predicting Students' Admission to a Graduate Program using Machine Learning Algorithms. International Association of Online Engineering, 17(02): 135-147. https://doi.org/10.3991/ijoe.v17i02.20049
21. Eryılmaz, T. (2004). Determination of cavitation characteristics of centrifugal pumps used in ırrigation. (MSc. Thesis) Selçuk University Institute of Science and Technology, Department of Agricultural Machinery, Konya, Türkiye.
22. Escaler, X., Egusquiza, E., Farhat, M., Avellan, F. and Coussirat, M. (2006). Detection of cavitation in hydraulic turbines. Mechanical Systems and Signal Processing, 20(4): 983-1007.
23. Geng, J., Gan, W., Xu, J., Yang, R. and Wang, S. (2020). Support vector machine regression (SVR)-based nonlinear modeling of radiometric transforming relation for the coarse-resolution data-referenced relative radiometric normalization (RRN). Geo-spatial Information Science, 23(3): 237-247. https://doi.org/10.1080/10095020.2020.1785958
24. Gültepe, Y. (2019). A Comparative Assessment on Air Pollution Estimation by Machine Learning Algorithms. European Journal of Science and Technology (16): 8-15. https://doi.org/10.31590/ejosat.530347
25. Güven, A. (2022). Prediction of air pollution with machine learning methods. (MSc Thesis). Bursa Uludağ University, Graduate School of Natural and Applied Sciences Department of Industrial Engineering, Bursa, Turkey.
26. Hanson, B., Weigand, C. and Orloff, S. (1996). Performance of electric irrigation pumping plants using variable frequency drives. Journal of irrigation and drainage engineering, 122(3): 179-182.
27. Jayalakshmi, T. and Santhakumaran, A. (2011). Statistical normalization and back propagation for classification. International Journal of Computer Theory and Engineering, 3(1): 1793-8201. https://doi.org/10.7763/IJCTE.2011.V3.288
28. Kan, K., Binama, M., Chen, H., Zheng, Y., Zhou, D., Su, W. and Muhirwa, A. (2022). Pump as turbine cavitation performance for both conventional and reverse operating modes: A review. Renewable and Sustainable Energy Reviews, 168: 112786.
29. Kaya, M. (2020). Computation and ımprovement of the cavitation performance of radial flow pumps (Ph.D. Thesis). İstanbul Teknik University, Institute Sciences, İstanbul, Turkey.
30. Keskin. (2002). Irrigation Machines. Ankara University Publications, Publication No: 1524.
31. Liakos, K. G., Busato, P., Moshou, D., Pearson, S. and Bochtis, D. (2018). Machine learning in agriculture: A review. Sensors, 18(8): 2674. https://doi.org/10.3390/s18082674
32. Loh, W. Y. (2011). Classification and regression trees. Wiley interdisciplinary reviews: data mining and knowledge discovery, 1(1): 14-23. https://doi.org/10.1002/widm.8
33. Matloobi, S. M. and Riahi, M. (2021). Identification of cavitation in centrifugal pump by artificial immune network. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, 235(6): 2271-2280.
34. Neill, G., Reuben, R. L., Sandford, P., Brown, E. and Steel, J. A. (1997). Detection of incipient cavitation in pumps using acoustic emission. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, 211(4): 267-277.
35. Panda, A. K., Rapur, J. S. and Tiwari, R. (2018). Prediction of flow blockages and impending cavitation in centrifugal pumps using Support Vector Machine (SVM) algorithms based on vibration measurements. Measurement, 130: 44-56.
36. Pattnaik, P., Sharma, A., Choudhary, M., Singh, V., Agarwal, P. and Kukshal, V. (2021). Role of machine learning in the field of Fiber reinforced polymer composites: A preliminary discussion. Materials Today: Proceedings, 44: 4703-4708. https://doi.org/10.1016/j.matpr.2020.11.026
37. Pekel, E. (2020). Estimation of soil moisture using decision tree regression. Theoretical and Applied Climatology, 139(3): 1111-1119. https://doi.org/10.1007/s00704-019-03048-8
38. Sahdev, M. (2005). Centrifugal Pumps: Basic concepts of operation, maintenance and trouble shooting, Part I. Chem. Eng. Resourc.[Online]. Available: www. cheresources. com.
39. Salem, A. M., Yakoot, M. S. and Mahmoud, O. (2022). Addressing Diverse Petroleum Industry Problems Using Machine Learning Techniques: Literary Methodology─ Spotlight on Predicting Well Integrity Failures. ACS omega, 7(3): 2504-2519. https://doi.org/10.1021/acsomega.1c05658
40. Salvadori, S., Cappelletti, A., Montomoli, F., Nicchio, A. and Martelli, F. (2015). Experimental and numerical evaluation of the NPSHr Curve of an industrial centrifugal pump. ETC 2015-011.
41. Shahhosseini, M., Martinez-Feria, R. A., Hu, G. and Archontoulis, S. V. (2019). Maize yield and nitrate loss prediction with machine learning algorithms. Environmental Research Letters, 14(12): 124026. https://doi.org/10.1088/1748-9326/ab5268
42. Shin, J.-H. and Cho, Y.-H. (2021). Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems. Applied Sciences, 12(1), 362. https://doi.org/10.3390/app12010362
43. Sun, H., Si, Q., Chen, N. and Yuan, S. (2020). HHT-based feature extraction of pump operation instability under cavitation conditions through motor current signal analysis. Mechanical Systems and Signal Processing, 139: 106613.
44. Takeda, H., Farsiu, S. and Milanfar, P. (2007). Kernel regression for image processing and reconstruction. IEEE Transactions on image processing, 16(2): 349-366. https://doi.org/10.1109/TIP.2006.888330
45. Wang, W., Li, Y., Osman, M. K., Yuan, S., Zhang, B. and Liu, J. (2020). Multi-condition optimization of cavitation performance on a double-suction centrifugal pump based on ANN and NSGA-II. Processes, 8(9): 1124.
46. Wang, W., Osman, M. K., Pei, J., Gan, X. and Yin, T. (2019). Artificial neural networks approach for a multi-objective cavitation optimization design in a double-suction centrifugal pump. Processes, 7(5): 246.
47. Yong, W., Lin, L. H., Qi, Y. S., Gao, T. M. and Kai, W. (2009). Prediction Research on Cavitation Performance for Centrifugal Pumps. IEEE International Conference on Intelligent Computing and Intelligent Systems, 137-140, Shanghai, China.
48. Yüksel, E. and Eker, B. (2009). Determination of possible wear on the centrifugal pump wheel used for agricultural irrigation purposes. Journal of Tekirdag Agricultural Faculty, 6(2): 203-214.