Vibration diagnostics method applied to the hydraulic equipment of technological machines: a case of a gear pump NSh-32A

The conventional system of maintenance and repair of hydraulic systems in technological (or industrial) machines cannot predict sudden failures. Transition to condition-based maintenance requires developing a methodology for real-time detection of defects in parts and assemblies. The condition of hydraulic system components can be more effectively assessed with the vibration analysis. The research aimed to develop and test a methodology for vibration diagnostics of hydraulic systems in technological machines based on the spectral analysis of the spectral power density of a vibration signal. The proposed methodology includes the following stages: obtaining raw data from sensors of the monitored mechanisms; preliminary data processing and feature selection to reduce the dimensionality of the raw data and obtain useful information from the signal; SPM-analysis and calculation of the peak factor and kurtosis; diagnostic classification of faults, defect identification; and real-time data visualization. The authors have developed a software package for automated processing of vibration signals. The analysis based on measuring the spectral density of vibration signal power demonstrated the effectiveness of defect identification under various operating modes. The methodology was tested on an NSh-32A gear-type hydraulic pump at three operating modes: 1000, 1500, and 2000 rpm. Informative features were detected from the vibration signal for diagnosing four pump conditions (serviceable, worn bearing, worn gear, and combined defects) with an accuracy of 90 to 93%. The developed methodology for controlling the hydraulic systems of technological machines can diagnose sudden failures with high accuracy. Future research plans to establish the relationship between the change in vibration acceleration and the volumetric efficiency of the gear pump.

1. Apatenko A.S., Sevryugina N.S. Mechanism for state recognition of structural components of processing machines. Remont. Vosstanovlenie. Modernizatsiya. 2020;12:23-28. (In Russ.)

2. Sevryugina N.S., Apatenko A.S. Integration of digital twin profiles for technological machines in the field of operation and maintenance. Naucho-informatsionnoe obespechenie innovatsionnogo razvitiya APK = Scientific and Information Support for the Innovative Development of the Agro-Industrial Complex: Proceedings of the XV International Scientific and Practical Conference. M.: FSBNI “Rosinformagrotekh”. 2023:84-91. (In Russ.)

3. Stupin O.A., Nekrasov S.I., Kuchinskiy R.G. Vibrodiagnostics as a modern method of monitoring and diagnostics of hydraulic drives of technological machines. International Technical Journal. 2022;5-6:75-86. (In Russ.)

4. Herszberg I., Bannister M.K., Li H.C.H., Tomson R.S. Structural Health Monitoring for advanced composite structures. ICCM International Conferences on Composite Materials. 2007. URL: https://www.researchgate.net/publication/289645207_Structural_health_monitoring_for_advanced_composite_structures

5. Peng Y., Dong M., Zuo M. Current status of machine prognostics in condition – based maintenance: a review. International Journal of Advanced Manufacturing Technology. 2010;50:297-313. https://doi.org/10.1007/s00170-009-2482-0

6. Stupin O.A., Nekrasov S.I. Analysis of vibration signal processing methods for diagnostics of elements of hydrosystems of techno-logical machines. Innovatsii v prirodoobustroystve i zashchite v chrezvychaynykh situatsiyakh = Innovations in Environmental Management and Protection in Emergency Situations: Proceedings of the IX International Scientific and Practical Conference, Saratov, April 27-28, 2022. Saratov: OOO “Amirit”, 2022:371-374. (In Russ.)

7. Saravanan N., Ramachandran K.I. Fault diagnosis of spur bevel gear box using discrete wavelet features and Decision Tree classification. Expert Systems with Applications. 2019;36(5):9564-9573. https://doi.org/10.1016/j.eswa.2008.07.089

8. Unal M., Onat M., Demetgul M., Kucuk H. Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network. Measurement. 2014;58:187-196. https://doi.org/10.1016/j.measurement.2014.08.041

9. Sevryugina N.S., Apatenko A.S. Import substitution and monitoring of workpiece quality. Russian Engineering Research. 2023;43(8):927-933. https://doi.org/10.3103/s1068798x23080294