Simple method of failure detection of rotary machines
More details
Hide details
Pedagogical University in Kraków
Akademia Górniczo-Hutnicza
Andrzej Bielecki   

Pedagogical University in Kraków
Submission date: 2021-06-15
Final revision date: 2021-09-23
Acceptance date: 2021-10-04
Online publication date: 2021-10-13
Publication date: 2021-10-13
Diagnostyka 2021;22(4):17–22
In the paper a simple unsupervised monitoring method of rotary machines is proposed. The method consists of three stages – multi-reference preliminary analysis of the vibration signals, auto-reference preliminary analysis and probabilistic analysis of the signals. The method is tested by using signals from eight machines. The efficiency of the method has been positively verified.
The paper was partially supported from the National Centre for Research and Development (NCBiR) under the grant no. POIR.04.01.04-00-0080/19.
Aggarwal C. Outlier analysis, in: Data Mining, Springer 2015; 237–263.
Bielecki A, Wójcik M. Hybrid system of ART and RBF neural networks for online clustering. Applied Soft Computing. 2017;58:1-10.
Bielecki A, Wojcik M. Hybrid AI system based on ART neural network and mixture of Gausians modules with application to intelligent monitoring of the wind turbine. Applied Soft Computing 2021; 108:107400.
Bielecki A, Barszcz T, Wójcik M, Bielecka M. Hybrid system of ART and RBF neural networks for classification of vibration signals and operational states of wind. Lecture Notes in Artificial Intelligence. 2014;8467:3-11.
Dao PB, Staszewski WJ, Barszcz T, Uhl T. Condition monitoring and fault detection in wind turbines based on cointegration analysis of SCADA system. Renevable Energy 2018; 116: 107-122.
Dinardo G, Fabbiano L, Vacca G. A smart and intuitive machine condition monitoring in the Industry 4.0 scenario. Measurement 2018; 26.
Gan M, Wang C. Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings. Mechanical Systems and Signal Processing. 2016;72-73:92-104.
Górski J, Jabłoński A, Heesh M, Dziendzikowski M, Dworakowski Z. Comparison of novelty detection methods for detection of various rotary machinery faults. Sensors. 2021;21(10):3536;
Jabłoński A. Condition Monitoring Algorithms in MATLAB, Springer 2021.
Randall RB. Vibration-based Condition Monitoring: Industrial, Automotive and Aerospace Applications. John Wiley and Sons, Ltd., 2nd edition 2021.
Rogalewicz M, Sika R. Methodologies of knowledge discovery from data and data mining methods in mechanical engineering. Management and Production Engineering Review 2016; 7(4): 97-108.
Urbanek J, Barszcz T, Jabłoński A. Application of angular-temporal spectrum to exploratory analysis of generalized angular-temporal deterministic signals. Applied Acoustics 2016; 109: 27–36.
Urbanek J, Barszcz T, Strączkiewicz M, Jabłoński A. Normalization of vibration signals generated under highly varying speed and load with application to signal separation. Mechanical Systems and Signal Processing 2017; 82: 13–31.
Wodecki J, Michalak A, Zimroz R, Wyłomańska A. Separation of multiple local-damage-related components from vibration data using Nonnegative Matrix Factorization and multichannel data fusion. Mechanical Systems and Signal Processing 2020; 145:106954.
Wodecki J, Stefaniak P, Obuchowski J, Wyłomańska A, Zimroz R. Combination of principal component analysis and time-frequency representations of multichannel vibration data for gearbox fault detection. Journal of Vibroengineering. 2016;18:2167-2175.