The Use of Deep Learning Methods in Diagnosing Rotating Machines Operating in Variable Conditions
Abstract
:1. Introduction
2. Materials and Methods
2.1. Testing Facility Description
2.2. Diagnostic Experiment
2.3. The Method of Determining Diagnostic Parameters
2.4. Using the Artificial Neural Network for Condition Assessment
- output shaft rotational speed;
- oil temperature;
- the current drawn by the motor;
- amplitude values of order k in the x-axis;
- z-axis amplitude values of the order k;
- a 30-neuron layer with RELU activation function and a drop-out layer with a drop rate of 20%;
- a 20-neuron layer with RELU activation function and a drop-out layer with a drop rate of 10%.
- using drop-out layers in the network architecture and randomizing the network by randomly deactivating neurons during learning;
- the learning set was randomly divided into a learning set and a validation set (which the network did not formally use for learning).
2.5. Verification of Artificial Neural Network Functionality
3. Results and Discussion
3.1. Results of the Order Analysis
3.2. Results Obtained from Deep Learning Neural Networks
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Pawlik, P.; Lepiarczyk, D.; Dudek, R.; Ottewill, J.R.; Rzeszuciński, P.; Wójcik, M.; Tkaczyk, A. Vibroacoustic Study of Powertrains Operated in Changing Conditions by Means of Order Tracking Analysis. Eksploat. i Niezawodn. Maint. Reliab. 2016, 18, 606–612. [Google Scholar] [CrossRef]
- Randall, R.B. Frequency Analysis; Bruel & Kjær: Nærum, Denmark, 1987. [Google Scholar]
- Wang, W.; Johnson, K.; Galati, T. Vibration Analysis of Planet Gear Bore-Rim Failure Using Enhanced Planet Time Synchronous Averaging. Eng. Fail. Anal. 2020, 117, 104942. [Google Scholar] [CrossRef]
- Zhang, S.; Tang, J. Integrating Angle-Frequency Domain Synchronous Averaging Technique with Feature Extraction for Gear Fault Diagnosis. Mech. Syst. Signal Process. 2018, 99, 711–729. [Google Scholar] [CrossRef]
- Cioch, W.; Knapik, O.; Leśkow, J. Finding a Frequency Signature for a Cyclostationary Signal with Applications to Wheel Bearing Diagnostics. Mech. Syst. Signal Process. 2013, 38, 55–64. [Google Scholar] [CrossRef]
- Cempel, C. Application of TRIZ Approach to Machine Vibration Condition Monitoring Problems. Mech. Syst. Signal Process. 2013, 41, 328–334. [Google Scholar] [CrossRef]
- Zimroz, R.; Bartkowiak, A. Two Simple Multivariate Procedures for Monitoring Planetary Gearboxes in Non-Stationary Operating Conditions. Mech. Syst. Signal Process. 2013, 38, 237–247. [Google Scholar] [CrossRef]
- Peruń, G.; Łazarz, B. Modelling of Power Transmission Systems for Design Optimization and Diagnostics of Gear in Operational Conditions. Solid State Phenom. 2014, 210, 108–114. [Google Scholar] [CrossRef]
- Pawlik, P. The Diagnostic Method of Rolling Bearing in Planetary Gearbox Operating at Variable Load. Diagnostyka 2019, 20, 69–77. [Google Scholar] [CrossRef]
- Pawlik, P. The Use of the Acoustic Signal to Diagnose Machines Operated Under Variable Load. Arch. Acoust. 2020, 45, 263–270. [Google Scholar] [CrossRef]
- Bartelmus, W.; Zimroz, R. A New Feature for Monitoring the Condition of Gearboxes in Non-Stationary Operating Conditions. Mech. Syst. Signal Process. 2009, 23, 1528–1534. [Google Scholar] [CrossRef]
- Lipinski, P.; Brzychczy, E.; Zimroz, R. Decision Tree-Based Classification for Planetary Gearboxes’ Condition Monitoring with the Use of Vibration Data in Multidimensional Symptom Space. Sensors 2020, 20, 5979. [Google Scholar] [CrossRef]
- Popiołek, K.; Pawlik, P. Diagnosing the Technical Condition of Planetary Gearbox Using the Artificial Neural Network Based on Analysis of Non-Stationary Signals. Diagnostyka 2016, 17, 57–64. [Google Scholar]
- Dabrowski, D. Condition Monitoring of Planetary Gearbox by Hardware Implementation of Artificial Neural Networks. Meas. J. Int. Meas. Confed. 2016, 91, 295–308. [Google Scholar] [CrossRef]
- Łazarz, B.; Wojnar, G.; Czech, P. Early Fault Detection of Toothed Gear in Exploitation Conditions. Eksploat. i Niezawodn. Maint. Reliab. 2011, 1, 68–77. [Google Scholar]
- Wang, K.; Zhao, W.; Xu, A.; Zeng, P.; Yang, S. One-Dimensional Multi-Scale Domain Adaptive Network for Bearing-Fault Diagnosis under Varying Working Conditions. Sensors 2020, 20, 6039. [Google Scholar] [CrossRef]
- Hasan, M.J.; Sohaib, M.; Kim, J.M. A Multitask-Aided Transfer Learning-Based Diagnostic Framework for Bearings under Inconsistent Working Conditions. Sensors 2020, 20, 7205. [Google Scholar] [CrossRef]
- Zhang, K.; Wang, J.; Shi, H.; Zhang, X.; Tang, Y. A Fault Diagnosis Method Based on Improved Convolutional Neural Network for Bearings under Variable Working Conditions. Measurement 2021, 182, 109749. [Google Scholar] [CrossRef]
- Azamfar, M.; Singh, J.; Bravo-Imaz, I.; Lee, J. Multisensor Data Fusion for Gearbox Fault Diagnosis Using 2-D Convolutional Neural Network and Motor Current Signature Analysis. Mech. Syst. Signal Process. 2020, 144, 106861. [Google Scholar] [CrossRef]
- Li, F.; Pang, X.; Yang, Z. Motor Current Signal Analysis Using Deep Neural Networks for Planetary Gear Fault Diagnosis. Meas. J. Int. Meas. Confed. 2019, 145, 45–54. [Google Scholar] [CrossRef]
- Han, T.; Yang, B.S.; Choi, W.H.; Kim, J.S. Fault Diagnosis System of Induction Motors Based on Neural Network and Genetic Algorithm Using Stator Current Signals. Int. J. Rotating Mach. 2006, 2006. [Google Scholar] [CrossRef] [Green Version]
- Batko, W.; Pawlik, P.; Cioch, W.; Dąbrowski, D. Method and System for Monitoring and Diagnosis of Gear, Especially Gear Wheel Drive Bucket Wheel Excavator. Patent PL 225381 B1 2013, 28 April 2017. [Google Scholar]
- Combet, F.; Zimroz, R. A New Method for the Estimation of the Instantaneous Speed Relative Fluctuation in a Vibration Signal Based on the Short Time Scale Transform. Mech. Syst. Signal Process. 2009, 23, 1382–1397. [Google Scholar] [CrossRef]
- National Instruments Corporation. LabVIEW, Order Analysis Toolkit User Manual; National Instruments Corporation: Austin, TX, USA, 2005. [Google Scholar]
- Pawlik, P. Single-Number Statistical Parameters in the Assessment of the Technical Condition of Machines Operating under Variable Load. Eksploat. Niezawodn. Maint. Reliab. 2019, 21, 164–169. [Google Scholar] [CrossRef]
- Lees, A.W. Misalignment in Rigidly Coupled Rotors. J. Sound Vib. 2007, 305, 261–271. [Google Scholar] [CrossRef]
- Jesse, S.; Hines, J.W.; Kuropatwinski, J.; Edmondson, A.; Carley, T.G. Motor Shaft Misalignment Versus Efficiency Analysis; The University of Tennessee: Knoxville, TN, USA, 1970. [Google Scholar]
- Qi, X.; Yuan, Z.; Han, X. Diagnosis of Misalignment Faults by Tacholess Order Tracking Analysis and RBF Networks. Neurocomputing 2015, 169, 439–448. [Google Scholar] [CrossRef]
- Kłosowski, G.; Rymarczyk, T.; Cieplak, T.; Niderla, K.; Skowron, Ł. Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography. Sensors 2020, 20, 3324. [Google Scholar] [CrossRef]
- Kłosowski, G.; Rymarczyk, T.; Kania, K.; Świć, A.; Cieplak, T. Maintenance of Industrial Reactors Supported by Deep Learning Driven Ultrasound Tomography. Eksploat. Niezawodn. Maint. Reliab. 2020, 22, 138–147. [Google Scholar] [CrossRef]
- Jeannette, L. Introduction To Neural Networks: Design, Theory, and Applications; California Scientific Software: Oak Grove, CA, USA, 1994. [Google Scholar]
- Bishop, C. Pattern Recognition and Machine Learning; Springer: New York, NY, USA, 2006. [Google Scholar]
- Naitzat, G.; Zhitnikov, A.; Lim, L.-H. Topology of Deep Neural Networks. J. Mach. Learn. Res. 2020, 21, 1–40. [Google Scholar]
- Shang, Y. Resilient Group Consensus in Heterogeneously Robust Networks with Hybrid Dynamics. Math. Methods Appl. Sci. 2021, 44, 1456–1469. [Google Scholar] [CrossRef]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet Classification with Deep Convolutional Neural Networks. Commun. ACM 2017, 60, 84–90. [Google Scholar] [CrossRef]
- Srivastava, N.; Hinton, G.; Krizhevsky, A.; Salakhutdinov, R. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. J. Mach. Learn. Res. 2014, 15, 1929–1958. [Google Scholar] [CrossRef]
- Shang, Y. Couple-Group Consensus of Continuous-Time Multi-Agent Systems under Markovian Switching Topologies. J. Frankl. Inst. 2015, 352, 4826–4844. [Google Scholar] [CrossRef]
- Okada, K. Negative Estimate of Variance-Accounted-for Effect Size: How Often It Is Obtained, and What Happens If It Is Treated as Zero. Behav. Res. Methods 2017, 49, 979–987. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Cohen, J. Statistical Power Analysis for the Behavioral Sciences, 2nd ed.; Lawrence Erlbaum Associates: New York, NY, USA, 1988. [Google Scholar]
Marking | Machine Condition | Measurement Time |
---|---|---|
F0 | Undamaged | 30 min |
F1 | Misaligned | 30 min |
F2 | Unbalanced | 30 min |
F3 | Misaligned and unbalanced | 30 min |
Range of | The Power of the Effect |
---|---|
0–0.1 | No effect |
0.1–0.3 | Little effect |
0.3–0.5 | Moderate effect |
0.5–1.0 | Large effect |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Pawlik, P.; Kania, K.; Przysucha, B. The Use of Deep Learning Methods in Diagnosing Rotating Machines Operating in Variable Conditions. Energies 2021, 14, 4231. https://0-doi-org.brum.beds.ac.uk/10.3390/en14144231
Pawlik P, Kania K, Przysucha B. The Use of Deep Learning Methods in Diagnosing Rotating Machines Operating in Variable Conditions. Energies. 2021; 14(14):4231. https://0-doi-org.brum.beds.ac.uk/10.3390/en14144231
Chicago/Turabian StylePawlik, Paweł, Konrad Kania, and Bartosz Przysucha. 2021. "The Use of Deep Learning Methods in Diagnosing Rotating Machines Operating in Variable Conditions" Energies 14, no. 14: 4231. https://0-doi-org.brum.beds.ac.uk/10.3390/en14144231