Abstract
Condition monitoring of roller element bearing defects has been one of the biggest problems in predictive maintenance since bearing failures may give catastrophic results on the machining operations and may cause downtime. Two of the well-established and widely used methods for bearing fault detection and diagnosis are the artificial neural network (ANN) and adaptive neuro-fuzzy inference systems (ANFIS). For this aim, a multi-staged decision algorithm was developed in this study based on ANN and ANFIS models. Both time and frequency domain parameters extracted from the vibration and current signals were used to train the ANN and ANFIS models, which were then used to detect and diagnose the severity of the bearing fault. Experimental data collected from a shaft-bearing mechanism were used to test the performances of the two schemes. The system was operated under four different speeds, for a brand-new bearing and bearings with artificially introduced local defects with various sizes. The experimental results showed that the proposed scheme is an effective means for detecting and diagnosing bearing faults. Furthermore, the results revealed that ANFIS-based scheme was superior to the ANN-based one especially in diagnosing fault severity.
Similar content being viewed by others
References
Yang H, Mathew J, Ma L (2005) Fault diagnosis of rolling element bearings using basis pursuit. Mech Syst Signal Process 19:341–356
EPRI (1982) Improved motors for utility applications, EL-2678, vol 1, p 1763-1
Konar P, Chattopadhyay P (2011) Bearing fault detection of induction motors using wavelet and support vector machines (SVMs). Appl Soft Comput 11:4203–4211
McFadden PD, Smith JD (1984) Model for the vibration produced by a single point defect in a rolling element bearing. J Sound Vib 96(1):69–82
McFadden PD, Smith JD (1985) The vibration produced by multiple point defects in a rolling element bearing. J Sound Vib 98(2):263–273
McFadden PD, Smith JD (1984) Vibration monitoring of rolling element bearings by high frequency resonance technique—a review. Tribol Int 77:3–10
Ocak H, Loparo KA (2004) Estimation of the running speed and bearing defect frequencies of an induction motor from vibration data. Mech Syst Signal Process 18:515–533
Ertunc HM, Ocak H, Merdoglu M, Bayram S, Cavus M (2011) Vibration analysis based localized bearing fault diagnosis under different load conditions. 12th International Workshop on Research and Education in Mechatronics, REM2011, Kocaeli, Turkey, pp 201–208
McInerny SA, Dai Y (2003) Basic vibration signal processing for bearing fault detection. IEEE Transact Edu 46(1):149–156
Randall RB, Antony J (2011) Rolling element bearing diagnostics—a tutorial. Mech Signal Process 25:485–520
Samanta B, Nataraj C (2008) Prognostics of machine condition using soft computing. Robot Comput Integr Manuf 24:816–823
Chow M, Tipsuwan Y, Hung JC (2000) Neural-network-based motor rolling bearing fault diagnosis. IEEE Transact Ind Electron 47(5):1060–1069
Kowalski CT, Kowalska TO (2003) Neural network application for induction motor fault diagnosis. Math Comput Simul 63:435–448
Goode PV, Chow MY (1995) Using a neural/fuzzy system to extract heuristic knowledge of incipient faults in induction motors: Part I and II. IEEE Trans Indust Electron 42(2):131–146
Goode PV, Chow MY (1993) Adaptation of neural/fuzzy fault detection system. Proc IEEE Conf Decision Control 2:1733–1738
Marichal GN, Artes M, Prada JCG, Casanova O (2011) Extraction of rules for faulty bearing classification by a Neuro-Fuzzy approach. Mech Syst Signal Process 25:2073–2082
Lou X, Loparo K (2004) Bearing fault diagnosis based on wavelet transform and fuzzy inference. Mech Syst Signal Process 18:1077–1095
Ballal MS, Khan ZJ, Suryawanshi HM, Sonolika RL (2007) Adaptive neural fuzzy inference system for the detection of inter-turn insulation and bearing wear faults in induction motor. IEEE Trans Ind Electron 54(1):250–258
Samhouri M, Al-Ghandoor A, Ali SA, Hinti I, Massad W (2009) An intelligent machine condition monitoring system using time-based analysis: neuro-fuzzy versus neural network. Jordan J Mech Ind Eng 3:294–305
Hong-Hee L, Nguyen NT, Kwon JM (2007) Bearing fault diagnosis using fuzzy inference optimized by neural network and genetic algorithm. J Elec Eng Technol 2(3):289–414
Tandon N, Choudhury A (1999) A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings. Tribol Int 32:469–480
Zareive J, Poshtan J (2007) Bearing fault detection using wavelet packet transform of induction motor stator current. Tribol Int 40:763–769
Haykin S (1994) Neural networks—a comprehensive foundation. McMillan, New Jersey
Jang J (1993) ANFIS: adaptive network-based fuzzy inference systems. IEEE Trans Syst Man Cybernet 23:665–685
Acknowledgments
The work presented in this paper is supported by TÜBİTAK under the project code 106M280. Besides, the authors appreciate Dr. Mehmet Ucar and Dr. Abdulkadir Cengiz for invaluable contributions to the study.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ertunc, H.M., Ocak, H. & Aliustaoglu, C. ANN- and ANFIS-based multi-staged decision algorithm for the detection and diagnosis of bearing faults. Neural Comput & Applic 22 (Suppl 1), 435–446 (2013). https://doi.org/10.1007/s00521-012-0912-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-012-0912-7