An Experimental Comparative Evaluation of Machine Learning Techniques for Motor Fault Diagnosis Under Various Operating Conditions

Martin-Diaz, Ignacio; Moriñigo-Sotelo, Daniel; Duque-Pérez, Óscar; Romero-Troncoso, René de Jesús

doi:10.1109/tia.2018.2801863

Cited by 82 publications

(57 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) RQA + SVM [19]: independent use of RQA for feature learning and optimal binary tree SVM for classification (2) LSTM: independent use of the proposed LSTM architecture on raw data 0.20 0.00 0.00 0.30 0.00 0.00 0.00 0.00 0.00 100.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 100.00 0.00 0.00 0.30 0.70 0.00 0.00 0.50 0.00 98.50 0.00 0.00 0.00 0.00 100.00 0.00 0.00 0.00 (3) MLP [7]: multilayer neural network on statistical features (4) CNN [32]: one-dimension CNN on raw data (5) SIFT + CNN [13]: short-time Fourier transform for feature learning and CNN for classification (6) CDFL [14]: convolutional discriminative learning of a BP network…”

Section: Performance Comparisonsmentioning

confidence: 99%

“…Recently, owing to the significant development of the computing ability [6], massive efforts for motor fault diagnosis have been devoted to the data-driven approaches. For instance, Diazet provided an experimental comparative evaluation of various classifiers including k-NN, Bagging, AdaBoost, and SVM for motor fault detection [7]. Zhang presented a motor fault identification method through sparse representation and achieved good robustness to noise [8].…”

Section: Introductionmentioning

confidence: 99%

“…However, the abovementioned methods still have some shortcomings. e performances of the traditional methods [7][8][9] generally depend on the manual feature extraction techniques, which may be incapable of fully exploiting the raw data and may omit some important information. Besides, they have limited adaptability when facing the new diagnosis issues or application objects.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Xiao

Huang

Qin

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

Motor fault diagnosis has gained much attention from academic research and industry to guarantee motor reliability. Generally, there exist two major approaches in the feature engineering for motor fault diagnosis: (1) traditional feature learning, which heavily depends on manual feature extraction, is often unable to discover the important underlying representations of faulty motors; (2) state-of-the-art deep learning techniques, which have somewhat improved diagnostic performance, while the intrinsic characteristics of black box and the lack of domain expertise have limited the further improvement. To cover those shortcomings, in this paper, two manual feature learning approaches are embedded into a deep learning algorithm, and thus, a novel fault diagnosis framework is proposed for three-phase induction motors with a hybrid feature learning method, which combines empirical statistical parameters, recurrence quantification analysis (RQA) and long short-term memory (LSTM) neural network. In addition, weighted batch normalization (BN), a modification of BN, is designed to evaluate the contributions of the three feature learning approaches. The proposed method was experimentally demonstrated by carrying out the tests of 8 induction motors with 8 different faulty types. Results show that compared with other popular intelligent diagnosis methods, the proposed method achieves the highest diagnostic accuracy in both the original dataset and the noised dataset. It also verifies that RQA can play a bigger role in real-world applications for its excellent performance in dealing with the noised signals.

show abstract

Section: Performance Comparisonsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Xiao

Huang

Qin

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…Furthermore, the fault diagnosis method based on the support vector machine (SVM) is employed in [37,38] for motor faults. Moreover, classifiers based on C4.5, K-nearest neighbors (k-NNs), and multilayer perceptron (MLP) are discussed in [39,40] to recognize faults.…”

Section: Introductionmentioning

confidence: 99%

Characteristics Analysis and Measurement of Inverter-Fed Induction Motors for Stator and Rotor Fault Detection

et al. 2019

View full text Add to dashboard Cite

Inverter-fed induction motors (IMs) contain a serious of current harmonics, which become severer under stator and rotor faults. The resultant fault components in the currents affect the monitoring of the motor status. With this background, the fault components in the electromagnetic torque under stator faults considering harmonics are derived in this paper, and the fault components in current harmonics under rotor faults are analyzed. More importantly, the monitoring based on the fault characteristics (both in the torque and current) is proposed to provide reliable stator and rotor fault diagnosis. Specifically, the fault components induced by stator faults in the electromagnetic torque are discussed in this paper, and then, fault components are characterized in the torque spectrum to identify stator faults. To achieve so, a full-order flux observer is adopted to calculate the torque. On the other hand, under rotor faults, the sidebands caused by time and space harmonics in the current are analyzed and exploited to recognize rotor faults, being the motor current signature analysis (MCSA). Experimental tests are performed on an inverter-fed 2.2 kW/380 V/50 Hz IM, which verifies the analysis and the effectiveness of the proposed fault diagnosis methods of inverter-fed IMs.

show abstract

“…Commonly, the diagnosis and predictions is calculated through current signature analysis (MCSA) [50,51], i.e., examining the output signals of the motor stator's current while running on a steady-state operating mood [52][53][54][55][56]. MCSA analyses the timefrequency decomposition of the current signals or by faults' frequencies in the frequency domain.…”

Section: Introductionmentioning

confidence: 99%

Multi-Label Classification for Fault Diagnosis of Rotating Electrical Machines

Dineva¹,

Mosavi²,

Gyimesi³

et al. 2019

Preprint

View full text Add to dashboard Cite

Primary importance is devoted to Fault Detection and Diagnosis (FDI) of electrical machine and drive systems in modern industrial automation. The widespread use of Machine Learning techniques has made it possible to replace traditional motor fault detection techniques with more efficient solutions that are capable of early fault recognition by using large amounts of sensory data. However, the detection of concurrent failures is still a challenge in the presence of disturbing noises or when the multiple faults cause overlapping features. The contribution of this work is to propose a novel methodology using multi-label classification method for simultaneously diagnosing multiple faults and evaluating the fault severity under noisy conditions. Performance of various multi-label classification models are compared. Current and vibration signals are acquired under normal and fault conditions. The applicability of the proposed method is experimentally validated under diverse fault conditions such as unbalance and misalignment.

show abstract

An Experimental Comparative Evaluation of Machine Learning Techniques for Motor Fault Diagnosis Under Various Operating Conditions

Cited by 82 publications

References 21 publications

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Characteristics Analysis and Measurement of Inverter-Fed Induction Motors for Stator and Rotor Fault Detection

Multi-Label Classification for Fault Diagnosis of Rotating Electrical Machines

Contact Info

Product

Resources

About