Generative Oversampling Method for Imbalanced Data on Bearing Fault Detection and Diagnosis

Suh, Sungho; Lee, Haebom; Jo, Jun; Lukowicz, Paul; Lee, Yong Oh

doi:10.3390/app9040746

Cited by 54 publications

(37 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The low volume of the potential target/important customer data (i.e., imbalanced data distribution) is a major challenge in extracting the latent knowledge in banks marketing data [1,3,10]. There is still an insisting need for handling the imbalanced dataset distribution reliably [15][16][17]; commonly used approaches [1,15,16,[18][19][20][21] impose processing overhead or lead to loss of information.…”

Section: Introductionmentioning

confidence: 99%

Business Analytics in Telemarketing: Cost-Sensitive Analysis of Bank Campaigns Using Artificial Neural Networks

et al. 2020

View full text Add to dashboard Cite

The banking industry has been seeking novel ways to leverage database marketing efficiency. However, the nature of bank marketing data hindered the researchers in the process of finding a reliable analytical scheme. Various studies have attempted to improve the performance of Artificial Neural Networks in predicting clients’ intentions but did not resolve the issue of imbalanced data. This research aims at improving the performance of predicting the willingness of bank clients to apply for a term deposit in highly imbalanced datasets. It proposes enhanced Artificial Neural Network models (i.e., cost-sensitive) to mitigate the dramatic effects of highly imbalanced data, without distorting the original data samples. The generated models are evaluated, validated, and consequently compared to different machine-learning models. A real-world telemarketing dataset from a Portuguese bank is used in all the experiments. The best prediction model achieved 79% of geometric mean, and misclassification errors were minimized to 0.192, 0.229 of Type I & Type II Errors, respectively. In summary, an interesting Meta-Cost method improved the performance of the prediction model without imposing significant processing overhead or altering original data samples.

show abstract

Section: Introductionmentioning

confidence: 99%

Business Analytics in Telemarketing: Cost-Sensitive Analysis of Bank Campaigns Using Artificial Neural Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A similar type of research conducted in [53] has proposed a fault detection method for induction motors utilizing empirical wavelet transform and CNN achieved 97.37% accuracy, which is also comparable with our result. In [54], authors used a vibration signal and CNN for fault detection and diagnosis, achieving accuracy between 88-99% for different ratios of data. Another method proposed in [55] attained 98% and 100% accuracy for detecting rotor fault and bearing fault respectively when using a CNN.…”

Section: Resultsmentioning

confidence: 99%

Bearing Fault Diagnosis of Induction Motors Using a Genetic Algorithm and Machine Learning Classifiers

Toma

Prosvirin

Kim

2020

Sensors

184

View full text Add to dashboard Cite

Efficient fault diagnosis of electrical and mechanical anomalies in induction motors (IMs) is challenging but necessary to ensure safety and economical operation in industries. Research has shown that bearing faults are the most frequently occurring faults in IMs. The vibration signals carry rich information about bearing health conditions and are commonly utilized for fault diagnosis in bearings. However, collecting these signals is expensive and sometimes impractical because it requires the use of external sensors. The external sensors demand enough space and are difficult to install in inaccessible sites. To overcome these disadvantages, motor current signal-based bearing fault diagnosis methods offer an attractive solution. As such, this paper proposes a hybrid motor-current data-driven approach that utilizes statistical features, genetic algorithm (GA) and machine learning models for bearing fault diagnosis. First, the statistical features are extracted from the motor current signals. Second, the GA is utilized to reduce the number of features and select the most important ones from the feature database. Finally, three different classification algorithms namely KNN, decision tree, and random forest, are trained and tested using these features in order to evaluate the bearing faults. This combination of techniques increases the accuracy and reduces the computational complexity. The experimental results show that the three classifiers achieve an accuracy of more than 97%. In addition, the evaluation parameters such as precision, F1-score, sensitivity, and specificity show better performance. Finally, to validate the efficiency of the proposed model, it is compared with some recently adopted techniques. The comparison results demonstrate that the suggested technique is promising for diagnosis of IM bearing faults.

show abstract

“…The cumulative number of signal values in the nested cluster is normalized in order to represent the density of the nested cluster. Although NSP removes the non-stationarity of the time sequence, it is an efficient imaging method for multi-variable correlation analysis [ 24 , 25 ].…”

Section: Supervised Health Stage Predictionmentioning

confidence: 99%

“…As represented in Figure 2 , at least two different data channels as data sources are required and the first step is the incorporation extraction of signals in three different bandwidths. Hilbert–Huang transformation (HHT) and Fast Fourier transform (FFT) are used to determine the bandwidth of bandpass filters [ 25 ]. In the second step, the extracted two-channel signals are compressed into nested clusters.…”

Section: Supervised Health Stage Predictionmentioning

confidence: 99%

Supervised Health Stage Prediction Using Convolutional Neural Networks for Bearing Wear

Suh

Jang

Won

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Early detection of faults in rotating machinery systems is crucial in preventing system failure, increasing safety, and reducing maintenance costs. Current methods of fault detection suffer from the lack of efficient feature extraction method, the need for designating a threshold producing minimal false alarm rates, and the need for expert domain knowledge, which is costly. In this paper, we propose a novel data-driven health division method based on convolutional neural networks using a graphical representation of time series data, called a nested scatter plot. The proposed method trains the model with a small amount of labeled data and does not require a threshold value to predict the health state of rotary machines. Notwithstanding the lack of datasets that show the ground truth of health stages, our experiments with two open datasets of run-to-failure bearing demonstrated that our method is able to detect the early symptoms of bearing wear earlier and more efficiently than other threshold-based health indicator methods.

show abstract

Generative Oversampling Method for Imbalanced Data on Bearing Fault Detection and Diagnosis

Cited by 54 publications

References 27 publications

Business Analytics in Telemarketing: Cost-Sensitive Analysis of Bank Campaigns Using Artificial Neural Networks

Business Analytics in Telemarketing: Cost-Sensitive Analysis of Bank Campaigns Using Artificial Neural Networks

Bearing Fault Diagnosis of Induction Motors Using a Genetic Algorithm and Machine Learning Classifiers

Supervised Health Stage Prediction Using Convolutional Neural Networks for Bearing Wear

Contact Info

Product

Resources

About