Binary feature selection classifier ensemble for fault diagnosis of submersible motor pump

Boldt, Francisco de Assis; Rauber, Thomas W.; Oliveira-Santos, Thiago; Rodrigues, Alexandre; Varejão, Flávio Miguel; Ribeiro, Marcos Pellegrini

doi:10.1109/isie.2017.8001523

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison of the proposed approach with the methods KNN [15], KNN + [15], KNN + FS [15], KNN + EFS [15], and the method, proposed by Oliveira-Santos et al [18], was also made. Table 7 shows the promising results of using the deep hybrid model for automatic diagnosis of ESP failures.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent diagnosis of petroleum equipment faults using a deep hybrid model

2020

View full text Add to dashboard Cite

Performance assessment and timely failure detection of the electric submersible pump can reduce operation costs and maintenance in the oil and gas field. Features of equipment malfunction are changes in vibration signals. Evaluation of vibrations based on accelerometer sensors can detect failures and allows assessment of system failures. This paper proposes a reliable deep learning-based method for electric submersible pump faults detection. The frequency, time and spectral information of the vibrational signal are considered as input to the deep hybrid model. The spectral information includes the spectrogram obtained using the short-time Fourier transform and the scalogram as a result of the continuous wavelet transform and provides a detailed study of the vibration signal. The proposed approach is compared with k-nearest neighbors, support vector machines, logistic regression, and random forest. The experimental evaluation shows that the proposed deep hybrid model is superior to these machine learning methods, and can automatically and simultaneously detect failures of the electric submersible pump according to the vibration signal that is generated during system operation. The proposed approach gives good results and can help an expert in automatic diagnostics of equipment and several complex technical systems.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The automatic feature selection of ESP vibration signals was investigated in [15]. A binary ensemble feature selection (EFS) algorithm with KNN trained with different feature sets (time-domain and frequency-domain features) was also proposed.…”

Section: Related Workmentioning

confidence: 99%

Intelligent diagnosis of petroleum equipment faults using a deep hybrid model

2020

View full text Add to dashboard Cite

show abstract

“…Over the past decade, MCSs have been actively exploited for improving classification accuracy and reliability over individual classifiers. MCSs have been widely used in areas such as the handwriting character recognition [2], [3], biometric identification [4], remote sensing [5], fault diagnosis [6], network security [7] and automatic object recognition [8].…”

Section: Introductionmentioning

confidence: 99%

A Ranking Distance Based Diversity Measure for Multiple Classifier Systems

Yang

Ding

Dezert

2018

2018 International Conference on Control, Automation and Information Sciences (ICCAIS)

View full text Add to dashboard Cite

Multiple classifier fusion belongs to the decisionlevel information fusion, which has been widely used in many pattern classification applications, especially when the single classifier is not competent. However, multiple classifier fusion can not assure the improvement of the classification accuracy. The diversity among those classifiers in the multiple classifier system (MCS) is crucial for improving the fused classification accuracy. Various diversity measures for MCS have been proposed, which are mainly based on the average sample-wise classification consistency between different member classifiers. In this paper, we propose to define the diversity between member classifiers from a different standpoint. If different member classifiers in an MCS are good at classifying different classes, i.e., there exist expert-classifiers for each concerned class, the improvement of the accuracy of classifier fusion can be expected. Each classifier has a ranking of classes in term of the classification accuracies, based on which, a new diversity measure is implemented using the ranking distance. A larger average ranking distance represents a higher diversity. The new proposed diversity measure is used together with each single classifier's performance on training samples to design and optimize the MCS. Experiments, simulations, and related analyses are provided to illustrate and validate our new proposed diversity measure.

show abstract