Fault identification using a chain of decision trees in an electrical submersible pump operating in a liquid-gas flow

Castellanos, Mauricio Barrios; Serpa, Alberto Luiz; Biazussi, Jorge Luiz; Verde, William Monte; Sassim, Natache do Socorro Dias Arrifano

doi:10.1016/j.petrol.2019.106490

Cited by 34 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With increased attention paid to data and the development of machine learning technology, data-driven fault analysis methods have been developed [1][2][3]. In the field of aircraft, some researchers have used data-driven methods to diagnose, predict, and analyze aircraft faults.…”

Section: Literature Review 21 Data Driven Fault Analysis Methodsmentioning

confidence: 99%

An Unmanned Aerial Vehicle Troubleshooting Mode Selection Method Based on SIF-SVM with Fault Phenomena Text Record

et al. 2021

View full text Add to dashboard Cite

At present, the research on fault analysis based on text data focuses on fault diagnosis and classification, but it rarely suggests how to use that information to troubleshoot faults reported in unmanned aerial vehicles (UAVs). Selecting the exact troubleshooting procedure to address faults reported by UAVs generally requires experienced technicians with professional equipment. To improve the efficiency of UAV troubleshooting, this paper proposed a troubleshooting mode selection method based on SIF-SVM (Serial information fusion and support vector machine) using the text feature data from fault description records. First, Word2Vec was used in text data feature extraction. Second, in order to increase the amount of information in the modeling data, we used the information fusion method. SVM was then used to construct the classification model for troubleshooting mode selection. Finally, the effectiveness of the proposed model was verified by using the fault record data of a new fixed-wing UAV.

show abstract

Section: Literature Review 21 Data Driven Fault Analysis Methodsmentioning

confidence: 99%

An Unmanned Aerial Vehicle Troubleshooting Mode Selection Method Based on SIF-SVM with Fault Phenomena Text Record

et al. 2021

View full text Add to dashboard Cite

show abstract

“…They proposed an application of the principal component analysis (PCA) model to perform ESP fault detection to maintain ESP in the normal operational range. Castellanos et al [29] showed the machine learning algorithm's preference for future failure prediction based on historical ESP data. They adopted Classification and Regression Trees (CART) to detect and classify elementary faults in the ESP well system.…”

Section: Esp Fault Monitoring and Diagnosis Reviewmentioning

confidence: 99%

A Nodal Analysis Based Monitoring of an Electric Submersible Pump Operation in Multiphase Flow

et al. 2022

View full text Add to dashboard Cite

Electrical submersible pump (ESP) operation is compromised by free gas, resulting in premature pump failure and production losses in new wells. It is essential to detect the onset of abnormal operations. We develop a model that predicts abnormal ESP operation when the free gas level increases in the pump. The model compares operation parameters with the parameters of normal operating ranges; it shuts down the ESP when necessary. We used a Schlumberger PIPESIM software (version 2017.01) to perform nodal analysis technique; we tested the model using the other multiphase correlation model and field case studies (where the gas problem in ESP was reported). We employ a homogenous model to calculate the differential pump pressures at various gas volume fractions. Nodal analysis of the intake and discharge point predicted the commencement of abnormal ESP conditions and the associated parameters (critical gas fraction, minimum operating pump intake pressure, and pump discharge pressure). The model results were similar to other surging correlation models (e.g., Romero, Dunbar, Turpin, Cirilo, and Zhou models); they were also identical to field case studies. We identify three performance stability phases when an ESP is exposed to free gas. These are the normal and abnormal operating ranges, as well as the ESP shutdown condition. Modeling permits careful monitoring of ESP operations that can be compromised by free gas.

show abstract

“…After estimating the vibration signals, the classification algorithms can be selected for FPRCI. To classify the signal's state different techniques have been used that are divided into three main groups: (a) classical classifiers such as the sliding mode technique [10]; (b)machine learning-based classifiers including support vector machine (SVM) [36] and decision trees [37]; (c) deep learning-based classifiers including convolution neural networks [38] and autoencoders [39]. In this work, the SVM is recommended for classification of the faults and identification of the crack sizes.…”

Section: Introductionmentioning

confidence: 99%

Bearing Anomaly Recognition Using an Intelligent Digital Twin Integrated with Machine Learning

Piltan

Kim

2021

Applied Sciences

View full text Add to dashboard Cite

In this study, the application of an intelligent digital twin integrated with machine learning for bearing anomaly detection and crack size identification will be observed. The intelligent digital twin has two main sections: signal approximation and intelligent signal estimation. The mathematical vibration bearing signal approximation is integrated with machine learning-based signal approximation to approximate the bearing vibration signal in normal conditions. After that, the combination of the Kalman filter, high-order variable structure technique, and adaptive neural-fuzzy technique is integrated with the proposed signal approximation technique to design an intelligent digital twin. Next, the residual signals will be generated using the proposed intelligent digital twin and the original RAW signals. The machine learning approach will be integrated with the proposed intelligent digital twin for the classification of the bearing anomaly and crack sizes. The Case Western Reserve University bearing dataset is used to test the impact of the proposed scheme. Regarding the experimental results, the average accuracy for the bearing fault pattern recognition and crack size identification will be, respectively, 99.5% and 99.6%.

show abstract

Fault identification using a chain of decision trees in an electrical submersible pump operating in a liquid-gas flow

Cited by 34 publications

References 8 publications

An Unmanned Aerial Vehicle Troubleshooting Mode Selection Method Based on SIF-SVM with Fault Phenomena Text Record

An Unmanned Aerial Vehicle Troubleshooting Mode Selection Method Based on SIF-SVM with Fault Phenomena Text Record

A Nodal Analysis Based Monitoring of an Electric Submersible Pump Operation in Multiphase Flow

Bearing Anomaly Recognition Using an Intelligent Digital Twin Integrated with Machine Learning

Contact Info

Product

Resources

About