Modelling System Failures of Electric Submersible Pumps in Sand Producing Wells

Kalu-Ulu, Torty C.; Andrawus, Jesse; George, Ian

doi:10.2118/151011-ms

Cited by 3 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sawaryn has derived analytical expressions describing failure patterns at a population level [12]. The amount of sand in the extracted fluid is one of the important causal factors affecting failure and Kalu-Ulu et al have modeled ESP failures in sand producing wells [13]. Furthermore, Liu et al [14] has adapted data mining classification algorithms and Liu et al [15] presents a Bayesian network-based machine learning algorithm to predict rod pump failures.…”

Section: Related Work On Esp Failure Predictionmentioning

confidence: 99%

Predicting Failures from Oilfield Sensor Data using Time Series Shapelets

Patri

Panangadan

Chelmis

et al. 2014

SPE Annual Technical Conference and Exhibition

View full text Add to dashboard Cite

Increasing instrumentation of the modem digital oilfield produces streams of data from sensors that monitor the functioning of different components in the field. This data should be converted to actionable information rapidly in order to respond to events as they happen or are predicted. The challenge is therefore to develop technologies that can process these large sensor datasets rapidly and with minimal manual supervision to ensure a data processing system that can scale with the increasing instrumentation.We consider as a use-case an oilfield with several Electrical Submersible Pumps (ESPs), each instrumented with sensors that continually measure electrical properties of the pump (the streams of sensor data), which are then relayed to a central location. In this paper, we demonstrate how a time-series analysis approach can be applied to failure detection and failure prediction from the streams of sensor data. The method involves identifying "shapelets" -short instances that are particularly distinct -in the streams of sensor data.The shapelets approach is particularly applicable to large oil and gas enterprise datasets because the algorithm does not need access to the entire historical data. This greatly reduces the amount of data that needs to be stored for data analysis. Moreover, unlike model-based approaches, shapelet-based analysis does not make any assumptions about the underlying nature of the data, making it practical for applications where a detailed physical model of the pump is not available.We validate our proposed method by analysis on a representative set of instrumented ESPs. We describe the preprocessing steps that were applied in our analysis. We report the results of experiments to study the effects of varying the data processing parameters on the accuracy of fault detection and prediction. These results indicate that shapelet-based approaches are promising for analysis of time-series data in the oil and gas industry.

show abstract

Section: Related Work On Esp Failure Predictionmentioning

confidence: 99%

Predicting Failures from Oilfield Sensor Data using Time Series Shapelets

Patri

Panangadan

Chelmis

et al. 2014

SPE Annual Technical Conference and Exhibition

View full text Add to dashboard Cite

show abstract

Enabling Oil Production Forecasting Using Machine Learning

Parhi¹,

Patwardhan²

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

The Evolution of ESP Technology in the North Sea: A Reliability Study Based on Historical Data and Survival Analysis

Pastre

Fastovets

2017

Day 1 Mon, October 16, 2017

View full text Add to dashboard Cite

High intervention costs to replace electric submersible pump (ESP) completions and high deferral production caused by ESP failures in offshore and remote locations are driving the efforts to increase ESP reliability around the world. ESP designs vary considerably depending on the application, for example, unconventional resource, heavy oil, high temperature, and high abrasives. Because of the wide range of ESP applications, the equipment specification requires a tailored solution for each application to increase reliability. This paper presents typical failures and the evolution of ESP technology deployed in the North Sea as well as the enhancements proposed to increase system reliability. The equipment improvements are based on failure analysis performed in the strings pulled from the North Sea. A large ESP population is analyzed, including 219 installations and 162 failures. Survival analysis enabled splitting the population into subsystems and analyzing the ESP performance individually after each major change in equipment specification. This approach made it possible to confirm the effectiveness of the changes and quantify the increase in reliability after each investment in equipment enhancement. It was also possible to identify the "less reliable" subsystem to focus on further improvements.

show abstract

Modelling System Failures of Electric Submersible Pumps in Sand Producing Wells

Cited by 3 publications

References 3 publications

Predicting Failures from Oilfield Sensor Data using Time Series Shapelets

Predicting Failures from Oilfield Sensor Data using Time Series Shapelets

Enabling Oil Production Forecasting Using Machine Learning

The Evolution of ESP Technology in the North Sea: A Reliability Study Based on Historical Data and Survival Analysis

Contact Info

Product

Resources

About