SPE-170680-MS Predicting Failures from Oilfield Sensor Data using Time Series Shapelets
نویسندگان
چکیده
Increasing instrumentation of the modern 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.
منابع مشابه
SPE-174907-MS Rapid Data Integration and Analysis for Upstream Oil and Gas Applications
The increasingly large number of sensors and instruments in the oil and gas industry, along with novel means of communication in the enterprise has led to a corresponding increase in the volume of data that is recorded in various information repositories. The variety of information sources is also expanding: from traditional relational databases to time series data, social network communication...
متن کاملUltra-Fast Shapelets for Time Series Classification
Time series shapelets are discriminative subsequences and their similarity to a time series can be used for time series classification. Since the discovery of time series shapelets is costly in terms of time, the applicability on long or multivariate time series is difficult. In this work we propose Ultra-Fast Shapelets that uses a number of random shapelets. It is shown that Ultra-Fast Shapele...
متن کاملUnsupervised Feature Learning from Time Series
In this paper we study the problem of learning discriminative features (segments), often referred to as shapelets [Ye and Keogh, 2009] of time series, from unlabeled time series data. Discovering shapelets for time series classification has been widely studied, where many search-based algorithms are proposed to efficiently scan and select segments from a pool of candidates. However, such types ...
متن کاملScalable Clustering of Time Series with U-Shapelets
A recently introduced primitive for time series data mining, unsupervised shapelets (u-shapelets), has demonstrated significant potential for time series clustering. In contrast to approaches that consider the entire time series to compute pairwise similarities, the u-shapelets technique allows considering only relevant subsequences of time series. Moreover, u-shapelets allow us to bypass the a...
متن کاملTemporal Feature Selection on Networked Time Series
This paper formulates the problem of learning discriminative features (i.e., segments) from networked time series data considering the linked information among time series. For example, social network users are considered to be social sensors that continuously generate social signals (tweets) represented as a time series. The discriminative segments are often referred to as shapelets in a time ...
متن کامل