Application of Machine Learning to Distributed Temperature Sensing (DTS) Systems

2018 ◽  
Author(s):  
Maria S. Araujo ◽  
Heath A. Spidle ◽  
Shane P. Siebenaler ◽  
Samantha G. Blaisdell ◽  
David W. Vickers
Keyword(s):  
Machine Learning ◽  
Leak Detection ◽  
Optical Signal ◽  
Operating Conditions ◽  
Temperature Sensing ◽  
Distributed Temperature Sensing ◽  
Fine Grained ◽  
Pipe Segment ◽  
Pipeline Segment ◽  
Processing Techniques

The timely detection of small leaks from liquid pipelines poses a significant challenge for pipeline operations. One technology considered for continual monitoring is distributed temperature sensing (DTS), which utilizes a fiber-optic cable to provide distributed temperature measurements along a pipeline segment. This measurement technique allows for a high accuracy of temperature determination over long distances. Unexpected deviations in temperature at any given location can indicate various physical changes in the environment, including contact with a heated hydrocarbon due to a pipeline leak. The signals stemming from pipeline leaks may not be significantly greater than the noise in the DTS measurements, so care must be taken to configure the system in a manner that can detect small leaks while rejecting non-leak temperature anomalies. There are many factors that influence the frequency and intensity of the backscattered optical signal. This can result in noise in the fine-grained temperature sensing data. Thus, the DTS system must be tuned to the nominal temperature profile along the pipe segment. This customization allows for significant sensitivity and can utilize different leak detection thresholds at various locations based on normal temperature patterns. However, this segment-specific tuning can require a significant amount of resources and time. Additionally, this configuration exercise may have to be repeated as pipeline operating conditions change over time. Thus, there is a significant need and interest in advancing existing DTS processing techniques to enable the detection of leaks that today go undetected by DTS due to their signal response being too close to the noise floor and/or requiring significant resources to achieve positive results. This paper discusses the recent work focused on using machine learning (ML) techniques to detect leak signatures. Initial proof-of-concept results provide a more robust methodology for detecting leaks and allow for the detection of smaller leaks than are currently detectable by typical DTS systems, with low false alarm rates. A key use of ML approaches is that the system can “learn” about a given pipeline on its own without the need to utilize resources for pipeline segment-specific tuning. The potential to have a self-taught system is a powerful concept, and this paper discusses some key initial findings from applying ML-based techniques to optimize leak detection capabilities of an existing DTS system.

Machine-Learning Distributed-Temperature-Sensing-Based Pipeline Leak Detection

2020 ◽  
Author(s):  
Wissem Sfar Zaoui ◽  
Thomas Lauber ◽  
Clemens Pohl ◽  
Michael Kerk ◽  
Thomas Glaeser ◽  
...  
Keyword(s):  
Machine Learning ◽  
Leak Detection ◽  
Temperature Sensing ◽  
Distributed Temperature Sensing

Fiber Optic DTS and DAS as an Alternative Interpreted Intelligent Completions Extended Abstract

2021 ◽  
Author(s):  
Nur'ain Minggu ◽  
Latief Riyanto ◽  
Chang Siong Ting ◽  
Dahlila Kamat ◽  
Dylan Zhe Ho ◽  
...  
Keyword(s):  
Fiber Optic ◽  
Production Optimization ◽  
Operating Conditions ◽  
Temperature Sensing ◽  
Position Tracking ◽  
Distributed Temperature Sensing ◽  
Acoustic Sensing ◽  
Valve Position ◽  
Valve Opening ◽  
Distributed Acoustic Sensing

Abstract This study aims to validate and track valve positions for all the zones applying recorded Distributed temperature sensing (DTS) and Distributed acoustic sensing (DAS) data interpretation in order to propose the best combination of downhole inflow control valve (ICV) openings, This is required to optimize Well X-2 multizone commingled production. Fiber DTS and DAS monitoring were relied on as an innovation against downhole conditions that has compromised the three out of four downhole dual-gauges and valve position sensors. For zonal water control purpose, ICV cycling and positioning have been attempted in 2019. The valve position tracking derived from the compromised downhole dual gauges and valve position sensors does not tally with the surface flow indication overall. Consequently, the original measurement intention of the permanently installed distributed fiber-optic which served as back-up zonal-rate calculation profiling and as potential sub-layer flow-contribution indicators is brought in as contingency zonal valve-opening tracking and guides that proved valuable for subsequent production optimization. First part of study involves interpretation of Distributed Temperature Sensing (DTS) data. Downloaded DTS data is depth matched and validated against known operating conditions like time of each cycling stage and surface well test parameters (i.e. Liquid Rate, Watercut, Tubing Head Pressure (THP), Total Gas, Gas-Oil Ratio (GOR)), etc. To establish a baseline, several DTS traces of historical operating condition during a known stable period were selected, i.e. stable flowing condition at only Zone 4 stable shut-in condition at surface with only ICV Zone 4 is opened Downhole valve-position tracking can be interpreted alternatively from induced fiber temperature activities across the valve depth with a good temperature baseline benchmarking from DTS temperature profiling. Second part of study involves interpretation of Distributed Acoustic Sensing (DAS) data. The data was acquired under single flowing condition one month post-ICV cycling. Without any changes made on the well operating conditions, the well is flowing under same condition post ICV cycling. Inflow point detection using joint interpretation of DAS and DTS, where simultaneously DAS spectral content (depth-frequency) was analysed alongside DTS traces to further discriminate between inflow and other noise sources. Through i) acoustic amplitude analysis, ii) DTS inversion, iii) noise speed and flow speed computation, composite production allocation can be derived for Well X-2. Using the alternative co-interpretations based on fiber temperature and acoustic measurement, it is found and validated that Zone 1 ICV is Closed, Zone 2, 3 and 4 are in opened position and continuously producing at any cycles. This is in conflict of zonal production control understanding initially based on the compromised downhole sensors indicating that all the zonal valves are supposedly in fully closed position. In this case-study, DTS and DAS data has been proven useful and as an innovative, alternative monitoring to determine downhole valve opening with analogue to flow contribution derivation methodology. Therefore, anytime in the future where Well X-2 valves cycling is planned to be carried out, there is now a corresponding operating procedure that is incorporated onsite real-time fiber optic DTS and/or DAS data monitoring to validate tracked valves positioning.

Employing Innovative Distributed Temperature Sensing Technique for Conclusive Downhole Leak Detection via Coiled Tubing: A Case Study from Pakistan

2019 ◽  
Author(s):  
Aizaz Khalid ◽  
Victor Briones ◽  
Pierre Ramondenc ◽  
Adnene Mhiri ◽  
Rao Shafin Ali Khan ◽  
...  
Keyword(s):  
Leak Detection ◽  
Temperature Sensing ◽  
Distributed Temperature Sensing ◽  
Coiled Tubing

Adsorption Isotherm Predictions for Multiple Molecules in MOFs Using the Same Deep Learning Model

2019 ◽  
Author(s):  
Ryther Anderson ◽  
Achay Biong ◽  
Diego Gómez-Gualdrón
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Molecular Simulation ◽  
Large Scale ◽  
Learning Model ◽  
Operating Conditions ◽  
Small Subset ◽  
Screening Methods ◽  
Large Set ◽  
Metal Organic

<div>Tailoring the structure and chemistry of metal-organic frameworks (MOFs) enables the manipulation of their adsorption properties to suit specific energy and environmental applications. As there are millions of possible MOFs (with tens of thousands already synthesized), molecular simulation, such as grand canonical Monte Carlo (GCMC), has frequently been used to rapidly evaluate the adsorption performance of a large set of MOFs. This allows subsequent experiments to focus only on a small subset of the most promising MOFs. In many instances, however, even molecular simulation becomes prohibitively time consuming, underscoring the need for alternative screening methods, such as machine learning, to precede molecular simulation efforts. In this study, as a proof of concept, we trained a neural network as the first example of a machine learning model capable of predicting full adsorption isotherms of different molecules not included in the training of the model. To achieve this, we trained our neural network only on alchemical species, represented only by their geometry and force field parameters, and used this neural network to predict the loadings of real adsorbates. We focused on predicting room temperature adsorption of small (one- and two-atom) molecules relevant to chemical separations. Namely, argon, krypton, xenon, methane, ethane, and nitrogen. However, we also observed surprisingly promising predictions for more complex molecules, whose properties are outside the range spanned by the alchemical adsorbates. Prediction accuracies suitable for large-scale screening were achieved using simple MOF (e.g. geometric properties and chemical moieties), and adsorbate (e.g. forcefield parameters and geometry) descriptors. Our results illustrate a new philosophy of training that opens the path towards development of machine learning models that can predict the adsorption loading of any new adsorbate at any new operating conditions in any new MOF.</div>

scholarly journals A review of infant cry analysis and classification

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chunyan Ji ◽  
Thosini Bamunu Mudiyanselage ◽  
Yutong Gao ◽  
Yi Pan
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Signal Analysis ◽  
Future Research ◽  
Prosodic Features ◽  
Infant Cry ◽  
Machine Learning Classification ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Processing Techniques

AbstractThis paper reviews recent research works in infant cry signal analysis and classification tasks. A broad range of literatures are reviewed mainly from the aspects of data acquisition, cross domain signal processing techniques, and machine learning classification methods. We introduce pre-processing approaches and describe a diversity of features such as MFCC, spectrogram, and fundamental frequency, etc. Both acoustic features and prosodic features extracted from different domains can discriminate frame-based signals from one another and can be used to train machine learning classifiers. Together with traditional machine learning classifiers such as KNN, SVM, and GMM, newly developed neural network architectures such as CNN and RNN are applied in infant cry research. We present some significant experimental results on pathological cry identification, cry reason classification, and cry sound detection with some typical databases. This survey systematically studies the previous research in all relevant areas of infant cry and provides an insight on the current cutting-edge works in infant cry signal analysis and classification. We also propose future research directions in data processing, feature extraction, and neural network classification fields to better understand, interpret, and process infant cry signals.

High-spatial-resolution Distributed Temperature Sensing System Based on a Mode-locked Fiber Laser

2020 ◽  
Author(s):  
Anton O. Chernutsky ◽  
Dmitriy A. Dvoretskiy ◽  
Ilya O. Orekhov ◽  
Stanislav G. Sazonkin ◽  
Yan Zh. Ososkov ◽  
...  
Keyword(s):  
Fiber Laser ◽  
Spatial Resolution ◽  
High Spatial Resolution ◽  
Temperature Sensing ◽  
Distributed Temperature Sensing ◽  
Sensing System

scholarly journals Thermodynamics of a fast-moving Greenlandic outlet glacier revealed by fiber-optic distributed temperature sensing

2021 ◽  
Vol 7 (20) ◽  
pp. eabe7136
Author(s):  
Robert Law ◽  
Poul Christoffersen ◽  
Bryn Hubbard ◽  
Samuel H. Doyle ◽  
Thomas R. Chudley ◽  
...  
Keyword(s):  
Fiber Optic ◽  
Basal Layer ◽  
Temperature Sensing ◽  
Distributed Temperature Sensing ◽  
Catchment Scale ◽  
Outlet Glacier ◽  
Coarse Spatial Resolution ◽  
High Vertical Resolution ◽  
Fast Motion ◽  
Strain Heating

Measurements of ice temperature provide crucial constraints on ice viscosity and the thermodynamic processes occurring within a glacier. However, such measurements are presently limited by a small number of relatively coarse-spatial-resolution borehole records, especially for ice sheets. Here, we advance our understanding of glacier thermodynamics with an exceptionally high-vertical-resolution (~0.65 m), distributed-fiber-optic temperature-sensing profile from a 1043-m borehole drilled to the base of Sermeq Kujalleq (Store Glacier), Greenland. We report substantial but isolated strain heating within interglacial-phase ice at 208 to 242 m depth together with strongly heterogeneous ice deformation in glacial-phase ice below 889 m. We also observe a high-strain interface between glacial- and interglacial-phase ice and a 73-m-thick temperate basal layer, interpreted as locally formed and important for the glacier’s fast motion. These findings demonstrate notable spatial heterogeneity, both vertically and at the catchment scale, in the conditions facilitating the fast motion of marine-terminating glaciers in Greenland.

Sign in / Sign up

Export Citation Format

Share Document