The SPE has split the former "Management & Information" technical discipline into two new technical discplines:
- Management
- Data Science & Engineering Analytics
Filters
Journal
- Loading...
Conference
- Loading...
Publisher
- Loading...
Theme
- Loading...
Author
- Loading...
Concept Tag
- Loading...
Source
- Loading...
File Type
- Loading...
Site News
Goto
No map tile layer
| Layer | Fill | Outline |
|---|
Map layers
| Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
|---|
| Fill | Stroke |
|---|---|
Collaborating Authors
This course is designed to give trainees an overview of various artificial lift solutions and related production optimization concepts. After introducing participants to the need for an artificial lift system, training will focus on each of the following lift methods: Gas lift, Reciprocating Rod Lift, Progressing Cavity Pumping, Hydraulic Pumping, Electrical Submersible Pumping, Plunger and Capillary System. For each lift type, the course covers main components, application envelope, relative strengths and weaknesses. Animations, field cases, and example-calculations are used to reinforce concepts. A unique feature of this course is discussion on digital oil field as applicable to lift optimization.
artificial lift dr, artificial lift system, asia government, data Science, discipline, engineering analytic production, India government, Interdependence, operation data analytic, operation full field optimization, optimization, participant, progressing cavity pump, pumping, rajan chokshi, reservoir, Upstream Oil & Gas
SPE Disciplines: Production and Well Operations > Artificial Lift Systems > Progressing cavity pumps (0.91)
Abstract This paper reports the development and tests of an advance methodologies to predict Upstream plant risky events, such as flaring, applying an integrated framework. The core idea is to exploit Machine Learning and big data analytics techniques to tackle and manage both major upsets that would lead to significant inefficiency and loss. The tool is developed for complex upstream production system, where upset could be caused by a huge amount of heterogeneous factors, exploiting data driven monitoring systems to identify the weak signals of the upcoming events. The framework proposed is mainly composed by a strong pipeline divided in 3 modules operating before (predictive phase), during and after the event. The former aims to reduce the probability of an event, the second works on the severity and the third one has a dual function: reporting upsets and feedback gathering system to be used to further improve the analytics implemented. The Predictive component alerts operators when it recognizes a dangerous pattern among the parameters considered. The other two components can support this one and can be exploited to detect early signs of deviations from the proper operating envelope, while predictive performances are not satisfying. Moreover, during an event occurrence, operators can promptly identify the causes of the upset through the entire production system. This allows a faster reaction and consequently a significant reduction in magnitude. The solution proposed provides 2 complementary methodologies: • an agnostic anomaly detection system, helping to map plant functional unit anomalous behavior, as a dynamic operating envelope, and identifying the most affected ones; • A real time root-cause analysis, as a vertical solution, obtained learning from the monitoring of the different specific functional unit; The tool is also able to provide an automatic event register using information provided by the root-cause system, including operator feedbacks that will improve the performances of each module of the framework.
advanced analytic, analytic, Artificial Intelligence, bianco, big data, big data analytic, cadei, data mining, Exhibition, hazardous event, machine learning, montini, offshore mediterranean conference, operator, plant engineer, production optimization, Ravenna, sensor, Upstream Oil & Gas, upstream production system
SPE Disciplines:
Technology:
- Information Technology > Data Science > Data Mining > Big Data (1.00)
- Information Technology > Artificial Intelligence > Machine Learning (1.00)
Real Time Implementation of ESP Predictive Analytics - Towards Value Realization from Data Science
Andrade Marin, Antonio (Petroleum Development Oman) | Al Balushi, Issa (Petroleum Development Oman) | Al Ghadani, Adnan (Petroleum Development Oman) | Al Abri, Hassana (Petroleum Development Oman) | Al Zaabi, Abdullah Khalfan Said (Petroleum Development Oman) | Dhuhli, Khalid (Petroleum Development Oman) | Al Hadhrami, Issa (Petroleum Development Oman) | Al Hinai, Saif Hamed (Petroleum Development Oman) | Al Aufi, Fahad Masoud (Petroleum Development Oman) | Al Bimani, Aziz Ali (Petroleum Development Oman) | Gala, Rahul Dinesh (Weatherford International) | Marin, Eduardo (Weatherford International) | Kumar, Nitish (Weatherford International) | Raj, Apurv (Weatherford International)
Abstract Failure Prediction in Oil and Gas Artificial Lift Systems is materializing through the implementation of advanced analytics driven by physics-based models. During the Phase I of this project, two early failure prediction machine learning models were trained offline with historical data and evaluated through a blind test. The next challenge, Phase II, is to operationalize these models on Real-Time and re-assess their accuracy, precision and early prediction (in days) while having the assets focusing on either extending the runtime through optimization, chemical injection, etc. or proactive pump replacement (PPR) for high producers wells with triggered early prediction alarms. The paper details Phase II of live prediction for two assets consisting of 740 wells to enable data-driven insights in engineers’ daily workflow. In Phase I, a collaboration between SMEs and Data Scientists was established to build two failure prediction models for Electrical Submersible Pumps (ESP) using historical data that could identify failure prone wells along with the component at risk with high precision. Phase II entails the development of a Real-Time scoring pipeline to avail daily insights from this model for live wells. To achieve this, PDO leveraged its Digital Infrastructure for extraction of high-resolution measured data for 750 wells daily. A Well Management System (WMS) automatically sustains physics-based ESP models to calculate engineering variables from nodal analysis. Measured and engineered data are sampled, and referencing learnt patterns, the machine learning algorithm (MLA) estimates the probability of failure based on a daily rolling data window. An Exception Based Surveillance (EBS) system tracks well failure probability and highlights affected wells based on business logic. A visualization is developed to facilitate EBS interpretation. All the above steps are automated and synchronized among data historian, WMS and EBS System to operate on a daily schedule. From the Asset, at each highlighted exception, a focus team of well owners and SME initiate a review to correlate the failure probability with ESP signatures to validate the alarm. Aided by physics-based well models, action is directed either towards a) optimization, b) troubleshooting or c) proactive pump replacement in case of inevitable failure conditions. This workflow enables IT infrastructure and Asset readiness to benefit from various modeling initiatives in subsequent phases. Live Implementation of Exceptions from Predictive Analytics is an effective complement to well owners for prioritization of well reviews. Based on alarm validity, risk of failure and underperformance – optimizations, PPRs or workover scheduling are performed with reliability. This methodology would enable a Phase III of scaling up in Real-Time with growing assets wherethe system would be periodically retrained on True Negatives and maintained automatically with minimum manual intervention. It is experienced that a high precision model alone is not enough to reap the benefits of Predictive Analytics. The ability to operate in a production mode and embedding insights into decisions and actions, determines ROI on Data Science initiatives. Digital Infrastructure, a Real Time Well Modeling Platform and Cognitive adaptation of analytics by Well Owners are key for this operationalization that demands reliable data quality, computational efficiency, and data-driven decisions philosophy.
algorithm, analytic, analytical model, Artificial Intelligence, artificial lift system, data mining, esp predictive analytic, failure prediction, failure probability, machine learning, optimization, Petroleum Engineer, predictive analytic, real time implementation, real time system, Upstream Oil & Gas, well owner
SPE Disciplines:
Technology:
Abstract Gas Lift has been applied in the oil field for more than 70 years, despite the new technology and developments there is always more optimization that can be done. In this paper we are giving a leading example of one of the oldest gas lift projects in gulf of Suez that has been running for more than 50 years where 540 MMSCFD being pumped on daily basis to produce more than 200 wells as of today. the experience in this field is quite historical but the question is always persisting are we making best use of lift gas volumes and pressure, does every well have the optimum design and receives the optimum gas lift rate. One more important question will be how to prioritize interventions and optimization operations to target wells with highest value. In order to assess the overall gas lift performance of the field an innovative dashboard was created including Key performance indicators that reflect benchmarking of Lift Gas Consumption compared with historical Performance of the field. This should spot the light to the field with lowest efficiency and most probably it is expected higher return of production if we dedicate efforts to this field. Moreover creating wells dashboard has valued new Key Performance indicators with New Diagnostic Graphs that was not given attention by the industry before. Having these diagnostic Plots allowed benchmarking performance of wells for similar reservoir, completion type, gas lift design and sand face completion. Using this technique, it became easy to detect wells with higher potential of production with proper gas lift intervention. Although Analytics can give some guidance on the required actions to enhance production of wells knowing the basic design, having the analytics coupled with Integarated Network modelling and well models added more value to the project. Data Driven Gas Lift Optimization approach was applied since Oct. 2021 in an extensive approach over GOS, the approach succeeded to define more than 74 Optimization and Intervention Opportunities 45 of them were actually intervened in less than a year and added more than 4000 BOPD to production capacity. It was not a surprise that some of historically known underperforming wells were interpreted underperforming for other reasons than gas lift in-efficiency but using Gas lift Analytics re-analysis of the system showed huge value for gas lift intervention in these wells and succeeded to revive them. Data Analytics and Data driven gas lift optimization is proved a huge leap in managing gas lift fields and keeping the system running closer to optimum.
africa government, Artificial Intelligence, artificial lift system, asia government, benchmarking, case study, data analytic drive production optimization, Efficiency, egypt government, gas injection, gas lift, gas lift well, Gulf, mandrel, mmscfd, operation, optimization, optimization problem, Orifice, orifice valve, reservoir, Saudi Arabia government, survey article, united states government, Upstream Oil & Gas, valve
Country:
- Africa > Middle East > Egypt (0.71)
- Asia > Middle East > Saudi Arabia (0.62)
- North America > United States (0.47)
Oilfield Places: Africa > Middle East > Egypt > Gulf of Suez > Gulf of Suez Basin > July Field (0.99)
Technology: Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (0.66)
Abstract In Petroleum Development Oman (PDO) mission that committed to empower employees with the needed capabilities and fuel innovation, efficiency and more importantly achieve and sustain a 100% Health, Safety and Environment (HSE), by transforming the way of handling HSE events by moving from reactive to proactive approach. Drilling operations represent a challenging environment due to human factors that prone focusing on operations mainly instead of safety of Personnel Protective Equipment (PPE). Surveillance cameras are installed in various locations in rig floor and contribute to security and safety. However, the current methods of video analytic in floor rigs are weak in the long-term sequence of nodes with missing and abnormal error value such nighttime, low illumination which causes poor images. In a proof-of-concept exercise, PDO has been provided the AI Solution to overcome all above limitation to develop AI Models based on drilling operation on rig floor. Consequently, this paper presents machine learning pipeline that is validated and evaluated the vendors Video AI detection of HSE violations of PPE and restricted zone access on the rig floor that shared video dataset. The pipeline can be described in two parts. Due to the complexity of the use case that usually difficult to be managed in-house, we propose a method to bring different algorithms solutions from different vendors where the evaluation is managed in-house. In this, we present a framework for video analytic evaluating safety operation drilling in floor rigs. This framework contains the data of video source that collected, annotations guidelines to support necessary data quantities for the best machine learning approaches, performance metrics, and tools that containing scoring baseline models to be able compute amazing performance output regarding annotated ground truth data. The benefit of this study was to address some challenges of video object analytic and tracking beyond evaluation framework that enables a significant comparison of Machine learning models, provides AI vendors with sufficient data for the exploration the automatic modeling approaches, encourages the incorporation evaluation the techniques with process development, and contributes valuable oil and gas drilling that will demonstrate very useful to Computer Vision (CV) research for next years.
algorithm, application, Artificial Intelligence, asia government, deep learning, drilling operation, drilling safety operation, evaluate video analytic, evaluation, information, machine learning, methodology, neural network, oman government, operation, recognition, Upstream Oil & Gas, video analytic, video dataset, violation, workflow
SPE Disciplines:
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.68)
Save or update focal point
Save a search / focal point to access it again.
Thank you!