Transient Nature of Well Properties

The transient nature of well properties contributes greatly to uncertainty and makes optimization an ongoing challenge for the production engineering team. The figure above provides 
a snapshot of a few key operating parameters 
of a well on an unconventional formation, over
na two-month range. During this period, the oil production rate declines sharply from 500 bbl/d to 150 bbl/d, the Water Cut varies heavily between 0.5-0.9 (50% to 90%), the casing pressure drops from about 800 psi to about 600 psi, the tubing pressure changes from about 170 psi to 110 psi and the calculated operating gas lift valve changes from the 5th valve (relatively shallow valve) to the 2nd valve (deeper valve).

Further, the figure demonstrates that around January 30th to February 7th, the well is subjected to interference from an external activity which can potentially be a frac hit. This can be observed by temporary increases in water cut, oil rate, casing pressure, tubing pressure, and operating gas lift valve (GLV) estimates. This is an example of potentially several other changes to the state of the well which demand constant attention for adaptive set-point changes.

Scalability of the well management problem 
is limited by the volume of wells coupled with uncertain parameters and transitionary behavior. Solving this purely with human input may require the engagement of several engineers with a great understanding of the well, reservoir, and surface conditions. In the context of unconventional
 wells with extremely low permeability, measuring the accurate representative Reservoir or Static Bottom-Hole pressure becomes an additional challenge. In the event of a well shut-in for testing, the bottom hole pressure in an unconventional well may remain transient for months.

Therefore, the true representative pressure to be used as a static bottom-hole pressure becomes uncertain and transitionary. The productivity index of 
the well also changes significantly with time, unlike a typical conventional well. This situation makes it arduous to effectively utilize nodal analysis on unconventionals using engineering estimates. Further adding to the problems of scale and accuracy, it can be argued that manual engineering efforts follow a reactive approach. This can be improved with a proactive approach which is probabilistic and learns from history 
and self-updates.

Our white paper, entitled “A Machine Learning Approach to Automate Gas Lift Optimization”  presents an automation solution which constantly monitors the well, generates candidate models through simulation, selects the appropriate model and provides a gas injection recommendation.  To request this white paper and learn more about our approach to automating gas lift optimization that assists with the transient nature of well properties, click here.

ospreydata predictive analysis coverage and continuity equate to source data quality

Coverage and Continuity Equate to Source Data Quality

Coverage and continuity of source data are important dimensions when evaluating source data.  Coverage describes the number of data sources that are available for a well. Many of the models that are used in advanced systems, such as OspreyData, are combining sensor based machine learning models with physics based models. With a holistic view of well design, attention to maintenance history and failure reports is critical to successful model development. Continuity of source data describes how much source data is available without gaps or lapses. This is very important when reviewing sensor streams, for example, or the set of dynacards available for rod pumps.

When considering coverage and continuity, review the figure above. It shows a set of sensors for a rod pump well. We
can see that each of these sensors is incomplete for the time range being viewed. There are multiple lapses in the signals (highlighted in yellow). It appears that there are more lapses in signal than there are actual signal values.

Lapses create gaps in the history of the well. It is possible that the key change in signal is lost or missed during a gap in the signal. In multiple projects, OspreyData has experienced a 30% reduction
in the number of failure examples used for model training. This reduction has been specifically due to a lack of signal preceding the failure. These wells had poor data continuity – being unable to see the signal stream preceding the failure meant that the machine learning models had to exclude those failures from training.

When considering data quality, coverage and continuity of source data are important dimensions used in the evaluation of the source data.  To consider the impacts of these source data issues, we suggest that you request our whitepaper, entitled  “Data Quality Fuels the AI Race.”  Feel free to comment or ask questions about our white paper below in our comments section.  We would love to hear your thoughts and begin a conversation.

Why Unified Monitoring is Mission Critical to Running a Digital Oilfield

ospreydata blog webcast unified monitoring mission critical digital oilfield screenshot

In this WebCast Replay, Jon Snyder, 10+ year Petroleum Analytics Engineer (formerly of eLynx, Venoco, and Encana) chats with OspreyData CTO Ron Frohock about how Unified Monitoring can bring immediate benefits to E&P operators.

Jon and Ron walk through the ways Unified Monitoring helps Production teams save time daily and reduce time to resolution for operational issues. They also discuss steps to implementation and illustrate the numerous benefits monitoring alone can deliver to producers.

TOPICS COVERED

  • How Unified Monitoring helps lower LOE
  • Reducing your daily effort using Centralized Surveillance
  • How Unified Monitoring helps build your Data Backbone
  • How a central data store benefits your organization
  • Making the transition from Monitoring to Optimization
  • How Unified Monitoring is an entry point to Advanced Analytics

Please contact us with any questions you may have about OspreyData’s Unified Monitoring. We would love to discuss our solutions for maximizing your Oil and Gas ROI.

OspreyData Value: How We Beat Other Solutions

Our goal is to provide you OspreyData value on your wells. Our methodology and science was developed to create long-term benefits for your well operations.  Below we highlight four reasons how we beat other software platforms in the market.  They are platforms, we are a solution:

1. We developed Human-Augmented Machine Learning to solve real problems in Oil & Gas.

We have 500,000 events used for training on 10,000+ wells across multiple lift types.  You can’t find anyone else with this type of development.

2. You can start with your existing sensors and hardware.

With Osprey Data, you start with no upfront capital expenditures unlike other solutions that need significant capex for proprietary sensors and comms.

3. Our web-based platform is intuitive and easy to use.

Our web-based platform is intuitive and easy to use.  We have a web-based app that can be access on any browser.  Our interface and visualizations easy-to-understand, and you can deploy your own models.  Other solutions require proprietary equipment, include long hours of ongoing training, and have no model deployment capability.

4. We measure ROI, and meet to understand, document and agree where your value is.

OspreyData lowers operating costs, predicts failure, provides operating recommendations, creates effective maintenance schedules, lowers downtime, and increases productions.  Others may focus on price and sales volume, but we focus on where the issues are and provide value to your operation.

For more information about how our models will bring you more value over time, click here.

How Our OspreyData Science Works

Our OspreyData science and methodological approach is simple: Our expertise meets your expertise to empower your wells.  Whether is it ESP, Rod Pump, Gas Lift, Plunger Lift, or Downhole Analysis, our approach is to help you optimize production.  Below, we will discuss our our OspreyData science works:

 1. We monitor and model on multiple sensors.

First, our models look for normal and indicative problem patterns across all signals and engineering models.

Your Artificial Lift experts and ours label problem states across this data, known as events.

2. We normalize your raw data to create modeling features.

We determine a normalized signal for wells by type and across fields. This removes the need to analyze by individual wells. Our models work across various wells regardless of size, allowing for rapid deployment across your fields.

3. Our Machine Learning finds labeled patterns.

We employ different machine learning models to find the patterns labeled by the expert team. Machine learning greatly automates this historically manual process.

4. We train & test to ensure models are working.

We train and test to ensure models perform well on new data.

5. We track key measurements of Model Performance.

We provide complete transparency to model effectiveness at every stage. We constantly work to improve model performance by monitoring Accuracy, Precision and Recall metrics.

6. You can adjust Model Performance to your liking.

Change your models’ performance thresholds to meet your business objectives.

The end result is a powerful solution that is uniquely yours!

 

Click here to learn more about our methodology and science, as well as what problems you can conquer.

Ron Frohock, Chief Technology Officer

Ron Frohock, a senior development executive with 20+ years experience, leads OspreyData in technology and software development. As First VP at JPMorgan Chase (formerly WaMu), Ron was responsible for the website and systems supporting home loans. As VP of Engineering for MindArrow Systems, Ron oversaw the design and development of self-service SAAS marketing automation tools, and he created and managed the Technical Client Services group which served Fortune 500 companies with web development and rich media messaging. As Director of Development at Epicor, Ron managed Epicor’s analytical product offering and application integration. As Director of Development at State of the Art (now Sage), Ron was the primary architect for one of the first client/server suites of financial applications.

View our entire leadership team at OspreyData, who bring business expertise, technical innovation, and tons of oil and gas experience.