To offset the fluctuations in the cost of oil, the oil and gas industry looks for improved efficiencies in all parts of its production chain. Predictive analytics leverages the large volumes and variety of historical well data to find critical patterns to improve performance, reduce losses, and enable operators to be more proactive in field operations.
Examples of deployed predictive analytics solutions in oil and gas production control and planning systems include the following:
- Shut-in forecasting
- Flow forecasting
- Downhole pump failure prediction
- Virtual metering
- Hydrate prediction
- Slug detection
Predictive analytics can prioritize preventative maintenance by forecasting adverse well events weeks in advance. Near real-time models can be trained to detect imminent problems and avoid significant losses.
Analytic solutions reduce deferrals, increase production, and lower operational costs and capital expenditures. For example, predicting which electrical submersible pump is at highest risk enables targeted intervention to extend the life of the pump, help maintain controlled production rates, and manage capital expenditures.
Elder Research has experience developing and deploying sophisticated analytic solutions for the oil and gas industry. These solutions build on existing engineering models, and account for the fluctuations and anomalies that occur in field operations. Integrating these models with current systems can reduce operational costs and enhance efficiency of entire systems, providing a sustainable competitive advantage and conserving natural resources.
Energy Case Studies
Our clients—whether newly formed analytics teams or established pros—find that we help them understand their data, strengthen their teams’ abilities, and bring to the forefront basic and advanced levels of insights aligned to their needs. Examples of our energy solutions include:
Predicting Natural Gas Well Freezing
Elder Research harnessed 20 years of detailed sensor readings from hundreds of wells to characterize transient well states. The goal was to predict gas well shut-ins (blockages preventing production) due to hydrate formations four to six months in advance in a North American field, where winter months allowed only very limited access.
Results: Our model was far more accurate than the existing heuristic models and it allowed operations personnel to know which clusters of well pads should be prioritized for treatment. A second model was created which clearly showed when in the new well life cycle a plunger pump system should be installed. The estimated return on investment for each model was less than one year. Read the Case Study
Identifying Predictive Indicators of Engine Oil Failure
Elder Research conducted descriptive and predictive analysis of engine oil laboratory results to identify indicators of oil failure and enable streamlining of laboratory work, over a 30 day period. More than 30 laboratory measurements from thousands of oil samples were analyzed to find correlations and their relationships to oil failure.
Results: A highly predictive model was built which demonstrated that just ten specific laboratory measurements are needed to fully assess oil health. This enabled significant reduction in laboratory costs and provided quantitative insight into what contaminants lead to engine oil failure, which in turn enables better oil filter design.