Energy
Industry

Learn More
h

Energy Systems
Design & Operations

We design and operate
the integrated energy
system of the future.

h

Data Engineering For Energy Industry

We use data
engineering to improvise
the energy industry.

h

Artificial Intelligence of Things (AIoT)

Our use of AIoT boosts
IoT operations and human-machine interactions.

h

Industrial Cloud
Digital Applications

We develop and customize cloud digital applications to boost operational efficiency.

Our Value-Added Solutions

To Oil and Gas Industries

Exploration and Assessment

Digitally uncover oil and gas fields in hard-to-access areas using predictive data analysis.

Oil Well Log Analysis

Leverage ML algorithms to automate well-log analysis and improve its quality.

Reservoir Characterization

Eliminate expensive methods in determining reservoir properties using neural networks.

System Design
& Operations

Overcome design and operational challenges in developing new oil and gas facilities.

Drilling Optimization

Monitor and optimize drilling operations in real-time and mitigate risks to increase efficiency.

Production Forecasting

Forecast production and ultimate recovery in reservoirs on time with high accuracy.​

Quantitative Visualization

Visualize oil fields with our intelligent analytics dashboards and get actionable insights.

Predictive Maintenance

Predict failures ahead of time and perform online maintenance to prevent downtime.​

Industrial Cybersecurity

Protect assets and data from external threats and secure your infrastructure proactively​.

Oil Well Log Analysis

Challenge

Well log data processing requires expert knowledge as geological data contains many uncertainties,
making logging interpretation a very time-consuming process.

Solution

  • Application of ML models to automate the well log data processing was recommended.
  • The data set was taken from a real oil field in Russia to develop ML models.
  • Gradient tree boosting and Convolutional neural network algorithms were used to reduce
    uncertainties in data interpretation.
  • Prediction by interval of depths using CNN turned out to be more successful than the prediction
    by sample using gradient tree boosting algorithm.

Reservoir Characterization

Challenge

The classification of reservoir fluids is a matter of considerable practical importance. By following the rule of thumb, fluid types in a reservoir can be identified, but laboratory observations are often required to verify them because of the imprecise and uncertainty that exist in reservoir parameters.

Solution

  • We have proposed the application of Artificial Neural Networks to classify the reservoir fluid types based on laboratory observation and field data.
  • More than 700 samples of different types of reservoir fluid types were used to develop the ANN model.
  • Different types of architecture for different groups of input data were tested using fitness criteria to identify an optimal architecture.
  • The optimal neural network was able to classify the reservoir fluid with high accuracy.

Drilling Optimization

Challenge

Drilling comprises a significant portion of oil and gas budgets, and any downtime experienced during drilling operations can be very expensive, leading to project cost escalation. Thus, any measure which saves time can reduce operational costs.

Solution

  • Since the Rate of Penetration (ROP) is a direct measure of the drilling time, machine learning algorithms and data analytics were employed to predict and maximize it.
  • A random forest was built on the training data and ROP was predicted throughout the depth of the well using RPM of the bit, WOB, UCS of rock, and flowrate as input features.
  • An optimization algorithm was applied to change the WOB and RPM of the test data to find the maximum attainable ROP.

Production Forecasting

Challenge

An important technique for estimating future oil well production is Decline Curve Analysis (DCA). But in practice, deterministic predictions of future declines are often inaccurate, as they are based on multiple assumptions and restrictions. Therefore, exploration and production (E&P) companies miss many opportunities to capitalize on real-time market conditions.

Solution

  • To increase the accuracy of production forecasting, different AI models were trained and compared.
  • Eight critical influencing parameters are considered as input factors to build the model.
  • Models were trained using 80% of all data generated through simulation while 20% was used for testing the models.
  • Results show that RSM and LSSVM have very accurate oil recovery forecasting capabilities.

Predictive Maintenance

Challenge

Oil and gas companies are adversely affected by pipeline failures because they experience numerous work interruptions and shutdowns that result in high maintenance costs. It is therefore necessary to apply smart predictive maintenance to prevent this issue.

Solution

  • Different failure modes of pipelines, their causes, and their consequences were studied in detail.
  • Based on the research conducted, a conceptual model for predictive maintenance was suggested.
  • The conceptual model was validated by triggering the most critical failures in a controlled environment.
  • Once 100% accuracy was achieved after the trial run, the conceptual model was implemented in the plant to attain near zero downtime.

Quantitative Visualization

Challenge

There is a disintegration of operational data across the oil and gas industry leading to poor decisions at every level that could endanger both the plant and its personnel and drastically reduce the operational performance.

Solution

  • Critical requirements for each stakeholder (operators, managers, investors, customers) were gathered.
  • Relevant OT and IT data are extracted from each stage of the upstream operations.
  • Developed a wireframe and workplan by collaborating with the domain experts and performed the ETL process.
  • Built insightful and appealing dashboards for each stakeholders to aid them in decision making.