Commodity cycles, capital planning challenges, and increasing operational risks in the oil and gas industry are all factors that make it more important than ever to make smarter and more efficient decisions. With AI and machine learning, companies can deliver the returns investors require, improve return on assets, and manage downside risks by turning much of the data collected into usable and valuable insight.

Unplanned downtime can be a costly nightmare for offshore oil and gas platforms—to the tune of a few $ million in a single day for catastrophic asset failures. Too many companies rely on outdated methods, prompting some to emphasize data and analytics to make maintenance decisions. A significant amount of unplanned downtime is driven by problems with a critical multi-phase pump.

CloudPrisma Analytics experts with the domain knowledge of O&G Drilling & Production environment can develop and deploy an expected behavior model of the multi-phase pump into AI-powered predictive maintenance software, which then alerted deviations from normal subsystem behavior. The AI software alerts operators and SMEs to a potential multi-phase pump trip caused by a failing seal, of which previous failures resulted in over $ multimillion in lost production. With the CloudPrisma solution, O&G companies can prevent pump failure and increase production by hundreds of thousands of dollars for each day of downtime avoided.

Some of the patterns to watch for –

1. Environment - remains fairly static over a period of time. A particular environment may throw vulnerable to a type of failure based on past behavior. Or any change in environment trigger by an event may have a history of increase of pump failure.
2. Repeat of a parameter deviation – Based on a single event, a repeat event's probability needs to be addressed while comparing the parameter's behavior from the history of the particular Pump or the OEM.
3. New Repeat of a parameter deviation in another Pump from the same or other OEM, the probability of impact in the other pump algorithm needs to be developed.
4. All Pump suppliers have different environment & control solutions from various OEM. Bringing different proprietary formats of information into a common repository is a big challenge for Oil & Gas companies.

‍

CloudPrisma brings innovative use of Artificial Intelligence and Machine Learning to develop advanced mathematical models for different scenarios based on various data sets like –

1. Apply them across different equipment types in the Oil & Gas value chain – Exploration, Concept, Project Execution, Drilling & Production
2. Creates customized dashboards for real time alerts, operational management, and executive decision making.
3. Create workflows for operational processes
4. Create Equipment Life Cycle Management workflows and dashboards
5. Integrate external data sources as per requirement using ETL (Extract, Transform & Load) to blend data from multiple sources and create Data Lakes and Data Warehouses.
6. Create an IoT grid to extract data where limited equipment interfaces available.

‍

Oil & Gas Company Current Setup 

‍Existing data across equipment type, multiple OEM's, PLC's, etc. CloudPrisma can also facilitate an IOT grid where current equipment's & PLC's have restricted data access.

‍

CloudPrisma Proposed Solution

• ‍Data Ingestion - data here is prioritized and categorized, making data flow smoothly in further layers in a common format. Transportation of data where components are decoupled to start analytic capability
• ‍Data Query Layer - Active analytics processing with the primary focus to gather data value to be more useful to the next layer. Some of the Tools used are Distributed SQL Query for Big Data (e.g., Presto, MY SQL, Apache Spark, MS SQL DB2, etc.)
• ‍Analytic Engine – Mathematical Modeling using Machine Learning and apply analytic tools for Statistics, Semantic, Predictive, Text & Video Analytics. (eg. Python, Java, R, etc.)
• ‍Data Visualization Layer - Presenting the data to make it "Valuable" and "Insightful." Tools using Tableau, Cognos, Power BI, etc.
• ‍Intelligent & Secured Hybrid Compute and Storage solution – Providing a mix of On-Premises, in the cloud, PaaS and Container-based or Serverless computing along with storage types like Object Storage, etc

‍

Enhance your equipment availability and control downtimes with CloudPrisma's innovative predictive insights.

‍

‍

‍