4 minute read
Advanced Analytics Solutions Drive
O&G Efficiency and Sustainability
By Morgan Bowling, Seeq Corporation
Over the decades, there has been a wide variety of process control and software systems deployed throughout refineries and petrochemical plants to monitor, gather, and process data in real time. These various systems include distributed control, supervisory control and data acquisition, laboratory information management, and others.
As information has increased, there is a growing volume of time-series data that can be used to identify operational optimization opportunities to increase efficiency and reduce upsets, aligning with critical corporate initiatives. Yet, many organizations face challenges accessing and connecting data from so many systems, analyzing it efficiently, and operationalizing insights in an effective manner.
Addressing these and other issues, modern advanced analytics solutions are enabling operating organizations throughout the energy and chemicals industries to automate data collection and cleansing. This enables companies to decrease time to value, by shifting operations and maintenance from reactive to proactive and predictive, and enabling teams to share insights more broadly with multidisciplinary teams.
Spreadsheet limitations
Although analytics applications have come a long way over the years, a shocking number of engineering experts are still stuck using spreadsheets for data aggregation and analysis, requiring time-consuming manual data preparation and cleansing from multiple sources. Spreadsheets present myriad limitations, including subpar computational capability, lack of live data connectivity, prohibitively difficult shareability, and clumsy visualization and reporting functionalities.
Void of live connections to both historical and live data sources, engineering experts are forced to manually query individual databases, extract the data needed for analysis, then aggregate and align mismatched timestamps in a spreadsheet. Whenever a new time period of interest is identified, the process must be repeated.
With so many hoops to jump through, it is easy to understand why nearly 80% of engineers, scientists, and analysts surveyed in a 2016 CrowdFlower study reported spending more time collecting and wrangling data into formats suitable for analysis than any other task (Figure 1).
In addition to the obstacles they present, spreadsheet-based analyses leave little time for gleaning meaningful insights, preventing organizations from making sense of data to garner insights necessary to increase operational efficiency and profitability.
Save valuable time with automated data conditioning and reporting Using advanced analytics solutions, organizations can shift away from spreadsheets—automating data collection, conditioning, and subsequent reporting— and free up large periods of experts’ time that can be reallocated to optimize operations and improve production efficiency.
Many of the world’s largest oil and gas companies are deploying advanced analytics solutions, like Seeq, to provide these automated and self-service analytics capabilities to their process engineers, operations personnel, and data scientists. These solutions immediately alleviate the challenges of live data connectivity because the software automatically connects to and aggregates data from many disparate sources. Information integrity is kept intact because the analytics solution does not modify any data stored in the system of record.
With data access and preparation barriers removed, SMEs (subject matter experts) can leverage purpose-built, point-and-click tools for descriptive, diagnostic, predictive, and prescriptive analytics to improve performance based on reliable insights. Advanced analytics solutions incorporate visualization into the analysis workflow, empowering SMEs to see the impact of their analyses in near-real time, identify errors, share insights with team members, and iterate more quickly than before.
These solutions empower SMEs to identify unique time periods of interest in their data, characterized by qualities known as conditions, to determine when equipment is exhibiting abnormal operational behavior. These time periods are typically defined by superimposing multiple operational parameters and identifying areas with rapid process value changes, specific signals, or trends that exceed static operating limits (Figure 2).
Figure 2: Advanced analytics solutions enable users to identify time periods of interest in their data and superimpose information from multiple assets to identify patterns and anomalies.
In the point-and-click environment, SMEs can quickly configure machine learning capable models without assistance from IT teams, regardless of their coding capabilities. Once unique conditions are defined for a single asset, the solution empowers teams to seamlessly scale a single configuration across a fleet of similar devices for nearreal time monitoring.
Automating greenhouse gas reporting
When Chevron needed to automate its regulatory compliance reporting for greenhouse gas (GHG) emissions across their refineries, the company turned to advanced analytics to automate this workflow. Using Seeq, Chevron populated data from refinery historians and applied calculations and contextualization for quarterly regulatory emissions reporting. Additionally, extensibility features within Seeq facilitated development of a custom solution for extracting final emissions data, and format it for direct ingestion into their corporate greenhouse gas reporting software (Figure 3). tasks and over 1,500 notifications each month. What was being manually identified in the past is now automatically flagged, increasing production capacity by proactively identifying issues to increase uptime.
Embracing advanced analytics applications for digital maturation
In today’s information landscape, leveraging advanced analytics solutions is critical for operators to maintain efficiency and competitive advantage. These solutions provide personnel with the tools they need to contextualize, analyze, and make the right decisions.
Chevron reduced analysis time from two or three days to only a few hours, enabled by automatic calculations and realtime updates incorporating the latest data. Most notably, access to this near-real time data empowered the team to shift to a proactive approach to emissions identification and mitigation. With up-to-date and readily available emissions performance information, emissions events can now be prevented, rather than detected after occurrence.
Automating exception-based surveillance
Marathon Oil teams are tasked with monitoring nearly 4,000 wells throughout its enterprise. Recently, the company eased this significant task by implementing and scaling Seeq, automating workflows to create alerts, which reduced the time required for this task from months to hours. These intelligent alerts drive and prioritize maintenance tasks and work orders for personnel in the field, empowering operational teams to reduce unplanned outages, which increases production and profitability.
Marathon Oil has over 50 employees using the solution with 170 Workbenches in Seeq, and the software generates 1,500
Advanced analytics solutions designed to scale high-value use cases across assets can increase data maturity. Digital transformation is an organizationwide initiative, and placing analytics solutions in the hands of all personnel can significantly increase adoption, leading to increased production, profitability, and sustainability.
All figures courtesy of Seeq
About the author
Morgan Bowling is Director of Industry at Seeq. She has a process engineering background with a BS in Chemical Engineering from the University of Toledo. Morgan has nearly a decade of experience working at both independent and integrated major oil and gas companies to solve high-value business problems leveraging time-series data. In her current role, she enjoys monitoring the rapidly changing trends surrounding digital transformation in the oil & gas industry and translating them into product requirements for Seeq.