M. Bowling, Seeq Corporation, Houston, Texas
Industrial process manufacturers and refiners are facing a storm of disruptive challenges. First and foremost, calls to mitigate climate change have taken a central position and must be prioritized, driving the decarbonization efforts of industrial and manufacturing processes. Secondly, business models and value chains are undergoing transformation as companies adjust to new external pressures to circularize their supply chains. Lastly, digital technologies now define customer, regulator, investor and employee expectations, driving procedural changes at warp speed.
With sustainability in the spotlight, one essential factor that characterizes successful companies pursuing ambitious initiatives is their adaptation from periodic, retrospective mitigation and management to continuous, real-time responsiveness. This shift is unfolding in the oil and gas industry, as leading companies are recognizing the benefits of digital solutions while they build on existing investments to make rapid impacts.
Paired with the expertise of inhouse subject matter experts (SMEs), oil and gas companies are leveraging advanced analytics applications to gain new visibility into their process data, helping minimize emissions with little to no new capital investment. These solutions help build models, providing adopters with a better understanding of how changes in their processes affect environmental performance, including emissions.
This article describes some of the key challenges organizations are facing as they adopt digital solutions to optimize operations in real time, while also working toward reducing their environmental footprint.
Escaping spreadsheet purgatory. Arguably the most challenging stage of a sustainable digital transformation journey is simply overcoming inertia and getting started because it requires preparation and strategic planning. For example, to effectively minimize operational emissions, organizations must ensure three key components are in place:
For organizations still relying on spreadsheet-based methods to conduct data analysis, putting these foundational blocks in place can be especially challenging. Spreadsheets impose significant limitations, including live data connectivity challenges, antiquated computational capabilities, poor online collaboration, and clumsy visualization and reporting functionalities. Using spreadsheets without live connections to both historical and live data sources, SMEs must manually query every individual database, extract the necessary information, and then aggregate and align mismatched timestamps. When a new time period of interest is identified, the process must be repeated.
Once SMEs sort all this out, they must then create intelligent models to provide value to operational users. These models must be capable not only of alerting but also generating root cause insights that guide operational decisions and adjustments.
An important tenet for building trustworthy models is coordination between engineers and operations staff during development and execution. Deploying black box machine-learning algorithms developed by data scientists in silos too frequently amounts to false alerts—which cause frustration among operations—or incomplete insights, which fail to provide helpful operational and preventive maintenance guidance.
Advanced analytics solutions automate data source connectivity, insight generation and emissions reporting. Fortunately, advanced analytics solutions are empowering organizations to automate data collection, conditioning and subsequent reporting to free up large amounts of SMEs’ time, which can instead be spent optimizing operations and improving plant efficiency.
Many of the world’s largest oil and gas companies are deploying software to provide automated and self-service analytics capabilities for SMEs, including process engineers, operations managers and operators. These solutions immediately provide live data connectivity with automatic aggregation from many disparate sources, bringing it together in a single and central platform. The software executes built-in cleansing and contextualization algorithms, empowering engineers to focus their efforts on higher-value tasks.
Equipped with point-and-click tools in an intuitive interface, SMEs can visually apply descriptive, diagnostic, predictive and prescriptive analytics, and then improve process performance using the insights gleaned. This can all be done with low- and no-code tools, facilitating collaborative model-building among multiple users.
These models combine information from multiple relevant data sources, providing context around operations of interest, and they are making it easier to identify anomalies. By coordinating with operations staff, SMEs can ensure process alerts include these details to guide informed decision-making and productive process improvements.
Justifying an idle boiler. To reduce the amount of wasted energy and, therefore, carbon emissions, process manufacturers need methods to identify time periods of wasteful operation—such as excessive electricity consumption or vented steam—and quantify the waste as a financial loss or carbon dioxide emissions equivalent. These quantities provide a common benchmark for comparing alternative operating strategies.
A major U.S. refining company leveraged the author’s company’s advanced analytics solutiona to justify idling a single boiler in a dual-boiler operation during the warm months of the year. SMEs configured the software to identify time periods when the dual-boiler system was operating at minimum firing rates while venting steam, and by examining these periods, they could aggregate potential annualized steam savings.
The SMEs then analyzed historical data to understand the probability of a boiler trip, which could have a significant financial impact in a single boiler operation. The potential steam cost and energy savings were then weighed against the risk—the probability of failure times the financial consequence—of running a single boiler (FIG. 1).
This analysis provided the necessary data to justify the decision to idle one boiler during prolonged periods of warm ambient weather, saving the refiner an average of $500,000/yr in vented steam costs. This operational change also reduced the operation’s carbon footprint by decreasing energy input to the boiler system.
Mitigating excess flaring. Oil and gas operations can result in unexpected swings and changes that cannot always be anticipated due to the sometimes-transient nature of many processes. Unfortunately, this means emissions events cannot always be completely prevented in the field; however, they can be curtailed.
Beyond responding quickly to emissions events to mitigate their impacts, emissions can also be reduced through root cause detection, which requires identifying problematic conditions and issuing an alert immediately so corrective action(s) can be taken. Advanced analytics solutions can be used to model, analyze and detect these conditions, additionally providing the contextual data required for responders to effectively mitigate any ensuing event duration and severity. These sorts of implementations help process manufacturers reduce overall emissions at their facilities and reduce expenditures.
For example, flares are safety devices at many facilities that relieve system pressure, preventing over-pressure events and managing unexpected operational upsets. However, flaring above design purge requirements wastes valuable energy and adds to greenhouse gas emissions.
At a large Canadian refinery, the process engineering team struggled to identify the targets and boundaries for flaring because operational states and conditions changed over time, and no baseline parameters had been established. After deploying the author’s company’s advanced analytics solutiona, the SMEs began identifying periods of time when equipment was on and running at high flowrates using capsule capabilities (FIG. 2), which are valuable for superimposing variables from multiple operational runs of the same type for comparison. The team was then able to use average flowrate as a baseline for proper operation of the flare stack. With a live connection to all real-time and historical data, the team rapidly analyzed more than 10 yr of data—combined with new information streaming in constantly—to establish the operational benchmark.
After defining this baseline, the SMEs developed a model to alert the operations staff when flare loads exceeded normal levels. When this occurred, the team could examine the various flaring sources and identify those out of alignment.
This model enabled the team to rapidly detect even the smallest of flaring sources, such as open valves at a sample station. The ability to identify baseline exceedances quickly and guide operations directly to the source is saving the company an estimated CAD $600,000/yr ($450,000/yr) in reduced flaring.
Implement advanced analytics solutions for collaboration and sustainability. With increasing industrywide emphasis on and the environmental importance of decarbonization, process manufacturers must find ways to adapt their operations to more stringent efficiency requirements and mandates for reduced emissions. Advanced data analytics solutions provide many of the process insights needed to identify opportunities for improvement, aiding optimization efforts and operational decision-making.
In the era of digital transformation, these types of solutions empower organizations to establish operational baselines, identify key performance indicators and use these metrics to track success toward sustainability goals. In addition, by leveraging advanced analytics solutions to establish the right models in plant environments, process manufacturers unlock the ability to not only respond quickly to emissions events as they occur, but to also predict impending events. Armed with these insights, operators and process engineers can take proactive steps to prevent emissions upsets.
These capabilities are bolstering companies’ sustainability efforts, helping them achieve ambitious net-zero goals. Those that adopt emissions monitoring and prevention into their digital transformation strategies, along with process optimization, will continue to experience success and maintain a competitive edge over their peers. HP
NOTE
a Seeq
Morgan Bowling is the Director of Industry at Seeq. She has a process engineering background and earned a BS degree in chemical engineering from the University of Toledo. Bowling has 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 and gas industry and translating them into product requirements for Seeq.