July 2020

Special Focus: The Digital Plant

What if your plant were truly digital?

With the increasing volatility of the oil and gas markets (involving price fluctuations and oil demand uncertainties) and stricter environmental constraints, a new normal for the world is being built right in front of us.

With the increasing volatility of the oil and gas markets (involving price fluctuations and oil demand uncertainties) and stricter environmental constraints, a new normal for the world is being built right in front of us. To succeed, companies must reinvent the way they manage business and operations. They will need to be nimble and resilient, connected and collaborative—and this will require radically different thinking.

Higher levels of digital maturity will be required to face new challenges. Digital transformation used to be driven by an increase in competitive market pressures. However, as a result of the COVID-19 pandemic, the drivers to invest in digital capabilities have pivoted from optimization and growth toward ensuring safe remote operations and also toward gathering and analyzing the right data across the organization to make optimal business decisions.

In this new normal, only the most robust and agile energy companies will survive in the long run. The strong players have full visibility on how market changes impact their business in real time, and on mechanisms that can enable them to quickly act to mitigate risks and to explore small windows of opportunity to improve margins.

TOP DIGITAL APPROACHES TO BEAT UNCERTAINTY

While the market and drivers have changed, new technologies and digital trends continue to emerge—leveraging massive remote communications, and continuity of operations and maintenance. They also provide secure access to information and analysis tools that enable critical decision making in response to constant market fluctuations. While digital solutions and big data are available, the competitive advantage will come from the way oil companies explore this technology and employ it. To be prepared for future downturns, it is important to evaluate various “what-if” scenarios. Following are the top digital approaches that oil companies should consider when facing these market uncertainties:

Planning and network optimization

Against the backdrop of today’s depressed oil prices, along with the global oversupply and drop in oil demand, oil companies must continually evaluate their production planning. They need to be flexible and to replan several times a day to rapidly react to market fluctuations. To take advantage of economic opportunities and to quickly react to every change, the planning process must allow the evaluation of numerous scenarios featuring different crude grades, oil prices and possible future demands. Having the agility to provide the best use of assets and to run scenarios for building short- and long-term plans for maximum profit will define which companies are going to succeed.

For larger players, single-site and multi-site modeling with network optimization will help improve the understanding of the interaction between assets/sites and the business itself (FIG. 1). This is the type of visibility required to allow the best decisions when faced with rapidly changing or uncertain information.

FIG. 1. Network distribution optimization model.

Besides selecting the best technology and defining the best processes to enable traders and planners to work better and more collaboratively, there is another key aspect to ensure success: cloud-enabled solutions. In the past few years, the cloud was considered an emerging trend adopted by companies that were ahead of their time and that were seeking to improve efficiency and reduce information technology (IT) costs. At present, it is a crucial element to promote speed and collaboration, as most employees are currently working from their homes. In 2017, BP moved several applications to the cloud, including its unified supply chain management platform. This implementation was so successful that Claire Dickson, CIO for Downstream at BP, made the following statement about the production planning application: “Believe it or not, for the same data set, the same crude and feedstocks, the same units, what used to take us seven hours to run now takes just over three minutes. I have to admit I didn’t really think that we’d get that out of the cloud, so it has been quite revolutionary for us.”1,2

Value chain optimization

The instability of the oil industry makes the energy value chain even more complicated than before. Despite the widespread use of technology, refineries are managed by a series of point solutions throughout their value chains. With each point solution comes its underlying assumptions, data models and constraints. This makes decision-making across the value chain opaque and results in a series of value leaks across the operations value chain. To recover faster and stronger from today’s market instabilities, an investment in digital capabilities must be wisely designed. Oil companies need to develop a strategic roadmap for their digital transformation journeys that allows for unlocking extra benefits within their existing assets in the near and long term (FIG. 2).

FIG. 2. Production scheduling: One of the elements of value chain optimization.

In addition to production planning, the optimization of the value chain must include production accounting, offsites management, process optimization, energy management, daily scheduling, quality analysis and logistics. In this new world, the different disciplines in the plant will need to work with common objectives, and within a single application that drives collaboration and knowledge sharing. Value chain optimization will result in faster and more robust decision-making aligned with risk management and margin improvements. Typical specific benefits achieved by companies that have invested in holistically optimizing the value chain include:

  • Supply chain:
    • Crude purchases: faster feedstock selection, reduced costs
    • Planning, scheduling, and logistics: Increased throughput and yield
  • Process performance: Longer equipment life and increased availability, quality and yields
  • Blending and oil movements: Reduced giveaway, no rework, minimum inventory and downgrades, higher fuel agility
  • Energy management: Reduced energy conversion and consumption costs, as well as decreased cost of crude for energy
  • Production management: Reduced accounting losses, decreased inventory, reduced hydrogen and steam consumption, increased throughput
  • Operations management: Reduced unplanned shutdowns, increased yield, decreased hydrogen and steam consumption, increased throughput.

AI-driven predictive maintenance

Process simulation and artificial intelligence (AI) are consolidated technologies that are used to understand equipment and process behaviors and to support the identification of unexpected events. Being able to run models under different scenarios and to get faster answers during critical times is even more important. Refineries can operate with 50% of their capacity under very low product demand phases, which can increase the number of unexpected events, since operators are not used to operating under those different conditions.

Some approaches for running models can be time-consuming without the full range of options and possibilities. Enhanced AI can be used to increase model speed and accuracy. The AI-driven predictive maintenance platform combines AI, deep learning, rigorous first-principles models and real-time optimization (FIG. 3). AI is infused with results from the rigorous process simulation and optimization algorithms, creating a sophisticated model capable of providing advice about the best cost-effective choices for operations and maintenance. One of the main results of conventional predictive analytics models is the provision of early warning notifications about equipment failures. However, when these models are combined with rigorous models and a deep learning approach, the benefits are stretched:

FIG. 3. The AI-driven predictive maintenance platform.
  • The model’s operational range is extended, as it is not limited to the operating range used to “train” the model (i.e., high-dynamic range models).
  • The model works for assets with limited historical data, so it can be applied as soon as the equipment is commissioned, or as soon as a completely new operation condition is imposed.
  • The model sensitivity is higher, so the process and equipment failure detection is provided much earlier, allowing enough time to plan for maintenance or for a planned shutdown.
  • It provides a single enterprise early warning notification system for any event related to unexpected process or equipment behavior.
  • The system is capable of estimating the remaining useful life of an asset, prescribing actions for planned outages.
  • The system provides automated risk vs. cost impact analysis, and is capable of determining if constrained equipment or loss of equipment is a viable scenario.

The AI-driven predictive maintenance platform provides a 360° view of risks related to asset and process health degradation, enabling the optimization of operational efficiency, production and costs based on known constraints or loss of equipment. As a result, the plant can manage risks—thereby decreasing production loss to downtime and optimizing operations and maintenance strategies.

Enterprise visibility

The integration of IT and operational technology (OT) is a critical step. Companies need to bring data from software and operational silos into a single view to align the “connection of things” with the “operational actions.”

Remote communications from edge internet-of-things (IoT) devices, instruments and equipment—as well as from entire production lines, processes and sites—are now available. This whole chain of equipment, processes and sites must be converted into a common single-pane solution for visualization, analysis and action (FIG. 4). As a result, companies can operate remotely, safely and intelligently through enterprise visibility to support real-time decision making.

FIG. 4. Enterprise visibility.

This single enterprise-wide view consolidates engineering information with operational context, maintenance strategy, energy management, real-time operational displays, and interfacing to specific applications (such as process simulation, real-time optimization and predictive analytics) and financial data—thus providing actionable guidance considering different situations. It is a transformative integration approach for assets, people, processes and technology that is designed to drive operational excellence across multiple sites, enabling the realization of up to a 40% increase in operational efficiency.

Abu Dhabi National Oil Company (ADNOC) has implemented its Panorama Digital Command Center—a fully integrated, real-time data visualization center that empowers ADNOC to gain insights, unlock efficiencies and identify new pathways to optimize performance (FIG. 5). This application integrates 14 organizations operating across the hydrocarbon value chain (including gas processing facilities, refineries and petrochemical plants), with more than 120 dashboards displaying approximately 200,000 data points. The company can monitor every site and asset in several layers, with a common source of information. With this application, ADNOC can monitor key performance indicators (KPIs), predictive analytics results, planning and scheduling, and energy management—guiding its teams, based on trusted information. The application has generated a paradigm shift for ADNOC personnel—allowing them to be more data driven and innovative, and to be more confident to take action. The savings for optimizing the integrated production planning can be $60 MM–$100 MM from a single model run.3

FIG. 5. ADNOC’s Panorama Digital Command Center.

“The importance of embedding digital technology in businesses has never been greater, and ADNOC’s continuous investment in digital transformation over the last three years allows us to be more resilient, agile and responsive in navigating today’s market landscape,” said Abdul Nasser Al Mughairbi, Senior Vice President, Digital, ADNOC. “Our Panorama Digital Command Center acts as our ‘eyes on the ground’ and enables speed, accessibility and integration across our operations—key attributes that are required to make smart business decisions.”4

What if your plant were truly digital?

“What if” will probably be the most commonly used term to start a question with in 2020. There are many aspects of life that we cannot control, so we need to dedicate time and effort to those aspects that we can address. We cannot predict market changes, but we can be ready to act fast to ensure business continuity and safety.

For most companies, digital transformation has always been an objective, but it has become a basic requirement to survive now and thrive later. The faster a strategic roadmap that increases the digital capabilities is established, the sooner the recovery can start. If your company has not started on that journey, look for guidance and for real examples, as well as for proven technology, so you can accelerate the time to value. No time should be wasted in transforming your plant into a truly digital plant. HP

LITERATURE CITED

  1. “BP revolutionizes its oil and gas downstream business with AVEVA’s solution in the cloud,” https://sw.aveva.com/success-stories/bp-unified-supply-chain
  2. Pudwell, S., “BP: Digital transformation enables ‘magical’ innovation beyond IT,” Silicon UK, June 2017, https://www.silicon.co.uk/cloud/bp-innovation-it-cloud-216091
  3. “ADNOC maximizes value and improves operations,” June 2019 https://www.youtube.com/watch?v=ICe6TArKesw&t=5s
  4. Menachery, M., “ADNOC’s Panorama Digital Command Center generates over $1 B in value and is enabling an agile response during COVID-19,” Refining & Petrochemicals Middle East, May 2020, https://www.refiningandpetrochemicalsme.com/products-services/28583-adnocs-panorama-digital-command-center-generates-over-1bn-in-value-enables-an-agile-response-during-covid

The Author

From the Archive

Comments

Comments

{{ error }}
{{ comment.comment.Name }} • {{ comment.timeAgo }}
{{ comment.comment.Text }}