Toward self-optimization: An interview with Antonio Pietri 0

Toward self-optimization: An interview with Antonio Pietri

By Dominik Don
McKinsey

Energy producers are looking to optimize operations and increase the performance of assets across the value chain. Linking technology, data, industrial AI, and advanced visualizations with operations can help.

The oil and gas industry is in transition. As energy increasingly moves away from fossil fuels and toward sources of renewable energy, companies must strike a balance between addressing climate change and managing their portfolio and performance. To successfully navigate the energy transition, stay competitive, and continue powering the world, oil and gas companies must embrace new digital technologies that not only enable more efficient operations but also reduce their carbon intensities. At the same time, they must transform management systems and expand workforce capabilities to capture the full value potential of digital.

Antonio Pietri

McKinsey: What are your thoughts on how digital technologies can help energy companies navigate the transition to renewables?

Antonio: Most of our customers are proceeding along their digitalization journeys, increasingly deriving real-time insights from their assets and, in some cases, optimizing individual processes. There has been a significant progression by capital-intensive industries around leveraging digital technologies—and increased automation has been integral to this acceleration.

At the same time, the energy transition and circular economy are driving the need for organizations to evaluate and transform existing business and operating models with a renewed focus on achieving sustainability goals. Operating in today’s uncertain times, energy companies are faced with three major challenges. First, there is the need for new technologies that either use carbon in a more efficient way or enable the use of renewable energy to lower carbon emissions. Second, there is a need for significant capital to transition the industry to new process technologies. And third, there is a business-model challenge, which is forcing a broader view of the value chain.

Energy producers are looking to optimize the health of their operations and the performance of their assets across the value chain as they face increased regulation and pressure to significantly reduce CO2 emissions in their existing assets, as well as establish alternatives to traditional fossil fuels. Adopting new technologies such as AI and machine learning enables increased levels of data usage and performance transparency, as well as faster decision loops. Embedding industrial AI within our software combines data science and machine learning with domain expertise, and it has created a lot of excitement among our customers and in the marketplace. By accelerating digitalization and enabling operational excellence for capital-intensive industries, our AI moves plants further down the path to self-optimization, developing increasingly autonomous processes to instantly react and adapt to changes across the value chain and driving higher levels of safety, sustainability, and profitability.

Sidebar About Antonio Pietri
Antonio is president and chief executive officer of AspenTech and serves on the company’s board of directors. He previously served as executive vice president, worldwide field operations, and before that he served as senior vice president and managing director, regional operations, Asia–Pacific. He holds an MBA from the University of Houston and a BS in chemical engineering from the University of Tulsa.

McKinsey: Regarding self-optimizing plants, what specifically has changed to make the consideration of such plants possible?

Antonio: Leveraging the ever-increasing amounts of structured and unstructured data, industrial AI improves visibility into operations and delivers insight into the future, providing the basis for increased autonomy. Cloud and edge technologies enable software solutions to be deployed and integrated throughout the plant to support the speed of analysis needed to provide timely insights.

The self-optimizing plant will be self-learning, self-adapting, and self-sustaining. “Self-learning” refers to the plant’s ability to continually monitor and capture performance data to understand the impact of changes in the environment or feedstock quality. Based on that knowledge, the facility self-adapts. For example, if a storm comes through and lowers the temperature by ten or 15 degrees Fahrenheit, the plant knows to adjust the recirculation rate in its towers as well as some inlet and outlet temperatures for heat exchangers.

This plant is self-sustaining because it will monitor equipment and process health. In the event of a potential equipment failure, the facility alerts the business that some action or response is required. In some cases, the response will need the approval of changes in operating constraints. And in some cases, it will mean automating decisions, much like we’ve done with advanced process controls over the past 30 years.1

McKinsey: What are some steps to help these companies begin or continue on the digitalization journey?

Antonio: We typically talk about five steps that help illustrate the maturity models of energy companies on the way to the self-optimizing plant. The spectrum of maturity ranges from basic operational control systems at plant sites to fully integrated, automated, and autonomous companies. Each subsequent level represents thematic step changes in the levels of digitalization applied.

The first step is basic digital adoption with simple applications of control systems in operations, site-by-site basic refinery planning, spreadsheet-based scheduling, ad-hoc troubleshooting, and maintenance work orders. The second step is selective advanced-analytics adoption. Companies fully embracing this second step today deploy advanced analytics for value-creating use cases, such as prescriptive maintenance for uptime, adaptive advanced process control, and online optimization of individual units to further orchestrate and improve value. The third step is cross-discipline optimization. Today’s industry leaders are already exploring cross-discipline optimization, which can require the deployment of multiple digital solutions.

The final two steps are step four, the self-optimizing plant, and step five, the self-optimizing enterprise. Transitioning to step four requires significant trust in digital tools, organizational alignment around risk, and fully fledged digital organizations that drive continuous change. At step five, an asset or plant creates value only in the context of the enterprise value chain. To unlock the full potential of the autonomous plant, the value chain must make decisions that prioritize which assets produce which products, as well as which objectives are being optimized for each product and production line at each site.

McKinsey: And what sort of challenges do you foresee?

Antonio: First, as digital technologies continue to evolve and become more affordable and easier to deploy, the energy sector’s rate of adoption will accelerate. Last September, we conducted a crowdsourced audience poll with 300 energy and chemical industry executives representing 150 companies. For this group, operational excellence, margin optimization, and sustainability were the top three priorities to help improve their operating environments. However, despite 60 percent stating they had invested in digitalization teams with clear mandates, there was rarely an explicit link between digitalization and executive priorities.

Second, in terms of specific technologies, I see a carefully determined combination of conventional technologies and AI. AI, ubiquitous data, connectivity, and collaboration can work in concert with established operational technologies to consider the future state of refineries and petrochemical plants. Until recently, most companies had to tie this all together themselves or through a multitude of disparate partnerships. Industrial AI that is seamlessly embedded is more ubiquitous, as it can be applied to a wide variety of operational datasets and models, which in turn gives plant personnel more impactful information that can reveal alternative strategies and be used to either advise operators or—where closed-loop systems are operational—enable rapid responses with autonomous control.

McKinsey: Keeping all of this in mind, where does one start?

Antonio: Incorporating even the smallest technological advances can stimulate a shift in the ambition and energy of the enterprise. While organizations often state, “We cannot afford to invest in technology in this environment,” we would assert that, in most cases, companies can’t afford not to.

For more on how oil and gas companies can embrace new digital technologies, see “The autonomous plant: Entering a new digital era” on McKinsey.com

Dominik Don is an associate partner in McKinsey’s Munich office.

1 For more on advanced process controls in energy and materials, see https://www.mckinsey.com/industries/metals-and-mining/our-insights/the-potential-of-advanced-process-controls-in-energy-and-materials

Previous Article

Most Popular Topics

Editor Picks