PTQ Q2 2026 Issue

control, and reinforces risk prevention across high-intensity units. Data integrity underpins these capabilities. Cloud deployment on secured industrial infrastructure ensures that calibration data and simulation outputs remain con- sistent and traceable, preserving model credibility for both engineering decisions and compliance audits. Simplifying complexity and sustaining expertise Automation helps bridge a widening workforce and skills gap across the energy and chemicals sector. Deloitte notes that the need for science, technology, engineering, and mathematics (STEM) talent, particularly in advanced engineering, operations, and analytics, already exceeds the available supply. At the same time, a significant portion of this workforce is preparing to retire, which intensifies the challenge of maintaining complex models and sustaining institutional knowledge. According to Deloitte, more than 1.2 million workers, representing roughly 60% of the energy and chemicals workforce, will require upskilling in digital technologies, processes, operations, and analytics to meet emerging operational demands.4 As digital systems become more deeply embedded in asset management and optimisation,

emissions, and enhances safety without adding complexity. As digital twins mature, their role also evolves within refinery operations. Historically, simulation models were used intermittently to validate design assumptions, support troubleshooting, or evaluate capital decisions. Continuous lifecycle management changes this paradigm by allowing simulation frameworks to participate directly in day-to-day operational decision-making. Planning, optimisation, and operational teams can rely on a shared and continuously validated representation of plant behaviour, reducing the disconnect that often exists between assumed optimisation and achievable operating conditions. Over time, this convergence enables more con- sistent decision-making across planning, scheduling, and operations, improving both responsiveness and confidence in model-driven outcomes. Rather than replacing engineer- ing expertise, automated lifecycle management amplifies it by ensuring that institutional knowledge is continuously embedded within the digital representation of the asset. In this way, next-generation digital twins become not only ana- lytical tools but operational systems that support sustained performance improvement across the refinery lifecycle. Ultimately, the move toward automated lifecycle manage- ment ensures that the digital twin remains an asset rather than a liability. As refining becomes more data-intensive, this framework provides the necessary bridge between human expertise and computational power, securing a competitive 1 Gelder, A., Wood Mackenzie. Woodmac.com, 31 Mar. 2025, www. woodmac.com/news/opinion/global-refinery-closure-outlook-2035. Accessed 17 Feb. 2026. 2 Technavio. Digital Transformation in Oil and Gas Industry Market Analysis, Size, and Forecast 2025-2029: APAC (China, India, Japan), North America (US and Canada), Middle East and Africa (UAE), Europe (Germany, Russia, UK), and South America (Brazil). Technavio. com, 2025, www.technavio.com/report/digital-transformation-mar- ket-size-in-the-oil-and-gas-industry-analysis. and sustainable future for the process industries. Acuity is a trademark of KBC (A Yokogawa Company) References 3 Baron, F., Quantifying the Payoff: How Digital Twin Technology Improves OPEX and ROI in Modern Refinery Operations. 2025. https:// tinyurl.com/398f7v3b 4 Yankovitz, D,, McLemore, N., Energy and Chemicals Future Workforce Development | Deloitte US. Deloitte, 2025, www.deloitte.com/us/en/ Industries/energy/perspectives/future-of-energy-chemicals-reskill- ing-upskilling-workforce.html. Soni Malik is a Product Management Senior Consultant responsible for KBC’s proprietary Acuity Process Twin Pro and the Petro-SIM reactor suite portfolio, as well as upcoming digital offerings. With nearly two decades of experience across downstream refining and petrochem - icals, she provides strategic direction for product development and growth initiatives, supporting the delivery of business objectives and long-term innovation strategies. Michelle Wicmandy , DBA, is a Marketing Campaigns Manager at KBC (A Yokogawa Company), where she focuses on digital transformation, process simulation, and performance improvement across refining and process industries. She also serves as a Senior Sustainability Advisor with The ESG Institute, contributing to initiatives focused on responsi- ble industrial transformation.

Automating model maintenance represents a decisive step toward the industry’s vision of autonomous, digitally optimised operations

refiners must balance this growing skills requirement with tightening labour availability. By automating routine calibration tasks, continuous auto- mated model maintenance applications enable smaller teams to manage larger, more complex operations. Junior engineers can focus on analysis rather than manual rec- onciliation while experts apply their knowledge to refining optimisation strategies. In essence, automation preserves process knowledge, prevents institutional ‘drift’, and pro- motes data-driven discipline. Standardised dashboards and guided workflows democratise access to model data. They make digital twin maintenance accessible across disciplines, from process engineering to planning and energy management, and sup- port more integrated decision-making. Conclusion: towards the autonomous refinery Automating model maintenance represents a decisive step toward the industry’s vision of autonomous, digitally optimised operations. By integrating domain expertise and automating a simulation framework powered by cloud computing, refineries can develop next-generation digital twins that evolve in step with their physical assets. This transformation turns process simulation from a periodic engineering task into a continuous performance system, one that strengthens decision quality, reduces

PTQ Q2 2026