Apr-2025

Pathway to autonomous operations in refining and petrochemicals

Harnessing advanced technologies to transform industrial operations and usher in a new era of efficiency.

Tom Fiske
Yokogawa

Article Summary

Petroleum refining and petrochemical companies operate in a highly complex and dynamic environment marked by numerous challenges that affect their efficiency, profitability, and sustainability. As these companies strive to meet global demand for their products, they encounter several significant obstacles, such as:
• Dealing with fluctuating raw material and energy costs.
• Adapting to changing raw material supplies and qualities.
• Complying with ever more stringent environmental regulations.
• Keeping pace with rapidly advancing technology.
• Managing ageing infrastructure and legacy systems.
• Combating an ageing workforce and talent shortages.
• Meeting sustainability goals.
• Ensuring safety.
• Creating resilient supply chains.

To meet these challenges, the downstream sector of the oil and gas industry is embracing digital technologies that enable it to significantly transform operations, control costs, and improve profitability. The next wave of efficiency improvements will be ushered in by industrial autonomy.

Industrial autonomy
Industrial autonomy has multiple benefits that go beyond autonomation. It has proven effective in nearly all aspects of operations by optimising production, reducing energy consumption, improving asset reliability, supporting sustainability goals, improving safety, and providing data-driven insight for continuous improvement and real-time decision-making.

The transition from Industrial Automation to Industrial Autonomy (IA2IA) is the next evolution of industrial operations. It is not about employing a single digital technology but rather the use of several advanced technologies in innovative ways to improve operations. It involves a combination of ubiquitous connectivity, smart sensors and Internet of Things (IoT), cloud computing, edge devices, drones and robotics, cybersecurity, and advanced data analytics and artificial intelligence (AI) to create self-governing systems that can function with minimal human intervention.

Industrial autonomy is the progression from automated systems to self-governing systems. Unlike traditional automation, which relies on pre-programmed instructions with human supervision, industrial autonomy leverages AI and machine learning (ML) to enable systems to make decisions, adapt to changes, and optimise performance in real-time.

Industrial autonomy maturity levels
Industrial autonomy (see Figure 1) can be applied to a wide variety of functional domains. AI powers industrial autonomy, serving as an advisor and decision-support system or enabling autonomous operations. There are different levels of industrial autonomy, ranging from manual to completely autonomous:
•    Level 5: A highly idealised state that extends autonomy to other functional domains like planning and scheduling, production, and maintenance to achieve complete autonomous operations.
•    Level 4: A system that operates autonomously in certain modes of operation and utilises orchestrated workflows to perform functions across multiple domains.
•    Level 3: Select autonomous applications that monitor processes and equipment and enable workers to make better decisions.
•    Level 2: A system where pre-programmed automations conduct most of the production with human supervision.
•    Level 1: A system where humans and automation share the workload.
•    Level 0:  Manual operations.

Pathway to autonomous operations
The journey towards autonomous operations involves several stages, each requiring careful planning, investment, and collaboration between technology providers and stakeholders. Not all companies start at the same point or have the same end goals. Some will be focused on digital transformation, while others will focus on decarbonisation, improving efficiencies, implementing AI solutions, and so on. Some of the stages towards autonomous operations may include:
• Defining strategic focus to identify areas where autonomy can provide the most significant benefits.
• Benchmarking/assessment to analyse workflows, data sources, and existing automation levels.
• Data integration and management – this is particularly important, as high-quality data is the basis for autonomous systems. Managing data from different sources helps AI and ML models learn and decide effectively. This includes upgrading infrastructure, setting data governance policies, and using data integration platforms.
• Developing a roadmap and selecting the right technologies is critical for successful implementation. This includes selecting AI and ML platforms, robotics, IoT devices, and analytics tools that align with the organisation’s goals and existing systems.
•  Skill development and change management to upskill employees to work with advanced technologies and allow them to perform higher value-added tasks.

When deploying autonomous systems, companies typically focus on three areas:
- Remote or integrated operations centre to remove people from hazardous environments or inconvenient locations.
- Augment automation to improve production, asset reliability, and safety.
- Increase worker productivity by automating tasks and providing them with AI-driven operational advisory decision support systems.