Digital Twin ‘Safeguards’ AI Value in Engineering and Operations

ITCAN Solutions, established in 2016, provides digital transformation services to large complex and data-intensive industries enabling them to democratize data improving productivity, safety, planning, reliability, and maintenance.

With its diligent approach, highly skilled workforce, and forward thinking, ITCAN Solutions services over 30 leading companies across the Energy, Power, Mining, Marine, and Food & Beverage, driving on its mission statement to allow organizations to “Achieve Further”.

In the midst of a digitalisation surge, the emergence of Digital Twin concepts, and recent rise of AI advancements, companies are grappling to stay afloat. In an exclusive interview, Ahmad Farshoukh, GM and VP of Projects & Engineering and an expert in data engineering with over 20 years of experience in Energy and Technology sectors, shares insight on the pivotal role of Digital Twins for enterprises, highlighting its foundational importance for AI adoption.

We are witnessing a strong demand for Artificial Intelligence in the industrial space, especially in the Energy Sector. Is Digital Twin still a top priority for CEOs?

Absolutely. Digital twin is an enabler for any type of AI technology that industrial organisations decide to pursue. In fact, we see that Digital Twin, if effectively and successfully implemented, will safeguard a company’s AI investment. Artificial Intelligence, by definition, is a toolkit that picks up patterns in large swarms of data, understands correlation and supports users in finding the best possible answers to optimise certain scenarios, forecast an outcome, or predict events.

So, no question AI will re-engineer every process, every workflow, every task, thus bringing tremendous opportunities and tangible value to organisations. However, there is a caveat. AI is really good when data is rich; otherwise “Garbage in, Garbage out”. In this context, I would like to highlight Gartner’s report which states that the failure of 80% of AI projects is due to lack of quality data, thus underscoring the critical role of Trusted Engineering Data.

In our opinion, Digital Twin acts as input and output validator for AI’s success. As much as clean and trusted data is key for accurately training AI models, the availability of the right set of knowledge brought forward by the Digital Twin becomes extremely critical in confining and limiting the recommendations of the AI model in the right engineering context.

Do we expect Digital Twins to evolve further with AI?

Today, accessing data with a click of a button is a common convenience, whether through smartphone applications, search engines, or platforms like LinkedIn, where you can instantly view someone’s professional history with just a single click. This convenience is similar to what is offered by the Digital Twin concept in the energy sector. We hear a lot about Digital Twin technology from vendors and consumers, but it’s important to understand that it goes beyond its general term.

Digital Twin is a multi-dimensional framework that combines the as-designed, as-built, and as operated states of an asset, covering its entire lifecycle from inception to decommissioning. One of the key factors in achieving this is the selection and deployment of the right set of tools.

For example, intelligent engineering systems ensure engineering data is populated and stored in compliance to guidelines, design tools that offer 3D and Spatial representation of the physical asset enabling immersive experiences, and finally asset information management tools that aggregate various types of information into a single pane of glass that users can interact with.

This by itself has brought a lot of convenience to the end user in the Energy industry and is seen today as a game changer, but with the infusion of AI technologies, we are witnessing a revolutionary shift.
The integration of Generative AI and advanced cognitive functions is setting a new standard in how we interact with these systems. Digital Twins will soon evolve into highly intelligent entities that serve as indispensable advisors to the users, offering not only just data replication but also strategic advice, expert guidance and ultimately autonomous decision making.

How do organisations justify investing in Digital Twin?

In addition to its value in leveraging AI in the right context, Digital Twins have demonstrated a lot of value over the past decade. The most critical KPI targets for industry leaders are safety, environment and production. In other words, the key challenge is how to meet production goals while ensuring both safety of personnel and compliance with environmental regulations.

While that sounds attainable, a seemingly small mistake whether at the shop level or in the engineering office, such as mislabeling a valve on a P&ID or a wrong property entered into a datasheet, can have severe consequences resulting in immediate equipment failure, leading to safety hazards, environmental damage, and financial losses. Let’s be reminded that one of the factors that led to the Deepwater Horizon catastrophic blowout in 2010 was errors in data interpretation.

Therefore, meticulous attention to detail and rigorous engineering data management are crucial to prevent such catastrophes. In this context, Digital Twin is nothing but a holistic framework that combines all efforts in ensuring consistent, complete, correct, and, most importantly accessible data to the operators and engineers to make informed decisions while ensuring safety across the entire lifecycle of the oil & gas assets.

How should organisations approach the deployment of Digital Twin within their enterprises?

We are frequently asked about the optimal deployment approach for digital twins. In
digitalisation, there’s no one-size-fits-all solution. While it may seem that companies face similar challenges, the specific nuances and depth of these challenges are unique to each company.

Therefore, the ideal approach should be determined on a case-by-case basis.
One approach is to start with a pilot scope, introducing the Digital Twin in a single asset, such as a unit, facility, or train, and then expanding it to other areas and plants. Another approach is to assess the current state, perform a gap analysis, and develop a targeted plan to address all the client’s needs and pain points. These approaches are iterative and dynamic in nature, requiring the involvement of key stakeholders to ensure that critical objectives are met first.

For example, in one of our recent engagements with a petrochemical company, equipment and instrument datasheets were identified as a top priority to address. This was crucial due to government regulations and industry guidelines essential for maintaining the operating licenses of their facilities. In brief, choosing the right approach greatly depends on the enterprise’s specific needs.

What sets ITCAN Solutions apart in enabling Energy companies to successfully implement Digital Twins?

At the heart of every successful business are its people. They not only drive operations but also uphold its values and goals. Our team embodies this principle, bringing together skilled professionals from various fields, such as engineering, petroleum, information management, maintenance, infrastructure, and design who collaborate to provide you with the best innovative solutions.

With extensive industry experience, especially within the Energy sector, we have a proven record of successfully working with numerous companies worldwide, which enables us to quickly identify areas for improvement and ensures that we have the necessary expertise to tackle any challenge.

Additionally, we are always at the forefront of evolving industry trends, ensuring that with our trusted engineering services, enterprises using or planning to leverage AI, can operate with confidence using trusted and reliable data. At ITCAN, we offer high-quality services tailored to your needs.