FEATURE MACHINE BUILDING, FRAMEWORKS & SAFETY
HYBRID DIGITAL TWINS
Revolutionising Industry 5.0 by powering
efficiency and sustainability. By Ron Beck, senior director, solutions marketing, AspenTech
growth and innovation. According to Fortune Business Insights, the global market for digital twins is expected to be worth US$259.32 billion by 2032, up from US$17.73 billion in 2024. That equates to a compound annual growth rate (CAGR) of 39.8% over that timeframe. In energy-intensive and hard to decarbonise
A
industries, digital twins are key to enhancing operational efficiency, driving decision-making and accelerating scale-up of low carbon innovation. Digital twins are dependent on access to operating and process data, and a crucial enabler is industrial AI – digital hybrid models that integrate domain expertise (engineering first principles) with AI-driven models. By merging the foundational understanding of physical processes with the predictive power of artificial intelligence, companies can deploy models that are continuously updated to reflect real-time operations, achieve unprecedented levels of precision and adaptability, and tie together systems across the value chain. One key innovation is using hybrid models as
feedback loops to rapidly diagnose operational and energy efficiencies and advise workers as to how to improve. This is crucial where new process technology is being introduced for green chemicals, for carbon removal and for hydrogen economy, for instance. After designing and building a first unit, the AI-enabled digital twin will drive improved economics and scale-up of the technology faster than envisioned. Envision Energy, for instance, is using this approach to take the results of their first commercial scale green ammonia installation and drive the cost of hydrogen and green ammonia down by 50%. Another innovation is using the same hybrid
model technology in operations to create detailed digital twin simulations of high-value manufacturing units. These models are extremely accurate and much faster to deploy then the previous generation, manually tuned systems, allowing digital twin technology to be extended to more operational units faster, achieving a better energy efficiency impact. The SOCAR energy company is deploying these hybrid models across multiple chemical units, in one case reducing energy use of the unit by more than 36%.
UNLOCKING MULTIPLE BENEFITS Hybrid digital twins offer business value along
s Industry 5.0 reshapes the industrial sector, digital twins continue to grow in importance as pivotal technology driving
several dimensions. Chief among them is operational agility. By simulating operational changes on the digital twin before applying them in actual plant operations, companies make more informed decisions, make them faster and more confidently, without risking operational integrity, and at the same time eliminating the trial-and- error approach. With this capability in place, a company can adjust swiftly to changed market fluctuations or supply chain disruptions, taking advantage of product and price opportunities. Additionally, hybrid digital twins enable
performance optimisation across multiple objectives. They are able to solve bigger models much more efficiently, using less compute power, getting results faster, and offering a comprehensive view of operations, across multiple plants and value chains, balancing factors such as production margins, yield, quality, emissions and energy sources and uses. By integrating these into a single model, companies can align economic and sustainability goals. Hybrid digital twins enhance process optimisation, resulting in higher production yields, reduced energy consumption, and lower costs. Real-time monitoring ensures operations run at peak efficiency. The technology also supports sustainability efforts, offering insights into energy use and emissions to reduce environmental impact and meet regulatory requirements.
CHALLENGES Despite the advantages, challenges remain in the widespread adoption of digital twin technology. One hurdle is the need to focus on use cases and manufacturing units where improved operations will generate significant economic value. Organisations must strategically prioritise resources to ensure maximum return on investment. Collaboration between manufacturers and digital solution providers will be key to share information in selecting the best use cases and in defining pathways to joint success. In refining and chemicals, strong use cases have included heat exchanger monitoring to maximise energy efficiency and digital twins of complex units with multiple chemical conversions going on inside that are difficult to measure. In digital grids, use cases include balancing power loads with renewable power and battery storage. There will be strong use cases for your business, and it will be important to focus early efforts in those areas. Another challenge is unlocking and ‘cleaning’ the right data to drive digital twins. Digital twins
22 DESIGN SOLUTIONS NOVEMBER 2024
sponsored by
rely on high-quality, real-time, data to span a broad range of operating conditions accurately. This necessitates a structured approach to data selection and data cleaning processes and policies to guarantee the digital twin receives reliable inputs. Without clean data, the effectiveness of a digital twin diminishes. To mobilise the data effectively, a modern data fabric solution that can unlock and contextualise information is an important component. Maintaining and updating digital twin models requires ongoing staff training and the establishment of business processes that sustain these models over time. Organisations need to build underlying understanding and trust in the digital technologies among operating staff, as well as to ensure that technical subject matter experts are available to keep models current.
BRIDGING THE SKILLS GAP Success in implementing digital twins demands an organisation structured for success. Creating teams that pair domain and operational knowhow (OT) with data and digital (IT), and AI knowhow, is a key predictor of success. Once this is done, one of the advantages of industrial AI approaches is its ability to act as an advisor to the operational and technical workers, helping a new generation of workers overcome their lack of experience. In fact, industrial-AI based digital twins are ideal upskilling tools, helping the next generation worker to understand the underlying technical systems, and why certain operational pathways are being recommended by the system. However, a recent IDC survey revealed that
nearly a fifth (18%) of manufacturing sector respondents had either ‘no’ or ‘limited’ awareness of digital twin technology, and only 40% reported ‘high awareness’. This highlights the need for educational initiatives and workforce development programmes to raise understanding levels across organisations. By investing in training and development, companies can empower their workforce to leverage digital twins effectively, driving innovation and competitive advantage.
LOOKING AHEAD As we advance further into the era of Industry 5.0, hybrid digital twins stand out as a transformative technology with the potential to revolutionise operations. By addressing the challenges and investing in the necessary skills and processes, organisations can unlock substantial economic and environmental benefits. Digital twins enhance operational efficiency and agility and support sustainability objectives by optimising energy use and reducing emissions. They provide a platform for continuous improvement, enabling companies to react to market changes and regulatory requirements. With the right approach, digital twins can serve as a catalyst for innovation, driving long-term success in an increasingly competitive and environmentally conscious market. As companies like Dow Chemical – which reported a 10% yield improvement on the first chemical process it applied hybrid models to – are finding, digital twins based on Industrial AI will unlock significant operational excellence, decarbonisation, and innovation value for a company.
AspenTech
www.aspentech.com/en
Feature
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60
