NoteTube

Industry Partners Series: how engineers design and run complex assets
1:40:11

Industry Partners Series: how engineers design and run complex assets

Engineers Australia

7 chapters8 takeaways14 key terms5 questions

Overview

This video explains how engineers design and operate complex electrical systems, focusing on the challenges posed by increasing electrification, digitalization, and AI. It introduces ETAP's "living digital twin" platform as a solution to integrate design, analysis, operation, and maintenance. The platform aims to create a unified, physics-based digital model that provides real-time insights, enables predictive maintenance, and supports complex decision-making across the entire asset lifecycle, ultimately leading to improved efficiency, reliability, and sustainability.

How was this?

Save this permanently with flashcards, quizzes, and AI chat

Chapters

  • The electrical industry faces unprecedented growth due to electrification, digitalization, and AI adoption, leading to more complex systems.
  • Global trends like population growth, climate change, and the demand for energy access are increasing power consumption.
  • The integration of renewables (like solar and wind) and distributed energy resources (DERs) makes grids dynamic and two-way.
  • Electrification of sectors like data centers and EVs, coupled with AI's massive power demands, creates non-linear and unpredictable load growth.
  • Traditional, disconnected systems struggle to cope with these complexities, leading to data silos, aging assets, and compliance issues.
Understanding these converging trends highlights the inadequacy of traditional engineering approaches and the urgent need for more sophisticated, integrated solutions to manage modern electrical infrastructure.
AI alone is projected to increase power consumption by 4x between 2023 and 2028, creating significant strain on existing electrical networks.
  • The lifecycle of electrical assets (design, build, operate, maintain) is plagued by fragmented information, with data lost or corrupted during handoffs between teams and tools.
  • This fragmentation leads to inefficiencies, higher costs, longer commissioning times, and inaccurate as-built information.
  • Electrical and process engineering domains often operate in isolation, despite critical interdependencies, leading to manual updates, rework, and inconsistencies.
  • The convergence of new technologies and operational demands exposes the limitations of these disconnected systems.
  • Digital transformation requires an end-to-end connected platform, a 'digital thread,' rather than just individual tools.
This chapter explains why current engineering practices are failing, emphasizing that the lack of data continuity and inter-domain integration is a root cause of inefficiency and risk in managing complex assets.
Data created during the initial design phase is often in a separate format and database from the data used by construction, maintenance, and operations teams, causing data loss and rework at each handover.
  • ETAP's solution is a physics-based digital twin, a unified platform that models the entire electrical power system lifecycle from design to operations and optimization.
  • Analogous to Google Maps or flight simulators, it provides real-time insights, predictive capabilities, and allows for virtual testing and planning.
  • The digital twin integrates all dimensions: design, analysis, build, construct, operate, maintain, automate, and optimize.
  • It goes beyond a simple digital thread to become an active blueprint with automated design, predictive analysis, and integrated power/process co-simulations.
  • This platform aims to create 'electric AI energy intelligence' by combining physical models, real-time data, historical data, and predictive simulations.
This introduces the core solution, explaining how a unified, physics-based digital twin addresses the fragmentation and isolation challenges by creating a single source of truth for all asset-related data and processes.
Like a flight simulator allows pilots to plan and practice in a virtual environment before actual flight, ETAP's offline simulation functions enable engineers to test and plan electrical system operations without real-world risk.
  • ETAP's digital twin facilitates seamless integration between electrical and process domains, crucial for complex facilities like green hydrogen plants.
  • It captures process flow diagrams and P&IDs to drive electrical design, analysis, and operational management.
  • This integration ensures that changes in one domain (e.g., process load) are accurately reflected in the other (e.g., power demand), preventing inconsistencies.
  • The platform covers the entire asset lifecycle, from inception to retirement, serving various user personas like project managers, engineers, and operators.
  • The principle of 'model once, use everywhere' ensures data continuity and consistency across all project phases and stakeholders.
This chapter emphasizes the critical need for cross-domain integration, showing how ETAP bridges the gap between electrical and process systems to achieve holistic optimization and business objectives.
In a green hydrogen plant, the digital twin models the electrolyzers and ammonia synthesis loop (process) to determine power demand, which then informs the electrical design, analysis, and real-time operational management of the power system.
  • The platform's architecture is built on the convergence of engineering technology (ET), operational technology (OT), and information technology (IT), offering openness and integration.
  • It supports over 20 OT and 10 IT industrial protocols, integrating data from field equipment and edge devices.
  • A unified database manages revisions, change management, and multiple configuration scenarios, ensuring a single source of truth.
  • ETAP 2026 introduces over 50 new features, including enhanced AI capabilities, cybersecurity, and extensive library models, built on nine pillars of innovation.
  • Key pillars include user experience, AI augmentation, cloud infrastructure, safety and protection, dynamics and transients, grid code compliance, asset management, interoperability, and energy intelligence.
This delves into the technical foundation, explaining how ETAP's architecture enables robust data integration, collaboration, and advanced functionalities necessary for a 'living digital twin'.
ETAP's integration with NVIDIA Omniverse creates a high-fidelity 3D virtual environment where electrical models are synchronized with the physical plant, enabling realistic simulations and operator training.
  • Energy intelligence is built on four core principles: a common ontology (shared model), physics-based validation, a semantic common language (consistent terminology), and real-time awareness.
  • This enables cross-domain autonomous reasoning, allowing the system to understand relationships and predict outcomes based on actual physics and real-time data.
  • ETAP's AI-native energy intelligence is distinct from generic AI; it's trained on specific ETAP digital twin data, understanding the user's plant, topology, and physics models.
  • The platform validates recommendations against physics models, ensuring safety and reliability, moving beyond purely data-driven insights.
  • This leads to a 'living engineering model' that continuously learns and adapts, driving smarter operations, predictive maintenance, and optimized asset performance.
This chapter clarifies the ultimate goal: transforming raw data into trustworthy, actionable intelligence that empowers engineers and operators to make informed decisions, improve safety, and enhance efficiency.
Instead of just alarming after a fault occurs, the system can predict how a disturbance will propagate through the network based on its understanding of asset ratings, relationships, and physics, allowing for proactive management.
  • A microgrid case study demonstrates how ETAP's digital twin can analyze the impact of adding a battery energy storage system (BESS).
  • The process involves defining inputs (equipment costs, load projections), using the digital twin for design and simulation, and analyzing outputs (financial metrics, operational efficiency).
  • A quasi-dynamic load flow simulation, which models both power system and control system interactions, is used to assess the battery's impact on optimal dispatch.
  • Results showed that adding a battery reduced overall fuel consumption by allowing generators to operate more efficiently and by leveraging solar energy.
  • The ETAP controller logic, validated in simulation, can be directly deployed to hardware, demonstrating the seamless transition from design to operation.
This practical example concretizes the benefits of using ETAP's digital twin, illustrating how it enables flexible analysis, optimizes system performance, and reduces operational costs through informed decision-making.
By adding a battery to a microgrid, fuel consumption was reduced from approximately 2,000 liters to 1,400 liters over a 6-hour simulation period, demonstrating significant cost savings and improved efficiency.

Key takeaways

  1. 1The increasing complexity of electrical systems driven by electrification, renewables, and AI necessitates a shift from disconnected tools to integrated, intelligent platforms.
  2. 2Fragmented data and isolated engineering domains are major sources of inefficiency, cost overruns, and operational risks in managing complex assets.
  3. 3ETAP's 'living digital twin' provides a unified, physics-based model that spans the entire asset lifecycle, from design to operation and maintenance.
  4. 4Integrating electrical and process domains within a single digital twin is crucial for holistic optimization and achieving business objectives in modern facilities.
  5. 5The platform's architecture supports seamless data flow, collaboration, and advanced analytics, powered by AI trained on specific system data.
  6. 6Energy intelligence, derived from a common ontology, physics validation, semantic language, and real-time awareness, transforms data into trustworthy, actionable insights.
  7. 7Using digital twins allows for 'model once, use everywhere,' ensuring data continuity, reducing rework, and enabling proactive management and predictive capabilities.
  8. 8The transition from design to operation is de-risked through virtual simulations, operator training, and the direct deployment of validated control logic.

Key terms

Digital TwinLiving Digital TwinElectric AI Energy IntelligencePhysics-Based ModelDigital ThreadAsset LifecycleElectrificationDistributed Energy Resources (DERs)Quasi-Dynamic Load FlowCommon OntologySemantic Common LanguageReal-time AwarenessModel Once, Use EverywhereInteroperability

Test your understanding

  1. 1What are the primary challenges introduced by the convergence of electrification, digitalization, and AI in electrical systems?
  2. 2How does ETAP's digital twin address the problem of fragmented data across the asset lifecycle?
  3. 3Explain the concept of 'energy intelligence' and its four core principles as presented in the video.
  4. 4What is the significance of integrating electrical and process domains within a digital twin, and how does ETAP facilitate this?
  5. 5How does ETAP's AI-native energy intelligence differ from generic AI, and why is this distinction important for trustworthiness?

Turn any lecture into study material

Paste a YouTube URL, PDF, or article. Get flashcards, quizzes, summaries, and AI chat — in seconds.

Summarize Your Own VideoSign up free

No credit card required