Articles tagged with "digital-twin"
Swiss startup turns NASA-inspired Mars tech into jet crack detector
Mondaic, a Swiss startup spun off from ETH Zurich, has adapted wave physics software originally developed to study Mars’s interior for use in monitoring infrastructure safety on Earth. Founded in 2018 by Christian Boehm and colleagues, the company repurposed modeling tools from NASA’s InSight Mars mission to non-invasively detect hidden structural flaws such as cracks, voids, and water infiltration in bridges, pipelines, and aircraft parts. Their technology works by sending waves through solid objects and comparing the wave behavior to a precise digital twin model, enabling identification and localization of damage without drilling or cutting. Transitioning from a research tool to a practical product required making the software stable, user-friendly, and fully automated. Leveraging cloud computing, Mondaic’s platform now performs complex wave analyses rapidly and is accessible to infrastructure teams without specialized wave physics knowledge. The system is currently employed in collaboration with the Swiss Federal Roads Office to inspect bridges, detecting early signs of damage to enable timely maintenance. Beyond
materialsinfrastructure-monitoringwave-physicsdigital-twinnon-destructive-testingcloud-computingstructural-health-monitoringMicrosoft’s light-powered computer could run AI 100x faster
Microsoft Research has developed a prototype analog optical computer (AOC) that uses beams of light instead of electrons to perform computations. This novel approach enables the AOC to solve complex optimization problems and potentially run artificial intelligence (AI) workloads with up to 100 times greater speed and energy efficiency compared to traditional silicon-based digital processors. The prototype is constructed from commercially available components such as micro-LEDs, optical lenses, and smartphone camera sensors, which could facilitate cost-effective mass production. Additionally, the team created a “digital twin” software model that simulates the hardware’s behavior, allowing researchers to test and scale AI and optimization tasks and collaborate externally. Early demonstrations of the AOC’s capabilities include optimizing financial transactions in partnership with Barclays Bank, where it efficiently handled thousands of delivery-versus-payment securities transactions among multiple parties, showcasing its potential impact on large-scale financial systems. In healthcare, the digital twin was used to reconstruct MRI scans with promising accuracy, suggesting the technology could reduce scan times from 30
energyoptical-computingAI-accelerationmicro-LEDanalog-computingMicrosoft-Researchdigital-twinThe Paradox Of American Technological Leadership In Renewable Energy - CleanTechnica
The article highlights a paradox in American technological leadership in renewable energy: while U.S. politics increasingly emphasize inward-looking, “America First” policies, American technology companies like AWS, Bentley, and Rockwell Automation are deeply integrated into the global renewable energy industry. These firms provide essential technological infrastructure—such as automation systems, digital twins, and cloud platforms—that enable renewable energy projects worldwide, from solar farms in India to wind farms in Denmark. This global deployment underscores a form of American leadership that prioritizes solving international challenges, reflecting a broader vision that transcends national boundaries and political rhetoric. Furthermore, the article emphasizes that this technological leadership is not solely the product of private enterprise but rests on decades of foundational research and collaboration supported by federal agencies like NASA, the Department of Energy, and the National Institute of Standards and Technology. These institutions provide critical data, materials research, and cybersecurity frameworks that underpin the renewable energy sector’s advancements. The multinational and diverse talent driving innovation within these companies further illustrates the necessity of global
energyrenewable-energyautomation-systemsdigital-twinglobal-technologyenergy-transitionAmerican-technologyAutomation Needed to Foward Renewable Energy Transition in Developing Nations - CleanTechnica
The article from CleanTechnica emphasizes that the global transition to renewable energy is fundamentally a technological revolution reliant on sophisticated automation and data intelligence systems. Beyond the physical deployment of solar panels and wind turbines, the integration of advanced control systems—such as programmable logic controllers and modernized SCADA platforms—is critical for optimizing operational efficiency, predictive maintenance, and managing intermittency challenges. Large-scale Battery Energy Storage Systems (BESS) and emerging technologies like green hydrogen production depend heavily on precise automation to ensure grid stability and safe, efficient operation. A significant innovation highlighted is the use of digital twins—virtual replicas of physical assets—that enable engineers to simulate and optimize renewable energy systems before real-world implementation. Leading American companies like AWS, Bentley Systems, and Rockwell Automation are at the forefront of this transformation, offering cloud infrastructure, digital twin platforms, and integrated control systems. Their approach reflects a broader American innovation philosophy aimed at addressing global-scale challenges through scalable, interconnected industrial automation solutions, exemplified by Rockwell Automation’s “
energyrenewable-energyautomationSCADAbattery-energy-storage-systemsdigital-twinindustrial-control-systemsBetterFleet's Software Helps Fleets Transition to Electric Vehicles - CleanTechnica
BetterFleet offers an advanced software suite designed to assist fleet managers in transitioning from diesel or natural gas vehicles to electric vehicles (EVs). While purchasing EVs may seem straightforward, the complexities of integrating charging infrastructure, route optimization, and cost management present significant challenges. BetterFleet addresses these issues by creating digital twins—virtual simulations of real-world routes and fleet operations—that incorporate variables such as weather, driver behavior, and vehicle load. This approach enables fleet managers to model and forecast the performance and costs of electric or mixed fleets with high accuracy, reducing downtime and improving operational predictability. The software also forecasts charging needs for fully or partially electrified fleets, helping managers plan infrastructure and financial investments more effectively. By leveraging real-world data and continuous model refinement, BetterFleet provides a holistic solution that integrates fleet management, financial forecasting, and infrastructure planning. This allows fleet operators to simulate various scenarios and make informed decisions without costly trial-and-error pilots, ultimately supporting a smoother, more cost-effective transition to zero-emission fleets
energyelectric-vehiclesfleet-managementdigital-twinbattery-electric-truckscharging-infrastructuresoftware-solutionIBM and NASA Develop a Digital Twin of the Sun to Predict Future Solar Storms
IBM and NASA have collaboratively developed Surya, an advanced AI foundation model that creates a digital twin of the Sun to improve predictions of solar storms. Trained on nine years of data from NASA’s Solar Dynamics Observatory (SDO), Surya processes high-resolution images and magnetic field measurements to better understand solar activity, particularly solar flares—bursts of electromagnetic radiation that can endanger astronauts and disrupt Earth’s technology infrastructure. By unifying diverse solar datasets and employing a long-range vision transformer architecture enhanced with spectral gating, Surya efficiently analyzes complex solar data with reduced noise and memory usage. Surya distinguishes itself by learning directly from raw data without extensive labeling, enabling faster adaptation and more accurate predictions. In tests, it integrated data from multiple solar observation instruments and outperformed traditional models by providing a two-hour advance warning of solar flares—double the typical one-hour lead time—and improved flare classification accuracy by 16 percent. NASA highlights Surya’s adaptable architecture, which could extend beyond heliophysics to
energysolar-energydigital-twinAI-predictionsolar-stormsNASAIBMWorld’s fastest supercomputer boosts US tsunami warning systems
US scientists at Lawrence Livermore National Laboratory (LLNL) have developed a real-time tsunami forecasting system powered by El Capitan, the world’s fastest supercomputer with a peak performance of 2.79 quintillion calculations per second. Utilizing over 43,500 AMD Instinct MI300A Accelerated Processing Units, the system solves complex acoustic-gravity wave propagation problems to create a detailed "digital twin" model of tsunami behavior. This model integrates real-time seafloor pressure sensor data with advanced physics-based simulations to infer earthquake-induced seafloor motion and predict tsunami wave propagation with quantified uncertainties, enabling rapid forecasts during actual events. The breakthrough hinges on solving a billion-parameter Bayesian inverse problem with unprecedented speed—less than 0.2 seconds—achieving a 10-billion-fold speedup compared to previous methods. This was made possible by leveraging El Capitan’s exascale computing power in an offline precomputation step, allowing subsequent rapid predictions on smaller GPU clusters. The system
energyIoTsupercomputingtsunami-warning-systemsdigital-twinsensor-datareal-time-forecastingRobots pack groceries in record-time at fully automated warehouse
Ocado’s fully automated warehouse system, known as the Hive, revolutionizes online grocery fulfillment by using fleets of AI-controlled robots to pick and pack orders in record time. Operating within a massive 3D grid holding thousands of grocery items, these bots move at speeds up to 9 miles per hour, communicating with a central AI system multiple times per second to efficiently collect products. Robotic arms then pack orders using computer vision and deep learning, arranging items to maximize space and protect fragile goods. This process can complete a 50-item order in just five minutes—six times faster than traditional manual picking. The Hive’s technology integrates artificial intelligence, robotics, and automation, supported by a digital twin—a virtual replica of the warehouse—that enables Ocado to simulate operations, optimize efficiency, and plan delivery routes without disrupting real-world activity. The system’s modular design allows it to scale flexibly, accommodating various warehouse sizes and locations, while storing up to 78 percent more products than typical supermarkets. This results
roboticsautomationAIwarehouse-automationdigital-twinsmart-logisticsgrocery-fulfillmentGerman robot works at construction site, helps humans to build wall
A German robot developed by the Technical University of Munich (TUM) is assisting humans on a construction site by precisely placing bricks to build a climate-optimized wall. The robot, equipped with a gripper and mounted on a mobile base, can move along a 4 x 2.5 meter wall and uses a digital twin of the structure to integrate assembly logic directly into the design process. This collaboration enhances precision beyond human capability without replacing skilled craftsmen, instead complementing their work. Apprentices working alongside the robot have adapted to this new method, highlighting that collaborative robotics expands craftsmanship rather than displacing it. The project emphasizes simpler, sustainable construction using only bricks arranged in multiple layers to create a thicker, climate-resilient wall. Different types of bricks—weather-resistant clinker on the outside and insulating perforated bricks inside—are used to improve durability and insulation. This monomaterial approach also facilitates easier dismantling and reusability, aligning with goals for sustainable urban building envelopes informed by climatic simulations
roboticsconstruction-robotcollaborative-robotsdigital-twinprecision-buildinghuman-robot-collaborationautomated-bricklayingArena simulation platform designed to accelerate Gatik autonomous trucking - The Robot Report
Gatik AI Inc. has launched Arena, a new simulation platform designed to accelerate the development and validation of its autonomous vehicles (AVs) by generating structured, controllable synthetic data. Arena addresses the limitations of traditional real-world data collection, which is time-consuming, expensive, and often unsafe, especially when capturing rare or high-risk scenarios. The platform uses advanced AI techniques such as neural radiance fields (NeRFs), 3D Gaussian splatting, and diffusion models to create photorealistic, high-fidelity simulations from various data inputs like segmentation maps, lidar, and HD maps. This enables comprehensive, closed-loop testing of the full autonomy stack, including multiple sensors (cameras, lidar, radar) and vehicle dynamics, while allowing scenario editing and A/B testing to simulate diverse environmental and traffic conditions. Arena aims to reduce the sim-to-real gap significantly, providing synthetic data that is sufficient for Gatik’s safety case and machine learning workflows without heavy reliance on annotated real-world data.
robotautonomous-vehiclessimulation-platformAIdigital-twinsensor-simulationautonomous-truckingAmazon cloud powers US bid for autonomous next-gen nuclear reactors
Idaho National Laboratory (INL) and Amazon Web Services (AWS) have partnered to leverage AWS’s cloud computing, AI foundation models via Amazon Bedrock, and specialized hardware to advance next-generation autonomous nuclear reactors. The collaboration aims to reduce the cost and time involved in designing, licensing, building, and operating nuclear facilities, with the long-term goal of enabling safe, reliable autonomous operation of advanced reactors to accelerate their deployment. INL will utilize AWS’s AI models and computing power to develop nuclear energy applications, including creating a digital twin—a virtual simulation model—of a small modular reactor (SMR) as a key initial project. This initiative is part of a broader strategy to foster collaboration among government labs, AI firms, and nuclear developers, enhancing reactor safety, efficiency, and responsiveness. The digital twin technology will allow near real-time simulations critical for autonomous control systems. The effort aligns with a growing trend of integrating AI into nuclear energy, exemplified by similar work at Oak Ridge National Laboratory, which
energynuclear-energyautonomous-reactorsAI-in-energycloud-computingdigital-twinsmall-modular-reactorsHitachi's metaverse for nuclear plants to boost design efficiency
Hitachi has launched a "Metaverse Platform for Nuclear Power Plants" aimed at enhancing design efficiency, safety, and maintenance operations within nuclear facilities. The platform recreates nuclear plants in a virtual metaverse environment using high-precision point cloud and 3D CAD data, allowing authorized users to navigate intuitively between plant floors and resume visits from previous locations. It supports simultaneous multi-user access for real-time communication and decision-making among geographically dispersed stakeholders, integrating engineering tools such as centimeter-level measurement, virtual meetings, annotations, and asset information linking to assist with precise planning and execution. The platform addresses challenges in nuclear plant operations, such as restricted access to controlled zones during operation and limited on-site surveys due to regulatory constraints. These factors complicate coordination among electric utilities, contractors, and other stakeholders. Additionally, Japan’s nuclear industry has faced workforce challenges, including retirements of skilled personnel and reduced training opportunities following the Great East Japan Earthquake. Hitachi’s metaverse platform aims to mitigate these issues by facilitating
energynuclear-powermetaverseAI-technologydigital-twinplant-maintenancedata-driven-power-plantMicrorobot system is designed to float inside stroke patient for autonomous thrombectomy - The Robot Report
robotthrombectomymicrorobotmedical-technologyautonomous-systemsdigital-twinhealthcare-innovationBlack Hawk successor: US virtually flies tiltrotor aircraft of future
robotIoTdigital-twinvirtual-prototypeaviation-technologytiltrotormilitary-technologyPUR-1: First US nuclear reactor digital twin achieves 99% accuracy
energynucleardigital-twinAIremote-monitoringreactor-technologycarbon-free-electricity