Predictive control for a single-blow cold upsetting using surrogate modeling for a digital twin

Summary In hole enlargement while drilling (HEWD) operations, underreamers are used extensively to enlarge the pilot hole. Reamer wipeout failure can cause additional bottomhole assembly (BHA) trips, which can cost operators millions of dollars. Excessive reamer shock and vibration are leading causes of reamer wipeout; therefore, careful monitoring of reamer vibration is important in mitigating such a risk. Currently, downhole vibration sensors and drilling dynamics simulations (DDSs) are used to comprehend and reduce downhole vibration, but vibration sensors cannot be placed exactly at the reamer to monitor the vibrations in real time. DDSs are difficult to calibrate and are computationally expensive for use in real time; therefore, the real-time reamer vibration status is typically unknown during drilling operations. A process digital twin using a hybrid modeling approach is proposed and tested to address the vibration issue. Large amounts of field data are used in advanced DDSs to calibrate the HEWD runs. For each HEWD section, calibrated DDSs are performed to comprehend the downhole vibration at the reamer and downhole vibration sensors. A surrogate regression model between reamer vibration and sensor vibration is built using machine learning. This surrogate model is implemented in a drilling monitoring software platform as a process digital twin. During drilling, the surrogate model uses downhole measurement while drilling (MWD) data as inputs to predict reamer vibration. Wipeout risk levels are calculated and sent to the operators for real-time decision-making to reduce the possibility of reamer wipeout. Large volumes of reamer field data, including field recorded vibration and reamer dull conditions were used to validate the digital twin workflow. Then, the process digital twin was implemented and tested in two reamer runs in the Gulf of Mexico. A downhole high-frequency sensor was placed 8 ft above the reamer cutting structure in one field run, and the recorded sensor vibration data and corresponding reamer dull conditions showed a very good match with the real-time digital twin predictions in a low-vibration scenario. Cases in high vibration are needed to fully validate the feasibility and accuracy of the digital twin. State-of-the-art downhole sensors, DDS packages, large amounts of field data, and a hybrid approach are the solutions to building, calibrating, and field testing the reamer digital twin to ensure its effectiveness and accuracy. Such a hybrid modeling approach can not only be applied to reamers but also to other critical BHA components.

An informed-decision making in managing risks due to climate-driven hazards for emergency response, designing preventive interventions, or policymaking for future requires either short-term and scenario-based assessments or long-term and uncertain assessments. Data requirements, spatial and temporal scales, observations required, and modelling techniques employed change drastically depending on the scope of the risk assessment. Digital twins (DT) in applications for natural hazards provide a great opportunity for significant improvements in disaster management. What makes DTs possible today is various technological advancements such as embedded sensors, cloud computing, edge computing, IoT. However, DTs also require a digital representation of the physical counterpart, mostly in the form of a computational or a data-driven model, to be able to predict future states. The utilisation of complex computational models in DTs is generally hindered by their relatively high computational budget and runtimes. A pathway to involve such models in (near) real-time decisions in DTs for geohazards is surrogate modelling. They are statistically valid representations of the computational model, into which physical laws and constraints can be embedded. Physics-compliant, physics-based or physics-informed surrogate models can facilitate DTs with i) instantaneous predictions, ii) the ability to conduct uncertainty quantification and sensitivity analysis to ensure reliability, iii) online updating of model parameters based on advanced calibration routines, iv) increased trust due to explainability based on physical laws. We present herein surrogate modelling as an enabler to replace computational models predicting the runout behaviour of geophysical flows. We investigate their applicability in uncertainty quantification, global sensitivity analysis, Bayesian parameter estimation, Bayesian model selection, and optimal experimental design. We demonstrate our workflow with two open-source computational models, r.avaflow 4.0 and synxflow, with synthetic and real-world case studies.

The move towards advanced manufacturing and Industry 4.0 is fed by increased demand for speeding up innovation, increasing flexibility, improving maintenance, and becoming more customized while saving on the total cost of operations. This is accompanied by increased dependence on virtual product and process development, data‐driven processes, and product knowledge. Other characteristics, affecting modern design, include big data intelligence in product, process, and maintenance. New technologies that empower data analytics include added manufacturing, flexible manufacturing, robotics, sensor technology, smart value/supply chains, and industrial information backbones. This paper is about surrogate models, also called digital twins, that provide an important complementary capacity to physical assets. Digital twins capture past, present, and predicted behavior of physical assets. Digital twin models are updated periodically to represent the current state of physical assets. This distinguishes digital twins from conventional simulations in that sensor data can continuously feed them. The type of curated information on the state of physical asset's history depends on how digital twins are used. For example, if a digital twin is used for fault classification, the history captured is operational data from equipment in healthy and faulty states. We provide here a review of digital twins, with an emphasis on Industry 4.0 applications.

We develop novel approaches to enhance the functionality and efficiency of digital twins through deep learning techniques. Digital twins, sophisticated virtual models of physical systems, serve as dynamic counterparts, mirroring real-world entities' behavior and performance. Their primary role includes real-time monitoring, flaw detection, automated control, and proactive maintenance. To perform such tasks it is necessary to use various methods from scientific computing to combine data with physics models. Furthermore, to assess the reliability of a digital twin, it is important to not only make predictions, but also quantify the uncertainty of estimations and predictions. In this regard, Bayesian methods serve as a natural framework to pose the problems. However, the complexity and real-time operation requirements pose significant computational challenges. The thesis explores the integration of deep learning in scientific computing for enabling digital twins. The focus is on overcoming the computational hurdles in real-time data assimilation and inverse problem-solving through surrogate modeling. Deep learning, with its capability to handle high-dimensional functions in both deterministic and stochastic settings is shown to be a viable solution to these challenges. This work investigates several key areas, beginning with a brief introduction to digital twins, data assimilation, and inverse problems. It proceeds to elaborate on the role of Bayesian inversion problems in static and dynamic contexts, highlighting the importance of uncertainty quantification. The focus is on the challenges of real-time computation and the potential of Bayesian methods, despite their computational intensity. The thesis investigates deep learning architectures like dense and residual neural networks, convolutional neural networks, recurrent neural networks and transformers. The core contributions are presented in the four main chapters of the thesis: 1) Reduced Order Modeling for Parameterized Time-Dependent Partial Differential Equations: Introducing a deep learning framework for solving parameterized PDEs using spatially and memory-aware neural networks, demonstrated on linear advection and incompressible Navier-Stokes equations. 2) Markov Chain Generative Adversarial Neural Networks: Enhancing Bayesian inversion for static problems with sparse observations using a unique algorithm combining MCMC and GANs, demonstrated on a Darcy flow problem and pipe flow leakage detection. 3) Probabilistic Digital Twin for Leak Localization: Developing a probabilistic framework using supervised Wasserstein Autoencoders for leak localization in water distribution networks, tested on several network models. 4) The Deep Latent Space Particle Filter: Proposing a real-time nonlinear data assimilation method for dynamic PDEs with uncertainty quantification, using transformer-based dimensionality reduction and time-stepping in particle filters, demonstrated on various dynamic systems. This thesis contributes significantly to digital twins, addressing computational limitations and opening new avenues for practical applications in various industries.

Deep-learning-enhanced digital twinning of complex composite structures and real-time mechanical interaction

A digital twin (DT), with the components of a physics-based model, a data-driven model, and a machine learning (ML) enabled efficient surrogate model, behaves as a virtual twin of the real-world physical process. In terms of Laser Powder Bed Fusion (L-PBF) based additive manufacturing (AM), a DT can predict the current and future states of the melt pool and the resulting defects corresponding to the input laser parameters, evolve itself by assimilating in-situ sensor data, and optimize the laser parameters to mitigate defect formation. In this paper, we present a deep neural operator enabled DT framework for closed-loop feedback control of the L-PBF process. This is accomplished by building a physics-based computational model to accurately represent the melt pool states, an efficient Fourier neural operator (FNO) based surrogate model to approximate the melt pool solution field, followed by a physics-based procedure to extract information from the computed melt pool simulation that can further be correlated to the defect quantities of interest (e.g., surface roughness). An optimization algorithm is then exercised to control laser input and minimize defects. On the other hand, the constructed DT also evolves with the physical twin via offline finetuning and online material calibration. For instance, the probabilistic distribution of laser absorptivity can be updated to match the real-time captured thermal image data. Finally, a probabilistic framework is adopted for uncertainty quantification. The developed DT is envisioned to guide the AM process and facilitate high-quality manufacturing in L-PBF-based metal AM.

Pharmaceutical manufacturing processes are moving towards automation and real-time process monitoring with the help of process analytical technologies (PATs) and predictive process models representing the real system. In this paper, we present a digital twin developed for an adjuvant manufacturing process involving a microfluidic formation of lipid particles. The twin uses a hybrid model for estimating the current state of the process and predicting system behavior in real time. The twin is used to control the adjuvant particle size, a critical quality attribute, by varying process parameters such as the temperature and inlet flow rates. We describe steps in the design and implementation of the twin, starting from the conception of the mechanistic model, up to the generation of its surrogate model used as state estimator, PATs and the setup of the information technology—Operational technology architecture. We demonstrate the performance of the twin by introducing different disturbances in the process and comparing the effect on the product critical quality attributes with and without the control of the digital twin. Finally, we showcase the digital twin implementation for the process in good manufacturing practice, through an engineering run, which demonstrated the robustness of the process when controlled by the digital twin.

The paper shows the feasibility of building closed-form and fast-to-evaluate surrogate models via supervised kernel-based machine learning regressions behaving as digital twins for computationally expensive multibody simulations. The aforementioned surrogate models are adopted to predict the railway vehicle dynamics safety indexes defined in the international standards, depending on the wheel-rail forces, directly from the results of longitudinal train dynamics simulations. The digital twin models are trained with the outputs of Simpack multibody simulations of a reference freight wagon, to which the in-train forces calculated by an in-house MATLAB longitudinal train dynamics simulator are applied. Two machine learning techniques are considered: the support vector machine and the least-squares support vector machine regressions. Both techniques ensure a good accuracy even with a limited number of training samples. The derivation of the surrogate models can strongly enhance the modelling capabilities of common longitudinal train dynamics simulators, that cannot evaluate the wheel-rail contact forces. At the same time, the method shown in the paper allows to strongly reduce the total computational times, as the evaluation of the closed-form surrogate models allows to effectively estimate the safety indexes with no need for computationally demanding multibody simulations.

This paper proposes a two-level, data-driven, digital twin concept for the autonomous landing of aircraft, under some assumptions. It features a digital twin instance (DTI) for model predictive control (MPC); and an innovative, real-time, digital twin prototype for fluid-structure interaction and flight dynamics to inform it. The latter digital twin is based on the linearization about a pre-designed glideslope trajectory of a high-fidelity, viscous, nonlinear computational model for flight dynamics; and its projection onto a low-dimensional approximation subspace to achieve real-time performance, while maintaining accuracy. Its main purpose is to predict in realtime, during flight, the state of an aircraft and the aerodynamic forces and moments acting on it. Unlike static lookup tables or regression-based surrogate models based on steady-state wind tunnel data, the aforementioned real-time digital twin prototype allows the DTI for MPC to be informed by a truly dynamic flight model, rather than a less accurate set of steady-state aerodynamic force and moment data points. The paper describes in detail the construction of the proposed two-level digital twin concept and its verification by numerical simulation. It also reports on its preliminary flight validation in autonomous mode for an off-the-shelf unmanned aerial vehicle instrumented at Stanford University. This article is part of the theme issue 'Data-driven prediction in dynamical systems'.

Digital twin-driven architecture for AIoT-based energy service provision and optimal energy trading between smart nanogrids

Digital twins (DTs) have witnessed a paramount increase in applications in multidisciplinary engineering systems. With advancements in structural health monitoring (SHM) methods and implementations, DT-based maintenance and operation stages have been implemented significantly during the life cycle of civil infrastructure. Recent literature has started laying the building blocks for incorporating the concept of DTs with SHM of large-scale civil infrastructure. This paper undertakes a systematic literature review of studies on DT-related applications for SHM of civil structures. It classifies the articles based on thematic case studies: transportation infrastructure (i.e. bridges, tunnels, roads, and pavements), buildings, off-shore marine infrastructure and wind turbines, and other civil engineering systems. The proposed review is further uniquely sub-classified using diverse modeling approaches such as building information modeling, finite element modeling, 3D representation, and surrogate and hybrid modeling used in DT implementations. This paper is solely focused on applications relating DTs to SHM practices for various civil engineering infrastructures, hence highlighting its novelty over previous reviews. Gaps and limitations emerging from the systematic review are presented, followed by articulating future research directions and key conclusions.

Amid urgent climate goals, the building sector’s high energy use demands smarter design and operation strategies. This paper critically explores recent peer-reviewed literature on AI-enhanced Building Information Modeling (BIM) systems for real-time energy performance simulation, highlighting how artificial intelligence (AI) techniques are integrated with BIM to improve building energy efficiency, reviewing global studies that combine BIM-based energy modeling with machine learning, optimization algorithms and digital twin frameworks. Key findings indicate that AI can dramatically accelerate energy simulations and enable real-time predictive analysis in both design and operational phases. Surrogate models (neural networks and gradient-boosted trees) trained on BIM-generated data achieve prediction accuracies above 90%, providing instant feedback on design alternatives. In operation, AI-driven digital twins linking BIM with IoT sensor data allow continuous monitoring and predictive control of building systems. These approaches have led to significant energy savings (often >10%) and support net-zero energy goals. However, challenges persist in data interoperability, model generalization and industry adoption. This paper contributes an integrated perspective on current methods, empirical outcomes and emerging themes (explainable AI and uncertainty analysis), outlining future research directions to fully realize real-time energy simulation in smart sustainable buildings.

The increasing integration of renewable energy sources, such as solar photovoltaics, wind turbines, hydropower, and energy storage systems, introduces substantial variability and complexity into modern power grids. This variability challenges grid stability, supply-demand balancing, and operational resilience. Digital twin (DT) technology, which provides a dynamic, real-time virtual representation of physical assets and systems, has emerged as a transformative tool for monitoring, analyzing, and optimizing energy grids. The incorporation of artificial intelligence (AI) into digital twins further enhances their capabilities, enabling predictive analytics, adaptive control, fault detection, and real-time decision-making for grid-specific objectives such as voltage/frequency regulation, congestion management, DER coordination, curtailment reduction, and resilience under fast renewable ramps. Machine learning, deep learning, and reinforcement learning techniques facilitate accurate forecasting of energy generation and demand, intelligent dispatch of distributed energy resources, and predictive maintenance, while hybrid models combining physics-based simulations with AI improve prediction accuracy in data-sparse or high-uncertainty environments. Despite these advancements, challenges persist, including data quality and availability, computational scalability, cybersecurity risks, and interoperability issues. This review synthesizes current research on AI-driven digital twins in renewable energy grids, highlights methodological and technological gaps, and identifies future research directions for developing resilient, scalable, and adaptive energy systems. The findings underscore the potential of AI-integrated digital twins to accelerate the transition toward intelligent, sustainable, and climate-resilient energy infrastructures. In addition, this review incorporates sustainability-oriented intelligent-system methodologies such as energy-aware edge–cloud cyber-physical architectures and digital-twin-enabled lifecycle sustainability frameworks to align DT optimization with contemporary sustainability practice better.

Digital twin technology has emerged as a transformative force in modern engineering. It allows real-time interrelations of physical and virtual resources to be used in the process of monitoring, optimization, and predictive control. This review examines the mathematical foundations and simulation frameworks that support the creation of digital twins, with particular focus on electromagnetic and energy transmission systems. It explores the integration of classical mathematical models that are based on Maxwell equations, finite elements, and model order reduction with modern data-driven and hybrid model strategies to boost accuracy and scalability. The paper also evaluates the progress made in simulation architectures with key features of co-simulation, hardware-in-the-loop testing, and data standards that work together to ensure coordination between the physical and digital worlds. Nevertheless, although there is significant advancement in the accuracy of computing and integration across domains, there are still issues of standardization, cybersecurity, and real-time data assimilation. The paper concludes that to develop digital twins applications in energy and electromagnetic systems, it is important to have unified modeling frameworks, enhanced interoperability protocols, and adaptable algorithms that combine physics-based accuracy with intelligent automation. Such insights lay the basis of future research that would help to come up with resilient, secure, and self-optimizing energy systems.

The convergence of Industrial Internet of Things (IIoT) and digital twin technology offers new paradigms for process automation and control. This paper presents an integrated IIoT and digital twin framework for intelligent control of a gas–liquid separation unit with interacting flow, pressure, and differential pressure loops. A comprehensive dynamic model of the three-loop separator process is developed, linearized, and validated. Classical stability analyses using the Routh–Hurwitz criterion and Nyquist plots are employed to ensure stability of the control system. Decentralized multi-loop proportional–integral–derivative (PID) controllers are designed and optimized using the Integral Absolute Error (IAE) performance index. A digital twin of the separator is implemented to run in parallel with the physical process, synchronized via a Kalman filter to real-time sensor data for state estimation and anomaly detection. The digital twin also incorporates structured singular value (μ) analysis to assess robust stability under model uncertainties. The system architecture is realized with low-cost hardware (Arduino Mega 2560, MicroMotion Coriolis flowmeter, pneumatic control valves, DAC104S085 digital-to-analog converter, and ENC28J60 Ethernet module) and software tools (Proteus VSM 8.4 for simulation, VB.Net 2022 version based human–machine interface, and ML.Net 2022 version for predictive analytics). Experimental results demonstrate improved control performance with reduced overshoot and faster settling times, confirming the effectiveness of the IIoT–digital twin integration in handling loop interactions and disturbances. The discussion includes a comparative analysis with conventional control and outlines how advanced strategies such as model predictive control (MPC) can further augment the proposed approach. This work provides a practical pathway for applying IIoT and digital twins to industrial process control, with implications for enhanced autonomy, reliability, and efficiency in oil and gas operations.