Search

The time-modulated active medium with linear independent frequency conversion method has been demonstrated to enable wave orientation and reconstruction. However, due to the symmetric scattering field, this technique requires intricate microcircuit designs. To overcome this limitation, this paper proposes a tunable piezoelectric metasurface based on acoustic black holes (ABHs) to redirect flexural wave reflections. The system can convert an incident flexural wave into a reflected wave of any direction and frequency. This is accomplished through the linear time modulation of the sensing signal, which breaks the constraints of Snell's law inherent in traditional designs and is insensitive to the incident amplitude. The coupling of the ABH damping system with a linear independent frequency conversion mechanism allows for the conversion of an incident flexural wave into a reflected wave in any direction and frequency while also eliminating the influence of second harmonic reflection on the wave field and simplifying the time modulation circuit. In addition, this paper demonstrates arbitrary angle reflection, focusing, beam splitting, and frequency conversion of the incident wave. By improving the flexibility of elastic wave manipulation, this paper introduces a new approach for active control of elastic waves and provides a design method that can be employed in a variety of applications ranging from vibration protection of engineering structures to vibration sensing and evaluation. [ABSTRACT FROM AUTHOR]

Laser-based powder bed fusion (L-PBF) has become the de facto choice for metal additive manufacturing (AM) processes. Even after considerable research investments, components manufactured using L-PBF lack consistency in their quality. Realizing the crucial role of the melt pool in controlling the final build quality, we predict the morphology of the melt pool directly from the build commands in an L-PBF process. We leverage machine learning techniques to predict quantitative attributes like the size as well as qualitative attributes like the shape of the melt pool. The area of the melt pool is predicted using an LSTM network. The outlined LSTM-based approach estimates the area with $ 90.7\% $ 90.7 % accuracy. The shape is inferred by synthesising the images of the melt pool by using a Melt Pool Generative Adversarial Network (MP-GAN). The synthetic images attain a structural similarity score of 0.91. The precision and accuracy of the results showcase the efficacy of the outlined approach and pave the way for real-time monitoring and control of the melt pool to build products with consistently better quality. [ABSTRACT FROM AUTHOR]

Community ambulation is essential for maintaining a healthy lifestyle, but it poses significant challenges for individuals with limb loss due to complex task demands. In wearable robotics, particularly powered prostheses, there is a critical need to accurately estimate environmental context, such as walking speed and slope, to offer intuitive and seamless assistance during varied ambulation tasks. We developed a user-independent and multicontext, intent recognition system that was deployed in real-time on an Open Source Leg (OSL). We recruited 11 individuals with transfemoral amputation, with seven participants used for real-time validation. Our findings revealed two main conclusions: (1) the user-independent (IND) performance across speed and slope was not statistically different from user-dependent (DEP) models in real-time and did not degrade compared to its offline counterparts, and (2) IND walking speed estimates showed ∼0.09 m/s mean absolute error (MAE) and slope estimates showed ∼0.95 deg MAE across multicontext scenarios. Additionally, we provide an open-source dataset to facilitate further research in accurately estimating speed and slope using an IND approach in real-world walking tasks on a powered prosthesis. [ABSTRACT FROM AUTHOR]

The takeover issue, especially the setting of the takeover time budget, is a critical factor restricting the implementation and development of conditionally automated vehicles. The general fixed takeover time budget has certain limitations, as it does not take into account the driver's non-driving behaviors. Here, we propose an intelligent takeover assistance system consisting of all-round sensing gloves, a non-driving behavior identification module, and a takeover time budget determination module. All-round sensing gloves based on triboelectric sensors seamlessly detect delicate motions of hands and interactions between hands and other objects, and then transfer the electrical signals to the non-driving behavior identification module, which achieves an accuracy of 94.72% for six non-driving behaviors. Finally, combining the identification result and its corresponding minimum takeover time budget obtained through the takeover time budget determination module, our system dynamically adjusts the takeover time budget based on the driver's current non-driving behavior, significantly improving takeover performance in terms of safety and stability. Our work presents a potential value in the application and implementation of conditionally automated vehicles. In this work, authors develop intelligent electronic gloves for Conditionally Automated Vehicles that dynamically adjust the time drivers have to take control based on real-time identification of non-driving behaviours improving takeover performance safety and stability. [ABSTRACT FROM AUTHOR]

Rain gauge measurements are one of the primary techniques used to estimate a precipitation field, but they require careful quality control. This paper describes a modified RainGaugeQC system, which is applied to real-time quality control of rain gauge measurements made every 10-min. This system works operationally at the national meteorological and hydrological service in Poland. The RainGaugeQC algorithms, which have been significantly modified, are described in detail. The modifications were made primarily to control data from non-professional measurement networks, which may be of lower quality than professional data, especially in the case of private stations. Accordingly, the modifications went in the direction of performing more sophisticated data control, applying weather radar data and taking into account various aspects of data quality, such as consistency analysis of data time series, bias detection, etc. The effectiveness of the modified system was verified based on independent measurement data from manual rain gauges, which are considered one of the most accurate measurement instruments, although they mostly provide daily totals. In addition, an analysis of two case studies is presented. This highlights various issues involved in using non-professional data to generate multi-source estimates of the precipitation field. [ABSTRACT FROM AUTHOR]

Introduction: Hybrid ventilation systems present a promising solution for reducing cooling energy consumption in buildings, particularly in hot climates. However, while existing research highlights their potential, variability in reported cooling energy reductions underscores the need for standardized performance evaluation methods. Methods: This review synthesizes findings from 84 research articles published between 2010 and the first quarter of 2024. The studies include simulation-based analyses, experimental investigations, and real-world case studies sourced from prominent academic databases. Results: The review identifies substantial potential for cooling energy reductions through hybrid ventilation systems. However, it also reveals significant variability in energy savings across studies, suggesting that further work is needed to standardize reporting methods for accurate performance comparisons. Discussion: To address these challenges, this paper proposes a framework integrating Industry 4.0 technologies. The framework emphasizes standardized research methodologies, context-specific design considerations, and robust knowledge dissemination strategies. Artificial Intelligence (AI) is positioned as a critical enabler of innovation, driving design optimization and smart control systems. The proposed framework aims to improve performance assessments, tailor system designs to specific building types and climates, and enable real-time control for enhanced energy efficiency and occupant comfort. This approach has the potential to support the wider adoption and optimized implementation of hybrid ventilation systems, contributing to a more sustainable and energy-efficient built environment, particularly in hot climates. [ABSTRACT FROM AUTHOR]

In response to the challenges posed by renewable energy integration, this study introduces a hybrid Attention-TCN-LSTM model for short-term photovoltaic (PV) power forecasting. The LSTM captures the sequence characteristics of PV output, which are then combined with the meteorological sequence features extracted by the Attention-TCN module. The model leverages the strengths of the TCN, the LSTM, and the self-attention mechanism to enhance prediction accuracy and construct reliable prediction intervals. Aiming to optimize both performance and efficiency, the PSO algorithm is used for hyperparameter optimization. Ablation studies and comparisons with other models confirm the effectiveness, accuracy and robustness of the proposed model. This hybrid approach contributes to improved renewable energy integration, offering a more stable and reliable energy supply. Future work will focus on incorporating intelligent systems for autonomous risk management and real-time control of dynamic PV output fluctuations. [ABSTRACT FROM AUTHOR]

Solar greenhouses are essential facilities for agricultural production in northern China, where uneven internal environments pose significant challenges. This study established a numerical model of photothermal conditions in solar greenhouses. Utilizing COMSOL MultiphysicsTM, we established a microclimate model that encompasses the greenhouse exterior and the soil directly below it, without considering the crops. This model coupled multiphysical fields with fluid flow and heat transfer processes. The boundary conditions and initial values of the external environment and soil were derived from meteorological data and an efficient interpolation function method, with the time step updated every 1h. The results demonstrate that the simulated values were in good agreement with the measured values. Our findings reveal the temporal dynamics of radiation and temperature changes, as well as spatial heterogeneity, within solar greenhouses under different winter weather conditions. Additionally, the potential of integrating with other real-time monitoring and control models was discussed. This study provides a theoretical foundation for developing microclimate models and predicting photothermal environments in greenhouses. [ABSTRACT FROM AUTHOR]

The ever-growing penetration of renewable energy with substantial uncertainties and stochastic characteristics significantly affects the modern power grid's secure and economical operation. Nevertheless, coordinating various types of resources to derive effective online control decisions for a large-scale power network remains a big challenge. To tackle the limitations of existing control approaches that require full-system models with accurate parameters and conduct real-time extensive sensitivity-based analyses in handling the growing uncertainties, this paper presents a novel data-driven control framework using reinforcement learning (RL) algorithms to train robust RL agents from high-fidelity grid simulations for providing immediate and effective controls in a real-time environment. A two-stage method, consisting of offline training and periodic updates, is proposed to train agents to enable robust controls of voltage profiles, transmission losses, and line flows using a state-of-the-art RL algorithm, soft actor–critic (SAC). The effectiveness of the proposed RL-based control framework is validated via comprehensive case studies conducted on the East China power system with actual operation scenarios. [ABSTRACT FROM AUTHOR]

Automating the extraction of mechanical fasteners from end-of-life (EOL) electronic waste is challenging due to unpredictable conditions and unknown fastener locations relative to robotic coordinates. This study develops a system for extracting cross-recessed screws using a Deep Convolutional Neural Network (DCNN) for screw detection, integrated with industrial robot simulation software. The simulation models the tooling, camera, environment, and robot kinematics, enabling real-time control and feedback between the robot and the simulation environment. The system, tested on a robotic platform with custom tooling, including force and torque sensors, aimed to optimize fastener removal. Key performance indicators included the speed and success rate of screw extraction, with success rates ranging from 78 to 89% on the first pass and 100% on the second. The system uses a state-based program design for fastener extraction, with real-time control via a web-socket interface. Despite its potential, the system faces limitations, such as longer cycle times, with single fastener extraction taking over 30 s. These challenges can be mitigated by refining the tooling, DCNN model, and control logic for improved efficiency. [ABSTRACT FROM AUTHOR]

Rising greenhouse gas emissions stemming from road transport have intensified the need for efficient and environmentally friendly propulsion technologies. Hybrid and fuel cell electric vehicles have emerged as a viable solution, integrating internal combustion engines and fuel cells with electric motors to optimize fuel efficiency and reduce emissions. This article reviews and analyzes energy management strategies for the principal powertrain topologies of hybrid electric vehicles, focusing on achieving solution optimality in real-time applications. A thorough and comprehensive overview of rule-based, optimization-based, and learning-based energy management strategies is presented, highlighting their main attributes and providing a comparative analysis in terms of fuel economy improvements, real-time implementation feasibility, and computational complexity, while simultaneously identifying and uncovering areas requiring further research in the field. We found that while rule-based methods offer simplicity and real-time capability, their adaptability remains limited. Optimization-based and learning-based approaches, although often achieving near-optimal solutions, face challenges due to their high computational demands and integration complexities. Our analysis also revealed the importance of leveraging vehicle connectivity and intelligent transportation systems for future energy management developments, which will contribute to broader sustainability goals in the automotive sector. [ABSTRACT FROM AUTHOR]

This work aims to develop and compare the performance of a line-following robot using both neural networks and classical controllers such as Proportional–Integral–Derivative (PID). Initially, the robot's infrared sensors were employed to follow a line using a PID controller. The data from this method were then used to train a Long Short-Term Memory (LSTM) network, which successfully replicated the behavior of the PID controller. In a subsequent experiment, the robot's camera was used for line-following with neural networks. Images of the track were captured, categorized, and used to train a convolutional neural network (CNN), which then controlled the robot in real time. The results showed that neural networks are effective but require more processing and calibration. On the other hand, PID controllers proved to be simpler and more efficient for the tested tracks. Although neural networks are very promising for advanced applications, they are also capable of handling simpler tasks effectively. [ABSTRACT FROM AUTHOR]

The accurate measurement of cooking vessel temperatures in induction hobs is crucial for ensuring optimal cooking performance and safety. To achieve this, improvements in existing measurement methods such as thermocouples, thermistors, and infrared (IR) temperature sensors are being explored. However, traditional IR sensors are sensitive to interference from the heated glass ceramic, severely affecting accuracy. This challenge is addressed by introducing a new sensor system with an optical filter designed to match the glass ceramic's optical characteristics. The theoretical model presented here proposes the separation of the total radiation reaching the IR sensor into components emitted by the cooking vessel and the glass ceramic. However, the radiation component originating from the glass ceramic mentioned here is significantly higher than the radiation component of the cooking vessel, which creates difficulties in measuring the temperature of the cooking vessel. Simulations and real cooking experiments validate the model and demonstrate that the optic filter significantly increases the contribution of pot radiation to the sensor measurement. This causes a more accurate reflection of the actual cooking vessel temperature, leading to improved temperature control and enhanced cooking experiences in domestic induction hob appliances. This research contributes to the field by innovatively addressing challenges in real-time temperature control for induction cooking appliances. The elimination of pot dependence and improved accuracy have significant implications for cooking efficiency, safety and food quality. [ABSTRACT FROM AUTHOR]

The effects of mechanical vibrations on control system stability could be significant in control systems designed on the assumption of rigid-body dynamics, such as launch vehicles. Vibrational loads can also cause damage to launch vehicles due to fatigue or excitation of structural resonances. This paper investigates a method to control structural vibrations in real time using a finite number of strain measurements from a fiber Bragg grating (FBG) sensor array. A scaled test article representative of the structural dynamics associated with an actual launch vehicle was designed and built. The main modal frequencies of the test specimen are extracted from finite element analysis. A model of the test article is developed, including frequency response, thruster dynamics, and sensor conversion matrices. A model-based robust controller is presented to minimize vibrations in the test article by using FBG measurements to calculate the required thrust in two cold gas actuators. Controller performance is validated both in simulation and on experiments with the proposed test article. The proposed controller achieves a 94% reduction in peak–peak vibration in the first mode, and 80% reduction in peak–peak vibration in the second mode, compared to the open loop response under continuously excited base motion. [ABSTRACT FROM AUTHOR]

Hazard-related data are a critical component in construction quality hazard management (CQHM). However, data security and latency issues in CQHM cannot be guaranteed in centralized systems currently and prevent it from achieving the goals of secure and efficient hazard analysis and further real-time quality process control. Focusing on these goals, a decentralized CQHM framework is proposed by introducing blockchain (BC) and deep learning (DL) technology. Moreover, considering the blockchain's limited storage capacity and block size, a deep learning–based multimodal storage strategy is designed with smart contracts and InterPlanetary File System (IPFS) for data lightweight. In accordance with the proposed framework, comparative experiments were conducted to demonstrate its feasibility by analyzing related metrics like accuracy, cost, and throughput. This study deepens the understanding of data security and latency issues in CQHM and offers technical guidance in establishing BC and DL solutions. Besides, the DL-based multimodal storage strategy provides a substantial data-driven advancement for lightweight on-chain data storage. Moreover, the proposed framework is promising to smooth the quality hazard analysis progress in improving on-site decision efficiency, promoting cooperation and standardizing quality process control. [ABSTRACT FROM AUTHOR]

Simultaneous regulation of multiple properties in next-generation tokamaks like ITER and fusion pilot plant may require the integration of different plasma control algorithms. Such integration requires the conversion of individual controller commands into physical actuator requests while accounting for the coupling between different plasma properties. This work proposes a tokamak and scenario-agnostic actuator-sharing algorithm (ASA) to perform the above-mentioned command-request conversion and, hence, integrate multiple plasma controllers. The proposed algorithm implicitly solves a quadratic programming (QP) problem formulated to account for the saturation limits and the relation between the controller commands and physical actuator requests. Since the constraints arising in the QP program are linear, the proposed ASA is highly computationally efficient and can be implemented in the tokamak plasma control system in real time. Furthermore, the proposed algorithm is designed to handle real-time changes in the control objectives and actuators' availability. Nonlinear simulations carried out using the Control Oriented Transport SIMulator illustrate the effectiveness of the proposed algorithm in achieving multiple control objectives simultaneously. [ABSTRACT FROM AUTHOR]

This paper proposes a leader–follower control method for multiple snake robot formation. Based on the simplified snake robot model, this work improves the traditional Serpenoid gait mode to a time-varying frequency form. Combined with the line-of-sight (LOS) method, a snake robot trajectory tracking controller is designed to enable the leader to track the desired trajectory at the ideal velocity. Then, the leader–follower following error system of a snake robot formation is established. In this framework, the follower can maintain a preset geometric position relationship with the leader to ensure the fast convergence of the formation location. Lyapunov's theory proves the stability of a snake robot formation error. Simulation and experimental results show that this strategy has the advantages of faster convergence speed and higher tracking accuracy than other current methods. • Based on a simplified snake robot model, a time-varying Serpenoid gait curve is proposed to control speed in real-time and solve traditional gait inefficiency. • This work presents the design of a snake robot trajectory tracker using LOS guidance and a time-varying Serpenoid gait, enabling the body can track the reference trajectory in accordance with the desired time-varying velocity. • A snake robot formation controller is designed based on the leader-follower idea so that the geometric position relationship between the robot follower and the leader can be maintained and converged to the formation position. [ABSTRACT FROM AUTHOR]

One of the most significant advantages of Model Predictive Control (MPC) is its ability to explicitly incorporate system constraints and actuator specifications. However, a major drawback is the computational cost associated with calculating the optimal control sequence at each sampling time, posing a substantial challenge for real-time implementation in high-order systems with fast dynamics. Additionally, uncertainties are inherently present in dynamic systems, requiring a robust formulation that accounts for these uncertainties. Additionally, uncertainties are inherently present in dynamic systems, requiring a robust formulation that accounts for these uncertainties. The tube-based MPC is one of the robustification formulations that can tackle these challenges. We propose a comprehensive methodology for designing a tube-based MPC framework specifically tailored for high-order Linear Parameter-Varying (LPV) systems with fast dynamics, along with its real-time implementation in embedded systems. Our innovations include the use of zonotopes for the offline computation of reachable sets, significantly reducing computational costs, and the development of new Linear Matrix Inequality (LMI) conditions that ensure the existence of nominal control and state sets. Additionally, we introduce a novel scaled-symmetric ADMM-based optimization algorithm, which diverges from conventional quadratic programming structures and integrates acceleration strategies and normalization techniques for enhanced numerical robustness and rapid convergence. The methodology is validated on a tiltrotor UAV with a suspended load, demonstrating its effectiveness in a trajectory tracking problem. Experimental results using a controller-in-the-loop (CIL) framework with a high-fidelity 3D simulator confirm its suitability for real-time control in practical scenarios. • A tube-based MPC approach for high-order LPV systems with fast dynamics. • A novel tube-based MPC designed for fast execution in embedded systems. • A zonotope-based formulation to compute the reachable sets for LPV systems • LMI conditions to obtain feedback gains, ensuring nominal control and state set existence • New LMI conditions for feedback gain computation, ensuring nominal set existence • Validation using CHIL and a 3D CAD-based simulator for a tiltrotor UAV. [ABSTRACT FROM AUTHOR]

This paper proposes a low-complexity model predictive current control (MPCC) strategy based on extended voltage vectors to enhance the computational efficiency and steady-state performance of three-phase series-winding permanent magnet synchronous motors (TPSW-PMSMs). Compared to conventional MPCC methods, this approach increases the number of candidate voltage vectors in the alpha–beta plane from 8 to 38, thereby achieving better steady-state performance. Specifically, the proposed method reduces the total harmonic distortion (THD) by 59%. To improve computational efficiency, a two-stage filtering strategy is employed, significantly reducing the computational burden. The number of voltage vectors traversed in one control period is reduced from 38 to a maximum of 4, achieving an 89% reduction in traversals. Additionally, to mitigate the impact of zero-sequence currents, zero-sequence current suppression is implemented within the control system for effective compensation. By combining low computational complexity, reliable steady-state performance, and real-time control capabilities, this strategy provides an efficient solution for TPSW-PMSM systems. Simulation results validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Test plants or laboratory prototypes are essential for developing training activities in engineering. In the field of automation and control, simulators or high-fidelity equipment models commonly used in industrial processes are necessary. These tools allow engineering trainees to gain experience working with devices similar to those they will encounter in their professional contexts. This paper presents the design and simulation of a fly-cutting plant for academic use. A 3D model was developed in SketchUp, incorporating features typical of industrial plants. The system's simulation was carried out in MATLAB R2023b using mathematical modeling. The primary contribution of this work is the design of a low-cost, compact industrial prototype that includes a conveyor belt and a continuous cutting mechanism, enabling the understanding and operation of large-scale industrial processes. Performance tests were conducted using MATLAB, Simulink, and Code Composer Studio. Subsequently, operational and cutting tests were performed using classical control techniques. Additionally, the design features of the fly-cutting plant, which can be easily implemented for process control training activities, are detailed. [ABSTRACT FROM AUTHOR]

Modern railway signalling systems are critical for ensuring the safe and efficient operation of railway networks. Educational institutions play a vital role in training students to design and implement these systems, replicating practical scenarios to bridge the gap between theory and application. Advanced electronic interlocking systems, such as SIMIS W, are widely used to manage complex signalling requirements in real-world railway environments. Existing model railway systems lack the capability to simulate advanced interlocking systems with real-time performance. This paper presents a model railway signalling system based on the SIMIS W interlocking system. The setup integrates ILTIS-N dispatcher workstations with a SIMATIC S7-1200 PLC, controlling signals, switches, and track circuits. A REST API ensures seamless data exchange between ILTIS-N and the PLC, achieving efficient system responsiveness. The system effectively replicates real-world signalling conditions with compatibility with existing protocols. Performance testing demonstrated a response time of approximately 1.2 s, achieving the design objective of a maximum 1.5 s. This ensures rapid and accurate signalling under real-time constraints. The developed system provides a practical educational platform for students to gain experience with advanced interlocking systems and serves as a basis for further research into scalable railway signalling solutions. [ABSTRACT FROM AUTHOR]

Non-Hermitian models describe the physics of ubiquitous open systems with gain and loss. One intriguing aspect of non-Hermitian models is their inherent topology that can produce intriguing boundary phenomena like resilient higher-order topological insulators (HOTIs) and non-Hermitian skin effects (NHSE). Recently, time-multiplexed lattices in synthetic dimensions have emerged as a versatile platform for the investigation of these effects free of geometric restrictions. Despite holding broad applications, studies of these effects have been limited to static cases so far, and full dynamical control over the non-Hermitian effects has remained elusive. Here, we demonstrate the emergence of topological non-Hermitian corner skin modes with remarkable temporal controllability and robustness in a two-dimensional photonic synthetic time lattice. Specifically, we showcase various dynamic control mechanisms for light confinement and flow, including spatial mode tapering, sequential non-Hermiticity on-off switching, dynamical corner skin mode relocation, and light steering. Moreover, we establish the corner skin mode's robustness in the presence of intensity modulation randomness and quantitatively determine its breakdown regime. Our findings extend non-Hermitian and topological photonic effects into higher synthetic dimensions, offering remarkable flexibility and real-time control possibilities. This opens avenues for topological classification, quantum walk simulations of many-body dynamics, and robust Floquet engineering in synthetic landscapes. Dynamic control of light flow in 2D synthetic landscapes is emerging as a valuable tool for the development of light-based technologies. Here the authors harness time-dependent non-Hermitian Hamiltonians to demonstrate dynamic control over the skin effect. [ABSTRACT FROM AUTHOR]

This paper presents a synthesis of higher-order control Lyapunov functions (HOCLFs) and higher-order control barrier functions (HOCBFs) capable of controlling nonlinear dynamic systems while maintaining safety. Building on previous Lyapunov and barrier formulations, we first investigate the feasibility of the Lyapunov and barrier function approach in controlling a non-affine dynamic system under certain convexity conditions. Then we propose an HOCLF form that ensures convergence of non-convex dynamics with convex control inputs to target states. We combine the HOCLF with the HOCBF to ensure forward invariance of admissible sets and guarantee safety. This online non-convex optimal control problem is then formulated as a convex Quadratic Program (QP) that can be efficiently solved on board for real-time applications. Lastly, we determine the HOCLBF coefficients using a heuristic approach where the parameters are tuned and automatically decided to ensure the feasibility of the QPs, an inherent major limitation of high-order CBFs. The efficacy of the suggested algorithm is demonstrated on the real-time six-degree-of-freedom powered descent optimal control problem, where simulation results were run efficiently on a standard laptop. [ABSTRACT FROM AUTHOR]

This study develops and validates a Reduced Order Model (ROM) integrated with Digital Twin technology for real-time temperature control in the Main Control Room (MCR) of a nuclear power plant. Utilizing Computational Fluid Dynamics (CFD) simulations, we obtained detailed three-dimensional thermal flow distributions under various operating conditions. A ROM was generated using machine learning techniques based on 94 CFD cases, achieving a mean temperature error of 0.35%. The ROM was further validated against two excluded CFD cases, demonstrating high correlation coefficients (R > 0.84) and low error metrics, confirming its accuracy and reliability. Integrating the ROM with the Heating, Ventilating, and Air Conditioning (HVAC) system, we conducted a two-month simulation, showing effective maintenance of MCR temperature within predefined criteria through adaptive HVAC control. This integration significantly enhances operational efficiency and safety by enabling real-time monitoring and control while reducing computational costs and time associated with full-scale CFD analyses. Despite promising results, the study acknowledges limitations related to ROM's dependency on training data quality and the need for more comprehensive validation under diverse and unforeseen conditions. Future research will focus on expanding the ROM's applicability, incorporating advanced machine learning methods, and conducting pilot tests in actual nuclear plant environments to further optimize the Digital Twin-based control system. [ABSTRACT FROM AUTHOR]

Real-time control (RTC) can be applied to optimize the operation of the anaerobic–anoxic–oxic (A2O) process in wastewater treatment for energy saving. In recent years, many studies have utilized deep reinforcement learning (DRL) to construct a novel AI-based RTC system for optimizing the A2O process. However, existing DRL methods require the use of A2O process mechanistic models for training. Therefore they require specified data for the construction of mechanistic models, which is often difficult to achieve in many wastewater treatment plants (WWTPs) where data collection facilities are inadequate. Also, the DRL training is time-consuming because it needs multiple simulations of mechanistic model. To address these issues, this study designs a novel data-driven RTC method. The method first creates a simulation model for the A2O process using LSTM and an attention module (LSTM-ATT). This model can be established based on flexible data from the A2O process. The LSTM-ATT model is a simplified version of a large language model (LLM), which has much more powerful ability in analyzing time-sequence data than usual deep learning models, but with a small model architecture that avoids overfitting the A2O dynamic data. Based on this, a new DRL training framework is constructed, leveraging the rapid computational capabilities of LSTM-ATT to accelerate DRL training. The proposed method is applied to a WWTP in Western China. An LSTM-ATT simulation model is built and used to train a DRL RTC model for a reduction in aeration and qualified effluent. For the LSTM-ATT simulation, its mean squared error remains between 0.0039 and 0.0243, while its R-squared values are larger than 0.996. The control strategy provided by DQN effectively reduces the average DO setpoint values from 3.956 mg/L to 3.884 mg/L, with acceptable effluent. This study provides a pure data-driven RTC method for the A2O process in WWTPs based on DRL, which is effective in energy saving and consumption reduction. It also demonstrates that purely data-driven DRL can construct effective RTC methods for the A2O process, providing a decision-support method for management. [ABSTRACT FROM AUTHOR]

This paper investigates the distributed formation control problem of underactuated unmanned surface vehicles (UUSVs) with uncertainties and disturbances and proposes a novel distributed formation controller. The proposed controller redefines the dynamic and kinematic models for each UUSV, which reduces the complexity of the underactuated controller design. Dynamic surface control (DSC) is employed to eliminate the repeated derivatives of the virtual control law, which is crucial for the generation of real-time control signals. The proposed controller integrates neural network approximation with MLP-based adaptive laws to enhance the model's resistance to disturbances. Then, an auxiliary adaptive law is designed for each UUSV to obtain a continuous controller under the compensation of approximate errors and disturbances. The results demonstrate that the controller achieves the desired goals for the formation control, and all control signals are guaranteed to be semi-global uniformly ultimately bounded (SGUUB). The final simulation results thoroughly prove the effectiveness of the theoretical results. [ABSTRACT FROM AUTHOR]

Featured Application: Proof-of-concept versions of mixed-reality applications for controlling and monitoring a digital twin-based roadheader with timeliness, accuracy, and reliability, and the general architecture of a mixed-reality digital twin monitoring system for a roadheader is constructed. The working environment of the coal mine boom-type roadheader is harsh with large blind areas and numerous safety hazards for operators. Traditional on-site or remote control methods do not meet the requirements for intelligent tunneling. This paper proposes a digital twin monitoring system of an EBZ-type roadheader based on mixed reality (MR). First, the system integrates a five-dimensional digital twin model to establish the boom-type roadheader digital twin monitoring system. Second, the Unity3D software (v2020.3.25f1c1) and the MR Hololens (v22621.1133 produced by Microsoft) are used to build a digital twin human–machine interaction platform, achieving bidirectional mapping and driving of cutting operation data. Third, a twin data exchange program is designed by employing the Winform framework and the C/S communication architecture, making use of the socket communication protocol to transmit and store the cutting model data within the system. Finally, a physical prototype of the boom-type roadheader is built, and a validation experiment of the monitoring system's digital twin is conducted. The experimental results show that the average transmission error of the cutting model data of the twin monitoring system is below 0.757%, and the execution accuracy error is below 3.7%. This system can achieve bidirectional real-time mapping and control between the twins, which provides a new monitoring method for actual underground roadheader operations. It effectively eliminates the operator's blind areas and improves the intelligence level of roadheader monitoring. Beyond mining, this methodology can be extended to the monitoring and control of other mining equipment, predictive maintenance in manufacturing, and infrastructure management in smart cities. [ABSTRACT FROM AUTHOR]

The voltage control of synchronous generators, particularly under varying load conditions, remains a significant and complex challenge in the field of engineering. Although various control methods have been implemented for automatic voltage regulator (AVR) systems to control the terminal voltage of synchronous generators, the PID-based control method continues to be one of the most basic and widely used approaches. Determining the optimal values for the Kp, Ki, and Kd values is essential to ensuring efficient and rapid performance in a PID controller. This study presents PLC-based PID controller tuning using an adaptive artificial bee colony–fuzzy logic (aABC-FL) approach for voltage control in a micro-hydro power plant installed as an experimental setup. The real-time control and monitoring of the system was conducted using an S7-1200 programmable logic controller (PLC) integrated with a totally integrated automation (TIA) portal interface and a SCADA screen. The aABC-Fuzzy design was developed using the MATLAB/Simulink platform, with PLC-MATLAB communication established through OPC UA and the KEPServerEX interface. The results obtained from experiments conducted under different load conditions showed that the proposed aABC-FL PID significantly minimized settling time and overshoot compared to the classical PLC-PID. Additionally, the proposed method not only provided a good dynamic response but also proved to be robust and reliable for real physical AVR systems. [ABSTRACT FROM AUTHOR]

Current Predictive Adaptive Cruise Control (PACC) systems pose significant challenges. These include poor collaborative optimisation between economic velocity and the powertrain system, conservative energy-saving strategies and underutilisation of map data due to real-time constraints. A computationally efficient collaborative optimisation method is proposed for economic following velocity and gear shifting based on Bi-level optimisation theory. Based on the Bi-level theory, economic following velocity and gear shifting are decoupled and hierarchically planned. The lower-level subproblem constructs the objective function based on a dynamic-weight safety distance model within the Model Predictive Control (MPC) framework, solving the economic following velocity by the Continuous Generalized Minimal Residual Method (C/GMRES). The upper-level subproblem solves the economic gear shifting by the optimal control law based on the economic following velocity. Finally, comparative experiments are conducted between the proposed PACC algorithm, a standard Adaptive Cruise Control (ACC) algorithm, and a benchmark Dynamic Programming-Model Predictive Control (DP-MPC) PACC algorithm. The results show that the proposed PACC algorithm reduces fuel consumption by approximately 5.76% compared to the ACC. Compared to the benchmark algorithm, the proposed PACC algorithm also demonstrates significantly improved computational efficiency while achieving comparable energy savings. [ABSTRACT FROM AUTHOR]

Microscopy is an indispensable tool for collecting biomedical information in pathological diagnosis, but manual annotation, measurement and interpretation are labor-intensive and costly. Here, we propose a task-driven framework powered by large models that excel in visual analysis and real-time control, paving the way for the next generation of microscopes. We achieve proof-of-concept success on clinical tasks, specifically in adaptive analysis of H&E-stained liver tissue slides. This work demonstrates the advanced capabilities for future digital pathology, setting a new standard for intelligent, efficient, and real-time analysis in clinical applications. A large model-powered smart microscope framework is developed to achieve adaptive decision-making and automated analysis by responding to the pathological features, accelerating the diagnostic paradigm of future digital pathology. [ABSTRACT FROM AUTHOR]