Real-time Dynamic Control Research Articles

Online multi-agent deep reinforcement learning platform for distributed real-time dynamic control of power systems

AbstractIn recent years, multi-agent deep reinforcement learning (MADRL) has made significant strides in power system decision-making and control. However, there is a scarcity of high-fidelity, real-time platforms for testing various DRL control algorithms in detailed power systems. Motivated by EtherCAT communication and DRL features, this study presents a MADRL online testing platform for distributed real-time dynamic control of power systems. The platform utilizes the Opal-RT real-time simulator for real-time simulation of dynamic power system environments and uses multiple AI workstations for the implementation of MADRL control algorithms. The proposed platform facilitates real-time interaction among AI workstations and the Opal-RT real-time simulator by leveraging the EtherCAT communication protocol to transmit system information and control signals. It enables the online and real-time training of distributed MADRL algorithms for power system dynamic control. The effectiveness and advantages of the proposed platform have been validated through detailed case studies of testing distributed MADRL algorithms for classical power system control problems.

Enhancing Obstacle Tracing in Self-Driving Cars by Combining Infrared Camera and Radar Sensor.

Building safe and reliable autonomous vehicles depend on accurate and efficient obstacle detection and tracing systems. On the other hand, this paper focuses on improving obstacle tracing in autonomous cars by employing infrared sensors and radar cameras within the framework of Bayesian networks. The proposed system merges the capabilities of the two sensors to enhance the fidelity and consistency of the interpretation of the external environment concerning obstacle detection. A Bayesian network is used to describe the uncertainty associated with each sensor, obstacle complexity, and environmental variables which, in turn, enable real-time interaction and dynamic control. The experiments' results are a good validation of the hypothesis, showing that the proposed system enhances the accuracy of obstacle tracing, decreases the number of false positives and negatives, and improves the safety and efficacy of self-driving cars. Keywords - Self-driving cars, Bayesian Networks, Infrared Sensors, Radar Cameras, Obstacle Detection, Sensor fusion.

Robust dynamic real-time control strategies for high-frequency bus service: a multi-agent reinforcement learning framework

This study addresses the multifaceted challenge of ensuring the regularity of bus services, minimizing bus bunching, and facilitating synchronized bus connections across routes. An enhanced multi-agent reinforcement learning algorithm, namely the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, is proposed to implement real-time control strategies for addressing these issues simultaneously. The merit of the modified MADDPG algorithm lies in its ability to continuously learn while adeptly navigating the non-stationary operating nature of bus system networks. A case study of a bus corridor is used to train and test the algorithm. Four robust scenarios, each presenting varying degrees of travel time and dwell time variations, are designed to assess the algorithm’s robustness. Results indicate that the MADDPG algorithm can significantly increase the likelihood of synchronized bus transfers across multiple routes by two or three times while maintaining the service reliability on each route. Moreover, the flexibility of the MADDPG algorithm in training bus policies allows it to effectively adapt to up to 90% variations in bus travel times and demand changes, even amid disruptive events in real-world scenarios.

Development and Application of Digital Twin Control in Flexible Manufacturing Systems

Flexible manufacturing systems (FMS) are highly adaptable production systems capable of producing a wide range of products in varying quantities. While this flexibility caters to evolving market demands, it also introduces complex scheduling and control challenges, making it difficult to optimize productivity, quality, and energy efficiency. This paper explores the application of digital twin technology to tackle these challenges and enhance FMS optimization and control. A digital twin, constructed by integrating simulation models, data acquisition, and machine learning algorithms, was employed to replicate the behavior of a real-world FMS. This digital twin enabled real-time dynamic optimization and adaptive control of manufacturing operations, facilitating informed decision making and proactive adjustments to optimize resource utilization and process efficiency. Computational experiments were conducted to evaluate the digital twin implementation on an FMS equipped with robotic material handling, CNC machines, and automated inspection. Results demonstrated that the digital twin significantly improved FMS performance. Productivity was enhanced by 14.53% compared to conventional methods, energy consumption was reduced by 13.9%, and quality was increased by 15.8% through intelligent machine coordination. The dynamic optimization and closed-loop control capabilities of the digital twin significantly improved overall equipment effectiveness. This research highlights the transformative potential of digital twins in smart manufacturing systems, paving the way for enhanced productivity, energy efficiency, and defect reduction. The digital twin paradigm offers valuable capabilities in modeling, prediction, optimization, and control, laying the foundation for next-generation FMS.

Artificial Intelligence Technology on Layered Water Injection in Oilfield Development Process

Since the 1960s, researchers have worked to advance water flooding technology to address challenges like high viscosity, low fluidity, and depleting reservoirs, aiming to prevent oil fields from becoming unproductive. The integration of artificial intelligence (AI), computer vision, and advanced algorithms like BP neural networks has recently revolutionized this field. These technological advancements have upgraded water injection methodologies, overcoming past limitations and enabling real-time monitoring and dynamic control of water injection into different oil layers. This 'intelligent layering' ensures optimized water management, enhancing overall recovery rates. This overview highlights the progression of water injection techniques, critiques traditional methods' shortcomings, and delves into the cutting-edge applications of AI-driven intelligent layering systems. It serves as a valuable guide for oil industry stakeholders, equipment manufacturers, and research institutions seeking to refine water injection practices and boost hydrocarbon extraction efficiency.

Reconfigurability-Encoded Hierarchical Rectifiers for Versatile 3D Liquid Manipulation.

Manipulating small-volume liquids is crucial in natural processes and industrial applications. However, most liquid manipulation technologies involve complex energy inputs or non-adjustable wetting gradient surfaces. Here, a simple and adjustable 3D liquid manipulation paradigm is reported to control liquid behaviors by coupling liquid-air-solid interfacial energy with programmable magnetic fields. This paradigm centers around a hierarchical rectifier with magnetized microratchets, using Laplace pressure asymmetry to enable multimodal directional steering of various surface tension liquids (23-72 mN m-1). The scale-dependent effect in microratchet design shows its superiority in handling small-volume liquids across three orders of magnitude (100-103 µL). Under programmed magnetic fields, the rectifier can reconfigure its morphology to harness interfacial energy to exhibit richer liquid behaviors without dynamic real-time control. Reconfigured rectifiers show improved rectification performance in the inertia-dominant fluid regime, i.e., a remarkable 2000-fold increase in the critical Weber number for pure ethanol. Moreover, the rectifier's switchable reconfigurations offer flexible control over liquid transport directions and spatiotemporally controllable 3D liquid manipulation reminiscent of inchworm motions. This scalable liquid manipulation paradigm promotes versatile engineering and biochemistry applications, e.g., portable liquid purity testing (screening resolution <1 mN m-1), logical open-channel microfluidics, and automated chemical reactionplatforms.

Maintain Power Transmission and Efficiency Tracking Using Variable Capacitors for Dynamic WPT Systems

This study introduces a new method for real-time efficiency tracking and stable output power of Dynamic Wireless Power Transfer (DWPT) systems using variable capacitors. A preliminary detailed discussion and an analysis of the DWPT system are carried out to show how the system can optimize power transmission and efficiency when the relative positions of transmitter and receiver change using a dynamic real-time control of the variable capacitors belonging to the compensation networks. This paper shows a detailed model of the DWPT system, including magnetic coupling analysis, circuit dynamics analysis, and efficiency characteristics analysis, in order to modify the control input values as needed. By utilizing a group optimization strategy, the transmission efficiency can be quickly maximized without using a position detection module. Simulation results demonstrate the effectiveness of the proposed method under various dynamic conditions, achieving significant improvements in energy efficiency and transmission reliability of the DWPT system. This research provides a powerful method to increase the overall performances of DWPT systems, which will help the development of future wireless charging technology.

Hierarchical control on EV charging stations with ancillary service functions for PV hosting capacity maximization in unbalanced distribution networks

Hierarchical control on EV charging stations with ancillary service functions for PV hosting capacity maximization in unbalanced distribution networks

Research on Intelligent Chemical Dosing System for Phosphorus Removal in Wastewater Treatment Plants

Whether the phosphorus removal chemical in wastewater treatment plants (WWTPs) can be accurately dosed not only affects the compliance of the effluent total phosphorus but also has a huge impact on sludge production and energy consumption during the wastewater treatment process. For the effluent from the secondary sedimentation tank of a wastewater treatment plant in southern China, based on experimental screening of the optimal pH value, chemical types and concentrations of chemicals, coagulation time, etc., a dynamic dosage prediction feedforward model for chemical phosphorus removal agents in the effluent from the secondary sedimentation tank of the WWTPs was developed to predict the most economical dosage of the chemicals. Meanwhile, combined with the adaptive fuzzy neural network P feedback control algorithm, dynamic real-time control of chemical dosing was achieved. Through micro-control design, a software model for signal collection and feedback in a specific phosphorus removal scenario was formed, and an automatic control system for chemical dosing was ultimately developed for a WWTP in a city in southern China. After stable operation for two months, the system achieved a 100% compliance rate for effluent total phosphorus (TP) concentration and a 67% improvement in effluent stability, helping the wastewater treatment plant achieve stable and precise control of the phosphorus removal process in the secondary sedimentation tank effluent, which is conducive to further promoting its implementation of low-carbon pathways.

Ancillary services from wind and solar energy in modern power grids: A comprehensive review and simulation study

Renewable energy sources like wind and solar have increased demand for surplus power capacity. The demand is primarily fueled by the growing impact of forecasting errors associated with these intermittent energy sources. Implementing advanced control methods for automatic generation control (AGC) is essential to integrate wind and solar power with conventional generation sources to balance the power system and reduce reliance on traditional reserves. Therefore, this paper comprehensively overviews solar and wind energy integration in the AGC framework to provide optimal grid ancillary services. Initially, the paper presents an overview of the basic equations used to integrate reserve power from the photovoltaic (PV) system by employing the de-loading strategy. Subsequently, a comprehensive review is conducted on integrating the PV system in AGC strategies to provide grid ancillary services. The study also analyzes the contribution of wind power in AGC services using relevant equations and past practices. The paper presents a real-time dynamic control strategy to optimize the dispatch of the AGC unit by integrating the operating reserves from wind energy systems in conjunction with thermal power systems. The study simulates an 8-bus, 5-machine model using the Dig-SILENT Power Factory. The findings reveal that utilizing operating reserves from wind power can significantly reduce large-scale forecasting errors in massively renewable energy resources (RES) integrated power systems, thereby ensuring the necessary system operational security and reducing the reliance on traditional generating units.

Design of image intelligent focusing system based on improved SMD function and RBF algorithm.

The utilization of digital statistical processes in images and videos can effectively tackle numerous challenges encountered in optical sensors. This research endeavors to overcome the limitations inherent in traditional focus models, particularly their inadequate accuracy. It aims to bolster the precision of real-time perception and dynamic control by employing enhanced data fusion methodologies. The ultimate objective is to facilitate information services that enable seamless interaction and profound integration between computational and physical processes within an open environment. To achieve this, an enhanced sum-modulus difference (SMD) evaluation function has been proposed. This innovation is founded on the concept of threshold value evaluation, aimed at rectifying the accuracy shortcomings of traditional focusing models. Through the computation of each gray value after threshold segmentation, the method identifies the most suitable threshold for image segmentation. This identified threshold is then applied to the focus search strategy employing the radial basis function (RBF) algorithm. Furthermore, an intelligent focusing system has been developed on the Zynq development platform, encompassing both hardware design and software program development. The test results affirm that the focusing model based on the improved SMD evaluation function rapidly identifies the peak point of the gray variance curve, ascertains the optimal focal plane position, and notably enhances the sensitivity of the focusing model.

Adaptive State Estimation of UAV Information Physical System Under Network Attack

with the idea of information physics system put forward, governments, enterprises and scientific research in-stitutions have joined the research and construction of information physics system. The construction and development of information physics system is bound to be restricted by the security and privacy of information physical system, which provides theoretical reference for clearing the current security threats of information physical system and providing theoretical reference for the security and privacy protection of information physical system. UAV is an intelligent infor-mation physics system which relies on ground communication and flight control system to realize autonomous flight. The concept of IT system was first proposed by NASA in 1992. As a new intelligent system, UAV has emerged and is widely used. It is a complex system of computing, network and physical entity integration and deep cooperation. Thus, the real-time perception, dynamic control and information service of large physical system and information system can be achieved.

Evaluation of dynamic control of continuous capture with periodic counter-current chromatography under feedstock variations

Multi-column periodic counter-current chromatography is a promising technology for continuous antibody capture. However, dynamic changes due to disturbances and drifts pose some potential risks for continuous processes during long-term operation. In this study, a model-based approach was used to describe the changes in breakthrough curves with feedstock variations in target proteins and impurities. The performances of continuous capture of three-column periodic counter-current chromatography under ΔUV dynamic control were systematically evaluated with modeling to assess the risks under different feedstock variations. As the concentration of target protein decreased rapidly, the protein might not breakthrough from the first column, resulting in the failure of ΔUV control. Small reductions in the concentrations of target proteins or impurities would cause protein losses, which could be predicted by the modeling. The combination of target protein and impurity variations showed complicated effects on the process performance of continuous capture. A contour map was proposed to describe the comprehensive impacts under different situations, and nonoperation areas could be identified due to control failure or protein loss. With the model-based approach, after the model parameters are estimated from the breakthrough curves, it can rapidly predict the process stability under dynamic control and assess the risks under feedstock variations or UV signal drifts. In conclusion, the model-based approach is a powerful tool for continuous process evaluation under dynamic changes and would be useful for establishing a new real-time dynamic control strategy.

Leveling Control of Hillside Tractor Body Based on Fuzzy Sliding Mode Variable Structure

To address the issues that arise when auto-leveling the vehicle body of a hillside tractor under complex working conditions, an auto-leveling control system was developed based on a newly developed hillside tractor and four-point body leveling mechanism. In this approach, leveling accuracy and stability were improved by adopting a sliding mode variable structure control algorithm based on fuzzy switching gain adjustment to achieve real-time dynamic auto-leveling control. To obtain curves of front and rear axle leveling displacement, speed, flow, pressure and body tilting angle during the leveling process, AMEsim/Simulink co-simulation was used to simulate and analyze the control system. The simulation results revealed that the tractor achieves a good leveling effect under complex working conditions in hilly and mountainous areas; the tractor can remain within a ±2° tilting angle range during the leveling process and can return to 0° after leveling, demonstrating good dynamic stability. To further assess the algorithm, a model of the system was submitted to live-testing on a custom-built auto-leveling test bench. Comparison of the test and simulation results revealed a close agreement between the two, indicating that the self-leveling control system and control algorithm developed in this study have high leveling accuracies. The results reported in this paper could provide assistance with or in reference to obtaining solutions to the problems of tractor body leveling in hilly and mountainous areas.

Real-Time Dynamic Planning and Tracking Control of Auto-Docking for Efficient Wireless Charging

Real-Time Dynamic Planning and Tracking Control of Auto-Docking for Efficient Wireless Charging

Construction of Real-time Dynamic Reversible Lane Safety Control Model in Intelligent Vehicle Infrastructure Cooperative System

ABSTRACT Reversible lanes play an important role in alleviating urban traffic congestion and improving the utilization of road resources. However, most of the reversible lanes currently implemented are timed and fixed, and there is little research on the safety of reversible lanes without isolation facilities. In view of the existing problems of reversible lanes, this paper proposed a real-time dynamic reversible lane safety control model. The influencing factors of reversible lane safety control are analyzed first, and then determine model parameters of the no-entry zone and the buffer zone in the conflict area. Moreover, model parameters of emptying, exit, and recovery zones in the operation process were determined as well. Additionally, this paper discussed the length of reversible lanes and the timing of signals. The surrogate safety assessment model (SSAM) is adopted to analyze vehicle trajectory data for traffic simulation under different traffic flows. The experiment results show that the proposed reversible lane safety control scheme can keep the vehicle’s traffic conflict rate below 5%, which can effectively ensure the safe operation of the reversible lane.

Edge Solution for Real-Time Motor Fault Diagnosis Based on Efficient Convolutional Neural Network

Real-time motor fault diagnosis can detect motor faults on time and prompt the repair or replacement of faulty motors which minimizes the potential losses caused by motor faults. Deep learning (DL) methods have been intensively applied in motor fault diagnosis. Most DL algorithms need to be trained with sufficient computation resources on cloud or local servers. However, uploading the raw data and downloading the command instructions to the edge will cause inevitable time delays and security concerns. This paper develops a DL algorithm based on efficient convolutional neural networks (ECNN) that can be deployed on an edge computing node for real-time motor fault diagnosis and dynamic control. The effectiveness, efficiency, and robustness of the ECNN model have been validated by experiments, and the results indicate that the ECNN model can achieve 100 % accuracy in recognition of 10 types of motor conditions, with the inference time and memory usage less than 14 ms and 44 KiB, respectively. The comparison results demonstrate that the ECNN model yields higher accuracy than the classical shallow neural networks, and it also presents the advantages of smaller model volume, lower prediction time, and higher accuracy as compared with the DL models. The proposed method shows significant potential for practical application in real-time motor fault detection and control.

Ensemble-Based Flow Field Estimation Using the Dynamic Wind Farm Model FLORIDyn

Wind farm control methods allow for a more flexible use of wind power plants over the baseline operation. They can be used to increase the power generated, to track a reference power signal or to reduce structural loads on a farm-wide level. Model-based control strategies have the advantage that prior knowledge can be included, for instance by simulating the current flow field state into the near future to take adequate control actions. This state needs to describe the real system as accurately as possible. This paper discusses what state estimation methods are suitable for wind farm flow field estimation and how they can be applied to the dynamic engineering model FLORIDyn. In particular, we derive an Ensemble Kalman Filter framework which can identify heterogeneous and changing wind speeds and wind directions across a wind farm. It does so based on the power generated by the turbines and wind direction measurements at the turbine locations. Next to the states, this framework quantifies uncertainty for the resulting state estimates. We also highlight challenges that arise when ensemble methods are applied to particle-based flow field simulations. The development of a flow field estimation framework for dynamic low-fidelity wind farm models is an essential step toward real-time dynamic model-based closed-loop wind farm control.

Sliding Mode Disturbance Observer-Based Adaptive Dynamic Inversion Fault-Tolerant Control for Fixed-Wing UAV

Unmanned aerial vehicles (UAVs) have been widely applied over the past decades, especially in the military field. Due to the unpredictability of the flight environment and failures, higher requirements are placed on the design of the control system of the fixed-wing UAV. In this study, a sliding mode disturbance observer-based (SMDO) adaptive dynamic inversion fault-tolerant controller was designed, which includes an outer-loop sliding mode observer-based disturbance suppression dynamic inversion controller and an inner-loop real-time aerodynamic identification-based adaptive fault-tolerant dynamic inversion controller. The sliding mode disturbance observer in the outer-loop controller was designed based on the second-order super-twisting algorithm to alleviate chattering. The aerodynamic identification in the inner-loop controller adopts the recursive least squares algorithm to update the aerodynamic model of the UAV online, thereby realizing the fault-tolerant control for the control surface damage. The effectiveness of the proposed SMDO enhanced adaptive fault-tolerant control method was validated by mathematical simulation.

Investigation of tunable structural color based on hexagonal boron nitride

Unlike the color development mechanism of pigments and dyes, the structural color is determined by the surface microstructure. Therefore, the structural color has the advantages of no pollution, not easy to fade, and high resolution, etc. However, there are still obstacles such as poor real-time dynamic control for the practical application of structural color. In this article, hexagonal boron nitride (h-BN) is introduced into metasurfaces to further explore tunable structural colors. Using the designed metasurface, we simulated three primary colors of red, green, and blue by adjusting the structural parameters, and realized the dynamic control of colors by adjusting the refractive index of h-BN. When the real part n of the complex refractive index of h-BN is adjusted by 0.1, the chromaticity coordinates in the x -direction change by about 0.025. As the real part n increases, the chromaticity coordinates in the color space shift from reddish orange to pink. Furthermore, as an application, we investigated the changes in the structural color of the proposed metasurface induced by the ambient refractive index. The results suggest that the proposed metasurface can be used to monitor or perceive the parameter changes in the background material by observing the color change of the metasurface. Our investigation provides theoretical references and new possibilities for the experimental research and applications of tunable structural color.