Real-time Operating Conditions Research Articles

Forecasting chaotic behavior of the drill bit in real-time using a DNN model integrated with rock surface morphology

The multiple regenerative effects during the drilling process cause the drilling system to exhibit complex motions, even leading to chaotic behavior. Additionally, due to the inability to obtain real-time rock parameters, traditional drilling dynamics models and time-series forecasting models cannot accurately forecast the real-time operational status of the drilling system. In this paper, a deep neural network (DNN) model integrated with rock surface morphology model is proposed to forecast the real-time operational status of the drill bit. This new model can permanently record the changes in rock surface morphology and multiple regenerative effects during the drilling process, enhancing the perception of rock parameters and improving the forecasting accuracy of the drill bit’s operational status. Experimental results show that the new model forecasts the drill bit’s operational status with higher accuracy compared to other typical time-series forecasting models without integrating surface morphology model. Furthermore, this new model demonstrates superior convergence speed, stability, and generalization ability compared to other models. In addition, the influence of hyperparameters on the forecast accuracy of the new model has also been studied. These results play an important role in forecasting and preventing adverse vibrations such as stick slip, impact, reversal, and rebound of the drill bit.

Virtual Power Plant Response Strategy Considering Dynamic Aggregation of Different Flexible Resources

Abstract Aggregate and adjust distributed resources, the virtual power plant realizes the collaborative optimization of different forms of electric energy, which greatly improves the flexibility of the power system. Considering the flexibility of distributed resources, this paper designs the active power and frequency regulation modes of virtual power plants, and proposes a response strategy for dynamic resource aggregation of virtual power plants. Firstly, the distributed energy resources of virtual power plants are classified, and their dynamic characteristics are fully considered for dynamic aggregation, and the active power and based on these characteristics, a frequency regulation model is established. Secondly, according to the real-time operation status of sampled distributed resources, a response prediction model of virtual power plant based on dynamic resource aggregation was proposed. Finally, taking the 35kV substation workbench as an example, the response effect of the virtual power plant at different times of a typical day is verified.

Optimizing High-Voltage Direct Current Transmission Corridors: Dynamic Thermal Line Rating for Enhanced Renewable Generation and Greenhouse Gas Emission Reductions

Recently, significant attention has been paid to the large-scale use of renewable energy through high-voltage direct current (HVDC) because of its economic feasibility. At the same time, the growing demand for electricity and the increasing penetration of renewable energy sources have prompted the electric power industry to explore methods to optimize the use of the existing grid infrastructure. Dynamic thermal line rating (DTLR) is a technique that allows transmission lines to operate at their maximum capacity, considering their real-time operating conditions. The majority of existing research on this topic has focused predominantly on employing DTLR in alternating current systems and exploring their applications. This study presents a novel approach by applying DTLR to HVDC transmission corridors, with the aim of maximizing the utilization of their capacity and facilitating increased integration of renewable energy. The performance of the proposed approach is evaluated by conducting a case study for an HVDC transmission line in Alberta, Canada. On average, the mean increase in ampacity above the static rating is 64% during winter and 34% during summer. This additional capacity can be used to integrate wind energy, replacing coal-fired generation. This leads to a significant reduction in greenhouse gas emissions, also quantified in this contribution.

A real-time network based anomaly detection in industrial control systems

Data manipulation attacks targeting network traffic of SCADA systems may compromise the reliability of an Industrial Control system (ICS). This can mislead the control center about the real-time operating conditions of the ICS and can alter commands sent to the field equipment. Deep Learning techniques appear as a suitable solution for detecting such complicated attacks. This paper proposes a Network based Anomaly Detection System (NADS) to detect data manipulation attacks with a focus on Modbus/TCP-based SCADA systems. The proposed NADS is a sequence to sequence auto encoder which uses the long short term memory units with embedding layer, teacher forcing technique and attention mechanism. The model has been trained and tested using the SWaT dataset, which corresponds to a scaled-down water treatment plant. The model detected 23 of 36 attacks and outperformed two other existing NADS with an improvement of 0.22 for simple attacks and obtained a recall value of 0.86 on attack 36 compared to the other NADS which obtained 0.74.

Adaptive Reactive Power Optimization in Offshore Wind Farms Based on an Improved Particle Swarm Algorithm

To address the reactive power optimization control problem in offshore wind farms (OWFs), this paper proposes an adaptive reactive power optimization control strategy based on an improved Particle Swarm Optimization (PSO) algorithm. Firstly, an OWF multi-objective optimization control model is established, with the total sum of voltage deviations at wind turbine (WT) terminals, active power network losses, and reactive power margin of WTs as comprehensive optimization objectives. Innovatively, adaptive weighting coefficients are introduced for the three sub-objectives, enabling the weights of each optimization objective to be adaptively adjusted based on real-time operating conditions, thus enhancing the adaptability of the reactive power optimization model to changes in operating conditions. Secondly, a Uniform Adaptive Particle Swarm Optimization (UAPSO) algorithm is proposed. On one hand, the algorithm initializes the particle swarm using a uniform initialization method; on the other hand, it improves the particle velocity update formula, allowing the inertia coefficient to adaptively adjust based on the number of iterations and the fitness ranking of particles. Simulation results demonstrate the following: (1) Under various operating conditions, the proposed adaptive multi-objective reactive power optimization strategy can ensure the stability of node voltages in offshore wind farms, reduce active power losses, and simultaneously improve reactive power margins. (2) Compared with the traditional PSO algorithm, UAPSO exhibits an approximately 10% improvement in solution speed and enhanced solution accuracy.

A Comparative Analysis on Proportional-Integral and Fuzzy-Logic Control Strategies for Doubly-Fed Induction Generators

This research investigates superior control methods for optimize the performance of Doubly-Fed Induction Generators in wind energy conversion systems. This proposed work, compares the well-established Proportional-Integral controller, with a Fuzzy Logic controller, known for its effectiveness in managing non-linear systems. To achieve a thorough analysis, this research develops a detailed mathematical model, specifically adopted to the DFIG system. It employs a PI controller for both the rotor-side and grid-side converters of the DFIG system. To enhance performance, a Fuzzy Logic controller is introduced to replace the PI controller, based on real-time operating conditions and gain values. Extensive simulations evaluate rigorously various performance metrics of the DFIG system under different control strategies. This analysis provides valuable insights to guide the selection of optimal control techniques, for wind energy systems using DFIGs. The analysis contributes to advancements in reliability, and efficiency for DFIG-based wind-energy systems, furthering the development of sustainable energy solutions.

Empirical analysis of sensor type importance for data preparation of real-time operational status monitoring in fused deposition modeling 3D printers

Empirical analysis of sensor type importance for data preparation of real-time operational status monitoring in fused deposition modeling 3D printers

Generalized Dynamic Predictive Control for Nonlinear Systems Subject to Mismatched Disturbances With Application to PMSM Drives

This paper investigates a generalized dynamic predictive control (GDPC) strategy with a novel autonomous tuning mechanism of the horizon for a class of nonlinear systems subject to mismatched disturbances. As a new incremental function for the predictive control method, the horizon can be determined autonomously with respect to the system working conditions, instead of selecting a fixed value via experience before, which is able to effectively improve the control performance optimization ability to a certain extent considering different system perturbation levels. To this aim, firstly, a non-recursive composite control framework is constructed based on a series of disturbance observations via higher-order sliding modes. Secondly, by designing a simple one-step scaling gain update mechanism into the receding horizon optimization, the horizon can be therefore adaptively tuned according to its real-time practical operating conditions. A three-order numerical simulation and a typical engineering application of permanent magnet synchronous motor (PMSM) drive system are carried out to demonstrate the effectiveness and conciseness of the proposed GDPC method.

Distributed Power Grid Connected Panoramic Perception Technology Based on Digital Twin Model

Abstract To address the issue that large-scale distributed Proton-exchange membrane fuel cell grid-connected operation status is difficult to effectively monitor, this study carried out clustering screening of Proton-exchange membrane fuel cell grid connected status variables. The digital twin model of the Proton-exchange membrane fuel cell group grid connection is established by using key important variables, and the digital model accurately reflects the real-time operation status of the Proton-exchange membrane fuel cell. Then, it predicts the operation status of the Proton-exchange membrane fuel cell. The experiment showcases that the optimal accuracy of fuzzy C-means clustering algorithm, K-means clustering algorithm and fuzzy C-means clustering algorithm in view of the objective function for clustering screening of grid-connected state quantity of Proton-exchange membrane fuel cell is 0.74, 0.65 and 0.59 respectively; The optimal recall rates are 0.84, 0.76, and 0.68, respectively; The optimal F-measure values are 0.78, 0.70, and 0.64, respectively. Among the three clustering analysis algorithms, the fuzzy C-means clustering algorithm, in view of the objective function, has the shortest running time and the least memory consumption. The monitoring results are basically consistent with the actual situation, indicating that this design method can complete the task of monitoring the operating status of distributed power grid-connected equipment. This study’s proposed method is more accurate than conventional methods and is better suited for monitoring the grid connection status of distributed power systems.

Structural Health Monitoring Design and Performance Evaluation of a Middle-Span Bridge

Structural health monitoring (SHM) has attracted significant attention over the past two decades due to its ability to provide real-time insight into the condition of structures. Despite the development of several SHM systems for long-span bridges, which play a crucial role in the assessment of these structures, studies focusing on short- or middle-span bridges remain scarce. This research paper presents an efficient and practical bridge monitoring and warning system established on a middle-span bridge, a key crossroad bridge located in Shenzhen. The monitoring system consists of sensors and measuring points that collect a substantial amount of data, enabling the close monitoring of various operational indicators to facilitate the early detection of threshold exceedances. Based on this system, the subtle condition of the bridge can be evaluated, and the operational condition of the bridge can be studied through the comparative analysis of the collected data. Over four months of monitoring, data including the strain and creep of the main beam, the strain and settlement of piers and the crack width of the bridge body are observed. Furthermore, the real-time operational status of the bridge is analyzed and evaluated through the combination of the collected data and the structural finite element model.

Joint Topology and State Estimation Using TTU Monitoring Data Considering Three-Phase Imbalance

A grand challenge for operators to develop optimal controls at the distribution level lies in how to obtain the real-time network topology and operation state in lack of specialized high precision monitoring devices, especially with high penetration of distributed renewable energy. Driven by this motivation, this paper proposes a novel topology and operation state joint estimation framework based on the monitoring data from transformer terminal units (TTUs). In the framework, the bottom layer generates an equivalent network model and nodal voltage and current measurements with synchronized phase angles from the distribution network and the voltage and power measurement data from TTU. The middle layer formulates, linearizes and solves an optimization problem to fit the model with the measurements. A global piecewise linearization method is proposed to convert the original mixed integer quadratically constrained program (MIQCP) problem into a mixed integer linear program (MILP) problem. In the top layer, the line switch states and feeder power flows are estimated with the solution of the optimization problem. Case studies are conducted in test systems to verify the accuracy, efficiency and robustness of the proposed framework and show that the proposed framework yields obvious advantages over the existing approaches on the estimation accuracy when using TTU measurements.

Deep-Learning-Based Koopman Modeling for Online Control Synthesis of Nonlinear Power System Transient Dynamics

Power system stability and control have become more challenging due to the increasing uncertainty associated with renewable generation. The performance of conventional control is highly driven by the physics-based, offline developed dynamic models that can deviate from the actual system characteristics under different operating conditions and/or configurations. Data-driven approaches based on online measurements can be a better solution to addressing these issues by capturing real-time operation conditions. This paper describes a novel, fully data-driven probabilistic framework to derive a linear representation of post-contingency grid dynamics and online prescribe control based on the derived model to enhance transient stability. The complex nonlinear power system dynamics is approximated by a linear model by using multiple neural network modules that infer distributions of the observations and introducing a Koopman layer to sample possible Koopman linear models from the inferred distributions. The trained model features linearity that can be easily incorporated into the existing linear control design paradigm and ease the controller design process. The effectiveness of Koopman-based control designs is validated through comparative case studies, which demonstrate increased prediction accuracy and control performance when applied to a power system with heterogeneous generator dynamics.

A digital twin to quantitatively understand aging mechanisms coupled effects of NMC battery using dynamic aging profiles

Traditional lithium-ion battery modeling does not provide sufficient information to accurately verify battery performance under real-time dynamic operating conditions, particularly when considering various aging modes and mechanisms. To improve the current methods, this paper proposes a lithium-ion battery digital twin that can capture real-time data and integrate the strong coupling between SEI layer growth, anode crack propagation, and lithium plating. It can be utilized to estimate aging behavior from macroscopic full-cell level to microscopic particle level, including voltage-current profiles in dynamic aging conditions, predict the degradation behavior of Nickel-Manganese-Cobalt-Oxide (NMC) based lithium-ion batteries, and assist in electrochemical analysis. This model can improve the root cause analysis of cell aging, enabling a quantitative understanding of aging mechanism coupled effects. Three charging protocols with dynamic discharging profiles are developed to simulate real vehicle operation scenarios and used to validate the digital twin, combining operando impedance measurements, post-mortem analysis, and SEM to further prove the conclusions. The digital twin can accurately predict battery capacity fade within 0.4% MAE. The results indicate that SEI layer growth is the primary contributor to capacity degradation and resistance increase. Based on the analysis of the model, it is concluded that one of the proposed multi-step charging protocols, in comparison to a standard continuous charging protocol, can reduce the degradation of NMC-based lithium-ion batteries. This paper represents a firm physical foundation for future physics-informed machine learning development.

Research on the Multi-probability of a Nuclear Reactor Core Digital Twins in the HeTu platform

Digital twin (DT) technology plays a fundamental role in innovation in the energy field. At present, research of nuclear reactor DT is mainly focused on methodologies of multi-disciplinary, multi-physical, and multi-scale coupling simulation. However, the lack of research on multi-probability seems to limit the DT application. Multi-probabilities are widely found in reactor operation, such as process measurement uncertainty, equipment degradation uncertainty, theoretical model uncertainty, and so on. How to realize the DT of the reactor system based on the multi-probability principle to achieve the real-time operation state and the remaining useful life estimation, and to realize the autonomous operation control under the uncertainties, are the current hotspot and difficult issues. The solutions of a reactor core DT platform HeTu are discussed in this paper for probability estimation and probability control based on probability programming methodologies. The results show that Bayesian estimation and model prediction control methods proposed in HeTu could obtain satisfactory results for practical application.

Cloud Server-Assisted Remote Monitoring and Core Device Fault Identification for Dynamically Tuned Passive Power Filters

Reliability and safety are crucial for the operation of a dynamically tuned passive power filter (DTPPF). Safe performance of DTTPFs implies complete normal filtering without failure within a specified period. To prevent potential disaster or economic loss, it is desirable to achieve early warning of any core device faults in a DTPPF based on its running state and to optimize its harmonic mitigation performance. In this paper, we explore effective methods for identifying core device faults in DTPPFs. First, we summarize the characteristic parameters of faults, running state parameters, parameters required for fault monitoring, and fault type parameters. Then, a cloud server-assisted remote monitoring and fault identification system for DTPPF is proposed, which consists of monitoring system’s architecture and cloud servers’ software architecture as well as software design of the back-end service layer and functional design of the front-end application layer. Our experiments demonstrate that the proposed system can monitor the real-time operational status of the DTPPF, enabling remote diagnosis and identification of core device faults. Moreover, it is user-friendly, as it is capable of optimizing equipment maintenance schedules and utilizing manufacturers’ service capacities. Therefore, this research provides a theoretical foundation for harmonic mitigation in low-voltage distribution networks and is valuable for practical engineering applications in industrial power grids.

Digital twin-driven identification of fault situation in distribution networks connected to distributed wind power

The gradual integration of distributed wind power into distribution networks presents significant challenges for identifying faults, as it requires accurate and timely fault identification based on large-scale data. This paper proposes a novel fault situation identification framework driven by digital twins to overcome the existing bottleneck of asynchronous online fault identification and offline post-event analysis. The framework employs a high-precision digital twin avatar with parallel strategies of fully electromagnetic transient calculation to obtain the real-time operation status of distribution networks connected with distributed wind power. Furthermore, the framework employs skip-connected dilated causal convolution to mine meaningful multi-time-scale features from massive data, while using an automatic hyper-parameter tuning strategy. A case study based on IEEE 33-node standard distribution network and a real-world distribution network demonstrates the effectiveness of this framework, achieving ultra-real-time and high-precision simulation and effective fault identification even under noise or missing data, accelerating traditional post-fault analysis to microsecond-level situation identification.

Multi-source-data state estimation for integrated electricity–heat-building networks

Building heating systems (BHS) play a major role in integrated electricity and heat systems (IEHS). To capture the real-time dynamic operating state of IEHS based on multi-source measurement data, this paper develops a comprehensive state estimation (SE) framework for IEHS with BHS fleets. First, a thermo-electrical SE model integrating BHS, electric power grid (EPG), and district heating network (DHN) is developed. Then, to jointly estimate the state variables of IEHS with different time scales of dynamics, a holistic SE algorithm is proposed based on the partial equivalence between the Weighted Least Squares (WLS) estimation problem and the correction stage of the Iterative Extended-Kalman Filter (IEKF). It also includes a data anomaly processing algorithm to combat data corruptions from sensing and communication processes. Simulation results show that the proposed framework can accurately track the thermo-electrical states of the system both in the presence of measurement noise and anomalies during various dynamics in IEHS.

Real-time economic and safe operation diagnosis of hydropower units

In order to ensure the safety and economy of the operation of hydropower units under the big data technology application platform and the automatic generation control system, and to tap the maximum power generation potential of the units, an effective method of economic operation evaluation of hydropower units combined with state diagnosis is proposed. Taking Unit 1 of Longtan Hydropower Station as an example, the economic evaluation and status diagnosis of the daily operating conditions are carried out, the real-time efficiency of the turbine is queried through the unit operating conditions data, and the economic operation of the unit is comprehensively evaluated using the standard water consumption index. In addition, the real-time operation condition of the unit shall be diagnosed according to the working condition zoning diagram, and the economic operation condition shall be combined with the unit state operation condition for joint assessment. It is strictly forbidden to operate the unit in the vibration zone and the vortex zone and it is determined that the unit can maximize the power generation efficiency after operating in the safe operation zone.

Optimal real-time Voltage/Var control for distribution network: Droop-control based multi-agent deep reinforcement learning

The photovoltaics (PVs) known as clean power generation has been highly penetrated in distribution networks, which motivates the network develops towards high uncertainty with complex real-time operation status. In this paper, an optimal real-time Voltage/Var control (ORT-VVC) method is proposed to reduce power losses and mitigate voltage fluctuations by optimizing the reactive power output of the PV inverter. And the ORT-VVC is implemented via a novelly proposed droop-control based multi-agent deep reinforcement learning (DC-MADRL). The VVC structure is constructed in distributed pattern with network partition and the multi-agents are established to rule the sub-networks via rare information communication between neighbors. Then, the PV control model is established as a Q-V droop control model with adjustable parameters. The MADRL is employed to optimize the PV controlling parameters instead of optimizing PV reactive power output directly, which aims to improve the real-time VVC performance for distribution network. The DC-MADRL model is established and solved via the multi-agent deep deterministic policy gradient (MADDPG) algorithm. Finally, numerical simulations are performed on the IEEE 123-bus test system to demonstrate the effectiveness of the proposed method.

Development of IoT Healthcare Platform Model for the Elderly using Bigdata and Artificial Intelligence

The entry into an ultra-old society in South Korea, the remarkable development of medical technology as well as the recent emergence of the Fourth Industrial Revolution have contributed to the steady growth of the silver industry in line with the demand for healthy lives of the elderly. However, the silver industry of South Korea is still a rudimentary level. The existing older telecare product was sensor-based and was able to respond at or after the accident. However, there are limitations in preventing and predicting accidents. In particular, preventive healthcare is very important because even in small accidents, older people can be at great risk. We intend to build a healthcare platform based on IoT, against this backdrop. Based on previous studies, we try to build a new concept of architecture by collecting, storing and analyzing data to overcome the limitations of existing platforms. It’s supposed to build cloud-based Bigdata storage that can collect and analyze real-time operating conditions for older people with cameras and mobile phones, and study algorithms for old-age care through Artificial Intelligence. This research would certainly give more safe accident prevention and health care for the elderly and the healthcare industry.