With the evolution of DC distribution networks from traditional radial topologies to more complex multi-branch structures,the number of measurement points supporting synchronous communication remains relatively limite...With the evolution of DC distribution networks from traditional radial topologies to more complex multi-branch structures,the number of measurement points supporting synchronous communication remains relatively limited.This poses challenges for conventional fault distance estimation methods,which are often tailored to simple topologies and are thus difficult to apply to large-scale,multi-node DC networks.To address this,a fault distance estimation method based on sparse measurement of high-frequency electrical quantities is proposed in this paper.First,a preliminary fault line identification model based on compressed sensing is constructed to effectively narrow the fault search range and improve localization efficiency.Then,leveraging the high-frequency impedance characteristics and the voltage-current relationship of electrical quantities,a fault distance estimation approach based on high-frequency measurements from both ends of a line is designed.This enables accurate distance estimation even when the measurement devices are not directly placed at both ends of the faulted line,overcoming the dependence on specific sensor placement inherent in traditional methods.Finally,to further enhance accuracy,an optimization model based on minimizing the high-frequency voltage error at the fault point is introduced to reduce estimation error.Simulation results demonstrate that the proposed method achieves a fault distance estimation error of less than 1%under normal conditions,and maintains good performance even under adverse scenarios.展开更多
The AC/DC hybrid distribution network is one of the trends in distribution network development, which poses great challenges to the traditional distribution transformer. In this paper, a new topology suitable for AC/D...The AC/DC hybrid distribution network is one of the trends in distribution network development, which poses great challenges to the traditional distribution transformer. In this paper, a new topology suitable for AC/DC hybrid distribution network is put forward according to the demands of power grid, with advantages of accepting DG and DC loads, while clearing DC fault by blocking the clamping double sub-module(CDSM) of input stage. Then, this paper shows the typical structure of AC/DC distribution network that is hand in hand. Based on the new topology, this paper designs the control and modulation strategies of each stage, where the outer loop controller of input stage is emphasized for its twocontrol mode. At last, the rationality of new topology and the validity of control strategies are verified by the steady and dynamic state simulation. At the same time, the simulation results highlight the role of PET in energy regulation.展开更多
A novel operation control method for relay protection in flexible DC distribution networks with distributed power supply is proposed to address the issue of inaccurate fault location during relay protection,leading to...A novel operation control method for relay protection in flexible DC distribution networks with distributed power supply is proposed to address the issue of inaccurate fault location during relay protection,leading to poor performance.The method combines a fault-tolerant fault location method based on long-term and short-term memory networks to accurately locate the fault section.Then,an operation control method for relay protection based on adaptive weight and whale optimization algorithm(WOA)is used to construct an objective function considering the shortest relay protection action time and the smallest impulse current.The adaptive weight and WOA are employed to obtain the optimal strategy for relay protection operation control,reducing the action time and impulse current.Experimental results demonstrate the effectiveness of the proposed method in accurately locating faults and improving relay protection performance.The longest operation time is reduced by 4.7023 s,and the maximum impulse current is limited to 0.3 A,effectively controlling the impact of large impulse currents and enhancing control efficiency.展开更多
ADC distribution network is an effective solution for increasing renewable energy utilization with distinct benefits,such as high efficiency and easy control.However,a sudden increase in the current after the occurren...ADC distribution network is an effective solution for increasing renewable energy utilization with distinct benefits,such as high efficiency and easy control.However,a sudden increase in the current after the occurrence of faults in the network may adversely affect network stability.This study proposes an artificial neural network(ANN)-based fault detection and protection method for DC distribution networks.The ANN is applied to a classifier for different faults ontheDC line.The backpropagationneuralnetwork is used to predict the line current,and the fault detection threshold is obtained on the basis of the difference between the predicted current and the actual current.The proposed method only uses local signals,with no requirement of a strict communication link.Simulation experiments are conducted for the proposed algorithm on a two-terminal DC distribution network modeled in the PSCAD/EMTDC and developed on the MATLAB platform.The results confirm that the proposed method can accurately detect and classify line faults within a few milliseconds and is not affected by fault locations,fault resistance,noise,and communication delay.展开更多
The escalating deployment of distributed power sources and random loads in DC distribution networks hasamplified the potential consequences of faults if left uncontrolled. To expedite the process of achieving an optim...The escalating deployment of distributed power sources and random loads in DC distribution networks hasamplified the potential consequences of faults if left uncontrolled. To expedite the process of achieving an optimalconfiguration of measurement points, this paper presents an optimal configuration scheme for fault locationmeasurement points in DC distribution networks based on an improved particle swarm optimization algorithm.Initially, a measurement point distribution optimization model is formulated, leveraging compressive sensing.The model aims to achieve the minimum number of measurement points while attaining the best compressivesensing reconstruction effect. It incorporates constraints from the compressive sensing algorithm and networkwide viewability. Subsequently, the traditional particle swarm algorithm is enhanced by utilizing the Haltonsequence for population initialization, generating uniformly distributed individuals. This enhancement reducesindividual search blindness and overlap probability, thereby promoting population diversity. Furthermore, anadaptive t-distribution perturbation strategy is introduced during the particle update process to enhance the globalsearch capability and search speed. The established model for the optimal configuration of measurement points issolved, and the results demonstrate the efficacy and practicality of the proposed method. The optimal configurationreduces the number of measurement points, enhances localization accuracy, and improves the convergence speedof the algorithm. These findings validate the effectiveness and utility of the proposed approach.展开更多
集散控制系统(distributed control system,DCS)是复杂的分布式控制系统,网络安全威胁多种多样,可能会针对DCS的不同层面进行攻击,如网络通信、数据存储、应用程序等,使网络风险安全监测变得更加复杂。为此,设计了一种燃煤电厂DCS的网...集散控制系统(distributed control system,DCS)是复杂的分布式控制系统,网络安全威胁多种多样,可能会针对DCS的不同层面进行攻击,如网络通信、数据存储、应用程序等,使网络风险安全监测变得更加复杂。为此,设计了一种燃煤电厂DCS的网络风险安全监测方法。基于电厂DCS构建了基于改进卡尔曼滤波的网络风险监测模型。试验结果表明,所提方法应用中网络环境的安全性得到明显改善,且监测的误报率始终低于3%。展开更多
研究基于DCS(Distributed Control System)的燃气-蒸汽联合循环机组运行智能控制系统,确保机组安全运行的同时,提高机组整体运行效率。构建基于DCS的燃气-蒸汽联合循环机组运行智能控制框架,过程控制层的Mark VI系统、DCS系统根据监测...研究基于DCS(Distributed Control System)的燃气-蒸汽联合循环机组运行智能控制系统,确保机组安全运行的同时,提高机组整体运行效率。构建基于DCS的燃气-蒸汽联合循环机组运行智能控制框架,过程控制层的Mark VI系统、DCS系统根据监测数据变化实现机组设备、旁路等自动控制。SIS层接收联合循环机组监测数据后,将其作为基于深度神经网络故障诊断模型的输入,实现机组设备故障的识别。在检测到故障时触发联锁保护子系统动作,将停机指令下达给自动启停控制子系统,使机组停止运行。实验结果表明,该系统可实现燃气-蒸汽联合循环机组设备故障识别,在100次训练后,训练损失为0.1左右,F-Score指标最大值为0.93;故障工况下,该系统可根据预定逻辑实现燃气-蒸汽联合循环机组自动停机。展开更多
This work concerns the study of problems relating to the adaptive internal model control of DC motor in both cases conventional and neural. The most important aspects of design building blocks of adaptive internal mod...This work concerns the study of problems relating to the adaptive internal model control of DC motor in both cases conventional and neural. The most important aspects of design building blocks of adaptive internal model control are the choice of architectures, learning algorithms, and examples of learning. The choice of parametric adaptation algorithm for updating elements of the conventional adaptive internal model control shows limitations. To overcome these limitations, we chose the architectures of neural networks deduced from the conventional models and the Levenberg-marquardt during the adjustment of system parameters of the adaptive neural internal model control. The results of this latest control showed compensation for disturbance, good trajectory tracking performance and system stability.展开更多
A new kind of dynamic neural network--diagonal recurrent neural network (DRNN) and its learning method and architecture are presented. A direct adaptive control scheme is also developed that is applied to a DC (Direct...A new kind of dynamic neural network--diagonal recurrent neural network (DRNN) and its learning method and architecture are presented. A direct adaptive control scheme is also developed that is applied to a DC (Direct Current) speed control system with the ability to auto-tune PI (Proportion Integral) parameters based on combining DRNN with PI controller. The simulation results of DRNN show better control performances and potential practical use in comparison with PI controller.展开更多
Brushless DC(BLDC)motor is a complex nonlinear system,of which some parameters will also change during operation.Therefore,obtaining accurate rotor position directly through the line voltage becomes more difficult.So ...Brushless DC(BLDC)motor is a complex nonlinear system,of which some parameters will also change during operation.Therefore,obtaining accurate rotor position directly through the line voltage becomes more difficult.So a new method is proposed in this paper which uses three line voltages as the input signal to identify the motor position based on adaptive wavelet neural network(WNN)and the differential evolution(DE)algorithm to optimize WNN structures,thus realizing the improvement of accuracy,exactness of the communication signals and convergence speed of the rotor position identification.Finally,both simulations and experimental results show that the proposed method has high accuracy of recognizing rotor position and strong orientation ability.展开更多
火电厂分布式控制系统(Distributed Control System,DCS)在机组控制与安全运行中依赖稳定的通信网络,而通信延迟易引发控制响应滞后与数据异常,影响运行可靠性。通过分析通信延迟问题,提出网络设备升级、系统配置优化及环境防干扰等解...火电厂分布式控制系统(Distributed Control System,DCS)在机组控制与安全运行中依赖稳定的通信网络,而通信延迟易引发控制响应滞后与数据异常,影响运行可靠性。通过分析通信延迟问题,提出网络设备升级、系统配置优化及环境防干扰等解决方案,并验证其实施效果,提出一系列优化策略。研究为提升火电厂DCS系统通信实时性与稳定性提供了工程参考与应用价值。展开更多
This paper presents the speed control of a separately excited DC motor using Neural Network (NN) controller in field weakening region. In armature control, speed controller has been used in outer loop while current co...This paper presents the speed control of a separately excited DC motor using Neural Network (NN) controller in field weakening region. In armature control, speed controller has been used in outer loop while current controller in inner loop is used. The function of NN is to predict the field current that realizes the field weakening to drive the motor over rated speed. The parameters of NN are optimized by the Social Spider Optimization (SSO) algorithm. The system has been implemented using MATLAB/SIMULINK software. The simulation results show that the proposed method gives a good performance and is feasible to be applied instead of others conventional combined control methods.展开更多
为提升火电厂分布式控制系统(Distributed Control System,DCS)通信网络的可靠性和实时性,通过分析常见火电厂DCS的冗余通信网络拓扑及其存在的问题,探讨了单点故障隐患、切换延迟大和网络负载不均等关键技术难点,提出了实现全路径物理...为提升火电厂分布式控制系统(Distributed Control System,DCS)通信网络的可靠性和实时性,通过分析常见火电厂DCS的冗余通信网络拓扑及其存在的问题,探讨了单点故障隐患、切换延迟大和网络负载不均等关键技术难点,提出了实现全路径物理+逻辑双冗余、采用毫秒级智能切换协议、部署动态负载均衡与服务质量(Quality of Service,QoS)策略等优化策略。验证结果表明,这些优化策略能够有效消除火电厂DCS的冗余通信网络拓扑单点故障风险,显著缩短冗余切换时间,合理分配网络带宽。展开更多
基金National Natural Science Foundation of China, grant number 52177074.
文摘With the evolution of DC distribution networks from traditional radial topologies to more complex multi-branch structures,the number of measurement points supporting synchronous communication remains relatively limited.This poses challenges for conventional fault distance estimation methods,which are often tailored to simple topologies and are thus difficult to apply to large-scale,multi-node DC networks.To address this,a fault distance estimation method based on sparse measurement of high-frequency electrical quantities is proposed in this paper.First,a preliminary fault line identification model based on compressed sensing is constructed to effectively narrow the fault search range and improve localization efficiency.Then,leveraging the high-frequency impedance characteristics and the voltage-current relationship of electrical quantities,a fault distance estimation approach based on high-frequency measurements from both ends of a line is designed.This enables accurate distance estimation even when the measurement devices are not directly placed at both ends of the faulted line,overcoming the dependence on specific sensor placement inherent in traditional methods.Finally,to further enhance accuracy,an optimization model based on minimizing the high-frequency voltage error at the fault point is introduced to reduce estimation error.Simulation results demonstrate that the proposed method achieves a fault distance estimation error of less than 1%under normal conditions,and maintains good performance even under adverse scenarios.
基金supported by National Key Research and Development Program of China (2016YFB0900500,2017YFB0903100)the State Grid Science and Technology Project (SGRI-DL-F1-51-011)
文摘The AC/DC hybrid distribution network is one of the trends in distribution network development, which poses great challenges to the traditional distribution transformer. In this paper, a new topology suitable for AC/DC hybrid distribution network is put forward according to the demands of power grid, with advantages of accepting DG and DC loads, while clearing DC fault by blocking the clamping double sub-module(CDSM) of input stage. Then, this paper shows the typical structure of AC/DC distribution network that is hand in hand. Based on the new topology, this paper designs the control and modulation strategies of each stage, where the outer loop controller of input stage is emphasized for its twocontrol mode. At last, the rationality of new topology and the validity of control strategies are verified by the steady and dynamic state simulation. At the same time, the simulation results highlight the role of PET in energy regulation.
文摘A novel operation control method for relay protection in flexible DC distribution networks with distributed power supply is proposed to address the issue of inaccurate fault location during relay protection,leading to poor performance.The method combines a fault-tolerant fault location method based on long-term and short-term memory networks to accurately locate the fault section.Then,an operation control method for relay protection based on adaptive weight and whale optimization algorithm(WOA)is used to construct an objective function considering the shortest relay protection action time and the smallest impulse current.The adaptive weight and WOA are employed to obtain the optimal strategy for relay protection operation control,reducing the action time and impulse current.Experimental results demonstrate the effectiveness of the proposed method in accurately locating faults and improving relay protection performance.The longest operation time is reduced by 4.7023 s,and the maximum impulse current is limited to 0.3 A,effectively controlling the impact of large impulse currents and enhancing control efficiency.
基金supported by Key Natural Science Research Projects of Colleges and Universities in Anhui Province(No.2022AH051831).
文摘ADC distribution network is an effective solution for increasing renewable energy utilization with distinct benefits,such as high efficiency and easy control.However,a sudden increase in the current after the occurrence of faults in the network may adversely affect network stability.This study proposes an artificial neural network(ANN)-based fault detection and protection method for DC distribution networks.The ANN is applied to a classifier for different faults ontheDC line.The backpropagationneuralnetwork is used to predict the line current,and the fault detection threshold is obtained on the basis of the difference between the predicted current and the actual current.The proposed method only uses local signals,with no requirement of a strict communication link.Simulation experiments are conducted for the proposed algorithm on a two-terminal DC distribution network modeled in the PSCAD/EMTDC and developed on the MATLAB platform.The results confirm that the proposed method can accurately detect and classify line faults within a few milliseconds and is not affected by fault locations,fault resistance,noise,and communication delay.
基金the National Natural Science Foundation of China(52177074).
文摘The escalating deployment of distributed power sources and random loads in DC distribution networks hasamplified the potential consequences of faults if left uncontrolled. To expedite the process of achieving an optimalconfiguration of measurement points, this paper presents an optimal configuration scheme for fault locationmeasurement points in DC distribution networks based on an improved particle swarm optimization algorithm.Initially, a measurement point distribution optimization model is formulated, leveraging compressive sensing.The model aims to achieve the minimum number of measurement points while attaining the best compressivesensing reconstruction effect. It incorporates constraints from the compressive sensing algorithm and networkwide viewability. Subsequently, the traditional particle swarm algorithm is enhanced by utilizing the Haltonsequence for population initialization, generating uniformly distributed individuals. This enhancement reducesindividual search blindness and overlap probability, thereby promoting population diversity. Furthermore, anadaptive t-distribution perturbation strategy is introduced during the particle update process to enhance the globalsearch capability and search speed. The established model for the optimal configuration of measurement points issolved, and the results demonstrate the efficacy and practicality of the proposed method. The optimal configurationreduces the number of measurement points, enhances localization accuracy, and improves the convergence speedof the algorithm. These findings validate the effectiveness and utility of the proposed approach.
文摘集散控制系统(distributed control system,DCS)是复杂的分布式控制系统,网络安全威胁多种多样,可能会针对DCS的不同层面进行攻击,如网络通信、数据存储、应用程序等,使网络风险安全监测变得更加复杂。为此,设计了一种燃煤电厂DCS的网络风险安全监测方法。基于电厂DCS构建了基于改进卡尔曼滤波的网络风险监测模型。试验结果表明,所提方法应用中网络环境的安全性得到明显改善,且监测的误报率始终低于3%。
文摘研究基于DCS(Distributed Control System)的燃气-蒸汽联合循环机组运行智能控制系统,确保机组安全运行的同时,提高机组整体运行效率。构建基于DCS的燃气-蒸汽联合循环机组运行智能控制框架,过程控制层的Mark VI系统、DCS系统根据监测数据变化实现机组设备、旁路等自动控制。SIS层接收联合循环机组监测数据后,将其作为基于深度神经网络故障诊断模型的输入,实现机组设备故障的识别。在检测到故障时触发联锁保护子系统动作,将停机指令下达给自动启停控制子系统,使机组停止运行。实验结果表明,该系统可实现燃气-蒸汽联合循环机组设备故障识别,在100次训练后,训练损失为0.1左右,F-Score指标最大值为0.93;故障工况下,该系统可根据预定逻辑实现燃气-蒸汽联合循环机组自动停机。
文摘This work concerns the study of problems relating to the adaptive internal model control of DC motor in both cases conventional and neural. The most important aspects of design building blocks of adaptive internal model control are the choice of architectures, learning algorithms, and examples of learning. The choice of parametric adaptation algorithm for updating elements of the conventional adaptive internal model control shows limitations. To overcome these limitations, we chose the architectures of neural networks deduced from the conventional models and the Levenberg-marquardt during the adjustment of system parameters of the adaptive neural internal model control. The results of this latest control showed compensation for disturbance, good trajectory tracking performance and system stability.
文摘A new kind of dynamic neural network--diagonal recurrent neural network (DRNN) and its learning method and architecture are presented. A direct adaptive control scheme is also developed that is applied to a DC (Direct Current) speed control system with the ability to auto-tune PI (Proportion Integral) parameters based on combining DRNN with PI controller. The simulation results of DRNN show better control performances and potential practical use in comparison with PI controller.
文摘Brushless DC(BLDC)motor is a complex nonlinear system,of which some parameters will also change during operation.Therefore,obtaining accurate rotor position directly through the line voltage becomes more difficult.So a new method is proposed in this paper which uses three line voltages as the input signal to identify the motor position based on adaptive wavelet neural network(WNN)and the differential evolution(DE)algorithm to optimize WNN structures,thus realizing the improvement of accuracy,exactness of the communication signals and convergence speed of the rotor position identification.Finally,both simulations and experimental results show that the proposed method has high accuracy of recognizing rotor position and strong orientation ability.
文摘火电厂分布式控制系统(Distributed Control System,DCS)在机组控制与安全运行中依赖稳定的通信网络,而通信延迟易引发控制响应滞后与数据异常,影响运行可靠性。通过分析通信延迟问题,提出网络设备升级、系统配置优化及环境防干扰等解决方案,并验证其实施效果,提出一系列优化策略。研究为提升火电厂DCS系统通信实时性与稳定性提供了工程参考与应用价值。
文摘This paper presents the speed control of a separately excited DC motor using Neural Network (NN) controller in field weakening region. In armature control, speed controller has been used in outer loop while current controller in inner loop is used. The function of NN is to predict the field current that realizes the field weakening to drive the motor over rated speed. The parameters of NN are optimized by the Social Spider Optimization (SSO) algorithm. The system has been implemented using MATLAB/SIMULINK software. The simulation results show that the proposed method gives a good performance and is feasible to be applied instead of others conventional combined control methods.
文摘为提升火电厂分布式控制系统(Distributed Control System,DCS)通信网络的可靠性和实时性,通过分析常见火电厂DCS的冗余通信网络拓扑及其存在的问题,探讨了单点故障隐患、切换延迟大和网络负载不均等关键技术难点,提出了实现全路径物理+逻辑双冗余、采用毫秒级智能切换协议、部署动态负载均衡与服务质量(Quality of Service,QoS)策略等优化策略。验证结果表明,这些优化策略能够有效消除火电厂DCS的冗余通信网络拓扑单点故障风险,显著缩短冗余切换时间,合理分配网络带宽。
