A novel fast distance relay for series compensated transmission lines

This paper presents a fast distance relay for series compensated transmission lines based on the R–L differential-equation algorithm using the theory of equal transfer process of transmission lines. The measuring distances based on the proposed algorithm can fast approach the actual value of fault distance when a fault occurs in front of the series capacitor. When a fault occurs behind of the series capacitor, the fault loop, including the series capacitor, does not match the R–L transmission line model, so the measuring distances fluctuate severely. Based on this, the relative position of the fault with respect to the series capacitor can be judged effectively according to the fluctuation range of the measuring distances, and the accurate fault location can be obtained fast. A variety of PSCAD/EMTDC simulation tests show that the new relay has fast operating speed and high accuracy when applied to the long series compensated transmission lines.     

L2 disturbance attenuation for highly dissipative nonlinear spatially distributed processes via HJI approach

For many practical industrial spatially distributed processes (SDPs), their dynamics are usually described by highly dissipative nonlinear partial differential equations (PDEs). In this paper, we address the L₂ disturbance attenuation problem of nonlinear SDPs using the Hamilton–Jacobi–Isaacs (HJI) approach. Firstly, by collecting an ensemble of PDE states, Karhunen–Loève decomposition (KLD) is employed to compute empirical eigenfunctions (EEFs) of the SDP based on the method of snapshots. Subsequently, these EEFs together with singular perturbation (SP) technique are used to obtain a finite-dimensional slow subsystem of ordinary differential equation (ODE) that accurately describes the dominant dynamics of the PDE system. Secondly, based on the slow subsystem, the L₂ disturbance attenuation problem is reformulated and a finite-dimensional H_∞ controller is synthesized in terms of the HJI equation. Moreover, the stability and L₂-gain performance of the closed-loop PDE system are analyzed. Thirdly, since the HJI equation is a nonlinear PDE that has proven to be impossible to solve analytically, we combine the method of weighted residuals (MWR) and simultaneous policy update algorithm (SPUA) to obtain its approximate solution. Finally, the simulation studies are conducted on a nonlinear diffusion-reaction process and a temperature cooling fin of high-speed aerospace vehicle, and the achieved results demonstrate the effectiveness of the developed control method.     

Frequency analysis and compensation of valve stiction in cascade control loops

Valve stiction is often a common problem in control loops and stiction induced oscillation is the main cause of poor performance in control systems. Cascade control is extensively applied in process industry as an effective strategy to restrain disturbances and compensate process nonlinearities. In recent years many studies have been performed on the detection and quantification of valve stiction in single feedback control loops. However, there is a lack in developing a mechanism which can analyze stiction induced oscillation in cascade control loops. This work focuses on the frequency analysis of stiction induced oscillations in cascade control loops and proposes a mechanism of oscillation compensation through outer and inner controller tuning. The effect of oscillation compensation by changing control strategies is also discussed. The theoretical analysis is evaluated through simulation examples and a pilot-scale flow-level cascade control experiment.     

融合共现推理的Faster R-CNN输电线路金具检测

为促进目标检测模型与电力领域业务知识有机融合,缓解金具样本间长尾分布问题,有效提升输电线路金具的自动化检测效果,提出了融合共现推理的Faster R-CNN(faster region-based convolutional neural network)输电线路金具检测模型。首先,深入研究输电线路金具结构化组合规则,通过数据驱动的方式以条件概率对金具目标间的共现连接关系进行有效表达;然后,结合图学习方法,利用学习并映射的共现概率关联作为共现图邻接矩阵,使用基线模型(Faster R-CNN)提取的特征向量作为图推理输入特征,以自学习的变换矩阵作为共现图传播权重,完成图信息传播并实现有效的共现推理模型嵌入。实验证明,融合共现推理模块的Faster R-CNN模型较原始模型提升了6.56%的准确率,对于长尾分布样本中数量较少的金具性能提升尤其显著。     

解列时刻对解列后孤网暂态稳定性的影响机理

解列时刻是解列后孤网能否保持同步稳定运行的一个关键参量.文中采用扩展等面积准则方法,将组成孤网的机组通过互补群惯量中心-相对运动变换映射为单机映象.基于单机映象等值电磁功率在解列前后的差值在等值功角变化区间上的积分,提出了解列时刻影响孤网暂态能量变化量的计算方法,从能量角度解释了不同解列时刻对孤网暂态稳定性的影响机理.进而提出了解列后孤网暂态稳定裕度对于解列时刻的灵敏度计算公式,判断延迟解列是否有利于孤网暂态稳定性,并通过仿真证明了分析方法的正确性.     

融合 Transformer 与残差通道注意力的恶劣场景水 位智能检测方法

精准感知水位信息变化是实现精细水务管控和洪涝灾害的关键环节之一,而低照度、雾霾、雨雪、冰冻、波浪、镜头抖动等恶劣场景给水位检测带来极大挑战。针对现有方法中难以实现水位精准检测难题,构建一种融合Transformer与残差通道注意力机制的Unet模型(TRCAM-Unet),进而提出基于TRCAM-Unet的恶劣场景水位智能检测方法。关键技术包括通过全尺度连接结构实现多层次特征融合,通过Transformer模块强化区域特征的关联性,通过残差通道注意力模块强化有用信息的表达并削弱无用信息的干扰。相关试验和实践表明,TRCAM-Unet取得了98.84%MIOU评分与99.42%的MPA评分,在约150 m距离外水位检测最大误差不超过0.08 m,水位偏差均值(MLD)仅有1.609×10^-2 m,优于Deeplab、PSPNet等主流语义分割算法。研究结果对解决恶劣场景下水位精准检测难题及洪涝灾害预警具有重要应用价值。     

基于改进生成对抗网络的谐波状态估计方法

传统的基于最小二乘法的谐波状态估计受到量测装置少、精确的谐波阻抗获取难、网络拓扑结构复杂以及电网运行方式变化等因素的限制,造成量测方程欠定、系统非全局可观以及节点间耦合关系难以准确提取等问题。文中提出了一种基于改进生成对抗网络的谐波状态估计方法。该方法基于pix2pix谐波状态估计网络拟合监测节点与目标节点间的耦合关系,利用采集的历史谐波数据,对模型进行批量训练,通过训练之后的生成网络估算目标节点谐波电流、谐波电压幅值,实现基于数据驱动的谐波状态估计。在加噪环境下对模型进行测试,仿真结果验证了所提方法的有效性。     

融合 CEEMD 和 TCN 的受热面积灰预测研究

对锅炉受热面积灰程度的有效预测,可为锅炉提升生产效率和故障预警提供重要依据。 采用清洁因子来评估受热面的 灰污沉积状况,针对其序列非线性、非平稳性的特点,提出一种基于互补集合经验模态分解与时间卷积网络的受热面积灰预测 方法。 首先,通过互补集合经验模态分解将经过小波阈值去噪处理后的原始序列分解为一组子序列分量;然后,针对不同子序 列分别构建基于时间卷积网络的时序预测模型,并优化网络超参数提升预测准确性;最后,将各 IMF 分量的预测结果叠加得出 清洁因子的预测数值。 由实验结果可得,相较于其他两种模型,预测精度分别提高 62. 1%和 57. 1%,CEEMD-TCN 模型对受热 面积灰状况预测精度最高,验证了该模型的准确性和可靠性。