Wind Speed Prediction Based on Improved VMD-BP-CNN-LSTM Model

Amid the randomness and volatility of wind speed, an improved VMD-BP-CNN-LSTM model for short-term wind speed prediction was proposed to assist in power system planning and operation in this paper. Firstly, the wind speed time series data was processed using Variational Mode Decomposition (VMD) to obtain multiple frequency components. Then, each individual frequency component was channeled into a combined prediction framework consisting of BP neural network (BPNN), Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) after the execution of differential and normalization operations. Thereafter, the predictive outputs for each component underwent integration through a fully-connected neural architecture for data fusion processing, resulting in the final prediction. The VMD decomposition technique was introduced in a generalized CNN-LSTM prediction model;a BPNN model was utilized to predict high-frequency components obtained from VMD, and incorporated a fully connected neural network for data fusion of individual component predictions. Experimental results demonstrated that the proposed improved VMD-BP-CNN-LSTM model outperformed other combined prediction models in terms of prediction accuracy, providing a solid foundation for optimizing the safe operation of wind farms.

Adaptive Gain Tuning Rule for Nonlinear Sliding-mode Speed Control of Encoderless Three-phase Permanent Magnet Assisted Synchronous Motor

In this paper, an adaptive gain tuning rule is designed for the nonlinear sliding mode speed control(NSMSC) in order to enhance the dynamic performance and the robustness of the permanent magnet assisted synchronous reluctance motor(PMa-Syn RM) with considering the parameter uncertainties. A nonlinear sliding surface whose parameters are altering with time is designed at first. The proposed NSMSC can minimize the settling time without any overshoot via utilizing a low damping ratio at starting along with a high damping ratio as the output approaches the target set-point. In addition, it eliminates the problem of the singularity with the upper bound of an uncertain term that is hard to be measured practically as well as ensures a rapid convergence in finite time, through employing a simple adaptation law. Moreover, for enhancing the system efficiency throughout the constant torque region, the control system utilizes the maximum torque per ampere technique. The nonlinear sliding surface stability is assured via employing Lyapunov stability theory. Furthermore, a simple sliding mode estimator is employed for estimating the system uncertainties. The stability analysis and the experimental results indicate the effectiveness along with feasibility of the proposed speed estimation and the NSMSC approach for a 1.1-k W PMa-Syn RM under different speed references, electrical and mechanical parameters disparities, and load disturbance conditions.

Empirical Mode Decomposition-k Nearest Neighbor Models for Wind Speed Forecasting

Hybrid model is a popular forecasting model in renewable energy related forecasting applications. Wind speed forecasting, as a common application, requires fast and accurate forecasting models. This paper introduces an Empirical Mode Decomposition (EMD) followed by a k Nearest Neighbor (kNN) hybrid model for wind speed forecasting. Two configurations of EMD-kNN are discussed in details: an EMD-kNN-P that applies kNN on each decomposed intrinsic mode function (IMF) and residue for separate modelling and forecasting followed by summation and an EMD-kNN-M that forms a feature vector set from all IMFs and residue followed by a single kNN modelling and forecasting. These two configurations are compared with the persistent model and the conventional kNN model on a wind speed time series dataset from Singapore. The results show that the two EMD-kNN hybrid models have good performance for longer term forecasting and EMD-kNN-M has better performance than EMD-kNN-P for shorter term forecasting.

Effect of wall-cooling on Mack-mode instability in high speed flat-plate boundary layers

The instability of the Mack mode is destabilized by wall-cooling in a high speed boundary layer. The aim of this paper is to study the mechanism of the wall cooling effect on the Mack mode instability by numerical methods. It is shown that the wall-cooling can destabilize the Mack mode instability, similar to the previous conclusions with the exception that the Mack mode instability can be stabilized by wall-cooling if the wall temperature is extremely low. The reversed wall temperature is related to a freestream condition. If the Mach number increases to a large enough value, e.g., about 7, the reversed wall temperature will tend to be zero. It seems that the Mack mode instability is determined by the region between the boundary layer edge and the critical layer. When the wall temperature decreases, this region becomes wider, and the boundary layer becomes more unstable. Additionally, a relative supersonic unstable mode can be observed when the velocity of the critical layer is less than 1 - liMa or is cancelled by the wall-cooling effect. These results provide a deeper understanding on the wall-cooling effect in high speed boundary layers.

PMSM speed control using adaptive sliding mode control based on an extended state observer

In this study,a composite strategy based on sliding-mode control( SMC) is employed in a permanent-magnet synchronous motor vector control system to improve the system robustness performance against parameter variations and load disturbances. To handle the intrinsic chattering of SMC,an adaptive law and an extended state observer( ESO) are utilized in the speed SMC controller design. The adaptive law is used to estimate the internal parameter variations and compensate for the disturbances caused by model uncertainty. In addition,the ESO is introduced to estimate the load disturbance in real time. The estimated value is used as a feed-forward compensator for the speed adaptive sliding-mode controller to further increase the system's ability to resist disturbances. The proposed composite method,which combines adaptive SMC( ASMC) and ESO,is compared with PI control and ASMC. Both the simulation and experimental results demonstrate that the proposed method alleviates the chattering of SMC systems and improves the dynamic response and robustness of the speed control system against disturbances.

THE APPLICATION OF BRANCH MODE METHOD TO THE CRITICAL SPEED ANALYSIS OF COMPOUND ROTATING SYSTEMS

This paper is devoted to the application of branch mode method in the critical speed ana-lysis of compound rotating systems, in which the distributed inertia including gyroscopic effectand distributed elastic support are taken into account. Finally, the method introduced in this paper is used to calculate the critical speeds of anew-type spindle on the spinning frame. The first three critical Speeds are calculated and com-pared with the values obtained from the experimental approach and other theoretical methods.The results show that they are in good agreement with each other.

基于轨道板振动加速度的钢轨振动加速度反演估计与现场验证

为研究高速铁路轨道板与钢轨之间的时空关联规律,提出变分模态-转换器(Variational Mode Decomposition-Transformer, VMD-T)反演模型,该模型通过分解轨道板振动加速度来反演估计钢轨振动加速度.首先,对数据进行预处理并利用双门限法检测振动端点,分离振动信号与静默信号、干扰信号,再将提取后的振动信号整合输入到VMD-T模型.其次,利用VMD模型将轨道板振动加速度数据分解成一系列不同的子模态,并网格遍历搜索与钢轨振动加速度相关系数最大的子模态,以降低原始数据的复杂度以及非平稳性,提升Transformer模型的特征抽取能力.然后,通过Transformer模型对搜索出的轨道板振动加速度子模态与钢轨振动加速度数据进行反演估计训练.最后,将该模型应用于某城际高速铁路轨道板与钢轨实测振动加速度数据反演估计试验.现场高铁试验结果表明:与单一Transformer模型相比,VMD-T模型均方根误差(RootMean Squared Error, RMSE)、绝对平均误差(Mean Absolute Error, MAE)及决定系数(R2_score)分别提升近20%、11%及48.1%,特征学习能力更强,反演估计效果更佳,初步实现钢轨垂向振动加速度幅值非接触式监测估计.

PMSM无模型滑模转速无差拍电流预测控制

针对传统永磁电机调速系统易受到参数摄动影响而导致控制精度下降的问题,提出一种基于扩张状态观测器(ESO)的永磁同步电机(PMSM)无模型滑模转速无差拍电流预测控制策略。首先用参数摄动下的PMSM调速系统数学模型归纳出系统对应的超局部模型,然后结合无差拍预测控制思想设计了电流环控制器,采用两步预测算法解决了传统无差拍算法存在的延时问题,并且提出校正算法进一步抑制实际的预测误差;利用变速率指数滑模趋近率设计了新型无模型滑模速度控制器,减弱抖振的同时提高了系统响应速度;并设计ESO对参数失配和扰动进行估计和补偿。最后,通过仿真与半实物实验验证了所提控制策略的有效性。

基于双环自适应滑模控制的高速列车运行追踪

针对列车高速运行跟踪控制问题,提出了一种基于双环结构的RBF神经网络自适应滑模控制算法。首先系统结构分为位移与速度控制子系统,防止列车因单个控制器故障而失控;在此基础上采用积分滑模控制,加强控制器的鲁棒性;同时在速度子系统中引入参数自适应算法与RBF神经网络自适应算法削弱列车受到基本阻力、附加阻力以及不确定性阻力带来的影响;最后通过Lyapunov稳定性分析证明系统的稳定性。通过仿真实验结果表明,位移误差在[-3.3×10^(-4),1.9×10^(-4)]范围以内,速度误差在[-2.1×10^(-2),3.1×10^(-2)]范围以内,该算法可以实现对列车的速度与位移精确追踪。

永磁同步电机新型趋近律滑模控制器设计

针对传统指数趋近律因函数不连续性引起抖振、趋近速度与抖振抑制之间无法同时满足高性能控制系统要求的问题,提出基于系统状态变量的新型滑模趋近律,并应用于永磁同步电机速度、电流控制器中。趋近律引入系统状态变量幂次项和状态变量的双曲正弦值,使系统状态变量以等速和指数2种速率趋向切换面,可以加快系统到达切换面的速度,当系统接近切换面时,指数项接近于0,等速项开始起关键作用,对系统的抖振进行抑制。同时采用双曲正切开关函数替代符号函数,以去除因函数的不连续性所引起的抖振问题。既能提高系统到达滑模面的速度,又能有效抑制固有抖振,提升系统的动态性能。仿真和实验结果表明,新型趋近律相比于传统指数趋近律能够有效降低永磁同步电机启动时转速超调,提高系统的响应速度,抑制系统的抖振。

应用于PMSM调速系统的改进超螺旋滑模控制

针对永磁同步电机(PMSM)易受外界扰动和参数不确定性的影响,此处设计了一种改进超螺旋滑模控制策略。该方法采用一种准滑动模态中的连续函数来替代符号函数,以克服传统滑模控制存在的抖振问题,并将比例控制和积分控制引入超螺旋滑模控制来提高控制系统对负载和参数变化的鲁棒性,采用Lyapunov函数对控制系统进行稳定性分析。实验结果表明,所设计的改进滑模控制器能有效抑制控制系统的抖振,实现控制系统的快速跟随和无超调工作,增强了系统的鲁棒性。

高速铁路日常客运量的EMD-Informer组合预测方法

铁路客流需求的科学预测是进行运输组织方案决策的重要依据。以高速铁路历史客票数据为基础,结合经验模态分解(empirical mode decomposition,EMD)与机器深度学习中的注意力机制,提出高速铁路日客流量的EMD-Informer组合预测方法。首先采用EMD方法分解高速铁路客流量序列,获得具有周期特征和线路客流内在特征的模态分量,再利用Informer模型分别训练和预测各模态分解分量,并通过多头注意力机制高效挖掘客流数据内在规律和捕捉数据序列中的关键特征,在此基础上重组各分量预测值,从而得到高速铁路日常客流的整体高精度预测值。同时,根据结合问题特征的大量实验,明确可供实际运用参考的超参数设置规则。基于京沪高速铁路全线的实例计算分析表明,相对对比预测方法,EMD-Informer组合预测方法在高速铁路客流的单步预测及超前预测上均具有明显更小的预测误差。

基于参数优化VMD和TET的柔直线路单端故障测距方法

单端行波故障测距方法在考虑频变波速影响时需要提取故障行波时频域特征,但现有方法存在时频分辨率较低、波头识别困难和波速计算不准确的问题。为此,提出一种基于参数优化变分模态分解(variational mode decomposition,VMD)和瞬态提取变换(transient extraction transform,TET)的单端故障定位方法。首先,利用麻雀搜索算法(sparrow search algorithm,SSA)优化VMD参数,提取含有故障特征的高频模态分量。然后,对该模态分量进行瞬态提取变换,通过去除短时傅里叶变换中模糊的时频能量,保留与信号瞬态特征密切相关的时频信息,得到故障行波时频域全波形。最后,在故障行波全波形中提取主频分量并标定初始波头与第二反射波头,通过计算主频分量下的波速度,结合行波定位方法实现单端故障测距。在PSCAD/EMTDC中搭建四端柔性直流电网的仿真结果表明,所提算法对过渡电阻和噪声具有较强的耐受性,即使在较低采样率下也能实现准确的故障定位。

计及误差信息的自适应超短期风速预测模型

为提升超短期风速预测精度,提出一种计及误差信息的自适应混合预测模型。应用自适应噪声的完备集合经验模态分解模型与鲸鱼优化的变分模态分解模型分别对风速样本数据与预测误差进行分解,同时计算各子序列的模糊熵以判断序列复杂程度。在此基础上,应用鲸鱼优化的长短期网络预测复杂程度较高的序列,差分自回归移动平均模型预测复杂程度较低的序列。最后,将初始风速预测结果和风速误差预测值相加得到基于误差修正的超短期风速预测值。结果表明,修正预测误差与考虑分解策略可有效提升点预测的性能,与基准模型相比,所提模型在多场景下均具备优良的预测精度。

基于滑模观测器的高速PMSM无传感器控制

针对基于饱和函数滑模观测器方法存在调节参数多及低通滤波器带来的相位延迟问题,研究一种基于超螺旋算法的滑模观测器无传感器控制策略,通过理论推导及系统稳定性分析,设计了一种滑模系数根据转速变化在线调节的自适应滑模系数算法。通过实验验证了该方法相比于基于饱和函数滑模观测器,能在较宽速度范围内有效地抑制抖振,提高了无传感器控制系统的估计精度,简化了参数调节过程及滤波器设计环节。

基于FT601Q的超高速多模式智能存储系统

针对目前大多数存储系统数据传输速率慢,传输模式单一,存储操作过于依赖上位机的问题,设计了一种基于FT601Q的超高速多模式智能存储系统。系统采用FPGA主控芯片,RS422接口接收PCM数据码流,光耦指令解析模块进行智能数据存储操作,并实现断电续存功能,通过检测判读“FF”位置确定断电位置,保证意外断电时,原有数据不被覆盖,通过USB3.0接口或千兆以太网方式将数据高速传至上位机显示。测试结果表明:该系统传输速率能够达到370 Mbit/s,存储数据读取速度得到极大提高,且未发现数据丢失现象,满足存储系统传输速率快、可靠性高、智能存储设计需求。

基于互补集成经验模态分解和Stacking融合的短期风速组合预测模型

针对风电场短期风速预测准确度不高的问题,提出一种基于互补集成经验模态分解和Stacking融合的短期风速组合预测模型。首先,为突出短期风速的局部特征并降低建模难度,通过互补集成经验模态分解算法将短期风速分解为若干个稳定分量。然后,利用信息熵和近似熵来判定各分量的复杂度,高复杂度分量选择最小二乘支持向量机、低复杂度分量选择随机配置网络作为对应的预测模型。利用Stacking算法对每个模型的预测值进行融合,使预测精度得到提升。最后,通过一组实际的短期风速数据作为研究对象,将提出的预测模型应用于其预测。对比结果表明,所提预测模型可提高短期风速的预测精度。

RBCC模态特征与热力循环分析样本全覆盖策略

为了获得样本全覆盖的RBCC全模态热力循环分析策略,针对目前尚有争议的低速阶段,采用数值模拟方法研究了支板式RBCC构型在Ma=0~2的流场演化特性,基于对流场演化的认识,区分了火箭-冲压联合工作阶段的模态,提出了除纯火箭模态以外的RBCC样本全覆盖的热力循环分析方法策略。研究结果表明,火箭-冲压联合工作阶段时,RBCC的工作模态包括引射模态、“火箭冲压协同”模态和“加力冲压”模态;在亚声速范围,只要正确赋值来流总温、总压,零速引射分析方法可以用于确定有速度条件的进气道入流流量和混合室出口条件;存在“扫掠激波”的超声速阶段与高亚声速阶段的流场特征相似,零速引射分析方法可用于存在“扫掠激波”的超声速阶段,输入条件取“扫掠激波”后的滞止参数;将零速引射分析方法和以燃烧区特征马赫数为表征的等效热力过程分析方法结合,可以实现RBCC除纯火箭模态以外的各模态样本全覆盖的热力循环分析。

永磁同步电机非线性增益非奇异快速终端滑模控制

为了研究传统滑模控制中系统误差在有限时间内无法收敛至0以及传统滑模控制中系统抖振与收敛速度互不兼容的问题,提出一种非奇异快速终端滑模控制与扰动观测器结合的速度控制器。通过将参数可变的非线性函数作为增益代替固定增益加入滑模控制策略中从而改善系统响应速度同时减小系统的抖振。针对转矩扰动对系统的影响,加入负载转矩扰动观测器并补偿到q轴电流中以进一步提高控制器抗负载扰动能力。根据李雅普诺夫稳定性理论对提出的新型滑模控制器进行稳定性证明,经过仿真和实验证明,电机在启动时响应快、无超调且抖振较小,在突加转矩时转速波动小且恢复时间迅速,证明了改进后的变增益非奇异终端滑模控制与传统非奇异快速终端滑模控制策略相比可以提高动态性能的同时抑制系统抖振、增强系统的鲁棒性。