Overall control strategy and operational performances of a doubly fed wind turbine generator system

In order to comprehensively and correctly analyze the real-time operational characteristics of a grid-connected wind turbine generator system, it is necessary to analyze the overall control strategies and operation performances of the wind turbine generator system. According to the type of a doubly fed wind turbine generator system, the mathematical models of wind turbine, drive train and doubly fed induction generator (DFIG) are presented. From the viewpoints of the maximum wind energy capture and safe operation of the wind turbine, a maximum power output control strategy is proposed by considering the DFIG loss minimization, and a variable pitch control strategy is also presented by considering generator rotational speed restriction and the output power restriction. Combined with a power decoupling strategy of DFIG, the overall operational performances of the doubly fed wind turbine generator system are simulated. By comparing the simulation, theoretical analysis and actual operational data, the results show that the presented model and overall control strategies of the doubly fed wind turbine generator system are valid.     

Modeling and simulation of a grid connected wind turbine withdoubly fed induction generator

In order to fully research the effects of external excitations, such as wind speed, wind direction and voltage disturbance, on a grid connected wind turbine with doubly fed induction generator, a co-simulation model of MW-class wind turbine system is established by using Simpack and Matlab/Simulink software. Also, by considering the actual control strategies in the process of simulation, the relationship between external excitations and mechanical system is studied. According to time-domain simulation under the turbulent wind condition, the dynamic meshing forces of gears are analyzed. Besides, the vibration responses of tower are calculated under the different external excitations. Research results lay a foundation for dynamic performance optimization and reliability design of a wind turbine.     

The design of torque dynamic sliding mode controller in permanent magnet synchronous generator for wind turbine

Permanent magnet synchronous generator for wind turbine is a multivariable nonlinear system with strong coupling. Considering the influence of the volatile parameters of the generator on the performance of vector control, the torque dynamic sliding-mode control strategy is further studied. The proposed first order dynamic sliding-mode control strategy reduces the chattering by using a new switch function constituted with derivative element. With the dynamic sliding-mode controller in the power outer loop, the PMSG vector control system shows excellent robustness and insensitivity to the parameters and disturbance, which is confirmed by simulation.     

Fault Diagnosis in Hydraulic Turbine Governor Based on BP Artificial Neural Network

The governing system of hydraulic turbine generator plays an important role in power system. It is significant to find out the faults of governing system and remove them quickly. This paper sets up a new fault diagnosis model of the hydraulic turbine generator governing system with the advanced ANN (artificial neural net). This 17-in-13-out model consists of three layers. It is proved that this model can find the fault accurately.     

system modeling and simulation of wind turbines

Wind turbines operate in harsh environment with transient and variable working conditions. As a result, wind turbines are complicated, nonlinear, uncertain systems. Modeling and analysis of these systems are crucial to their design. Based on MATLAB, a new dynamic simulation model of a stalled wind turbine was presented. The blade element momentum theory and the state space method were programmed into MATLAB/SIMULINK to calculate wind turbine aerodynamic performance. The generator was also modeled in MATLAB/SIMULINK, taking the coupling between the generator and the rotor speed into consideration. Based on the proposed MATLAB model, an analysis of a 600 kW wind turbine was carried out. The calculation values were compared with the measured data. The results indicate the correctness of the proposed MATLAB model. The simulation model can be applied to optimize design and control of stalled wind turbines.     

Gear-bearing coupling dynamics characteristics of wind turbine planetary gear transmission system under variable load

Considering that the transmission system of wind turbine works in complex and changing load environment caused by stochastic wind speed,this paper uses sparse least squares support vector machine(SL-SVM) to simulate wind speed of true wind field,and obtains time-varying wind load caused by stochastic wind speed. The lumped-parameter method is used to develop a dynamic model of planetary gear transmission system of wind turbine coupled with bearing. The model includes the varying wind load,time-vary mesh stiffness of gear pair and time-vary stiffness of rolling element bearing. The numerical method is used to simulate the dynamic performance of planetary gear system of Multibrid Technology Wind Turbine with 1.5 MW rated power. The vibration displacement responses of the transmission system are obtained as well as dynamic meshing force each pair of gear and nonlinear bearing forces. The research can provide a foundation for optimizing dynamic performance and reliable design of gear transmission system of wind generator.     

Using BP Neural Network to Determine the Membership Function of the Input of Fuzzy Control System

While design the fuzzy controller, it is very important to determine the membership function of fuzzy variables.The data can be broadly classified as fuzzy sets by using the classification property of the BP neural network. The author selects a BP neural network with one hide layer and uses S function to the input and hide layer, and linear function to the output layer.Advanced BP algorithm isused to train the BP neural network in the environment of MATLAB . The nearer to the target values is the better the last output is.With the trained BP network , the membership values of the inputs can be got ten. This method has high rate and low error.     

Calculation Model Based on Improved BP Network of Refrigerant State Parameters

BP network is improved by using Levenberg-Marquardt optimization method. Under large swatch input circumstance, more fast network constringency speed and more highly approach precision are obtained. Calculation model based on improved BP neural network of refrigerant state parameters is established. The main defect of refrigerant hot ties of matter model in existing refrigeration and air-conditioning appliances simulation system is overcome.     

山西日光温室逐日极端气温预测模型研究

利用山西省忻州市日光温室的室内小气候观测数据及气象站资料,用BP神经网络及逐步回归法建立以多种输入变量的不同天气条件下的日光温室内最高温度、最低温度的模型。结果表明,利用BP神经网络及逐步回归法建立的模型R2均在0.96以上,RMSE与AE大部分在2℃之下。利用逐步回归方法在模拟日光温室内晴天最高、最低温度和寡照的最高温度精度较高,利用BP神经网络模型在多云的最高、最低温度与寡照的最低温度模拟的精度较高。选择精度更好的模型对日光温室的极端气温做准确的预测,可为山西省设施农业的管理和调控及小气候预报提供支持。     

An asymmetric fault ride-through control method forPMSG wind turbine based onsuper-capacitors

With the rapid increasing interaction between wind turbines and power systems, wind turbines have to have the fault ride-through (FRT) capability to ensure the safe operation of power grid. In order to improve the asymmetric FRT capability of permanent magnet synchronous generator (PMSG) wind turbine, a novel control FRT method based on super-capacitors is proposed. In this method, super-capacitors are connected to the DC bus of AC-DC-AC converter via a bi-directional DC-DC converter, and the power processed by the super-capacitors is controlled to limit the increasing of the DC bus voltage of the AC-DC-AC converter in grid failure condition, and to reduce the 2nd order voltage ripple in the DC bus. Meanwhile, the proposed control method employs the grid voltage feed-forward approach to reduce the negative sequence current component in the grid side converter. According to the low voltage ride through (LVRT) standard, the selection of the super-capacitor capacity is also discussed, and then a mathematical model of the super-capacitor with the bi-directional DC-DC converter is established for designing the controller. Simulation results for a 1MW PMSG wind turbine by MATLAB show that the proposed control method reduces both the negative sequence current component in grid side converter and the 2nd order voltage ripple in DC link at the same time. The results also demonstrate that the asymmetric FRT capability of PMSG wind turbine is improved, which verifies the effectiveness of the proposed control method in this paper.     

A new pattern recognition method of gas sensor array detection

BP neural network based gas sensor array detection pattern recognition has some disadvantages, such as slow convergence and local minimum problem. A modified immune neural network model which combines BP algorithm and immune algorithm is proposed to enhance global search capability and improve the performance of the neural network model. Orthogonal test is adopted to design the study samples of neural network. This ensures the accuracy of neural network while reducing the number of samples. The simulation results show that the proposed pattern recognition method solves the cross sensitivity of gas sensor effectively, overcomes the disadvantages of traditional BP neural network and improves the learning speed and detection accuracy.     

基于人工神经网络的落叶松毛虫发生量预测模型的研究

运用人工神经网络的原理和算法,根据相关系数法和逐步回归法选取了蒸发量、气温、风速、相对湿度等气象因子作为预报因子,建立了内蒙古东部地区的鄂伦春自治旗落叶松毛虫的发生面积及虫口密度与气象因子之间的BP网络模型。结果表明：所建立的模型具有较高的预测效果。通过逐步回归筛选出的预报因子,与事实吻合,选取合理。误差较小,控制在0.1%~25.0%之间。可以作为病虫害综合防治的依据。     

联想神经网络的风速序列预测分析

为了提高风速序列预测的可靠性,针对具有混沌特性的风速序列,构造了一种用于风速序列预测的联想网络。以风速序列的波动性作为相似性测度准则,构造联想网络的存储样本模式,根据存储模式中蕴含的关联信息完成网络的无监督学习,从而完成具有自相似性的风速序列的一步或多步预测分析。与传统前向型神经网络相比,该网络预测机理明确,预测结果唯一,且可一次给出多步预测结果。仿真实验结果表明,该网络的具有良好预测性能,适用于风速序列的动态预测。     

artificial neural networks based prediction of electromagnetic compatibility problems

It is necessary to predict electromagnetic compatibility (EMC) for electronic equipment and systems. We proposed a fast EMC prediction approach via artificial neural networks (ANN). By choosing relevant electromagnetic interference parameters as the input prediction features, a back propagation (BP) neural network was used to construct the mapping between the input prediction features and the electromagnetic disturbance response of the sensitive system. The EMC fast prediction BP model was trained and tested by sample sets generated using an electromagnetic computational method. We used this method to predict the crosstalk coupling between two wires. The experimental results show the effectiveness of the proposed method.     

Dynamic characteristics analysis of megawatt wind turbine drive train

Since the wind turbines are installed on the flexible support tower, the drive train of the wind turbines runs under severe work conditions with varying wind directions and loads. So its failure rate is high and it is the bottle neck of the wind power development. This work presents a study which takes the coupling effect of oscillating of tower barrel and the twisting vibration of driven train into account. Using the lumped parameter method, a coupled dynamic model for the megawatt wind turbine drive train is built by considering the flexible tower barrel support effects. Then, the dynamic characteristics of the megawatt wind turbine drive train are analyzed. The Campbell chart is used in this research to analyze the potential resonance points. And the potential resonance frequencies between the cutting in and cutting out rotational speed of the drive train are obtained. Finally, Simpack is used to analyze the dynamic characteristics of drive train and verify the correctness of the proposed method.     

应用STATCOM的DFIG风力发电机低电压穿越能力分析

针对DFIG（double fed induction generator）风电机组低电压穿越能力（LVRT,low voltage ride through）问题,笔者基于STATCOM研究了一种电压外环与电流内环相结合的双闭环反馈控制策略,并仿真验证了所提出方法的有效性。将STATCOM分别安装风电机组机端、并网点高压侧和低压侧,且设置不同电压跌落深度,比较其补偿效果。实验结果表明,安装在风电机组机端时补偿效果最好。在电网电压跌落时,STATCOM能快速为电网输入无功,抬高风力机的机端电压,从而提高风电场的LVRT能力,从STATCOM输出无功大小和风电场机端电压被抬升的比例两方面分析,对于不同深度的电压跌落,STATCOM补偿效果都较为显著。     

基于遗传算法的BP神经网络在小麦蛋白质含量预测中的应用

为了快速、简便、准确地测定小麦蛋白质的含量,本文提出了应用近红外光谱分析技术结合遗传算法(GA)的BP神经网络的建模方法。采用SPXY算法对光谱数据进行了合理划分,并运用连续投影算法(SPA)将预处理过的数据压缩,对光谱数据提取最佳敏感波点作为GA-BP神经网络的输入,建立小麦蛋白质含量的校正模型。模型的预测均方根误差和预测相关系数为1.3379和0.979,并与BP神经网络所建立的校正模型进行了比较。结果表明：GA-BP神经网络所建模型收敛速度快、训练时间短、准确度也较高,能够实现对小麦蛋白质含量快速高效的检测。     

Nonlinear Forecast System for River Water Pollution Based on GIS

Based on the analysis of the water pollution spatial distribution characters of Yangtze River in Chongqing,a new method based on the integration of BP neural network and genetic arithmetic(GA) is proposed.For some shortcomings existed in the standard BP neural network,this method has ultimately overcome these shortcomings by combining the GA with BP artificial neural network through altering stimulating function,adding momentum factor to power value for BP algorithm and introducing genetic arithmetic to searching for the knots of the hidden layer,momentum factor and learning level.Using this method can easily overcome the difficulty of measuring the water prediction model's parameters.GIS is used as a tool for data management and spatial analysis,and the prediction result of the model for the water pollution spatial distribution characters of Yangtze River in Chongqing is visualized and explored with the precision of more than 78%.     

Modeling and Simulation of a Novel Drive Train for Wind Turbine with Large Capacity

On the basis of a planetary transmission, a novel hydrodynamic speed controlled transmission system for wind turbines with large capacity is presented. The new drive train consists of wind rotors, planet accelerators, hydro-mechanical and synchronous generators. The dynamic mathematical model of the drive train is established. The digital simulation of speed regulation characteristics for hydrodynamic speed controlled system is studied by using Matlab/Simulink. The simulation results show that continuously variable transmission and fixed speed control can be achieved, and the drive train works well in stability and dynamic performances. They can increase the power yield from the wind, smooth the electric power output, and alleviate the load peak in the new drive train .     

Voltage and Reactive Power Optimization of Main Electric Power Network in Chongqing

Based on the reactive surplus of Chongqing 220 kV main electric power network under low water and low load, and on state of higher system voltage, a thorough research is done on voltage and reactive power of the system power network by means of calculation,analysis and experiments. A main network calculating equivalence model of power network in Chongqing is constructed. And reactive power optimizing calculation is figured out on the Chongqing power network on condition that the loss minimum of the active power network is object function. Several optimizing compensatory schemes are put forward. Based on the calculation result and the analysis of all schemes, the most reasonable and feasible optimizing scheme could be achieved. Meanwhile, the feasibility that the system voltage could be adjusted when generator operating under excitation was demonstrated. According to the experience of under-excitation operation of the same type units , it decreases the system voltage, improves Chongqing power network running performance, and strengthens the coordination and stabilization of system.