Time filter

Source Type

Xiang C.M.,Frontier Electrical Technology Co. | Gu T.W.,Nanjing Southeast University | Fan L.X.,Frontier Electrical Technology Co. | Jiang Y.Q.,Frontier Electrical Technology Co.
Applied Mechanics and Materials | Year: 2013

This paper presents a new method to enhance the participation of doubly fed induction generators (DFIG) effectively in system frequency regulation. A new associated control based on Hopfield neural network (HNN) is proposed to control the rotor kinetic energy and the primary reserve power of DFIG simultaneously. The proposed approach takes advantage of the learning ability of neural network to form an adaptable Hopfield neural network controller (HNNC). And the feasibility of all those control strategies is analyzed in a Two-area four-generator system based on PSCAD/EMTDC. Simulation results indicate that the proposed strategy can greatly improve system frequency stability compared with classical strategies. © (2013) Trans Tech Publications, Switzerland.

Fan L.,Frontier Electrical Technology Co. | Jiang Y.,Frontier Electrical Technology Co. | Gu T.,Nanjing Southeast University
Applied Mechanics and Materials | Year: 2013

This paper proposes an improved algorithm for tracking the Thévenin equivalent parameters with local phasor measurements for voltage stability analysis. Estimation errors between the Thévenin equivalent voltage and impedance are mathematically formulated, and then used to correct the equivalent parameters with two subsequent measurements. This algorithm does not introduce any parameters drift problems and does not need a large data window to converge. A 2-bus test system, the IEEE 14-buses system and an actual 500kV grid system from China are used to test the proposed algorithm. Test results indicate that this algorithm is accurate, robust and fast for real time voltage stability monitoring and control. © (2013) Trans Tech Publications, Switzerland.

Wei Y.-F.,Hohai University | Wei Z.-N.,Hohai University | Zhang Y.-Q.,Chongqing Electric Power Research Institute | Sun G.-Q.,Hohai University | And 2 more authors.
Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | Year: 2012

Leading phase of generator is an effective method to reduce voltage of the key point which is much high in valley load period. First, this paper summarizes the progress of research on leading phase operation of generator both at home and abroad, including the constraining factors of leading phase ability, stability monitoring, leading phase ability model, particular influence induced by leading phase operation of generator, and the application in different fields of black start, pumped storage power station, wind farm, and so on. Then the opinions about the future works for leading phase operation management database and leading phase operation of multi-generators are presented. The voltage regulation and depth optimization relating to leading phase of multi-generators are discussed, and the key problems of leading phase of multi-generators are also addressed. At last, the corresponding analysis ideas for researches on the above issues are extended, which direct the orientation of the development of leading phase of multi-generators.

Zhai X.,Frontier Electrical Technology Co. | Wei Z.,Hohai University | Fan L.,Frontier Electrical Technology Co. | Xu G.,Frontier Electrical Technology Co. | And 2 more authors.
Dianli Zidonghua Shebei/Electric Power Automation Equipment | Year: 2015

As generator is a multivariable and strongly-coupled nonlinear system, it is difficult to establish an accurate leading phase capability model of generator by traditional analysis method. A generator leading phase capability model based on the RVM(Relevance Vector Machine) is proposed, which takes the active power and reactive power of generator as its inputs and the generator power-angle and grid voltage as its outputs. With the test results of generator leading phase operation in typical operating conditions as the training samples and test samples, a RVM-based model of generator leading phase capability is built for a 600 MW generator. The influence of the kernel function selection on the convergence accuracy of RVM-based model is discussed. Simulative results show that, the model based on RVM has higher accuracy and better generalization ability than that based on BP neural network, RBF(Radial Basis Function) neural network or SVM(Support Vector Machine). It overcomes the limitations of traditional methods effectively and is suitable for the real-time control of generator leading phase operation. ©, 2015, Electric Power Automation Equipment Press. All right reserved.

Wang C.,Frontier Electrical Technology Co. | Wang H.,Hohai University | Xu G.,Frontier Electrical Technology Co.
Dianwang Jishu/Power System Technology | Year: 2011

A new back propagation neural network (BPNN)-based method for the modeling of generator leading phase ability is proposed. The BPNN possesses two hidden layers and a output layer and taking the active and reactive power as inputs and the generator angle and network votlage as output. Taking the resuts of generator leading operation test under typical operation conditions as training sampling and test sampling, a BPNN model of leading phase ability of a certain 600 MW generator is built. With a view of optimal convergence accuracy, in the model design the number of hidden layers, neurons of the model as well as its transfer function are optimized. Results of both simulation and leading phase tests show that the proposed modeling method, which can effectively overcome the boundedness of traditional analysis method, possesses strong generalization ability and the model designed by the proposed method is accurate.

Liu Y.,Frontier Electrical Technology Co. | Fan L.,Frontier Electrical Technology Co. | Xu G.,Frontier Electrical Technology Co. | Tang Y.,Frontier Electrical Technology Co. | And 2 more authors.
Gaoya Dianqi/High Voltage Apparatus | Year: 2016

The concentration of dissolved gases in transformer oil is an important parameter to evaluate insulation state of oil-immersed transformer. Effective concentration prediction of the dissolved gases can help to identify latent faults of transformer in time. In this paper, a concentration prediction model of dissolved gases in transformer oil is proposed based on the nonnegative matrix factorization (NMF) and the improved extreme learning machine (ELM). The input data is decomposed by using the NMF algorithm to reduce the dimension of input variables. Then Adaboost algorithm is introduced to improve the extreme learning machine, and the derived nonnegative lower-dimension mapping matrix is taken as the inputs of the model for training. Simulation illustrates the effectiveness and availability of the proposed method in reducing the dimension of the input variables, performing the concentration prediction of dissolved gases in transformer oil, and improving the prediction accuracy. © 2016, Xi'an High Voltage Apparatus Research Institute Co., Ltd. All right reserved.

Wang C.,Hohai University | Wang C.,Frontier Electrical Technology Co. | Wang H.,Hohai University | Xiang C.,Frontier Electrical Technology Co. | Xu G.,Frontier Electrical Technology Co.
Diangong Jishu Xuebao/Transactions of China Electrotechnical Society | Year: 2012

Generator leading phase operation is a kind of economic and effective measures of voltage regulation and power quality improvement. Due to the synchronous generator is a multivariable and strong coupling nonlinear system, it is difficult to obtain satisfactory results by traditional analysis method. This paper proposes a new method of modeling generator leading phase ability based on radial basis function (RBF) neural network. The model with active power and reactive power of generator for input, with generator voltage and power-angle for output, using a 600 MW generator leading phase test data training RBF neural network and testing network generalization ability, the choice of the base wide, the number of neurons in hidden layer in RBF network convergence precision influence are discussed. Research shows that this generator leading phase RBF model set up in the paper has the advantages of high speed and precision, and its performance is superior to the BP neural network model.

Loading Frontier Electrical Technology Co. collaborators
Loading Frontier Electrical Technology Co. collaborators