The Experts below are selected from a list of 5547 Experts worldwide ranked by ideXlab platform

Kaijian Ou - One of the best experts on this subject based on the ideXlab platform.

  • rtds real time digital simulator real time digital closed loop converter Transformer Protection test system
    2011
    Co-Authors: Kaijian Ou
    Abstract:

    The utility model relates to a RTDS real-time digital closed-loop converter Transformer Protection test system. The test system comprises a real-time digital simulator (RTDS) and a converter Transformer Protection, the real-time digital simulator outputs the voltage and the current analog signals and the tap position digital signal in a converter Transformer simulation model to the converter Transformer Protection, the converter Transformer Protection inputs a protective tripping digital signal into the real-time digital simulator, a direct-current power transmission system simulation model of a converter Transformer, which is built in the real-time digital simulator, is a single-phase model, and moreover, additional inductors Xp are connected between the converter Transformer and a converter valve. The test system can provide the three-phase current outputs of the head ends of the primary side and the secondary side of the converter Transformer, which are needed by a real-time converter Transformer Protection simulation test, and also can provide the three-phase current outputs of the tail ends of the primary side and the secondary side of the converter Transformer in order to meet the requirements of the RTDS converter Transformer Protection test.

  • converter Transformer Protection rtds real time digital closed loop test system for and method thereof
    2011
    Co-Authors: Kaijian Ou
    Abstract:

    The invention discloses a converter Transformer Protection real-time digital system (RTDS) real-time digital closed loop test system and a method thereof. The test system comprises an RTDS real-time digital simulator and a converter Transformer Protection device, wherein the RTDS real-time digital simulator outputs a voltage analog signal, a current analog signal and a tap joint gear digital signal in a converter Transformer simulation model to the converter Transformer Protection device; the converter Transformer Protection device inputs a Protection trip digital signal to the RTDS real-time digital simulator; a direct-current power transmission system simulation model, established in the RTDS real-time digital simulator, of the converter Transformer is a single-phase model; and an additional inductor Xp is connected between a converter Transformer and a converter valve. The test system can provide the primary side head-end three-phase current output and the secondary side head-end three-phase current output, required for a converter Transformer Protection real-time simulation test, of the converter Transformer, and also can provide the primary side tail-end three-phase current output and the secondary side tail-end three-phase current output of the converter Transformer, thereby meeting the requirements on a converter Transformer Protection RTDS test.

Zaibin Jiao - One of the best experts on this subject based on the ideXlab platform.

  • Knowledge-based artificial neural network for power Transformer Protection
    IET Generation Transmission & Distribution, 2020
    Co-Authors: Zaibin Jiao
    Abstract:

    Data-driven and artificial intelligence based Transformer Protection has attracted increasing attention but not been widely applied in the power system owing to the poor generalisation ability. In this study, a feature transferring method is proposed for a knowledge-based artificial neural network (ANN) to develop a Transformer Protection with an improved generalisation ability. Normally, power experts can reliably identify the running states based on the professional knowledge of only focusing on the unsaturated parts of equivalent magnetisation curve (voltage of magnetising branch-differential current). In order to imitate the power experts, the images of equivalent magnetisation curves whose saturated parts are removed are defined as source domain and the original samples are target domain. An ANN named as S:ANN is firstly trained through the source domain where the extracted features are equivalent to the professional knowledge. Then another ANN with the same structure as S:ANN is trained through the target domain and named as T:ANN. It is specially designed for T:ANN that adaptive layers are employed between S:ANN and T:ANN to reduce the feature differences. Finally, simulations and experiments reveal that the knowledge-based ANN namely the determined T:ANN shows a better generalisation ability through paying more attention to the unsaturated parts.

  • A Transformer Protection Scheme Based on The Deep Forest Algorithm
    2020 IEEE Power & Energy Society General Meeting (PESGM), 2020
    Co-Authors: Zaibin Jiao
    Abstract:

    A Transformer Protection scheme based on the deep forest is proposed to improve the performance of Transformer Protection. Considering that the magnetization curve can reflect the essential cause of the inrush current, but it is difficult to measure, the voltage and differential current sequences are selected as alternative input of the deep forest. The classification deviation of each layer is defined to automatically determine the depth of the deep forest. The Protection acts based on the algorithm output. The deep forest is trained by the simulation sampling data from PSCAD/EMTDC simulation. The performance of the deep forest algorithm is verified through simulation data and dynamic model experimental data. The test results show that the deep forest algorithm can identify the operating states of Transformer quickly and reliably. It has good generalization and no requirement of high sampling frequency, and has certain adaptability to CT saturation and over excitation.

  • Transfer Learning Based Equivalent Magnetization Hysteresis Recognition Algorithm for Transformer Protection
    2019 IEEE 8th International Conference on Advanced Power System Automation and Protection (APAP), 2019
    Co-Authors: Wang Xiaopeng, Li Zongbo, Zaibin Jiao
    Abstract:

    Power Transformer is a key equipment of power system, and Transformer Protection is still an important research hotspot for the safe operation of the electric power system. Kinds of transform Protection algorithms have been proposed including many artificial intelligence (AI) algorithms. But the requirement of big data limits the generalization of AI algorithms. Different types of ferromagnetic material have the same shape of magnetization hysteresis which is an effective indicator for Transformer Protection. We propose transfer learning based equivalent magnetization hysteresis recognition algorithm for Transformer Protection which use little trial/real data with simulation data to solve the few-shot problem. In our experiments, we validate that the proposed algorithm can reach an improved accuracy compared with other two mentioned in the article.

  • A Novel Transformer Protection Scheme Based on Equivalent Excitation Impedance Characteristics
    2019 IEEE 8th International Conference on Advanced Power System Automation and Protection (APAP), 2019
    Co-Authors: He Xiao, Baofeng Zuo, Zaibin Jiao
    Abstract:

    A new power Transformer Protection scheme based on equivalent excitation impedance is proposed to improve the performance of Transformer Protection. Firstly, the equivalent excitation impedance is defined and analyzed. Analysis of characteristics of Transformer equivalent excitation impedance shows that the equivalent excitation impedance fluctuates sharply in a power frequency period when inrush current occurs in Transformer; when internal faults occur, the equivalent excitation impedance drops to a lower level and the fluctuation is small; when normal operation or external faults occur, the equivalent excitation impedance is large and the fluctuation is small. Therefore the Transformer Protection scheme is constructed using the mean square error and mean of the equivalent excitation impedance, which is calculated by the half-wave Fourier algorithm. PSCAD simulation results verify the effectiveness of the proposed scheme. Without obtaining internal parameters of the Transformer, the proposed scheme can discriminate inrush current from internal faults fast and accurately.

Qin Jian - One of the best experts on this subject based on the ideXlab platform.

Wang Zeng - One of the best experts on this subject based on the ideXlab platform.

Wang Zengping - One of the best experts on this subject based on the ideXlab platform.

  • Application of Morphological Gradient with Adaptive Weighting in Transformer Protection
    Automation of electric power systems, 2006
    Co-Authors: Wang Zengping
    Abstract:

    On the basis of basic morphological transforms and their combined modes,transient current signals can be extracted by use of morphological gradient with adaptive weighting.Meanwhile various kinds of additive noises are effectively suppressed by adaptive approach.Based on the different characteristics of spectrum analysis of extracted transients between the short circuit current and the inrush current,a new method of Transformer Protection is proposed.This method can avoid the symmetrical inrush current and non-periodic components can he sufficiently depressed.The results of dynamic simulation verify the feasibility of the proposed method.

  • Study on the Improved Transformer Protection Scheme Based on The OCT
    2005 2006 PES TD, 1
    Co-Authors: Xu Yan, Liu Qing, Wang Zengping
    Abstract:

    This paper presents a new scheme for Transformer differential Protection based on the OCT. The scheme can operate reliably when internal faults occurred and do not operate in the condition of external faults, inrush and overexcitation. This scheme combines harmonic restraint and blocking methods with dc content blocking. In this paper, the digital signal processor (DSP) is applied to improve computation and render fast Protection feasible. The novel Transformer Protection system interface construction, hardware structure, software algorithm are discussed. Performance analysis shows its has distinguish advantages over the traditional Transformer Protection

  • Research on a novel digital Transformer Protection method based on the OCT
    2004 International Conference on Power System Technology 2004. PowerCon 2004., 1
    Co-Authors: Liu Qing, Xu Yan, Wang Zengping, Jiao Yan-jun
    Abstract:

    This paper describes a new approach for Transformer differential Protection based on OCT that ensures security for external faults, inrush, and overexcitation conditions and provides dependability for internal faults. This approach combines harmonic restraint and blocking methods with DC content blocking. In this paper, the digital signal processor (DSP) is applied to improve computation and render fast Protection feasible. The novel Transformer Protection system interface construction, hardware structure, software algorithm are discussed. Performance analysis shows its has distinguish advantages over the traditional Transformer Protection.