Power Transformer Differential Protection Research Articles

A Novel Approach for Diagnosing Transformer Internal Defects and Inrush Current Based on 1DCNN and LSTM Deep Learning

In power systems, power transformer (Pt) protection plays a vital role in ensuring that customers have a reliable power supply. Correctly recognizing inrush currents from internal defects and preventing differential relay malfunctions are two of biggest challenges facing the differential protection of power transformers. Although previous approaches suggested to overcome these issues have promising outcomes, increasing the accuracy and reducing the execution time and complexity of transformer differential relays are still interesting topics for researchers. Accordingly, a new fault diagnostic method based on wavelet transform (WT) and deep learning is introduced in paper. In the proposed approach, Discrete WT is used to extract the features of differential currents, and combined one-dimensional convolutional neural networks and long short-term memory (1DCNN-LSTM)) is applied for classify internal faults from other abnormal events. High accuracy, no need for any thresholds or transformer parameters and fast fault detection are the main advantages of the proposed approach. The simulation results for a 132/11 kV, 63 MVA power transformer approved the proposed method for its ability to accurately differentiate between inrush currents and internal defects after 5 ms, as well as its accuracy for abnormal event classification of about 99.4%.

A power transformer differential protection method based on variational mode decomposition and CNN‐BiLSTM techniques

AbstractPower transformers play a critical role in the performance of power systems. This equipment is costly due to significant copper and iron prices and manufacturing costs. Therefore, maintenance and protection of such equipment is essential. Despite its robust performance, maloperation of differential protection (DP) in transformers may cause operational challenges to power system operators. The differential relay may operate incorrectly after the transformer energization leads to an inrush current (IC) and the relay identifies the event as an internal fault, and consequently issues the trip command. The other case of maloperation includes, but not limited to, a moment when the current transformer saturates due to an external fault. In this paper, a novel approach for DP is proposed, that is based on signal processing methods. In this paper, variational mode decomposition (VMD) and the deep neural network are implemented by using the convolutional neural network (CNN) and bi‐directional long short‐term memory (BiLSTM) models. The VMD decomposes differential current signal (DCS) to intrinsic mode functions with corresponding narrow‐band property frequency spectrums, which provides more detailed information about signal characteristics in different frequency bands. At the next stage, an effective feature for the BiLSTM is extracted by the CNN with the convolutional layers to classify events and proper discrimination. Extensive simulations on a 500 MVA transformer in MATLAB demonstrate the effectiveness of the proposed protection approach to differentiate ICs from internal and external faults with 99.8% accuracy in less than 1/8th of a power cycle.

Interoperability Challenges in Multivendor IEC 61850 Devices for Parallel Power Transformer Differential Protection

Interoperability of GOOSE messages is essential for the proper operation of protection schemes such as the parallel power transformer (PTRF) differential protection scheme, especially when using multivendor IEC 61850 devices. GOOSE messages allow for fast and reliable communication between intelligent electronic devices (IEDs) and are based on Ethernet communication. To ensure the interoperability of GOOSE messages between multivendor devices, adherence to the IEC 61850 standard specifications is crucial. The standard defines the format and content of GOOSE messages, including the data object model, data types, and communication protocols. Third-party testing and certification programs can also ensure compliance with the standard and help guarantee interoperability between different vendors. Device conformance with these standards does not ensure interoperability when devices from various manufacturers are utilized. Interoperability is necessary between the relevant devices from various vendors to provide system power stability and protection. If multivendor device interoperability is achieved, power utilities will be able to utilize multivendor devices in substations. The study investigates and provides comprehensive methods for achieving IEC 61850 standard-based interoperability problems in parallel with PTRF’s current differential protection schemes between IEDs (SEL-487E and MiCOM-P645) produced by different vendors under fault conditions. In a lab-scale environment with RTDS for real-time simulation in Hardware-in-the-Loop (HIL), the designed technique is simulated and tested.

Efficient practical method for differential protection of power transformer in the presence of the fault current limiters

AbstractThe algorithms of the present generation of practical differential relays are based on two methods. The first method is based on the ratio of the harmonic content of the differential current, and the second one is based on the length of the time interval between the zero‐crossing points of the differential current, called the gap‐detection method. However, these methods suffer from the installation of the fault current limiters (FCLs) in the power system and current transformer (CT) saturation phenomenon. This paper deals with a simple practical method for differential relays to secure their performance. In the suggested method, a classifying algorithm is used to categorize the input signal of the relay and then the best method of the present generation of differential relays is employed. By this simple decision, the method takes the advantage of harmonic‐based and gap‐detection methods, while avoiding their drawbacks. To prove the robustness of the suggested method, a test bench with a resistive solid‐state fault current limiter (SSFCL) is implemented and examined in different situations. The results validate the consistency and the accuracy of the modified technique not only in the absence and the presence of the FCL but in the case of CT saturation.

A Data-Aided Power Transformer Differential Protection Without Inrush Blocking Module

When a slightly faulty transformer closes without load, the current waveform presents the coexistence of inrush and fault current. At this time, the inrush blocking module will block the relay, which may delay the removal of the slight fault and lead to more serious faults. To address this problem, this paper proposes a data-aided power transformer differential protection without inrush blocking module. The key to eliminating the negative influence of inrush current is to extract the fundamental component from the non-inrush part of the current waveform, which corresponds to the unsaturation period of the transformer core. Firstly, a data-aided module, namely an Attention module embedded Fully Convolutional Network (A-FCN), is built to distinguish the inrush and non-inrush parts of the current waveform. Then, a physical model of the current waveform is built for the non-inrush part, and the fundamental component is extracted by the nonlinear least square (NLS) algorithm. The proposed method can avoid the block of differential protections when inrush current occurs, which improves the sensitivity and rapidity of the relay, especially in the case of a weak internal fault hidden in inrush current. Finally, simulation and experimental data verify the effectiveness and generalization of the proposed method.

Application of Wavelet Packet and S Transforms for Differential Protection of Power Transformer

The differential protection of power transformers appears to be more difficult than any type of protection for any other part or element in a power system. Such difficulties arise from the existence of the magnetizing inrush phenomenon. Therefore, it is necessary to recognize between inrush current and the current arise from internal faults. In this paper, two approaches based on wavelet packet transform (WPT) and S-transform (ST) are applied to recognize different types of currents following in the transformer. In WPT approach, the selection of optimal mother wavelet and the optimal number of resolution is carried out using minimum description length (MDL) criteria before taking the decision for the extraction features from the WPT tree. In ST approach,the spectral energy index and the standard deviation (STD) are calculated from the S-matrix obtained by discrete S-transform. The two approaches are tested for generating a trip signal and disconnecting the transformer supply experimentally using 1KVA, 220/110V, 50Hz, ∆ / Y threephase transformer. The experimental results show that the trip signal is initiated faster in WPT approach while the transformer is disconnected from the supply after a delay of 10-15msec in thetwo approaches due to computer interface and the relay circuit used.

An Approach to Performing Stability Analysis for Power Transformer Differential Protection: A Case Study

Differential protection normally detects short circuits and ground faults in the windings of a power transformer and its terminals. Inter-turn faults refer to flashovers among the electrodes that arise only in a similar type of physical winding. Inter-turn faults can be examined when the adequate sum of turns is served as short-circuited. In electrical protection, it is difficult to detect inter-turn faults. An inter-turn fault of small magnitude is based on the limited number of turns that resultantly provide a large quantity of current. Due to this reason, protection that comes from the differential scenario possesses a higher degree of sensitivity without causing unwanted operations during external faults. In this paper, a protection-based stability method is proposed whereby external voltages are applied at the low-voltage (LV) side of the transformer while keeping the high-voltage (HV) side short-circuited. This was conducted using a three-phase power transformer (rating: 100 MVA, 380 kV/13.8 kV) at SWCC Shoaiba Power Plant, Saudi Arabia. In this work, differential protection (87T) and high-impedance differential protection for HV-restricted earth faults (REFs) were verified by creating In-Zone and Out-Zone fault conditions to ensure current transformer (CT) circuits and tripping logic. All of the IEDs, protection, and control schemes involved were designed by ABB. This method verifies protection stability for power transformers by implementing differential protection (87T) and high-impedance restricted earth fault (64HV) schemes through creating In-Zone and Out-Zone fault conditions.

A new high-frequency-based method for the very fast differential protection of power transformers

A novel algorithm based on Teager energy operator (TEO) and hidden Markov model (HMM) is presented for the transformer differential protection. After detecting any increase in the amplitude of the transformer differential currents, it is needed to know if the over-current is because of an internal fault or an inrush phenomenon. In this paper, a combination of TEO and HMM is used to discriminate between the magnetizing inrush currents and the internal fault currents. TEO is used to extract high frequency components of the signal and present them as a curve, named as Teager output curve (TOC). Then TOC is used as the input for HMM. First, the HMM training process is implemented by an adequate number of the train signals and then, the unknown signals are identified by the testing process. Fault type identification is also performed by the use of TOC. TOC has a separated region for each of the three phases. TEO of the zero-sequence signal has a peak for the grounded and no peak for the un-grounded faults. Train and test signals are generated by the simulated system in PSCAD/EMTDC. Results by means of the simulated and experimental data show the robustness of the proposed algorithm.

Improvement of power transformer differential protection through detection and exploitation of the negative sequence currents

Introduction. Power transformers are the most important and the most expensive equipment used in transport and distribution of electrical energy. Their failure results in huge economic losses. Despite the great advances in the design of power equipment in recent years, the feeble link in the chain remains the insulation weakness of coil turns of the power transformer. The novelty of the proposed research consists in the development of a new procedure for diagnosing and localizing the occurrence of turn to turn short-circuits in the windings of three-phase power transformer. The main problems of the current differential relay are short circuits of one or more turns of a transformer winding. Hence a new approach using' the amplitude comparison between the negative sequence currents' is developed and a digital discriminator internal / external fault is applied to discriminate turn to turn faults among the other ones. The proposed procedure is based on the exploitation of the negative sequence currents. The purpose of using this new procedure is to identify small faults inside power transformer coils and to distinguish inner faults from the outer faults by using an ameliorate circuit. The method used in this paper is a novel algorithm which based on the comparison between the negative sequence current amplitudes and to calculate the corresponding phase angle shifts. The performance of the proposed procedure has been confirmed by MATLAB/Simulink environment. The results of simulation reveal the efficiency of the suggested procedure, and indicate that this procedure can provide fast and sensitive approach for detecting low level turn-to-turn faults.

An intelligent differential protection of power transformer based on artificial neural network

This paper describes the application of artificial neural network (ANN) techniques for protecting small power transformer 2 kVA (Terco type). ANN network trained according to the primary and secondary currents data under NN tool, this network performs as a function of differential protection relay. Symmetrical and unsymmetrical faults are analyzed using Matlab environment. ANN network senses the difference in the internal current of both transformer sides and sending a trip to the circuit breaker (CB) at moment of fault occurrence. All the voltages and the currents waveforms affected with the fault and the response time increased according to this technique. Finally, the trip signal and the quick disconnect time were improved according to ANN technique.

Overcurrent and Differential Protections for Power Substations Using Three-Winding Transformer

This paper presents a method to determine parameters of overcurrent and differential protections for power substations using three-winding power transformers. Active current threshold and time and working area are shown in this paper to help to calculate and set above relaying protections. An experimental model depicted a relaying system for a power substation using two three-winding power transformers is built to serve education training. It has a complete system structure of relaying protection, including a Arduino Mega 2560 processor, measuring system emulated by variable resistors, real time module and SD card module to record fault events, relays to represent on/off states of circuit breakers. Parameters of relaying protections can be adjusted in the processor to customize the its operation of system and make a visual view about its responses in real working process of power substations. Results received from the model showed the accurate setting method and its meaning that help to verify theory and make clear about relaying protections in education training. Keywords: Overcurrent protection, differential protection for power transformer, relaying protection for power transformer, setting parameters for relaying protection, active current threshold, working time.

Presenting an Adaptive Restraint Method to Improve Performance of Ground Differential Protection of Power Transformer

The ground differential (GD) relay is used to detect internal ground faults on the power transformer windings and terminals. In fact, this relay is employed as a complement to the phase differential (PD) relay. However, its stability is affected by magnetic saturation in current transformers (CTs) cores so that the spurious differential current caused by CT saturation may lead to the relay malfunction. In this paper, by modifying the restraining current definition in a conventional method, an adaptive restrain method is proposed. To evaluate the proposed method performance compared with conventional method, a real 230/63 kV power transformer under a large number of internal fault, external fault and in rush current cases are simulated in PSCAD/EMTDC environment. It is worth noting that Jiles-Atherton (JA) model is utilized to simulate CTs. MATLAB software is used to implement and analyze these methods using obtained simulation. Obtained results show that the proposed method is quite superior to the conventional method, despite its simplicity.

Differential Protection Algorithm Founded on Kalman Filter-Based Phase Tracking

Owing to the large magnitude of the inrush currents, the functionality of differential protection of power transformer may be threatened in correct discrimination between inrush and internal faults. This article enhances the functionality of differential protection through a computationally efficient method that utilizes the phase angle current signals of the current transformers (CTs). The proposed discrimination criterion (PDC) tracks the fundamental phase angle of the current signals of the CTs. While during an internal fault, the phase angles of both CTs are almost constant and in phase, during the external fault and inrush currents, the phase angles of both CTs have notable distance. On this ground, this article employs a developed Kalman filter (KF)-based phase angle estimator to measure the fundamental phase angles of the current signals of the CTs. Afterward, PDC is introduced that measures the distance between the estimated phase angles of the CT’s currents. Evaluating the effectiveness of the PDC with several simulated and experimental recorded current signals reveals the PDC is able to detect internal faults even in the presence of CT saturation and also to deal with inrush and external fault currents.

A Sub-Cycle phase angle distance measure algorithm for power transformer differential protection

Power transformer differential protection may confront mal-functioning in authentic discrimination between inrush and internal faults. To tackle the latter mal-functioning, a new two-stages algorithm based on phase content of the current signal of the current transformers (CTs) is put forward. The proposed algorithm is designed based on the fact that the fundamental phase angle of a fault signal ideally remains constant during the fault. However, during inrush cases, the phase angle varies. Also, during the internal fault, the phase angles of the current signals of CTs are in phase while during the external fault, the phase angles of the current signals of CTs are 180° out of phase. In the first stage, the proposed algorithm calculates the fundamental phase angles of the current signals of the CTs using sub-cycle modified recursive least squares (MRLS). Afterward, normalized mean residue (NMR) is employed to measure distance between the estimated phase angles of the CT’s currents. MRLS and NMR algorithms require limited samples (i.e. 10 and 5 samples respectively) for executing their calculations. Performance evaluation with simulated and experimental recorded current signals shows the ability of the proposed method in discrimination of the internal faults from inrush and external fault currents.

Equivalent statistics based inrush identification method for differential protection of power transformer

Second harmonic restraint as a traditional inrush identification method is widely used in power transformer protection. However, it may fail in the case of inrush current with a high remanence in transformer and may restrain the protection relay for an unnecessarily long time in the cases such as an internal fault during current transformer saturation or an internal fault contaminated by inrush current. Therefore, this paper proposes an equivalent statistics-based inrush identification method to improve the reliability and sensitivity of transformer differential protection. Firstly, the waveform of differential current is intercepted and reshaped so that it can be abstractly seen as a probability density function. Then, the equivalent statistics are used to quantify the features of the function’s waveform. On this basis, a group of criteria is presented to discriminate disturbances from internal fault. A large number of simulation studies and experimental tests have been conducted to verify the effectiveness of the proposed method, and the results indicate that it outperforms the second harmonic restraint method.

Artificial Neural Network Applied to Differential Protection of Power Transformers

Artificial Neural Network Applied to Differential Protection of Power Transformers

A new fast method for improvement of power transformer differential protection based on discrete energy separation algorithm

Differential protection is one of the most widely used protections in power transformers. The challenges associated with this protection are distinguishing the inrush current, overexcitation, and external fault conditions from internal and winding faults. So far, various methods have been proposed to prevent differential protection from mal-operation, which are not necessarily simple to implement and do not guarantee the proper performance in all scenarios. This paper proposes a new method based on the discrete energy separation algorithm to improve differential protection. The proposed method consists of two sections. The first section detects internal disturbances from external faults, and the other distinguishes the inrush current and overexcitation from internal and winding faults. One of the advantages of the proposed method is the parallel employment of these two sections in the logic of the method, which reduces the detection time. Moreover, other advantages such as the fast detection speed (1.5 ms), simple implementation, and low computational burden make it possible to implement the method in real-time. The simulation results show the appropriate efficiency of the proposed method in detecting all disturbances even in noisy conditions and saturation of current transformers.

Improving the Differential Protection of Power Transformers Based on Clarke Transform and Fuzzy Systems

Improving the Differential Protection of Power Transformers Based on Clarke Transform and Fuzzy Systems

A Novel Signal Localized Convolution Neural Network for Power Transformer Differential Protection

This paper presents a novel signal localized convolution neural network (SLCNN) for the power transformer differential protection. The distinct signal localization is performed with the convolution process sequentially on the frequency and time coefficients which are obtained from the wavelet decomposition of the differential current signal. The SLCNN is trained with a modified back-propagation algorithm according to SLCNNs architecture. Three power transformer test systems are considered for evaluation of the proposed SLCNN. The training patterns of each transformer are generated for various operating conditions. The SLCNN for each transformer is trained, validated and tested using its corresponding patterns. Then the performance of SLCNN is evaluated through confusion matrix analysis and is also compared with long short-term memory (LSTM) deep neural network, support vector machine (SVM), conventional back-propagation neural network (CBPNN) and conventional biased restraint second harmonic (CBSH) blocking method.

A power transformer differential protection based on support vector machine and wavelet transform

This paper presents a power transformer differential protection scheme based on support vector machines (SVM) combined with high-frequency features extracted with the real-time boundary stationary wavelet transform (RT-BSWT). SVM models are derived with synthetic data, considering a wide variety of events, such as inter-turn faults, external faults during CT saturation, and evolving external-to-internal faults. A comparative performance assessment is carried out considering accuracy and other reliability indices, as well as operating time, and good results were achieved. The simplicity of the presented SVM-based relay, without hard-to-derive parameters, built on the classical differential protection framework, highlights potential aspects towards real-life implementation.