Modeling transformers with internal incipient faults

In this study, a hyperbolic S-transform-based method is proposed to discriminate most important transient fault currents of transformers. First, the proposed method discriminates external faults from other disturbances. Then, the S-transform is applied to differential currents. An index is suggested by using absolute deviations of the S-matrix of differential currents to discriminate internal incipient faults in addition to inrush currents and internal faults. The relay issues an alarm signal in the case of the incipient fault but restrains during the magnetising inrush current. If an internal fault is recognised, the relay will issue a trip signal. To study the robustness of the suggested method, a program is developed in the MATLAB environment. The inputs of this program are differential current signals, derived from a system modelled by EMTP software. In order to simulate the internal incipient fault along with internal turn to turn and turn to earth faults, the transformer is modelled as 8×8 RL matrices, derived by using subroutine BCTRAN in EMTP. Also, differential currents are contaminated by noise and it is shown that the suggested method is not affected by noise and it can discriminate incipient faults, inrush currents, internal faults and external faults.

Transformer fault detection and diagnosis is becoming more important due to the restructuring of the electric power industry. In this era of deregulation, loading transformers to their optimum capacity is becoming normal practice, which in turn applies high stresses on the insulation of the transformers and increases the probability of occurrence of internal short circuit winding faults. Such faults can lead to catastrophic failure and hence cause outages. Utilities and other entities in the electric power business are therefore exploring ways of detecting these faults in transformers in the incipient stage. Terminal values, primary and secondary currents and voltages of the transformer convey information that can be used to detect internal transformer failures before developing a detection method. The behavior of these terminal values should be understood. In an effort to characterize the behavior of the terminal values of a transformer during internal short circuit and incipient faults, short circuit faults were staged on a 25 kVA, 7200 V/240 V/120 V two winding custom-built transformer. This paper discusses the results of the field experiments performed over a 19-month period. It presents time domain results of selected short circuit experiments. It also presents recordings of advance incipient-like behavior during the last set of experiments.

An advanced distance relay strategy for incipient fault detection and location in underground distribution systems

SUMMARY In this paper, the application of the hyperbolic S-transform is proposed for detecting internal incipient faults of transformers during the impulse test. This test is performed on the under consideration transformer and during this test, the input current and applied voltage are recorded. The S-transform is applied to the recorded input current. An index is proposed and computed considering absolute deviations of the S-matrix. Faulty and non-faulty windings are discriminated by using the suggested index. The data obtained from field tests of a 66 kV/25MVA interleaved transformer winding and computer simulations, are recorded. Then, these data are fed to the proposed method, and faulty and normal conditions are discriminated, accordingly. Also, a wavelet-based method is implemented in MATLAB environment and the proposed method is compared with the wavelet-based method. According to simulations and experimental results, the proposed method is superior to wavelet transform-based method. Copyright © 2012 John Wiley & Sons, Ltd.

This paper presents the characterization of transients resulting from faults in transformers using discrete wavelet transform (DWT). This characterization will aid in the development of an automatic detection method for internal incipient faults in the transformers. The detection method can provide information to predict failures ahead of time so that the necessary corrective actions are taken to prevent outages and reduce down times. The analyzed data are obtained from simulations and experiments for different normal and abnormal operating cases such as external faults, internal short circuit faults, magnetizing inrush, and internal incipient faults. The simulation method and experiment setup are discussed. The experiments and simulations are conducted on a single-phase transformer as an example case. The results of applying the DWT are discussed.

The incipient fault detection of a complex industrial process is a challenging problem for traditional dynamic detection methods. Traditional dynamic detection methods usually decouple the correlations among the variables and dynamic correlations simultaneously, which makes the two types of correlations mixed and may lead to performance deterioration in long-sequence dynamic detection. Some incipient faults may not change the amplitudes of process variables but change the long-sequence dynamic features. Based on the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$T^{2}$</tex-math> </inline-formula> statistic and matrix multiplication transformation ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$T^{2}$</tex-math> </inline-formula> S-MMT), traditional dynamic detection methods can detect many faults effectively. However, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$T^{2}$</tex-math> </inline-formula> S-MMT can not effectively detect some incipient faults due to the above two types of correlations mixed. In order to overcome the shortcomings of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$T^{2}$</tex-math> </inline-formula> S-MMT and improve the detection ability of some incipient faults, this paper proposes a fault detection method based on the dynamic k-nearest neighbor model and Dual Control Chart (DKNN-DCC), which can improve the incipient fault detection performance by using long-sequence dynamic detection. The proposed method is verified by the Tennessee Eastman (TE) process and the continuously stirred tank reactor (CSTR) process. The experimental results show the effectiveness of the proposed method in incipient fault detection compared with traditional dynamic detection methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper presents a novel incipient fault detection method, which directly mines the long-sequence dynamic abnormal information from the process variable and overcomes the problem of some abnormal information being submerged in the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$T^{2}$</tex-math> </inline-formula> statistic calculated based on the matrix multiplication transformation. The proposed method can detect incipient faults that are not easily detected by some traditional methods and can help operators find the abnormal and avoid more serious losses. The structure of the proposed method jumps out of the frameworks of traditional dynamic detection methods, which is feasible to apply to different stable industrial processes.

In this paper, a laboratory test setup designed to perform transformer insulation experiments at low voltage level is introduced. Monitoring the leakage current flowing through the insulation samples that are taken from an aged distribution transformer is the principle of the investigation. The electrode system utilized and the experimental procedure are described. The test results that highlight important aspects of the insulation behavior concerning incipient fault detection and diagnosis is addressed. The results help identify particular phenomena that might happen when an incipient fault initiates and taking them into account in the characterization of such faults to develop a detection method for the distribution transformer incipient fault.

Early detection of incipient faults is of vital importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is known that the performance of supervised learning approaches highly relies on the availability and quality of labeled training data. In Fault Detection and Diagnosis (FDD) applications, the lack of labeled incipient fault data has posed a major challenge to applying these supervised learning techniques to commercial buildings. To overcome this challenge, this paper proposes using Monte Carlo dropout (MC-dropout) to enhance the supervised learning pipeline, so that the resulting neural network is able to detect and diagnose unseen incipient fault examples. We also examine the proposed MC-dropout method on the RP-1043 dataset to demonstrate its effectiveness in indicating the most likely incipient fault types.

Dissolved gas analysis (DGA) is a well-known method for diagnosis of incipient faults in power transformers. Some traditional criteria of the dissolved gas analysis are published in standards and technical reports which are still in use in many electrical utilities around the world. This paper describes a hybrid algorithm using neural-fuzzy system for incipient fault detection in power transformers. In order to reach a higher degree of reliability with respect to each technique individually, the proposed method is based on the combined use of six standardized criteria. Six neural networks are trained based on randomly generated data considering the individual standards and the results are mixed to give the better results. The proposed method is tested using realistic data. The experiments results showed that the proposed algorithm is accurate, reliable and robust in identifying incipient faults in power transformers.

In chemical processes, there are both nonlinearity and slow dynamics among process variables. Meanwhile, at the beginning of faults, slight variation may not prompt the significant parametric changes. Traditional fault detection methods, based on mean and variation shifts, often fail to achieve satisfactory performance. To improve the detection of incipient quality-related faults, a novel orthonormal slow feature-based quality-related data decomposition network with Jensen-Shannon divergence (OSF-JS) fault detection method is proposed. The orthonormal subspace analysis (OSA) is embedded with Siamese to extract orthonormal slow features (OSFs) from decomposed subspaces. Enhancing the detection of incipient faults, JS divergence combined with a sliding window algorithm is introduced to construct statistics. The effectiveness of OSF-JS is validated for a wastewater treatment process and a real-world chemical process. Results show that the proposed OSF-JS method not only improves the fault detection rate (FDR) and reduces false alarm rate (FAR) but also identifies whether faults occur in the quality-related component.

The objective of this paper is to present the development and numerical testing of a robust fault detection and identification (FDI) system using artificial neural networks (ANNs), for incipient (slowly developing) faults occurring in process systems. The challenge in using ANNs in FDI systems arises because of one's desire to detect faults of varying severity, faults from noisy sensors, and multiple simultaneous faults. To address these issues, it becomes essential to have a learning algorithm that ensures quick convergence to a high level of accuracy. A recently developed accelerated learning algorithm, namely a form of an adaptive back propagation (ABP) algorithm, is used for this purpose. The ABP algorithm is used for the development of an FDI system for a process composed of a direct current motor, a centrifugal pump, and the associated piping system. Simulation studies indicate that the FDI system has significantly high sensitivity to incipient fault severity, while exhibiting insensitivity to sensor noise. For multiple simultaneous faults, the FDI system detects the fault with the predominant signature. The major limitation of the developed FDI system is encountered when it is subjected to simultaneous faults with similar signatures. During such faults, the inherent limitation of pattern-recognition-based FDI methodsmore » becomes apparent. Thus, alternate, more sophisticated FDI methods become necessary to address such problems. Even though the effectiveness of pattern-recognition-based FDI methods using ANNs has been demonstrated, further testing using real-world data is necessary.« less

Incipient faults would repeatedly occur in underground cables when cable insulations or splices are damaged and would eventually develop into a permanent fault. Due to the short duration of incipient faults, the conventional protection relays cannot detect this type of faults. The objective of this paper is to develop a robust incipient fault detection algorithm by using phase current. Based on morphological gradient wavelet (MGW), the proposed algorithm is to detect the fault-induced or operation-induced transients, and therefore identify the incipient faults according to the unique characteristics. It can be applied to detect both sub-cycle and multi-cycle incipient faults. The performance of the proposed algorithm is evaluated using data collected from PSCAD/EMTDC. In addition, to verify the applicability of the proposed algorithm, other disturbances caused by permanent fault, capacitor bank switching, load change, etc, are studied as well.

Detection of incipient (slowly developing) faults is crucial in automated maintenance problems where early detection of worn equipment is required. In this paper, a general framework for model-based fault detection and diagnosis of a class of incipient faults is developed. The changes in the system dynamics due to the fault are modeled as nonlinear functions of the state and input variables, while the time profile of the failure is assumed to be exponentially developing. An automated fault diagnosis architecture using nonlinear online approximators with an adaptation scheme is designed and analyzed. A simulation example of a simple nonlinear mass-spring system is used to illustrate the results.

This paper addresses the problem of incipient fault detection and isolation for a class of Lipschitz nonlinear systems with multiple sensor biases and explores further results of total measurable fault information residual (ToMFIR). Firstly, state and output transformations are introduced to transform the original system into two subsystems. Since the effects of system disturbances on the residuals are completely decoupled, the incipient faults in the second subsystem can be detected by constructing ToMFIR. Further, sliding-mode observers (SMOs) based fault isolation scheme is designed to guarantee the isolation of multiple sensor faults even if they occur at the same time, which is the main contribution of this paper. Finally, application results conducted on a CRH2 high-speed railway traction motor are given to illustrate the effectiveness of the proposed approach.

Voltage sags are often manifested as the permanent or incipient faults occurred in the power system because of equipment malfunctions or failures. The incipient faults which are originally self-cleaning faults may repeatedly occur and gradually develop to a permanent fault after its first occurrence. The incipient fault detection is considered as a crucial task in predictive maintenance for power equipment such as transformers, circuit breakers, and underground cables. This paper proposes a hybrid method for incipient faults detection and classification. The proposed method firstly adopts two extraction methods and two feature measures to obtain seven peculiar features from voltage waveforms of abnormal phases recorded by power quality monitors at substations in a transmission network. Then, a feature selection method and the support vector machine combined with particle swarm optimization are applied to classify various types of incipient faults. Test results show that the proposed method contributes relatively accurate classification of incipient faults and can be employed as a useful tool for condition monitoring of major power equipment in the transmission network.