RESUMO
Partial discharge (PD) fault diagnosis is of great importance for ensuring the safe and stable operation of power transformers. To address the issues of low accuracy in traditional PD fault diagnostic methods, this paper proposes a novel method for the power transformer PD fault diagnosis. It incorporates the approximate entropy (ApEn) of symplectic geometry mode decomposition (SGMD) into the optimized bidirectional long short-term memory (BILSTM) neural network. This method extracts dominant PD features employing SGMD and ApEn. Meanwhile, it improves the diagnostic accuracy with the optimized BILSTM by introducing the golden jackal optimization (GJO). Simulation studies evaluate the performance of FFT, EMD, VMD, and SGMD. The results show that SGMD-ApEn outperforms other methods in extracting dominant PD features. Experimental results verify the effectiveness and superiority of the proposed method by comparing different traditional methods. The proposed method improves PD fault recognition accuracy and provides a diagnostic rate of 98.6%, with lower noise sensitivity.
RESUMO
The lifetime of power transformers is closely related to the insulating oil performance. This latter can degrade according to overheating, electric arcs, low or high energy discharges, etc. Such degradation can lead to transformer failures or breakdowns. Early detection of these problems is one of the most important steps to avoid such failures. More efficient diagnostic systems, such as artificial intelligence techniques, are recommended to overcome the limitations of the classical methods. This work deals with diagnosing the power transformer insulating oil by analysis of dissolved gases using new techniques. For this, we have proposed intelligent techniques based on Multilayer artificial neural networks (ANN). Thus, a multi-layer ANN-based model for fault detection is presented. To improve its classification rate, this one was optimized by a meta-heuristic technique as the particle swarm optimization (PSO) technique. Optimized ANNs have never been used in transformer insulating oil diagnostics so far. The robustness and effectiveness of the proposed model is demonstrated, and high accuracy is obtained.
RESUMO
Power transformer is widely used in the power system with the rapid development of the power converters connected to the grid. When a transformer operates under DC bias conditions, its iron core loss increases significantly, causing local overheating and threatening the proper operation of the transformer. However, there are persistent difficulties in accurately assessing the core loss when the induction waveform is influenced by a DC bias. This paper first proposes improvements to the J-A and Preisach models to evaluate the core loss of the iron core under DC bias. Additionally, we incorporate the hysteresis models into the finite element method (FEM) by modifying the fundamental constitutive equations in the FEM model in order to perform a precise core loss/distribution calculation. To verify the accuracy of prediction, a transformer prototype with a laminated core is developed. The improved J-A-FEM and Preisach-FEM models were directly compared in terms of calculation accuracy, numerical implementation, and computational burden.
RESUMO
Dissolved gas analysis (DGA) in transformer oil, which analyzes its gas content, is valuable for promptly detecting potential faults in oil-immersed transformers. Given the limitations of traditional transformer fault diagnostic methods, such as insufficient gas characteristic components and a high misjudgment rate for transformer faults, this study proposes a transformer fault diagnosis model based on multi-scale approximate entropy and optimized convolutional neural networks (CNNs). This study introduces an improved sparrow search algorithm (ISSA) for optimizing CNN parameters, establishing the ISSA-CNN transformer fault diagnosis model. The dissolved gas components in the transformer oil are analyzed, and the multi-scale approximate entropy of the gas content under different fault modes is calculated. The computed entropy values are then used as feature parameters for the ISSA-CNN model to derive diagnostic results. Experimental data analysis demonstrates that multi-scale approximate entropy effectively characterizes the dissolved gas components in the transformer oil, significantly improving the diagnostic efficiency. Comparative analysis with BPNN, ELM, and CNNs validates the effectiveness and superiority of the proposed ISSA-CNN diagnostic model across various evaluation metrics.
RESUMO
Accurate interpretation of dissolved gas analysis (DGA) measurements for power transformers is essential to ensure overall power system reliability. Various DGA interpretation techniques have been proposed in the literature, including the Doernenburg Ratio Method (DRM), Roger Ratio Method (RRM), IEC Ratio Method (IRM), Duval Triangle Method (DTM), and Duval Pentagon Method (DPM). While these techniques are well documented and widely used by industry, they may lead to different conclusions for the same oil sample. Additionally, the ratio-based methods may result in an out-of-code condition if any of the used gases fall outside the specified limits. Incorrect interpretation of DGA measurements can lead to mismanagement and may lead to catastrophic consequences for operating power transformers. This paper presents a new interpretation technique for DGA aimed at improving its accuracy and consistency. The proposed multi-method approach employs s scoring index and random forest machine learning principles to integrate existing interpretation methods into one comprehensive technique. The robustness of the proposed method is assessed using DGA data collected from several transformers under various health conditions. Results indicate that the proposed multi-method, based on the scoring index and random forest; offers greater accuracy and consistency than individual conventional interpretation methods alone. Furthermore, the multi-method based on random forest demonstrated higher accuracy than employing the scoring index only.
RESUMO
Transformer performance and efficiency can be enhanced by effectively address the properties of its insulation system. The power transformer insulation system weakens as a result of operational thermal stresses brought on by dynamic loading and shifting environmental patterns. Winding hot spot temperature is a crucial metric that must be maintained below the prescribed limit while power transformers are operating so as to maintained power system reliability. This is due to the fact that, among other variables, the time-dependent aging effect of insulation depends on transitions in hot spot temperatures. Due to the non-linear nature of the conventional mathematical models used to determine these temperatures, and complexity of thermal phenomena, investigations still need to be exercised to fully understand the variables that associate with hot spot temperature computation with minimum error. This paper explores the possibilities of enhancing top oil and hot spot temperature estimation accuracy through the use of an adaptive neuro-fuzzy inference (ANFIS) technique. The paper presents an adaptive neuro fuzzy model to approximate the hot spot temperature of a mineral oil-filled power transformer based on loading, and established top oil temperature. Initially, a sub-ANFIS top oil temperature estimation model based on loading and ambient temperature as inputs is established. Using a hybrid optimization technique, the ANFIS membership functions were fine-tuned throughout the training process to reduce the difference between the actual and anticipated outcomes. The correctness and reliability of the created adaptive neural fuzzy model have been verified using real-world field data from a 60/90MVA, 132 kV power transformers under dynamic operating regimes. The ANFIS model results were validated against field measured values and literature-based electrical-thermal analogous models, establishing a precise input-output correlation. The developed ANFIS model achieves the highest coefficient of determination for both TOT and HST (0.98 and 0.96) and the lowest mean square error (7.8 and 10.3) among the compared thermal models. Correct determination of HST can help asset managers in thermal analysis trending of the in-service transformers, helping them to make proper loading recommendations for safeguarding the asset.
RESUMO
This paper presents the finite element method (FEM) simulation of the propagation, measurement and evaluation of the time of arrival (TOA) of the acoustic wave created by a partial discharge (PD) in a transformer model using COMSOL multiphysics software. This model is a flat tank filled with an insulating liquid. In addition, 8 acoustic probes placed on one of the outer faces of the tank provide information on acoustic pressure levels for specific values of angles of incidence of the acoustic signal. The addition of signal transmission zones for each of the probes makes it possible to define precise paths for the acoustic signal, enabling the TOA of the acoustic wave to be evaluated for each path. The results of this study show that for angular values less than 40°, the error on the TOA is practically zero, but for values greater than 40° this error increases exponentially with the angle. This means that for an angle of 40.41° the error is 6µs, corresponding to 1.7%, and for an angle of 71.70° the error is 332µs, corresponding to 40.3%. This highlights the optimal nature of the choice of sensor position for locating partial discharge.
RESUMO
The introduction of artificial intelligence (AI) to ultra-high-frequency (UHF) partial discharge (PD) monitoring systems in power transformers for the localization of PD sources can help create a robust and reliable system with high usability and precision. However, training the AI with experimental data or data from electromagnetic simulation is costly and time-consuming. Furthermore, electromagnetic simulations often calculate more data than needed, whereas, for localization, the signal time-of-flight information is the most important. A tailored pathfinding algorithm can bypass the time-consuming and computationally expensive process of simulating or collecting data from experiments and be used to create the necessary training data for an AI-based monitoring system of partial discharges in power transformers. In this contribution, Dijkstra's algorithm is used with additional line-of-sight propagation algorithms to determine the paths of the electromagnetic waves generated by PD sources in a three-dimensional (3D) computer-aided design (CAD) model of a 300 MVA power transformer. The time-of-flight information is compared with results from experiments and electromagnetic simulations, and it is found that the algorithm maintains accuracy similar to that of the electromagnetic simulation software, with some under/overestimations in specific scenarios, while being much faster at calculations.
RESUMO
This paper presents an alternative approach to the Transformer Assessment Index (TAI) by proposing a relatively simple rating method called the Exploitation Perspective Index (EPI). The method provides two numerical indicators: the first reflects the overall technical condition of the particular unit, and the second shows the condition of the unit in the context of the entire fleet. The objective of the EPI method is to support the decision-making process regarding the technical condition assessment of each of the transformers in the target population, considering not only technical but also economic aspects of transformer maintenance. Application of the method is described step by step, including input data, parametrization of the weights, and interpretation of the output results it provides. The proposed method is evaluated by two representative use cases and compared with two other methods. As a result, EPI confirms its applicability, and it has already been successfully implemented by the electric power industry. EPI can be potentially freely adopted for any transformer fleet, as well as for the specific situation of the utility, by adjusting the relevant parameters.
RESUMO
The detection of On-Load Tap-Changer (OLTC) faults at an early stage plays a significant role in the maintenance of power transformers, which is the most strategic component of the power network substations. Among the OLTC fault detection methods, vibro-acoustic signal analysis is known as a performant approach with the ability to detect many faults of different types. Extracting the characteristic features from the measured vibro-acoustic signal envelopes is a promising approach to precisely diagnose OLTC faults. The present research work is focused on developing a methodology to detect, locate, and track changes in on-line monitored vibro-acoustic signal envelopes based on the main peaks extraction and Euclidean distance analysis. OLTC monitoring systems have been installed on power transformers in services which allowed the recording of a rich dataset of vibro-acoustic signal envelopes in real time. The proposed approach was applied on six different datasets and a detailed analysis is reported. The results demonstrate the capability of the proposed approach in recognizing, following, and localizing the faults that cause changes in the vibro-acoustic signal envelopes over time.
RESUMO
Mineral oil (MO) is the most popular insulating liquid that is used as an insulating and cooling medium in electrical power transformers. Indeed, for green energy and environmental protection requirements, many researchers introduced other oil types to study the various characteristics of alternative insulating oils using advanced diagnostic tools. In this regard, natural ester oil (NEO) can be considered an attractive substitute for MO. Although NEO has a high viscosity and high dielectric loss, it presents fire safety and environmental advantages over mineral oil. Therefore, the retrofilling of aged MO with fresh NEO is highly recommended for power transformers from an environmental viewpoint. In this study, two accelerated aging processes were applied to MO for 6 and 12 days to simulate MO in service for 6 and 12 years. Moreover, these aged oils were mixed with 80% and 90% fresh NEO. The dielectric strength, relative permittivity, and dissipation factor were sensed using a LCR meter and oil tester devices for all prepared samples to support the condition assessment performance of the oil mixtures. In addition, the electric field distribution was analyzed for a power transformer using the oil mixtures. Furthermore, the dynamic viscosity was measured for all insulating oil samples at different temperatures. From the obtained results, the sample obtained by mixing 90% natural ester oil with 10% mineral oil aged for 6 days is considered superior and achieves an improvement in dielectric strength and relative permittivity by approximately 43% and 48%, respectively, compared to fresh mineral oil. However, the dissipation factor was increased by approximately 20% but was at an acceptable limit. On the other hand, for the same oil sample, due to the higher molecular weight of the NEO, the viscosities of all mixtures were at a higher level than the mineral oil.
RESUMO
Fast and accurate fault diagnosis is crucial to transformer safety and cost-effectiveness. Recently, vibration analysis for transformer fault diagnosis is attracting increasing attention due to its ease of implementation and low cost, while the complex operating environment and loads of transformers also pose challenges. This study proposed a novel deep-learning-enabled method for fault diagnosis of dry-type transformers using vibration signals. An experimental setup is designed to simulate different faults and collect the corresponding vibration signals. To find out the fault information hidden in the vibration signals, the continuous wavelet transform (CWT) is applied for feature extraction, which can convert vibration signals to red-green-blue (RGB) images with the time-frequency relationship. Then, an improved convolutional neural network (CNN) model is proposed to complete the image recognition task of transformer fault diagnosis. Finally, the proposed CNN model is trained and tested with the collected data, and its optimal structure and hyperparameters are determined. The results show that the proposed intelligent diagnosis method achieves an overall accuracy of 99.95%, which is superior to other compared machine learning methods.
RESUMO
The article presents in detail the construction of a low-cost, portable online PD monitoring system based on the acoustic emission (AE) technique. A highly sensitive piezoelectric transducer was used as the PD detector, whose frequency response characteristics were optimized to the frequency of AE waves generated by discharges in oil-paper insulation. The popular and inexpensive Teensy 3.2 development board featuring a 32-bit MK20DX256 microcontroller with the ARM Cortex-M4 core was used to count the AE pulses. The advantage of the system is its small dimensions and weight, easy and quick installation on the transformer tank, storage of measurement data on a memory card, battery power supply, and immediate readiness for operation without the need to configure. This system may contribute to promoting the idea of short-term (several days or weeks) PD monitoring, especially in developing countries where, with the dynamically growing demand for electricity, the need for inexpensive transformer diagnostics systems is also increasing. Another area of application is medium-power transformers (up to 100 MVA), where temporary PD monitoring using complex measurement systems requiring additional infrastructure (e.g., control cabinet, cable ducts for power supply, and data transmission) and qualified staff is economically unjustified.
RESUMO
A voiceprint signal as a non-contact test medium has a broad application prospect in power-transformer operation condition monitoring. Due to the high imbalance in the number of fault samples, when training the classification model, the classifier is prone to bias to the fault category with a large number of samples, resulting in poor prediction performance of other fault samples, and affecting the generalization performance of the classification system. To solve this problem, a method of power-transformer fault voiceprint signal diagnosis based on Mixup data enhancement and a convolution neural network (CNN) is proposed. First, the parallel Mel filter is used to reduce the dimension of the fault voiceprint signal to obtain the Mel time spectrum. Then, the Mixup data enhancement algorithm is used to reorganize the generated small number of samples, effectively expanding the number of samples. Finally, CNN is used to classify and identify the transformer fault types. The diagnosis accuracy of this method for a typical unbalanced fault of a power transformer can reach 99%, which is superior to other similar algorithms. The results show that this method can effectively improve the generalization ability of the model and has good classification performance.
RESUMO
Despite major progress in the design of power transformers, the Achilles' heel remains the insulation system, which is affected by various parameters including moisture, heat, and vibrations. These important machines require extreme reliability to guarantee electricity distribution to end users. In this contribution, a fiber optic sensor (FOS), consisting of a Fabry-Perot cavity made up of two identical fiber Bragg gratings (FBGs), is proposed, to monitor the temperature and vibration of power transformer windings. A phase shifted gratings recoated sensor, with multilayers of polyimide films, is used to monitor the moisture content in oil. The feasibility is investigated using an experimental laboratory transformer model, especially fabricated for this application. The moisture contents are well correlated with those measured by a Karl Fisher titrator, while the values of temperature compare well with those recorded from thermocouples. It is also shown that the sensors can be used to concurrently detect vibration, as assessed by sensitivity to the loading current. The possibility of dynamically measuring humidity, vibrations, and temperatures right next to the winding, appears to be a new insight that was previously unavailable. This approach, with its triple ability, can help to reduce the required number of sensors and therefore simplify the wiring layout.
RESUMO
The interest in developing new fluids that can be used as dielectric liquids for transformers has driven the research on dielectric nanofluids in the last years. A number of authors have reported promising results on the electrical and thermal properties of dielectric nanofluids. Less attention has been paid to the interaction of these fluids with the cellulose materials that constitute the solid insulation of the transformers. In the present study, the dielectric strength of cellulose insulation is investigated, comparing its behavior when it is impregnated with transformer mineral oil and when it is impregnated with a dielectric nanofluid. The study includes the analysis of the AC breakdown voltage and the impulse breakdown voltage of the samples. Large improvements were observed on the AC breakdown voltages of the specimens impregnated with nanofluids, while the enhancements were lower in the case of the impulse tests. The reasons for the increase in AC breakdown voltage were investigated, considering the dielectric properties of the nanofluids used to impregnate the samples of cellulose. The analysis was completed with a finite element study that revealed the effect of the nanoparticles on the electric field distribution within the test cell, and its role in the observed enhancement.
RESUMO
Acetylene detection plays an important role in fault diagnosis of power transformers. However, the available dissolved gas analysis (DGA) techniques have always relied on bulky instruments and are time-consuming. Herein, a high-performance acetylene sensor was fabricated on a microhotplate chip using In2O3 as the sensing material. To achieve high sensing response to acetylene, Pd-Ag core-shell nanoparticles were synthesized and used as catalysts. The transmission electron microscopy (TEM) image clearly shows that the Ag shell is deposited on one face of the cubic Pd nanoseeds. By loading the Pd-Ag bimetallic catalyst onto the surface of In2O3 sensing material, the acetylene sensor has been fabricated for acetylene detection. Due to the high catalytic performance of Pd-Ag bimetallic nanoparticles, the microhotplate sensor has a high response to acetylene gas, with a limit of detection (LOD) of 10 ppb. In addition to high sensitivity, the fabricated microhotplate sensor exhibits satisfactory selectivity, good repeatability, and fast response to acetylene. The high performance of the microhotplate sensor for acetylene gas indicates the application potential of trace acetylene detection in power transformer fault diagnosis.
RESUMO
In order to accurately diagnose the fault type of power transformer, this paper proposes a transformer fault diagnosis method based on the combination of time-shift multiscale bubble entropy (TSMBE) and stochastic configuration network (SCN). Firstly, bubble entropy is introduced to overcome the shortcomings of traditional entropy models that rely too heavily on hyperparameters. Secondly, on the basis of bubble entropy, a tool for measuring signal complexity, TSMBE, is proposed. Then, the TSMBE of the transformer vibration signal is extracted as a fault feature. Finally, the fault feature is inputted into the stochastic configuration network model to achieve an accurate identification of different transformer state signals. The proposed method was applied to real power transformer fault cases, and the research results showed that TSMBE-SCN achieved 99.01%, 99.1%, 99.11%, 99.11%, 99.14% and 99.02% of the diagnostic rates under different folding numbers, respectively, compared with conventional diagnostic models MBE-SCN, TSMSE-SCN, MSE-SCN, TSMDE-SCN and MDE-SCN. This comparison shows that TSMBE-SCN has a strong competitive advantage, which verifies that the proposed method has a good diagnostic effect. This study provides a new method for power transformer fault diagnosis, which has good reference value.
RESUMO
Power fault monitoring based on acoustic waves has gained a great deal of attention in industry. Existing methods for fault diagnosis typically collect sound signals on site and transmit them to a back-end server for analysis, which may fail to provide a real-time response due to transmission packet loss and latency. However, the limited computing power of edge devices and the existing methods for feature extraction pose a significant challenge to performing diagnosis on the edge. In this paper, we propose a fast Lightweight Fault Diagnosis method for power transformers, referred to as LightFD, which integrates several technical components. Firstly, before feature extraction, we design an asymmetric Hamming-cosine window function to reduce signal spectrum leakage and ensure data integrity. Secondly, we design a multidimensional spatio-temporal feature extraction method to extract acoustic features. Finally, we design a parallel dual-layer, dual-channel lightweight neural network to realize the classification of different fault types on edge devices with limited computing power. Extensive simulation and experimental results show that the diagnostic precision and recall of LightFD reach 94.64% and 95.33%, which represent an improvement of 4% and 1.6% over the traditional SVM method, respectively.
Assuntos
Fontes de Energia Elétrica , Redes Neurais de Computação , Simulação por Computador , InteligênciaRESUMO
Checking the stable supply voltage of a power distribution transformer in operation is an important issue to prevent mechanical failure. The acoustic signal of the transformer contains sufficient information to analyze the transformer conditions. However, since transformers are often exposed to a variety of noise environments, acoustic signal-based methods should be designed to be robust against these various noises to provide high accuracy. In this study, we propose a method to classify the over-, normal-, and under-voltage levels supplied to the transformer using the acoustic signal of the transformer operating in various noise environments. The acoustic signal of the transformer was converted into a Mel Spectrogram (MS), and used to classify the voltage levels. The classification model was designed based on the U-Net encoder layers to extract and express the important features from the acoustic signal. The proposed approach was used for its robustness against both the known and unknown noise by using the noise rejection method with U-Net and the ensemble model with three datasets. In the experimental environments, the testbeds were constructed using an oil-immersed power distribution transformer with a capacity of 150 kVA. Based on the experimental results, we confirm that the proposed method can improve the classification accuracy of the voltage levels from 72 to 88 and to 94% (baseline to noise rejection and to noise rejection + ensemble), respectively, in various noisy environments.