Winding Type Recognition through Supervised Machine Learning using Frequency Response Analysis (FRA) Data

Frequency response analysis (FRA) is regarded as the most effective technique to detect mechanical faults of transformers. Over the years, FRA measurement data have been collected by utilities into transformer asset databases. The characteristic of FRA data is fundamentally determined by the transformer's equivalent electrical circuit, which consists of inductance and capacitance parameters that are windings' design and structure dependent. Different winding types tend to have different FRA characteristics, and a transformer's design information such as winding type, dimension etc. is often not known to the utility but critically important for asset management. This study reviews the state‐of‐the‐art transformer FRA databases and application of machine learning techniques in this field, and proposes to apply a support vector machine (SVM) model onto the FRA data to identify the winding type. The SVM model is first trained by FRA traces of transformers with known winding types, and after testing, the SVM model is then applied to FRA traces with unknown winding information. A set of data from the UK's National Grid FRA database, was used to demonstrate and verify the SVM model. All transformers used in this study are 400/275/13 kV transmission transformers, which were designed using four different winding types, namely multiple layer, plain disc, interleaved disc and single helical windings. The proposed method can successfully identify the correct winding type.

Power transformers are important assets in power grid. Winding deformation is one of main fault types of transformer internal failures. The accurate diagnosis of transformer winding deformation is significant and meaningful. In this study, an improved method of classifying winding deformation types is proposed. The polar plot is first plotted by using the amplitude and phase information of the measured frequency response analysis (FRA) traces, then the digital image processing technology is used to extract three image texture features from polar plot, and three support vector machines (SVMs) are independently trained by using the extracted texture features. As a result, a strong classifier is eventually obtained by combining the three trained SVMs, for fault type classification and recognition. The proposed method is verified on the experimental FRA data obtained from an actual model transformer, which demonstrates that the proposed method has more excellent performance compared with the traditional method based on the FRA trace and single SVM.

This paper presents various types of windings in a power transformer, their FEM methods, frequency response analysis etc. Frequency response analysis (FRA) standards are used in all places. In frequency response, one reference spectrum is first done and after fault is done, spectrum is compared with reference one. A 3-D model of a transformer is considered to show the field distribution, inductance and capacitance matrices, force analysis etc. The forces developed in a transformer winding has also been explained and transient case has been studied.

Frequency response analysis (FRA) is a well-known method to assess the mechanical integrity of the active parts of the power transformer. The measurement procedures of FRA are standardized as described in the IEEE and IEC standards. However, the interpretation of FRA results is far from reaching an accepted and definitive methodology as there is no reliable code available in the standard. As a contribution to this necessity, this paper presents an intelligent fault detection and classification algorithm using FRA results. The algorithm is based on a multilayer, feedforward, backpropagation artificial neural network (ANN). First, the adaptive frequency division algorithm is developed and various numerical indicators are used to quantify the differences between FRA traces and obtain feature sets for ANN. Finally, the classification model of ANN is developed to detect and classify different transformer conditions, i.e., healthy windings, healthy windings with saturated core, mechanical deformations, electrical faults, and reproducibility issues due to different test conditions. The database used in this study consists of FRA measurements from 80 power transformers of different designs, ratings, and different manufacturers. The results obtained give evidence of the effectiveness of the proposed classification model for power transformer fault diagnosis using FRA.

Interpreting results of a transformer frequency response analysis (FRA) is quite challenging. One of the common methods to summarize FRA data is to employ statistical indicators (SIs) over FRA spectra. However, SI-specific boundary conditions for various operational modes of transformers are left unexplored. The lack of such boundary conditions renders interpretation of SIs difficult and subjective. In this article, in an attempt to find data-driven boundary conditions, first the conventional measurement setup of FRA technique is modified to emulate interturn winding short-circuit. Then, the boundary conditions of various SIs for normal, suspicious, and critical operational modes of transformers under fault are obtained. Nevertheless, the price of moving subjective boundaries to their objective data-driven counterparts is paid in an intrinsic uncertainty introduced by the process of data collection per se. In order to capture and quantify this uncertainty, a novel solution inspired by bolstered error estimation used in pattern recognition is proposed. In particular, the proposed method allows reporting the level of confidence that an observed magnitude of SI belongs to a specific operational mode. Having this confidence level is also warranted from an operational perspective because it enables utility operators to enhance the decision-making process and estimate the severity of transformer faulty conditions.

According to statistics from the Global Burden of Cancer Study (Globocon) of the World Health Organization (WHO), cancer, particularly breast cancer, is a severe health issue in Indonesia with 68,858 new cases and 22,000 deaths recorded in 2020. Ultrasonography (USG) technology is acknowledged as one of the potentials to support early detection, which is vital in reducing mortality from breast cancer. This study focuses on classifying ultrasound images using the Support Vector Machine (SVM) algorithm, GLCM feature extraction, Min-Max normalization, and Mutual Information with SelectKBest Feature Selection. From several experiments using the SVM algorithm with various combinations of parameter values that have been set and different Tests, namely using a Train/Test Split with a proportion of 80/20 and K-Fold Cross Validation, it shows that the SVM algorithm is capable of classifying ultrasound images of breast cancer. into two categories (Benign Tumor and Malignant Tumor) with the same maximum accuracy of 79% after applying the SMOTE Balancing Data technique or without using the Balancing Data technique. As a result, the Support Vector Machine (SVM) algorithm has the potential to be an effective model for identifying breast cancer ultrasound images, both on data from the original set that has not been balanced and data from the set that has been balanced.

India is ranked 120th among 122 countries globally in WaterAid’s water quality index. Regular water quality monitoring is essential to determine which inland water bodies are experiencing depreciating water quality. Long-term trends have been obtained using satellite remote sensing, necessitating multiple image analysis. The computational burden of processing numerous satellite images can be reduced using Google Earth Engine’s (GEE) cloud computing capabilities. Thorough research was conducted to determine the global spatio-temporal and biochemical factors impacting surface water quality (WQ). The public availability of geospatial datasets and free access to cloud-based geo-computing platforms such as GEE are widely used for spatio-temporal mapping, global surface water monitoring, water quality parametric variation, and real-time forecasting. Many researchers have recently focused on improving data mining and machine learning algorithms to accurately deal with image classification and predictive problems for crop identification and monitoring. In the present study, we propose to define band spectral ratios, spectral band equations, and empirical models for water quality parameters. A few neural network models will be used to (i) query and pre-process satellite earth observations that coincide with the study area, (ii) extract the spectra, and (iii) use spectral band wavelength charts, time-series charts, spatial-distribution maps, and the development of an online dashboard application to visualize the results graphically upon using integrated Landsat (8,9), Sentinel-2A/B and PlanetScope satellite data for the pre-monsoon and post-monsoon seasons in 2023 in the pan-India region. MODIS-TERRA provides LST spatial-temporal monitoring. In this, we have assessed and compared the performance of CART, SVM, and RF ML algorithms. We found that RF outperforms CART and SVM algorithms in the GEE platform with PlanetScope data (80.71% overall accuracy (OA) with Kappa 0.89) and also with the integration of PlanetScope and Sentinel-2A/B data (OA = 85.53%, Kappa 0.91). But CART outperforms RF and SVM algorithms with Sentiel-2A/B data (OA = 81.59%, Kappa 0.85). The SAM technique, spectral feature fitting, continuum band removal, and other band-spectral ratio techniques are employed for quantitative hyperspectral data analysis. Specifically, the performance metrics of XGBoost and SGD for both Chl-a (R^2 = 0.818) and Turbidity (R^2 = 0.815) models exhibited robust accuracy. We have also developed a Google API-based JavaScript code that can be tested under complex coastal shores, challenging inundation and variable climatic conditions. Our method provides the end-to-end cloud computing workflow shown in this research, considering cost and computational efficiency for timely information delivery.Keywords: Classification and Regression Trees (CART), Chlorophyll-a (conc), Color dissolved organic matter (CDOM), Composite water management index (CWMI), Environmental Mapping and Analysis Program (EnMAP), Land Surface Temperature (LST), Machine Learning (ML), Random Forest (RF), Spectral Angle Mapper (SAM), Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), Total Suspended Solids (TSS), Water Quality (WQ), XGBoost (Extreme Gradient Boosting).

In this study, a data-driven fault diagnosis method was developed for solid oxide fuel cell (SOFC) systems. First, the complete experimental data was obtained following the design of the SOFC system experiments. Then, principal component analysis (PCA) was performed to reduce the dimensionality of the obtained experimental data. Finally, the fault diagnosis algorithms were designed by support vector machine (SVM) and BP neural network to identify and prevent the reformer carbon deposition and heat exchanger rupture faults, respectively. The research results show that both SVM and BP fault diagnosis algorithms can achieve online fault identification. The PCA + SVM algorithm was compared with the SVM algorithm, BP algorithm, and PCA + BP algorithm, and the results show that the PCA + SVM algorithm is superior in terms of running time and accuracy, the diagnosis accuracy reached more than 99%, and the running time was within 20 s. The corresponding system optimization scheme is also proposed.

Dilihat dari sisi konsumen, ada berbagai aspek yang mempengaruhi konsumen untuk membeli suatu kendaraan bermotor. Hal ini karena masing-masing orang memiliki minat dan kebutuhan yang berbeda. Oleh karena itu, tujuan dari penelitian ini adalah untuk mengetahui kelompok umur dan profesi apa saja yang menjadi pelanggan potensial di SPS Motor Honda Lombok Timur. Metode penelitian yang digunakan adalah metode analitik deskriptif, dimana peneliti mengambil data-data penjualan sepeda motor dari SPS Motor Honda Lombok Timur, yang selanjutnya diolah dan dianalisis menggunakan software Rapidminer 5. Hasil analisis data tersebut selanjutnya dideskripsikan dengan detail mengenai kelompok pelanggan potensial. Berdasarkan analisis yang telah dilakukan, dapat ditarik kesimpulan bahwa kelompok yang termasuk dalam pelanggan potensial dari SPS Motor Honda Lombok Timur adalah kelompok dengan kriteria umur berkisar 33-46 tahun yang berprofesi sebagai wiraswasta dan petani, Hal ini disebabkan karena, pelanggan tersebut memiliki penghasilan dengan usia produktif. Sedangkan kelompok pelanggan yang tidak potensial ada 2 irisan yaitu yang pertama apabila kategori usia produktif tapi tidak memiliki penghasilan dengan rentang umur 17-32 tahun dengan profesi pelajar dan wiraswasta. Kedua yaitu, apabila kategori usia tidak produktif dengan rentang usia 47-73 tahun dan tidak memiliki penghasilan dengan profesi petani dan wiraswata.DOI : 10.29408/jit.v2i2.1447

Traditional approaches require a velocity model to compute travel times for estimating the location of earthquakes. Moreover, the velocity model typically assumed is layered in nature, ignoring the perturbations around the background velocity model. In this study, we propose a novel method that does not require any assumption on a velocity model. Also, triangulation estimates of location require three-station recordings. Even if the single station is used, three components of recordings are needed. In this work, we propose a machine learning method, based on support vector machines (SVM), that can predict earthquake location and magnitude with just one component (vertical) of a single station. Machine learning methods are typically used for either regression or classification. Literature shows that the SVM algorithm is promising for the classification of an arbitrary signal. This research demonstrates that, by using complementary input features from a seismic recording, a comparable performance can be obtained, with a substantial reduction in detection time. Furthermore, only the vertical component of a single recording station data is used to train the network. The SVM algorithm is applied on synthetic seismograms from 400 earthquakes of different focal mechanisms and magnitudes. This falls under supervised machine learning, as we give the input features and use them for training the model. Overfitting is avoided by tenfold cross-validation, i.e., the algorithm is repeated ten times, each time giving a different 10% as a testing portion. The classifier's performance is quite good, on the synthetic noise-free data, in predicting the magnitude, elevation angle, and hypocentral distance, but not the azimuthal angle. The trained model in the present work can be readily used where noise levels are quite low without sophisticated ray-tracing or Green's function computation. The performance of the algorithm is checked by adding additive noise to the data. The novelty of this work is that knowledge of the velocity model is not required, and the estimation of magnitude and the origin of the earthquake are done using the single-station/single-component earthquake records.

In order to improve the accuracy of the prediction model of lung tuberculosis, a prediction model of lung tuberculosis based on grayscale mixed nucleus AR-SVM model is proposed in the Thesis. First, early warning model of the incidence trend of lung tuberculosis was constructed by using support vector machine (SVM) algorithm which includes two circumstances. One is that there is no extreme risk preference; the other is that there is extreme risk preference. And the searching was conducted in the optimum sorting process in training set based on SVM algorithm; Secondly, aimed at the problem that early warning of extreme risk preference of SVM model is easily out of order in the prediction of incidence trend of lung tuberculosis, data record of incidence trend of lung tuberculosis was preprocessed by using improved SVM model and SVM algorithm was improved by polynomial kernel SVM, which achieved improvement of prediction performance of autoregression model of sample data; finally, the effectiveness of algorithm is verified by positive analysis.

In many domains such as Telecom various scenarios necessitate the processing of large amounts of data using statistical and machine learning algorithms. A noticeable effort has been made to move the data management systems into MapReduce parallel processing environments such as Hadoop and Pig. Nevertheless these systems lack the features of advanced machine learning and statistical analysis. Frame-works such as Mahout on top of Hadoop support machine learning but their implementations are at the preliminary stage. For example Mahout does not provide Support Vector Machine (SVM) algorithms and it is difficult to use. On the other hand traditional statistical software tools such as R containing comprehensive statistical algorithms for advanced analysis are widely used. But such software can only run on a single computer and therefore it is not scalable. In this paper we propose an integrated solution RPig which takes the advantages of R (for machine learning and statistical analysis capabilities) and parallel data processing capabilities of Pig. The RPig framework offers a scalable advanced data analysis solution for machine learning and statistical analysis. Analysis jobs can be easily developed with RPig script in high level languages. We describe the design implementation and an eclipse-based RPigEditor for the RPig framework. Using application scenarios from the Telecom domain we show the usage of RPig and how the framework can significantly reduce the development effort. The results demonstrate the scalability of our framework and the simplicity of deployment for analysis jobs.

In the present work, model transformer windings were used to obtain Sweep frequency Response Analyzer measurement data for various experimentally simulated faults. Transfer function and its corresponding parameters were computed for different types of transformer faults by subspace based identification method. An attempt was made to use these parameters for training Artificial Neural Network. The result of study on application of Artificial Neural Network algorithm for diagnosing and identifying the transformer winding faults from the Frequency Response Analysis data is presented. It was observed that, predicted fault closely follows the created fault suggesting the effectiveness of Artificial Neural Network technique for distinguishing between the normal and failed state quite satisfactorily.

In this study, a method that recognizes the sound of hail is proposed for a system designed to minimize the damage caused by hail to vehicles. The designed system uses signal processing and machine learning. The sounds received by a microphone in the vehicle were converted into frequency space and the kernel density estimation of the frequency values occurring in a certain time interval (approximately 2 seconds) was obtained. This is based on the prediction that the histogram of the frequency of hail falling on the car can have a defining characteristic. In this context, it has been designed to create a two-class machine learning problem, including full sound samples and ambient sound samples. A solution to the machine learning problem was sought with the Support Vector Machines (SVM) algorithm. The SVM algorithm was chosen due to its simplicity and fast working dynamics. While learning is offline in the SVM algorithm, testing is done online. Related software was implemented using MATLAB. In experimental studies, we collected a dataset where almost 500 hail sound segments were used and similarly 400 ambient sound segments were collected. A hold out cross validation approach with various split ratio values are used. It has been seen that the proposed method predicts hail sounds with 92.22% accuracy when the hold out cross validation ration is 90% and 10%.

Food flavor analysis 4.0: A cross-domain application of machine learning