Improved Self-Organizing Map Clustering of Power Transformer Dissolved Gas Analysis Using Inputs Pre-Processing

With an onset of social network amount of data is increasing day by day. In order to analyze the data and extract useful information, the data mining technology can be used. Clustering is one of the popular method of data mining. Clustering can be used for visualizing and analyzing of data. We are discussing Kohonen SOM. We are using neural networks, as a data mining tool which provides statistical observation and layout from big data-sets. We determine how Self-Organizing Kohonen Maps, can be efficiently used for data mining purposes. The Self Organizing Map (SOM) unsupervised learning is an effective computational tool in data mining processes. Self-Organizing Maps (SOMs) used to visualize social network dataset. We used Self-Organizing Map for clustering and analyzing high-dimensional and complex social network datasets. This paper also visualizes SOM neighbor connection, SOM neighbor weight distance, SOM weight position. We perform self organizing map algorithm for social network dataset in matlab.

Power transformers are one of the most crucial as well as costly equipment in power grids. Nowadays, a set of factors like the growing load, expanding power consumption, and market liberation affect on the transformer reliability and operational lifetime. At present, numerous approaches are on hand to diagnosis and evaluate their operational conditions. Dissolved gas analysis (DGA) in the insulation oil is an efficient diagnostic scheme which can offer an essential source for transformer failure diagnosis. In this paper, five existing approaches of utilizing dissolved gas data to identify fault kind in power transformers oil are employed. The considered methods are: key gas technique, IEC 60599 technique, Doernenburg ratio scheme, Duval triangle framework, as well as Rogers ratio scheme. These fault diagnosis methods are used to interpret and validate the dissolved gas analysis (DGA) results for four case studies. The experiments are performed on four 15.75 kV/400 kV, 3-Phase, 250 MVA power transformers in a thermal power plant. The obtained DGA results reveal that all considered DGA methods have effectively detected the fault type for each considered case except Duval triangle method which has failed to discover the fault type for two cases.

The power transformer is the core equipment of the power system, a sudden failure of which will seriously endanger the safety of the power system. In recent years, artificial intelligence techniques have been applied to the dissolved gas analysis evaluation of power transformers to improve the accuracy and efficiency of power transformer fault diagnosis. However, most of the artificial intelligence techniques are data-driven algorithms whose performance decreases when the data are limited or significantly imbalanced. In this paper, we propose an active learning framework for power transformer dissolved gas analysis, in which the model can be dynamically trained based on the characteristics of the data and the training process. In addition, this paper also improves the original active learning spatial search strategy and uses the product of sample feature differences instead of the original sum of differences as a measure of sample difference. Compared to passive learning algorithms, the novel approach could significantly reduce the data labeling effort while improving prediction accuracy.

This paper proposes an integrated approach utilizing Fuzzy Logic and Decision Tree algorithms to diagnose early-stage faults in power transformers based on Dissolved Gas Analysis (DGA) test results of transformer insulation oil. Overcoming limitations in conventional methods such as Duval Triangle, Key Gas Analysis, Rogers Ratio, IEC Ratio, and Doernenburg Ratio, our Fuzzy Logic and Decision Tree models address issues like inaccurate diagnosis, inconsistent diagnosis, lack of decisions or out-of-code results, and time-intensive manual calculations for large DGA datasets. The Decision Tree algorithm, a machine learning technique is applied to categorize faults into thermal and electrical types. Trained with over 300 DGA samples from transformers with known faults, the models exhibit robust performance during testing with different datasets. Notably, the Duval Triangle decision tree model attains the highest accuracy among the ten developed models, achieving a 98% accuracy rate when tested with 50 samples with known faults. Moreover, Decision Tree models for KGA, Doernenburg, Rogers, and IEC also demonstrate substantial prediction accuracy at 92%, 86%, 92%, and 90% respectively underscoring the efficacy of artificial intelligence methods over traditional approaches.

To allow utilities to fulfill self-imposed and regulative performance targets the demand for new optimized tools and techniques to Estimate the performance of modern Transformers has increased. The modern power transformers has subjected to different types of faults, which affect the continuity of power supply which in turn causes serious economic losses. To avoid the interruption of power supply, various fault diagnosis approaches are adopted to detect faults in the power transformer and has to eliminate the impacts of the faults at the initial stage. Among the fault diagnosis methods, the hybrid technique of Particle Swarm Optimization (PSO) with Support Vector Machine (SVM) learning algorithm is simple conceptually derived and its implementation process is faster with better scaling properties for complex problems with non linearity and load variations but performance factor related to accuracy has a declined value in case of correlations implicit . In order to obtain better fault diagnosis to improve the service of the power transformer, SVM is optimized with Improved PSO technique to achieve high interpretation accuracy for Dissolved Gas Analysis (DGA) of power transformer through the extracting positive features from both the techniques. Primary SVM is applied to establish classification features for faults in the transformer through DGA. The features are applied as input data to Autonomous optimized Technique for faults analysis. The proposed methodology obtains the DGA data set from diagnostic gas in oil of 500 KV main transformers of Pingguo Substation in South China Electric Power Company. The simulations are carried out in MATLAB software with an Intel core 3 processor with speed of 3 GHZ and 4 GB RAM PC. The result obtained by Autonomous optimized Technique (IPSO-SVM) is compared against PSO-SVM to estimate the performance of the classifiers in terms of execution time and quality of classification for precision. The test results indicate that the Autonomous optimization of IPSO-SVM approach has significantly improved the classification accuracy and computational time for power transformer fault classification. Keywords: Transformer Fault Analysis, Improved Particle Swarm Optimization, Hybrid Optimization, Dissolved Gas Analysis, Support Vector Machine

This paper presents a rotor bars Modeling. The rotor of an Electrical asynchronous machine is modeled by an equivalent electrical diagram related to the squirrel-cage connected together electrically and coupled magnetically, the frequencies characteristics of fault break bars. An intelligent strategy was adopted for fault detection in rotor using the map SOM (Self Organizing Map). It involves the most significant parameters of SOM, such as the topological structure of the map, the Kohonen learning algorithm, and also the activity diagram UML (Unified Modeling Language). Eventually, the measurement of the stator current on the experimental bench at a specific moment in the NDC (Non Destructive Control) Laboratory was applied. A comparative study of the fault detection performance was conducted under the SOM neural map and the spectral analysis method. It will be a more synthetic analysis.

Measuring brain activity through Electroencephalogram (EEG) analysis for eye state prediction has attracted attention from machine learning researchers. There have been many methods for EEG analysis using supervised and unsupervised machine learning techniques. The tradeoff between the accuracy and computation time of these methods in performing the analysis is an important issue that is rarely investigated in the previous research. This paper accordingly proposes a new method for EEG signal analysis through Self-Organizing Map (SOM) clustering and Deep Belief Network (DBN) approaches to efficiently improve the computation and accuracy of the previous methods. The method is developed using SOM clustering and DBN, which is a deep layer neural network with multiple layers of Restricted Boltzmann Machines (RBMs). The results on a dataset with 14980 instances and 15 attributes representing the values of the electrodes demonstrated that the method is efficient for EEG analysis. In addition, compared with the other supervised methods, the proposed method was able to significantly improve the accuracy of the EEG prediction.

Adipogenesis is of significant relevance from an agricultural perspective. Traits such as subcutaneous fat thickness, marbling and waste fat are of substantial economic importance in animal production. In order to discover more about the genetic basis of this process, a study was undertaken to examine the changes that occur daily in global gene expression as 3T3-L1 cells differentiate from preadipocyte to adipocyte. Duplicate RNA samples were collected daily during the differentiation process and probed with the Affymetrix U74Av2 GeneChip® microarray to allow the time-course analysis of the gene expression profile in these differentiating cells. Self-organizing maps (SOM) clustering was performed to extract patterns of expression over the course of the experiment (day 0 to day 6). The clustering generated nine distinct expression patterns containing between 74 and 420 genes/ESTs. Functional clusters and important chronological changes in the expression of key genes and gene groups were identified. The pattern of expression observed for many genes not only confirmed what has been shown previously for the early stages of differentiation, but also expanded this pattern to cover the whole differentiation process thus giving a very comprehensive overview of patterns and changes in gene expression over the time course of adipocyte differentiation. Key words: Adipocyte differentiation, gene expression, SOM clustering

The purpose of this study is to investigate the effects of toolpath patterns, geometry types, and layering effects on the mechanical properties of parts manufactured by direct energy deposition (DED) additive manufacturing using data analysis and machine learning methods. A total of twelve case studies were conducted, involving four distinct geometries, each paired with three different toolpath patterns based on finite element method (FEM) simulations. These simulations focused on residual stresses, strains, and maximum principal stresses at various nodes. A comprehensive analysis was performed using a linear mixed-effects (LME) model, principal component analysis (PCA), and self-organizing map (SOM) clustering. The LME model quantified the contributions of geometry, toolpath, and layer number to mechanical properties, while PCA identified key variables with high variance. SOM clustering was used to classify the data, revealing patterns related to stress and strain distributions across different geometries and toolpaths. In conclusion, LME, PCA, and SOM offer valuable insights into the final mechanical properties of DED-fabricated parts.

Self Organization Map(SOM) is an automatic tool in data analysis in data mining,it is used to explore the multi-dimentional data which simplifies complexity and produce meaningful relation with each other or high dimentional into low dimentional .the powerful method of SOM i.e learning method results excellent performance .the SOM algorithum have various steps from starting stage to the final neuron and their weight updation and modification, these procedure resultant a lot of compplexity accoording to the parameters on the basis of experiments .this paper will compare and discuss various papameters and their result or factors that can improve and refine the image through varius process of SOM.

We have been working on the application of Machining Learning in Metabolomics, Drug-Drug Interaction Discovery and Human Gait Recognition [1-5], profiling large data sets. Extraction of vital information about 1) plant metabolomics that can improve the environment and food quality, 2) in vitro neuronal network behavior patterns for various drugs that can be used to characterize drugs for brain deceases and 3) human gait patterns that can reveal various diseases were among these applications. We have demonstrated with considerable success in using unsupervised clustering techniques to analyze genetic and metabolomic data. This includes analysis of drought resistance in wheat [4] and microbial metagenomes [5].We introduced two methods: Near Unsupervised Learning (NUL) and Sub-sample Error Graphs (SEGs) [5] to analyze large amount of data. Self Organizing Map (SOM), which is one of the widely used Unsupervised Neural Networks, has been used as a data-mining tool due to its ability to map high dimensional data into a two dimensional feature map, which is expected to be topology preserving allowing users to visually identify clusters by their topological relationships in terms of their proximity on the map. The Growing Self Organizing Maps (GSOM) further allows the map size to be determined by the algorithm, which relies upon a user set parameter called Spread Factor (SF) [6]. The wide availability of GPUs for affordable prices allows faster comparison of various SOMs with different maps sizes taking away some of the advantages GSOM claimed. Further development of GSOM into a Dynamic SOM Tree exploits the possibility of varying SF to obtain multiple GSOMs from a small number of compact clusters to a large number of sparse clusters [7]. NUL methods can be applied on GSOM using a small number of labels that should be available for every class. This is however not realistic in some applications where the number of classes cannot be explicitly known. We propose a new method call Deep Near Unsupervised Learning (D-NUL), where Dynamic SOM tree is used instead of GSOM and the number of classes are not assumed to be known. The implementation of Dynamic SOM tree methods with varying SF on GPUs will make the computation with D-NUL possible for many problems in big data analytics.

Knowledge discovery consists of finding new knowledge from data bases where dimension, complexity or amount of data is prohibitively large for human observation alone. The Self Organizing Map (SOM) is a powerful neural network method for the analysis and visualization of high-dimensional data. The need for efficient data visualization and clustering is often faced, for instance, in the analysis, monitoring, fault detection, or prediction of various engineering plants. In this paper, the use of a SOM based method for prediction of disruptions in experimental devices for nuclear fusion is investigated. The choice of the SOM size is firstly faced, which heavily affects the performance of the mapping. Then, the ASDEX Upgrade Tokamak high dimensional operational space is mapped onto the 2-dimensional SOM, and, finally, the current process state and its history in time has been visualized as a trajectory on the map, in order to predict the safe or disruptive state of the plasma.KeywordsKnowledge DiscoverySelf Organizing MapsTokamak Disruptions

Artificial neural network is powerful in analyzing and solving complicated and non-linear matters. SOFM (self-organizing feature map) clustering was described and applied to the analysis of woodland communities in the Guancen Mountains of China. The dataset was consisted of importance values of 112 species in 53 quadrats. SOFM clustering classified the 53 quadrats into eight groups, representing eight associations of vegetation. These results are ecologically meaningful, which suggests that SOFM clustering is effective method in studies of ecology.

Artificial Neural Networks (ANN) are a classic pattern classifier and widely applicable to various problems and are relatively easy to use. Three of the most popular ANNs are Multilayer Perceptron (MLP) with Backpropagation learning algorithm, Self Organizing Map (SOM) and Recurrent Neural Network (RNN). Support Vector Machines (SVM) have gained great interest in the last few years in pattern recognition. Thus, this research compares the recognition performance of text and non-text images (text, table, figure and graph) from technical document images based on the pixel intensity of various zones between BPNN, SOM, RNN and SVM. Symmetrical and non-symmetrical zoning algorithms were compared as input. 400 different datasets have been tested and the experiments indicate that SVM classification is superior to the other three classifiers. The experiments also indicate that the combination of symmetrical and non-symmetrical zoning design is better than non-symmetrical or symmetrical zoning only.

Electrical transformers are the most important elements in the process of transmission and distribution of electricity. Depending on the size and position of the transformer, the sudden device failure can cause tremendous damage. Neural networks are widespread technique for transformer health monitoring. Neural Network Ensembles are an advanced neural technique that improves the accuracy and reliability in the transformers health diagnosis and failure prognosis. This paper describes a technique how to identify causal relation of dissolved gases in transformers oil and the current state of the transformers health. The described algorithm improves the interpretation of results obtained by dissolved gas analysis (DGA) technique. The most important result of this algorithm is a timely and reliable prediction of transformers failure based on incipient faults detection.