Detection of Transformer Defects in Smart Environment Using Frequency Response Analysis and Artificial Neural Network Based on Data-Driven Systems

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.

Download Full-text

Feed-forward artificial neural network provides data-driven inference of functional connectivity

Chaos An Interdisciplinary Journal of Nonlinear Science ◽

10.1063/1.5117263 ◽

2019 ◽

Vol 29 (9) ◽

pp. 091101 ◽

Cited By ~ 9

Author(s):

Nikita Frolov ◽

Vladimir Maksimenko ◽

Annika Lüttjohann ◽

Alexey Koronovskii ◽

Alexander Hramov

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Functional Connectivity ◽

Data Driven ◽

Feed Forward ◽

Artificial Neural

Download Full-text

Data-driven framework towards realistic bottom-up energy benchmarking using an Artificial Neural Network

Applied Energy ◽

10.1016/j.apenergy.2021.117960 ◽

2022 ◽

Vol 306 ◽

pp. 117960

Author(s):

Matheus Soares Geraldi ◽

Enedir Ghisi

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Data Driven ◽

Bottom Up ◽

Energy Benchmarking ◽

Artificial Neural

Download Full-text

A MLMVN with Arbitrary Complex-Valued Inputs and a Hybrid Testability Approach for the Extraction of Lumped Models Using FRA

Journal of Artificial Intelligence and Soft Computing Research ◽

10.2478/jaiscr-2018-0021 ◽

2019 ◽

Vol 9 (1) ◽

pp. 5-19 ◽

Cited By ~ 2

Author(s):

Igor Aizenberg ◽

Antonio Luchetta ◽

Stefano Manetti ◽

Maria Cristina Piccirilli

Keyword(s):

Neural Network ◽

Frequency Response ◽

Learning Algorithm ◽

Repeated Measurements ◽

Distributed Parameter ◽

Response Analysis ◽

Frequency Response Analysis ◽

Arbitrary Complex ◽

Lumped Models ◽

Complex Valued

Abstract A procedure for the identification of lumped models of distributed parameter electromagnetic systems is presented in this paper. A Frequency Response Analysis (FRA) of the device to be modeled is performed, executing repeated measurements or intensive simulations. The method can be used to extract the values of the components. The fundamental brick of this architecture is a multi-valued neuron (MVN), used in a multilayer neural network (MLMVN); the neuron is modified in order to use arbitrary complex-valued inputs, which represent the frequency response of the device. It is shown that this modification requires just a slight change in the MLMVN learning algorithm. The method is tested over three completely different examples to clearly explain its generality.

Download Full-text

Data-driven modeling to optimize the injection well placement for waterflooding in heterogeneous reservoirs applying artificial neural networks and reducing observation cost

Energy Exploration & Exploitation ◽

10.1177/0144598720927470 ◽

2020 ◽

Vol 38 (6) ◽

pp. 2413-2435 ◽

Cited By ~ 1

Author(s):

Xinwei Xiong ◽

Kyung Jae Lee

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Injection Well ◽

Data Driven ◽

Well Placement ◽

Heterogeneous Reservoirs ◽

Modeling Approach ◽

Artificial Neural ◽

Well Data ◽

Data Driven Modeling

Secondary recovery methods such as waterflooding are often applied to depleted reservoirs for enhancing oil and gas production. Given that a large number of discretized elements are required in the numerical simulations of heterogeneous reservoirs, it is not feasible to run multiple full-physics simulations. In this regard, we propose a data-driven modeling approach to efficiently predict the hydrocarbon production and greatly reduce the computational and observation cost in such problems. We predict the fluid productions as a function of heterogeneity and injection well placement by applying artificial neural network with small number of training dataset, which are obtained with full-physics simulation models. To improve the accuracy of predictions, we utilize well data at producer and injector to achieve economic and efficient prediction without requiring any geological information on reservoir. The suggested artificial neural network modeling approach only utilizing well data enables the efficient decision making with reduced computational and observation cost.

Download Full-text

The Hyper-Angular Cube Concept for Improving the Spatial and Acoustic Resolution of MBES Backscatter Angular Response Analysis

Geosciences ◽

10.3390/geosciences8120446 ◽

2018 ◽

Vol 8 (12) ◽

pp. 446 ◽

Cited By ~ 3

Author(s):

Evangelos Alevizos ◽

Jens Greinert

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Data Structure ◽

Supervised Classification ◽

Incidence Angle ◽

Ground Truth ◽

Response Analysis ◽

Ground Truth Data ◽

Angular Response ◽

Artificial Neural

This study presents a novel approach, based on high-dimensionality hydro-acoustic data, for improving the performance of angular response analysis (ARA) on multibeam backscatter data in terms of acoustic class separation and spatial resolution. This approach is based on the hyper-angular cube (HAC) data structure which offers the possibility to extract one angular response from each cell of the cube. The HAC consists of a finite number of backscatter layers, each representing backscatter values corresponding to single-incidence angle ensonifications. The construction of the HAC layers can be achieved either by interpolating dense soundings from highly overlapping multibeam echo-sounder (MBES) surveys (interpolated HAC, iHAC) or by producing several backscatter mosaics, each being normalized at a different incidence angle (synthetic HAC, sHAC). The latter approach can be applied to multibeam data with standard overlap, thus minimizing the cost for data acquisition. The sHAC is as efficient as the iHAC produced by actual soundings, providing distinct angular responses for each seafloor type. The HAC data structure increases acoustic class separability between different acoustic features. Moreover, the results of angular response analysis are applied on a fine spatial scale (cell dimensions) offering more detailed acoustic maps of the seafloor. Considering that angular information is expressed through high-dimensional backscatter layers, we further applied three machine learning algorithms (random forest, support vector machine, and artificial neural network) and one pattern recognition method (sum of absolute differences) for supervised classification of the HAC, using a limited amount of ground truth data (one sample per seafloor type). Results from supervised classification were compared with results from an unsupervised method for inter-comparison of the supervised algorithms. It was found that all algorithms (regarding both the iHAC and the sHAC) produced very similar results with good agreement (>0.5 kappa) with the unsupervised classification. Only the artificial neural network required the total amount of ground truth data for producing comparable results with the remaining algorithms.

Download Full-text

MATHEMATICAL-ARTIFICIAL NEURAL NETWORK HYBRID MODEL TO PREDICT ROLL FORCE DURING HOT ROLLING OF STEEL

International Journal of Computational Materials Science and Engineering ◽

10.1142/s2047684113500048 ◽

2013 ◽

Vol 02 (01) ◽

pp. 1350004 ◽

Cited By ~ 1

Author(s):

S. RATH ◽

P. P. SENGUPTA ◽

A. P. SINGH ◽

A. K. MARIK ◽

P. TALUKDAR

Keyword(s):

Neural Network ◽

Mathematical Model ◽

Artificial Neural Network ◽

Flow Stress ◽

Mathematical Models ◽

Hybrid Model ◽

Data Driven ◽

Roll Force ◽

Hot Strip ◽

Artificial Neural

Accurate prediction of roll force during hot strip rolling is essential for model based operation of hot strip mills. Traditionally, mathematical models based on theory of plastic deformation have been used for prediction of roll force. In the last decade, data driven models like artificial neural network have been tried for prediction of roll force. Pure mathematical models have accuracy limitations whereas data driven models have difficulty in convergence when applied to industrial conditions. Hybrid models by integrating the traditional mathematical formulations and data driven methods are being developed in different parts of world. This paper discusses the methodology of development of an innovative hybrid mathematical-artificial neural network model. In mathematical model, the most important factor influencing accuracy is flow stress of steel. Coefficients of standard flow stress equation, calculated by parameter estimation technique, have been used in the model. The hybrid model has been trained and validated with input and output data collected from finishing stands of Hot Strip Mill, Bokaro Steel Plant, India. It has been found that the model accuracy has been improved with use of hybrid model, over the traditional mathematical model.

Download Full-text