Fault Classification in Mixed Signal Circuits using Artificial Neural Networks

Deep learning techniques for transmission line fault classification – A comparative study

In order to run power plant operations smoothly, power plant faults need to be detected, located, and classified quickly. For this, artificial neural network approaches are considered significant tool in related application of power system. This research paper focuses on power plant faults detection and classification using intelligent approach of artificial neural network. There is frequent nature of power plant faults, in particular transmission line faults. The key intention of this research is to use ANN approach to detect and classify power plant faults, and in the end to compare their performance and accuracy. In this proposal, the three-phase current and voltage are use as input. Backpropagation (BPNN) technique is used in developing the learning algorithm for multi-layer neural network that can accurately and reliably classify faults. The multi-layer neural network such as Levenberg-Marquardt and Bayesian regularization are used for offline training of the data. Findings from this research show that both Levenberg-Marquardt and Bayesian regularization show good accuracy to detect and classify faults in transmission line. However, LM algorithm trained data much faster than BR. LM shows fastest detection of faults with overall mean square error value of 6.13785e-3 at the 91 epoch. Whereas, BR trained network at the 717 epochs with overall mse of 4.67123e-3. It is to be noted that the accuracy of trained network to classify all the fault types is found to be 81.1%, which is higher than previous studies using Backpropagation neural network technique. Training and test results show that these neural network-based methods can effectively detect and classify faults and faults types and have adequate performance. Matlab is used in this research because it has toolbox, which has effective features to train required data and achieve effective result.

As the electric power system grows in size and complexity with a large number of interconnections, the assessment of the transient stability of power systems became an extremely intricate and highly non‐linear problem. Its solution needs either numerical methods involving bulk computations or specific dedicated methods to analyse dynamic non‐linear systems. Either method mostly assesses, particularly in the post‐fault condition, the critical clearing time (CCT). This parameter constitutes very complex functional relationships between the pre‐fault condition, type, and location of fault beside the clearance sequence. The available methods for evaluating such parameter had been previously reviewed. New approaches using the locally‐tuned radial basis function (RBF) network, an artificial neural network (ANN) paradigm have been recently proposed. The goal of this paper is to develop methods that can combine both neural networks and genetic algorithms (GA) into a common framework, and apply them to prediction problems. In the paper, the application of genetic algorithms in selecting the input patterns for the RBF network is proposed. Description of this combined approach and the results of its application to two power systems, one for four‐machine six‐bus system and the other for an existing system of North Sumatra. Indonesia, are also given in the paper. The attainable results show that the performance of the RBF network can be maintained and improved in spite of less features in the input patterns.

This study aims to develop a real-time model for detecting and classifying various fault types in power distribution networks to enhance reliability and operational efficiency. A hybrid DWT–SVM approach is essential for accurately detecting and classifying faults in modern power distribution systems, especially under non-stationary and dynamic conditions. The proposed method addresses a range of fault scenarios, including single-phase-to-ground, line-to-line, double-line-to-ground, and three-phase faults, within a 33 kV distribution network. A hybrid approach combining Discrete Wavelet Transform (DWT) and Support Vector Machine (SVM) is introduced. Using the Debauchies-4 (Db4) wavelet, DWT effectively decomposes transient fault currents at the source terminal, capturing critical time-frequency domain features. Fault classification is performed using an SVM optimized with a Radial Basis Function (RBF) kernel and Particle Swarm Optimization (PSO), enabling precise mapping of data into higher-dimensional spaces for optimal separation. Validation conducted with MATLAB R2023b demonstrates a detection accuracy of 100% and a classification accuracy of 99%. Comparative analyses against models such as PSO-based Support Vector Machine (PSO-SVM), DWT-DNN and wavelet transform with artificial neural networks (WT-ANN) on the IEEE 13-bus system highlight the proposed method's superior performance. This innovative approach proves to be robust, adaptable, and highly effective across diverse fault scenarios, offering significant improvements in accuracy and reliability for fault detection and classification in power distribution networks. The method supports real-time operation by using high-speed simulation platforms MATLAB/Simulink to process signals and classify faults within milliseconds using a pre-trained SVM model.

The artificial neural network is a powerful tool for the detection of the transmission line faults due to its ability to differentiate between various patterns. This paper deals with the application of artificial neural networks (ANNs) to the fault detection and classification in high voltage transmission lines for high speed protection which can be used in digital power system protection. The three phase currents of one end are taken as inputs in the proposed scheme. The feed forward neural network along with back propagation algorithm has been employed for detection and classification of the fault for analysis of each of the three phases involved in the process. The ANN was trained and tested using various sets of field data, which was obtained from the simulation of faults at various fault scenarios (fault types, fault locations and fault resistance) of 230 kV, 193.2 km in length “Mansan-Shwesaryan, Mandalay Region, Myanmar” transmission line using a computer program based on MATLAB/Simulink. Simulation results confirm that the proposed method can efficiently be used for accurate fault classification on the transmission line.

This paper presents an efficient wavelet and neural network (WNN) based algorithm for fault classification in single circuit transmission line. The first level discrete wavelet transform is applied to decompose the post fault current signals of the transmission line into a series of coefficient components (approximation and detail). The values of the approximation coefficients obtained can accurately discriminate between all types of fault in transmission line and reduce the number of data feeding to the ANN. These coefficients are further used to train an Artificial Neural Network (ANN) fitting function. The trained FFNN clearly distinguishes and classify very accurate and very fast the fault type. A typical generation system connected by single circuit transmission line to many nodes of lodes at the receiving end was simulated using MATLAB simulation software using only one node to do this work. The generated data were used by the MATLAB software to test the performance of the proposed technique. The simulation results obtained show that the new algorithm is more reliable and accurate.

This paper presents a method for analog circuit fault diagnosis by using neural networks. This method exploits a DC approach for constructing a dictionary in fault diagnosis using the neural network's classification capability. Also, Radial Basis Function (RBF) and backward error propagation (BEP) networks are considered and compared for analog fault diagnosis. The primary focus of the paper is to provide robust diagnosis using a mechanism to deal with the problem of component tolerance and reduce testing time. Simulation results show that the radial basis function network with reasonable dimension has double precision in fault classification but its classification is local, while the backward error propagation network with reasonable dimension has single precision in fault classification but its classification is global.

This study aims to improve the performance of transmission line directional relaying, fault classification and fault location schemes using fuzzy system. Three separate fuzzy inference system are designed for complete protection scheme for transmission line. The proposed technique is able to accurately detect the fault (both forward and reverse), locate and also identify the faulty phase(s) involved in all ten types of shunt faults that may occur in a transmission line under different fault inception angle, fault resistances and fault location. The proposed method needs current and voltage measurements available at the relay location and can perform the fault detection and classification in about a half‐cycle time. The proposed fuzzy logic based relay has less computation complexity and is better than other AI based methods such as artificial neural network, support vector machine, and decision tree (DT) etc. which require training. The percentage error in fault location is within 1 km for most of the cases. Fault location scheme has been validated using χ2 test with 5% level of significance. Proposed scheme is a setting free method and is suitable for wide range of parameters, fault detection time is less than half cycle and relay does not show any reaching mal‐operation so it is reliable, accurate and secure.

Time domain complete protection scheme for parallel transmission lines

The proposed technique consists of a pre-processing unit based on Continuous Wavelet Transform (CWT) in combination with an Artificial Neural Networks (ANN). CWT acts as an extractor of distinctive features in the transient current signals at the sending and receiving end of the transmission line. This information is then fed to the ANN for detecting the fault type and location of fault. The results presented clearly indicate that the present technique is very fast, computationally efficient and intelligent enough to accurately identify three different types of fault (LG & LLG) and their locations.

Fault analysis is an important consideration in power system planning, protection and overall system reliability assessment. When a fault occurs at some point in the network, normal operating conditions are upset; if the fault is persistent severe loss of load, property damage and steep economic losses can arise as undesirable consequences. Relay, circuit breakers and other protective elements are used to prevent such damages. Different types of faults in busbar are classified using the bus voltages and line fault current. In this paper, we have proposed an effective way of fault detection and classification in busbars using Artificial Neural Network (ANN). This can make the power system protection more effective. We have considered IEEE 9-bus system and a dataset has been generated using PSAF CYME software. This dataset is used to train and test our network in MATLAB software. The algorithm can be used for any bus system given the voltage magnitude and angles, which will be helpful for the authorities to get notified and solve the problem as soon as possible, since repair mechanism of each type of fault is different from others.

Prediction of stock market indices is an interesting and challenging research problem in financial data mining area because movement of stock indices are nonlinear and they are dependent upon different constitutional and extraneous aspects. In this paper we come up with the practice of different techniques of Artificial Neural Network (ANN) in stock market prediction. Here we have selected Multilayer Perceptron model (MLP), Radial Basis Functional Network (RBFN) and an optimized Radial Basis Functional neural network. The proposed model provides an optimized set of center set to Radial Basis Functional Network for experiment and Particle swarm algorithm is used for this boosting process. Lastly in order to verify the best tactics, a comparative result of the applied models is represented.

Faults in engineering systems are difficult to avoid and may lead to degraded performance, malfunctions or failures. In complex systems, a fault possesses the potential to impact the entire system behavior. In this paper, a fault detection technique for Permanent Magnet Synchronous Motor is proposed for detecting different type of faults. The proposal uses an artificial neural network to detect faults that develop gradually in the system. The Artificial Neural Network is trained using Levenberg-Marquardt algorithm and a Discrete Wavelet Transform based feature extraction block for Permanent magnet synchronous motor drive system is employed. The fault detection system classifies four of the most common and highly probable faults such as inverter short circuit, inverter open circuit, winding short circuit and winding open circuit. The proposed approach suggests that with a robust learning approach, a diagnostic system can be trained based on the machine parameters, which can lead to a correct identification of faults over a wide operating region.

Accurate prediction of missing hydro-meteorological data is crucial in planning, design, development and management of water resources systems. In the present research, prediction of such data using Artificial Neural Networks (ANN) based on temporal and spatial auto-correlation has been conducted for upper Tana River basin in Kenya. Different ANN models were formulated using a combination of numerous data delays in the ANN input layer. The findings show that the best models comprise of a feed-forward neural network trained on Levenberg-Marquardt algorithm with single hidden layer. Additionally, the best ANN architecture model for predicting missing stream flow data was at gauge station 4CC03 with correlation coefficient and MSE of 0732 and 0.242 respectively during validation. Temporal auto-correlation of the observed and the predicted stream flow values were evaluated using a correlation coefficient R that resulted to highest value of 0.756 at gauge station 4AB05. The best ANN model for prediction of missing precipitation data was at station 9037112 with R value of 0.970. In both cases the best performance was at epochs 9 and 20 respectively. The spatial auto-correlation show that the best ANN architecture model for prediction of missing stream flow data was at gauge station 4CC03 with R value of 0.723, while the one for precipitation was at station 9037096 with R value of 0.712 during the validation. The results indicate that the spatial auto-correlation of hydro-meteorological data using ANN is better than the temporal auto-correlation in the data prediction in upper Tana River basin.

In this study, barley yield has been estimated via radial basis function network (RBF) and feed-forward neural networks (GFF) models of artificial neural network (ANNs) in Torbat-Heydarieh of Iran. For this purpose, a dataset consists of 200 data at three levels of irrigation with well water, industrial wastewater (sugar factory wastewater), a combination of well water and wastewater in two levels (complete irrigation and irrigation with 75 % water stress) and soil characteristics of area were used as input parameters. To achieve this goal, based on the number of data and inputs, 200 barley field experiments data set were used, of which 80 % (160 data) was used for the training and 20 % (40 data) for the testing the network. The results showed that RBF model has high potential in estimating barley yield with Levenberg Marquardt training and 4 hidden layers. Also the values of statistical parameters R2 and RMSE were 0.81 and the 33.12, respectively. In general, the results showed that ANNs model is able to better estimate the barley yield when irrigation water level parameter with well water is selected as input.