Narrow Results

Fault location in distribution networks is a major challenge that needs to be addressed in power distribution systems. Currently, fault location methods based on matrix algorithms, genetic algorithms, deep learning, and other algorithms have received wide attention from the industry. However, such methods have some drawbacks: (1) they require high accuracy in fault information uploads, which can lead to low fault tolerance; (2) they tend to converge early and get stuck in local optimal solutions; (3) they involve high computational complexity, leading to location delays. In this study, we propose a fault location framework based on recurrent neural network (RNN) and transfer learning. In this method, we first encode the information data collected from distribution terminals, and then use RNN to establish a nonlinear mapping relationship between fault features and fault location intervals, which effectively improves fault tolerance and reduces misjudgment issues. We then use transfer learning to load the pre-trained model onto the target task to address the problem of insufficient data for fault location in distribution networks. Experimental results show that after 15 rounds of training, our T-RNN model has achieved over 80% accuracy. Benefiting from Glorot weight initialization adopted after transfer learning, the model achieves good performance early on compared to the BP model, converges faster, and ultimately achieves a prediction accuracy of 96.5%.

With the rapid development of the smart grid, the fast and accurate fault location of low-voltage distribution networks has become the key to ensuring the stability and reliability of the power supply. This paper aims to explore and construct a fault location model of low-voltage distribution network based on an attention diagram neural network. First, this paper analyzes the current situation and challenges of fault location in low-voltage distribution network, and points out that traditional methods have limitations when processing large-scale and high-dimensional power system data. Subsequently, a graph neural network (GNN) is introduced for processing graph-structured network data, and combined with attention mechanisms. Thus, an innovative attention-graph neural network model (named as A-GNN) is proposed for the purpose. The model can make full use of the topology structure and node feature information in the power grid, and dynamically adjust the information aggregation weight between different nodes through the attention mechanism. This is expected to achieve efficient and accurate fault location. In the experimental part, we trained and tested the A-GNN model based on the real low-voltage distribution network dataset, and compared it with several prediction models. The experimental results show that the A-GNN model has higher accuracy and recall rate in fault location tasks, especially in complex fault scenarios.

The task of locating an arcing-fault on overhead line using sampled measurements obtained at a single line terminal could be classified as a practical nonlinear system identification problem. The practical reasons impose the requirement that the solution should be with maximum possible precision. Dynamic behavior of an arc in open air is influenced by the environmental conditions that are changing randomly, and therefore the useful practically application of parametric modeling is out of question. The requirement to identify only one parameter is yet another specific of this problem. The parameter we need is the one that linearly correlates the voltage samples with the current derivative samples (inductance). The correlation between the voltage samples and the current samples depends on the unpredictable arc dynamic behavior. Therefore this correlation is reconstructed using nonparametric regression. A partially linear model combines both, parametric and nonparametric parts in one model. The fit of this model is noniterative, and provides an efficient way to identify (pull out) a single linear correlation from the nonlinear time series.

We propose a method to locate wire faults using a chaotic signal generated by an improved Colpitts oscillator. The chaotic signal is divided into two parts: one serves as a reference signal, and the other serves as a probe signal which is sent down to the wire. The fault is detected by correlating the reference signal with the probe signal back-reflected from the fault. Experimental and numerical studies show that the chaotic signal generated by the improved Colpitts oscillator has a broad spectrum and excellent correlation properties. Using this chaotic signal, we experimentally prove our method can be used to locate open circuits, short circuits, impedance discontinuities and other different damage cases on wires, and also demonstrate its ability for testing live wires through the numerical simulation. The results show that a spatial resolution of 0.2 m and a maximum range of about 930 m can be achieved. Furthermore, the interference margin is about 167 dB for the digital signals such as Mil-Std 1553 data on wire.

The generation and retrieval of comparison-based probabilistic diagnostic data for fault location in homogeneous systems is presented. A distance-based approach avoids the exponential size of a priori test information. The operation-time computation complexity is O(m), where m is the number of links and O(log m) when some prior reference data is stored. Optimizations for hard real-time systems are provided.

The theme of the paper is to emphasize the detection and classification of faults and their site location in the transmission line using machine learning techniques which help to indemnify the foul-up of the humans in identifying the site and type of occurrence of fault. Moreover, the transient stability is a supreme one in power systems and so the disturbances like faults are required to be separated to preserve the transient stability. In general, the protection of the transmission line includes the installation of relays at both ends of the line that constantly monitor voltages and currents and operate unless a fault occurs on a line. Therefore, this paper intends to introduce a novel transmission line protection model by exploiting the hybrid optimization concept to train the Convolutional Neural Network (CNN). Here, the fault detection, classification and site location are diagnosed by using CNN which is trained and tested by making use of diverse synthetic field data derived from the simulation models of distinct types of transmission lines. Hence, the location and the type of faults will be predicted by the CNN depending on the fault signal characteristics which are optimally trained by a new hybrid algorithm named Chicken Swarm Insisted Spotted Hyena (CSI-SH) Algorithm that hybrids both the concept of Spotted Hyena Optimization (SHO) and Chicken Swarm Optimization (CSO). Finally, the proposed method based on CNN for fault classification and site location of transmission lines is implemented in MATLAB/Simulink and the performances are compared with various measures like classification accuracy, fault detection rate and so on.

Once a fault occurs in the nanofiber sensor, the scientific and reliable three-dimensional (3D) human motion detection results will be compromised. It is necessary to accurately and rapidly perceive the fault signals of the nanofiber sensor and determine the type of fault, to enable it to continue operating in a sustained and stable manner. Therefore, we propose a fault signal perception method for 3D human motion detection nanofiber sensor based on multi-task deep learning. First, through obtaining the fault characteristic parameters of the nanofiber sensor, the fault of the nanofiber sensor is reconstructed to complete the fault location of the nanofiber sensor. Second, the fault signal of the nanofiber sensor is mapped by the penalty function, and the feature extraction model of the fault signal of the nanofiber sensor is constructed by combining the multi-task deep learning. Finally, the multi-task deep learning algorithm is used to calculate the sampling frequency of the fault signal, and the key variable information of the fault of the nanofiber sensor is extracted according to the amplitude of the state change of the nanofiber sensor, to realize the perception of the fault signal of the nanofiber sensor. The results show that the proposed method can accurately perceive the fault signal of a nanofiber sensor in 3D human motion detection, the maximum sensor fault location accuracy is 97%, and the maximum noise content of the fault signal is only 5 dB, which shows that the method can be widely used in fault signal perception.

Petri net is an effective tool to analyze the operating rules of the system. Petri net process can reflect the feature of the system fault propagation. Construction and definition method of Petri net fault detection process is presented and the fault performance features in the Petri net process are analyzed. Based on the above research foundation, a method of fault detection and location with Petri net process is presented. Firstly, Petri net model with input and output for fault detection is given. Then fault detection and location method with this model is described in detail. Finally, an example of fault detection in sequential circuit is given to verify the correctness of the method.

This study proposes an automatic fault location approach combining support vector machine. Different from the usual fault localization approach, the support vector machine is applied to classify the program statement into two classes. If there is only one class, the classification probability is used to rank the statements. If a statement has a minimum probability, it will have a maximum probability to be a fault. And empirical results of applying SVM are also presented to locate the fault and compare them against the results of other algorithms for the JTCAS program.