Search

The reliable operation of power systems becomes a formidable job these days due to the high amount of complexities in the expanded power system networks. The power system networks often comprise microgrids that encounter over 80% of faults due to their exposure to unpredictable weather conditions, which reduce the insulation strength of the conductors which damaged the distribution system. Therefore, detection, classification, and location of such faults in the distributing systems are a must to ensure the flawless operation of the power systems. Machine learning methodologies are getting more attention to detect these types of faults due to their capability to handle complex fault information. Nevertheless, the obstacles are even now on the board as the traditional machine learning techniques rely on oversimplified frameworks that are incapable of analyzing a wide range of latent and explicit parameters and are also time-consuming. In this work, a unique defect diagnosis technique based on a multiblock deep belief network (DBN) and the fundamental discrete wavelet transform (DWT) is proposed, allowing the architecture to identify the deterministic reconstructing throughout its inputs. This method enables a strong multilevel generative network to utilize fault-related properties, decodes high variability functionalities, and requires minimal previous knowledge. The suggested approach is validated using a wide set of input data at various sampling frequencies. To evaluate the efficiency of DBN, a benchmark methodology based on the International Electrotechnical Commission (IEC) standard was used. White Gaussian Noise (WGN) was also implemented to test the envisioned network's resilience. The findings show that the approach is capable of executing exact diagnosis procedures. [ABSTRACT FROM AUTHOR]

Although the use of a series capacitor increases the transmission line (TL) capacity, it inverts the voltage/current and creates a sub-harmonic frequency that results in unintended operation of the protection devices, which further decreases the transient stability under fault conditions. Restoring the transient stability requires an accurate diagnosis of faults in TLs, which further requires exploration of in-depth features. This imposes challenges for the existing approaches as they demand a large amount of data. In this paper, a self-attentive weight-sharing capsule network (WSCN) is proposed to achieve robust and high classification performance while utilizing a limited amount of data. The capsule network, with the weight-sharing mechanism delivers robust performance in detecting and classifying the faults in the TL domain. Simultaneously, the self-attention layer highlights the more dominant features that make the network work upon the limited data effectively. A Western-System-Coordinating-Council WSCC 9-bus and 3-machine test model, which was modified with the series capacitor was studied to quantify the robustness of the self-attention WSCN. The results were compared with those of others networks to confirm the explicit classification ability of the proposed network. A study on real-world data obtained from power network was also conducted to validate the proposed self-attention WSCN. [ABSTRACT FROM AUTHOR]

With the expansion of the modern power system, it is of increasing significance to analyze the faults in the transmission lines. As the transmission line is the most exposed element of a power system, it is prone to different types of environmental as well as measurement uncertainties. This uncertainties influence the sampled signals and negatively affects the fault detection and classification performance. Therefore, an unsupervised deep learning framework named deep belief network is presented in this paper for fault detection and classification of power transmission lines. The proposed framework learns the beneficial feature information from the uncertainty affected signals with a unique two stage learning strategy. This strategy enables the proposed framework to extract lower level fault-oriented information which may remain unobserved for other alternative approaches. The efficacy of the proposed framework has been examined on the IEEE-39 bus benchmark topology. The in-depth accuracy assessment with different accuracy metrics along with exclusive case studies such as the influence of noise, measurement error as well as line and source parameter variations will be conducted in this paper to justify the real-world applicability of the proposed framework. Furthermore, the relative performance assessment with the cutting-edge rival techniques is also presented in this paper to verify if the proposed framework attains a state-of-the-art classification performance or not. [Display omitted] • Deep learning-based framework is proposed for transmission line fault analysis. • Environmental uncertainty is used to measure the robustness of the proposed DL method. • System uncertainty is also studied to observe the proposed DL framework. • Measurement uncertainty is modeled in terms of partially non-existent data. • The result is compared with state-of-the-art approaches to confirm high performance. [ABSTRACT FROM AUTHOR]

• Proposed an intelligent approach for transmission line fault analysis based on capsule network. • An unsupervised model is developed which requires no manual labeling of the data. • The performance against line parameter variation and high impedance faults is assessed. • Noises are considered to justify the robustness of the proposed approach. • The performance is compared with the baseline capsule network and existing approaches. Detection and classification of transmission line (TL) faults are key factors for the fault root cause analysis and rapid restoration of the power network. Deep learning can extract representative features automatically from big data, thus becoming an important breakthrough in fault analysis. Existing deep learning-based fault diagnosis models rely on a large number of data obtained from a variety of fault conditions to be generalized. Indeed, in the TL domain, it is difficult to define and, therefore to collect the fault incepted features of all possible fault scenarios. This paper proposes an unsupervised framework for fault detection and classification (FDC) of TL based on a capsule network (CN). Instead of using the baseline CN, an extension to this with a sparse filtering technique is adopted in this work. The capsule network with sparse filtering (CNSF) voluntarily learns the expensive fault features and significantly improves the model performance without involving a large number of data. The proposed scheme receives 1 / 2 cycle post-fault three-phase signals and encodes them into a single image that is defined as the input for the proposed CNSF model. The effectiveness of the proposed CNSF model is corroborated by four different TL topology confirming the model's adaptability to a topology change in response to intended control action or the switching actions due to cascading faults. Further assessment of the model's performance against noise, high impedance faults (HIF), and line parameter variations are also carried out in order to confirm the high reliability of the proposed model. In addition, a rigorous comparative study is conducted to guarantee the state-of-the-art performance of the proposed model. [ABSTRACT FROM AUTHOR]

• Development of a new approach for transmission line faults detection and classification based on the convolutional neural network combined with wavelet transform which makes the network to efficiently train and extract the relevant features from the three phase faulty data. • Integration of the self attention mechanism with proposed CNN to identify the particular type of fault more accurately that enables the model to perform the precise classification. • Variation of input signals like voltage signal, current signal, and combined with voltage and current signal are employed at various sampling frequency to verify the performance of proposed model. • Noises are considered to prepare the input data to confirm the robustness of proposed SAT-CNN model. • Performance comparison between proposed and some other state-of-the-art model is done to confirm the high performance of proposed SAT-CNN model. This paper introduces a novel self-attention convolutional neural network (SAT-CNN) model for detection and classification (FDC) of transmission line faults. The transmission lines continuously experience the number of shunt faults and its effect in the practical system rises the instability, line restoration cost and damages the load. Therefore, a robust and precise model is needed to detect and classify the faults for the rapid restoration of faulty phases. In this paper, we propose a SAT-CNN framework with time series imaging based feature extraction model for FDC of a transmission line. To ensure the noise immunity performance, the discrete wavelet transform (DWT) has been used to denoise the faulty voltage and current signals. The effectiveness of the proposed SAT-CNN framework is tested by varying the input signals namely voltage, current, and combined voltage and current signal, under the various sampling frequencies. The robustness of the proposed model is verified by adding the noises to the input data. Results show that the proposed model is capable to perform precise classification and detection of transmission line faults with high accuracy. A comparison between the proposed and other state-of-the-art FDC model is also studied to show the superiority of the proposed SAT-CNN model. [ABSTRACT FROM AUTHOR]