Search

High-impedance fault (HIF) detection has always been difficult in distribution networks due to the lack of field data and the large difference between field and simulation waveforms. Based on the characteristics of zero-sequence currents, a novel HIF detection methodology is proposed, which combines time–frequency spectrum (TFS) and transfer convolutional neural network (TCNN). First, the TFSs are acquired by applying continuous wavelet transform (CWT) to the collected zero-sequence currents. Then, the TFSs of simulated zero-sequence currents are utilized for training source-domain convolutional neural network (SCNN). Next, the SCNN is transfer learned with very few TFSs of field zero-sequence currents to obtain TCNN. The performance of the proposed method is verified by simulation samples and field samples. The results show that the proposed method can effectively extract fault features from small-scale training samples under different fault circumstances. Besides, TCNN can adaptively extract the effective features of field HIF and detect field HIF more accurately than SCNN. Finally, this article provides a visualization scheme for interpretability of the neural network, which offers visual explanations for the decision-making basis of the neural network.

It is still a huge challenge for data-driven methods to detect high impedance fault (HIF) within limited field fault data. Even more, classification of imbalanced data has encountered a significant degradation in predictive performance since most classifiers were trained with the premise of a relatively balanced distribution. In this paper, a data-driven methodology combined with generative adversarial network (GAN) for HIF detection with imbalanced sample scenarios is proposed. By extending the structure and specializing loss function, the improved GAN (IGAN) can be established to learn the intrinsical probability distribution of raw data and sample new HIF data easily. Adding the high-quality dummy fault data into the original imbalanced training data set, equitable predictive accuracy can be achieved and unbiased classification models are available. Experimental results revealed that the proposed method can generate data subject to target distribution outperformed existing methods. Moreover, the validation results on filed data revealed that the proposed method can detect HIF at around 60 ms with fairly higher accuracy on imbalanced samples compared to mainstream data-driven algorithms.

Designing a neural network using simulation waveforms for high-impedance fault (HIF) detection is a challenging task, particularly in case of applications on distribution networks. Based on the characteristics of HIF transient zero sequence currents (TZSCs), a novel methodology is proposed for HIF detection in the time domain, which includes 1-D variational prototyping-encoder (1-D-VPE) and decision tree (DT) algorithm. The proposed HIF detection scheme consists of four steps: First, the TZSCs collected from simulations are applied to train the 1-D-VPE neural network, whose encoder is used as the feature extractor. Then, the extracted features are utilized to train the DT classifier. After that, the well-trained encoder and DT are employed to test field TZSCs. Finally, the 1-D-VPE neural network is fine-tuned with some of the field TZSCs. The performance of the proposed method is analyzed using waveform samples collected from the PSCAD/EMTDC simulation platform and the actual distribution networks. The results show that the proposed method provides good classification performances on both simulation and field data at high noise levels without transformation between different domains, and the classification accuracy can be improved by fine-tuning with some field TZSCs.

Given the rapid expansion of car ownership worldwide, vehicle safety is an increasingly critical issue in the automobile industry. The reduced cost of cameras and optical devices has made it economically feasible to deploy front-mounted intelligent systems for visual-based event detection. Prior to vehicle event detection, detecting vehicles robustly in real time is challenging, especially conducting detection process in images captured by a dynamic camera. Therefore in this study, a robust vehicle detector is developed. The proposed contribution is three-fold. Road modelling is first proposed to confine detection area for maintaining low computation complexity and reducing false alarms as well. Haar-like features and eigencolours are then employed for the vehicle detector. To tackle the occlusion problem, chamfer distance is used to estimate the probability of each individual vehicle. Consequently, to find the bounding box of vehicle candidate, the authors take the configuration of a normalised chamfer distance map that corresponds to the maximum score as the target using exponential entropy. Experiments on an extensive dataset show that the proposed system can effectively detect vehicles under different lighting and traffic conditions, and thus demonstrates its feasibility in real-world environments.

In this paper, a framework of automatic human action segmentation and recognition in continuous action sequences is proposed. A star figure enclosed by a bounding convex polygon is used to effectively represent the extremities of the silhouette of a human body. The human action, thus, is recorded as a sequence of the star-figure's parameters, which is used for action modeling. To model human actions in a compact manner while characterizing their spatio-temporal distributions, the star-figure's parameters are represented by Gaussian mixture models (GMM). In addition, to address the intrinsic nature of temporal variations in a continuous action sequence, we transform the time sequence of star-like figure parameters into frequency domain by discrete cosine transform (DCT) and use only the first few coefficients to represent different temporal patterns with significant discriminating power. The performance shows that the proposed framework can recognize continuous human actions in an efficient way.