An official website of the United States government
The high impedance fault (HIF) has random, irregular and unsymmetrical characteristics, making such a fault difficult to detect in distribution grids via conventional relay measurements with relatively low resolution and accuracy. This paper proposes a stochastic HIF monitoring and location scheme using high-resolution time-synchronized data in μ-PMUs for distribution network protection. Specifically, we systematically design a process based on feature selections, semi-supervised learning (SSL), and probabilistic learning for fault detection and location. For example, a wrapper method is proposed to leverage output data in feature selection to avoid overfitting and reduce communication demand. To utilize unlabeled data and quantify uncertainties, an SSL-based method is proposed using the Information Theory for fault detection. For location, a probabilistic analysis is proposed via moving window total least square based on the probability distribution of the fault impedance. For numerical validation, we set up an experiment platform based on the real-time simulator, so that the real-time property of μ-PMU can be examined. Such experiment shows enhanced HIF detection and location, when compared to the traditional methods.
more »
« less
Mining Partially Labeled Data from Edge Devices to Detect and Locate High Impedance Faults
The security of active distribution systems is critical to grid modernization along with deep renewable penetration, where the protection plays a vital role. Among various security issues in protection, conventional protection clears only 17.5% of staged high impedance faults (HIFs) due to the limited electrical data utilization. For resolving this problem, a detection and location scheme based on μ-PMUs is presented to enhance data processing capability for HIF detection through machine learning and big data analytics. To detect HIFs with reduced cost on data labeling, we choose expectation-maximization (EM) algorithm for semi-supervised learning (SSL) since it is capable of expressing complex relationships between the observed and target variables by fitting Gaussian models. As one of the generative models, EM algorithm is compared with two discriminative models to highlight its detection performance. To make HIF location robust to HIF impedance variation, we adopt a probabilistic model embedding parameter learning into the physical line modeling. The location accuracy is validated at multiple locations of a distribution line. Numerical results show that the proposed EM algorithm greatly saves labeling cost and outperforms other SSL methods. Hardware-in-the-loop simulation proves a superior HIF location accuracy and detection time to complement the HIF's probabilistic model. With outstanding performance, we develop software for our utility partner to integrate the proposed scheme.
more »
« less
- Award ID(s):
- 1810537
- PAR ID:
- 10189312
- Date Published:
- Journal Name:
- 2019 IEEE Sustainable Power and Energy Conference (iSPEC)
- Page Range / eLocation ID:
- 2170 to 2175
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
High impedance faults present unique challenges for power system protection engineers. The first challenge is the detection of the fault, given the low current magnitudes. The second challenge is to locate the fault to allow corrective measures to be taken. Corrective actions are essential as they mitigate safety hazards and equipment damage. The problem of high impedance fault detection and location is not a new one, and despite the safety and reliability implications, relatively few efforts have been made to find a general solution. This work presents a hybrid data driven and analytical-based model for high impedance fault detection in distribution systems. The first step is to estimate a state space model of the power line being monitored. From the state space model, eigenvalues are calculated, and their dynamic behavior is used to develop zones of protection. These zones of protection are generated analytically using machine learning tools. High impedance faults are detected as they drive the eigenvalues outside of their zones. A metric called eigenvalue drift coefficient was formulated in this work to facilitate the generalization of this solution. The performance of this technique is evaluated through case studies based on the IEEE 5-Bus system modeled in Matlab. Test results are encouraging indicating potential for real-life applications.more » « less
-
Abstract Insect pests cause significant damage to food production, so early detection and efficient mitigation strategies are crucial. There is a continual shift toward machine learning (ML)‐based approaches for automating agricultural pest detection. Although supervised learning has achieved remarkable progress in this regard, it is impeded by the need for significant expert involvement in labeling the data used for model training. This makes real‐world applications tedious and oftentimes infeasible. Recently, self‐supervised learning (SSL) approaches have provided a viable alternative to training ML models with minimal annotations. Here, we present an SSL approach to classify 22 insect pests. The framework was assessed on raw and segmented field‐captured images using three different SSL methods, Nearest Neighbor Contrastive Learning of Visual Representations (NNCLR), Bootstrap Your Own Latent, and Barlow Twins. SSL pre‐training was done on ResNet‐18 and ResNet‐50 models using all three SSL methods on the original RGB images and foreground segmented images. The performance of SSL pre‐training methods was evaluated using linear probing of SSL representations and end‐to‐end fine‐tuning approaches. The SSL‐pre‐trained convolutional neural network models were able to perform annotation‐efficient classification. NNCLR was the best performing SSL method for both linear and full model fine‐tuning. With just 5% annotated images, transfer learning with ImageNet initialization obtained 74% accuracy, whereas NNCLR achieved an improved classification accuracy of 79% for end‐to‐end fine‐tuning. Models created using SSL pre‐training consistently performed better, especially under very low annotation, and were robust to object class imbalances. These approaches help overcome annotation bottlenecks and are resource efficient.more » « less
-
This paper presents a domain-guided approach for learning representations of scalp-electroencephalograms (EEGs) without relying on expert annotations. Expert labeling of EEGs has proven to be an unscalable process with low inter-reviewer agreement because of the complex and lengthy nature of EEG recordings. Hence, there is a need for machine learning (ML) approaches that can leverage expert domain knowledge without incurring the cost of labor-intensive annotations. Self-supervised learning (SSL) has shown promise in such settings, although existing SSL efforts on EEG data do not fully exploit EEG domain knowledge. Furthermore, it is unclear to what extent SSL models generalize to unseen tasks and datasets. Here we explore whether SSL tasks derived in a domain-guided fashion can learn generalizable EEG representations. Our contributions are three-fold: 1) we propose novel SSL tasks for EEG based on the spatial similarity of brain activity, underlying behavioral states, and age-related differences; 2) we present evidence that an encoder pretrained using the proposed SSL tasks shows strong predictive performance on multiple downstream classifications; and 3) using two large EEG datasets, we show that our encoder generalizes well to multiple EEG datasets during downstream evaluations.more » « less
-
Automated segmentation of grey matter (GM) and white matter (WM) in gigapixel histopathology images is advantageous to analyzing distributions of disease pathologies, further aiding in neuropathologic deep phenotyping. Although supervised deep learning methods have shown good performance, its requirement of a large amount of labeled data may not be cost-effective for large scale projects. In the case of GM/WM segmentation, trained experts need to carefully trace the delineation in gigapixel images. To minimize manual labeling, we consider semi-surprised learning (SSL) and deploy one state-of-the-art SSL method (FixMatch) on WSIs. Then we propose a two-stage scheme to further improve the performance of SSL: the first stage is a self-supervised module to train an encoder to learn the visual representations of unlabeled data, subsequently, this well-trained encoder will be an initialization of consistency loss-based SSL in the second stage. We test our method on Amyloid-β stained histopathology images and the results outperform FixMatch with the mean IoU score at around 2% by using 6,000 labeled tiles while over 10% by using only 600 labeled tiles from 2 WSIs.Clinical relevance— this work minimizes the required labeling efforts by trained personnel. An improved GM/WM segmentation method could further aid in the study of brain diseases, such as Alzheimer’s disease.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/iSPEC48194.2019.8974897
