High Impedance Fault Detection Using Feature Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for high impedance fault (HIF) detection in power distribution systems are ineffective due to reliance on simple thresholds and lack of a systematic procedure for feature selection, leading to inadequate detection of HIFs, especially with low fault currents and varying scenarios.
Innovation Solution
A systematic design for HIF detection using a logic-based detector that extracts power features such as active and reactive power, employs discrete Fourier transform for harmonic analysis, and integrates Kalman Filter-based harmonics to determine fault occurrence, duration, and magnitude, with a feature ranking procedure to balance information gain and complexity, thereby improving detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional relay methods with simple thresholds are used for HIF detection, then the device complexity is low, but the detection precision and reliability are insufficient
Solution Approach 1:
The detection system segments the feature extraction process into distinct modules: discrete Fourier transform for frequency analysis, wavelet transform for time-frequency analysis, and mathematical morphology for signal processing. Each module extracts specific features from the current signal, allowing systematic analysis without overwhelming complexity
Solution Approach 2:
The system dynamically selects and weights different features based on their relevance to HIF detection. The feature selection process adapts to different fault scenarios by evaluating feature importance metrics, allowing the system to optimize detection precision while managing complexity through adaptive feature weighting
2Reliability
If comprehensive feature extraction using multiple signal processing techniques is implemented, then the detection reliability improves, but the device complexity and computational burden increase
Solution Approach 1:
The system performs preliminary feature extraction using discrete Fourier transform, wavelet transform, and mathematical morphology to generate a comprehensive set of candidate features before detection. This preliminary action organizes the complex feature space in advance, making the subsequent detection process more reliable while managing computational complexity through structured feature organization
Solution Approach 2:
The system extracts specific power features (active power, reactive power, apparent power) and their derivatives from the comprehensive feature set. This extraction focuses on the most relevant features for HIF detection, separating essential detection features from less important ones, thereby improving reliability while controlling system complexity
3Productivity
If feature selection is omitted to simplify the system, then the device complexity is reduced, but the detection accuracy and information utilization are insufficient
Solution Approach 1:
The system implements feedback through feature selection and weighting mechanisms that evaluate the importance of each extracted feature. By analyzing the contribution of individual features to HIF detection accuracy, the system provides feedback to optimize the feature set, improving detection accuracy while managing complexity through intelligent feature selection based on feature importance metrics
Data Source
AI summary
Effective feature set-based high impedance fault (HIF) detection is provided. Systems, methods and devices described herein present a systematic design of power feature extraction for HIF detection and classification. For example, power features associated with HIF events are extracted according to when a fault happens, how long it lasts, and the magnitude of the fault. Complementary power expert information is also integrated into feature pools. In another aspect, a ranking procedure is deployed in a feature pool for balancing information gain and complexity in order to avoid over-fitting of features. In aspects described herein, a logic-based HIF detector implements HIF feature extraction. To determine when an HIF occurs, the HIF detector calculates different quantities, such as active power and reactive power, based on a voltage and current time series, and uses the derivative of these quantities to tell when there is a potential change due to HIF.