Partial Discharge Defect Recognition With Adaptive ISODATA Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for identifying partial discharge defects in electrical systems, such as ISODATA clustering, require manual definition of cluster numbers, leading to unsatisfactory accuracy in defect type recognition.
Innovation Solution
An apparatus and method that utilizes power and potential transducers to acquire electrical measurements, applies ISODATA and CLARANS partitioning to correlate and cluster electrical characteristics, and calibrates defect indexes using Z-score normalization to enhance defect recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If ISODATA clustering method is used for pattern recognition, then the processing speed is improved, but the measurement precision of defect identification deteriorates due to manual definition of cluster numbers
Solution Approach 1:
The system performs self-calibration by automatically determining optimal cluster numbers through iterative testing with standard samples. The defect identification system calibrates itself by comparing test results against known defect patterns, eliminating the need for manual cluster number definition while maintaining high processing speed through automated parameter optimization.
Solution Approach 2:
The system dynamically adjusts cluster number parameters based on the specific defect types being detected. Instead of using fixed manual parameters, the system modifies clustering parameters adaptively during operation, allowing the same ISODATA algorithm to achieve high precision across different defect scenarios by automatically optimizing parameter settings.
2Device complexity
If manual definition of cluster numbers is used, then the device complexity is reduced, but the reliability of defect testing outcomes deteriorates
Solution Approach 1:
The system performs preliminary calibration using standard defect samples before actual defect detection. By pre-establishing accurate cluster configurations through calibration with known defect patterns, the system ensures reliable testing outcomes without requiring complex real-time parameter adjustments during actual defect identification.
Solution Approach 2:
The system incorporates feedback mechanisms where test results are continuously compared against calibration data, and cluster parameters are automatically adjusted based on detection accuracy. This closed-loop feedback ensures high reliability by continuously optimizing the clustering parameters based on actual performance rather than relying solely on manual configuration.
Data Source
AI summary
A method for pattern recognition of a partial discharge defect type includes, by resolving the degree of correlation between respective electrical characteristics during operating, synchronously obtaining criticality indexes of the electrical characteristics based on the resolved degree, synchronously obtaining numerical lines of individual electrical characteristics based on the continuous, non-interrupted characteristic of operating of the electrical loads under test, and calibrating the numerical partial discharge defect index obtained using the ISODATA method based on the numerical probability. The correctness of the partial discharge defect test value is enhanced, the partial discharge defect of the corresponding electrical load under test can be identified in real time when the electrical load under test is operating, whereby the electrical characteristic information of the electrical load under test is obtained more intuitively, and, based on real-time analysis of the test values, the operational performance of the electrical load under test can be maintained.