Exciter Current Voltage Regression for Flashover Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electric machine systems fail to effectively predict and prevent flashover conditions, which can lead to costly and time-consuming repairs due to undetected wear, breaks in the field winding, improper insulation, or other issues.
Innovation Solution
A monitoring system that measures current and voltage from an exciter to a generator, creates a regression model from sampled data, and generates an alarm when predicted parameters deviate significantly from expected values, allowing for real-time monitoring and prevention of flashovers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional monitoring methods are used for electric machines, then the system structure remains simple, but flashover conditions cannot be predicted and prevented in real-time
Solution Approach 1:
The system performs preliminary actions by continuously collecting exciter current and voltage data, creating regression models in advance, and calculating predicted parameters before flashover conditions occur. This allows the system to predict potential failures proactively rather than reactively, maintaining reliability while managing complexity through preventive modeling.
Solution Approach 2:
The system implements feedback by comparing predicted parameters against actual measured parameters in real-time. When deviations exceed predetermined thresholds, the system generates alarms and provides feedback signals. This closed-loop feedback mechanism enables continuous monitoring and prediction capability without requiring overly complex manual intervention systems.
2Reliability
If real-time monitoring and prediction systems are implemented, then flashover conditions can be predicted and prevented, but the device complexity and cost increase
Solution Approach 1:
The system applies self-service by using the exciter's own current and voltage measurements to predict flashover conditions. The regression models are created and updated automatically using the machine's operational data itself, eliminating the need for external complex monitoring infrastructure. This self-service approach reduces overall system complexity while maintaining reliable flashover prediction capability.
3Measurement precision
If comprehensive monitoring of current and voltage parameters is performed, then prediction accuracy improves, but data processing requirements and computational load increase
Solution Approach 1:
The system extracts and focuses on the most critical parameters (exciter current and voltage) that directly influence flashover prediction. Rather than monitoring all possible electrical parameters, the regression models are specifically designed to use only these essential measurements, reducing computational load while maintaining high prediction accuracy for the specific failure mode being prevented.
Data Source
AI summary
A system for predicting a condition includes an electric machine having slip rings and an exciter providing current and voltage to the electric machine through the slip rings. The system also includes a monitoring device that measures the current and voltage provided by the exciter to the electric machine and that forms a regression model from a current sample and compares values from a next sample to values predicted by the regression model.