Optical monitoring to detect contamination of power grid components
A monitoring system includes an array of optical sensors disposed within a transformer tank. Each optical sensor is configured to have an optical output that changes in response to a temperature within the transformer tank. An analyzer is coupled to the array of optical sensors. The analyzer is configured to determine a sensed temperature distribution based on the sensed temperature. The sensed temperature distribution is compared to an expected distribution. Exterior contamination of the transformer tank is detected based on the comparison.
1. A method, comprising:
exciting a transformer disposed in a fluid-filled transformer tank under different loading conditions;
measuring, for the different loading conditions, a plurality of temperature values using an array of optical sensors disposed at disparate locations within the transformer tank;
generating predicted temperature values using a physics-based model that receives at least ambient temperature at the transformer;
producing a set of estimated parameters using the measured and predicted temperatures;
determining a set of optimized parameters of the physics-based model that could have generated the measured temperature values given the different loading conditions using at least the set of estimated parameters; and
detecting exterior degradation or contamination of the transformer tank using the physics-based model and the set of optimized parameters.
2. The method of claim 1 , wherein generating the predicted temperature values comprises generating the predicted temperatures using the physics-based model that receives ambient temperature and one or more other conditions at the transformer.
3. The method of claim 1 , wherein determining the set of optimized parameters comprises determining the set of optimized parameters using a Bayesian optimization technique.
4. The method of claim 1 , wherein determining the set of optimized parameters comprises determining the set of optimized parameters comprises using input priors indicative of knowledge about the transformer.
5. The method of claim 4 , wherein the input priors are indicative of one or more transformer degradation scenarios.
6. The method of claim 1 , wherein residuals between simulated data and actual data are used to update the set of optimized parameters using Bayesian inference.
7. The method of claim 1 , wherein measuring the plurality of temperature values comprises continuously measuring the plurality of temperature values within the transformer tank.
8. The method of claim 1 , wherein detecting exterior degradation or contamination of the transformer tank comprises detecting one or more of soiling, degradation, and debris on the transformer tank.
9. The method of claim 1 , wherein detecting exterior degradation or contamination of the transformer tank comprises detecting degradation of one or more transformer components other than the transformer tank.
10. The method of claim 1 , wherein detecting exterior degradation or contamination of the transformer tank comprises detecting corrosion of the transformer tank based.
11. A system, comprising:
an array of optical sensors disposed at disparate locations within a fluid-filled transformer tank comprising a transformer, each optical sensor configured to have an optical output that changes in response to a temperature within the transformer tank; and
an analyzer comprising a processor and coupled to the array of optical sensors, the analyzer configured to:
excite the transformer under different loading conditions;
measure, for the different loading conditions, a plurality of temperature values using the array of optical sensors;
generate predicted temperature values using a physics-based model that receives at least ambient temperature at the transformer;
produce a set of estimated parameters using the measured and predicted temperatures;
determine a set of optimized parameters of the physics-based model that could have generated the measured temperature values given the different loading conditions using at least the set of estimated parameters; and
detect exterior degradation or contamination of the transformer tank using the physics-based model and the set of optimized parameters.
12. The system of claim 11 , wherein the analyzer is configured to generate the predicted temperatures using the physics-based model that receives ambient temperature and one or more other conditions at the transformer.
13. The system of claim 11 , wherein the analyzer is configured to determine the set of optimized parameters using a Bayesian optimization technique.
14. The system of claim 11 , wherein the analyzer is configured to determine the set of optimized parameters using input priors indicative of knowledge about the transformer.
15. The system of claim 14 , wherein the input priors are indicative of one or more transformer degradation scenarios.
16. The system of claim 11 , wherein the analyzer is configured to use residuals between simulated data and actual data to update the set of optimized parameters using Bayesian inference.
17. The system of claim 11 , wherein the analyzer is configured to continuously measure the plurality of temperature values within the transformer tank.
18. The system of claim 11 , wherein the analyzer is configured to detect one or more of soiling, degradation, and debris on the transformer tank.
19. The system of claim 11 , wherein the analyzer is configured to detect degradation of one or more transformer components other than the transformer tank.
20. The system of claim 11 , wherein the analyzer is configured to detect corrosion of the transformer tank.