Power Transformer Temperature Estimation via Model Parameter Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mathematical models for power transformers require a large number of predefined parameters, making them cumbersome and rarely used in practice for modeling power transformer properties due to the significant effort needed to determine these parameters.
Innovation Solution
A device with a signal interface, processor unit, and memory unit that receives sensor data, executes a simulation model to estimate temperature inside the power transformer by optimizing model parameters over time, using predefined reference parameters and recently determined optimization parameters to minimize the squared error between estimated and actual sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If mathematical models with many predefined parameters are used to accurately model power transformer properties, then measurement precision and reliability are improved, but device complexity and the effort needed to determine parameters increase significantly
Solution Approach 1:
The patent extracts only the essential parameters needed for temperature estimation from the complex mathematical models, separating them from the numerous predefined parameters. By focusing on a reduced set of critical parameters (such as thermal conductivity, specific heat capacity, and density of transformer oil), the system achieves accurate temperature monitoring without requiring determination of all parameters in traditional comprehensive models.
Solution Approach 2:
The patent changes the approach from using fixed predefined parameters to dynamically adapting parameters based on operating conditions. The system adjusts thermal parameters according to the transformer's load, ambient temperature, and cooling conditions, allowing accurate temperature estimation with fewer parameters by leveraging real-time operational data.
2Measurement precision
If traditional mathematical models with predefined parameters are used, then measurement precision is improved, but productivity and ease of operation deteriorate due to significant effort required to determine parameters
Solution Approach 1:
The system performs self-calibration by automatically determining thermal parameters from standard transformer specifications and operating data without requiring manual measurement or external calibration procedures. The processor unit automatically extracts necessary parameters from available documentation and adjusts them based on real-time sensor readings, eliminating the need for time-consuming parameter determination by specialists.
Solution Approach 2:
The patent prepares the model parameters in advance by pre-processing transformer specification data and storing baseline thermal properties. This preliminary preparation allows the system to quickly adapt to specific transformer configurations without requiring time-consuming parameter determination during deployment or maintenance.
3Measurement precision
If sensors are installed to directly detect temperature at multiple points, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent introduces a thermal model as an intermediary between available sensor data and the desired temperature information. Instead of directly measuring temperature at multiple critical points with sensors, the system uses a thermal model that calculates temperatures based on measurements from fewer sensors, transforming the measurement problem into a computational problem that requires fewer physical sensors.
Solution Approach 2:
The system creates a virtual thermal model (a digital copy) of the transformer's thermal behavior that replicates the temperature distribution without requiring physical sensors at every location. This virtual model is continuously updated with data from minimal physical sensors, providing comprehensive temperature monitoring through simulation rather than direct measurement.
Data Source
AI summary
A model of a power transformer describes a transfer behavior for input data into output data as a function of model parameters. In successive time windows, measurement dataset is received from first and second sensors of the power transformer. The model parameters are optimized by executing, for each of the time windows, the following group of steps a) to c), repeatedly: a) determining the output of the model using the input data defined by first sensor data, for the first execution of predefined parameters are used; b) determining a target value, which includes at least one squared error, weighted by a first weighting factor, the squared error is between the second sensor data from the measurement dataset assigned to the given time window and a previously determined output data, and c) determining optimization parameters as new model parameters based on the target value.