Distribution Transformer Ageing Prediction Under Variable Loading
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The impact of additional loading on the ageing of distribution transformers is not accurately reconciled, affecting distribution system efficiency, and human forecasting of this impact is tedious and prone to missing critical load criteria, leading to potential malfunctions and breakdowns.
Innovation Solution
A distribution network manager utilizing machine learning, specifically an ensemble learning algorithm, integrates static and dynamic transformer data, maintenance, inspection, and weather data to predict distribution network integrity and autonomously adjust operations to optimize transformer age forecasting, accommodating real-time changes and flexibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If human forecasting methods are used to assess transformer ageing impact, then the process is simple and easy to perform, but the accuracy is low and critical load criteria may be missed
Solution Approach 1:
The patent replaces manual human forecasting methods with an automated machine learning system that processes transformer data. The ML model automatically evaluates static and dynamic transformer parameters, maintenance records, and operational data to predict ageing impact, eliminating human error while maintaining system usability through automated decision support.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between raw transformer data and forecasting decisions. This intermediary processes and analyzes multiple data sources (static parameters, dynamic operational data, maintenance records) to generate accurate ageing predictions, bridging the gap between complex data and actionable insights.
2Measurement precision
If comprehensive data collection and machine learning models are implemented, then forecasting accuracy improves, but computational resources and system complexity increase
Solution Approach 1:
The patent performs preliminary data processing and feature extraction during data collection phases, preparing data in advance for the machine learning model. By pre-processing static transformer data, dynamic operational data, and maintenance records before prediction, the system reduces the computational burden during actual forecasting operations.
Solution Approach 2:
The patent implements a tiered data collection approach where the ML model processes comprehensive data sets for critical predictions while using simplified data subsets for routine assessments. This partial action strategy balances accuracy requirements with computational resource constraints, avoiding unnecessary processing of all possible data parameters in every prediction scenario.
Data Source
AI summary
A method includes obtaining static transformer data for a first transformer. The method includes obtaining dynamic transformer data for the first transformer. The method includes obtaining inspection transformer data regarding the first transformer. The method includes obtaining first maintenance data regarding the first transformer. The method includes obtaining first weather data regarding the first transformer. The method includes determining, by a computer processor, predicted distribution network integrity data using a first machine-learning model and the static transformer data, the dynamic transformer data, the inspection transformer data, the first maintenance data, and the first weather data. The first machine-learning model is trained using an ensemble learning algorithm. The method includes determining a transformer operation based on the predicted distribution network integrity data and transmitting a command to a control system coupled to the first transformer. The transformer operation is performed using the control system in response to receiving the command.