ANN-Based Energy Measurement Validation in Gas Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for validating energy measurements in high pressure gas distribution networks are inadequate, leading to potential errors and significant losses due to drift, malfunctioning equipment, and infrequent validation, which can result in inaccurate billing and profit loss.
Innovation Solution
A method and system utilizing an artificial neural network (ANN) engine to calculate validation energy values based on measured parameters such as gross volume, pressure, temperature, and calorific value, with a multilayered perceptron network structure, to compare and validate actual energy values, identifying discrepancies and alerting for potential errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional SCADA systems with infrequent validation (e.g., once every 6 months) are used, then system complexity is reduced, but measurement precision and reliability deteriorate due to undetected errors and drift
Solution Approach 1:
The patent implements continuous feedback validation by comparing actual energy measurements against predicted values generated by an artificial neural network model. The system continuously monitors measurement deviations and triggers alerts when discrepancies exceed predefined thresholds, enabling real-time detection of metering errors, drift, or equipment malfunction without requiring complex validation infrastructure.
Solution Approach 2:
The system employs self-service validation where the artificial neural network model continuously predicts expected energy values based on historical data and system parameters, automatically comparing these predictions against actual measurements. This self-validating mechanism detects anomalies and potential errors autonomously, reducing the need for external validation systems while maintaining high measurement precision.
2Reliability
If validation is performed frequently or continuously, then reliability and error detection improve, but loss of time and computational resources increase
Solution Approach 1:
The patent applies partial validation by focusing computational resources on detecting significant deviations rather than continuously validating every parameter at full precision. The system uses the artificial neural network to predict expected values and only triggers detailed validation checks when deviations exceed predefined thresholds, achieving high reliability for critical errors while minimizing unnecessary computational time and resources.
3Measurement precision
If sophisticated control systems with continuous monitoring are implemented, then measurement precision and reliability improve, but device complexity and cost increase
Solution Approach 1:
The patent introduces an artificial neural network model as an intermediary component that simplifies the validation process. Instead of implementing complex continuous monitoring systems, the neural network predicts expected energy values based on historical data and system parameters, providing a computationally efficient mediator that detects measurement anomalies without requiring sophisticated control infrastructure.
Data Source
AI summary
A method and system for validating energy measurement in a high pressure gas distribution network. The method comprises the steps of calculating a validation energy value using an artificial neural network (ANN) engine based on measured parameters associated with a gas flow in the gas distribution network; measuring an actual energy value of the gas flow; and comparing the validation energy value and the actual energy value, wherein the actual energy value is validated if the validation energy value and the actual energy value are substantially equal.