Blocked Meter Detection Using Synthetic Variables
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting blocked communicating meters in distribution networks are inefficient and unreliable, leading to prolonged periods of unaccounted consumption, as manual analysis is time-consuming and often incorrect, and systematic verification is costly due to the low proportion of blocked meters among those without consumption.
Innovation Solution
A method that calculates an index value based on cumulative consumption data, transmitted regularly to a central unit, where differences in index values are used to determine a stopping period, and synthetic variables are generated to autonomously detect blocked meters using a supervised automatic learning module, specifically a decision tree forest method, to classify meters as blocked or non-blocked.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual analysis is used to determine blocked meters, then reliability of detection is improved, but time consumption increases significantly
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated computer-based detection system that processes meter data automatically. The system uses software algorithms to analyze consumption patterns and identify blocked meters without human intervention, thereby reducing time consumption while maintaining detection reliability through systematic automated verification.
Solution Approach 2:
The system enables self-service detection where the automated system performs its own analysis of meter data without requiring manual intervention. The computer system independently processes consumption indices, identifies anomalies, and determines blocked meters through automated algorithms, allowing the system to serve itself rather than requiring manual analysis.
2Reliability
If systematic verification of all meters with no consumption is performed, then detection reliability is improved, but cost increases due to the low proportion of blocked meters
Solution Approach 1:
The patent segments the verification process by first filtering meters based on specific criteria (such as consumption patterns, meter type, and historical data) to identify a subset of potential blocked meters. This segmentation allows the system to focus verification resources on the most likely candidates rather than systematically verifying all meters with no consumption, thereby reducing overall cost while maintaining detection reliability.
Solution Approach 2:
The system applies different verification strategies to different types of meters based on their specific characteristics and risk profiles. By analyzing local qualities such as meter age, consumption history, and operational patterns, the system can prioritize verification efforts on meters most likely to be blocked, optimizing the balance between detection reliability and verification cost.
3Measurement precision
If the minimum threshold value for significant consumption is set low, then detection sensitivity is improved, but false positives increase
Solution Approach 1:
The patent implements feedback mechanisms where the system continuously monitors and analyzes consumption data, comparing detected anomalies against historical patterns and established criteria. The feedback loop allows the system to adjust its detection thresholds and verification processes based on actual meter behavior patterns, reducing false positives while maintaining high detection sensitivity through iterative refinement of detection parameters.
Data Source
Figure 1~3
Figure 2
AI summary
The invention relates to a method for detecting blocked meters (20) for metering the use of a resource, such as water, gas or electricity, among a group of meters (20); each meter calculating an index value depending on the measured cumulative use; comprising, for each stopped meter: - a step of acquiring (11) the index values stored over a second preset period prior to the last stop date (T0) of the meter (20); - a step of generating (12) a plurality of synthetic variables (Vn) depending on the index values acquired for the second preset period, and - a decision step (13) during which it is determined, depending on the calculated synthetic variables, whether the meter is blocked.