Infrastructure Pipe Attribute Imputation via Network Topology

Solution Overview

Problem

Infrastructure information, such as installation year, material, and dimensions, is often outdated due to poor record keeping and changes over time, making it costly and time-consuming to identify and maintain infrastructure components, particularly for buried elements, which are difficult to access.

Innovation Solution

A method to impute attribute information for infrastructure elements based on known attribute information from other elements, using a computer system that receives location and attribute data, determines adjacency, and imputes missing information for pipes and supply-side structures, reducing the need for manual collection and verification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual collection and verification of infrastructure information is performed, then accuracy of infrastructure data is improved, but time and cost increase significantly

Engineering Contradiction:

Improveaccuracy of infrastructure dataVSAvoidtime for data collection

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent creates a virtual copy of the infrastructure network model and uses it to impute missing attribute information. Instead of manually visiting each infrastructure element to collect data, the system copies known attributes from similar elements in the virtual model to fill gaps, dramatically reducing time while maintaining data accuracy through systematic imputation based on network topology and historical patterns.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The infrastructure information system performs self-service by automatically imputing missing attributes using its own stored data and network models. The system uses known attributes from similar infrastructure elements to infer and fill in missing information autonomously, eliminating the need for manual data collection efforts while maintaining data quality through algorithmic imputation.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If manual collection and verification of infrastructure information is performed, then accuracy of infrastructure data is improved, but cost increases significantly

Engineering Contradiction:

Improveaccuracy of infrastructure dataVSAvoidresource allocation

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent creates a virtual copy of the infrastructure network model and uses it to impute missing attribute information. Instead of manually visiting each infrastructure element to collect data, the system copies known attributes from similar elements in the virtual model to fill gaps, dramatically reducing time while maintaining data accuracy through systematic imputation based on network topology and historical patterns.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The infrastructure information system performs self-service by automatically imputing missing attributes using its own stored data and network models. The system uses known attributes from similar infrastructure elements to infer and fill in missing information autonomously, eliminating the need for manual data collection efforts while maintaining data quality through algorithmic imputation.

Inventive Principle:

Principle #25Self-service

3Measurement precision

If infrastructure information is updated manually, then data accuracy is maintained, but productivity of maintenance operations decreases

Engineering Contradiction:

Improvedata accuracyVSAvoidmaintenance operation efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system implements feedback mechanisms where imputed attribute information is used to update the virtual infrastructure network model, which then feeds back into maintenance prioritization decisions. This continuous feedback loop ensures data accuracy is maintained while enabling faster, more efficient maintenance operations by automatically identifying critical infrastructure elements based on updated attribute information.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary actions by pre-processing and organizing infrastructure data into a virtual network model with established relationships and patterns. This preliminary structuring enables rapid imputation of missing attributes during maintenance operations without requiring manual data collection, thus maintaining data accuracy while significantly improving operational productivity.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20240386393A1Methods of Imputing Attribute Information for Infrastructure Elements

Publication Date: 2024.11.21 FRACTA

AI summary

An electronic device receives attribute information for a first plurality of pipes, a second plurality of pipes, and a plurality of supply-side structures. The attribute information for the first plurality of pipes includes, for each pipe, location information and a value for a characteristic. The attribute information for the second plurality of pipes includes, for each pipe, location information, and does not include values for the characteristic. The attribute information for the plurality of supply-side structures includes location information. The electronic devices determines, for each respective pipe of the second plurality of pipes, unknown attribute information, including: determining, based on the attribute information for the plurality of supply-side structures and location information for the respective pipe, an adjacent pipe connected to the respective pipe; and determining, based on a respective value for the characteristic for the adjacent pipe, a value for the characteristic for the respective pipe.