Surface Failure Prediction Using Persistent Grid Movement Patterns

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies struggle to accurately predict surface failures such as landslides, avalanches, and rockfalls due to limitations in monitoring and analyzing geomaterial movements, leading to delayed or inadequate warnings.

Innovation Solution

A method involving a network of nodes associated with grid elements on a surface, using closeness centrality and pattern recognition to identify potential surface failures by analyzing movement data, generating alerts when risk thresholds are exceeded, and utilizing synthetic datasets for enhanced prediction accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional monitoring methods are used to detect surface failures, then the system is simple to operate, but the prediction accuracy is insufficient and warnings are delayed

Engineering Contradiction:
Improveprediction accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The surface is divided into multiple grid elements, each with associated nodes that independently track movement patterns. This segmentation allows localized analysis of geomaterial movements while maintaining overall system coherence, improving prediction accuracy without requiring a complete system redesign

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a network dimension by creating nodes and connections between grid elements based on closeness centrality. This transforms the traditional 2D surface monitoring into a 3D network structure where relationships between adjacent movements are captured, enhancing prediction capability while adding a manageable layer of complexity

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If more measurement data is collected to improve prediction reliability, then the prediction reliability improves, but the data processing complexity increases

Engineering Contradiction:
Improveprediction reliabilityVSAvoiddata processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts only the most relevant features from measurement data by calculating closeness centrality values and identifying interface sets. Instead of processing all raw measurement data, the system extracts key structural relationships between grid elements, maintaining high prediction reliability while reducing processing complexity

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary processing by pre-calculating closeness centrality values and identifying potential interface sets before actual failure detection. This preliminary structuring of data relationships enables faster, more reliable predictions without requiring complex real-time processing of all measurement parameters

Inventive Principle:
Principle #10Preliminary action

3Area of stationary object

If the monitoring coverage area is expanded to detect larger surface failures, then the detection capability improves, but the false alarm rate increases due to noise from non-critical movements

Engineering Contradiction:
Improvemonitoring coverage areaVSAvoidfalse alarm rate
Core Design Contradiction:
Area of stationary objectVSLoss of information

Solution Approach 1:

The patent applies different analytical treatments to different regions of the monitored surface by identifying interface sets with persistent patterns. Critical regions showing consistent movement patterns across multiple datasets receive focused analysis, while isolated noise events in other regions are filtered out, maintaining high detection capability across large areas while reducing false alarms

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system uses feedback from multiple measured datasets to validate movement patterns. By requiring persistence of interface sets across multiple time points and using closeness centrality to weight the importance of different grid elements, the system distinguishes between critical failure patterns and non-critical noise, reducing false alarms while maintaining broad monitoring coverage

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3616178B1Method for prediction of a surface event
Publication Date: 2025.08.06 UNIVERSITY OF MELBOURNE
  • EP3616178B1 patent drawingFigure 1
  • EP3616178B1 patent drawingFigure 2
  • EP3616178B1 patent drawingFigure 3

AI summary

Methods and systems for predicting surface failure of a surface, for example a method comprising the steps of: obtaining a group of measured datasets, each including: a measurement value of at least a first type for each of a plurality of grid elements, each grid element associated with a location on the surface; and a time value, such that the group of datasets includes datasets associated with a plurality of unique time values, identifying an interface set of grid elements for each measured dataset, each interface set comprising grid elements of the associated measured dataset meeting a connection threshold according to a connection rule in dependence on the measurement values of the grid elements, determining a risk of surface failure in accordance with identification of a pattern of grid elements of the interface set which has a persistent location with respect to the surface of interface sets over a plurality of measured datasets.