Vehicle-Mounted Sensor Infrastructure Anomaly Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional infrastructure inspection methods are time-consuming, inefficient, and unable to provide timely notifications of anomalies, often resulting in outdated reports and increased repair costs due to manual inspections and lack of real-time data analysis.

Innovation Solution

A cognitive-based system utilizing imaging and motion sensors mounted on vehicles to collect and compare current data against historical data, automatically detecting anomalies and triggering notifications when predefined thresholds are exceeded, thereby facilitating timely corrective actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual inspection by employees is used, then infrastructure conditions can be assessed, but the process becomes extremely time-consuming and inefficient

Engineering Contradiction:
Improveinfrastructure condition assessmentVSAvoidinspection efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual mechanical inspection with an automated system using vehicles equipped with imaging sensors (cameras), motion sensors (accelerometers, gyroscopes), and GPS receivers. These sensors automatically capture and transmit data about infrastructure conditions, eliminating the need for manual inspection while maintaining assessment accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables infrastructure to be inspected through self-reporting mechanisms. As vehicles travel along infrastructure, their sensors automatically detect and report anomalies without human intervention. The system processes data autonomously, generating reports and notifications automatically, making the inspection process self-sufficient.

Inventive Principle:
Principle #25Self-service

2Loss of information

If manual inspection methods are used, then infrastructure data can be collected, but the reports become outdated and not reflective of current state

Engineering Contradiction:
Improvecurrent state informationVSAvoidreport generation time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system implements continuous monitoring as vehicles continuously travel through infrastructure regions. Sensors constantly capture data, and the system continuously processes this information, ensuring that infrastructure status is always current. This eliminates the periodic gaps inherent in manual inspection schedules.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The system immediately processes sensor data and provides feedback through automated notifications when anomalies are detected. The feedback loop from data collection to anomaly detection to notification occurs in real-time, ensuring that current state information is promptly communicated without delay.

Inventive Principle:
Principle #23Feedback

3Reliability

If conventional inspection methods are used, then infrastructure monitoring can be performed, but repair costs increase due to delayed anomaly detection

Engineering Contradiction:
Improveanomaly detection accuracyVSAvoidmaintenance cost
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary detection of infrastructure anomalies before they become critical failures. By continuously monitoring and detecting issues early in their development, the system enables preventive maintenance actions that are less costly than emergency repairs of failed infrastructure.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The automated notification system provides immediate feedback when anomalies are detected, triggering timely responses. This rapid feedback loop ensures that repairs are initiated promptly, preventing minor issues from escalating into major problems that would require more expensive repairs.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS11157741B2Determining the state of infrastructure in a region of interest
Publication Date: 2021.10.26 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US11157741B2 patent drawing
  • US11157741B2 patent drawing
  • US11157741B2 patent drawing

AI summary

A method includes confirming when a vehicle accesses a region of interest, obtaining data associated within the region of interest, and determining, based on analytics performed on the data obtained of the region of interest, whether one or more anomalies are present at the region of interest. Obtaining data includes at least one of collecting, with an imaging sensor associated with the vehicle, image data of a given point of interest within the region of interest or collecting, with a motion sensor associated with the vehicle, motion data of the vehicle in a given fragment of interest within the region of interest. The confirming, obtaining and determining steps are performed by at least one processing device comprising a processor operatively coupled to a memory.