UAV Diagnostic Path Planning via ROI Length Change Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Diagnosing facility systems, such as solar and wind power generation systems, is difficult due to their large size and remote locations, making it challenging to accurately detect and capture images of specific parts using drones without precise location information.

Innovation Solution

An apparatus and method for determining a diagnostic path using an unmanned aerial vehicle (UAV) that includes a communication module, processor, and object recognition model to detect regions of interest (ROI) in X-ray images, identifying changes in ROI lengths, and determining flight directions for effective diagnosis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If drones are used to capture images of facility systems in wide areas, then the ability to diagnose remote facilities is improved, but the difficulty of accurately detecting specific diagnosis parts increases when location information is missing or changed

Engineering Contradiction:

Improveability to diagnose remote facilitiesVSAvoiddifficulty of detecting diagnosis parts

Core Design Contradiction:

Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent replaces GPS-based mechanical location tracking with an image-based object recognition system. The server apparatus uses object recognition models to detect diagnosis parts in images captured by drones, substituting the mechanical GPS localization system with an optical recognition system that can identify parts regardless of location data accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an image-based intermediary system between the drone and the diagnosis part. Instead of directly locating parts using GPS coordinates, the system captures images as an intermediary step, then uses object recognition models to identify diagnosis parts within those images, creating a mediating layer that overcomes GPS limitations.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If multiple images are captured to ensure detection of diagnosis parts, then detection accuracy is improved, but the time and effort required for diagnosis increases

Engineering Contradiction:

Improvedetection accuracy of diagnosis partsVSAvoidtime required for diagnosis

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary action by pre-training object recognition models with facility system images and diagnosis part locations before actual diagnosis operations. This preliminary training enables the system to quickly identify diagnosis parts in new images without requiring extensive manual analysis, reducing diagnosis time while maintaining accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback through the server apparatus that receives images from drones, automatically analyzes them using object recognition models, and provides guidance on where to capture next. This automated feedback loop reduces manual intervention time and enables faster iterative diagnosis compared to manual image analysis.

Inventive Principle:

Principle #23Feedback

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables accurate detection and diagnosis of facility parts within facility systems by controlling UAV flight paths based on X-ray image analysis, without relying on GPS or additional location data, improving efficiency and accuracy in diagnosing complex structures.

Implementation Method 1

a first unmanned aerial vehicle provided with an X-ray generator; a second unmanned aerial vehicle provided with an X-ray detector; the server apparatus acquires an X-ray image which is based on emission of the X-ray generator and generated by the X-ray detector

Methodology Applied

Scientific EffectX-ray emission: X-Ray

Data Source

PatentUS20250314496A1Apparatus and method for determining diagnostic path and facility diagnostic system

Publication Date: 2025.10.09 ELECTRONICS & TELECOMM RES INST

AI summary

Provided is an apparatus for determining a diagnostic path, the apparatus including: a communication module; and a processor, wherein the processor acquires an image related to a diagnostic target and captured by an unmanned aerial vehicle unit through the communication module, detects a region of interest (ROI) including an object of interest from the acquired image through an object recognition model, identifies a change in length of ROIs between a rotational image of the acquired image and the acquired images, and determines a flight direction of the unmanned aerial vehicle unit for photographing the object of interest based on the identified change in length.