Drone Audio Fault Detection Using Graph Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manual troubleshooting of device faults in the spinning process is labor-intensive due to the complexity and length of the process, necessitating an automated fault detection method.
Innovation Solution
An audio-based device fault detection method using a drone to collect audio data, preprocess it, extract features, construct an information graph, and utilize a graph neural network model for fault detection, enabling real-time monitoring and automatic fault identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual troubleshooting method is used for device fault detection, then detection accuracy can be maintained through human expertise, but labor intensity increases and detection efficiency decreases
Solution Approach 1:
The patent replaces manual mechanical troubleshooting with an automated audio-based detection system. A drone equipped with audio sensors collects sound data from spinning devices, and a graph neural network model automatically analyzes the audio features to detect faults, substituting human expertise with an automated intelligent system that maintains detection accuracy while dramatically improving efficiency
Solution Approach 2:
The system enables devices to self-diagnose faults through automated audio analysis. The graph neural network model processes audio features extracted from device sounds and automatically identifies fault conditions without requiring manual intervention, allowing the system to perform self-monitoring and self-detection
2Ease of operation
If manual troubleshooting method is used for device fault detection, then complex fault analysis can be performed through human judgment, but human resources are heavily consumed
Solution Approach 1:
The patent replaces human judgment and analysis with an automated graph neural network model that processes audio features. The model constructs information graphs from audio data and automatically identifies fault patterns, substituting human cognitive capabilities with an intelligent algorithm that requires no human resources for actual fault detection
Solution Approach 2:
The patent introduces audio features and information graphs as intermediary representations between the physical device and the detection system. The graph neural network model uses these intermediaries to translate complex audio signals into interpretable fault diagnoses, enabling automated analysis without direct human involvement
Data Source
AI summary
Provided is an audio-based device fault detection method, an electronic device, and a storage medium, relating to the field of data processing and in particular to technical fields of deep learning and voice technology. The method includes: obtaining initial audio data collected by a drone for a target device; preprocessing the initial audio data to obtain audio data to be detected; performing feature extraction on the audio data to be detected to obtain an audio feature of the audio data to be detected; constructing an information graph based on the audio feature; and obtaining a fault detection result for the target device based on the information graph and a graph neural network model.