UAV Active Noise Abatement Using Predictive Anti-Noise Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aerial vehicles (UAVs) generate noise during operations that can be annoying or deafening to humans and animals, and existing noise reduction methods are inadequate for effectively mitigating these sounds in various environmental conditions.
Innovation Solution
The implementation of a system that captures and correlates environmental and operational data with acoustic energy data to train a machine learning system, which predicts noise levels and generates anti-noises to cancel out the effects of the predicted noises, thereby reducing the overall sound emitted by the UAV.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If traditional passive noise reduction methods are used, then noise levels are reduced to some extent, but the methods are inadequate for effectively mitigating noises in various environmental conditions
Solution Approach 1:
The patent implements dynamic noise cancellation by continuously adapting the anti-noise signal generation based on real-time environmental conditions and operational parameters. The system transitions from static passive noise reduction to active dynamic cancellation that adjusts to varying flight conditions, frequencies, and environmental factors, thereby resolving the contradiction between noise reduction effectiveness and adaptability to various environmental conditions
Solution Approach 2:
The system changes key parameters including sound pressure levels, frequencies, and phase angles of anti-noise signals based on detected noise characteristics and environmental conditions. By dynamically adjusting these acoustic parameters, the system achieves effective noise mitigation across diverse operational scenarios, resolving the limitation of fixed-parameter passive noise reduction methods
2Object-affected harmful factors
If active noise control systems are implemented, then noise cancellation effectiveness is improved, but the system complexity increases
Solution Approach 1:
The patent employs feedback mechanisms where noise detectors continuously monitor the acoustic environment and feed this information to the control system. The system processes this feedback in real-time to generate appropriate anti-noise signals, creating a closed-loop control system that achieves effective noise cancellation while managing complexity through intelligent feedback processing rather than overly complex hardware architectures
Solution Approach 2:
The system replaces complex mechanical noise isolation structures with electronic and software-based active noise control mechanisms. By using electronic signal processing, machine learning algorithms, and computational methods to generate anti-noise signals, the system achieves effective noise cancellation with reduced mechanical complexity compared to traditional passive acoustic isolation approaches
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
This approach effectively shapes the aggregate sounds emitted by UAVs, significantly reducing noise levels perceived by humans and animals through the use of anti-noises tailored to specific environmental and operational conditions, enhancing noise abatement efficiency.
Implementation Method 1
An anti-noise to counteract the predicted noise may be determined in real time or near real time as the aerial vehicle is en route. The anti-noise may be emitted from one or more sound emitters provided on the aerial vehicle.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
Noises that are to be emitted by an aerial vehicle (1210) during operations may be predicted using one or more machine learning systems, algorithms or techniques. Anti-noises having equal or similar intensities and equal but out-of-phase frequencies may be identified and generated based on the predicted noises, thereby reducing or eliminating the net effect of the noises. The machine learning systems, algorithms or techniques used to predict such noises may be trained using emitted sound pressure levels observed during prior operations of aerial vehicles, as well as environmental conditions, operational characteristics of the aerial vehicles or locations of the aerial vehicles during such prior operations. Anti-noises may be identified and generated based on an overall sound profile of the aerial vehicle, or on individual sounds emitted by the aerial vehicle by discrete sources.