Microphone Array Localization of Impact Hotspots in Machinery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively detect and spatially localize high impact soundwaves in complex industrial machinery, leading to inefficiencies in predictive maintenance due to transient, non-stationary, and wideband sound signals, and conventional methods result in high localization errors.
Innovation Solution
A method and system using a microphone array to record sound signals, apply filtering, perform eigenvalue decomposition, and determine a spatial power matrix to project a localization map, identifying impact hotspots on machinery surfaces with reduced RMSE through targeted steering vectors and spatial power matrix evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional two-stage separate networks are used for sound event detection and direction-of-arrival estimation, then the system avoids multi-objective problems, but the system complexity and overall network size increase
Solution Approach 1:
The patent combines sound event detection and direction-of-arrival estimation into a single unified neural network model. The network simultaneously processes audio signals to detect multiple overlapping sound events and estimate their directional information in one integrated framework, eliminating the need for separate two-stage networks while reducing overall system complexity
2Measurement precision
If microphone arrays are placed inside industrial machinery for runtime inspection, then detection capability is improved, but the system becomes intrusive and requires shutdown for setup
Solution Approach 1:
The patent replaces contact-based mechanical sensing with acoustic field-based detection using microphone arrays positioned outside the machinery. The system captures impact-induced sound waves propagating through the air and structure-borne sound, enabling non-intrusive monitoring of internal machinery conditions without requiring physical sensor installation inside the equipment
Solution Approach 2:
The patent uses the machinery's own structure and surrounding air as acoustic waveguides to transmit impact sound signals from internal sources to external microphones. The housing and structural components act as intermediaries that conduct acoustic energy from impact events to the external sensing array, enabling remote detection without direct internal sensor placement
3Adaptability or versatility
If existing sound detection methods are applied to complex machinery, then general sound events can be detected, but high impact soundwaves in transient and wideband conditions cannot be effectively localized
Solution Approach 1:
The patent employs adaptive parameter adjustment in the neural network to handle transient and wideband impact sounds. The system dynamically adjusts frequency weighting, time-window parameters, and spectral analysis settings based on the detected sound characteristics, enabling precise localization of high-impact events while maintaining versatility across different sound types and operational conditions
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
Accurately localizes impact sound sources with less than 10% RMSE, enabling effective predictive maintenance by identifying wear zones in industrial machinery without contact-based sensing.
Implementation Method 1
placing a microphone array at different locations within the machinery to record a sound signal
Implementation Method 2
The the time windowed sound signal is filtered by applying filtering (308) to obtain a filtered sound signal based on (i) a sliding narrow band pass filter of central frequency f, (ii) a frequency range between a spectral response of impact type, and (iii) a band distance
Implementation Method 3
The method performs an eigenvalue decomposition over a covariance matrix of the filtered sound signal s(t) FILT to determine a noise subspace
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
This disclosure relates generally to method and system for unobtrusive spatial localization and detection of impact induced soundwaves. Runtime localization of surface wear zones in industrial machines has been a daunting problem in the domain of predictive maintenance. The method disclosed provides spatial localization of impacts soundwaves generated to locate the wearzones. The method processes the sound signal from the microphone array occurred surface of target of interest of the machinery. The sound signal is processed to identify one or more impact hotspots on the target surface of the machinery by searching one or more peaks. Finally, exact location of occurred impact sound from the one or more impact hotspots is localized and is projected on the machinery.