Noise Generation Cause Identification via Microphone Response Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing noise generation cause identification methods in vehicles suffer from reduced accuracy due to variations in microphone models, leading to deviations in frequency responses and inconsistent identification of sound sources.
Innovation Solution
A noise generation cause identifying method and device that corrects the frequency response of sound signals using model information to align with a learning microphone's response, employing multiple response correcting processes and selecting generation causes based on multiple output variables to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sound signals from different microphone models are input directly to the map, then the identification process is simple and fast, but the frequency response varies due to microphone model differences, reducing identification accuracy
Solution Approach 1:
The patent applies preliminary action by performing frequency response correction on sound signals before they are input to the map. The correction process adjusts the frequency response of sound signals from different microphone models to match a reference frequency response, ensuring consistent input quality to the map regardless of the microphone model used. This preliminary processing step resolves the contradiction by preparing the data in advance to eliminate variability.
Solution Approach 2:
The patent applies parameter changes by modifying the frequency response parameter of sound signals based on the microphone model. The system identifies the microphone model and applies corresponding correction parameters to adjust the frequency response, transforming variable inputs into standardized inputs that maintain high identification accuracy while accounting for hardware differences.
2Measurement precision
If frequency response correction is applied to align with the learning microphone, then variations in frequency response are reduced and identification accuracy improves, but the processing time and computational load increase
Solution Approach 1:
The frequency response correction is performed as a preliminary step before map processing, allowing the correction algorithms to be optimized and cached. By preparing correction factors in advance based on microphone model identification, the system reduces real-time computational overhead while maintaining accuracy improvements.
Solution Approach 2:
The system applies pre-determined correction parameters specific to each microphone model, reducing the computational complexity of the correction process. Instead of performing complex real-time adjustments, the system selects and applies predetermined correction factors that have been optimized during system setup, balancing accuracy improvement with processing efficiency.
Data Source
Figure 1
Figure 2
Figure 3(A)~3(B)
AI summary
A noise generation cause identifying method and a noise generation cause identifying device (60) are provided. A response correcting process (S83) corrects a sound signal obtained through a sound signal obtaining process (S41) based on obtained model information so that a frequency response of the obtained sound signal approaches a frequency response of a learning sound signal. A variable obtaining process (S87) obtains a variable (y) output from a map by inputting the corrected sound signal (xa) to the map. A cause identifying process (S89) identifies a generation cause of a sound picked up by a microphone (35) using the variable (y) obtained through the variable obtaining process (S87)(Fig. 5).