Abnormal Sound Detection via Phase-Preserving Frequency Band Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic abnormal sound detection technologies face challenges in achieving high accuracy due to the time-averaging effect of Fast Fourier Transform processing, which smooths sound burst sites and makes it difficult to distinguish abnormal sounds from road noise, and the inability to preserve phase differences in FFT data.
Innovation Solution
An abnormal sound detection apparatus and method that record reference sound data with phase and amplitude in multiple frequency bands, acquire test sound data with phase and amplitude, and compare it to the reference data by changing the amplitude of the test sound data based on the reference sound data while maintaining phase, to detect abnormal sounds effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If Fast Fourier Transform processing is used to automatically detect abnormal sound, then automation is achieved, but time-averaging effect smooths sound burst sites making distinction from road noise difficult
Solution Approach 1:
The patent segments the sound detection process into multiple frequency bands and processes each band separately. By dividing the frequency spectrum into discrete bands and analyzing sound bursts in each band independently, the system preserves temporal resolution of sound burst sites while achieving automated detection. This segmentation allows identification of abnormal sounds without the smoothing effect that would occur in full-spectrum FFT processing.
Solution Approach 2:
The patent transitions from time-domain analysis to frequency-domain analysis by dividing the sound spectrum into multiple frequency bands. This dimensional transformation allows the system to detect abnormal sounds based on their frequency characteristics while maintaining temporal precision through band-specific processing, thereby resolving the contradiction between automation and measurement precision.
2Productivity
If FFT data is used for sound analysis, then processing efficiency is improved, but phase difference preservation is impossible
Solution Approach 1:
The patent segments frequency analysis into multiple discrete frequency bands, processing each band separately. This segmentation enables the system to calculate phase differences within each frequency band while maintaining overall processing efficiency. By analyzing phase relationships in segmented frequency domains rather than attempting full-spectrum phase analysis, the system preserves necessary phase information without sacrificing productivity.
Solution Approach 2:
The patent applies local quality analysis by examining phase differences and sound characteristics within specific frequency bands rather than treating the entire frequency spectrum uniformly. This localized approach allows phase difference preservation in relevant frequency ranges while maintaining computational efficiency through selective processing of each frequency band.
Data Source
AI summary
In detecting abnormal sound of a test object such as a vehicle immediately after completion of vehicle assembly, a reference sound data is recorded as reference data having phase and amplitude in each of multiple frequency bands reference sounds of types not previously recorded as abnormal sounds in the test object similar to the test object, test sound data is acquired which has phase and amplitude in the multiple frequency bands from test sounds generated by the test object. And sound feature data is acquires by comparing the test sound data with reference sound data in frequency bands the same as the multiple frequency bands and by changing amplitude of the test sound data based on amplitude of the reference sound data while maintaining phase of the test sound data, and abnormal sound is detected based on the acquired sound feature data.