Abnormal sound detection apparatus and detection method

Patent metadata

Field	Value
Publication number	US-10607632-B2
Application number	US-201916354804-A
Country	US
Kind code	B2
Filing date	Mar 15, 2019
Priority date	Mar 20, 2018
Publication date	Mar 31, 2020
Grant date	Mar 31, 2020

Abstract

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.

First claim

What is claimed is:

1. An apparatus for detecting abnormal sound of a test object, comprising:
a reference sound data recording unit configured to record 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;
a test sound data acquisition unit configured to acquire test sound data having phase and amplitude in the multiple frequency bands from test sounds generated by the test object;
a sound feature data acquisition unit configured to acquire sound feature data 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
an abnormal sound detection unit configured to detect abnormal sound based on the acquired sound feature data.

2. The apparatus according to claim 1 , wherein the abnormal sound detection unit has a conversion unit configured to convert sound feature data acquired by the sound feature data acquisition unit to a sound feature sound signal, and abnormal sound is detected based on the converted sound feature sound signal.

3. The apparatus according to claim 1 , wherein the sound feature data acquisition unit is configured to acquire the sound feature data by changing amplitude of the test sound data based on ratio of amplitude of the test sound data amplitude to amplitude of the reference sound data.

4. The apparatus according to claim 2 , wherein the abnormal sound detection unit has a learning unit configured to perform machine learning of the sound feature sound signal converted by the conversion unit.

5. The apparatus according to 1 , wherein the sound feature data acquisition unit is configured to compare the test sound data and the reference sound data in frequency bands same as frequencies higher than the multiple predetermined frequencies.

6. The apparatus according to claim 1 , wherein the test object is a vehicle.

7. A method for detecting abnormal sound of a test object, comprising the steps of:
recording 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;
acquiring test sound data having phase and amplitude in the multiple frequency bands from test sounds generated by the test object;
acquiring sound feature data 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
detecting abnormal sound based on the acquired sound feature data.

8. The method according to claim 7 , wherein the step of abnormal sound detection has the step of:
converting sound feature data acquired by the step of sound feature data acquisition to a sound feature sound signal, and abnormal sound is detected based on the converted sound feature sound signal.

9. The method according to claim 7 , wherein the step of sound feature data acquisition is configured to acquire the sound feature data by changing amplitude of the test sound data based on ratio of amplitude of the test sound data amplitude to amplitude of the reference sound data.

10. The method according to claim 8 , wherein the step of abnormal sound detection has the step of:
performing machine learning of the sound feature sound signal converted by the step of conversion.

11. The method according to 7 , wherein the step of sound feature data acquisition is configured to compare the test sound data and the reference sound data in frequency bands same as frequencies higher than the multiple predetermined frequencies.

12. The method according to claim 7 , wherein the test object is a vehicle.

13. An apparatus for detecting abnormal sound of a test object, comprising:
an electronic control unit constituted of a microcomputer equipped with at least one processor and at least one memory coupled to the processor;
wherein the processor is configured to:
record 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;
acquire test sound data having phase and amplitude in the multiple frequency bands from test sounds generated by the test object;
acquire sound feature data 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
detect abnormal sound based on the acquired sound feature data.

14. The apparatus according to claim 13 , wherein the processor is configured to convert sound feature data to a sound feature sound signal, and abnormal sound is detected based on the converted sound feature sound signal.

15. The apparatus according to claim 13 , wherein the processor is configured to acquire the sound feature data by changing amplitude of the test sound data based on ratio of amplitude of the test sound data amplitude to amplitude of the reference sound data.

16. The apparatus according to claim 14 , wherein the processor is configured to perform machine learning of the sound feature sound signal.

17. The apparatus according to 3 , wherein processor is configured to compare the test sound data and the reference sound data in frequency bands same as frequencies higher than the multiple predetermined frequencies.

18. The apparatus according to claim 13 , wherein the test object is a vehicle.

Assignees

• Honda Motor Co Ltd

Inventors

• Sudo Yui

Classifications

• G01H17/00

  Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the other groups of this subclass · CPC title

• H04R29/00

  Monitoring arrangements; Testing arrangements {(for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308)} · CPC title

• G01M17/007

  Wheeled or endless-tracked vehicles (G01M17/08 takes precedence) · CPC title

• G06F17/141

  Discrete Fourier transforms · CPC title

• G10L25/18

  the extracted parameters being spectral information of each sub-band · CPC title