Measurement terminal, measurement system, measurement method, and program

Patent metadata

Field	Value
Publication number	US-11629993-B2
Application number	US-201917255279-A
Country	US
Kind code	B2
Filing date	Mar 13, 2019
Priority date	Jun 27, 2018
Publication date	Apr 18, 2023
Grant date	Apr 18, 2023

Abstract

A measurement terminal includes: a storage that stores, for each of one or more inspection objects, setting information including a parameter related to a feature of an inspection and an abnormality; a processor; and a memory having instructions that, when executed by the processor, cause the processor to perform operations. The operations include: acquiring audio data of sound from an inspection object; deriving, based on the setting information of a corresponding one of the one or more inspection objects, a required time for acquiring the audio data of sound from the inspection object to be used for determining a presence or absence of the abnormality in the inspection object; and determining the presence or absence of the abnormality in the inspection object based on the audio data of sound from the inspection object for the derived required time.

First claim

The invention claimed is:

1. A measurement terminal, comprising:
a storage that stores, for each of one or more inspection objects, setting information comprising a coefficient α based on an inspection schedule and a coefficient β based on an abnormality importance;
a processor; and
a memory having instructions that, when executed by the processor, cause the processor to perform operations, the operations comprising:
determining, based on audio data of sound received from an inspection object, an occurrence of an abnormal sound pattern;
deriving, based on the setting information and for the inspection object, the coefficient α corresponding to the inspection schedule;
deriving, based on the setting information and for the inspection object, the coefficient β corresponding to the abnormality importance;
calculating, based on a predetermined equation and in response to the determining of the occurrence of the abnormal sound pattern, a measurement time Tm for reacquiring the audio data of the sound from the inspection object to be used for determining a presence or absence of a failure in the inspection object; and
determining the presence or the absence of the failure in the inspection object based on the audio data of the sound from the inspection object based on the measurement time Tm,
wherein the coefficient α is a value in a range of 0 to 1,
the coefficient β is a second value, and
the predetermined equation is:
Tm=T 0+α×β,

where T0 is a fixed value set for the inspection object.

2. The measurement terminal according to claim 1 , wherein the operations further comprise:
displaying, on a display, an indication prompting acquisition of the audio data of the sound from the inspection object for the measurement time.

3. The measurement terminal according to claim 1 ,
wherein the setting information comprises the inspection schedule of the inspection object, an abnormality occurrence pattern of the inspection object, and the abnormality importance related to occurrence of the failure in the inspection object.

4. The measurement terminal according to claim 1 ,
wherein the determining the presence or the absence of the failure in the inspection object comprises: sequentially receiving the audio data of the sound from the inspection object as an input, and
wherein the operations further comprise: in a case where the audio data of the sound from the inspection object as the input for the measurement time is input, displaying, on a display, a determination result of the presence or the absence of the failure based on the audio data for the measurement time.

5. The measurement terminal according to claim 4 ,
wherein the operations further comprise:
registering audio data of a normal sound determined as having no abnormality and audio data of an abnormal sound determined as having the abnormality in the memory, and
extending the measurement time in a case where the audio data sequentially received as the input does not match any of the audio data of the normal sound and the audio data of the abnormal sound.

6. The measurement terminal according to claim 1 ,
wherein the calculating the measurement time comprises: adjusting the measurement time so as to lengthen and shorten a length of the measurement time in accordance with an appearance frequency of the audio data of the abnormal sound pattern.

7. The measurement terminal according to claim 1 ,
wherein the presence or the absence of the failure in the inspection object is determined using a learned model generated in advance by machine learning.

8. A measurement system comprising:
a measurement terminal comprising:
a first communication device;
a first processor; and
a first memory having instructions that, when executed by the processor, cause the first processor to perform first operations, the first operations comprising:
acquiring audio data of sound from an inspection object;
transmitting, via the first communication device, the audio data of the sound from the inspection object and an analysis instruction of the audio data;
receiving, via the first communication device, a determination result of a presence or an absence of a failure based on the audio data of the sound from the inspection object; and
displaying the determination result on a display; and

an analysis device comprising:
a storage that stores, for each of one or more inspection objects, setting information comprising a coefficient α based on an inspection schedule and a coefficient β based on an abnormality importance;
a second communication device;
a second processor; and
a second memory having instructions that, when executed by the processor, cause the second processor to perform second operations, the second operations comprising:
receiving, via the second communication device, the audio data of the sound from the inspection object and the analysis instruction from the measurement terminal;
determining, based on the audio data of the sound received from the inspection object, an occurrence of an abnormal sound pattern;
deriving, based on the setting information and for the inspection object, the coefficient α corresponding to the inspection schedule;
deriving, based on the setting information and for the inspection object, the coefficient β corresponding to the abnormality importance;
calculating, based on a predetermined equation and in response to an occurrence of an abnormal sound pattern, a measurement time Tm for reacquiring the audio data of the sound from the inspection object to be used for determining the presence or the absence of the failure in the inspection object;
determining the presence or the absence of the failure in the inspection object based on the audio data of the sound from the inspection object based on the measurement time Tm; and
transmitting, via the second communication device, the determination result to the measurement terminal,

wherein the coefficient α is a value in a range of 0 to 1,
the coefficient β is a second value, and
the predetermined equation is:
Tm=T 0×α×β,

where T0 is a fixed value set for the inspection object.

9. The measurement system according to claim 8 ,
wherein the presence or the absence of the failure in the inspection object is determined using a learned model generated in advance by machine learning.

10. A measurement method, comprising:
acquiring audio data of sound from an inspection object;
accessing a storage that stores, for each of one or more inspection objects, setting information comprising a coefficient α based on an inspection schedule and a coefficient β based on an abnormality importance;
determining, based on the audio data of the sound acquired from the inspection object, an occurrence of an abnormal sound pattern;
deriving, based on the setting information and for the inspection object, the coefficient α corresponding to the inspection schedule;
deriving, based on the setting information and for the inspection object, the coefficient β corresponding to the abnormality importance;
calculating, based on a predetermined equation and in response to the determining of the occurrence of the abnormal sound pattern, a measurement time Tm for reacquiring the audio data of the sound from the inspection object to be used for determining a presence or an absence of a failure in the inspection object; and
determining the presence or the absence of the failure in the inspection object based on the audio data of the sound from the inspection object based on the measurement time Tm,
wherein the coefficient α is a value in a range of 0 to 1,
the coefficient β is a second value, and
the predetermined equation is:
Tm=T 0×α×β,

where T0 is

Assignees

• Panasonic Ip Man Co Ltd

Inventors

• Fujii Ryota

Classifications

• G01H11/06

  by electric means · CPC title

• G01M99/00

  Subject matter not provided for in other groups of this subclass · CPC title

• G01H3/04 Primary

  Frequency · CPC title

• G01H3/005

  Testing or calibrating of detectors covered by the subgroups of G01H3/00 (calibrating geophysical instruments, e.g. seismic receivers G01V13/00) · CPC title

• G01H9/002 Primary

  for representing acoustic field distribution (sonar systems for imaging G01S7/56, G01S15/89; acoustic holography G03H3/00) · CPC title