Monitoring apparatus and method

• US 8,831,233 B2
• Filed: 03/22/2012
• Issued: 09/09/2014
• Est. Priority Date: 09/28/2009
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Hosaka, Rika, Ouchi, Kazushige, Imoto, Kazunori, Ootomi, Koichi, Kikuchi, Masaaki
• Primary Examiner(s): Zhang, Leshui
• Application Number:
  US13/427,133
• Publication Number:
  US 20120219157A1
• Time in Patent Office: 901 Days
• Field of Search: 381/56, 381/57, 381/58, 381/92, 381/100, 381/101, 381/102, 381/103, 381/120, 381/124, 700/94, 73/18.2, 735/84, 735/85, 735/86, 735/87, 736/48, 736/59, 736/61, 738/611.8
• US Class Current: 381/56
• CPC Class Codes: G01H 3/08 Analysing frequencies present in complex vibrations, e.g. comparing harmonics present acoustic presence detection G01V1/001
• CPC Class Codes: G01H 7/00 Measuring reverberation time ; room acoustic measurements

Abstract

According to one embodiment, a monitoring apparatus includes an acquisition unit, an analysis unit, a calculation unit, a storage, a determination unit. The acquisition unit acquires an environmental sound. The analysis unit performs frequency analysis to extract characteristic frequency components. The calculation unit calculates first values of metrics. The storage stores contour data generated by second values of the metrics. The determination unit determines whether or not there is a first measurement point in which a first value and a second value match, if there is no first measurement point or the change is not less than the threshold value, determines that the machines is abnormal.

Claims

1. A monitoring apparatus, comprising:

an acquisition unit configured to acquire an environmental sound in measurement points within a space in which one or more machines to be measured are present to produce an environmental sound signal;

an analysis unit configured to perform frequency analysis by sampling the environmental sound signal, to extract characteristic frequency components of the machines, each of the characteristic frequency components being a frequency component with the highest sound pressure level in frequency components included in operating sounds of the machines;

a calculation unit configured to calculate a first value of metrics in the measurement points based on the sound pressure levels of the characteristic frequency components, the metrics indicating at least one index for determining difference of sound quality;

a storage to store contour data items generated by connecting a second value of the metrics in the measurement points, the second values being pre-calculated according to an operational state of the machines; and

a determination unit configured to determine whether or not there is a first measurement point in which the first value and the second value match,

if there is the first measurement point and change of the first value is less than a threshold value, determine that the operational state of the machines is normal,

if there is no first measurement point or the change is not less than the threshold value, determine that the operational state of at least one of the machines is abnormal, and

if the first value stays constant for a certain period, determine that at least one of a user and the machines is abnormal in status.

2. The apparatus according to claim 1, wherein the calculation unit calculates loudness and sharpness as the metrics.

3. The apparatus according to claim 2, wherein the calculation unit further calculates roughness, variation intensity and impulsiveness as the metrics.

4. A monitoring apparatus, comprising:

an acquisition unit configured to acquire an environmental sound in measurement points within a space in which one or more machines to be measured are present to produce an environmental sound signal;

an analysis unit configured to perform frequency analysis by sampling the environmental sound signal, to extract characteristic frequency components of the machines, each of the characteristic frequency components being a frequency component with the highest sound pressure level in frequency components included in operating sounds of the machines, and to obtain a first value of the sound pressure level in the measurement points;

a storage to store contour data items generated by connecting a second value of the sound pressure level in the measurement points, the second value being pre-calculated according to an operational state of the machines; and

a determination unit configured to determine whether or not there is a first measurement point in which the first value and the second value match,

if there is the first measurement point and change of the first value is less than a threshold value, determine that the operational state of the machines is normal,

if there is no first measurement point or the change is not less than the threshold value, determine that the operational state of at least one of the machines is abnormal, and

if the first value stays constant for a certain period, determine that at least one of a user and the machines is abnormal in status.

5. A monitoring method, comprising:

acquiring an environmental sound in measurement points within a space in which one or more machines to be measured are present to produce an environmental sound signal;

performing frequency analysis by sampling the environmental sound signal, to extract characteristic frequency components of the machines, each of the characteristic frequency components being a frequency component with the highest sound pressure level in frequency components included in operating sounds of the machines;

calculating a first value of metrics in the measurement points based on the sound pressure levels of the characteristic frequency components, the metrics indicating at least one index for determining difference of sound quality;

storing, in a storage, contour data items generated by connecting a second value of the metrics in the measurement points, the second values being pre-calculated according to operational states of the machines; and

determining whether or not there is a first measurement point in which the first value and the second value match,

if there is the first measurement point and change of the first value is less than a threshold value, determining that the operational state of the machines is normal,

if there is no first measurement point or the change is not less than the threshold value, determining that the operational state of at least one of the machines is abnormal, and

if the first value stays constant for a certain period, determining that at least one of a user and the machines is abnormal in status.

6. The method according to claim 5, wherein the calculating the first value calculates loudness and sharpness as the metrics.

7. The method according to claim 6, wherein the calculating the first value further calculates roughness, variation intensity and impulsiveness as the metrics.