Acoustics based anomaly detection in machine rooms

Patent metadata

Field	Value
Publication number	US-9892744-B1
Application number	US-201715430771-A
Country	US
Kind code	B1
Filing date	Feb 13, 2017
Priority date	Feb 13, 2017
Publication date	Feb 13, 2018
Grant date	Feb 13, 2018

Abstract

Monitoring a plurality of machines located in an operating environment. First and second acoustic signal readings and their respective detecting locations are received from a sensing device. First and second acoustic signal spatialization map containing characteristic data signatures for the machines are generated based on the first and second acoustic signal readings. One or more differences are determined that exceed a predetermined threshold value, between corresponding characteristic data signatures in each of the first and second acoustic signal spatialization maps. At least one of the machines that are associated with the determined differences is identified. A corrective action to perform on the machine is identified, based on the determined one or more differences. Commands are transmitted to a corrective action module in the operating environment to cause the corrective action module to perform the corrective action.

First claim

What is claimed is:

1. A method for monitoring a plurality of machines located in an operating environment, the method comprising:
receiving, from a sensing device over a network to a computing system, a first acoustic signal readings and their respective detecting locations;
generating, by the computing system, a first acoustic signal spatialization map containing characteristic data signatures, based on the first acoustic signal readings and their respective detecting locations, each of the characteristic data signatures being associated with one or more of the plurality of machines;
receiving, from the sensing device over the network to the computing system, a second acoustic signal readings and their respective detecting locations;
generating, by the computing system, a second acoustic signal spatialization map containing characteristic data signatures, based on the second acoustic signal readings and their respective detecting locations, each of the characteristic data signatures being associated with one or more of the plurality of machines;
determining, by the computing system, that there are one or more differences, that exceed a predetermined threshold value, between one or more characteristic data signatures in the first acoustic signal spatialization map and corresponding one or more characteristic data signatures in the second acoustic signal spatialization map;
identifying at least one of the plurality of machines that are associated with the determined differences;
identifying, by the computing system, a corrective action to perform on a machine of the plurality of machines, based on the determined one or more differences in the generated first and second acoustic signal spatialization maps; and
transmitting, by the computing system, to a corrective action module in the operating environment, commands to cause the corrective action module to perform the identified corrective action.

2. The method of claim 1 , further comprising:
taking, by one or more sensors of the sensing device at a first time and at a first plurality of locations in the operating environment, first acoustic signal readings of acoustic emissions emitted by the plurality of machines, and transmitting the first acoustic signal readings to the computing system; and
taking, by the one or more sensors of the sensing device at a second time and at a second plurality of locations in the operating environment, second acoustic signal readings of acoustic emissions emitted by the plurality of machines, and transmitting the second acoustic signal readings to the computing system.

3. The method of claim 1 , further comprising:
executing, by the corrective action module, the corrective action on the machine of the plurality of machines.

4. The method of claim 1 , wherein the sensing device is a device selected from a group consisting of: a smart phone, a sound level meter, and a sound dosimeter.

5. The method of claim 2 , wherein the one or more sensors include at least one sensor selected from a group comprising: a piezoelectric sensor, a capacitive sensor, a fiber optic sensor, and a microelectrical mechanical system sensor.

6. The method of claim 2 , wherein
taking, by one or more sensors of the sensing device at the first time and at the first plurality of locations in the operating environment, and taking, by one or more sensors of the sensing device at the second time and at the second plurality of locations in the operating environment, further comprises:
mounting the sensing device to a mobile platform and positioning and orienting the sensing device at the first and second plurality of locations by the mobile platform.

7. The method of claim 1 , wherein the first acoustic signal reading detecting locations comprise between 6 and 60 locations, and the second acoustic signal reading detecting locations comprises two or more locations.

8. The method of claim 1 , wherein generating, by the computing system, the first acoustic signal spatialization map and the second acoustic signal spatialization map further comprises:
generating, by the computing system, the characteristic data signatures by performing one or more from a group consisting of: transforms, sparse approximation algorithms, and statistical measurements.

9. The method of claim 8 , wherein
the one or more transforms is selected from a group consisting of: Laplace transform, Fourier transform (FT), fast Fourier Transform (FFT), discrete Fourier transform (DFT), discrete sine transform (DST), discrete cosine transform (DCT), discrete wavelet transform (DWT), Mel-frequency cepstrum (MFC), Mel-frequency cepstral coefficients (MFCCs), linear prediction cepstral coefficients (LPCCs), and analog-to-information (ATI);
the one or more sparse approximation algorithms is selected from a group consisting of: matching pursuit, basis pursuit, and orthogonal matching pursuit; and
the one or more statistical measurements is selected from a group consisting of: short-time energy, short-time average zero-crossing rate, and time-domain harmonics amplitudes.

10. A computer system for monitoring a plurality of machines located in an operating environment, the computer system comprising:
one or more computer processors, one or more computer-readable storage media, and program instructions stored on one or more of the computer-readable storage media for execution by at least one of the one or more processors, the program instructions, when executed by the at least one of the one or more processors, causing the computer system to perform a method comprising:
receiving, from a sensing device over a network to a computing system, a first acoustic signal readings and their respective detecting locations;
generating, by the computing system, a first acoustic signal spatialization map containing characteristic data signatures, based on the first acoustic signal readings and their respective detecting locations, each of the characteristic data signatures being associated with one or more of the plurality of machines;
receiving, from the sensing device over the network to the computing system, a second acoustic signal readings and their respective detecting locations;
generating, by the computing system, a second acoustic signal spatialization map containing characteristic data signatures, based on the second acoustic signal readings and their respective detecting locations, each of the characteristic data signatures being associated with one or more of the plurality of machines;
determining, by the computing system, that there are one or more differences, that exceed a predetermined threshold value, between one or more characteristic data signatures in the first acoustic signal spatialization map and corresponding one or more characteristic data signatures in the second acoustic signal spatialization map;
identifying at least one of the plurality of machines that are associated with the determined differences;
identifying, by the computing system, a corrective action to perform on a machine of the plurality of machines, based on the determined one or more differences in the generated first and second acoustic signal spatialization maps; and
transmitting, by the computing system to a corrective action module in the operating environment, commands to cause the corrective action module to perform the identified corrective action.

11. The computer system of claim 10 , wherein the method further comprises:
taking, by one or more sensors of the sensing device at a first time and at a first plurality of locations in the operating environment, first acoustic signal readings of acoustic emissions emitted by the plurality of machines, and transmitting the first acoustic sig

Assignees

• IBM

Inventors

• Salonidis Theodoros
• Verma Dinesh C
• Wood Iii David A

Classifications

• G05B23/0237

  based on parallel systems, e.g. comparing signals produced at the same time by same type systems and detect faulty ones by noticing differences among their responses · CPC title

• G10L25/51 Primary

  for comparison or discrimination · CPC title

• G10L21/10

  Transforming into visible information · CPC title

• G10L25/03

  characterised by the type of extracted parameters · CPC title

• G05B19/406

  characterised by monitoring or safety (G05B19/19 takes precedence) · CPC title