公开(公告)号：US20210256991A1

公开(公告)日：2021-08-19

申请号：US17173946

申请日：2021-02-11

Applicant: Purdue Research Foundation

Inventor： Martin Byung-Guk Jun ,  Hanjun Kim

IPC: G10L25/51 ,  G10L25/18 ,  H04R1/08 ,  G10L25/30 ,  G06N3/08

Abstract: A system and methods for machine anomaly and behavior classification is provided. An audio capture device may attach to a mechanical apparatus comprising a first component and a second component. The first component and second component may separately generate audible noise. The capture device may include a body, a diagraph disposed in the body, and a microphone. The diagraph may vibrate in response to sound generated by the mechanical device. The microphone may generate a signal in response audio caused by the vibrating diagram. The system may receive the signal generated by the microphone of the audio capture device. The system may determine, based on a machine learning model and the signal, an anomalous event associated with the first component, a second component, or a combination thereof. Alternatively, or in addition, the system may classify operation of the machine based on second machine learning model.

公开(公告)号：US20230078351A1

公开(公告)日：2023-03-16

申请号：US17948680

申请日：2022-09-20

Applicant: Purdue Research Foundation

Inventor： Martin Byung-Guk Jun ,  Hanjun Kim

IPC: G10L25/51 ,  G10L25/18 ,  G06N3/08 ,  G10L25/30 ,  H04R1/08

Abstract: A system and methods for machine anomaly and behavior classification is provided. An audio capture device may attach to a mechanical apparatus comprising a first component and a second component. The first component and second component may separately generate audible noise. The audio capture device may generate a signal in response audio caused by the vibrating diagram. The system may receive the signal generated by the microphone of the audio capture device. The system may determine, based on a machine learning model and the signal, an anomalous event associated with the first component, a second component, or a combination thereof. Alternatively, or in addition, the system may classify operation of the machine based on second machine learning model.

公开(公告)号：US11475910B2

公开(公告)日：2022-10-18

申请号：US17173946

申请日：2021-02-11

Applicant: Purdue Research Foundation

Inventor： Martin Byung-Guk Jun ,  Hanjun Kim

IPC: H04R29/00 ,  G10L25/51 ,  G10L25/18 ,  G06N3/08 ,  G10L25/30 ,  H04R1/08

Abstract: A system and methods for machine anomaly and behavior classification is provided. An audio capture device may attach to a mechanical apparatus comprising a first component and a second component. The first component and second component may separately generate audible noise. The capture device may include a body, a diagraph disposed in the body, and a microphone. The diagraph may vibrate in response to sound generated by the mechanical device. The microphone may generate a signal in response audio caused by the vibrating diagram. The system may receive the signal generated by the microphone of the audio capture device. The system may determine, based on a machine learning model and the signal, an anomalous event associated with the first component, a second component, or a combination thereof. Alternatively, or in addition, the system may classify operation of the machine based on second machine learning model.

公开(公告)号：US11688415B2

公开(公告)日：2023-06-27

申请号：US17948680

申请日：2022-09-20

Applicant: Purdue Research Foundation

Inventor： Martin Byung-Guk Jun ,  Hanjun Kim

IPC: G10L25/51 ,  G10L25/18 ,  G06N3/08 ,  G10L25/30 ,  H04R1/08

CPC classification number: G10L25/51 ,  G06N3/08 ,  G10L25/18 ,  G10L25/30 ,  H04R1/08

Abstract: A system and methods for machine anomaly and behavior classification is provided. An audio capture device may attach to a mechanical apparatus comprising a first component and a second component. The first component and second component may separately generate audible noise. The audio capture device may generate a signal in response audio caused by the vibrating diagram. The system may receive the signal generated by the microphone of the audio capture device. The system may determine, based on a machine learning model and the signal, an anomalous event associated with the first component, a second component, or a combination thereof. Alternatively, or in addition, the system may classify operation of the machine based on second machine learning model.