UNDERCARRIAGE WEAR PREDICTION BASED ON MACHINE VIBRATION DATA
원문보기
IPC분류정보
국가/구분
United States(US) Patent
공개
국제특허분류(IPC7판)
G07C-005/00
G07C-005/08
G06F-017/14
출원번호
16949450
(2020-10-29)
공개번호
20220139118
(2022-05-05)
발명자
/ 주소
ZHANG, Li
XU, Yingbiao
출원인 / 주소
Caterpillar Inc.
인용정보
피인용 횟수 :
0인용 특허 :
0
초록▼
A system may include a device. The device may be configured to receive machine vibration data identifying a measure of vibration of a machine. The vibration, of the machine, may be caused by a combination of first vibration caused by a motion of components of an undercarriage of the machine and seco
A system may include a device. The device may be configured to receive machine vibration data identifying a measure of vibration of a machine. The vibration, of the machine, may be caused by a combination of first vibration caused by a motion of components of an undercarriage of the machine and second vibration that is unrelated to the first vibration. The device may be configured to identify a segment, of the machine vibration data, corresponding to the first vibration; transform the segment, using a Fast Fourier Transform (FFT), into a signal in a frequency domain; and analyze the signal to identify a signature spectrum associated with the motion of components. The device may be configured to predict, based on the signature spectrum, an amount of wear of the components. The device may be configured to cause an action to be performed based on the amount of wear of the components.
대표청구항▼
1. A method performed by a device, the method comprising: receiving machine vibration data identifying a measure of vibration, of a machine, over a period of time;segmenting the machine vibration data to obtain time domain signals that include a time domain signal related to vibration associated wit
1. A method performed by a device, the method comprising: receiving machine vibration data identifying a measure of vibration, of a machine, over a period of time;segmenting the machine vibration data to obtain time domain signals that include a time domain signal related to vibration associated with an undercarriage of the machine;transforming the time domain signal, using a Fast Fourier Transform (FFT), into a spectral domain signal;identifying, from the spectral domain signal, a signature spectrum associated with a motion of components of the undercarriage of the machine;predicting, based on an amplitude of the signature spectrum, an amount of wear of the components; andcausing an action to be performed based on the amount of wear of the components. 2. The method of claim 1, wherein the vibration, of the machine, is caused by the motion of the components and caused by one or more implements of the machine engaging a ground surface; wherein the method further comprises: receiving implement data indicating whether the one or more implements are engaging the ground surface during the period of time; andwherein segmenting the machine vibration data comprises: segmenting the machine vibration data, based on the implement data, to identify the time domain signals. 3. The method of claim 2, wherein receiving the machine vibration data includes receiving the machine vibration data from one or more first sensor devices of the machine; and wherein receiving the implement data comprises at least one of: receiving, from one or more second sensor devices of the machine, sensor data indicating whether the one or more implements are engaging the ground surface; orreceiving, from one or more operator controls of the machine, operator controls data indicating whether the one or more implements are engaging the ground surface. 4. The method of claim 1, wherein the time domain signal is a first time domain signal; and wherein the time domain signals include a second time domain signal related to vibration that is unrelated to the vibration associated with the undercarriage of the machine. 5. The method of claim 1, wherein transforming the time domain signal into the spectral domain signal comprises causing: a first portion of the time domain signal, corresponding to the motion of the components, to be amplified based on a power spectral density of the time domain signal, anda second portion of the time domain signal, corresponding to random noise associated with terrain conditions at a location of the machine, to be reduced based on the power spectral density of the time domain signal, wherein the power spectral density is determined using the FFT; andwherein the signature spectrum is identified in a portion of the power spectral density corresponding to the first portion of the time domain signal. 6. The method of claim 1, wherein predicting an amount of wear of the components comprises: predicting the amount of wear of the components based on: the amplitude of the signature spectrum, andhistorical wear data associated with the components. 7. The method of claim 1, wherein performing the action comprises at least one of: causing the components to be serviced;causing the components to be replaced;causing an adjustment to an operation of the machine; orproviding an alert to a device of an operator of the machine. 8. A system, comprising: a device configured to: receive machine vibration data identifying a measure of vibration of a machine, wherein the vibration, of the machine, is caused by a combination of first vibration caused by a motion of components of an undercarriage of the machine and second vibration that is unrelated to the first vibration;identify a segment, of the machine vibration data, corresponding to the first vibration;transform the segment, using a Fast Fourier Transform (FFT), into a signal in a frequency domain;analyze the signal to identify a signature spectrum associated with the motion of components;predict, based on the signature spectrum, an amount of wear of the components; andcause an action to be performed based on the amount of wear of the components. 9. The system of claim 8, wherein, when predicting the amount of wear of the components, the device is configured to: predict the amount of wear of the components based on an amplitude of the signature spectrum. 10. The system of claim 8, wherein, when predicting the amount of wear of the components, the device is configured to: predict the amount of wear of the components based on: the signature spectrum, andhistorical wear data associated with the components. 11. The system of claim 8, wherein, when performing the action, the device is configured to: cause the components to be serviced;cause the components to be replaced;cause an adjustment to an operation of the machine;provide information regarding the amount of wear to a device that monitors wear of components of machines; orprovide an alert to a device of an operator of the machine. 12. The system of claim 8, wherein, when identifying the segment, the device is configured to: receive implement data indicating whether an implement, of the machine, is engaging a ground surface; andidentify the segment based on the implement data. 13. The system of claim 12, wherein the implement data includes at least one of: machine speed data identifying a speed of the machine;implement command data identifying a command for controlling the implement;steering command data identifying a steering command of the machine; or gear setting data identifying a gear setting of the machine. 14. The system of claim 8, wherein, when transforming the segment, the device is configured to: cause a portion of the segment, corresponding to the motion of the components, to be maximized based on a power spectral density of the segment, wherein the power spectral density of the segment is determined using the FFT; andwherein the signature spectrum is identified in a portion of the power spectral density corresponding to the portion of the segment. 15. A device, comprising: one or more memories; andone or more processors configured to: receive machine vibration data identifying a measure of vibration of a machine, wherein the vibration, of the machine, is caused by a combination of first vibration caused by a motion of components of an undercarriage of the machine and second vibration that is unrelated to the first vibration;identify a segment, of the machine vibration data, corresponding to the first vibration;transform the segment, using a Fast Fourier Transform (FFT), into a signal in a frequency domain;analyze the signal to identify a signature spectrum associated with the motion of components;predict, based on the signature spectrum, an amount of wear of the components; andcause an action to be performed based on the amount of wear of the components. 16. The device of claim 15, wherein the components include at least one of a sprocket, an idler, or a track link; and wherein, when receiving the machine vibration data, the one or more processors are configured to receive the machine vibration data from one or more first sensor devices of the machine. 17. The device of claim 16, wherein the one or more processors are configured to at least one of: receive, from one or more second sensor devices of the machine, sensor data indicating whether an implement, of the machine, is engaging a ground surface; orreceive, from one or more operator controls of the machine, operator controls data indicating whether the implement is engaging the ground surface; andwherein, when identifying the segment, the one or more processors are configured to: identify the segment based on at least one of the sensor data or the operator controls data. 18. The device of claim 17, wherein the second vibration corresponds to vibration caused by the implement, of the machine, engaging the ground surface. 19. The device of claim 15, wherein, when performing the action, the one or more processors are configured to: cause the components to be serviced;cause the components to be replaced;cause an adjustment to an operation of the machine;provide information regarding the amount of wear to a device that monitors wear of components of machines; orprovide an alert to a device of an operator of the machine. 20. The device of claim 15, wherein, when predicting the amount of wear of the components, the one or more processors are configured to: predict the amount of wear of the components based on: the signature spectrum, and historical wear data associated with the components.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.