IP Library Granted Patent US 11,977,741
Granted Patent B2
US 11,977,741 · App. 17/155,272 · Granted May 7, 2024

System and method for acquiring and using audio detected during operation of a hard disk drive to determine drive health

Inventors: Deepak Gowda (Cary, NC); Sathish Kumar Bikumala (Round Rock, TX)
Assignee: Dell Products L.P.
G06F3/0619G06F3/0616G06F3/0653G06F3/0673H03M1/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,977,741
App. No.
17/155,272
Granted
May 7, 2024
Kind
B2
Abstract

A method, system, and computer-usable medium are disclosed for acquiring and using audio detected during operation of a hard disk drive to determine the status of the hard disk drive. One general aspect of the disclosure is directed to a computer-implemented method that includes receiving analog audio detected by an audio transducer in proximity to moving mechanical components of a hard disk drive, converting the received analog audio to digital audio, and assigning a health classification status to the hard disk drive based on a classification of the digital audio.

Claims (64)

1. A computer-implemented method comprising:

receiving analog audio detected by an audio transducer in proximity to moving mechanical components of a hard disk drive;

converting the received analog audio to digital audio, the converting the received analog audio comprising extracting an audio feature from the received analog audio to provide a respective feature vector, the respective feature vector being one of a plurality of feature vectors; and

assigning a health classification status to the hard disk drive based on a classification of the digital audio, the assigning the health classification status using a trained machine learning model, the trained machine learning model comprising a neural network, the neural network being trained using feature vectors corresponding to digital audio generated by moving components of a failing hard disk drive.

2. The computer-implemented method of claim 1 , wherein the receiving audio comprises:

receiving audio from the audio transducer, where the audio transducer is in fixed alignment with a hard disk drive controller board of the hard disk drive.

3. The computer-implemented method of claim 2 , wherein receiving the analog audio comprises:

receiving analog audio detected by the audio transducer, where the audio transducer is mounted to the hard disk drive controller board of the hard disk drive at a location on the hard disk drive controller board at which the audio transducer can detect audio resulting from operation of the moving mechanical components of the hard disk drive.

4. The computer-implemented method of claim 3 , further comprising:

amplifying the analog audio detected by the transducer using an audio amplifier, wherein the audio amplifier is mounted to the hard disk drive controller board; and

converting the amplified analog audio to digital data, wherein the converting the amplified analog audio to digital data is executed by one or more components of the hard disk drive controller board.

5. The computer-implemented method of claim 1 , wherein

the hard disk drive includes a hard disk drive controller board, the hard disk drive controller board including:

a hard disk drive controller;

a motor controller configured to receive signals from the hard disk drive controller, wherein the motor controller is configured to control the moving mechanical components of the hard disk drive in response to the signals received from the hard disk drive controller;

the audio transducer, wherein the audio transducer is located on the hard disk drive controller board at a position to detect sound from operation of the moving mechanical components of the hard disk drive;

an audio amplifier configured for amplifying analog audio detected by the audio transducer; and

an analog-to-digital converter configured for converting the amplified analog audio to digital audio.

6. The computer-implemented method of claim 5 , wherein assigning the health classification to the hard disk drive comprises:

using the hard disk drive controller to analyze the digital audio, wherein the analysis of the digital audio is based on a comparison of the digital audio with digital audio generated by moving components of the failing hard disk drive.

7. The computer-implemented method of claim 5 , wherein assigning the health classification of the hard disk drive comprises:

using the hard disk drive controller to execute a trained hard disk drive health classifier, wherein the hard disk drive health classifier includes the neural network that has been trained using digital audio generated by moving components of the failing hard disk drive.

8. The computer-implemented method of claim 1 , wherein:

each respective feature vector includes an audio feature vector and a corresponding feature vector label.

9. The computer-implemented method of claim 8 , wherein:

the audio feature vector and the corresponding feature vector label are stored in a table of feature vectors.

10. A system comprising:

a hard disk drive controller;

a non-transitory, computer-readable storage medium embodying computer program executable by the hard disk drive controller and configured for:

receiving analog audio detected by an audio transducer in proximity to moving mechanical components of a hard disk drive;

converting the received analog audio to digital audio, the converting the received analog audio comprising extracting an audio feature from the received analog audio to provide a respective feature vector, the respective feature vector being one of a plurality of feature vectors; and

assigning a health classification status to the hard disk drive based on a classification of the digital audio, the assigning the health classification status using a trained machine learning model, the trained machine learning model comprising a neural network, the neural network being trained using feature vectors corresponding to digital audio generated by moving components of a failing hard disk drive.

11. The system of claim 10 , wherein the receiving audio comprises:

receiving audio from the audio transducer, where the audio transducer is in fixed alignment with a hard disk drive controller board of the hard disk drive.

12. The system of claim 11 , wherein receiving the analog audio comprises:

receiving analog audio detected by the audio transducer, where the audio transducer is mounted to the hard disk drive controller board of the hard disk drive at a location on the hard disk drive controller board at which the audio transducer can detect audio resulting from operation of the moving mechanical components of the hard disk drive.

13. The system of claim 12 , further comprising:

amplifying the analog audio detected by the transducer using an audio amplifier, wherein the audio amplifier is mounted to the hard disk drive controller board; and

converting the amplified analog audio to digital data, wherein the converting the amplified analog audio to digital data is executed by one or more components of the hard disk drive controller board.

14. The system of claim 10 , wherein

the hard disk drive includes a hard disk drive controller board, the hard disk drive controller board including:

the hard disk drive controller;

a motor controller configured to receive signals from the hard disk drive controller, wherein the motor controller is configured to control the moving mechanical components of the hard disk drive in response to the signals received from the hard disk drive controller;

the audio transducer, wherein the audio transducer is located on the hard disk drive controller board at a position to detect sound from operation of the moving mechanical components of the hard disk drive;

an audio amplifier configured for amplifying analog audio detected by the audio transducer; and

an analog-to-digital converter configured for converting the amplified analog audio to digital audio.

15. The system of claim 14 , wherein assigning the health classification to the hard disk drive comprises:

using the hard disk drive controller to analyze the digital audio, wherein the analysis of the digital audio is based on a comparison of the digital audio with digital audio generated by moving components of the failing hard disk drive.

16. The system of claim 14 , wherein assigning the health classification of the hard disk drive comprises:

using the hard disk drive controller to execute a trained hard disk drive health classifier, wherein the hard disk drive health classifier includes the neural network that has been trained using digital audio generated by moving components of the failing hard disk drive.

17. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:

receiving analog audio detected by an audio transducer in proximity to moving mechanical components of a hard disk drive;

converting the received analog audio to digital audio, the converting the received analog audio comprising extracting an audio feature from the received analog audio to provide a respective feature vector, the respective feature vector being one of a plurality of feature vectors; and

assigning a health classification status to the hard disk drive based on a classification of the digital audio, the assigning the health classification status using a trained machine learning model, the trained machine learning model comprising a neural network, the neural network being trained using digital audio generated by moving components of a failing hard disk drive.

18. The non-transitory, computer-readable storage medium of claim 17 , wherein the instructions are configured for:

receiving audio from an audio transducer that is in fixed alignment with a hard disk drive controller board of the hard disk drive.

19. The non-transitory, computer-readable storage medium of claim 18 , wherein the instructions are configured for:

receiving analog audio detected by an audio transducer that is mounted to the hard disk drive controller board of the hard disk drive at a location on the hard disk drive controller board at which the audio transducer can detect audio resulting from operation of the moving mechanical components of the hard disk drive.

20. The non-transitory, computer-readable storage medium of claim 19 , wherein the instructions are further configured for:

converting the analog audio to digital data, wherein the converting the analog audio to digital data is executed by one or more components of the hard disk drive controller.

21. The non-transitory, computer-readable storage medium of claim 17 , wherein

the instructions are configured for execution by a hard disk drive controller.

22. The non-transitory, computer-readable storage medium of claim 21 , wherein the instructions are configured for:

using the hard disk drive controller to analyze the digital audio, wherein the analysis of the digital audio is based on a comparison of the digital audio with digital audio generated by moving components of the failing hard disk drive.

Assignments (9)
RELEASE OF SECURITY INTEREST IN PATENTS PREVIOUSLY RECORDED AT REEL/FRAME (055479/0342) Recorded Jun 10, 2022
From: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
To: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
Reel/Frame 062021/0460 →
RELEASE OF SECURITY INTEREST IN PATENTS PREVIOUSLY RECORDED AT REEL/FRAME (055479/0051) Recorded Jun 10, 2022
From: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
To: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
Reel/Frame 062021/0663 →
RELEASE OF SECURITY INTEREST IN PATENTS PREVIOUSLY RECORDED AT REEL/FRAME (056136/0752) Recorded Jun 10, 2022
From: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
To: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
Reel/Frame 062021/0771 →
RELEASE OF SECURITY INTEREST AT REEL 055408 FRAME 0697 Recorded Nov 2, 2021
From: CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH
To: DELL PRODUCTS L.P.; EMC IP HOLDING COMPANY LLC
Reel/Frame 058001/0553 →
SECURITY INTEREST Recorded Mar 3, 2021
From: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
To: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
Reel/Frame 056136/0752 →
SECURITY INTEREST Recorded Mar 3, 2021
From: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
To: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
Reel/Frame 055479/0051 →
SECURITY INTEREST Recorded Mar 3, 2021
From: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
To: THE BANK OF NEW YORK MELLON TRUST COMPANY, N.A., AS NOTES COLLATERAL AGENT
Reel/Frame 055479/0342 →
SECURITY AGREEMENT Recorded Feb 25, 2021
From: EMC IP HOLDING COMPANY LLC; DELL PRODUCTS L.P.
To: CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH
Reel/Frame 055408/0697 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 22, 2021
From: GOWDA, DEEPAK; BIKUMALA, SATHISH KUMAR
To: DELL PRODUCTS L.P.
Reel/Frame 054994/0962 →