# US 2023/0062615 A1 · Estimating recording head fly height using machine learning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0062615 A1
- Document ID: US20230062615A1
- Status: Published application
- Kind: A1
- Application number: 17/409,927
- Filed: 2021-08-24
- Published: 2023-03-02
- Earliest claimed: 2021-08-24
- Assignees: Seagate Technology LLC
- Applicants: Seagate Technology LLC
- Inventors: Zheng Wang; Ara Patapoutian; Timothy F. Ellis; Jason Bellorado; William M. Radich
- Web page: https://patentgrep.com/patent/US20230062615A1

## CPC

- G11B 5/6029: {Measurement using values derived from the data signal read from the disk}
- G11B 5/5565: {system adaptation for compensation of variations of physical parameters, e.g. temperature}
- G11B 5/59622: {Gain control; Filters}
- G11B 5/607: {using thermal means}
- G11B 20/10518: {using neural networks}
- G11B 20/1258: {where blocks are arranged within multiple radial zones, e.g. Zone Bit Recording or Constant Density Recording discs, MCAV discs, MCLV discs}
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)

## Abstract

Two or more data values are received from one or more sensors of a hard disk drive. The two or more data values are indicative of a fly height of a recording head of the hard disk drive. The two or more data values are input into a machine-learning processor during operation of the hard disk drive. A fly height of the recording head during the operation of the hard drive head is adjusted based on an output of the machine learning processor

## Claims

### Claim 1

A method, comprising:
receiving two or more data values from one or more sensors of a hard disk drive, the two or more data values indicative of a fly height of a recording head of the hard disk drive;
inputting the two or more data values into a machine learning processor during operation of the hard disk drive, wherein the machine learning processor provides two or more outputs indicative of two or more probabilities that the fly height is respectively within two or more different ranges; and
adjusting the fly height of the recording head during the operation of the hard disk drive based on an output of the machine learning processor.

### Claim 2 (depends on 1)

The method of claim 1, wherein the two or more data values comprise two or more frequency components of a servo address mark signal.

### Claim 3 (depends on 2)

The method of claim 2, wherein the method further comprises averaging time domain samples read from the servo address mark signal, the two or more frequency components obtained by transforming the averaged time domain samples into a frequency domain.

### Claim 4 (depends on 2)

The method of claim 2, wherein the two or more frequency components of the servo address mark signal comprise three or more frequency components of the servo address mark signal.

### Claim 5 (depends on 1)

The method of claim 1, wherein the two or more data values comprise an automatic gain control signal.

### Claim 6 (depends on 1)

The method of claim 1, wherein the two or more data values comprise an indicator of radial position of the recording head over a disk surface.

### Claim 7

A method, comprising:
receiving two or more data values from one or more sensors of a hard disk drive, the two or more data values indicative of a fly height of a recording head of the hard disk drive;
inputting the two or more data values into a machine learning processor during operation of the hard disk drive, wherein the two or more data values comprise an indicator of a radial zone in which the recording head is located, the radial zone indicative of a bit density of data read by the recording head;
adjusting the fly height of the recording head during the operation of the hard disk drive based on an output of the machine learning processor.

### Claim 8 (depends on 1)

The method of claim 1, wherein the two or more data values comprise a temperature measurement.

### Claim 9 (depends on 1)

The method of claim 1, wherein the machine learning processor comprises a feedforward neural network.

### Claim 10 (depends on 9)

The method of claim 9, wherein the feedforward neural network provides a single output indicative of at least one of:
the fly height; and
an adjustment to a fly height estimate obtained by a fly height controller.

### Claim 11

(canceled)

### Claim 12 (depends on 1)

A hard disk drive comprising a controller coupled to the recording head, the controller operable to perform the method of claim 1.

### Claim 13

A method, comprising:
measuring at least one of a servo address mark signal and an automatic gain control signal to determine a first data value indicative of fly height of a recording head over a disk surface of a hard disk drive;
determining a second data value indicative of the fly height based on an indicator of a radial position of the recording head over the disk surface;
inputting the first and second data values into a machine learning processor during operation of the hard disk drive; and
adjusting the fly height of the recording head during the operation of the hard disk drive based on an output of the machine learning processor.

### Claim 14 (depends on 13)

The method of claim 13, wherein the first data values comprises two or more frequency components of the servo address mark signal.

### Claim 15 (depends on 13)

The method of claim 13, wherein the indicator of the radial position of the recording head over the disk surface comprises an identifier of a track on which the recording head is currently located.

### Claim 16 (depends on 13)

The method of claim 13, wherein the indicator of the radial position of the recording head over the disk surface comprises an indicator of a radial zone in which the recording head is located, the radial zone indicative of a bit density of data read by the recording head.

### Claim 17 (depends on 13)

The method of claim 13, further comprising measuring temperature data of the hard disk drive and inputting the temperature data into the machine learning processor during the operation of the hard disk drive.

### Claim 18 (depends on 13)

The method of claim 13, wherein the machine learning processor comprises a feedforward neural network, and wherein the feedforward neural network provides a single output indicative of at least one of: the fly height; and an adjustment to a fly height estimate of a fly height controller.

### Claim 19 (depends on 13)

The method of claim 13, wherein the machine learning processor comprises a feedforward neural network, and wherein the feedforward neural network provides two or more outputs indicative of two or more probabilities that the fly height is respectively within two or more different ranges.

### Claim 20

(canceled)
