Multitask neural network based on polarity transition soft information assistance and multi-track detection method

A technology of neural network and detection method, applied in the field of multi-task neural network and multi-track detection assisted by soft information based on polarity transition, can solve problems such as few signal processing algorithms, achieve good balance and prediction effect, improve performance, reduce The effect of inter-QR code interference

Active Publication Date: 2021-11-05
SHANGHAI JIAO TONG UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current research on heat-assisted alternating magnetic recording systems mainly focuses on the design of new read-write systems and the optimization of read-write performance, and there are few corresponding researches and reports on signal processing algorithms.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multitask neural network based on polarity transition soft information assistance and multi-track detection method
  • Multitask neural network based on polarity transition soft information assistance and multi-track detection method
  • Multitask neural network based on polarity transition soft information assistance and multi-track detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with accompanying drawing. The multi-task neural network and multi-track detection method based on polarity transition soft information aided by the present invention mainly include the following steps:

[0037] Step 1: Write randomly generated user bit data into a magnetic recording medium, such as figure 2 shown. The heat-assisted alternating magnetic recording system includes two high-temperature write tracks HT1 and HT3 and three low-temperature write tracks LT0, LT2, and LT4.

[0038] Step 2: Use the read head array to obtain the readback signals of the three middle tracks HT1, LT2 and HT3 at the same time. In order to reduce the interference of the outermost tracks LT0 and LT4, when obtaining the readback signals, the readback signals corresponding to the high temperature tracks HT1 and HT3 on both sides are The head position moves toward the middle.

[0039] Step 3: Input the readback signal...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a multitask neural network based on polarity conversion soft information assistance and a multi-track detection algorithm for a heat-assisted alternating magnetic recording system. The method mainly comprises the following steps that: in a first iteration process, read-back signals of the three middle magnetic tracks are input into the multi-task neural network to obtain balanced signals and bit soft information of the three magnetic tracks, the balanced signals and the bit soft information are input into the improved BCJR detector and the LDPC decoder, and turbo balance is formed by exchanging soft information between the BCJR detector and the LDPC decoder; and, in the second iteration process, the log-likelihood ratio output by the LDPC decoder is converted into two-dimensional polarity conversion soft information, the two-dimensional polarity conversion soft information and the read-back signals of the three magnetic tracks are input into the multi-task neural network together to obtain updated equalization signals and bit soft information, and then the bit error rate is sent to an improved BCJR detector and an LDPC decoder to obtain the bit error rate of the magnetic recording system.

Description

technical field [0001] The invention relates to the technical field of signal processing in a heat-assisted alternating magnetic recording system, in particular to a multi-task neural network and multi-track detection method based on polarity transition soft information assistance. Background technique [0002] The mainstream magnetic recording technology currently used in the market is mainly based on perpendicular magnetic recording technology. "Limits further increases in its storage density. In order to further increase the storage density, the corresponding bit size needs to be reduced, and the particle volume of the magnetic recording medium also needs to be reduced to maintain a sufficient signal-to-noise ratio. But on the other hand, in order to ensure the thermal stability of magnetic recording medium particles, it is necessary to significantly increase their anisotropy, which poses a serious challenge to the write magnetic field that can be generated by the curren...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08G11C11/46G11C11/48
CPCG06N3/04G06N3/08G11C11/48G11C11/46
Inventor 王遥徐钰舒文玉梅李平陈蕾
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products