Deep Neural Network Media Noise Predictor Turbo-Detection System for 1-D and 2-D High-Density Magnetic Recording
Deep Neural Network Media Noise Predictor Turbo-Detection System for 1-D and 2-D High-Density Magnetic Recording
复制标题
DOI：
10.1109/tmag.2020.3038419
复制
发表时间：
2020-08
影响因子：
2.1
通讯作者：
Amirhossein Sayyafan;Ahmed Aboutaleb;B. Belzer;K. Sivakumar;Anthony Aguilar;Christopher A. Pinkham;K. Chan;Ashish James
中科院分区：
文献类型：
--
作者：
Amirhossein Sayyafan;Ahmed Aboutaleb;B. Belzer;K. Sivakumar;Anthony Aguilar;Christopher A. Pinkham;K. Chan;Ashish James
本文提出了一种级联的Bahl-Cocke-Jelinek-Raviv（BCJR）检测器、低密度奇偶校验（LDPC）解码器和深度神经网络（DNN）架构，用于1-D和2-D磁记录（1DMR和TDMR）的涡轮检测系统。输入读数首先被馈送到部分响应（PR）均衡器。研究了两种类型的均衡器：具有1-D/2-D PR目标的线性滤波器均衡器和在这项工作中提出的卷积神经网络（CNN）PR均衡器。均衡的输入被传递到BCJR以生成对数似然比（LLR）输出。我们将BCJR LLR输入到CNN噪声预测器以预测信号相关的媒体噪声。两个不同的CNN接口与信道解码器进行评估TDMR。然后，BCJR的第二遍被提供估计的媒体噪声，并且其将其输出馈送到LDPC解码器。系统在BCJR、LDPC和CNN之间迭代地交换LLR以实现更高的区域密度。模拟结果是在晶粒翻转概率（GFP）模型上进行的，每平方英寸（Tg/in 2）为11.4太朗。对于18 nm磁道间距（TP）和11 nm位长（BL）的GFP数据，所提出的TDMR方法比1-D模式相关噪声预测（PDNP）获得了27.78%的面密度增益。所提出的BCJR-LDPC-CNN涡轮检测系统对于11.4 Tg/in 2 GFP模型数据获得3.877太比特/平方英寸（T/bin 2）面密度，这是迄今为止报道的最高面密度之一。
This article presents a concatenated Bahl–Cocke–Jelinek–Raviv (BCJR) detector, low-density parity-check (LDPC) decoder, and deep neural network (DNN) architecture for a turbo-detection system for 1-D and 2-D magnetic recording (1DMR and TDMR). The input readings first are fed to a partial response (PR) equalizer. Two types of the equalizer are investigated: a linear filter equalizer with a 1-D/2-D PR target and a convolutional neural network (CNN) PR equalizer that is proposed in this work. The equalized inputs are passed to the BCJR to generate the log-likelihood-ratio (LLR) outputs. We input the BCJR LLRs to a CNN noise predictor to predict the signal-dependent media noise. Two different CNN interfaces with the channel decoder are evaluated for TDMR. Then, the second pass of the BCJR is provided with the estimated media noise, and it feeds its output to the LDPC decoder. The system exchanges LLRs between BCJR, LDPC, and CNN iteratively to achieve higher areal density. The simulation results are performed on a grain flipping probabilistic (GFP) model with 11.4 Teragrains per square inch (Tg/in2). For the GFP data with 18 nm track pitch (TP) and 11 nm bit length (BL), the proposed method for TDMR achieves 27.78% areal density gain over the 1-D pattern-dependent noise prediction (PDNP). The presented BCJR-LDPC-CNN turbo-detection system obtains 3.877 Terabits per square inch (T/bin2) areal density for 11.4 Tg/in2 GFP model data, which is among the highest areal densities reported to date.