R&D: Multi-track Detection With 2D Soft Transition Assisted Multi-task Neural Network for Heat Assisted Interlaced Magnetic Recording

IEEE Magnetics Letters has published an article written by Yushu Xu, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China, Yao Wang, Lei Chen, Key Laboratory of Computer Vision and Intelligent Information System, Chongqing University of Arts and Sciences, Chongqing, China, Yumei Wen, and Ping Li, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.

Abstract: “Heat assisted interlaced magnetic recording (HIMR) further increases the recording density compared to heat assisted magnetic recording due to the interlaced track layout. However, the smaller circular thermal profile of top low temperature written tracks results in severe transition curvatures, which causes non-linear distortions of the readback signal and degrades the bit error rate (BER) performance. Moreover, the increased recording density causes severe 2D inter-symbol interference (ISI) along both down track and cross track directions. To mitigate the effect of non-linear distortion and 2D ISI in HIMR system, we propose a 2D soft transition information assisted multi-task neural network and modified Bahl-Cocke-Jelinek-Raviv (BCJR) detector (2DST-MTNN-MB) algorithm to detect three tracks simultaneously. Readback signal and 2D soft transition information are fed into multi-task neural network to obtain equalized signals and soft bit estimates of three tracks simultaneously. Then the signal of current track and soft estimates of side tracks are embedded into the branch metrics of modified BCJR detector for data detection, and the low-density parity check (LDPC) decoder is cascaded for error correction. The simulation results show that the proposed 2DST-MTNN-MB algorithm provides 5.0 dB SNR gains with reduced computation complexity compared to single-track single-task neural network and 1D BCJR detector algorithm for the low temperature written track at channel bit density of 3.51 Tb/in², thereby narrowing the gap of BER performances between high and low temperature written tracks.“