Lifetime Improvement of 28 nm Resistive Random Access Memory Chip by Machine Learning‐Assisted Prediction Model Collaborated with Resurrection Algorithm

• Published in: Advanced electronic materials 2024-05, Vol.10 (5), p.n/a
• Main Authors: Zheng, Xu, Wu, Lizhou, Xie, Yuanlu, Lai, Jinru, Sun, Wenxuan, Yu, Jie, Dong, Danian, Yu, Zhaoan, Xue, Xiaoyong, Chen, Bing, Yang, Yan, Xu, Xiaoxin, Liu, Qi, Liu, Ming
• Format: Article
• Language: English
• Subjects: machine learning; prediction; reliability; resistive random access memory
• ISSN: 2199-160X; 2199-160X
• DOI: 10.1002/aelm.202300504

In this work, a machine learning‐assisted prediction model is proposed to analyze the reliability issues in the 28 nm resistive random access memory (RRAM) chip with raw data measured from RRAM test chip. The neural network of long‐short time memory (LSTM) is trained by the voltages and resistance during the endurance test (input vectors) and generates the output of the dichotomy states with a satisfied testing result >83.08%. According to the prediction results, the “real fail” state or “fake fail” state of the devices can get in the future. By collaborating with a well‐designed resurrection algorithm (RA), the percentage of real and fake failed cells dropped by 35% and 29%, respectively. Besides, the tail bits in retention significantly reduced from 33% to 14.6% due to the reduction of oxygen vacancies in the gaps of conducting filaments by applying ten consecutive cycles of RA. This intelligent prediction and repair module can prolong the lifetime of RRAM chips effectively in practical applications. The physical model of resistive random access memory (RRAM) is well fitting quantum point contact (QPC) model. Based on the data set from RRAM chips, the long‐short time memory (LSTM) prediction model is proposed to predict endurance. A resurrection algorithm is proposed to improve the stability and longevity of RRAM chips. The hardware implementation scheme is also proposed.