Bi-Directional Long Short-Term Memory Neural Network Modeling of Data Retention Characterization in 3-D Triple-Level Cell NAND Flash Memory

Data retention (a time-variant characteristic of 3-D- NAND flash memory) is predicted through a bi-directional long short-term memory (LSTM) neural network (NN) model that learns sequential data obtained from chip measurements of a triple-level cell (TLC). The predicted results for all time points of each program (PGM) state are accurately predicted by the threshold voltage ( ${V}_{\text {th}}$ ) distribution. Thus, the predicted ${V}_{\text {th}}$ can be used to analyze the cause of retention failure. When the ${V}_{\text {th}}$ of the target cell is high or when that of the adjacent cell is small, the ${V}_{\text {th}}$ loss of the target cell is large. In addition, the ${V}_{\text {th}}$ loss increases as the ${V}_{\text {th}}$ of the adjacent cell decreases. Using a fully calibrated TCAD simulation, we verify the NN-based ${V}_{\text {th}}$ prediction by checking the change in the electron concentration in the nitride layer. Furthermore, the NN model predicts the ${V}_{\text {th}}$ for cells existing in other blocks, showing that they are consistent with the measured ${V}_{\text {th}}$ . The prediction times were 5 $\times \,\,10^{{5}}$ s, 5 $\times \,\,10^{{6}}$ s, and 2 $\times \,\,10^{{6}}$ s, but using machine learning (ML), we reduced the time required to predict the ${V}_{\text {th}}$ to only 2 s. Therefore, the proposed ML method enables fast, accurate, and effective predictive modeling of the time-variant ${V}_{\text {th}}$ of 3-D TLC NAND flash memory. Finally, the predicted ${V}_{\text {th}}$ can be included in the read retry table or included in the lookup table of the compensation circuit in NAND solutions. This can save a significant amount of time that would otherwise be spent on actual long-term measurements.