A flash memory service life prediction method based on support vector regression

Abstract

The invention discloses a flash memory service life prediction method based on support vector regression. The method comprises the following steps: (1) obtaining the characteristic quantity of a flashmemory to be tested, wherein the characteristic quantity comprises the programming time, the reading time, the erasing time, the current, the power consumption, the threshold voltage distribution, the storage block number, the storage page number, the programming / erasing period number currently experienced by the flash memory, the condition error page number, the condition error block number, theerror bit number and the error rate; (2) processing the characteristic quantity to obtain an operation result; And (3) forming a set by the characteristic quantity and the operation result, and performing support vector regression operation by taking the subset in the set as the input of a support vector regression model to obtain a service life prediction value of the flash memory correspondingto the characteristic quantity. The residual service life of the flash memory can be predicted, so that a flash memory storage device user knows the loss state of the memory in the using process of the device, and data loss caused by failure of the memory unit is avoided.

Description

technical field [0001] The invention belongs to the technical field of flash memory lifetime prediction, and more particularly relates to a flash memory lifetime prediction method based on support vector regression. Background technique [0002] In the modern electronic information industry, memory has always played a very important role as a carrier for storing data in electronic equipment. At present, the memory on the market is mainly divided into: volatile memory and non-volatile memory. Flash memory is a non-volatile memory that can save data for a long time after power failure, and has the advantages of fast data transmission speed, low production cost, and large storage capacity, so it is widely used in electronic devices. [0003] At present, due to the continuous improvement of semiconductor manufacturing technology, the reduction of the distance between memory cells and the reduction of the thickness of the oxide layer make the inherent errors in flash memory more...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the defects of the prior art, the purpose of the present invention is to provide a flash memory life prediction method based on support vector regression, aiming at solving the problem that in the prior art, due to the difference in life span and feature quantity difference between different flash memories, it is impossible to pass a single and conventional method. Method for Predicting the Flash Memory Lifetime Problem

Images