CN116434813A - Flash memory detection method, electronic device and storage medium - Google Patents
Flash memory detection method, electronic device and storage medium Download PDFInfo
- Publication number
- CN116434813A CN116434813A CN202310242687.9A CN202310242687A CN116434813A CN 116434813 A CN116434813 A CN 116434813A CN 202310242687 A CN202310242687 A CN 202310242687A CN 116434813 A CN116434813 A CN 116434813A
- Authority
- CN
- China
- Prior art keywords
- flash memory
- threshold voltage
- voltage distribution
- block
- memory block
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000009826 distribution Methods 0.000 claims abstract description 128
- 238000013145 classification model Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
- G11C29/04—Detection or location of defective memory elements, e.g. cell constructio details, timing of test signals
- G11C29/08—Functional testing, e.g. testing during refresh, power-on self testing [POST] or distributed testing
- G11C29/12—Built-in arrangements for testing, e.g. built-in self testing [BIST] or interconnection details
- G11C29/12005—Built-in arrangements for testing, e.g. built-in self testing [BIST] or interconnection details comprising voltage or current generators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
- G11C29/04—Detection or location of defective memory elements, e.g. cell constructio details, timing of test signals
- G11C29/08—Functional testing, e.g. testing during refresh, power-on self testing [POST] or distributed testing
- G11C29/12—Built-in arrangements for testing, e.g. built-in self testing [BIST] or interconnection details
- G11C29/18—Address generation devices; Devices for accessing memories, e.g. details of addressing circuits
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Read Only Memory (AREA)
- Techniques For Improving Reliability Of Storages (AREA)
Abstract
The invention discloses a flash memory detection method, electronic equipment and a storage medium. The method comprises the following steps: acquiring a threshold voltage distribution classification model comprising valid threshold voltage distributions and invalid threshold voltage distributions determined based on the number of read errors for each page in a flash memory block; reading each page in a flash memory block to be tested to obtain the error number of each page; acquiring the block error number corresponding to the flash memory block to be tested based on the error number, so as to compare the block error number with a preset threshold value; if the block error number is smaller than the preset threshold value, inputting the threshold voltage distribution of the flash memory block to be tested into the threshold voltage distribution classification model; and if the threshold voltage distribution is determined to be valid based on the threshold voltage distribution classification model, determining that the detection of the flash memory block to be detected is passed. According to the invention, the threshold voltage distribution form of the page in the flash memory block is checked through the threshold voltage classification model.
Description
Technical Field
The present invention relates to the field of memory technologies, and in particular, to a flash memory detection method, an electronic device, and a storage medium.
Background
Flash memory (Flash memory) is a semiconductor nonvolatile memory, and with the progress of Flash technology, more and more Flash memory products are being developed. 3D Nand Flash (3D Nand Flash) is a new generation of memory products. The 3D Nand Flash can save 3Bit data by equally dividing and encoding the threshold voltage interval 8 of the 3D Nand Flash. When data is read, the threshold voltage is determined by applying different voltages to the gate to determine the value of the memory cell. Since the storage value is determined by the amount of charge stored in the storage unit, errors in reading data due to the change of the amount of charge may occur during the use of the storage unit, and thus some strategies are required to ensure the reliability of the data.
The method adopted at present is as follows: when page programming is carried out, writing data error correction codes, and when page reading is carried out, rapidly obtaining the error quantity of the current page data through the error correction codes. After the error numbers of all pages in the block are obtained, the average error number of the pages or the maximum error number of the pages is compared with a threshold value, so that whether the current block is a bad block or not is judged and marked. When the flash memory leaves the factory, bad block marking is carried out on all blocks once. In the use process, marking is carried out when the inspection condition is met. However, there is a limit to judging a bad block only by the number of page faults, and it is impossible to find a bad page voltage distribution.
Disclosure of Invention
The invention provides a flash memory detection method, electronic equipment and a storage medium, which can improve the accuracy of judging bad blocks and the reliability of reading data, realize better prediction of the bad blocks and prevent data loss.
In one aspect of the present invention, a flash memory detection method is provided. The method comprises the following steps: acquiring a threshold voltage distribution classification model comprising valid threshold voltage distributions and invalid threshold voltage distributions determined based on the number of read errors for each page in a flash memory block; reading each page in a flash memory block to be tested to obtain the error number of each page; acquiring the block error number corresponding to the flash memory block to be tested based on the error number, so as to compare the block error number with a preset threshold value; if the block error number is smaller than the preset threshold value, inputting the threshold voltage distribution of the flash memory block to be tested into the threshold voltage distribution classification model; and if the threshold voltage distribution is determined to be valid based on the threshold voltage distribution classification model, determining that the detection of the flash memory block to be detected is passed.
In some embodiments, obtaining the block error number corresponding to the flash block under test based on the error number includes: obtaining an average page error number or a maximum page error number based on the error numbers of the pages; and taking the average page fault number or the maximum page fault number as the block fault number.
In some embodiments, the method further comprises: after a target flash block is programmed, determining whether the target flash block reaches a detection condition based on a last read error number of the target flash block or a last time interval from a current time interval of the target flash block; and if the target flash memory block reaches the detection condition, taking the target flash memory block as the flash memory block to be detected.
In some embodiments, the method further comprises: and if the threshold voltage distribution classification model is based on the threshold voltage distribution, determining that the threshold voltage distribution is invalid, and determining that the detection of the flash memory block to be detected fails.
In some embodiments, the method further comprises: and if the block error number is greater than or equal to the preset threshold value, determining that the detection of the flash memory block to be detected fails.
In some embodiments, the method further comprises: acquiring the threshold voltage distribution of the flash memory block to be tested comprises: acquiring starting point voltage, end point voltage and reading step length according to the type of the flash memory block to be tested; sequentially taking the reading step length as a voltage difference from the starting point voltage to the end point voltage, and reading the corresponding data quantity under each voltage value; and fitting the difference value of the data quantity between the adjacent voltage values to obtain the threshold voltage distribution.
In some embodiments, the method further comprises: training to obtain the threshold voltage distribution classification model, including: acquiring threshold voltage distribution data of a preset number of flash memory blocks; training a classifier according to the threshold voltage distribution data to obtain the threshold voltage distribution classification model.
In some embodiments, obtaining threshold voltage distribution data for a predetermined number of flash memory blocks includes: reading the error number of each page in the current flash memory block to obtain an error value corresponding to the current flash memory block; judging whether the error value corresponding to the current flash memory block is smaller than an error threshold value or not; if yes, reading the threshold voltage distribution data of the current flash memory block, and recording the threshold voltage distribution data as valid; and if not, marking the current flash memory block as a bad block, reading the threshold voltage distribution data of the current flash memory block, and recording the threshold voltage distribution data as invalid.
In some embodiments, obtaining threshold voltage distribution data for a predetermined number of flash memory blocks further comprises: judging whether all the flash memory blocks finish the reading operation; if not, executing the reading operation on the next flash memory block until all the flash memory blocks complete the reading operation.
In some embodiments, training the classifier according to the threshold voltage distribution data, the deriving the threshold voltage distribution classification model includes: obtaining an effective threshold voltage distribution model according to the effective threshold voltage distribution data; and obtaining an invalid threshold voltage distribution model according to the invalid threshold voltage distribution data.
In another aspect of the invention, an electronic device is provided. The electronic device includes: a memory configured to store a computer program; and a processor configured to execute the computer program to perform the flash memory detection method described above.
In yet another aspect of the present invention, a computer storage medium is provided. The medium has stored thereon a computer program to be executed by a processor to implement the above-described flash memory detection method.
According to the embodiment of the invention, the threshold voltage classification model is obtained through the effective threshold voltage distribution and the ineffective threshold voltage distribution which are determined based on the read error numbers of the pages in the flash memory block, so that when the flash memory is used for triggering inspection, the error numbers of the pages in the flash memory block to be detected are acquired, the error flash memory is judged through the preset threshold value and the threshold voltage classification model, the flash memory judged to be invalid is marked as a bad block, the inspection of the threshold voltage distribution form of the pages in the flash memory block is increased, the judgment accuracy of the bad block and the reliability of read data are improved, the bad block is predicted better, and the data loss is prevented.
Drawings
FIG. 1 is a flow chart of a flash memory detection method according to an embodiment of the invention;
FIG. 2 is a flowchart of a method for obtaining threshold voltage distribution data corresponding to a predetermined number of flash blocks according to the flash detection method of the embodiment of the present invention;
FIG. 3 is a schematic diagram of a method for obtaining threshold voltage distribution in a flash memory detection method according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to describe the technical contents, the achieved objects and effects of the present invention in detail, the following description will be made with reference to the embodiments in conjunction with the accompanying drawings.
In the prior art, whether the flash memory block is a bad block is judged only by the page fault number corresponding to the flash memory block, and some potential bad blocks caused by uneven page voltage distribution cannot be detected, so that the bad blocks cannot be accurately identified in the inspection process, and the problems of data loss and the like occur in the flash memory use process.
In order to solve at least the above technical problems, the present disclosure provides a flash memory detection method. According to an embodiment of the present disclosure, a threshold voltage classification model is obtained by an effective threshold voltage distribution and an ineffective threshold voltage distribution determined based on the number of read errors of each page in a flash memory block; and when the flash memory is shipped from the factory, the threshold voltage classification model is burnt into the flash memory, so that when the flash memory is used for triggering inspection, the error number of each page in the flash memory block to be detected is acquired, the error flash memory is judged sequentially through the preset threshold value and the threshold voltage classification model, the flash memory judged as the bad page is marked as the bad block, the inspection of the threshold voltage distribution form of the page in the flash memory block is increased, the judgment accuracy of the bad block and the reliability of read data are improved, the bad block is better predicted, and the data loss is prevented.
Hereinafter, a technical scheme according to the present disclosure will be described with reference to specific embodiments and with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a flash memory detection method 100 according to an embodiment of the present disclosure. Referring to fig. 1, the method 100 includes the following steps 102-110.
At step 102, a threshold voltage distribution classification model is obtained that includes valid and invalid threshold voltage distributions determined based on the number of read errors for each page in a flash block. In some embodiments, a trained threshold voltage distribution classification model is received from a predetermined storage location. In some embodiments, the threshold voltage classification model is burned into the flash memory at the time of shipment.
In some embodiments, the classifier is trained according to the threshold voltage distribution data to obtain the threshold voltage distribution classification model. In some embodiments, an active threshold voltage distribution model is derived from the active threshold voltage distribution data and an inactive threshold voltage distribution model is derived from the inactive threshold voltage distribution data. In some embodiments, threshold voltage distributions and corresponding valid/invalid labels are used in training the model, and training the model is performed based on a supervised learning method in machine learning, such as a support vector machine, a random gradient descent method, a nearest neighbor node algorithm, a deep neural network, and the like.
In some embodiments, the threshold voltage distribution classification model is obtained through training prior to step 102. In some embodiments, threshold voltage distribution data of a preset number of flash memory blocks is obtained, and a classifier is trained according to the threshold voltage distribution data to obtain the threshold voltage distribution classification model.
In this way, an effective threshold voltage distribution model and an ineffective threshold voltage distribution model are obtained respectively, so that the threshold voltage distribution data corresponding to the input flash memory block can be accurately classified according to the effective threshold voltage distribution model and the ineffective threshold voltage distribution model.
In step 104, each page in the flash block to be tested is read to obtain the error number of each page. In some embodiments, a read error number for each page in a flash block under test is obtained.
In step 106, the number of block errors corresponding to the flash memory block to be tested is obtained based on the number of errors, so as to compare the number of block errors with a predetermined threshold. In some embodiments, an average page fault number or a maximum page fault number is derived based on the fault numbers of the respective pages, and the average page fault number or the maximum page fault number is taken as the block fault number. In this way, whether the current flash memory block is a bad block can be judged based on the average page fault number or the maximum page fault number corresponding to the calculated current flash memory block, and the bad block is identified in a plurality of different judging modes, so that the bad block can be predicted better, and the data loss is prevented.
In step 108, if the number of block errors is less than the predetermined threshold, the threshold voltage distribution of the flash memory block under test is input into the threshold voltage distribution classification model. The threshold voltage distribution classification model is the trained model received in step 102. In some embodiments, obtaining the threshold voltage distribution of the flash block under test comprises: acquiring starting point voltage, end point voltage and reading step length according to the type of the flash memory block to be tested; sequentially taking the reading step length as a voltage difference from the starting point voltage to the end point voltage, and reading the corresponding data quantity under each voltage value; and fitting the difference value of the data quantity between the adjacent voltage values to obtain the threshold voltage distribution.
In step 110, if the threshold voltage distribution is determined to be valid based on the threshold voltage distribution classification model, it is determined that the detection of the flash memory block under test is passed.
In some embodiments, the method may further comprise: and if the threshold voltage distribution classification model is based on the threshold voltage distribution, determining that the threshold voltage distribution is invalid, and determining that the detection of the flash memory block to be detected fails.
In this way, in some embodiments, when the bad block is not detected by using the number of block errors, the page with the maximum number of errors of the current flash block is extracted, the threshold voltage distribution data corresponding to the page with the maximum number of errors is input into the threshold voltage distribution model to be distinguished, so as to realize the inspection of the threshold voltage distribution form of the page in the flash block, and the flash block judged as invalid in the threshold voltage distribution is removed, so that the page with the potential uneven threshold voltages in the flash block can be found.
In some embodiments, the method may further comprise: and if the block error number is greater than or equal to the preset threshold value, determining that the detection of the flash memory block to be detected fails. In this way, the flash memory blocks can be removed by first screening the flash memory blocks by the relationship between the number of block errors and the predetermined threshold value, the number of block errors being greater than or equal to the predetermined threshold value.
In some embodiments, prior to step 104, the method may further comprise: after a target flash block is programmed, determining whether the target flash block reaches a detection condition based on a last read error number of the target flash block or a last time interval from a current time interval of the target flash block; and if the target flash memory block reaches the detection condition, taking the target flash memory block as the flash memory block to be detected. In this way, the flash blocks can be continually detected, and potentially bad blocks can be identified and marked as unusable in a timely manner.
FIG. 2 is a flow chart illustrating a training to derive the threshold voltage distribution classification model method 102 according to an embodiment of the disclosure. Referring to fig. 2, the method 102 includes the following steps 102.2 through 102.18.
In step 102.2, screening is started, and full-disc screening is performed on the flash memory before delivery.
In step 102.4, the error number of each page in the current flash memory block is read, and an error value corresponding to the current flash memory block is obtained. After reading, calculating the average error number corresponding to the current flash memory block according to the error number, and simultaneously recording the page corresponding to the maximum error number, wherein the error value comprises the average error number and/or the maximum error number corresponding to the current flash memory block.
In step 102.6, it is determined whether the error value corresponding to the current flash block is smaller than an error threshold, and the error value is taken as an average/maximum error number of the current flash block as an example, if the average/maximum error number of the current flash block is smaller than the error threshold, step 102.8 is executed if the average/maximum error number is larger than the error threshold, and step 102.12 is executed if the average/maximum error number is smaller than the error threshold. In the case of threshold judgment, the judgment mode may be: after judging whether the average error number is smaller than the error threshold, judging whether the maximum error number is smaller than the error threshold, or judging whether the average error number or the maximum error number is smaller than the error threshold, and setting a corresponding judging mode according to actual requirements.
At step 102.8, the current flash block is marked as bad or unusable and step 102.10 is performed.
In step 102.10, the threshold voltage distribution data of the current flash block is read and recorded as invalid, and then step 102.14 is performed.
In step 102.12, the threshold voltage distribution data of the current flash block is read and recorded as valid.
In step 102.14, it is determined whether all the flash memory blocks have completed the read operation, if yes, step 102.18 is executed, and if no, step 102.16 is executed.
At step 102.16, the next flash block is screened, i.e., a read operation is performed on the next said flash block.
In step 102.18, step 102 ends.
In this way, the flash memory blocks with error values larger than the error threshold are marked as bad blocks, the bad blocks are prevented from being used, the threshold voltage distribution data corresponding to the bad blocks are recorded as invalid, the threshold voltage distribution data corresponding to the valid blocks are recorded as valid, the threshold voltage distribution data corresponding to the good blocks and the bad blocks are accurately distinguished, so that an effective threshold voltage distribution model can be obtained according to the valid threshold voltage distribution data or an invalid threshold voltage distribution model can be obtained according to the invalid threshold voltage distribution data in the model training process, and therefore the valid threshold voltage distribution model and the invalid threshold voltage distribution model can be obtained respectively, and the threshold voltage distribution data corresponding to the input flash memory blocks can be accurately classified according to the valid threshold voltage distribution model and the invalid threshold voltage distribution model.
Fig. 3 is a schematic diagram illustrating a method 300 of reading threshold voltage distribution data of a currently described flash block according to an embodiment of the present disclosure. Referring to fig. 3, the method 300 includes the following steps S1 to S3.
In step S1, a starting voltage, an ending voltage and a reading step size are obtained according to the type of the flash memory block. If voltages V1 to V8 to be read are obtained according to the voltage range to be detected and the reading step length, eight voltage points to be read are all obtained.
In step S2, from the starting voltage V1 to the ending voltage V8, the corresponding data amount under each voltage value is sequentially read by taking the reading step as a voltage difference, that is, the data amounts corresponding to the voltages V1 to V8 to be read are sequentially read. When the NAND Flash uses different voltages to be read for reading, the cell (cell) with the threshold voltage smaller than the read voltage is regarded as storing information as "1", the cell with the threshold voltage larger than the read voltage is regarded as storing information as "0", taking the voltage to be read V1 as an example, when the voltage to be read V1 is used for reading, the cell with the threshold voltage smaller than V1 is regarded as "1", and the cell with the threshold voltage larger than V1 is regarded as "0".
In step S3, the difference between the data amounts of the adjacent voltage values is fitted to obtain the threshold voltage distribution data. If the data are read by using the voltages V1 and V2 in sequence, the part of the cells with the threshold voltages between V1 and V2 is changed from 0 to 1, that is, the number of cells between V2 and V1 is defined as bin0 by subtracting the number of bits 1 in the V1 read data from the number of bits 1 in the V2 read data. That is, the number of bit1 in the read data of the voltages V1 and V2 to be read is calculated, so as to obtain an approximate value bin0 of the curve height. And similarly, sequentially obtaining the difference value of the data quantity between the read voltages V1 to V8 to obtain bin0 to bin6, and fitting the bin0 to bin6 to obtain the threshold voltage distribution data of the voltages V1 to V8.
In this way, the start voltage, the end voltage, and the step size of each shift of the read data can be decided according to different NAND Flash, thereby plotting the threshold voltage distribution of all memory cells in the entire page.
In another aspect of the invention, fig. 4 is a schematic diagram illustrating an electronic device 400 according to an embodiment of the invention. Referring to fig. 4, the electronic device 400 comprises a memory 402, a processor 404 and a computer program stored on said memory and executable on the processor, which processor implements the steps of the flash memory detection method as described above when executing said computer program.
In yet another aspect of the invention, a computer-readable medium is provided. The medium has stored thereon a computer program to be executed by a processor to implement the above-described flash memory detection method.
In summary, the invention provides a method and a device for debugging flash memory, an electronic device and a storage medium, wherein a classifier is trained by acquiring threshold voltage distribution data corresponding to flash memory blocks in the same batch to obtain a threshold voltage classification model; when the flash memory is shipped from the factory, the threshold voltage classification model is burnt into the flash memory, so that when the inspection is triggered in the use process of the flash memory, the flash memory with errors can be judged through the threshold voltage classification model, the flash memory judged as a bad page is marked as a bad block, the inspection of the threshold voltage distribution form of the flash memory page is increased, the accuracy of judging the bad block and the reliability of reading data are improved, the bad block is predicted better, and the data loss is prevented.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent changes made by the specification and drawings of the present invention, or direct or indirect application in the relevant art, are included in the scope of the present invention.
Claims (12)
1. A method for detecting flash memory, comprising:
acquiring a threshold voltage distribution classification model comprising valid threshold voltage distributions and invalid threshold voltage distributions determined based on the number of read errors for each page in a flash memory block;
reading each page in a flash memory block to be tested to obtain the error number of each page;
acquiring the block error number corresponding to the flash memory block to be tested based on the error number, so as to compare the block error number with a preset threshold value;
if the block error number is smaller than the preset threshold value, inputting the threshold voltage distribution of the flash memory block to be tested into the threshold voltage distribution classification model; and
and if the threshold voltage distribution is determined to be effective based on the threshold voltage distribution classification model, determining that the detection of the flash memory block to be detected passes.
2. The flash memory detection method of claim 1, wherein obtaining a block error number corresponding to the flash memory block under test based on the error number comprises:
obtaining an average page error number or a maximum page error number based on the error numbers of the pages; and
and taking the average page fault number or the maximum page fault number as the block fault number.
3. The flash memory detection method according to claim 1, further comprising:
after a target flash block is programmed, determining whether the target flash block reaches a detection condition based on a last read error number of the target flash block or a last time interval from a current time interval of the target flash block; and
and if the target flash memory block reaches the detection condition, taking the target flash memory block as the flash memory block to be detected.
4. The flash memory detection method according to claim 1, further comprising:
and if the threshold voltage distribution classification model is based on the threshold voltage distribution, determining that the threshold voltage distribution is invalid, and determining that the detection of the flash memory block to be detected fails.
5. The flash memory detection method according to claim 1, further comprising:
and if the block error number is greater than or equal to the preset threshold value, determining that the detection of the flash memory block to be detected fails.
6. The flash memory detection method according to claim 1, further comprising:
acquiring the threshold voltage distribution of the flash memory block to be tested comprises:
acquiring starting point voltage, end point voltage and reading step length according to the type of the flash memory block to be tested;
sequentially taking the reading step length as a voltage difference from the starting point voltage to the end point voltage, and reading the corresponding data quantity under each voltage value; and
and fitting the difference value of the data quantity between the adjacent voltage values to obtain the threshold voltage distribution.
7. The flash memory detection method according to claim 1, further comprising:
training to obtain the threshold voltage distribution classification model, including:
acquiring threshold voltage distribution data of a preset number of flash memory blocks; and
training a classifier according to the threshold voltage distribution data to obtain the threshold voltage distribution classification model.
8. The method of claim 7, wherein obtaining threshold voltage distribution data for a predetermined number of flash blocks comprises:
reading the error number of each page in the current flash memory block to obtain an error value corresponding to the current flash memory block;
judging whether the error value corresponding to the current flash memory block is smaller than an error threshold value or not;
if yes, reading the threshold voltage distribution data of the current flash memory block, and recording the threshold voltage distribution data as valid; and
if not, marking the current flash memory block as a bad block, reading the threshold voltage distribution data of the current flash memory block, and recording the threshold voltage distribution data as invalid.
9. The method of claim 8, wherein obtaining threshold voltage distribution data for a predetermined number of flash blocks further comprises:
judging whether all the flash memory blocks finish the reading operation;
if not, executing the reading operation on the next flash memory block until all the flash memory blocks complete the reading operation.
10. The method of claim 7, wherein training a classifier based on the threshold voltage distribution data to obtain the threshold voltage distribution classification model comprises:
obtaining an effective threshold voltage distribution model according to the effective threshold voltage distribution data; and
and obtaining an invalid threshold voltage distribution model according to the invalid threshold voltage distribution data.
11. An electronic device, comprising:
a memory configured to store a computer program; and
a processor configured to execute the computer program to perform the method according to any one of claims 1 to 10.
12. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program is executed to implement the method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310242687.9A CN116434813A (en) | 2023-03-14 | 2023-03-14 | Flash memory detection method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310242687.9A CN116434813A (en) | 2023-03-14 | 2023-03-14 | Flash memory detection method, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116434813A true CN116434813A (en) | 2023-07-14 |
Family
ID=87091648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310242687.9A Pending CN116434813A (en) | 2023-03-14 | 2023-03-14 | Flash memory detection method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116434813A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117130822A (en) * | 2023-10-24 | 2023-11-28 | 杭州阿姆科技有限公司 | Method and system for predicting NAND flash data errors |
| CN117854581A (en) * | 2024-03-07 | 2024-04-09 | 合肥康芯威存储技术有限公司 | Memory test system and memory test method |
-
2023
- 2023-03-14 CN CN202310242687.9A patent/CN116434813A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117130822A (en) * | 2023-10-24 | 2023-11-28 | 杭州阿姆科技有限公司 | Method and system for predicting NAND flash data errors |
| CN117854581A (en) * | 2024-03-07 | 2024-04-09 | 合肥康芯威存储技术有限公司 | Memory test system and memory test method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116434813A (en) | Flash memory detection method, electronic device and storage medium | |
| CN107967928B (en) | Flash memory chip life prediction method based on mathematical model | |
| CN107452421B (en) | Solid state storage device and state prediction method thereof | |
| JP6047286B2 (en) | Early detection of flash memory degradation using test cells | |
| KR101348665B1 (en) | Method for estimating and reporting the life expectancy of flash-disk memory | |
| CN108682442B (en) | Online testing and classifying method and testing system for different packaged flash memory chips | |
| JP5882719B2 (en) | Data management of flash memory using probability of failure | |
| CN109830255B (en) | Characteristic quantity-based flash memory life prediction method and system and storage medium | |
| US11398291B2 (en) | Method and apparatus for determining when actual wear of a flash memory device differs from reliability states for the flash memory device | |
| CN105590649A (en) | Read-Threshold Calibration In A Solid State Storage System | |
| JP5997441B2 (en) | Data management of flash memory using probability of failure | |
| CN113010391A (en) | Memory subsystem analysis based on threshold distribution | |
| US11450401B2 (en) | Method, system and computer program product for memory repair | |
| US20150082120A1 (en) | Selective In-Situ Retouching of Data in Nonvolatile Memory | |
| CN107632778B (en) | Nand Flash scanning detection method and system | |
| US20220366996A1 (en) | Method, system and computer program product for memory repair | |
| CN114005481A (en) | Flash memory erasing capability test method and device, computer equipment and storage medium | |
| US10957400B1 (en) | Memory system | |
| US20220283894A1 (en) | Detection method and system applied to intelligent analysis and detection for flash, intelligent terminal, and computer-readable storage medium | |
| US7835203B2 (en) | Programming method and memory device using the same | |
| CN113421605A (en) | Method and device for testing service life of electric energy meter storage | |
| CN109448774B (en) | Method for judging interference storage area position of flash memory | |
| CN116469441A (en) | Method for acquiring ambient temperature of storage device, electronic equipment and readable storage device | |
| CN116665745A (en) | Flash memory reading method and device | |
| CN115966235A (en) | 3D NAND flash life warning method, system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |