CN115421967A - A method and system for evaluating abnormal risk points of secondary equipment storage - Google Patents

Abstract

The present invention provides a method and system for evaluating storage abnormality risk points of secondary equipment. The method combines the characteristics of single-event flipping of storage chips and the typical topology of secondary equipment to determine the storage abnormality risk to be evaluated in the chip equipped with storage units. Based on its data characteristics, different methods are used to determine its original soft error rate, the original error rate is corrected according to its reinforcement characteristics and geographical location, and its dynamic soft error rate is obtained by considering its use frequency and load rate, and finally according to the dynamic The size of the soft error rate determines its risk level. The method and system realize quantitative evaluation of potential storage abnormal points in secondary equipment, can guide manufacturers to carry out chip selection, promote manufacturers to strengthen prevention and improvement of risk points, and develop high-reliability secondary equipment, thereby improving power grid Ability to operate safely and stably.

Description

A method and system for evaluating abnormal risk points of secondary equipment storage

technical field

The present invention relates to a secondary equipment detection technology in a power system, and more specifically, to a method and system for evaluating abnormal storage risk points of secondary equipment.

Background technique

With the continuous development of semiconductor technology and the improvement of component integration, the impact of single event upset on secondary equipment has become more and more obvious. For the single event effect of devices in integrated circuits, single event upsets can cause malfunctions in the memory structure of the core chip. Ultimately, the individual chip hardware on the board is abnormal, some program codes run incorrectly, unexpected alarms or restart lockouts may occur during operation, and even protection malfunctions occur. At the current stage, it is urgent to solve the storage reliability problem of secondary equipment based on single event flipping, and evaluate the abnormal risk points of secondary equipment storage.

The existing research on the storage reliability of secondary equipment mainly introduces the impact on the storage structure in the protection device from the aspects of hardware architecture and software architecture as a whole. However, in order to analyze the risk points of storage abnormalities in secondary equipment in detail, it is necessary to study the mechanism and characteristics of single event upset on storage abnormalities of protection devices, and analyze the impact on key components in secondary equipment. However, in the method and formula for quantitatively evaluating the storage risk of secondary equipment introduced at this stage, the data acquisition method is not clearly expressed, and the method is ideal, without considering the difficulty of data acquisition. Moreover, chip reliability evaluation is a static evaluation, which does not take into account that different storage units in actual applications are greatly different from the actual situation due to the influence of frequency of use and load. At present, there is no relevant analysis and research in the field of secondary equipment.

Contents of the invention

In order to solve the problem in the prior art that the data acquisition method of the chip reliability evaluation of the storage unit in the secondary device is not clear, the difficulty of data acquisition is not considered, and only the static evaluation is considered, the present invention provides a method for evaluating the storage abnormality of the secondary device Risk point method and system.

According to one aspect of the present invention, the present invention provides a method for evaluating abnormal storage risk points of secondary equipment, the method comprising:

According to the different effects of single event upset on chips with storage units in the integrated circuits of secondary equipment, combined with the typical topology of secondary equipment in the power network, determine the storage abnormality risk points to be evaluated in the chips with storage units;

According to the data characteristics of the storage abnormal risk point to be evaluated, the original soft error rate of the storage abnormal risk point to be evaluated is determined according to the preset original soft error rate matching rule, wherein the data characteristics include whether there is a soft error rate at the storage abnormal risk point to be evaluated. Error rate data and presence or absence of single event flipping saturation cross-section data;

Based on the reinforcement characteristics of storage abnormal risk points to be evaluated, the first corrected soft error rate of the storage abnormal risk points to be evaluated is determined according to the set first correction expression and the original soft error rate, wherein the reinforcement characteristics include the storage risk points to be evaluated Whether the point supports the ECC algorithm for detecting and correcting memory errors;

Carry out geographical location correction on the first corrected soft error rate according to the set second corrected expression, and determine the second corrected soft error rate of the storage abnormality risk point to be evaluated;

Based on the use frequency and load rate of the abnormal risk point to be stored, the dynamic soft error rate of the abnormal risk point to be evaluated is determined according to the set third modified expression and the second modified soft error rate;

The risk level of the storage abnormality risk point to be evaluated is determined according to the dynamic soft error rate of the storage abnormality risk point to be evaluated.

Optionally, according to the data characteristics of the storage abnormal risk point to be evaluated, the original soft error rate of the storage abnormal risk point to be evaluated is determined according to the preset original soft error rate matching rule, including:

When there is soft error rate data at the storage abnormal risk point to be evaluated, the obtained soft error rate data corresponding to the storage abnormal risk point to be evaluated is used as its original soft error rate;

When there is no soft error rate data at the storage anomaly risk point to be evaluated, and there is single event reversal saturation cross-section data, the original soft error rate is determined according to the experimental neutron flux and single event reversal saturation cross-section value of the storage abnormality risk point to be evaluated, Its expression is:

，

和

分别为待评估存储异常风险点原始软错误率，实验数据地中子通量和单粒子翻转饱和截面值；In the formula,

,

with

Respectively, the original soft error rate of the storage anomaly risk point to be evaluated, the neutron flux of the experimental data and the saturation cross-section value of single event upset;

When there is no soft error rate data and single event flipping saturation cross-section data at the storage abnormality risk point to be evaluated, the original soft error rate is determined according to the process and storage medium capacity of the storage abnormality risk point to be evaluated, and its expression is:

和

分别为待评估存储异常风险点根据其制程确定的软错误率典型值和存储容量。In the formula,

with

are respectively the typical value of the soft error rate and the storage capacity of the abnormal storage risk point to be evaluated according to its manufacturing process.

Optionally, based on the reinforcement characteristics of the storage abnormal risk point to be evaluated, the first corrected soft error rate of the storage abnormal risk point to be evaluated is determined according to the set first corrected expression and the original soft error rate, including:

When the storage risk point to be evaluated supports the ECC algorithm for detecting and correcting memory errors, the first correction expression is:

是待评估存储风险点第一修正软错误率，

是常数；In the formula,

is the first corrected soft error rate of the storage risk point to be evaluated,

is a constant;

When the storage risk point to be evaluated does not support the ECC algorithm for detecting and correcting memory errors, the first correction expression is:

。

.

Optionally, the geographical location correction is performed on the first corrected soft error rate according to the set second corrected expression to determine the second corrected soft error rate of the abnormal storage risk point to be evaluated, wherein the second corrected expression is:

和

分别是待评估存储风险点第二修正软错误率和其使用地中子通量。In the formula,

with

are respectively the second corrected soft error rate of the storage risk point to be evaluated and the neutron flux used by it.

Optionally, based on the usage frequency and load rate of the abnormal risk point to be stored, the dynamic soft error rate of the storage abnormal risk point to be evaluated is determined according to the set third modified expression and the second modified soft error rate, wherein the third modified The expression is:

，

和

分别为待评估存储异常风险点的动态软错误率，使用频率和负载率，当

等于1时，表示实时参与运行，当

等于1时，表示满载参与运行。In the formula,

,

with

are respectively the dynamic soft error rate, usage frequency and load rate of storage exception risk points to be evaluated, when

When it is equal to 1, it means real-time participation in running, when

When it is equal to 1, it means full load is involved in running.

According to another aspect of the present invention, the present invention provides a system for evaluating abnormal storage risk points of secondary equipment, the system comprising:

The first result unit is used to determine, according to the different influences of single event upsets on the chips with storage units in the integrated circuits of secondary devices, combined with the typical topology of secondary devices in the power network, to determine the Abnormal risk points of storage to be assessed;

The first calculation unit is configured to determine the original soft error rate of the storage abnormality risk point to be evaluated according to the data characteristics of the storage abnormality risk point to be evaluated according to the preset original soft error rate matching rule, wherein the data characteristics include the data characteristics to be evaluated Store whether there is soft error rate data and whether there is single event flipping saturation cross-section data at abnormal risk points;

The second calculation unit is configured to determine the first modified soft error rate of the storage abnormal risk point to be evaluated based on the hardening characteristics of the storage abnormal risk point to be evaluated according to the set first modified expression and the original soft error rate, wherein the The hardening features include whether the storage risk point to be evaluated supports the ECC algorithm for detecting and correcting memory errors;

The third calculation unit is used to correct the geographical position of the first corrected soft error rate according to the set second corrected expression, and determine the second corrected soft error rate of the storage abnormality risk point to be evaluated;

The fourth calculation unit is used to determine the dynamic soft error rate of the abnormal risk point to be evaluated and stored according to the set third correction expression and the second corrected soft error rate based on the usage frequency and load rate of the abnormal risk point to be stored;

The second result unit is configured to determine the risk level of the storage abnormal risk point to be evaluated according to the dynamic soft error rate of the storage abnormal risk point to be evaluated.

Optionally, the first calculation unit determines the original soft error rate of the storage abnormality risk point to be evaluated according to the data characteristics of the storage abnormality risk point to be evaluated according to the preset original soft error rate matching rule, including:

When there is soft error rate data at the storage abnormal risk point to be evaluated, the obtained soft error rate data corresponding to the storage abnormal risk point to be evaluated is used as its original soft error rate;

When there is no soft error rate data at the storage anomaly risk point to be evaluated, and there is single event reversal saturation cross-section data, the original soft error rate is determined according to the experimental neutron flux and single event reversal saturation cross-section value of the storage abnormality risk point to be evaluated, Its expression is:

，

和

分别为待评估存储异常风险点原始软错误率，实验数据地中子通量和单粒子翻转饱和截面值；In the formula,

,

with

Respectively, the original soft error rate of the storage anomaly risk point to be evaluated, the neutron flux of the experimental data and the saturation cross-section value of single event upset;

When there is no soft error rate data and single event flipping saturation cross-section data at the storage abnormality risk point to be evaluated, the original soft error rate is determined according to the process and storage medium capacity of the storage abnormality risk point to be evaluated, and its expression is:

和

分别为待评估存储异常风险点根据其制程确定的软错误率典型值和存储容量。In the formula,

with

are respectively the typical value of the soft error rate and the storage capacity of the abnormal storage risk point to be evaluated according to its manufacturing process.

Optionally, the second calculation unit determines the first corrected soft error rate of the storage abnormal risk point to be assessed according to the set first corrected expression and the original soft error rate based on the reinforcement characteristics of the storage abnormal risk point to be assessed, including:

When the storage risk point to be evaluated supports the ECC algorithm for detecting and correcting memory errors, the first correction expression is:

是待评估存储风险点第一修正软错误率，

是常数；In the formula,

is the first corrected soft error rate of the storage risk point to be evaluated,

is a constant;

When the storage risk point to be evaluated does not support the ECC algorithm for detecting and correcting memory errors, the first correction expression is:

。

.

Optionally, the third calculation unit performs geographical correction on the first corrected soft error rate according to the set second corrected expression, and determines the second corrected soft error rate of the storage abnormality risk point to be evaluated, wherein the second corrected expression for:

和

分别是待评估存储风险点第二修正软错误率和其使用地中子通量。In the formula,

with

are respectively the second corrected soft error rate of the storage risk point to be evaluated and the neutron flux used by it.

Optionally, the fourth calculation unit determines the dynamic soft error rate of the abnormal risk point to be evaluated according to the set third modified expression and the second modified soft error rate based on the usage frequency and load rate of the abnormal risk point to be stored, wherein , the third modified expression is:

，

和

分别为待评估存储异常风险点的动态软错误率，使用频率和负载率，当

等于1时，表示实时参与运行，当

等于1时，表示满载参与运行。In the formula,

,

with

are respectively the dynamic soft error rate, usage frequency and load rate of storage exception risk points to be evaluated, when

When it is equal to 1, it means real-time participation in running, when

When it is equal to 1, it means full load is involved in running.

The method and system for evaluating storage abnormality risk points of secondary equipment provided by the technical solution of the present invention combine the characteristics of single-event flipping of storage chips and the typical topological structure of secondary equipment to determine storage abnormality risk points to be evaluated in chips with storage units, and Based on its data characteristics, different methods are used to determine its original soft error rate, the original error rate is corrected according to its reinforcement characteristics and geographical location, and its dynamic soft error rate is obtained by considering its use frequency and load rate, and finally according to the dynamic soft error rate The size determines its risk level. The method and system realize quantitative evaluation of potential storage abnormal points in secondary equipment, can guide manufacturers to carry out chip selection, promote manufacturers to strengthen prevention and improvement of risk points, and develop high-reliability secondary equipment, thereby improving power grid Ability to operate safely and stably.

Description of drawings

A more complete understanding of the exemplary embodiments of the present invention can be had by referring to the following drawings:

Fig. 1 is a flow chart of a method for evaluating abnormal risk points of secondary equipment storage according to a preferred embodiment of the present invention;

Fig. 2 is a schematic structural diagram of a system for assessing abnormal storage risk points of secondary equipment according to a preferred embodiment of the present invention.

detailed description

Exemplary embodiments of the present invention will now be described with reference to the drawings; however, the present invention may be embodied in many different forms and are not limited to the embodiments described herein, which are provided for the purpose of exhaustively and completely disclosing the present invention. invention and fully convey the scope of the invention to those skilled in the art. The terms used in the exemplary embodiments shown in the drawings do not limit the present invention. In the figures, the same units/elements are given the same reference numerals.

Unless otherwise stated, the terms (including scientific and technical terms) used herein have the meanings commonly understood by those skilled in the art. In addition, it can be understood that terms defined by commonly used dictionaries should be understood to have consistent meanings in the context of their related fields, and should not be understood as idealized or overly formal meanings.

Fig. 1 is a flow chart of a method for assessing abnormal storage risk points of secondary equipment according to a preferred embodiment of the present invention. As shown in FIG. 1 , the method for assessing abnormal storage risk points of secondary equipment described in this preferred embodiment starts from step 101 .

In step 101, according to the different effects of single event upset on chips with storage units in integrated circuits of secondary equipment, combined with the typical topology of secondary equipment in the power network, determine the storage capacity to be evaluated in the chip with storage units Unusual risk points.

In one embodiment, according to the relay protection data from 2019 to 2021, a manufacturer in the State Grid area has a total of 55,940 devices in operation, 321 recorded defects in the protection device body, and a total of 100 failures of various chips. The CPU plug-in of 110kV and above lines and auxiliary protection equipment is composed of two boards, the startup CPU and the protection CPU. Generally, it is composed of processors with storage functions, FPGAs, memory chips, ADC chips, power chips and other chips. In terms of quantity, The board usually includes 1 piece of CPU, 1 piece of FPGA, 1 piece of Flash of Spansion Semiconductor, 1 piece of Flash of MICROCHIP, 5 pieces of DDR2 of Micron, 2 pieces of ADC of AD7606, etc. , ADC, and power supply chips will have single-event upsets.

Possible failure locations for a single-event upset of a CPU are internal memory cells, flip-flops, user and control register bits, registers not accessible through the processor's instruction set, and embedded memory such as register files and caches. A single-event flip of the main control chip may affect the CPU’s real-time calculation of the collected data according to a certain protection algorithm, causing the drive to send out a signal outside the protection action condition, and then act on the corresponding relay of the outlet plug-in, and finally drive the plug-in to operate incorrectly. action.

The single-event upset failure model of SRAM-based FPGAs includes two categories, SEU in user bits will cause transient errors, and SEU in configuration bits will cause permanent errors. A single event flip occurs in the FPGA, which may affect the timing of multi-channel parallel acquisition by the FPGA, which in turn will affect the real-time calculation of the collected data by the CPU and eventually cause malfunctions. For the intelligent station, it may affect the reception of SV and GOOSE messages, and then affect the processing of the CPU and receive the CPU trip command.

There are two types of single event upset faults in Flash. Occurs in memory cells, the mechanism of action is mainly related to the process of charge loss on the floating gate, when the amount of charge on the floating gate changes, the storage state also changes, and the floating gate error still exists after continuous re-reading; the control circuit and Flipping of the page buffer causes a bit fault of the memory cell, and the error disappears after consecutive reads. There are two types of DDR single event upset faults. Contains a large number of erroneous address locations, covering a broad area of logical memory, divided into address location flip faults on logical rows and address location flip faults on logical columns.

A single event flip occurs in RAM, which may affect the CPU to copy the program to RAM for execution through instructions, change the data variables during operation, and cause the program to run abnormally. A single event flip occurs in the Flash, which may affect the copying of the program stored in the FLASH by the CPU through instructions, causing the program to run abnormally.

Single event upset faults mainly occur in the digital circuit part of the ADC such as the output latch.

For the power supply module, generally only care about the change of the output voltage under the SET response.

According to the typical topological structure of the secondary device and the different effects of single event flipping on the chip with the storage unit in the integrated circuit of the secondary device, it can be seen that all CPUs, FPGAs, Flash, DDR2, ADCs with storage units in the secondary device and so on are storage exception risk points to be evaluated that may have storage exceptions.

In step 102, according to the data characteristics of the abnormal storage risk point to be evaluated, the original soft error rate of the abnormal storage risk point to be evaluated is determined according to the preset original soft error rate matching rule, wherein the data characteristics include the abnormal storage risk point to be evaluated Whether the point has soft error rate data and whether there is single event flip saturation cross-section data.

Preferably, according to the data characteristics of the storage abnormal risk point to be evaluated, the original soft error rate of the storage abnormal risk point to be evaluated is determined according to the preset original soft error rate matching rule, including:

When there is soft error rate data at the storage abnormal risk point to be evaluated, the obtained soft error rate data corresponding to the storage abnormal risk point to be evaluated is used as its original soft error rate;

When there is no soft error rate data at the storage anomaly risk point to be evaluated, and there is single event reversal saturation cross-section data, the original soft error rate is determined according to the experimental neutron flux and single event reversal saturation cross-section value of the storage abnormality risk point to be evaluated, Its expression is:

，

和

分别为待评估存储异常风险点原始软错误率，实验数据地中子通量和单粒子翻转饱和截面值；In the formula,

,

with

Respectively, the original soft error rate of the storage anomaly risk point to be evaluated, the neutron flux of the experimental data and the saturation cross-section value of single event upset;

When there is no soft error rate data and single event flipping saturation cross-section data at the storage abnormality risk point to be evaluated, the original soft error rate is determined according to the process and storage medium capacity of the storage abnormality risk point to be evaluated, and its expression is:

和

分别为待评估存储异常风险点根据其制程确定的软错误率典型值和存储容量。In the formula,

with

are respectively the typical value of the soft error rate and the storage capacity of the abnormal storage risk point to be evaluated according to its manufacturing process.

In one embodiment:

The CPU in the main control chip can be obtained through the soft error rate data provided by the chip manufacturer and the radiation effect test data provided by domestic and foreign space agencies. Relevant websites include ESA radiation database, aerospace electronic device space radiation effect database, TI company The FIT estimator etc. For example, for a certain ARM9-based processor of TI, the original soft error rate can be found to be 1.5FIT, and the converted fault frequency is 1.5/10E-09*24=3.6E-08 times/(day·piece), which is the same as the above In the embodiment, the relay protection defect data of a manufacturer in the China Network area is relatively consistent.

进行计算可得CRAM原始软错误率为104.98FIT/Mb，BRAM原始软错误为182.74FIT/Mb。For FPGAs, the raw soft error rate can be determined by obtaining the single event upset saturation cross section value. For example, for a certain Spartan-6 series FPGA equipped with 0.5Mbit CRAM and 18Kb BRAM, according to the single event flipping test, its CRAM flipping saturation cross section value is 8.1E-15cm2/bit, and the BRAM flipping saturation cross section value is 1.41E-14cm2/bit bit. use the formula

After calculation, the original soft error rate of CRAM is 104.98FIT/Mb, and the original soft error rate of BRAM is 182.74FIT/Mb.

For Flash chips and DDR2, if the original soft error rate and single event upset saturation cross-section value cannot be obtained, the original soft error rate can be determined according to the process and storage medium capacity of the storage abnormality risk point to be evaluated. For example, when the storage capacity of the Flash chip is 4Mb and the 32nm process is used, the typical value of its soft error rate is 10FIT/Mb. According to the calculation formula, its original soft error rate can be determined as 40FIT. When the storage capacity of the DDR chip is 1Gb and the typical value of the soft error rate is 1FIT/Mb, the original soft error rate can be determined to be 1024FIT according to the calculation formula.

In step 103, based on the reinforcement characteristics of storage abnormality risk points to be evaluated, the first corrected soft error rate of storage abnormality risk points to be evaluated is determined according to the set first correction expression and the original soft error rate, wherein the reinforcement characteristics include It is to be assessed whether storage risk points support the ECC algorithm for detecting and correcting memory errors.

Preferably, based on the reinforcement characteristics of the storage abnormality risk point to be evaluated, the first modified soft error rate of the storage abnormality risk point to be evaluated is determined according to the set first modified expression and the original soft error rate, including:

When the storage risk point to be evaluated supports the ECC algorithm for detecting and correcting memory errors, the first correction expression is:

是待评估存储风险点第一修正软错误率，

是常数；In the formula,

is the first corrected soft error rate of the storage risk point to be evaluated,

is a constant;

When the storage risk point to be evaluated does not support the ECC algorithm for detecting and correcting memory errors, the first correction expression is:

。

.

In step 104, the geographic location correction is performed on the first corrected soft error rate according to the set second corrected expression, and the second corrected soft error rate of the storage abnormal risk point to be evaluated is determined.

取0.02，当其原始软错误率为52.41FIT时，根据第一修正表达式可知其第一修正软错误率为1.05。In one embodiment, when the configured RAM supports the ECC algorithm, since 99.8% of its errors can be corrected,

Taking 0.02, when the original soft error rate is 52.41FIT, according to the first modified expression, it can be known that the first modified soft error rate is 1.05.

Preferably, the geographical location correction is performed on the first corrected soft error rate according to the set second corrected expression, and the second corrected soft error rate of the abnormal storage risk point to be evaluated is determined, wherein the second corrected expression is:

和

分别是待评估存储风险点第二修正软错误率和其使用地中子通量。In the formula,

with

are respectively the second corrected soft error rate of the storage risk point to be evaluated and the neutron flux used by it.

In one embodiment, for example, the original soft error rate of a CPU is obtained according to its test in New York, and when it is used in Beijing, China, it needs to be based on the neutron flux of the New York experiment and Beijing.

In step 105, based on the usage frequency and load rate of the abnormal risk point to be stored, the dynamic soft error rate of the abnormal risk point to be evaluated is determined according to the set third modified expression and the second modified soft error rate.

Preferably, based on the use frequency and load rate of the abnormal risk point to be stored, the dynamic soft error rate of the abnormal risk point to be evaluated is determined according to the set third modified expression and the second modified soft error rate, wherein the third modified expression The formula is:

，

和

分别为待评估存储异常风险点的动态软错误率，使用频率和负载率，当

等于1时，表示实时参与运行，当

等于1时，表示满载参与运行。In the formula,

,

with

are respectively the dynamic soft error rate, usage frequency and load rate of storage exception risk points to be evaluated, when

When it is equal to 1, it means real-time participation in running, when

When it is equal to 1, it means full load is involved in running.

In one embodiment, the use frequency and load rate are respectively assigned according to the length of time and load capacity of the storage abnormality risk point to be evaluated.

In step 106, the risk level of the storage abnormal risk point to be evaluated is determined according to the dynamic soft error rate of the storage abnormal risk point to be evaluated.

In one embodiment, after determining the dynamic soft error rate of the storage abnormal risk point to be evaluated, the dynamic soft error rate threshold corresponding to the risk level can be set according to the risk level that needs to be divided, and according to the dynamic soft error rate threshold The corresponding judgment interval is generated, so as to determine the risk level according to the judgment interval of the dynamic soft error rate of the storage abnormal risk point to be evaluated.

Fig. 2 is a schematic structural diagram of a system for assessing abnormal storage risk points of secondary equipment according to a preferred embodiment of the present invention. As shown in Figure 2, the system for assessing abnormal risk points of secondary equipment storage described in this preferred embodiment includes:

The first result unit 201 is configured to, according to the different influences of single event upsets on chips with storage units in integrated circuits of secondary equipment, and in combination with the typical topology of secondary equipment in the power network, determine the storage exception risk points to be evaluated;

The first calculation unit 202 is configured to determine the original soft error rate of the storage abnormality risk point to be evaluated according to the data characteristics of the storage abnormality risk point to be evaluated according to the preset original soft error rate matching rule, wherein the data characteristics include the data characteristics to be evaluated Evaluate whether there is soft error rate data and single event flip saturation cross-section data at storage abnormal risk points;

The second calculation unit 203 is configured to determine the first modified soft error rate of the storage abnormal risk point to be evaluated based on the hardening characteristics of the storage abnormal risk point to be evaluated according to the set first modified expression and the original soft error rate, wherein, The above hardening features include whether the storage risk point to be evaluated supports the ECC algorithm for detecting and correcting memory errors;

The third calculation unit 204 is configured to correct the geographical position of the first corrected soft error rate according to the set second corrected expression, and determine the second corrected soft error rate of the storage abnormality risk point to be evaluated;

The fourth calculation unit 205 is used to determine the dynamic soft error rate of the abnormal risk point to be evaluated and stored according to the set third modified expression and the second modified soft error rate based on the usage frequency and load rate of the abnormal risk point to be stored;

The second result unit 206 is configured to determine the risk level of the storage abnormal risk point to be evaluated according to the dynamic soft error rate of the storage abnormal risk point to be evaluated.

Preferably, the first calculation unit 202 determines the original soft error rate of the storage abnormal risk point to be evaluated according to the data characteristics of the storage abnormal risk point to be evaluated according to the preset original soft error rate matching rule, including:

When there is soft error rate data at the storage abnormal risk point to be evaluated, the obtained soft error rate data corresponding to the storage abnormal risk point to be evaluated is used as its original soft error rate;

When there is no soft error rate data at the storage anomaly risk point to be evaluated, and there is single event reversal saturation cross-section data, the original soft error rate is determined according to the experimental neutron flux and single event reversal saturation cross-section value of the storage abnormality risk point to be evaluated, Its expression is:

，

和

分别为待评估存储异常风险点原始软错误率，实验数据地中子通量和单粒子翻转饱和截面值；In the formula,

,

with

Respectively, the original soft error rate of the storage anomaly risk point to be evaluated, the neutron flux of the experimental data and the saturation cross-section value of single event upset;

When there is no soft error rate data and single event flipping saturation cross-section data at the storage abnormality risk point to be evaluated, the original soft error rate is determined according to the process and storage medium capacity of the storage abnormality risk point to be evaluated, and its expression is:

和

分别为待评估存储异常风险点根据其制程确定的软错误率典型值和存储容量。In the formula,

with

are respectively the typical value of the soft error rate and the storage capacity of the abnormal storage risk point to be evaluated according to its manufacturing process.

Preferably, the second calculation unit 203 determines the first corrected soft error rate of the stored abnormal risk point to be assessed according to the set first corrected expression and the original soft error rate based on the reinforcement characteristics of the stored abnormal risk point to be assessed, including:

When the storage risk point to be evaluated supports the ECC algorithm for detecting and correcting memory errors, the first correction expression is:

是待评估存储风险点第一修正软错误率，

是常数；In the formula,

is the first corrected soft error rate of the storage risk point to be evaluated,

is a constant;

When the storage risk point to be evaluated does not support the ECC algorithm for detecting and correcting memory errors, the first correction expression is:

。

.

Preferably, the third calculation unit 204 performs geographical correction on the first corrected soft error rate according to the set second corrected expression, and determines the second corrected soft error rate of the storage exception risk point to be evaluated, wherein the second corrected expression for:

和

分别是待评估存储风险点第二修正软错误率和其使用地中子通量。In the formula,

with

are respectively the second corrected soft error rate of the storage risk point to be evaluated and the neutron flux used by it.

Preferably, the fourth calculation unit 205 determines the dynamic soft error rate of the abnormal risk point to be evaluated according to the set third modified expression and the second modified soft error rate based on the usage frequency and load rate of the abnormal risk point to be stored, wherein , the third modified expression is:

，

和

分别为待评估存储异常风险点的动态软错误率，使用频率和负载率，当

等于1时，表示实时参与运行，当

等于1时，表示满载参与运行。In the formula,

,

with

are respectively the dynamic soft error rate, usage frequency and load rate of storage exception risk points to be evaluated, when

When it is equal to 1, it means real-time participation in running, when

When it is equal to 1, it means full load is involved in running.

The system for evaluating abnormal risk points of secondary equipment storage described in this preferred embodiment determines the original soft error rate of the abnormal risk point of energy storage to be evaluated through its digital characteristics, and corrects the original soft error rate according to its reinforcement characteristics and geographical location, Then, after determining the dynamic soft error rate by considering its use frequency and load rate, the steps of determining its storage abnormal risk level according to the dynamic soft error rate are the same as the steps taken in the method for evaluating secondary equipment storage abnormal risk points described in the present invention, and the achieved The technical effect is also the same, and will not be repeated here.

The invention has been described with reference to a small number of embodiments. However, it is clear to a person skilled in the art that other embodiments than the invention disclosed above are equally within the scope of the invention, as defined by the appended patent claims.

Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise therein. All references to "a/the/the [means, component, etc.]" are openly construed to mean at least one instance of said means, component, etc., unless expressly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowcharts and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and combinations of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a Means for realizing the functions specified in one or more steps of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart flow or flows and/or block diagram block or blocks.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the present invention can still be Any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention shall fall within the protection scope of the claims of the present invention.

Claims (10)

1. A method of evaluating a secondary device storage anomaly risk point, the method comprising:

determining abnormal risk points of storage to be evaluated in a chip with a storage unit according to different influences of the single event upset on the chip with the storage unit in an integrated circuit of secondary equipment and by combining a typical topological structure of the secondary equipment in a power network;

determining the original soft error rate of the storage abnormal risk point to be evaluated according to the data characteristics of the storage abnormal risk point to be evaluated and the preset original soft error rate matching rule, wherein the data characteristics comprise whether the storage abnormal risk point to be evaluated has soft error rate data and whether single event upset saturated section data exists;

determining a first correction soft error rate of the storage abnormal risk point to be evaluated according to a set first correction expression and an original soft error rate based on the reinforcement characteristic of the storage abnormal risk point to be evaluated, wherein the reinforcement characteristic comprises whether the storage abnormal risk point to be evaluated supports an ECC algorithm for detecting and correcting the memory error;

performing geographical position correction on the first correction soft error rate according to a set second correction expression, and determining a second correction soft error rate of the storage abnormal risk point to be evaluated;

determining the dynamic soft error rate of the abnormal risk points to be evaluated and stored according to the set third correction expression and the second correction soft error rate based on the use frequency and the load rate of the abnormal risk points to be stored;

and determining the risk level of the storage abnormal risk point to be evaluated according to the dynamic soft error rate of the storage abnormal risk point to be evaluated.

2. The method of claim 1, wherein determining an original soft error rate of the storage abnormal risk point to be evaluated according to a preset original soft error rate matching rule according to the data characteristics of the storage abnormal risk point to be evaluated comprises:

when soft error rate data exist in the storage abnormal risk point to be evaluated, the obtained soft error rate data corresponding to the storage abnormal risk point to be evaluated are used as the original soft error rate;

when the storage abnormal risk point to be evaluated does not have soft error rate data and has single event upset saturation section data, determining the original soft error rate according to the neutron flux and the single event upset saturation section value of the experimental ground of the storage abnormal risk point to be evaluated, wherein the expression is as follows:

in the formula (I), the compound is shown in the specification,

，

and

respectively storing the original soft error rate of the abnormal risk point to be evaluated, the neutron flux of the experimental data and the single-particle upset saturation cross section value;

when the storage abnormal risk point to be evaluated does not have soft error rate data and the single event upset saturation cross section data, determining the original soft error rate according to the manufacturing procedure of the storage abnormal risk point to be evaluated and the capacity of a storage medium, wherein the expression is as follows:

in the formula (I), the compound is shown in the specification,

and

respectively determining a typical value of the soft error rate and the storage capacity of the storage abnormal risk point to be evaluated according to the manufacturing process of the storage abnormal risk point.

3. The method according to claim 1, wherein determining a first revised soft error rate of the storage anomaly risk point to be evaluated according to the set first revised expression and the original soft error rate based on the reinforcement characteristic of the storage anomaly risk point to be evaluated comprises:

when the storage risk point to be evaluated supports the ECC algorithm for detecting and correcting the memory error, the first correction expression is as follows:

in the formula (I), the compound is shown in the specification,

is the first fix soft error rate for the storage risk point to be evaluated,

is a constant;

when the storage risk point to be evaluated does not support the ECC algorithm for detecting and correcting the memory error, the first correction expression is as follows:

。

4. the method according to claim 1, wherein the geographical position correction is performed on the first corrected soft error rate according to a set second correction expression, and a second corrected soft error rate of the storage anomaly risk point to be evaluated is determined, wherein the second correction expression is as follows:

in the formula (I), the compound is shown in the specification,

and

the second corrected soft error rate of the storage risk point to be evaluated and the neutron flux of the using place thereof are respectively.

5. The method according to claim 1, characterized in that based on the frequency of use and the load rate of the abnormal risk points to be stored, the dynamic soft error rate of the abnormal risk points to be evaluated is determined according to a third correction expression and a second correction soft error rate, wherein the third correction expression is as follows:

in the formula (I), the compound is shown in the specification,

，

and

dynamic soft error rate, usage frequency and load rate, respectively, for the storage of abnormal risk points to be evaluated

When equal to 1, it represents real-time participation in operation, when

When equal to 1, it indicates full load participation in operation.

6. A system for evaluating secondary device storage anomaly risk points, the system comprising:

the first result unit is used for determining a storage abnormal risk point to be evaluated in a chip with a storage unit according to different influences of single event upset on the chip with the storage unit in an integrated circuit of secondary equipment and by combining a typical topological structure of the secondary equipment in a power network;

the first computing unit is used for determining the original soft error rate of the storage abnormal risk point to be evaluated according to the data characteristics of the storage abnormal risk point to be evaluated and the preset original soft error rate matching rule, wherein the data characteristics comprise whether the storage abnormal risk point to be evaluated has soft error rate data and whether single event upset saturation section data exists;

the second calculation unit is used for determining a first correction soft error rate of the storage abnormal risk point to be evaluated according to the set first correction expression and the original soft error rate based on the reinforcement characteristic of the storage abnormal risk point to be evaluated, wherein the reinforcement characteristic comprises whether the storage abnormal risk point to be evaluated supports the ECC algorithm for detecting and correcting the memory error;

the third calculation unit is used for performing geographical position correction on the first corrected soft error rate according to the set second correction expression and determining a second corrected soft error rate of the storage abnormal risk point to be evaluated;

the fourth calculation unit is used for determining the dynamic soft error rate of the abnormal risk point to be evaluated and stored according to the set third correction expression and the second correction soft error rate on the basis of the use frequency and the load rate of the abnormal risk point to be stored;

and the second result unit is used for determining the risk level of the storage abnormal risk point to be evaluated according to the dynamic soft error rate of the storage abnormal risk point to be evaluated.

7. The system according to claim 6, wherein the first calculating unit determines the original soft error rate of the storage abnormal risk point to be evaluated according to a preset original soft error rate matching rule based on the data characteristics of the storage abnormal risk point to be evaluated, and the method comprises the following steps:

when soft error rate data exist in the storage abnormal risk point to be evaluated, the obtained soft error rate data corresponding to the storage abnormal risk point to be evaluated are used as the original soft error rate;

when the storage abnormal risk point to be evaluated does not have soft error rate data and single event upset saturation section data, determining the original soft error rate according to the neutron flux and the single event upset saturation section value of the experimental ground of the storage abnormal risk point to be evaluated, wherein the expression is as follows:

in the formula (I), the compound is shown in the specification,

，

and

respectively storing the original soft error rate of the abnormal risk point to be evaluated, the neutron flux of the experimental data and the single-particle upset saturation cross section value;

when the storage abnormal risk point to be evaluated does not have soft error rate data and the single event upset saturation cross section data, determining the original soft error rate according to the manufacturing procedure of the storage abnormal risk point to be evaluated and the capacity of a storage medium, wherein the expression is as follows:

in the formula (I), the compound is shown in the specification,

and

respectively determining a typical value of the soft error rate and the storage capacity of the storage abnormal risk point to be evaluated according to the manufacturing process of the storage abnormal risk point.

8. The system according to claim 6, wherein the second computing unit determines a first corrected soft error rate of the storage abnormal risk point to be evaluated according to the set first correction expression and the original soft error rate based on the reinforcement characteristic of the storage abnormal risk point to be evaluated, and comprises:

when the storage risk point to be evaluated supports the ECC algorithm for detecting and correcting the memory errors, the first correction expression is as follows:

in the formula (I), the compound is shown in the specification,

is the first fix soft error rate for the storage risk point to be evaluated,

is a constant;

when the storage risk point to be evaluated does not support the ECC algorithm for detecting and correcting the memory error, the first correction expression is as follows:

。

9. the system according to claim 6, wherein the third computing unit performs geographical location correction on the first corrected soft error rate according to a set second correction expression, and determines a second corrected soft error rate of the storage anomaly risk point to be evaluated, wherein the second correction expression is as follows:

in the formula (I), the compound is shown in the specification,

and

the second corrected soft error rate of the storage risk point to be evaluated and the neutron flux of the using place thereof are respectively.

10. The system according to claim 6, wherein the fourth computing unit determines the dynamic soft error rate of the abnormal risk point to be evaluated based on the use frequency and the load rate of the abnormal risk point to be stored according to a third correction expression and a second correction soft error rate, wherein the third correction expression is as follows:

in the formula (I), the compound is shown in the specification,

，

and

dynamic soft error rate, usage frequency and load rate, respectively, for the storage of abnormal risk points to be evaluated

When equal to 1, it represents real-time participation in operation, when

When equal to 1, it indicates full load participation in operation.

Images