Protection method and device for electrostatic discharge event, electronic equipment, medium and product

Abstract

The invention discloses a protection method and device for an electrostatic discharge event, electronic equipment, a medium and a product, and relates to the technical field of health management of electronic equipment, the target health degree of the electronic equipment is determined according to index values of a plurality of operation indexes, and the influence of the electrostatic discharge event on the electronic equipment is judged from multiple dimensions; when the electrostatic discharge event is detected, event features are obtained, and a fault mode of the electrostatic discharge event is determined according to the event features and a pre-constructed electrostatic discharge attack feature library; collecting index values of a plurality of operation indexes of the electronic equipment; predicting a fault module of the electronic equipment according to the fault mode and the index values of the plurality of operation indexes; determining a target health degree of the electronic equipment according to the index values of the plurality of operation indexes; determining an electrostatic discharge protection strategy of the electronic equipment under the target health degree according to the fault module of the electronic equipment; wherein different target health degrees correspond to different electrostatic discharge protection strategies. Therefore, the effectiveness of protecting the electronic equipment can be improved.

Description

Technical Field

[0001] This application relates to the field of health management technology for electronic devices, and in particular to methods, devices, electronic devices, media, and products for protecting against electrostatic discharge events. Background Technology

[0002] Electrostatic discharge (ESD) is the phenomenon of charge transfer that occurs when objects with different electrostatic potentials approach or come into direct contact with each other, and the release process after static electricity accumulates to a certain level. ESD events are increasingly damaging to electronic devices, and highly integrated circuit components may fail due to ESD events.

[0003] Currently, related technologies protect electronic devices by directly resetting them upon detecting electrostatic discharge events that could affect them. However, this approach is overly simplistic and therefore offers limited protection. Summary of the Invention

[0004] This application provides methods, devices, electronic equipment, media, and products for protecting against electrostatic discharge events, in order to at least address the problem of poor protection effectiveness in related technologies.

[0005] This application provides a method for protecting against electrostatic discharge (ESD) events, comprising: detecting ESD events affecting electronic devices; acquiring event characteristics upon detection of an ESD event; determining the failure mode of the ESD event based on the event characteristics and a pre-built ESD attack feature library; collecting the index values ​​of multiple operating indicators of the electronic device; predicting the faulty module of the electronic device based on the failure mode and the index values ​​of the multiple operating indicators; determining the target health level of the electronic device based on the index values ​​of the multiple operating indicators; determining the ESD protection strategy of the electronic device under the target health level based on the faulty module of the electronic device; wherein different target health levels correspond to different ESD protection strategies; and protecting the electronic device according to the ESD protection strategy.

[0006] This application also provides a protection device for electrostatic discharge (ESD) events, comprising: a detection module for detecting ESD events affecting electronic devices; an acquisition module for acquiring event characteristics upon detection of an ESD event; a first determination module for determining a fault mode of the ESD event based on the event characteristics and a pre-built ESD attack feature library; a collection module for collecting the index values ​​of multiple operating indicators of the electronic device; a prediction module for predicting a fault mode of the electronic device based on the fault mode and the index values ​​of multiple operating indicators; a second determination module for determining a target health level of the electronic device based on the index values ​​of multiple operating indicators; a third determination module for determining an ESD protection strategy for the electronic device under the target health level based on the fault mode of the electronic device; wherein different target health levels correspond to different ESD protection strategies; and a protection module for protecting the electronic device according to the ESD protection strategy.

[0007] This application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for implementing the steps of any of the above-described electrostatic discharge event protection methods when executing the computer program.

[0008] This application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of any of the above-described electrostatic discharge event protection methods.

[0009] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described electrostatic discharge event protection methods.

[0010] This application enables the accurate acquisition of the target health status of electronic devices from multiple dimensions based on the values ​​of multiple operational indicators. When an electrostatic discharge (ESD) event is detected, event characteristics are acquired, and the failure mode of the ESD event can be determined based on these characteristics and a pre-built ESD attack feature library. Based on the failure mode and the values ​​of multiple operational indicators, the failure modules of the electronic device can be predicted, allowing for early identification of modules prone to failure. Combining the failure modules of the electronic device, ESD protection strategies for the electronic device under different target health statuses are determined. Different target health statuses correspond to different ESD protection strategies, enabling targeted protection of the electronic device according to these strategies. On the one hand, direct reset operations may lead to data loss and failure to recover from the fault. Compared to direct reset operations, the method of this application can provide targeted protection for the electronic device based on different ESD protection strategies corresponding to different target health statuses, improving the fault recovery rate. On the other hand, by predicting the failure modules of the electronic device, protection can be implemented before the failure modules fail, preventing fault propagation, shortening fault handling time, and increasing the mean time between failures (MTBF) of the electronic device. Therefore, the effectiveness of electronic device protection can be improved. Attached Figure Description

[0011] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application;

[0013] Figure 2 Flowchart of the electrostatic discharge event protection method provided in the embodiments of this application Figure 1 ;

[0014] Figure 3 Flowchart of the electrostatic discharge event protection method provided in the embodiments of this application Figure 2 ;

[0015] Figure 4 Flowchart of the electrostatic discharge event protection method provided in the embodiments of this application Figure 3 ;

[0016] Figure 5 A schematic diagram of the structure of the electrostatic discharge protection device provided in the embodiments of this application;

[0017] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0019] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0020] Electrostatic discharge (ESD) is the phenomenon of charge transfer that occurs when objects with different electrostatic potentials approach or come into direct contact, followed by the release of static electricity after it has accumulated to a certain level. ESD events are increasingly damaging to electronic devices, and highly integrated circuit components may fail due to ESD events. Currently, related technologies protect electronic devices by directly resetting them upon detecting an ESD event. However, this method of protection is overly simplistic and therefore ineffective.

[0021] To address the aforementioned technical problems, this application proposes the following technical concept: Accurately obtain the target health level of electronic devices from multiple dimensions based on the values ​​of multiple operational indicators; predict the faulty modules of electronic devices based on the failure modes of electrostatic discharge (ESD) events and the values ​​of multiple operational indicators; determine ESD protection strategies for electronic devices under different target health levels based on the faulty modules of the electronic devices; different target health levels correspond to different ESD protection strategies, enabling targeted protection of electronic devices. On the one hand, direct reset operations may lead to data loss and failure to recover from faults. Compared to direct reset operations, the method of this application can provide targeted protection for electronic devices based on different ESD protection strategies corresponding to different target health levels, thereby improving the fault recovery rate. On the other hand, targeted protection of electronic devices according to ESD protection strategies can prevent fault propagation before it occurs, shorten fault handling time, and increase the mean time between failures (MTBF) of electronic devices. Therefore, the effectiveness of electronic device protection can be improved.

[0022] The specific application environment architecture or specific hardware architecture on which the implementation of electrostatic discharge protection methods depends is described here.

[0023] refer to Figure 1 , Figure 1 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. Figure 1 The diagram includes a first graphics processing unit (GPU) module 101, a second GPU module 102, a region manager 103, and a main controller 104.

[0024] The first GPU module 101 is used to monitor voltage and clock jitter; the second GPU module 102 is used to monitor temperature and cyclic redundancy check error rate. When the first GPU module 101 detects abnormal voltage or clock jitter, the second GPU module 102 immediately obtains the temperature and cyclic redundancy check error rate, avoiding blind spots in single-point monitoring.

[0025] In this embodiment, the region manager 103 is used to aggregate monitoring data from the first GPU module 101 and the second GPU module 102 with a latency of less than 200 nanoseconds, and to calculate the target health. The region manager 103 is mounted on a field-programmable gate array (FPGA). The FPGA can process data streams from 32 sensors simultaneously, has a highly stable response time to input events, and its response time fluctuation is less than 5 nanoseconds; in addition, the FPGA supports remote updates to the protection strategy.

[0026] In this embodiment, the main controller 104 determines the failure mode of an electrostatic discharge (ESD) event based on event characteristics and a pre-built ESD attack feature library; predicts the faulty modules of the electronic device based on the failure mode and the values ​​of multiple operating indicators; and makes decisions based on the target health calculated by the area manager 103 to determine the protection strategy. The core of the main controller 104 is a machine learning accelerator, which determines the failure mode of the ESD event and predicts the faulty modules of the electronic device.

[0027] Figure 2 Flowchart of the electrostatic discharge event protection method provided in the embodiments of this application Figure 1 ,like Figure 2 As shown, embodiments of this application provide a method for protecting against electrostatic discharge events. The method is described in detail below:

[0028] S201: Detect electrostatic discharge events that affect electronic equipment.

[0029] In this embodiment, the voltage of the electronic device is received from a voltage sensor; the electromagnetic field strength and electromagnetic field change rate of the electronic device are received from an electromagnetic field probe; and the current change rate of the electronic device is received from a current sensor. Based on the voltage, electromagnetic field strength, electromagnetic field change rate, and current change rate, it is determined whether the triggering conditions for an electrostatic discharge event are met. If the triggering conditions for an electrostatic discharge event are met, it is determined that an electrostatic discharge event affecting the electronic device has been detected. The triggering conditions for an electrostatic discharge event include at least one of the following: the voltage exceeds a voltage threshold, the electromagnetic field strength exceeds an electromagnetic field strength threshold, the electromagnetic field change rate exceeds an electromagnetic field change rate threshold, and the current change rate exceeds a current change rate threshold.

[0030] Optionally, the voltage sensor is a distributed voltage sensor.

[0031] In this embodiment, an electrostatic discharge (ESD) event will cause a violent voltage fluctuation. The distributed voltage sensor can collect voltage changes in real time. When the voltage exceeds the voltage threshold, such as 4kV, it is preliminarily determined that an ESD event has occurred.

[0032] Optionally, the electromagnetic field probe is a high-frequency electromagnetic field probe with a bandwidth greater than 1 GHz.

[0033] In this embodiment, the essence of an ESD event is rapid charge transfer, which is accompanied by the instantaneous generation and change of a strong electromagnetic field, such as within 0.7 nanoseconds to 1 nanosecond. A high-frequency electromagnetic field probe can monitor the electromagnetic field strength and rate of change in real time. When high-frequency, rapid electromagnetic field fluctuations are detected—that is, when the electromagnetic field strength exceeds the electromagnetic field strength threshold and the rate of change of the electromagnetic field exceeds the electromagnetic field rate of change threshold—an ESD event is preliminarily determined to exist.

[0034] In this embodiment, the concentrated energy of an ESD event, such as the energy release lasting between 30 and 100 nanoseconds, will cause the current to increase sharply in a very short time, that is, the rate of change of current exceeds the current rate of change threshold, such as 1 A / ns.

[0035] S202: Acquire event characteristics when an electrostatic discharge event is detected.

[0036] In this embodiment, the event characteristics include voltage, electromagnetic field strength, electromagnetic field change rate, and current change rate. When an electrostatic discharge event is detected, the event characteristics, including voltage characteristics, electromagnetic field strength characteristics, electromagnetic field change rate characteristics, and current change rate characteristics, are acquired.

[0037] S203: Determine the failure mode of an electrostatic discharge event based on event characteristics and a pre-built database of electrostatic discharge attack characteristics.

[0038] Specifically, a first electrostatic discharge waveform is obtained using a convolutional neural network model to identify event characteristics; a second electrostatic discharge waveform matching the first electrostatic discharge waveform is obtained from multiple second electrostatic discharge waveforms in a pre-built electrostatic discharge attack feature library; the pre-built electrostatic discharge attack feature library stores multiple second electrostatic discharge waveforms and the fault modes corresponding to each second electrostatic discharge waveform; the fault mode corresponding to the second electrostatic discharge waveform is determined as the fault mode of the electrostatic discharge event.

[0039] In this embodiment, the event features are processed by a convolutional neural network, and the time features are converted into the electrostatic discharge waveform of the current ESD event.

[0040] In this embodiment, the pre-built electrostatic discharge attack feature library stores two types of core data: multiple second electrostatic discharge waveforms, covering more than 200 typical electrostatic discharge waveforms, such as contact discharge waveforms and air discharge waveforms; and the fault modes corresponding to each second electrostatic discharge waveform, such as local module interference mode, power domain damage mode, and data link failure mode, which are all typical fault types summarized from historical ESD events.

[0041] In this embodiment, a second electrostatic discharge (ESD) waveform that best matches the first ESD waveform is selected from a pre-built ESD attack feature library, such as when the first ESD waveform matches the contact discharge waveform by more than 90%. The fault mode corresponding to the successfully matched second ESD waveform is determined as the fault mode of the ESD event.

[0042] Optionally, a mapping relationship is established between the first electrostatic discharge waveform of the event characteristics and the failure mode of the electrostatic discharge event; the mapping relationship is saved to a pre-built electrostatic discharge attack feature library to update the pre-built electrostatic discharge attack feature library.

[0043] S204: Collect the index values ​​of multiple operating indicators of electronic equipment.

[0044] In this embodiment, a micro-sensor array is deployed on the key integrated circuits or key modules of the electronic device, and the micro-sensor array collects the index values ​​of multiple operating indicators.

[0045] In this embodiment, several operational metrics include voltage, clock jitter, temperature, and cyclic redundancy check (CR) error rate. Voltage is fundamental to power supply; ESD events easily cause voltage transients, and voltage directly reflects power supply stability. Clock jitter refers to the deviation between the actual trigger time and the ideal trigger time during clock signal transmission or generation, and is a key indicator for measuring clock signal stability. The concentrated energy release of an ESD event can cause localized instantaneous temperature rise; the rate of temperature change can capture thermal anomalies caused by the ESD event. The CR error rate is used to verify data integrity; an excessive CR error rate indicates that the ESD event has affected the reliability of data transmission.

[0046] In this embodiment, the normal range for voltage is 1.70V~1.80V; a warning is triggered when the voltage is 5% below 1.70V or 5% above 1.80V. The normal range for clock jitter is 0~50ps; a value greater than 100ps is considered a fault. The normal range for temperature is 25℃~85℃; a temperature change rate greater than 10℃ / ms is considered an abnormal transient. The normal range for cyclic redundancy check error rate is 0~ Cyclic redundancy check error rate is greater than At that time, data protection should be activated.

[0047] In this embodiment, the sampling frequency is 100MHz.

[0048] S205: Predicts fault modules of electronic equipment based on fault modes and the values ​​of multiple operating indicators.

[0049] Specifically, the fault modes are encoded to obtain fault mode encoding vectors; the index values ​​of multiple operating indicators are converted into time-series operating indicator data according to the time sequence of collection; the encoding vectors and time-series operating indicator data are input into the Long Short-Term Memory (LSTM) network model, so that the LSM network model can predict the fault modules of the electronic equipment based on the encoding vectors and time-series operating indicator data.

[0050] In this embodiment, since the fault mode is text information, it needs to be encoded first to map the fault mode into a fixed-dimensional encoding vector so that it can be recognized by the Long Short-Term Memory network model.

[0051] In this embodiment, the values ​​of multiple operational indicators collected, including voltage, clock jitter, temperature, and cyclic redundancy check error rate, are arranged in the order of collection time to form time-series operational indicator data. The time-series operational indicator data reflects the changing trend of each operational indicator over time after an ESD event occurs.

[0052] In this embodiment, the Long Short-Term Memory (LSTM) network model can capture the changing patterns of performance metrics over time.

[0053] In this embodiment, the encoding vector of the fault mode and the time-series operation index data are jointly input into the Long Short-Term Memory Network Model. The Long Short-Term Memory Network Model outputs the specific fault module through the correspondence between the historical training fault modes, changes in operation indexes and fault modules.

[0054] S206: Determine the target health level of electronic equipment based on the values ​​of multiple operating indicators.

[0055] In this embodiment, the target health level of the electronic device is determined based on the values ​​of multiple operational indicators, using the following formula:

[0056]

[0057] in, Let i represent the target health status of the electronic device, where i represents the i-th operational indicator, and n represents the number of operational indicators. This represents the weight of the i-th performance indicator. This represents the value of the i-th operational indicator. This represents the minimum value of the i-th performance indicator. This represents the maximum value of the i-th operating indicator.

[0058] In this embodiment, the weights of each operating indicator can be adjusted according to actual conditions. For example, the weight of voltage is 0.3, the weight of clock jitter is 0.25, the weight of temperature is 0.2, and the weight of cyclic redundancy check error rate is 0.25.

[0059] In this embodiment, the weights of various operational indicators are dynamically adjusted using a digital twin model, such as increasing the weight of temperature in a high-temperature environment. The digital twin model simulates the execution results of different protection strategies under different ESD events based on event characteristics, the values ​​of multiple operational indicators, and protection strategies. The digital twin model can adapt the weights of various operational indicators to different ESD events.

[0060] In this embodiment, the target health status of the electronic device is updated in real time, once every 10 microseconds.

[0061] S207: Based on the faulty modules of the electronic equipment, determine the electrostatic discharge protection strategy of the electronic equipment under the target health level; where different target health levels correspond to different electrostatic discharge protection strategies.

[0062] In this embodiment, if the target health level of the electronic device is greater than or equal to the first health level threshold, the electrostatic discharge protection strategy of the electronic device is to maintain the operating state of the electronic device.

[0063] In this embodiment, the first health threshold is 0.8. When the target health is greater than or equal to the first health threshold, it indicates that the ESD event has a minor impact on the electronic device, the fault mode has no actual damage, and the faulty module has not affected the core function. Therefore, the protection strategy is to maintain only the current operating state of the electronic device; at the same time, the event characteristics are recorded to update the pre-built electrostatic discharge attack characteristic library. During this process, the processing latency is less than 1 microsecond and the CPU resource usage is less than 0.1%.

[0064] In this embodiment, if the target health level of the electronic device is less than the first health threshold and greater than the second health threshold, the electrostatic discharge protection strategy of the electronic device is to transfer the data in the faulty module of the electronic device and initialize the faulty module.

[0065] In this embodiment, the second health threshold is 0.4. When the target health is less than 0.8 but greater than 0.4, it indicates that the ESD event caused a minor anomaly in the faulty module. The protection strategy is as follows: critical data in the faulty module, such as cached data and link configuration information, are backed up by transferring them to a non-volatile dual in-line memory module (NVDIMM) or ferroelectric random access memory (FRAM) to avoid data loss; selective initialization is performed on the faulty module, such as resetting the network card data link module, while retaining core configurations, such as the PCIe link training state, to avoid a complete system restart. The recovery time during this process is approximately 3 to 5 milliseconds.

[0066] In this embodiment, if the target health level of the electronic device is less than or equal to the second health level threshold, the electrostatic discharge protection strategy of the electronic device is as follows: obtain the faulty power supply module in the faulty module of the electronic device, and the normal power supply modules in the electronic device other than the faulty power supply module; disconnect the electrical connection between the faulty power supply module and the normal power supply module; after disconnecting the electrical connection of the faulty power supply module, perform a discharge operation on the parasitic capacitor until the voltage of the parasitic capacitor is less than the safe voltage threshold; after the voltage of the parasitic capacitor is less than the safe voltage threshold, perform a power-on operation on the normal power supply module in the order of input / output module, calculation module and phase-locked loop module.

[0067] Among them, the first health threshold is greater than the second health threshold.

[0068] In this embodiment, a target health level of 0.4 or less indicates that an ESD event has damaged the power domain in the faulty module, causing a system crash. The protection strategy is implemented in three steps: power isolation, parasitic capacitance discharge, and phased power-on. First, the faulty power module in the faulty module and the normal power module of the electronic device are identified. The electrical connection of the faulty power module is disconnected to prevent its abnormal voltage from affecting the normal power module. After disconnecting the faulty power module, the parasitic capacitance in the electronic device is discharged until the voltage is below the safe voltage threshold to avoid residual discharge causing secondary damage. The normal power modules are powered on in a fixed sequence: first the input / output modules, then the computing modules, and finally the phase-locked loop modules to avoid instantaneous current surges that could damage the modules.

[0069] In this embodiment, when the target health level is less than 0.8 and greater than 0.4, critical data has been backed up to NVDIMM or FRAM. At this stage, critical data is directly read from the backup, and the working context is automatically restored. The working context refers to the service's operational state before the crash. In this process, the crash reconstruction time is shorter than traditional reset solutions. Traditional reset solutions require a complete machine restart, reconfiguration, and reloading of services.

[0070] In this embodiment, the first health threshold and the second health threshold are dynamically adjusted. Specifically, historical ESD events, along with the corresponding target health, first health threshold, second health threshold, protection strategy, and protection result, are acquired as training data. The protection result refers to whether the protection of the electronic device is successful. A reinforcement learning algorithm is selected and trained using the training data. The trained model is then used to adjust the first health threshold and the second health threshold based on event characteristics and the values ​​of multiple operational metrics. By dynamically adjusting the first and second health thresholds, the flexibility of the protection strategy is improved, thereby further enhancing the protection effect.

[0071] S208: Protect electronic equipment in accordance with electrostatic discharge protection strategies.

[0072] For example, taking a 6kV ESD attack on a PCIe network card as an example, during the process of determining the target health of the electronic device, the voltage score drops from 0.92 to 0.15, and the clock jitter score drops from 0.85 to 0.08, causing the target health to drop from 0.78 to 0.32. At this point, data is transferred, and the corresponding protection strategy is activated. After 2 milliseconds, the voltage returns to normal, the voltage score increases from 0.15 to 0.88, the clock jitter score increases from 0.08 to 0.4, and the target health increases from 0.32 to 0.65. At this point, the speed is reduced to PCIe Gen3 mode, and the corresponding protection strategy is activated. After 5 milliseconds, the clock jitter returns to normal, the voltage score increases from 0.88 to 0.95, the clock jitter score increases from 0.4 to 0.92, and the target health increases from 0.65 to 0.91.

[0073] For example, compared to directly performing a reset operation, a comparison is made in four aspects: recovery efficiency, data security, signal quality, and protection range. The recovery time of a direct reset operation is 120 milliseconds, while the recovery time of the method in this application is 18 milliseconds, representing an 85% improvement in recovery time; the data loss rate of a direct reset operation is 43%, while the data loss rate of the method in this application is less than 0.1%, a reduction of 99.7%; the signal quality of a direct reset operation decreases by 20%, while the signal quality of the method in this application decreases by 2%, a 10-fold optimization; the protection range of a direct reset operation is single-point protection, while the protection range of the method in this application is module-level, thus increasing the protection range.

[0074] In this embodiment, the fault recovery rate of the electrostatic discharge (ESD) event protection strategy is 99.998%, meeting ESD testing standards; the mean time between failures (MTBF) is increased to over 100,000 hours. Traditional methods use metal shields to protect a portion of the circuitry in electronic devices and add ESD protection components to the lines to isolate ESD events. ESD protection components include transient suppression diodes, varistors, and composite filter circuits. The method in this application replaces hardware protection, eliminating the need for metal shields and increasing the amount of ESD protection components, thus achieving cost optimization; the signal distortion rate of the PCIe network card is less than 1.5 dB; and the power consumption is low when implementing the protection strategy.

[0075] In summary, based on the values ​​of multiple operational indicators, the target health of electronic devices can be accurately obtained from multiple dimensions. When an electrostatic discharge (ESD) event is detected, event characteristics are acquired, and based on these characteristics and a pre-built ESD attack feature library, the failure mode of the ESD event can be determined. Based on the failure mode and the values ​​of multiple operational indicators, the faulty modules of the electronic device can be predicted, allowing for early identification of modules prone to failure. Combining the faulty modules of the electronic device, ESD protection strategies for the electronic device under different target health levels can be determined. Different target health levels correspond to different ESD protection strategies, enabling targeted protection of the electronic device according to these strategies. On the one hand, direct reset operations may lead to data loss and failure to recover from the fault. Compared to direct reset operations, the method of this application can provide targeted protection for the electronic device based on different ESD protection strategies corresponding to different target health levels, improving the fault recovery rate. On the other hand, by predicting the faulty modules of the electronic device, protection can be implemented before the faulty modules fail, preventing fault propagation, shortening fault handling time, and increasing the mean time between failures (MTBF) of the electronic device. Therefore, the effectiveness of electronic device protection can be improved.

[0076] refer to Figure 3 , Figure 3 Flowchart of the electrostatic discharge event protection method provided in the embodiments of this application Figure 2 In this embodiment, the processing procedure for when the target health level of the electronic device is less than or equal to the second health level threshold is supplemented and detailed below:

[0077] S301: Protect electronic devices through preset recovery strategies.

[0078] In this embodiment, if the target health level is less than or equal to 0.4, the region manager first protects the electronic device through a preset recovery strategy. The preset recovery strategy includes PCIe speed degradation and video memory refresh, etc.

[0079] S302: If the preset recovery strategy fails to protect the electronic device, then execute the electrostatic discharge protection strategy corresponding to when the target health of the electronic device is less than or equal to the second health threshold.

[0080] In this embodiment, if the electronic device is successfully protected by the preset recovery strategy, the electrostatic discharge protection strategy corresponding to the electronic device's target health level being less than or equal to the second health level threshold is not executed. If the electronic device fails to be protected by the preset recovery strategy, then the electrostatic discharge protection strategy corresponding to the electronic device's target health level being less than or equal to the second health level threshold is executed.

[0081] In summary, attempting to protect electronic devices using a pre-set recovery strategy reduces both protection time and resource consumption compared to directly implementing a protection strategy. Only if the pre-set recovery strategy fails to protect the electronic device will the electrostatic discharge (ESD) protection strategy corresponding to the target health level being less than or equal to the second health threshold be executed. This ESD protection strategy serves as a fallback solution to ensure effective repair of the electronic device.

[0082] refer to Figure 4 , Figure 4 Flowchart of the electrostatic discharge event protection method provided in the embodiments of this application Figure 3 In this embodiment, the disaster recovery strategy is described in detail below:

[0083] S401: When the electrostatic discharge protection strategy for electronic equipment cannot be determined based on event characteristics, the values ​​of multiple operational indicators, and a pre-built electrostatic discharge attack feature library, the disaster recovery strategy is activated.

[0084] In this embodiment, when the main controller fails, the electrostatic discharge (ESD) protection strategy of the electronic device cannot be determined, and a disaster recovery strategy is activated. The disaster recovery strategy involves the area manager determining the ESD protection strategy of the electronic device.

[0085] S402: Through disaster recovery strategies, based on event characteristics, the values ​​of multiple operational indicators, and a pre-built electrostatic discharge (ESD) attack feature library, determine the ESD protection strategy for electronic devices.

[0086] In this embodiment, the area manager determines the electrostatic discharge (ESD) protection strategy for electronic devices based on event characteristics, the values ​​of multiple operational metrics, and a pre-built ESD attack signature database. Furthermore, the area manager monitors the electronic devices using a dual watchdog mechanism to ensure their normal operation.

[0087] In summary, when the main controller malfunctions and is unable to make decisions on the electrostatic discharge protection strategy for electronic devices, activating the disaster recovery strategy can immediately fill the gap, preventing the electrostatic discharge event from continuing to affect the electronic devices due to decision delays, thereby ensuring the effectiveness of the protection.

[0088] Figure 5 A schematic diagram of the structure of the electrostatic discharge protection device provided in the embodiments of this application. Figure 5 As shown, embodiments of this application also provide a protection device for electrostatic discharge events, including: a detection module 501, an acquisition module 502, a first determination module 503, a collection module 504, a prediction module 505, a second determination module 506, a third determination module 507, and a protection module 508.

[0089] The detection module 501 is used to detect electrostatic discharge events that affect electronic equipment.

[0090] The acquisition module 502 is used to acquire event characteristics when an electrostatic discharge event is detected.

[0091] The first determining module 503 is used to determine the failure mode of an electrostatic discharge event based on the event characteristics and a pre-built electrostatic discharge attack characteristic library.

[0092] The acquisition module 504 is used to acquire the values ​​of multiple operating indicators of electronic equipment.

[0093] The prediction module 505 is used to predict the failure of electronic equipment based on the failure mode and the values ​​of multiple operating indicators.

[0094] The second determining module 506 is used to determine the target health level of electronic equipment based on the index values ​​of multiple operating indicators.

[0095] The third determining module 507 is used to determine the electrostatic discharge protection strategy of the electronic device under the target health level based on the fault module of the electronic device; wherein different target health levels correspond to different electrostatic discharge protection strategies.

[0096] Protection module 508 is used to protect electronic equipment according to electrostatic discharge protection strategies.

[0097] In one possible implementation, the first determining module 503 includes:

[0098] The first acquisition submodule is used to acquire the first electrostatic discharge waveform of the event features through a convolutional neural network model.

[0099] The second acquisition submodule is used to acquire a second electrostatic discharge waveform that matches the first electrostatic discharge waveform from multiple second electrostatic discharge waveforms in a pre-built electrostatic discharge attack feature library; wherein the pre-built electrostatic discharge attack feature library stores multiple second electrostatic discharge waveforms and the fault modes corresponding to each second electrostatic discharge waveform.

[0100] The first determination submodule is used to determine the fault mode corresponding to the second electrostatic discharge waveform as the fault mode of the electrostatic discharge event.

[0101] In one possible implementation, the protection device for electrostatic discharge events further includes a updating module, which includes:

[0102] A submodule is established to establish the mapping relationship between the first electrostatic discharge waveform of the unit's event characteristics and the fault mode of the electrostatic discharge event.

[0103] The update submodule is used to save the mapping relationship to the pre-built electrostatic discharge attack feature library to update the pre-built electrostatic discharge attack feature library.

[0104] In one possible implementation, the prediction module 505 includes:

[0105] The encoding submodule is used to encode the fault modes and obtain the encoding vector of the fault modes.

[0106] The conversion submodule is used to convert the values ​​of multiple operational indicators into time-series operational indicator data according to the time sequence of collection.

[0107] The prediction submodule is used to input the encoding vector and timing performance data into the Long Short-Term Memory (LSTM) network model, so that the LSM network model can predict the fault module of the electronic device based on the encoding vector and timing performance data.

[0108] In one possible implementation, the third determining module 507 includes:

[0109] The first judgment submodule is used to determine the electrostatic discharge protection strategy of the electronic device if the target health level of the electronic device is greater than or equal to the first health level threshold: maintain the operating state of the electronic device.

[0110] The second judgment submodule is used to determine the electrostatic discharge protection strategy of the electronic device if the target health level of the electronic device is less than the first health threshold and greater than the second health threshold: the data in the fault module of the electronic device is transferred and the fault module is initialized.

[0111] The third judgment submodule is used to determine the electrostatic discharge protection strategy of the electronic device if the target health level of the electronic device is less than or equal to the second health level threshold. The strategy is as follows: obtain the faulty power supply module in the faulty module of the electronic device, and the normal power supply modules in the electronic device other than the faulty power supply module; disconnect the electrical connection between the faulty power supply module and the normal power supply module; after disconnecting the electrical connection of the faulty power supply module, perform a discharge operation on the parasitic capacitor until the voltage of the parasitic capacitor is less than the safe voltage threshold; after the voltage of the parasitic capacitor is less than the safe voltage threshold, perform a power-on operation on the normal power supply module in the order of input / output module, calculation module and phase-locked loop module.

[0112] Among them, the first health threshold is greater than the second health threshold.

[0113] In one possible implementation, the third determination submodule further includes:

[0114] The protection unit is used to protect electronic devices through preset recovery strategies.

[0115] The execution unit is used to execute the electrostatic discharge protection strategy corresponding to the target health level of the electronic device being less than or equal to the second health level threshold if the preset recovery strategy fails to protect the electronic device.

[0116] In one possible implementation, the formula for the second determining module 506 is:

[0117]

[0118] in, Let i represent the target health status of the electronic device, where i represents the i-th operational indicator, and n represents the number of operational indicators. This represents the weight of the i-th performance indicator. This represents the value of the i-th operational indicator. This represents the minimum value of the i-th performance indicator. This represents the maximum value of the i-th operating indicator.

[0119] In one possible implementation, the detection module 501 includes:

[0120] The first receiving submodule is used to receive the voltage of the electronic device sent by the voltage sensor.

[0121] The second receiving submodule is used to receive the electromagnetic field strength and electromagnetic field change rate of the electronic device transmitted by the electromagnetic field probe.

[0122] The third receiving submodule is used to receive the rate of change of current of the electronic device sent by the current sensor.

[0123] The fourth judgment submodule is used to determine whether the triggering conditions for an electrostatic discharge event are met based on voltage, electromagnetic field strength, electromagnetic field change rate, and current change rate.

[0124] The determination submodule is used to determine that an electrostatic discharge event affecting the electronic device has been detected if the triggering conditions of the electrostatic discharge event are met. The triggering conditions of the electrostatic discharge event include at least one of the following: voltage exceeding a voltage threshold, electromagnetic field strength exceeding an electromagnetic field strength threshold, electromagnetic field change rate exceeding an electromagnetic field change rate threshold, and current change rate exceeding a current change rate threshold.

[0125] In one possible implementation, the protection device against electrostatic discharge events further includes a disaster recovery module. The disaster recovery module includes:

[0126] The startup submodule is used to initiate a disaster recovery strategy when the electrostatic discharge protection strategy of an electronic device cannot be determined based on event characteristics, the values ​​of multiple operating indicators, and a pre-built electrostatic discharge attack feature library.

[0127] The second determination submodule is used to determine the electrostatic discharge protection strategy for electronic devices based on event characteristics, the values ​​of multiple operational indicators, and a pre-built electrostatic discharge attack feature library, through disaster recovery strategies.

[0128] For a description of the features in the embodiment of the electrostatic discharge protection device, please refer to the relevant description of the embodiment of the electrostatic discharge protection method, which will not be repeated here.

[0129] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the electronic device further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus.

[0130] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to execute the above-described embodiment of the electrostatic discharge event protection method.

[0131] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0132] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0133] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0134] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0135] Embodiments of this application also provide a computer-readable storage medium storing a computer program configured to execute the steps in any of the above embodiments of the electrostatic discharge event protection method.

[0136] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0137] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the electrostatic discharge event protection method.

[0138] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the electrostatic discharge event protection method.

[0139] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0140] The foregoing has provided a detailed description of a method, apparatus, electronic device, medium, and product for protecting against electrostatic discharge events. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of these embodiments are only intended to aid in understanding the method and core concepts of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the scope of protection of the claims of this application.

Claims

1. A method for protecting against electrostatic discharge events, characterized in that, include: Detecting electrostatic discharge events that affect electronic devices; When the electrostatic discharge event is detected, the event characteristics are acquired; Based on the event characteristics and a pre-built database of electrostatic discharge attack characteristics, the failure mode of the electrostatic discharge event is determined. Collect the values ​​of multiple operating indicators of the electronic device; Based on the fault mode and the values ​​of the multiple operating indicators, predict the fault modules of the electronic device; The target health level of the electronic device is determined based on the values ​​of the multiple operating indicators. Based on the faulty modules of the electronic device, determine the electrostatic discharge protection strategy of the electronic device under the target health level; Different target health levels correspond to different electrostatic discharge protection strategies; The electronic device is protected according to the electrostatic discharge protection strategy described above.

2. The method according to claim 1, characterized in that, The step of determining the failure mode of the electrostatic discharge event based on the event characteristics and a pre-built electrostatic discharge attack feature library includes: The first electrostatic discharge waveform of the event features is obtained using a convolutional neural network model. From a pre-built electrostatic discharge attack feature library, a second electrostatic discharge waveform matching the first electrostatic discharge waveform is obtained; wherein the pre-built electrostatic discharge attack feature library stores a number of second electrostatic discharge waveforms and the fault modes corresponding to each second electrostatic discharge waveform. The fault mode corresponding to the second electrostatic discharge waveform is determined as the fault mode of the electrostatic discharge event.

3. The method according to claim 2, characterized in that, After determining the fault mode corresponding to the second electrostatic discharge waveform as the fault mode of the electrostatic discharge event, the method further includes: Establish a mapping relationship between the first electrostatic discharge waveform of the event characteristics and the failure mode of the electrostatic discharge event; The mapping relationship is saved to a pre-built electrostatic discharge attack feature library to update the pre-built electrostatic discharge attack feature library.

4. The method according to claim 1, characterized in that, The module for predicting the faults of the electronic device based on the fault mode and the values ​​of the multiple operating indicators includes: The fault mode is encoded to obtain the encoding vector of the fault mode; The values ​​of the multiple operational indicators are converted into time-series operational indicator data according to the time sequence of collection. The encoding vector and the timing performance index data are input into the Long Short-Term Memory (LSTM) network model, so that the LSM network model can predict the fault modules of the electronic device based on the encoding vector and the timing performance index data.

5. The method according to claim 1, characterized in that, The step of determining the electrostatic discharge protection strategy of the electronic device under the target health level based on the faulty module of the electronic device includes: If the target health status of the electronic device is greater than or equal to the first health status threshold, then the electrostatic discharge protection strategy of the electronic device is to maintain the operating state of the electronic device. If the target health status of the electronic device is less than a first health threshold and greater than a second health threshold, then the electrostatic discharge protection strategy of the electronic device is to transfer the data in the fault module of the electronic device and initialize the fault module. If the target health level of the electronic device is less than or equal to the second health level threshold, the electrostatic discharge protection strategy of the electronic device is as follows: Identify the faulty power supply module in the faulty module of the electronic device, and the normal power supply modules in the electronic device other than the faulty power supply module; disconnect the electrical connection between the faulty power supply module and the normal power supply module; after disconnecting the electrical connection of the faulty power supply module, perform a discharge operation on the parasitic capacitor until the voltage of the parasitic capacitor is less than the safe voltage threshold; after the voltage of the parasitic capacitor is less than the safe voltage threshold, sequentially perform a power-on operation on the normal power supply module in the order of input / output module, calculation module, and phase-locked loop module. Wherein, the first health threshold is greater than the second health threshold.

6. The method according to claim 5, characterized in that, After the target health level of the electronic device is less than or equal to the second health level threshold, the method further includes: The electronic device is protected by a preset recovery strategy; If the preset recovery strategy fails to protect the electronic device, then the electrostatic discharge protection strategy corresponding to when the target health of the electronic device is less than or equal to the second health threshold is executed.

7. The method according to claim 1, characterized in that, The formula for determining the target health level of the electronic device based on the values ​​of the multiple operating indicators is as follows: in, This represents the target health level of the electronic device, where i represents the i-th operating indicator, and n represents the number of operating indicators. This represents the weight of the i-th performance indicator. This represents the value of the i-th operational indicator. This represents the minimum value of the i-th performance indicator. This represents the maximum value of the i-th operating indicator.

8. The method according to any one of claims 1-7, characterized in that, The detection of electrostatic discharge events affecting electronic devices includes: Receives the voltage of the electronic device from the voltage sensor; The electronic device receives the electromagnetic field strength and electromagnetic field change rate transmitted by the electromagnetic field probe. The rate of change of current of the electronic device is received from the current sensor; Based on the voltage, the electromagnetic field strength, the rate of change of the electromagnetic field, and the rate of change of the current, determine whether the triggering conditions for the electrostatic discharge event are met. If the triggering conditions of the electrostatic discharge event are determined to be met, then it is determined that an electrostatic discharge event affecting the electronic device has been detected; wherein the triggering conditions of the electrostatic discharge event include at least one of the following: the voltage exceeds a voltage threshold, the electromagnetic field strength exceeds an electromagnetic field strength threshold, the electromagnetic field change rate exceeds an electromagnetic field change rate threshold, and the current change rate exceeds a current change rate threshold.

9. The method according to any one of claims 1-7, characterized in that, The method further includes: If the electrostatic discharge protection strategy of the electronic device cannot be determined based on the event characteristics, the index values ​​of the multiple operating indicators, and the pre-built electrostatic discharge attack feature library, a disaster recovery strategy shall be activated. Based on the disaster recovery strategy, the electrostatic discharge protection strategy of the electronic device is determined according to the event characteristics, the index values ​​of the multiple operating indicators, and the pre-built electrostatic discharge attack feature library.

10. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the method for protecting against electrostatic discharge events as described in any one of claims 1-9 when executing the computer program.

Images