Aging test equipment pre-protection control method and device based on fault prediction

Abstract

The embodiment of the invention provides an aging test equipment pre-protection control method and device based on fault prediction, and relates to the technical field of aging test equipment, and the method comprises the steps: carrying out the assessment of fault hazards through combining the severity of a fault and the fault prevention capability of each piece of sub-equipment according to a specific working scene; acquiring state information and a fault prediction model to obtain accurate prediction of a potential fault; based on the prediction result and a set fault hazard grade standard, a health state comprehensive evaluation algorithm of the aging test equipment is designed to reflect the health state of the aging test equipment in real time, and it is ensured that the aging test equipment can maintain stable operation when facing a fault risk through pre-designed corresponding protection control measures; and the machine can be stopped stably when faults which cannot be repaired effectively occur.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of non-destructive reliability screening of integrated circuits, and more particularly to a method and device for pre-protection control of aging test equipment based on fault prediction. Background Art

[0002] Existing high-temperature aging products can achieve long-term monitoring of the test environment by adding long-term in-machine monitoring and overstress protection mechanisms. This allows for timely response when a product fails, enabling post-fault repairs based on the failure data. However, due to the lack of active protection technologies for high-temperature aging products, existing aging products have difficulty in achieving the integrity of the test process and consistency of the test environment stress. This can easily lead to the test process being forced to be interrupted due to product failures, resulting in significant property losses such as damage to millions of test devices. Alternatively, due to adverse effects such as the introduction of additional stress during the test due to product performance degradation, the aging test may be deemed a failure test, resulting in an ineffective waste of resources. At the same time, ensuring the quality of high-temperature aging tests can prevent over-aging and under-aging failures in integrated circuits, significantly reducing the failure rate of integrated circuits and preventing large-scale electronic system failures such as new energy vehicles, civil airliners, and energy storage and transmission stations from shutting down due to integrated circuit failures.

[0003] During the testing process, various sub-devices or components of burn-in test equipment may malfunction. These failures may not only directly lead to test failure but also cause irreversible damage to the device under test. Therefore, ensuring that burn-in test equipment can maintain its stable operating state during operation and achieve a smooth shutdown when a fault cannot be repaired is a key technical issue that needs to be solved urgently. Summary of the Invention

[0004] In light of this, embodiments of this specification provide a method for pre-protection control of aging test equipment based on fault prediction. One or more embodiments of this specification also include a pre-protection control device for aging test equipment based on fault prediction, a computing device, a computer-readable storage medium, and a computer program to address technical deficiencies in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a method for pre-protection control of aging test equipment based on fault prediction is provided, comprising: Acquire real-time operating data and current basic information of each sub-device in the aging test equipment, and determine the current fault hazard level of each sub-device based on the current basic information of each sub-device; By inputting the real-time operating data of each sub-device into the fault prediction model, the fault prediction information of each sub-device is predicted; By inputting the current fault hazard level and fault prediction information of each sub-device into the health status comprehensive assessment algorithm, the health status and fault prediction time of each sub-device are obtained; The health status and fault prediction time of each sub-device are used to determine a pre-protection control strategy for each sub-device, and pre-protection control processing is performed on the sub-device based on the pre-protection control strategy for each sub-device.

[0006] Preferably, the current basic information includes: a current working scenario, a current severity level, and a current controllability level; wherein, determining the current fault hazard level of each sub-device based on the current basic information of each sub-device includes: Obtain a pre-built and stored aging test equipment hazard level table containing basic information on working scenarios, severity levels, and controllability levels, and the corresponding relationship between fault hazard levels; According to the current working scenario, current severity level and current controllability level of each sub-device, the fault hazard level corresponding to the current working scenario, current severity level and current controllability level of each sub-device is queried from the aging test equipment hazard level table, and the queried fault hazard level is used as the fault hazard level of each corresponding sub-device.

[0007] Preferably, determining the pre-protection control strategy for each sub-device by utilizing the health status and fault prediction time of each sub-device includes: Determine the critical time for triggering the early warning signal of each sub-device in the aging test equipment; Obtaining the current system running time of each sub-device in the aging test device; The pre-protection control strategy for each sub-device is determined by using the health status of each sub-device, the current system operating time, the fault prediction time and the critical time.

[0008] Preferably, the health status includes: healthy state, sub-healthy state and dangerous state; the fault prediction time includes: the first fault prediction time for the health status of each sub-device to enter the sub-healthy state from the healthy state and the second fault prediction time for the health status to enter the dangerous state from the sub-healthy state; the critical time includes: the first critical time and the second critical time; wherein, the first critical time is determined based on the fault predicted at the first fault prediction time, and is greater than the time required for the pre-protection controller corresponding to the fault to eliminate its impact; the second critical time is the time required to achieve a smooth shutdown in the face of the fault predicted at the second fault prediction time.

[0009] Preferably, determining the pre-protection control strategy for each sub-device by utilizing the health status of each sub-device, the current system operating time, the fault prediction time, and the critical time includes: If the health status of each sub-device is in a healthy state, and the difference between the first fault prediction time and the current system operation time is greater than or equal to the first critical time, it is determined that each sub-device is operating smoothly and no pre-protection control strategy is required; If the health status of each sub-device is in a dangerous state, a shutdown alarm is issued and emergency shutdown measures are immediately initiated without taking a pre-protection control strategy.

[0010] Preferably, the determining of the pre-protection control strategy for each sub-device by utilizing the health status of each sub-device, the current system operating time, the fault prediction time, and the critical time further comprises: If the health status of each sub-device is in a healthy state, and the difference between the first fault prediction time and the current system operation time is less than the first critical time, or if the health status of each sub-device is in a sub-healthy state, and the difference between the second fault prediction time and the current system operation time is greater than or equal to the second critical time, a secondary warning is issued, and a series of pre-designed protection and control measures are synchronously started according to the fault prediction information, so as to carry out effective intervention and protection before the fault occurs.

[0011] Preferably, the determining of the pre-protection control strategy for each sub-device by utilizing the health status of each sub-device, the current system operating time, the fault prediction time, and the critical time further comprises: If the health status of each sub-device is in a sub-healthy state, and the difference between the second fault prediction time and the current system operation time is less than the second critical time, a first-level warning is issued and smooth shutdown measures are executed at the same time; If during a smooth shutdown process, real-time monitoring is performed to determine whether the health status of each sub-device changes from a sub-healthy state to a dangerous state; If it is monitored that each sub-device enters a dangerous state from a sub-healthy state, a shutdown alarm is issued and emergency shutdown measures are immediately initiated; otherwise, each sub-device maintains a stable shutdown measure.

[0012] According to a second aspect of the embodiments of this specification, a pre-protection control device for aging test equipment based on fault prediction is provided, comprising: an acquisition module configured to acquire real-time operating data and current basic information of each sub-device in the aging test equipment, and determine a current fault hazard level of each sub-device based on the current basic information of each sub-device; A prediction module is configured to predict fault prediction information of each sub-device by inputting real-time operation data of each sub-device into a fault prediction model; An evaluation module is configured to obtain the health status and failure prediction time of each sub-device by inputting the current fault hazard level and failure prediction information of each sub-device into a health status comprehensive evaluation algorithm; The pre-protection control module is configured to determine the pre-protection control strategy of each sub-device by using the health status and fault prediction time of each sub-device, and perform pre-protection control processing on the sub-device based on the pre-protection control strategy of each sub-device.

[0013] According to a third aspect of an embodiment of this specification, a computing device is provided, including: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement any one of the steps of the aging test equipment pre-protection control method based on fault prediction.

[0014] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of any one of the methods for pre-protection control of aging test equipment based on fault prediction are implemented.

[0015] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned pre-protection control method for aging test equipment based on fault prediction.

[0016] The embodiments of this specification target specific work scenarios, evaluate the hazards of faults in combination with the severity of the faults and the fault prevention capabilities of each sub-device; utilize collected status information and fault prediction models to obtain accurate predictions of potential faults; and design a comprehensive health status assessment algorithm for aging test equipment based on the prediction results and established fault hazard level standards to reflect the health status of the aging test equipment in real time. Pre-designed corresponding protection and control measures are used to ensure that the aging test equipment can maintain stable operation when facing fault risks, and can be shut down smoothly when facing faults that cannot be effectively repaired. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a pre-protection control method for aging test equipment based on fault prediction provided by an embodiment of this specification; Figure 2 This is a structural diagram of a pre-protection control process of aging test equipment based on fault prediction provided by an embodiment of this specification; Figure 3 This is a schematic diagram of the health status of an aging test device at various times provided by an embodiment of this specification; Figure 4 This is a schematic diagram of the pre-protection controller architecture provided by an embodiment of this specification; Figure 5 This is a flowchart of the pre-protection control of the pre-protection controller 1 provided in one embodiment of this specification; Figure 6 This is a flowchart of the pre-protection control of the pre-protection controller 2 provided in one embodiment of this specification; Figure 7 This is a flowchart of the pre-protection control of the pre-protection controller 3 provided in one embodiment of this specification; Figure 8 This is a flow chart of the pre-protection control of the pre-protection controller 4 provided in one embodiment of this specification; Figure 9 This is a specific flow chart of a pre-protection control method for aging test equipment based on fault prediction provided by an embodiment of this specification; Figure 10 This is a schematic structural diagram of a pre-protection control device for aging test equipment based on fault prediction provided by an embodiment of this specification; Figure 11 This is a structural block diagram of a computing device provided by one embodiment of this specification. DETAILED DESCRIPTION

[0018] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0019] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0020] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0021] In this specification, a pre-protection control method for aging test equipment based on fault prediction is provided. This specification also involves a pre-protection control device for aging test equipment based on fault prediction, a computing device, a computer-readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.

[0022] Figure 1 A flow chart of a method for pre-protection control of aging test equipment based on fault prediction according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0023] Step S101: acquiring real-time operating data and current basic information of each sub-device in the aging test equipment, and determining the current fault hazard level of each sub-device based on the current basic information of each sub-device; In an optional embodiment, the current basic information includes: the current working scenario, the current severity level and the current controllability level; wherein, determining the current fault hazard level of each sub-device based on the current basic information of each sub-device includes: obtaining a pre-constructed and stored aging test equipment hazard level table containing the correspondence between the basic information of the working scenario, severity level and controllability level and the fault hazard level; according to the current working scenario, current severity level and current controllability level of each sub-device, querying the fault hazard level corresponding to the current working scenario, current severity level and current controllability level of each sub-device from the aging test equipment hazard level table respectively, and using the queried fault hazard level as the fault hazard level of each corresponding sub-device.

[0024] Step S102: predicting fault prediction information of each sub-device by inputting the real-time operating data of each sub-device into a fault prediction model; Step S103: The health status and failure prediction time of each sub-device are obtained by inputting the current fault hazard level and failure prediction information of each sub-device into the health status comprehensive evaluation algorithm; Step S104: using the health status and fault prediction time of each sub-device, determining a pre-protection control strategy for each sub-device, and performing pre-protection control processing on the sub-device based on the pre-protection control strategy for each sub-device.

[0025] In an optional embodiment, the method of determining the pre-protection control strategy for each sub-device by utilizing the health status and fault prediction time of each sub-device includes: determining the critical time for triggering the early warning signal of each sub-device in the aging test equipment; obtaining the current system operation time of each sub-device in the aging test equipment; and determining the pre-protection control strategy for each sub-device by utilizing the health status of each sub-device, the current system operation time, the fault prediction time, and the critical time. The health status includes: healthy state, sub-healthy state, and dangerous state; the fault prediction time includes: the first fault prediction time for the health status of each sub-device to change from healthy state to sub-healthy state, and the second fault prediction time for the health status of each sub-device to change from sub-healthy state to dangerous state; the critical time includes: the first critical time and the second critical time; the first critical time is determined based on the fault predicted at the first fault prediction time, and is greater than the time required for the pre-protection controller corresponding to the fault to eliminate its impact; the second critical time is the time required to achieve a smooth shutdown in the face of the fault predicted at the second fault prediction time.

[0026] In an optional embodiment, the use of the health status of each sub-device, the current system operation time, the fault prediction time and the critical time to determine the pre-protection control strategy of each sub-device includes: if the health status of each sub-device is in a healthy state, and the difference between the first fault prediction time and the current system operation time is greater than or equal to the first critical time, then it is determined that each sub-device is operating smoothly and no pre-protection control strategy needs to be adopted; if the health status of each sub-device is in a healthy state, and the difference between the first fault prediction time and the current system operation time is less than the first critical time, or if the health status of each sub-device is in a sub-healthy state, and the difference between the second fault prediction time and the current system operation time is greater than or equal to the second critical time, then a secondary pre-protection control strategy is issued. An alarm is issued, and a series of pre-designed protection and control measures are synchronously started according to the fault prediction information, so as to carry out effective intervention and protection before the fault occurs; if the health status of each sub-device is in a sub-healthy state, and the difference between the second fault prediction time and the current system operation time is less than the second critical time, a first-level warning is issued, and smooth shutdown measures are executed at the same time; if in the smooth shutdown process, the health status of each sub-device is monitored in real time to see whether it enters a dangerous state from a sub-healthy state; if it is monitored that each sub-device enters a dangerous state from a sub-healthy state, a shutdown alarm is issued and emergency shutdown measures are immediately started, otherwise, each sub-device maintains smooth shutdown measures; if the health status of each sub-device is in a dangerous state, a shutdown alarm is issued and emergency shutdown measures are immediately started, without the need to adopt pre-protection control strategies.

[0027] The embodiments of this specification evaluate the hazards of faults based on specific working scenarios, taking into account the severity of the faults and the fault prevention capabilities of each sub-device. Accurate predictions of potential faults are obtained by using collected status information and fault prediction models. Based on the prediction results and the established fault hazard level standards, a comprehensive health status assessment algorithm for aging test equipment is designed to reflect the health status of the aging test equipment in real time. Through pre-designed corresponding protection and control measures, it is ensured that the aging test equipment can maintain stable operation when facing the risk of failure, and can be shut down smoothly when facing faults that cannot be effectively repaired.

[0028] Figure 2 This is a structural diagram of a pre-protection control process of an aging test equipment based on fault prediction provided by an embodiment of this specification, such as Figure 2 As shown, specifically including: Failure hazard analysis and assessment First, three different working scenarios are defined according to the different stages of the aging test equipment workflow: the startup stage, the stable operation stage, and the test end stage, as shown in Table 1.

[0029] Table 1 Division of work scenarios

[0030] In order to clearly evaluate the fault conditions of each sub-device on the aging test equipment, the severity of the fault (Severity, represented by S) is divided into three gradually increasing levels: S0, S1, and S2 according to the technical safety requirements. The specific classification standards are detailed in Table 2.

[0031] Table 2 Severity levels

[0032] To evaluate the failure prevention capabilities of each sub-device, particularly its ability to quickly restore the system to stable operation by adjusting control algorithms or activating backup components when faced with potential failures, an evaluation system for controllability (C) was introduced. This system divides the controllability of each sub-device into three levels: C0, C1, and C2, with controllability gradually decreasing, as shown in Table 3.

[0033] Table 3 Controllability level

[0034] For the specific faults of each sub-device, the degree of harm caused by the fault to the aging test equipment is comprehensively evaluated from three dimensions: working scenario, severity level, and controllability level. Combined with the technical safety requirements, the degree of harm is divided into five levels from low to high: A, B, C, D, and E, as shown in Table 4 below.

[0035] Table 4 Hazard level of aging test equipment

[0036] System operation status information collection and storage To comprehensively monitor and manage the operating status of each sub-device, real-time operating data generated by each subsystem is collected and stored. Specifically, the collected information includes the temperature of the high-temperature test chamber, the voltage of the drive control protection board, the current and voltage of the primary and secondary switching power supplies, the temperature, current, and voltage of the MOSFET switching tube in the secondary power supply, and the temperature and humidity of the high-temperature and high-humidity test chamber.

[0037] Fault prediction and health status assessment of aging test equipment Fault prediction and identification By extracting the health status characteristics and key performance indicators of each sub-device (or subsystem), a data-driven approach is used to establish a fault prediction model. Based on this model and real-time system status information, key information such as the time of occurrence, probability, potential fault type, and fault severity is predicted.

[0038] Specifically, during the high-temperature aging test, sensors were used to collect multi-dimensional data, such as voltage, current, and temperature, from each sub-device. After data collection, the data was first filtered to eliminate noise. Interpolation was then used to fill missing values. The data was then normalized to map data with different characteristics to the same numerical range, ensuring accuracy and consistency, thereby obtaining high-quality data samples. Subsequently, a Transformer-based fault prediction model was established. During model training, the cross-entropy loss function was used as a loss metric to measure the difference between the model's predictions and the true labels. Simultaneously, the Adam optimizer was used to update the model parameters. During training, the training set data was input into the Transformer model. The backpropagation algorithm was used to calculate the gradient of the loss function with respect to the model parameters. The Adam optimizer then updated the model parameters based on these gradients. Training was iterated until the model achieved optimal performance on the validation set or met a pre-defined termination condition.

[0039] After training is completed, the health assessment curve of each subsystem is generated based on this model and the real-time status information of the system operation.

[0040] Health status assessment of aging test equipment By inputting each sub-device's current fault hazard level and fault prediction information into the comprehensive health status assessment algorithm, the health status and predicted failure time of each sub-device are determined. The system health status is then determined by weighted fusion of the health assessment curves generated by each subsystem's fault prediction model. Based on the predicted failure times provided by each subsystem's fault prediction model, a weighted average method is used to calculate the predicted failure time of the system. During this process, the weight corresponding to each subsystem is determined based on the fault hazard level standards clearly defined in the fault hazard analysis and assessment, expert knowledge, and analysis and statistics of historical data.

[0041] The algorithm can classify the health status of aging test equipment into three levels: healthy state, subhealthy state and dangerous state.

[0042] Healthy state: When all predicted faults are of low hazard level and the probability of fault occurrence is extremely low, the aging test equipment is considered to be in a healthy state and operating stably.

[0043] Subhealthy: If there is a prediction of a medium-criticality fault, or the probability of a low-criticality fault has increased but has not yet reached an emergency level, the burn-in test equipment is classified as subhealthy. This means that although there is a certain risk, the system can still operate safely under monitoring.

[0044] Dangerous state: If a high-hazard failure is predicted, or the cumulative risk of low- and medium-hazard failures reaches or exceeds a preset threshold, the burn-in test equipment is in a dangerous state. In this case, immediate shutdown measures should be taken to ensure system safety.

[0045] Pre-protecting the controller module Fault warning and corresponding measures Each moment is defined as follows: t – current moment, i.e. the real-time running time of the system; T1 - the moment when the health status of the aging test equipment enters the sub-healthy state; T2 - the moment when the health status of the aging test equipment enters a dangerous state.

[0046] Among them, T1 and T2 are given by the comprehensive evaluation algorithm of the health status of the aging test equipment, that is, the first fault prediction time and the second fault prediction time in the fault prediction time. The relationship between each time is as follows Figure 3 shown.

[0047] Based on the health status of the aging test equipment at the current moment and the time intervals between the current moment and the key time points T1 and T2, a set of fault warning strategies was designed. For details of the specific strategies, see Table 5.

[0048] Table 5 Fault warning and corresponding measures

[0049] In the table above, T_w1 and T_w2 are defined as preset time threshold intervals, which play a key role in triggering the early warning signal. T_w1 is determined based on the faults predicted by the fault prediction model at time T1. T_w1 should be selected to exceed the time required for the corresponding preemptive protection controller to eliminate the impact of these faults. This time is closely related to the equipment's operating status, fault severity, and device response time, and requires specific testing to determine. T_w2 should be selected to meet the time requirement for achieving a smooth shutdown in the event of a fault predicted at time T2. Similarly, this time is also related to factors such as the equipment's operating status, fault severity, and device response time, and requires verification through actual testing. Fault Early Warning Measures. Specifically, if the difference between the current time t and the predicted time point T1 is less than T_w1, or if the difference between the current time t and the predicted time point T2 is less than T_w2, the system automatically triggers the secondary early warning mechanism and simultaneously initiates a series of pre-designed protection and control measures to effectively intervene and prevent the fault before it occurs. If the system is in a subhealthy state, and the difference between the current time t and the predicted time point T2 is less than T_w2, the system will issue a more urgent Level 1 warning signal. At this point, a smooth shutdown will be immediately implemented, aiming to gradually reduce the system's operating status in an orderly manner, thereby minimizing the losses and impacts caused by the shutdown. If the system is in a dangerous state, the system will unconditionally issue a shutdown alarm and immediately initiate emergency shutdown measures to ensure the safety of personnel and equipment.

[0050] Healthy operation In this case, all performance indicators of the system remain within the preset safety range, the system runs smoothly, and no additional protective measures are required for intervention.

[0051] Preemptive protective control measures Based on fault prediction information and combined with the real-time operating status and characteristics of each sub-device, the system can quickly respond to and effectively deal with potential or existing faults by adjusting control algorithms or immediately enabling redundant backup components, thereby ensuring that the system can quickly recover to a stable and healthy operating state.

[0052] First, define the system prediction fault code as shown in Table 6 below.

[0053] Table 6 System Predicted Fault Codes

[0054] Furthermore, the pre-protection controller architecture is as follows Figure 4 shown.

[0055] Pre-protection controller 1 When the drive control protection board is predicted to be facing an overvoltage condition and the pre-protection mechanism is triggered, such as Figure 5 As shown, the digital signal generator, analog signal generator, and power supply PWM signal driver are first immediately stopped. The driver protection board is then reset. After the reset is complete, the digital signal generator, analog signal generator, and power supply PWM signal driver are restarted.

[0056] Pre-protection controller 2 When an overvoltage or overcurrent condition is predicted and the pre-protection mechanism is triggered, such as Figure 6 As shown, first adjust the power supply's drive control signal to reduce the PWM signal's duty cycle, thereby lowering the output voltage and current. If this measure fails to effectively improve the situation, safely isolate the faulty power module from the system and immediately activate a redundant power module to ensure unaffected power supply to the load.

[0057] Pre-protection controller 3 When the overheating risk of the switching device is predicted and the pre-protection mechanism is triggered, such as Figure 7 As shown, it should be turned off to prevent potential thermal damage. After that, it is necessary to wait for a preset safety cooling time to ensure that the switching device is fully cooled before turning it on again to maintain normal operation of the circuit.

[0058] Pre-protection controller 4 The temperature and humidity of the test chamber are determined by the heating wire, humidifier, fan and refrigerator. Figure 8 As shown, assume that the input of the pre-protection controller Corresponding to the normalized outputs of the heating wire, humidifier, fan and refrigerator, and the output of the pre-protection controller are the temperature and humidity of the test chamber respectively. Due to the complex working environment and potential unknown failures, it is impossible to establish an accurate system model.

[0059] Assume that the system satisfies the following incremental model:

[0060] Where, , , is the unknown pseudo-Jacobian matrix. The update law of the pseudo-Jacobian matrix and the control input is as follows:

[0061] Where, For design parameters, select according to actual debugging and experience, is the expected system output.

[0062] Smooth shutdown measures According to the technical safety requirements for aging test equipment, the temperature and humidity of the system are gradually reduced so that it can be gradually stopped in a safe and orderly manner.

[0063] Generate temperature and humidity target curves According to the current temperature and humidity, the following temperature and humidity target curve is constructed

[0064] Where, and are the desired temperature and humidity target values, and They are the safe temperature and humidity corresponding to shutdown. These are the design parameters obtained from actual debugging. The parameters selected here must ensure that the expected temperature is greater than the dew point temperature corresponding to the expected humidity.

[0065] Achieve smooth shutdown according to temperature and humidity target curves The pre-protection controller 4 is used to control the temperature and humidity to gradually reduce the temperature and humidity of the system until it shuts down.

[0066]

[0067] Where, The target values ​​of temperature and humidity generated by 4.4.1.

[0068] Emergency shutdown measures When the aging test equipment is in a dangerous state, quickly cut off the system power supply to protect personnel safety and minimize equipment damage.

[0069] Figure 9 FIG. 1 shows a specific flow chart of a method for pre-protection control of aging test equipment based on fault prediction provided by an embodiment of this specification, as shown in FIG. Figure 9 As shown, including: Step 901: Information collection and storage; The real-time operation data generated by each subsystem is collected and stored.

[0070] Step 902: Fault prediction model; Based on the fault prediction model and the real-time status information of the system operation, key information such as the time of occurrence, probability, potential fault type and fault severity of the fault is predicted.

[0071] Step 903: Health status assessment; Based on the prediction information provided by the fault prediction model and combined with the fault hazard level standards that have been clearly defined in the fault hazard analysis and assessment, a health status assessment algorithm is performed on the aging test equipment.

[0072] Step 904: According to the current health status and the set warning conditions, execute corresponding measures respectively: If the aging test equipment is in a healthy state and T1 - t >= T_w1, the aging test equipment runs smoothly and no additional protection measures are required for intervention; If the aging test equipment is in a healthy state and T1 - t < T_w1, a secondary warning is issued, and a series of pre-designed protection control measures are synchronously started according to the fault prediction information; If the aging test equipment is in a sub-healthy state and T2 - t >= T_w2, a secondary warning is issued, and a series of pre-designed protection control measures are synchronously started according to the fault prediction information; If the aging test equipment is in a sub-healthy state and T2 - t < T_w2, a primary warning is issued, and the smooth shutdown measure is executed simultaneously; Further, if the system is monitored to be in a dangerous state during the smooth shutdown process, a shutdown alarm is issued and the emergency shutdown measure is immediately started; otherwise, the system shuts down smoothly.

[0073] If the system is in a dangerous state, a shutdown alarm is issued and the emergency shutdown measure is immediately started.

[0074] [[ID=1s]]The embodiment of the present application also provides a method for determining the maintenance opportunity of the switching power supply of the aging test equipment, which is used to determine the maintenance opportunity during the pre-protection control process of the aging test equipment.

[0075] Further, the method for determining the maintenance opportunity of the switching power supply of the aging test equipment in the embodiment of the present application includes: Step 1001: Determine the regular maintenance opportunity of the switching power supply closest to the current moment.

[0076] The method for determining the maintenance opportunity of the switching power supply of the aging test equipment provided by the embodiment of the present application can be applied to an electronic device. An aging test equipment switching power supply maintenance computer program is set in the electronic device. When the computer program is executed by a processor, the method for determining the maintenance opportunity of the switching power supply of the aging test equipment in the embodiment of the present application is realized. The aging test equipment switch can be a front-end isolated switching power supply.

[0077] Through the aging test equipment provided by the embodiment of the present application, non-destructive aging detection can be performed on the test piece to be detected. In the embodiment of the present application, the maintenance opportunity of the switching power supply of the aging test equipment is determined, and the occurrence time of the next failure of the switching power supply of the aging test equipment can be predicted in advance, so as to ensure the safety of the test piece to be detected.

[0078] The maintenance timing for switching power supplies in burn-in test equipment is determined by combining scheduled maintenance timing and predicted maintenance timing (the first timing described below). The operating instructions or maintenance manual for burn-in test equipment typically include the expected lifespan and maintenance schedule for the switching power supply. Specifically, the preventive maintenance plan and time window under fault-free conditions are referred to as the "scheduled maintenance timing." Using fault prediction technology, the predicted time for the next switching power supply failure is calculated as the predicted maintenance timing.

[0079] An optional method for determining the periodic maintenance opportunity of the switching power supply closest to the current moment may be: Method 1: Find the nearest scheduled maintenance time from the scheduled maintenance schedule in the maintenance manual of the switching power supply of the aging test equipment; or Method 2: Determine the expected life of the switching power supply of the aging test equipment; calculate the nearest scheduled maintenance opportunity for the switching power supply based on the expected life and the average daily usage time of the switching power supply.

[0080] If the method in method 1 does not find a regular maintenance plan, consult the user manual of the switch power supply and obtain the expected life of the switch power supply of the aging test equipment from the manual. , then the regular maintenance time It can be set to the time when the service life is exhausted, which can be calculated by the following method:

[0081] in, The average daily usage time.

[0082] Step 1002: Predicting a first timing when a switching power supply fails.

[0083] Since the occurrence of failures is somewhat random, there are certain limitations in making maintenance timing decisions solely through “regular maintenance”. If a failure occurs before the scheduled maintenance time, it may cost manpower, material resources, and time, and affect the normal operation of the aging test equipment; if a failure occurs after the scheduled maintenance time, early maintenance will lead to an increase in maintenance costs per unit time. In view of the fact that regular maintenance times at fixed intervals are prone to “over-maintenance” or “under-maintenance”, the embodiment of the present application utilizes trend prediction technology to predict the time (i.e., the timing) when the switching power supply may fail in the future, and the predicted failure time is recorded as .

[0084] Step 1003: Determine a scheduled maintenance time window and a predicted maintenance time window based on the scheduled maintenance opportunity and the first opportunity respectively.

[0085] Since both the regular maintenance timing and the first timing have certain uncertainties, it is reasonable to carry out maintenance activities within a time window before or after this timing. In the embodiment of this application, the regular maintenance time window and the predicted maintenance time window are determined based on the regular maintenance timing and the first timing, and the target maintenance time window of the switching power supply is subsequently determined based on these two timing windows.

[0086] In an optional embodiment, the method for determining the scheduled maintenance time window according to the scheduled maintenance opportunity may be as follows: The difference between the scheduled maintenance opportunity and half of the preset time window parameter is determined as the lower limit of the scheduled maintenance time window; the sum of the first opportunity and half of the preset time window parameter is determined as the upper limit of the predicted maintenance time window.

[0087] Example: Setting time window parameters , then the regular maintenance time window can be expressed as:

[0088] In an optional embodiment, the method for determining the predicted maintenance time window according to the first opportunity may be as follows: The difference between the first opportunity and half of the preset time window parameter is determined as the lower limit value of the predicted maintenance time window; the sum of the first opportunity and half of the preset time window parameter is determined as the upper limit value of the predicted maintenance time window.

[0089] Example: Setting time window parameters , the predicted fault occurrence time (i.e. the first opportunity) is , then the predicted maintenance time window can be expressed as:

[0090] Step 1004: Calculate the target maintenance time window of the switching power supply according to the scheduled maintenance time window, the predicted maintenance time window, the preset objective function, and the constraints.

[0091] This step considers both the scheduled maintenance window and the predicted maintenance window, employing multiple constraints to solve the maintenance window for the switching power supply of the burn-in test equipment. The switching power supply maintenance window is defined as any moment within this window. Since the switching power supply is a core component of the burn-in test equipment, the predicted maintenance window should be as close to the scheduled maintenance window as possible, ensuring that the maintenance timing falls within the predicted maintenance window. This minimizes the impact of maintenance on the burn-in test equipment's scheduled testing schedule.

[0092] In an optional embodiment, based on the scheduled maintenance time window, the predicted maintenance time window, the preset objective function, and the constraints, the target maintenance time window for the switching power supply can be solved as follows: Determine whether the scheduled maintenance time window and the predicted maintenance time window have a time window intersection; If it exists, the intersection of the time windows is determined as the target maintenance time window of the switching power supply; if it does not exist, the target maintenance time window of the switching power supply is determined by multi-objective solution based on the regular maintenance time window, the predicted maintenance time window, the preset objective function and the constraints.

[0093] When the scheduled maintenance time window and the predictive maintenance time window have a time window intersection, the predictive maintenance time window (i.e., the target maintenance time window of the switching power supply) can be expressed as:

[0094] When there is no time window intersection between the scheduled maintenance time window and the predicted maintenance time window, the predictive maintenance time window is mainly based on the predicted maintenance time window.

[0095] When the scheduled maintenance window and the predictive maintenance window do not overlap, the predictive maintenance timing (i.e., the target maintenance timing for the switching power supply) is determined within the predictive maintenance window, taking into account the characteristics of the burn-in test equipment and the application scenario. As the maintenance window is delayed, component performance deteriorates, increasing the risk of failure. The power supply may fail at a critical moment, interrupting the test. This failure may also damage the burn-in test equipment and the test device, posing a serious safety hazard. As the maintenance window is advanced, maintenance activities are more likely to be performed before the equipment fails, resulting in wasted time and resources and increased maintenance costs. Furthermore, when using burn-in test equipment for testing, test plans are typically prepared in advance. A conflict between the predictive maintenance timing and the test plan can impact test progress, increasing test time and labor costs. Since the test plan is developed with reference to the maintenance plan, the degree of conflict between the predictive maintenance timing and the plan can be expressed using the scheduled maintenance timing. In summary, in order to balance various considerations, the above-mentioned cost-safety risk-test plan trade-off relationship is quantitatively expressed to solve the multi-objective maintenance timing problem, and a predictive maintenance timing optimization model is constructed. Based on the constructed optimization model, the target maintenance time window of the switching power supply is finally solved.

[0096] In an optional embodiment, based on the scheduled maintenance time window, the predicted maintenance time window, a preset objective function, and constraints, a method for solving the target maintenance time window of the switching power supply may include the following sub-steps: Sub-step 1: Set the objective function with maintenance time as the independent variable.

[0097] Among them, the objective function includes: the cost function representing the maintenance cost of the aging test equipment , representing the risk function of the safety risk of experimental terminal and equipment damage and a planning function representing the impact of schedule conflicts with the experimental plan .

[0098] The three objective function independent variables are maintenance time, and the domains are Among them, the cost function It is monotonically decreasing in the domain of definition, and the risk function It is monotonically increasing in the domain of definition, and the planning function It is related to the maintenance plan. Since the experimental risk is a strong constraint and the cost and plan are weak constraints, the quadratic form is used to fit the risk function and the linear form is used to fit the cost and plan function. The specific expression of the objective function can be shown as follows:

[0099]

[0100]

[0101] in, 、 、 is the fitting coefficient, Constitutes the domain , It is time for regular maintenance.

[0102] Sub-step 2: Initialize the particle swarm.

[0103] In sub-step 2, initialize the particle swarm and set particles, each particle group includes the following attribute information: used to characterize the location of the switch power supply maintenance time , used to characterize the speed of change of maintenance time in the optimization process and the individual historical best position used to characterize the optimal maintenance moment In addition, the best historical position of all particles is taken as the global best position , set the estimated maintenance interval window size to .

[0104] Sub-step 3: For each particle in the particle swarm, update the particle's velocity and position based on its velocity, individual historical best position, and global best position.

[0105] In actual implementation, the update can be achieved through the following formula:

[0106]

[0107] in, is the inertia weight, and is the learning factor, and It is a random number between 0 and 1.

[0108] Sub-step 4: Calculate the particle's fitness based on the updated velocity, position, and objective function.

[0109] In the actual implementation process, the weighted sum can be used to represent the fitness of the current particle, and the fitness calculation formula can be .in For the The fitness of a particle, 、 、 is the weight coefficient.

[0110] Sub-step 5: Based on the fitness and the fitness corresponding to the individual historical best position of the particle, the individual historical best position of the particle is updated.

[0111] For each particle in the particle swarm, if the fitness of the current particle position is better than the fitness of its individual historical best position, its position is updated to the individual historical best position; if it is better than the fitness of the global optimal position, its position is updated to the global optimal position.

[0112] For each particle in the particle swarm, sub-steps 3 to 5 are executed to obtain the individual best historical position of each particle.

[0113] Sub-step 6: Traverse the individual historical best position of each particle in the particle swarm, determine the maximum and minimum values ​​to generate the current maintenance time window.

[0114] Traverse the individual best historical positions of all particles , calculate its maximum and minimum values, and determine the current maintenance window , expressed as: .

[0115] By executing sub-steps 3 to 6, the calculation of the current maintenance time window can be completed.

[0116] Sub-step 7: If the current maintenance time window meets the preset conditions, determine the current maintenance time window as the target maintenance time window of the switching power supply, which is recorded as .

[0117] If the current maintenance time window meets the preset conditions, then execute sub-step 7, and the maintenance time window of the switching power supply of the aging test equipment is If the current maintenance time window does not meet the preset conditions, return to execute sub-step 3 to update the speed and position of each particle in the particle swarm according to the speed, individual historical best position and global best position, until sub-step 6 is completed to recalculate a current maintenance time window; again determine whether the recalculated current maintenance time window meets the preset conditions. If so, execute sub-step 7. If not, return to execute sub-step 3.

[0118] Repeat the process of sub-step 3 to sub-step 6 once or multiple times until the generated current maintenance time window meets the preset conditions and then execute step 7.

[0119] The preset condition can be set as follows: the difference between the upper limit and the lower limit of the current maintenance time window is less than Or equal to the expected maintenance interval window size, that is .

[0120] In a more preferred embodiment, the method of solving the target maintenance time window of the switching power supply may further include: Sub-step 8: Correct the target maintenance time window based on thermal parameters. The thermal parameters include the surface temperature data of two key components, MOSFET and capacitor, in the isolated switching power supply at the front end of the aging test equipment. By referring to the instructions for use of the aging test equipment, the rated operating temperature of MOSFET and capacitor can be obtained. The time that the surface temperature of MOSFET and capacitor exceeds their respective rated operating temperatures since the power-on is counted, which is called the over-limit time, and the correction rate is calculated. The formula is:

[0121] Pass correction rate Correct the target maintenance time window and obtain the corrected target maintenance time window, which is recorded as , the formula is:

[0122] This time window can also be called the predictive maintenance time window of the isolated switching power supply at the front end of the aging test equipment.

[0123] The method for determining the maintenance timing of a switching power supply for aging test equipment provided in an embodiment of the present application determines the scheduled maintenance timing of the switching power supply closest to the current moment; predicts the first time when a failure of the switching power supply will occur; determines a scheduled maintenance time window based on the scheduled maintenance timing; determines a predicted maintenance time window based on the first time; and solves a target maintenance time window for the switching power supply based on the scheduled maintenance time window, the predicted maintenance time window, a preset objective function, and constraints. The method provided in an embodiment of the present invention combines the scheduled maintenance timing with the fault prediction timing (i.e., the first time) to comprehensively plan and determine the predictive maintenance timing of the switching power supply. The determined target maintenance timing of the switching power supply is objective and reliable.

[0124] Corresponding to the above-mentioned embodiment of the pre-protection control method of aging test equipment based on fault prediction, this specification also provides an embodiment of a pre-protection control device of aging test equipment based on fault prediction. Figure 10 FIG1 shows a schematic diagram of a structure of a pre-protection control device for aging test equipment based on fault prediction provided by an embodiment of this specification. Figure 10 As shown, the device includes: The acquisition module 1001 is configured to acquire real-time operating data and current basic information of each sub-device in the aging test equipment, and determine the current fault hazard level of each sub-device based on the current basic information of each sub-device; The prediction module 1002 is configured to predict fault prediction information of each sub-device by inputting the real-time operation data of each sub-device into the fault prediction model; Evaluation module 1003 is configured to obtain the health status and failure prediction time of each sub-device by inputting the current fault hazard level and failure prediction information of each sub-device into the health status comprehensive evaluation algorithm; The pre-protection control module 1004 is configured to determine a pre-protection control strategy for each sub-device using the health status and fault prediction time of each sub-device, and perform pre-protection control processing on the sub-device based on the pre-protection control strategy of each sub-device.

[0125] The above is a schematic diagram of a pre-protection control device for aging test equipment based on fault prediction according to this embodiment. It should be noted that the technical solution of this pre-protection control device for aging test equipment based on fault prediction is based on the same concept as the technical solution of the pre-protection control method for aging test equipment based on fault prediction. For any details not described in detail in the technical solution of the pre-protection control device for aging test equipment based on fault prediction, please refer to the description of the technical solution of the pre-protection control method for aging test equipment based on fault prediction.

[0126] Figure 11The block diagram of a computing device 500 according to one embodiment of the present disclosure is shown. Components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and a database 550 is used to store data.

[0127] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)), whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0128] In one embodiment of the present specification, the above components of the computing device 500 and Figure 11 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 11 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0129] Computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 500 can also be a mobile or stationary server.

[0130] The processor 520 is configured to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned method for pre-protection control of aging test equipment based on fault prediction.

[0131] The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of this computing device is based on the same concept as the technical solution of the aforementioned method for pre-protection control of aging test equipment based on fault prediction. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the aforementioned method for pre-protection control of aging test equipment based on fault prediction.

[0132] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the above-mentioned method for pre-protection control of aging test equipment based on fault prediction are implemented.

[0133] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium is based on the same concept as the technical solution of the aforementioned method for pre-protection control of aging test equipment based on fault prediction. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the aforementioned method for pre-protection control of aging test equipment based on fault prediction.

[0134] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for pre-protection control of aging test equipment based on fault prediction.

[0135] The above is a schematic diagram of a computer program according to this embodiment. It should be noted that the technical solution of this computer program is based on the same concept as the technical solution of the aforementioned method for pre-protection control of aging test equipment based on fault prediction. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the aforementioned method for pre-protection control of aging test equipment based on fault prediction.

[0136] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0137] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium may be appropriately increased or decreased based on the requirements of legislation and patent practice within a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0138] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0139] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A pre-protection control method for aging test equipment based on fault prediction, characterized in that: include: Acquire the real-time operation data and current basic information of each sub-device in the aging test equipment, and determine the current fault hazard level of each sub-device based on the current basic information of each sub-device; By inputting the real-time operation data of each sub-device into the fault prediction model, the fault prediction information of each sub-device is predicted; By inputting the current fault hazard level and fault prediction information of each sub-device into the health status comprehensive evaluation algorithm, the health status and fault prediction time of each sub-device are obtained; The health status and fault prediction time of each sub-device are used to determine the pre-protection control strategy of each sub-device, and pre-protection control processing is performed on the sub-device based on the pre-protection control strategy of each sub-device.

2. The method according to claim 1, characterized in that The current basic information includes: the current working scenario, the current severity level and the current controllability level; wherein, based on the current basic information of each sub-device, determining the current fault hazard level of each sub-device includes: Obtain a pre-built and stored aging test equipment hazard level table containing basic information of working scenarios, severity levels, and controllability levels and the corresponding relationship between fault hazard levels; According to the current working scenario, current severity level and current controllability level of each sub-device, the fault hazard level corresponding to the current working scenario, current severity level and current controllability level of each sub-device is queried from the hazard level table of the aging test equipment respectively, and the queried fault hazard level is used as the fault hazard level of each corresponding sub-device.

3. The method according to claim 1, characterized in that Determining the pre-protection control strategy of each sub-device by using the health status and fault prediction time of each sub-device includes: Determine the critical time for triggering the early warning signal of each sub-device in the aging test equipment; Obtaining the current system running time of each sub-device in the aging test device; The pre-protection control strategy of each sub-device is determined by using the health status of each sub-device, the current system operating time, the fault prediction time and the critical time.

4. The method according to claim 3, characterized in that The health status includes: healthy state, sub-healthy state and dangerous state; the fault prediction time includes: the first fault prediction time for the health status of each sub-device to enter the sub-healthy state from the healthy state and the second fault prediction time for the health status to enter the dangerous state from the sub-healthy state; the critical time includes: the first critical time and the second critical time; wherein, the first critical time is determined based on the fault predicted at the first fault prediction time, and is greater than the time required for the pre-protection controller corresponding to the fault to eliminate its impact; the second critical time is the time required to achieve a smooth shutdown in the face of the fault predicted at the second fault prediction time.

5. The method according to claim 4, characterized in that Determining the pre-protection control strategy of each sub-device by using the health status of each sub-device, the current system running time, the fault prediction time and the critical time includes: If the health status of each sub-device is in a healthy state, and the difference between the first fault prediction time and the current system operation time is greater than or equal to the first critical time, it is determined that each sub-device is running smoothly and there is no need to adopt a pre-protection control strategy; If the health status of each sub-device is in a dangerous state, a shutdown alarm is issued and emergency shutdown measures are immediately initiated without taking a pre-protection control strategy.

6. The method according to claim 4, characterized in that The determining of the pre-protection control strategy of each sub-device by using the health status of each sub-device, the current system running time, the fault prediction time and the critical time further comprises: If the health status of each sub-device is in a healthy state, and the difference between the first fault prediction time and the current system operation time is less than the first critical time, or the health status of each sub-device is in a sub-healthy state, and the difference between the second fault prediction time and the current system operation time is greater than or equal to the second critical time, a secondary warning is issued, and a series of pre-designed protection and control measures are synchronously started according to the fault prediction information, so as to carry out effective intervention and protection before the fault occurs.

7. The method according to claim 4, characterized in that The determining of the pre-protection control strategy of each sub-device by using the health status of each sub-device, the current system running time, the fault prediction time and the critical time further comprises: If the health status of each sub-device is in a sub-healthy state, and the difference between the second fault prediction time and the current system operation time is less than the second critical time, a first-level warning is issued, and smooth shutdown measures are executed at the same time; If during the smooth shutdown process, real-time monitoring of the health status of each sub-device to see whether it changes from a sub-healthy state to a dangerous state; If it is monitored that each sub-device enters a dangerous state from a sub-healthy state, a shutdown alarm is issued and emergency shutdown measures are immediately initiated; otherwise, each sub-device maintains a stable shutdown measure.

8. A pre-protection control device for aging test equipment based on fault prediction, comprising: An acquisition module is configured to acquire real-time operation data and current basic information of each sub-device in the aging test equipment, and determine the current fault hazard level of each sub-device based on the current basic information of each sub-device; A prediction module, configured to predict fault prediction information of each sub-device by inputting real-time operation data of each sub-device into a fault prediction model; An evaluation module is configured to obtain the health status and failure prediction time of each sub-device by inputting the current failure hazard level and failure prediction information of each sub-device into a health status comprehensive evaluation algorithm; The pre-protection control module is configured to determine the pre-protection control strategy of each sub-device by using the health status and fault prediction time of each sub-device, and perform pre-protection control processing on the sub-device based on the pre-protection control strategy of each sub-device.

9. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the pre-protection control method of aging test equipment based on fault prediction as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the pre-protection control method for aging test equipment based on fault prediction as described in any one of claims 1 to 7.

Images