Microcomputer host aging test method and system

Abstract

The invention discloses a microcomputer host aging test method and system, and relates to the technical field of computer performance tests.The microcomputer host aging test method comprises the steps that to-be-tested equipment is connected to a test system, system standby test is conducted, and initial reference data are collected; constructing an aging prediction model and optimizing a model training strategy in combination with course learning and transfer learning; and performing a host preheating test and a high-load test by using AIDA64 based on a prediction result, synchronously operating a Heven Benchmark tool, and testing the graphic processing capability of the computer. The method combines a radial basis function neural network aging prediction model, carries out model training through curriculum learning and transfer learning, intelligently analyzes the CPU / GPU degradation trend, combines a quantum random number generator to generate a random load mode, simulates load fluctuation in an actual application scene, and improves the test trueness. In addition, a BIOS optimization strategy is provided to realize intelligent aging prediction and optimization regulation and control, so that the long-term stability and the service life of the microcomputer host are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer performance testing, and in particular to a microcomputer host aging testing method and system. Background Art

[0002] With the rapid development of computer hardware, microcomputer hosts have been widely used in industrial control, edge computing, smart home, embedded systems and other fields due to their small size, high energy efficiency and strong computing power. However, during long-term operation, computer hardware equipment gradually shows performance degradation or even failure due to factors such as heat accumulation, material aging, circuit loss, and storage medium fatigue, which affects the stability and service life of the system. Therefore, how to effectively evaluate the aging status of microcomputer hosts and optimize their operation strategies to extend their service life has become an important research direction in the current field of computer hardware engineering.

[0003] At present, the evaluation methods for computer hardware aging in the industry mainly include accelerated aging tests, temperature stress tests, power consumption monitoring, storage life evaluation, etc. These methods generally use long-term high-load operation, temperature and humidity extreme environment tests, etc. to observe the stability and performance degradation trend of the equipment under harsh conditions. For example, traditional computer aging tests usually use AIDA64 FPU to test CPU performance, Heaven Benchmark to evaluate GPU rendering capabilities, Rebooter to perform continuous restart tests, and S3 / S4 sleep recovery tests to verify the stability of low-power modes. These test methods can simulate different working scenarios, but there are problems such as long test cycles, insufficient data analysis, and limited test coverage, which makes it difficult to fully reflect the aging trends of microcomputer hosts in different application scenarios. In addition, most of the existing test methods rely on fixed test modes and cannot adapt to the aging characteristics of different devices, resulting in poor generalization of test results. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a microcomputer host aging test method and system to solve the problem that most existing test methods rely on fixed test modes and cannot adapt to the aging characteristics of different devices, resulting in poor generalization ability of test results.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a microcomputer host aging test method, which comprises: Connect the device under test to the test system, perform system standby testing, and collect initial benchmark data; Build an aging prediction model and optimize the model training strategy by combining curriculum learning and transfer learning; Based on the prediction results, AIDA64 was used to perform host warm-up tests and high-load tests, and the HeavenBenchmark tool was run simultaneously to test the computer's graphics processing capabilities; Use the quantum random number generator to generate random load patterns, alternate between high and low CPU / GPU loads, simulate real user scenarios, perform Rebooter and S3 / S4 sleep recovery tests, and trigger exceptions; Comprehensively analyze all test data and provide optimization suggestions.

[0007] As a preferred solution of the microcomputer host aging test method of the present invention, the construction of the aging prediction model and the optimization model training strategy in combination with curriculum learning and transfer learning include the following steps: Use radial basis function neural network model to build aging prediction model, define curriculum learning strategy, and divide curriculum learning into three stages: basic stage, adaptation stage and generalization stage for model training; The radial basis function neural network model trained through course learning is used as the starting point of transfer learning. The first N layers of the radial basis function neural network model are frozen and remain unchanged. Only the center point of the radial basis function neural network model in the last M layers is optimized. The correlation alignment loss function is used to align data features. The radial basis function neural network model is optimized using the gradient descent method. After the training is completed, the radial basis function neural network model parameters are updated. The radial basis function neural network model trained through transfer learning is saved as the final model. After normalizing the data in the benchmark data set, the data is input into the radial basis function neural network model to obtain the aging trend of the computer host.

[0008] As a preferred solution of the microcomputer host aging test method of the present invention, the host preheating test and high load test are performed using AIDA64 based on the prediction results, and the Heaven Benchmark tool is run simultaneously to test the computer's graphics processing capability, including the following steps: Calculate the baseline performance deviation ratio based on the prediction results , set threshold A, if the offset ratio is greater than threshold A, reduce the CPU core voltage in advance, run AIDA64 FPU test, record CPU temperature, power consumption and fan speed, and calculate the temperature change rate of CPU frequency through multiple steps and the actual frequency reduction ratio ; If the actual frequency reduction ratio is greater than the baseline performance deviation ratio, it means that the prediction error is large, and the BIOS adjustment mode is entered, including further reducing the CPU core voltage and increasing the fan speed; Continue to run the AIDA64 FPU test, record the CPU frequency and calculate the CPU frequency reduction rate, set the threshold D, if the CPU frequency reduction rate is less than the threshold D, enter the BIOS power reduction strategy, optimize the voltage and power consumption management, and simultaneously run HeavenBenchmark for GPU high load test, record the GPU frequency and calculate the GPU frequency reduction trend, if the GPU frequency reduction trend is less than the threshold D, adjust the GPU frequency management strategy and optimize the power consumption mode.

[0009] As a preferred solution of the microcomputer host aging test method of the present invention, wherein: the use of a quantum random number generator to generate a random load pattern, alternating high and low loads of the CPU / GPU, simulating real user scenarios, and calculating the system stability parameters after the high load test includes the following steps: Extract GPU frequency curve and CPU temperature curve from high load test results; Use quantum random number generator to generate nonlinear CPU load patterns and GPU load fluctuation ranges; Use the nonlinear mutation mode of the quantum random number generator to calculate the response time of the CPU load change and set the threshold I. If the response time is greater than the threshold I, the BIOS power reduction mode is entered; Switch Heaven Benchmark between high load, power saving mode and sleep mode; Calculate the GPU frequency fluctuation rate and set a threshold p. If the fluctuation rate is greater than the threshold p, enter the BIOS power reduction mode.

[0010] As a preferred solution of the microcomputer host aging test method of the present invention, the Rebooter and S3 / S4 sleep recovery tests and abnormal triggering include the following steps: Conduct a standardized test environment to ensure that the external power supply is stable. Call the Rebooter automated test script to perform H consecutive restarts and record the startup time of each restart. Calculate the startup time drift rate based on the maximum startup time and the minimum startup time, set the threshold E, and if the drift rate is greater than the threshold E, trigger anomaly detection and enter the low power recovery test. After the rebooter executes x reboots, it calls the ACPI command to put the device into S3 sleep mode, calculates the policy CPU response delay, sets the threshold J, and if the delay is greater than the threshold J, enters the BIOS adjustment; if the delay is less than or equal to the threshold J, continues to perform the S4 mode test; Send ACPI instructions to put the device into S4 mode, calculate the time required to enter sleep mode, trigger S4 mode recovery, calculate the consistency of storage data, if inconsistent, it means that the storage data is damaged, and perform automatic repair.

[0011] As a preferred solution of the microcomputer host aging test method of the present invention, the comprehensive analysis of all test data and providing optimization suggestions include: Calculate the average frequency of the CPU and GPU at the beginning of the test and at the current time point, collect the SSD read and write rates, calculate the device degradation rate based on the CPU / GPU frequency obtained at the current time point and the device's running time, and set a threshold F. If the degradation rate exceeds the threshold F, it indicates that the device is seriously aged and optimization measures need to be taken.

[0012] As a preferred solution of the microcomputer host aging test method of the present invention, the initial reference data refers to the fan speed, CPU frequency ,temperature and power consumption And GPU frequency ,temperature and power consumption , and the randomness measure of the initial state of the device .

[0013] In a second aspect, the present invention provides a microcomputer host aging test system, comprising: A data acquisition module is used to connect the device under test to the test system, perform system standby testing, and collect initial benchmark data; Aging prediction module, which is used to build an aging training model using a radial basis function neural network model, and improve the generalization ability of the model by combining curriculum learning and transfer learning; Performance testing module for CPU / GPU high load testing via AIDA64 + Heaven Benchmark; Mutation stress test module, used to generate nonlinear CPU / GPU load patterns, simulate real usage scenarios, calculate load response time, and trigger BIOS power reduction mode; The test module is used to perform the Rebooter continuous restart test, calculate the system stability, trigger anomaly detection, and optimize the sleep recovery strategy; The optimization suggestion module is used to comprehensively analyze all test data and provide equipment optimization suggestions.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the microcomputer host aging test method as described in the first aspect of the present invention is implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the microcomputer host aging test method as described in the first aspect of the present invention is implemented.

[0016] The beneficial effects of the present invention are as follows: the present invention combines the radial basis function neural network aging prediction model, uses curriculum learning and transfer learning to perform model training, intelligently analyzes the CPU / GPU degradation trend, and combines the quantum random number generator to generate random load patterns, simulates load fluctuations in actual application scenarios, and improves the authenticity of the test. In addition, the present invention provides BIOS optimization strategies, such as dynamically adjusting the CPU / GPU frequency, optimizing the fan strategy, and enabling the SSD TRIM operation, to achieve intelligent aging prediction and optimization regulation, thereby improving the long-term stability and service life of the microcomputer host. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 This is a flow chart of the microcomputer host aging test method in Example 1.

[0019] Figure 2 This is a structural diagram of the microcomputer host aging test system in Example 1.

[0020] Figure 3 This is a schematic diagram of the process of training the aging model in Example 1.

[0021] Figure 4 This is a schematic diagram of the load test process in Example 1. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0025] Example 1, reference Figure 1-Figure 4 , which is the first embodiment of the present invention, provides a microcomputer host aging test method, comprising the following steps: S1. Connect the device under test to the test system, perform system standby test, and collect initial benchmark data; Specifically, select a standard regulated power supply (DC 12V±0.5V), ensure that the input voltage is stable, connect a power sensor, measure and record the input voltage V, and calculate the standby power consumption: , In the formula, is the standby power consumption, V is the input voltage, and I is the standby current; Connect the current sensor to the host power input terminal and configure the sampling frequency (1kHz) to record the initial current. , calculate its mean, if If the deviation is more than 10% from the normal value, check the power supply system of the equipment under test; Read SSD SMART data, record health status, perform a 10-minute standby test, and record fan speed and CPU frequency ,temperature and power consumption And GPU frequency ,temperature and power consumption ; The permutation entropy (PE) method is used to calculate the system state distribution of the device under test in the standby state. The permutation entropy (PE) is used as the randomness measure of the initial state. The calculation formula is as follows: ; In the formula, is the base permutation entropy, is the probability of the jth system state occurring, k is the number of possible states of the system; In this test environment, the system status refers to the performance of the CPU, GPU, and other key hardware components within a specific time window, including but not limited to the following indicators: CPU status, GPU status, storage device status, cooling system status, and memory status; Integrate benchmark datasets based on collected data: .

[0026] Select a standard regulated power supply (DC 12V±0.5V) to ensure stable input voltage, avoid test results affected by power supply voltage fluctuations, ensure a stable test environment, maintain the stability of the host's internal power supply, and prevent mismeasurements caused by power supply anomalies. Use this as a test benchmark to make data between different test devices more comparable. Connect a power sensor, measure and record input voltage, calculate standby power consumption, accurately measure the host's standby power consumption, evaluate the power consumption of the device in different operating modes, and monitor the power supply system status. If power consumption increases abnormally, it may indicate hardware anomalies or that standby mode is not correctly activated. After calculating power consumption, you can further combine BIOS adjustment strategies to optimize power consumption management and improve host energy efficiency. Connect a current sensor, configure sampling frequency (1kHz), record initial current, and high-frequency sampling (1kHz) to improve test accuracy and ensure that small current fluctuations are detected. Read SSD SMART Data, recording the health status can detect the degree of SSD degradation in advance, such as key parameters such as write life, I / O rate, temperature, etc., perform a 10-minute standby test, record fan speed, CPU frequency, temperature, power consumption and GPU frequency, you can identify whether the fan strategy needs to be adjusted, analyze the standby power consumption performance of the device, compare it with high-load test data, quantify the aging trend, use the permutation entropy (PE) method to calculate the randomness of the system state, provide a tool for quantitatively evaluating the stability of the device standby state, and help identify the degree of system fluctuations.

[0027] S2, build an aging prediction model and optimize the model training strategy by combining curriculum learning and transfer learning; Specifically, building an aging prediction model and optimizing the model training strategy by combining curriculum learning and transfer learning includes the following steps: The aging prediction model was constructed using the radial basis function neural network model, including the input layer, hidden layer and output layer, and the course learning strategy was defined, which divided the course learning into three stages: the basic stage, the adaptation stage and the generalization stage; The basic stage refers to the first 10% of the test time, which is used for initial training, using low-complexity data to reduce model errors and ensure stability; The adaptation phase refers to 10%-50% of the test time, which is used to increase data complexity and improve the model's adaptability to aging trends; The generalization phase refers to more than 50% of the test time, which is used to optimize the generalization ability of the model, adapt it to different aging modes, and optimize the BIOS resource management strategy; Collect historical equipment data and normalize it, use the aging trend curve of historical data as the initial approximate prediction value, use weighted mean square error to calculate the training error in the basic stage, reduce the impact of outliers on the model in the early training process, use 90% real data and 10% predicted data for training, prevent over-reliance on predicted values ​​from causing unstable initial training results, set the learning rate to 0.01 to reduce gradient fluctuations and improve convergence stability, train RBFNN to enable it to initially learn data distribution characteristics, and provide a basis for subsequent training stages; In the adaptation phase, more complex aging features are collected, including storage I / O rate and thread management abnormal data (thread starvation, thread deadlock, and thread leakage). 80% of real data and 20% of predicted data are used for training to improve the adaptability of the model to long-term operation. Huber loss is used to handle outliers. This loss function is used during training to reduce the impact of sudden abnormal data on model convergence. The learning rate is decayed to 0.005 to prevent training oscillations in the model during the adaptation phase. The thread starvation is measured by the thread waiting time. If the waiting time is too long, it means that the thread is in a starvation state for a long time. The thread deadlock is measured by the thread mutex waiting time. If the waiting time increases for a long time, there may be a deadlock risk. The thread leakage is measured by the total number of active threads. If the total number continues to increase while the CPU load does not increase significantly, there may be a thread leakage. The specific judgment criteria are determined according to the actual application scenario and the experience of professionals; In the generalization stage, we collected system call exception data (invalid parameters, unavailable resources, timeouts, and interruptions) and process management status data (new state, ready state, running state, blocked state, and terminated state). We used 70% real data and 30% predicted data for training to improve the generalization ability of the model. We used the L1+L2 combined loss function for regularization to prevent the model from overfitting. We reduced the learning rate to 0.001 to ensure the final convergence of the model. The radial basis function neural network model trained through course learning is used as the starting point of transfer learning. The first N layers of the radial basis function neural network model are frozen and remain unchanged, and only the last M layers are optimized. The KL divergence is used to evaluate the difference between the new device data distribution and the old device data. The judgment threshold P is set by the cross-validation method. If the difference is greater than the threshold P, it means that the new device data distribution is different from the old device data, and data normalization processing is required (through Z-score normalization and batch normalization method). If the difference is less than or equal to the threshold P, transfer learning training is directly entered without additional data preprocessing. During the transfer learning training process, only the center point of the radial basis function neural network model is optimized, and the correlation alignment loss function is used to align data features to reduce the differences in data distribution of different devices. The radial basis function neural network model is optimized using the gradient descent method. After the training is completed, the radial basis function neural network model parameters are updated, and the radial basis function neural network model completed by transfer learning training is saved as the final model. After normalizing the data in the benchmark dataset, the data is input into the radial basis function neural network model to obtain the aging trend of the computer host.

[0028] The basic stage (the first 10% of the test time) improves the robustness of the initial model to ensure that subsequent training will not be disturbed by early prediction errors. The adaptation stage (10%-50% of the test time) improves the model's adaptability to complex aging patterns and enhances the prediction accuracy of devices running for a long time. The generalization stage (more than 50% of the test time) improves the model's adaptability on different devices and improves the generalization effect of aging prediction. Transfer learning (TL) optimizes the adaptability of new devices, reduces the distribution difference of data between new and old devices, improves the generalization ability of the model, and makes aging prediction more accurate. In the process of transfer learning, the correlation alignment loss function (CORAL) is used to reduce the difference in data distribution between devices, improve the consistency of the model on different devices, and reduce the migration error caused by data distribution differences.

[0029] S3. Based on the prediction results, use AIDA64 to perform host warm-up test and high-load test, and simultaneously run the HeavenBenchmark tool to test the computer's graphics processing capabilities; Specifically, based on the prediction results, AIDA64 is used to perform host warm-up tests and high-load tests, and the Heaven Benchmark tool is run simultaneously to test the computer's graphics processing capabilities. The following steps are included: Calculate the baseline performance deviation ratio based on the prediction results : , In the formula, is the predicted frequency reduction trend, is the initial CPU frequency; A threshold A is set based on the calculation method of the quantile of historical data. If the offset ratio is greater than the threshold A, the CPU core voltage is reduced in advance. Run the AIDA64 FPU test, increasing the load by 10% every 5 minutes until the load reaches 50% for 30 minutes, record the CPU temperature, power consumption and fan speed, and calculate the temperature change rate of the CPU frequency through multiple steps and the actual frequency reduction ratio : ; In the formula, is the CPU frequency change, is the CPU temperature change; ; In the formula, is the initial CPU frequency, is the CPU frequency attenuation; If the actual frequency reduction ratio is greater than the baseline performance deviation ratio, it means that the prediction error is large, and the BIOS adjustment mode is entered, including further reducing the CPU core voltage and increasing the fan speed; Continue to run the AIDA64 FPU test, increase the CPU load to 100% and maintain it for 3.5 hours, record the CPU frequency and calculate the CPU frequency reduction rate, set the threshold D based on industry experience, and if the CPU frequency reduction rate is less than the threshold D, enter the BIOS power reduction strategy to optimize voltage and power management; Simultaneously run Heaven Benchmark for GPU high load testing (4K rendering + maximum anti-aliasing + maximum lighting rendering) for 3.5 hours; Record GPU frequency and calculate GPU downclocking trend : ; In the formula, is the actual operating frequency of the GPU at the current moment, is the base frequency of the GPU at the beginning of the test, and t is the running time; If the GPU frequency reduction trend is less than the threshold D, the GPU frequency management strategy is adjusted to optimize the power consumption mode.

[0030] Based on the prediction results, intelligent aging test optimization is performed, CPU and GPU load tests are performed through AIDA64 and Heaven Benchmark, and dynamic analysis is performed in combination with the benchmark performance offset ratio, CPU frequency change rate, and GPU frequency attenuation rate. At the same time, the CPU / GPU operating status is optimized through BIOS adjustment strategies to improve heat dissipation efficiency, reduce power consumption, and improve the long-term stability of the device. Compared with traditional fixed-mode aging tests, this method is more intelligent, adaptable, and has power optimization capabilities.

[0031] S4, using the quantum random number generator to generate random load patterns, alternating high and low CPU / GPU loads, simulating real user scenarios, performing Rebooter and S3 / S4 sleep recovery tests, and performing abnormal triggering; Specifically, using a quantum random number generator to generate a random load pattern, alternating high and low CPU / GPU loads, simulating real user scenarios, and calculating system stability parameters after high load testing includes the following steps: Extract GPU frequency curve and CPU temperature curve from high load test results; Use quantum random number generator to generate nonlinear CPU load patterns and GPU load fluctuation ranges; The generating nonlinear CPU load mode refers to connecting a quantum random number generator based on single photon detection to the test system to ensure that it can stably output a random number stream, setting the sampling rate of the quantum random number generator so that it can provide random number data in real time, usually set at more than 1 Mbps (million bits per second) to ensure that the random number generation speed meets the CPU load regulation requirements, running the quantum random number generator self-test program to verify whether its output meets the uniform randomness requirements, using standard NIST randomness tests (such as single-bit frequency test, run test, block frequency test, etc.) to ensure that the generated random number sequence is qualified, obtaining the original random bit stream generated by the quantum random number generator through an API or driver, using a bit conversion algorithm to convert the binary random sequence into a floating-point random sequence W, using 16 bits as a data block to convert into a floating-point number between 0 and 1, and using a linear transformation to convert the data into a range of [-1,1] so that the change in CPU load can fluctuate upward or downward; Since noise may occur in the quantum measurement process, the random numbers are filtered for uniformity to ensure that the random number distribution is close to the standard uniform distribution. The sliding window smoothing algorithm is used to pre-process W so that the random load changes will not have extreme deviations; Extract the CPU's operating parameters under high load, including the maximum load power consumption and the benchmark load power consumption. Use the random number generated by the quantum random number generator to regulate the CPU load. If the random number is greater than 0, increase the CPU load, and the amplitude is controlled by the quantum random number generator. If the random number is less than 0, reduce the CPU load, and the amplitude is also controlled by the quantum random number generator. Record the CPU load variation range, and adjust the range of the quantum random number generator according to the load variation range. For example, if the load variation range is greater than 30% (the load variation is too large), reduce the load variation range of the quantum random number generator. If the load variation range is less than 10%, expand the load range of the quantum random number generator. Generating the GPU load fluctuation range includes reading the GPU frequency and power consumption data when the Heaven Benchmark is running, and calculating the GPU power consumption fluctuation rate recorded by the Heaven Benchmark; Use the quantum random number generator to generate a set of real random numbers to control the switching of GPU load mode: The GPU load of Heaven Benchmark is usually relatively stable. The random numbers generated by the quantum random number generator can simulate the uncertainty of GPU load and improve the authenticity of the test. Use the random numbers generated by the quantum random number generator to regulate the GPU load, record the GPU load change range, and use Heaven Benchmark to make sudden changes in the GPU load in the following mode: High-performance mode (GPU frequency full load): simulates high-load scenarios such as games and deep learning training; Power saving mode (GPU frequency reduced by 30%): simulates normal web browsing, video playback and other scenarios; Sleep mode (GPU enters the lowest power consumption state): simulates long-term idle state; Generate random loads through the quantum random number generator to control the switching time between different modes of Heaven Benchmark, ensuring that the GPU load can truly reflect the changes in burst computing tasks; Generate random numbers through the quantum random number generator to control the mutation process of GPU load and simulate the GPU load mutation in tasks such as game rendering and deep learning reasoning; The actual GPU load data recorded by Heaven Benchmark is used as the benchmark parameter to ensure that the changes in GPU load are reasonable; If the GPU load changes too much (more than 25%), adjust the quantum random number generator calculation formula to make the GPU load more stable; If the GPU load change is too small (less than 10%), increase the fluctuation range generated by the quantum random number generator to ensure that the GPU load change is more in line with the actual application scenario; The GPU frequency and power consumption data recorded by Heaven Benchmark are compared with the GPU load fluctuations generated by the quantum random number generator to ensure that GPU load mutations will not cause overheating or abnormal crashes. If the GPU load mutation exceeds the device tolerance threshold (for example, the temperature is higher than 85°C), the fan speed-up mode is entered to reduce the GPU load and optimize heat dissipation management. Using the quantum random number generator nonlinear mutation mode, load fluctuation is performed every 20 seconds (the load adjustment range is 30%-100%, and the maximum instantaneous change amplitude ), calculate the CPU load change response time, dynamically set the threshold I based on the sliding window statistics, and enter the BIOS power reduction mode if the response time is greater than the threshold I; Switch Heaven Benchmark between high performance mode, power saving mode and sleep mode; Calculate the GPU frequency fluctuation rate, and set the threshold p by counting the standard deviation of the fluctuation rate. If the fluctuation rate is greater than the threshold p, enter the BIOS power reduction mode.

[0032] Traditional aging tests usually use a fixed CPU load curve, such as linear increase or constant full load, while the random load pattern generated by the quantum random number generator can more accurately simulate nonlinear load fluctuations in actual application scenarios, such as burst computing tasks, switching between high-load tasks, etc. Since the load fluctuations generated by the quantum random number generator are nonlinear and highly random, they can avoid the pattern dependence that may occur in fixed load tests, improve the scope of application of the test, and make the test results more representative. By using the quantum random number generator to control CPU load fluctuations and dynamically adjusting the fluctuation amplitude generated by the quantum random number generator according to the load variation range, it can ensure that the CPU load test is closer to the actual operating environment and improve the accuracy of aging prediction. Heaven Benchmark usually uses a constant load when running, but in actual application scenarios, the GPU load fluctuates greatly. For example, in tasks such as games and AI computing, the GPU load will mutate. The present invention uses random numbers generated by a quantum random number generator to control the GPU load mode and simulate GPU load mutations to make the test more in line with actual usage. The quantum random number generator is used to control Heaven Benchmark to run in different modes (high performance mode, power saving mode, and sleep mode), which ensures that the GPU load test not only covers high-load tasks, but also includes low-power modes, making the test more comprehensive. If the GPU load fluctuation is too large, it may cause the GPU temperature to rise above a safe threshold (e.g., 85°C). The present invention uses a quantum random number generator to control the GPU load, so that the GPU load fluctuation is in line with the set range, avoiding GPU overheating and improving the long-term stability of the device. In many computing tasks, the CPU and GPU need to work together, such as games, video processing, and AI training. The present invention adopts a quantum random number generator to control the CPU / GPU load, so that its load mode can be dynamically adjusted, which is more in line with the actual application scenario. The quantum random number generator is used to perform CPU / GPU load switching test, and the CPU load change response time is calculated to ensure that the CPU / GPU load switching will not cause system instability or crash, thereby improving the reliability of the test. Heaven Benchmark provides GPU load benchmark test data. The present invention controls the GPU load mode through a quantum random number generator, so that the test is more stable and there will be no excessive load fluctuations. The GPU frequency and power consumption data recorded by Heaven Benchmark can be used to optimize the calculation formula of the quantum random number generator, so that the GPU load change is more in line with the actual application scenario, thereby improving the test accuracy.

[0033] Furthermore, to ensure that the device can normally enter low power mode after high load operation and maintain data integrity at startup, the rebooter and S3 / S4 sleep recovery tests and abnormal triggering include the following steps: Conduct a standardized test environment to ensure that the external power supply is stable. Call the Rebooter automated test script to perform H consecutive restarts and record the startup time of each restart. Calculate the startup time drift rate based on the maximum startup time and the minimum startup time. Set the threshold E by performing statistical analysis on historical data. If the drift rate is greater than the threshold E, anomaly detection is triggered and low-power recovery test is entered. After Rebooter executes 10 reboots, it calls the ACPI (Advanced Configuration and Power Interface) command to put the device into S3 sleep mode, records the total time of entering sleep mode, waits for 180 seconds, simulates the normal user usage scenario, presses the power button or keyboard and mouse to wake up the device, records the time required for wake-up, runs scheduled calculation tasks (such as CPU instruction cycle calculation), calculates the strategy CPU response delay, and sets the threshold J through experiments. If the delay is greater than the threshold J, it indicates that the CPU has a delay after waking up, which may be caused by power consumption management problems. Enter BIOS to adjust. If the delay is less than or equal to the threshold J, it means that the CPU response time is normal, and continue to perform S4 (sleep) mode test; Send ACPI instructions to put the device into S4 mode. The device shuts down all active processes, writes the data in the memory to the storage device, and completely turns off the power. The time required to enter hibernation is calculated. After the device is completely powered off for 30 minutes, press the power button to trigger S4 mode recovery and calculate the consistency of the storage data. If it is inconsistent, it means that the storage data is damaged and automatic repair is performed.

[0034] The present invention introduces Rebooter restart test and S3 / S4 sleep recovery test, and combines with automatic abnormality detection mechanism, which significantly improves the aging test accuracy of microcomputer host. The traditional method only monitors a single restart time. The present solution calculates the drift rate through multiple continuous tests, which can detect the startup delay caused by storage device degradation or BIOS configuration problems earlier, and provide data support for device optimization. The traditional low-power mode test only detects whether the device can be restored. The present solution further quantifies key parameters such as CPU response time and storage data consistency to ensure that power consumption management and data integrity meet industrial standards. The traditional method only detects abnormalities but does not provide optimization suggestions. When the present solution detects abnormal startup time drift rate, excessive CPU response delay, and storage data damage, it can automatically adjust the BIOS settings, optimize the device power consumption management strategy, and improve the long-term stability of the device. If the traditional method finds that the dormant data is damaged, it usually needs to be repaired manually. The present solution combines the TRIM operation, data verification and error detection mechanism of the SSD, and can automatically repair when the storage data is damaged, ensuring the data integrity after the device is restored and improving the system reliability.

[0035] S5. Comprehensively analyze all test data and provide optimization suggestions; Specifically, we comprehensively analyze all test data, evaluate equipment life, and provide optimization suggestions including: Calculate the average frequency of the CPU and GPU at the beginning of the test and at the current time point, collect the SSD read and write rate, calculate the device decay rate based on the CPU / GPU frequency obtained at the current time point and the device running time, set the threshold F by fitting the decay curve to the historical device failure data, if the decay rate exceeds the threshold F, it indicates that the device is seriously aged and optimization measures need to be taken, the optimization measures include reducing the power consumption of the CPU and GPU, reducing overheating and frequency reduction under high load conditions, adjusting the fan strategy, improving the heat dissipation efficiency, preventing the device from accelerating aging due to long-term high temperature, optimizing storage management, improving the SSD read and write efficiency, avoiding I / O degradation affecting system performance, intelligently adjusting BIOS parameters, adaptively adjusting frequency and voltage, so that the device runs more stably.

[0036] By real-time monitoring of CPU / GPU frequency and SSD read / write rate, it is possible to accurately identify the decline trend of device performance, rather than relying solely on long-term test data, to ensure the real-time and reliability of test results. The decay rate is calculated in combination with the device running time, making the test method applicable to different usage scenarios, whether it is a long-term high-load server or a light office device. By adjusting the voltage and frequency of the CPU and GPU, it can adaptively adjust power consumption under different load modes, reduce the hardware aging rate caused by continuous high-load operation, avoid the CPU and GPU from entering the thermal throttling state, and improve the stability of computing tasks. By optimizing the fan speed curve, the fan speed is increased in advance when the CPU / GPU temperature reaches a specific threshold, reducing the impact of excessive temperature on device hardware. The garbage collection mechanism of the storage medium is optimized through the TRIM instruction to reduce the performance degradation of the SSD caused by the write amplification effect of the storage unit. By intelligently adjusting the BIOS settings, the CPU and GPU automatically adjust the voltage, power consumption and cooling strategy under different load modes to optimize the energy efficiency of the hardware.

[0037] This embodiment also provides a microcomputer host aging test system, including: A data acquisition module is used to connect the device under test to the test system, perform system standby testing, and collect initial benchmark data; Aging prediction module, which is used to build an aging training model using a radial basis function neural network model, and improve the generalization ability of the model by combining curriculum learning and transfer learning; Performance testing module for CPU / GPU high load testing via AIDA64 + Heaven Benchmark; Mutation stress test module, used to generate nonlinear CPU / GPU load patterns, simulate real usage scenarios, calculate load response time, and trigger BIOS power reduction mode; The test module is used to perform the Rebooter continuous restart test, calculate the system stability, trigger anomaly detection, and optimize the sleep recovery strategy; The optimization suggestion module is used to comprehensively analyze all test data and provide equipment optimization suggestions.

[0038] This embodiment also provides a computer device suitable for the microcomputer host aging test method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the microcomputer host aging test method proposed in the above embodiment.

[0039] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0040] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the microcomputer host aging test method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0041] In summary, the present invention combines the radial basis function neural network aging prediction model, uses curriculum learning and transfer learning to train the model, intelligently analyzes the CPU / GPU degradation trend, and combines the quantum random number generator to generate random load patterns, simulates load fluctuations in actual application scenarios, and improves the authenticity of the test. In addition, the present invention provides BIOS optimization strategies, such as dynamically adjusting the CPU / GPU frequency, optimizing the fan strategy, and enabling SSD TRIM operations, to achieve intelligent aging prediction and optimization regulation, thereby improving the long-term stability and service life of the microcomputer host.

[0042] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A microcomputer host aging test method, characterized in that: include, Connect the device under test to the test system, perform system standby testing, and collect initial benchmark data; Build an aging prediction model and optimize the model training strategy by combining curriculum learning and transfer learning; Based on the prediction results, AIDA64 was used to perform host warm-up tests and high-load tests, and the HeavenBenchmark tool was run simultaneously to test the computer's graphics processing capabilities; Use the quantum random number generator to generate random load patterns, alternate between high and low CPU / GPU loads, simulate real user scenarios, perform Rebooter and S3 / S4 sleep recovery tests, and trigger exceptions; Comprehensively analyze all test data and provide optimization suggestions.

2. The microcomputer host aging test method according to claim 1, characterized in that: The method of constructing an aging prediction model and optimizing the model training strategy by combining curriculum learning and transfer learning includes the following steps: Use radial basis function neural network model to build aging prediction model, define curriculum learning strategy, and divide curriculum learning into three stages: basic stage, adaptation stage and generalization stage for model training; The radial basis function neural network model trained through course learning is used as the starting point of transfer learning. The first N layers of the radial basis function neural network model are frozen and remain unchanged. Only the center point of the radial basis function neural network model in the last M layers is optimized. The correlation alignment loss function is used to align data features. The radial basis function neural network model is optimized using the gradient descent method. After the training is completed, the radial basis function neural network model parameters are updated. The radial basis function neural network model trained through transfer learning is saved as the final model. After normalizing the data in the benchmark data set, the data is input into the radial basis function neural network model to obtain the aging trend of the computer host.

3. The microcomputer host aging test method as claimed in claim 2, characterized in that: The method of using AIDA64 to perform host warm-up test and high-load test based on the prediction results, and running the Heaven Benchmark tool simultaneously to test the computer's graphics processing capability includes the following steps: Calculate the baseline performance deviation ratio based on the prediction results , set threshold A. If the offset ratio is greater than threshold A, lower the CPU core voltage in advance, run AIDA64 FPU test, record CPU temperature, power consumption and fan speed, and calculate the temperature change rate α and actual frequency reduction ratio β of CPU frequency through multiple steps; If the actual frequency reduction ratio is greater than the baseline performance deviation ratio, it means that the prediction error is large, and the BIOS adjustment mode is entered, including further reducing the CPU core voltage and increasing the fan speed; Continue to run the AIDA64 FPU test, record the CPU frequency and calculate the CPU frequency reduction rate, set the threshold D, if the CPU frequency reduction rate is less than the threshold D, enter the BIOS power reduction strategy, optimize the voltage and power consumption management, and simultaneously run the Heaven Benchmark for GPU high load test, record the GPU frequency and calculate the GPU frequency reduction trend, if the GPU frequency reduction trend is less than the threshold D, adjust the GPU frequency management strategy and optimize the power consumption mode.

4. The microcomputer host aging test method as claimed in claim 3, characterized in that: The method of using a quantum random number generator to generate a random load pattern, alternating high and low CPU / GPU loads, simulating real user scenarios, and calculating system stability parameters after high load testing includes the following steps: Extract GPU frequency curve and CPU temperature curve from high load test results; Use quantum random number generator to generate nonlinear CPU load patterns and GPU load fluctuation ranges; Use the nonlinear mutation mode of the quantum random number generator to calculate the response time of the CPU load change and set the threshold I. If the response time is greater than the threshold I, the BIOS power reduction mode is entered; Switch Heaven Benchmark between high load, power saving mode and sleep mode; Calculate the GPU frequency fluctuation rate and set a threshold p. If the fluctuation rate is greater than the threshold p, enter the BIOS power reduction mode.

5. The microcomputer host aging test method as claimed in claim 4, characterized in that: The Rebooter and S3 / S4 sleep recovery tests and abnormal triggering include the following steps: Conduct a standardized test environment to ensure that the external power supply is stable. Call the Rebooter automated test script to perform H consecutive restarts and record the startup time of each restart. Calculate the startup time drift rate based on the maximum startup time and the minimum startup time, set the threshold E, and if the drift rate is greater than the threshold E, trigger anomaly detection and enter the low power recovery test. After the rebooter executes x reboots, it calls the ACPI command to put the device into S3 sleep mode, calculates the policy CPU response delay, sets the threshold J, and if the delay is greater than the threshold J, enters the BIOS adjustment; if the delay is less than or equal to the threshold J, continues to perform the S4 mode test; Send ACPI instructions to put the device into S4 mode, calculate the time required to enter sleep mode, trigger S4 mode recovery, calculate the consistency of storage data, if inconsistent, it means that the storage data is damaged, and perform automatic repair.

6. The microcomputer host aging test method according to claim 5, characterized in that: The comprehensive analysis of all test data and the provision of optimization suggestions include: Calculate the average frequency of the CPU and GPU at the beginning of the test and at the current time point, collect the SSD read and write rates, calculate the device degradation rate based on the CPU / GPU frequency obtained at the current time point and the device's running time, and set a threshold F. If the degradation rate exceeds the threshold F, it indicates that the device is seriously aged and optimization measures need to be taken.

7. The microcomputer host aging test method according to claim 6, characterized in that: The initial benchmark data refers to fan speed, CPU frequency ,temperature and power consumption And GPU frequency ,temperature and power consumption , and the randomness measure of the initial state of the device .

8. A microcomputer host aging test system, based on the microcomputer host aging test method according to any one of claims 1 to 7, characterized in that: include, A data acquisition module is used to connect the device under test to the test system, perform system standby testing, and collect initial benchmark data; Aging prediction module, which is used to build an aging training model using a radial basis function neural network model, and improve the generalization ability of the model by combining curriculum learning and transfer learning; Performance testing module for CPU / GPU high load testing via AIDA64 + Heaven Benchmark; Mutation stress test module, used to generate nonlinear CPU / GPU load patterns, simulate real usage scenarios, calculate load response time, and trigger BIOS power reduction mode; The test module is used to perform the Rebooter continuous restart test, calculate the system stability, trigger anomaly detection, and optimize the sleep recovery strategy; The optimization suggestion module is used to comprehensively analyze all test data and provide equipment optimization suggestions.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the microcomputer host aging test method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the microcomputer host aging test method described in any one of claims 1 to 7 are implemented.

Images