POE switch aging test device and method for security and protection

Abstract

The invention relates to the technical field of switch aging test, and discloses a POE switch aging test device and method for security protection, and the method comprises the steps: fixing a to-be-tested POE switch on a test platform, respectively applying a standard load to a POE power supply port through a load simulator, obtaining a power supply parameter and a port state, and obtaining initial test data; performing classification to generate a layered test reference matrix; respectively executing a POE port full load test, a port isolation data flow test and an automatic negotiation interaction test, and collecting a full test data set according to a hierarchical progressive mode; pSE power supply feature calculation, MAC address aging feature calculation and port performance feature calculation are carried out to generate a plurality of device state feature vectors; according to the method, the correlation analysis of the multi-dimensional performance parameters of the equipment is realized, and the adaptive capacity and the prediction accuracy of the test method in an extreme environment are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of switch aging test, and in particular to an aging test device and method for a POE switch for security. Background Art

[0002] With the rapid development and popularization of security systems, the reliability and stability of POE switches, as the core equipment for power supply and network transmission of security equipment, directly affect the operation of the entire security system. Traditional POE switch testing methods mainly focus on the verification of single performance parameters, such as power supply capacity testing or network performance testing, and lack comprehensive performance evaluation of the equipment in complex application environments.

[0003] The current POE switch aging test has problems such as incomplete test coverage, strong independence of test parameters, and insufficient correlation analysis of test data. Especially in complex application scenarios such as dual protocol support of IEEE802.3af / at standards, full-port full-load power supply, and port isolation, it is difficult to accurately evaluate the aging trend of the equipment and predict the reliability of the equipment, which may lead to unpredictable failures of the equipment in actual operation. In addition, the existing POE switch testing methods lack intelligence and adaptability, and cannot dynamically adjust the test strategy according to the real-time status of the equipment, nor can they deeply mine and analyze multi-dimensional test data, making it difficult to establish an accurate equipment life prediction model, affecting the long-term stable operation of the security system. Summary of the invention

[0004] The present invention provides a POE switch aging test device and method for security, which realizes the correlation analysis of multi-dimensional performance parameters of the device and enhances the adaptability and prediction accuracy of the test method in extreme environments.

[0005] In a first aspect, the present invention provides a POE switch aging test method for security, the POE switch aging test method for security comprising: The POE switch to be tested is fixed on the test platform, and a standard load is applied to the POE power supply port through a load simulator to obtain power supply parameters and port status to obtain initial test data; Classifying the initial test data according to POE power supply parameters, port negotiation status and temperature distribution data to generate a hierarchical test benchmark matrix; Based on the hierarchical test benchmark matrix, the POE port full load test, the port isolation data flow test and the automatic negotiation interaction test are respectively performed by the intelligent PSE controller, and the full test data set is collected in a hierarchical progressive manner; Perform PSE power supply feature calculation, MAC address aging feature calculation and port performance feature calculation on the full test data set to generate multiple device status feature vectors; The multiple equipment state feature vectors are input into an aging prediction model set to calculate equipment degradation trends, thereby obtaining equipment degradation prediction indicators.

[0006] In a second aspect, the present invention provides a POE switch aging test device for security, the POE switch aging test device for security comprising: The acquisition module is used to fix the POE switch to be tested on the test platform, apply standard loads to the POE power supply ports through the load simulator, obtain power supply parameters and port status, and obtain initial test data; A classification module, used to classify the initial test data according to POE power supply parameters, port negotiation status and temperature distribution data to generate a hierarchical test benchmark matrix; A test module is used to perform a POE port full load test, a port isolation data flow test and an automatic negotiation interaction test respectively through an intelligent PSE controller based on the hierarchical test benchmark matrix, and collect a full test data set in a hierarchical progressive manner; A calculation module, used to perform PSE power supply feature calculation, MAC address aging feature calculation and port performance feature calculation on the full test data set to generate multiple device status feature vectors; The processing module is used to input the multiple equipment state feature vectors into the aging prediction model set to calculate the equipment degradation trend and obtain the equipment degradation prediction index.

[0007] The third aspect of the present invention provides a computer device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned POE switch aging test method for security.

[0008] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned aging test method for a POE switch for security.

[0009] In the technical solution provided by the present invention, a comprehensive test of the power supply capacity, network performance and environmental adaptability of the POE switch is achieved through a hierarchical and progressive testing strategy, thereby improving the test coverage; an intelligent PSE controller and multi-dimensional data fusion technology are used to establish a device state feature vector, thereby making the test result more objective and accurate; an aging prediction model set based on deep learning is introduced, and the weighted fusion mechanism of the AdaBoost algorithm is combined to improve the accuracy of the prediction of the device degradation trend; through a dynamic test parameter adjustment mechanism, the test process can be adaptively optimized according to the device state, thereby reducing the waste of test resources; a complete multi-modal feature sequence analysis system is established, thereby realizing the correlation analysis of the multi-dimensional performance parameters of the device, thereby providing a reliable basis for equipment maintenance decisions; through a hierarchical early warning mechanism and a temperature compensation strategy, the adaptability and prediction accuracy of the test method in extreme environments are enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] 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 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 any creative work.

[0011] Figure 1 A schematic diagram of the steps of the aging test method of a security POE switch according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a POE switch aging test device for security use in an embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The embodiment of the present invention provides an aging test device and method for a POE switch for security. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the aging test method of the security POE switch in the embodiment of the present invention includes: Step S1, fix the POE switch to be tested on the test platform, apply standard load to the POE power supply port through the load simulator, obtain power supply parameters and port status, and obtain initial test data; It is understandable that the execution subject of the present invention may be a POE switch aging test device for security, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0014] Specifically, the POE switch to be tested is fixed on a standard 13-inch rack to ensure the stability of the device during the test and avoid test errors caused by unstable position. The physical ports of the POE switch to be tested are numbered and identified by a scanner to obtain the accurate position mapping data of the port. The 16 POE ports of the switch to be tested are respectively configured with a load simulator of the IEEE802.3af / at standard. The IEEE802.3af / at standard is a common standard for POE power supply. The load simulator simulates the power consumption requirements of different devices for the POE power supply port to ensure that the test conditions meet the actual usage. After applying an appropriate load to each port through the load simulator, a digital multimeter is used to collect the voltage value of the power supply end of each port to obtain the initial voltage data of the power supply port. The initial voltage data is used to understand the power supply status of the device under the standard load. The initial voltage data is input into the voltage regulation controller, and the output voltage of each POE port is scanned in the power range of 0 to 30W through PWM wave modulation. The voltage fluctuation of the POE switch port under different loads is tested to obtain the curve data of the port power supply. By analyzing the power supply curve data, the power supply stability and reliability of each port are evaluated, and then the working ability of the port under high load is determined. The port power supply curve data is compared by threshold, and the power supply reference value and voltage deviation value of each POE port are set by using a voltage comparator. In this way, the power supply reference data of the port is obtained. According to the power supply reference data, the Auto MDI / MDI-X automatic flip test is performed on each POE port through the intelligent PSE controller to obtain the port line pair identification data. MDI / MDI-X automatic flip refers to the transmission mode of automatically switching the network connection port. Through this test, it can ensure that the POE port can correctly identify the type of connected device and optimize the connection stability of the network. Cross-matrix analysis is performed on the port line pair identification data. Through Boolean algebra operations, a cross-correlation table between ports is generated to reflect the state relationship between each port, and the port state matrix is ​​obtained. The port state matrix helps to evaluate the performance of each port under different network configurations. To test the port performance, a 15.4W standard load is applied to each POE port in the port state matrix on this basis. After applying the standard load, the temperature sensors are used to collect the temperature values ​​of the power module, PSE controller and Ethernet chip respectively to obtain the temperature distribution data of the target point. By monitoring the temperature changes of the equipment under load conditions, its thermal stability and potential heat dissipation problems are evaluated. The initial voltage data of the power supply port, the port power supply curve data, the port state matrix and the temperature distribution data of the target point are fused to obtain the initial test data.

[0015] Step S2, classifying the initial test data according to POE power supply parameters, port negotiation status and temperature distribution data to generate a hierarchical test benchmark matrix; Specifically, the POE power supply parameters in the initial test data are numerically classified, and the power supply is segmented by the 15.4W threshold of the IEEE802.3af standard and the 30W threshold of the IEEE802.3at standard to obtain interval data of different power supply levels. The interval data helps to analyze the power supply performance under different loads and divide the power supply capacity of the equipment into different level intervals, providing a clear classification standard for subsequent testing and evaluation. Based on the power supply level interval data, the power supply parameters of each POE port are standardized and calculated to obtain the power supply reference value of the port. The standardized calculation can eliminate the impact caused by hardware differences or different test conditions between different ports, so that the power supply performance of each port can be compared under the same standard. The power supply reference values ​​are arranged in the order of port numbers, and a 16×3-dimensional power supply parameter matrix is ​​generated through matrix operation. The matrix contains the power supply data of 16 POE ports under different load conditions, reflecting the stability and power distribution capacity of each port under different working conditions, and obtaining the POE power supply reference data. The Auto MDI / MDI-X status data in the port status matrix is ​​extracted. The Auto MDI / MDI-X automatic flip function is used to automatically identify the type of network connection and ensure the correct connection between different devices. After extracting the status data of the port, the negotiation capability of each port is verified through the port isolation function to ensure that each port can normally identify and adapt to different types of network devices. Through this step, the negotiation status data of each port is obtained, reflecting the switch's adaptive ability in different network environments. The port negotiation status data and the IEEE802.3X flow control status are combined and analyzed to evaluate the stability and data processing capability of the switch under complex conditions such as high load and flow control. By mapping the status of these data, the negotiation benchmark parameters of each POE port are generated to obtain the negotiation status benchmark data. The temperature distribution data of the key points about temperature in the initial test data are processed. These data include the temperature data of the power module, PSE controller and Ethernet chip, which directly affect the stability and life of the equipment. By performing partition statistics according to the location of the temperature data, the temperature distribution of each area is obtained, and the temperature distribution characteristics are generated according to the temperature gradient calculation, which reflects the thermal stability of the equipment under different working environments and helps evaluate the reliability of the equipment under high or low temperature conditions to obtain temperature benchmark data. The POE power supply benchmark data, negotiation status benchmark data and temperature benchmark data are arranged in a two-dimensional matrix to form a hierarchical feature matrix. By linearly transforming these data, different types of test data are unified into a standard framework to obtain test hierarchy data. The test hierarchy data is restructured, and the test parameters of the power supply layer, negotiation layer and temperature layer are integrated through hierarchical mapping rules to obtain a hierarchical test benchmark matrix.

[0016] Step S3: Based on the hierarchical test benchmark matrix, the POE port full load test, the port isolation data flow test and the automatic negotiation interaction test are respectively performed by the intelligent PSE controller, and the full test data set is collected in a hierarchical progressive manner; Specifically, the first layer of testing is performed based on the power layer parameters in the layered test benchmark matrix. The testing at this stage focuses on the load capacity and continuous power supply performance of the POE port. In the first layer of testing, a rated load of 15.4W is applied to a single POE port and the power supply is continuously supplied for 8 hours to simulate the performance of the device under normal working load. Through this test, the power supply data of a single port under rated load is obtained, and its stability and durability are evaluated. Based on the single-port rated load data, the first layer of progressive testing is performed. In this test, a larger load of 30W maximum load is applied to a single POE port, and the power supply is continuously supplied for 8 hours. The progressive test can evaluate the working ability of the device under higher load conditions and its response to load fluctuations. The first layer of full load testing is performed based on the single-port maximum load data. A total power load of 240W is applied to all POE ports and the power supply is continuously supplied for 24 hours. The long-term operation capability of the entire switch system under high load conditions is comprehensively evaluated, and the full-port full load test data is obtained through testing to confirm the stability, power supply efficiency and potential failure risks of the device under full load. Based on the performance layer parameters in the hierarchical test benchmark matrix, enter the second layer test. At this stage, focus on the network performance of the device, especially the data flow isolation capability between ports. Through the port isolation function, all ports are isolated to prevent signal interference between different ports, and the port isolation configuration data is obtained. These data can help evaluate whether the data transmission between different ports of the switch is independent and avoid the risk of network congestion or data conflict. After completing the port isolation configuration test, perform the second layer progressive test, and use the IEEE802.3X flow control protocol to perform concurrent data transmission tests on all isolated ports to obtain data throughput test data, revealing the performance of the switch under high concurrent transmission conditions, especially key indicators such as data throughput, delay and error rate. According to the temperature layer parameters in the hierarchical test benchmark matrix, enter the third layer test. Test the working ability and stability of the device under different temperature environments. In a low temperature environment of -10℃, keep all ports at 30% load for 4 hours to obtain low temperature test data to evaluate the startup performance and long-term operation stability of the device under low temperature conditions. Based on the low-temperature test data, the third-layer progressive test is performed. In a high-temperature environment of 55°C, all ports are kept at the same 30% load for 4 hours to obtain high-temperature test data to evaluate the heat dissipation performance, thermal stability and potential overheating problems of the equipment under high-temperature conditions, helping to predict the long-term durability of the equipment. The full-port full-load test data, data throughput test data, low-temperature test data and high-temperature test data are integrated in a time-series relationship to obtain a full test data set.

[0017] Step S4: Calculate the PSE power supply characteristics, MAC address aging characteristics, and port performance characteristics of the full test data set to generate multiple device status feature vectors; Specifically, the voltage data in the full-port full-load test data is normalized. The voltage data is converted into a standardized form to eliminate the numerical differences under different ports or test conditions, so that the voltage fluctuations of each port can be compared for consistency. The voltage fluctuation data under 240W full load conditions is used to calculate the value of voltage stability and obtain the power supply fluctuation characteristic data, which reflects the voltage fluctuation range of the POE switch under large load conditions, thereby evaluating its power supply stability during long-term use. According to the power supply fluctuation characteristic data, the POE port power supply parameters are analyzed, and the PSE power supply quality data is obtained by calculating the voltage ripple coefficient and power factor at the 52V power output end, reflecting the power supply stability, efficiency and comprehensive quality of the power supply system of the equipment under different load conditions. According to the data throughput test data, the MAC address learning rate test is performed on each POE port. By calculating the address update time in the IEEE802.3X full-duplex mode, the address processing rate data of each port is obtained, which reflects the efficiency of the switch in processing MAC address learning, thereby affecting its network traffic forwarding capability. According to the address processing rate data, the MAC address aging time and failure probability of each POE port are statistically calculated to obtain the address aging characteristic data. The aging time and failure probability of MAC addresses are important indicators of switch performance, which directly affect the address table management capability and data processing efficiency of the switch after long-term operation. Based on low-temperature test data and high-temperature test data, the slope of the temperature rise curve of the power module, PSE controller and Ethernet chip is calculated to obtain temperature change characteristic data. The temperature rise curve reflects the thermal response characteristics of the device under different working environments. By calculating the slope of the temperature rise curve, the thermal stability of the device after long-term operation is evaluated. The test data under high and low temperature conditions help to understand the heat dissipation capacity of the device and its operating conditions in extreme environments, ensuring the reliability of the device under various temperature environments. According to the correlation analysis of PSE power supply quality data and temperature change characteristic data, the coupling coefficient between power supply parameters and temperature changes is calculated to obtain the power supply status characteristic vector, which reflects the degree of correlation between power supply quality and device temperature changes, thereby evaluating the impact of temperature fluctuations on the power supply status of the device. The performance score calculation of the address aging characteristic data is performed, and the port performance characteristic vector is obtained based on the data forwarding efficiency and address table item utilization in port isolation mode to evaluate the data processing capability of each port under different working conditions. The port performance feature vector can reflect the stability and data forwarding efficiency of the switch after long-term operation, especially when the network load is high. The power supply status feature vector and the port performance feature vector are combined to generate multiple device status feature vectors according to the classification structure of power supply features, aging features and performance features.

[0018] Step S5: Input multiple equipment state feature vectors into the aging prediction model set to calculate equipment degradation trends and obtain equipment degradation prediction indicators.

[0019] Specifically, the power supply status feature vectors in the multiple device status feature vectors are input into the PSE power supply weak classifier. The classifier consists of three main parts: feature extraction layer, timing analysis layer and status prediction layer. The feature extraction layer adopts a three-layer fully connected network structure, and each layer performs feature dimension reduction in turn, which are 512 dimensions, 256 dimensions and 128 dimensions respectively. This process is processed by ReLU activation function and Dropout layer to prevent overfitting and increase the robustness of the model. The timing analysis layer adopts a bidirectional LSTM (long short-term memory network) structure, which contains 64 hidden units to capture the dynamic characteristics of power supply parameters changing over time. Bidirectional LSTM can process the front-to-back dependencies in time series data and analyze the changing trend of power supply status more accurately. The status prediction layer uses a Softmax classifier for classification output to obtain the PSE power supply degradation score, which reflects the degree of degradation of the power supply system of the equipment during long-term operation. In the processing of the PSE power supply weak classifier, the timing characteristics of the power supply status can be extracted through the dimension reduction of the three-layer fully connected network and the timing modeling of the bidirectional LSTM network. The port performance feature vectors in multiple device status feature vectors are input into the port performance weak classifier. The port performance weak classifier consists of a data preprocessing layer, a feature enhancement layer, and a classification output layer. The data preprocessing layer adopts a batch normalization structure, which can standardize the input data to improve the training efficiency and stability of the model. The feature enhancement layer adopts a residual network structure, which uses a three-layer stacking structure, each layer contains two 3x3 convolutional layers and a short-circuit connection to enhance the feature expression ability, prevent the gradient vanishing problem and accelerate training. Each convolutional layer is followed by a LeakyReLU activation function to further improve the nonlinear expression ability of the model. Through this structure, the port performance time series features are extracted, and the classification output layer adopts a cross entropy loss function to output the port performance degradation score to measure the performance degradation degree of the switch port after long-term operation, including data forwarding efficiency, processing capacity, etc. The temperature change feature data is input into the temperature feature weak classifier, which consists of a temperature curve analysis layer, a trend extraction layer, and a result output layer. The temperature curve analysis layer uses a one-dimensional convolutional network for processing. The number of convolution kernels is set to 32, and the size of each convolution kernel is 3. The feature dimension is compressed through the maximum pooling layer. This layer mainly extracts effective time series features from the temperature change data to reveal the thermal response of the device under different temperature conditions. The trend extraction layer uses an attention mechanism that can automatically focus on the most important time points in the temperature curve. The time series changes of the temperature data are weighted through the scaled dot-product structure to obtain the temperature change time series features. The result output layer calculates the temperature degradation score based on the extracted features, reflecting the performance change trend of the device under different temperature environments.The AdaBoost algorithm is used to perform weighted fusion of the PSE power supply degradation score, port performance degradation score, and temperature degradation score. The AdaBoost algorithm is an ensemble learning method that improves the accuracy of the final model by combining the prediction results of multiple weak classifiers. In this application, the AdaBoost algorithm performs weighted fusion of the degradation scores of the three aspects of PSE power supply, port performance, and temperature to obtain a comprehensive device degradation prediction index to evaluate the overall health of the device in long-term operation.

[0020] The PSE timing features, port performance timing features and temperature change timing features are time-series segmented to better process and analyze these data. The PSE timing features are first time-series segmented to obtain PSE sequence data; the port performance timing features are second time-series segmented to obtain port sequence data; the temperature change timing features are third time-series segmented to obtain temperature sequence data. The sequence data are uniformly sampled by timestamp alignment. A multimodal feature sequence with a uniform sampling interval is generated by a cubic spline interpolation algorithm to obtain aligned feature data. Next, the first stage feature fusion is performed. The first fusion weight coefficient is obtained by calculating the coupling coefficient between PSE power supply and temperature and the coupling coefficient between port performance and temperature, reflecting the mutual influence between power supply, port performance and temperature change. Based on the fusion coefficient, the PSE power supply degradation score and the port performance degradation score are weighted. This process is implemented by the first-level classifier of the improved AdaBoost algorithm, in which the score weighting is further optimized by introducing a weak classifier group with a temperature compensation factor. The weighted score constitutes the degradation index of the first stage, reflecting the overall degradation trend of the device under current conditions. The second-stage feature fusion is performed on the first-stage degradation index and temperature degradation score, and the second fusion weight coefficient is calculated by introducing a multi-level weighting method with an adaptive temperature threshold. According to the impact of actual temperature changes on equipment degradation, the weights of different features are automatically adjusted to obtain equipment degradation prediction data. Based on the weighted calculation of the first-stage degradation index and the second fusion weight coefficient, the final degradation prediction index of the equipment is obtained. In order to refine the prediction results, the grading standard is used to calibrate the degree of equipment degradation. The prediction results are set to [0.3, 0.6) for mild degradation, [0.6, 0.8) for moderate degradation, and [0.8, 1.0] for severe degradation, and the equipment degradation prediction index is obtained.

[0021] In the embodiment of the present invention, a hierarchical and progressive testing strategy is used to achieve a comprehensive test of the power supply capacity, network performance and environmental adaptability of the POE switch, thereby improving the test coverage; an intelligent PSE controller and multi-dimensional data fusion technology are used to establish a device state feature vector, thereby making the test result more objective and accurate; an aging prediction model set based on deep learning is introduced, and the weighted fusion mechanism of the AdaBoost algorithm is combined to improve the accuracy of the prediction of the device degradation trend; a dynamic test parameter adjustment mechanism is used to enable the test process to be adaptively optimized according to the device state, thereby reducing the waste of test resources; a complete multi-modal feature sequence analysis system is established, thereby achieving a correlation analysis of the multi-dimensional performance parameters of the device, thereby providing a reliable basis for equipment maintenance decisions; and a hierarchical early warning mechanism and a temperature compensation strategy are used to enhance the adaptability and prediction accuracy of the test method in extreme environments.

[0022] In a specific embodiment, the process of executing step S1 may specifically include the following steps: Fix the POE switch to be tested on a standard 13-inch rack, and use a scanner to number and identify the physical ports of the POE switch to be tested to obtain port location mapping data; The 16 POE ports in the port location mapping data are respectively configured with a load simulator of the IEEE802.3af / at standard, and the voltage value of the 52V power output terminal is collected by a digital multimeter to obtain the initial voltage data of the power supply port; The initial voltage data of the power supply port is input into the voltage regulation controller, and the output voltage of each POE port is scanned in the range of 0-30W through PWM wave modulation to obtain the port power supply curve data; Perform threshold comparison on the port power supply curve data, set the power supply reference value and voltage deviation value of each POE port through the voltage comparator, obtain the port power supply reference data, and based on the port power supply reference data, perform Auto MDI / MDI-X automatic flip test on each POE port through the intelligent PSE controller to obtain the port line pair identification data; Perform cross-matrix analysis on the port line pair identification data, generate a cross-correlation table between ports through Boolean algebra operations, obtain the port status matrix, and apply a 15.4W standard load to each POE port in the port status matrix. Use temperature sensors to collect the temperature values ​​of the power module, PSE controller, and Ethernet chip to obtain the target point temperature distribution data. The initial voltage data of the power supply port, the port power supply curve data, the port state matrix and the target point temperature distribution data are fused to obtain the initial test data.

[0023] Specifically, the POE switch to be tested is fixed on a standard 13-inch rack. As a standardized test platform, the 13-inch rack can ensure the stability and uniformity of the equipment during the test. The fixed device uses a scanner to number and identify the physical ports of the POE switch, and automatically scans each port through the scanner to obtain the number of each port and its physical position on the switch, and generate port position mapping data. According to the 16 POE ports in the port position mapping data, load simulators of the IEEE802.3af / at standard are configured respectively. The load simulator simulates the current and power required by the POE port during actual use, and evaluates the performance of the switch in actual work by simulating the working state under different load conditions. The voltage value of the 52V power output terminal of each POE port is measured by a digital multimeter to obtain the initial voltage data of the power supply port, reflecting the power supply state of the POE switch without load. The initial voltage data is input into the voltage regulation controller. The voltage regulation controller accurately controls the output voltage of each POE port by adopting PWM wave modulation technology. During the test, the controller performs a power scan in the range of 0 to 30W on each POE port to obtain the power supply curve data of the port. By scanning the voltage response under different power, we can understand the power supply capacity and stability of the switch under different load conditions. Perform threshold comparison on the port power supply curve data. Through the voltage comparator, set the power supply reference value and voltage deviation value of each POE port. The power supply reference value indicates the voltage value that the port should maintain under standard working conditions, while the voltage deviation value reflects the deviation between the actual port voltage and the standard voltage, which is specifically expressed by the following formula: ; in, Indicates voltage deviation, is the actual voltage value measured, is the standard voltage value. In this way, the power supply stability of the POE port is judged and compared with the standard value to generate port power supply reference data. Based on these power supply reference data, the intelligent PSE controller performs the Auto MDI / MDI-X automatic flip test. MDI / MDI-X refers to the automatic identification function of the network port to determine the connectivity of the port and whether the data is exchanged correctly. Through the automatic flip test, the reliability of the port connection is ensured, and the port line pair identification data is generated according to the test results. The port line pair identification data is subjected to cross matrix analysis. Cross matrix analysis is a technology that generates a cross-correlation table between ports through Boolean algebra operations, and generates a port status matrix by analyzing the mutual relationship between different ports. The matrix can reflect the working status of each port, such as whether it is enabled, whether there is signal interference, etc. A standard load of 15.4W is applied to each POE port in the port status matrix. This is a load level based on the IEEE802.3af standard, which can simulate the typical load state of the switch during actual use. While applying the load, a temperature sensor is used to monitor the temperature values ​​of the power module, PSE controller and Ethernet chip in real time. The temperature data collected by the temperature sensor is used to obtain the temperature distribution data of the target point, which reflects the temperature changes under different working conditions on different components. The acquisition formula of the temperature distribution data of the target point is expressed as: ; in, Indicates the temperature of the power module. represents the applied load power, Indicates the test time. Through this formula, the temperature change trend with load change is dynamically monitored to ensure the reliability of the equipment in a high temperature environment. The initial voltage data of the power supply port, the port power supply curve data, the port state matrix, and the target point temperature distribution data are fused. Data from different sources are processed comprehensively to generate a comprehensive initial test data set.

[0024] In a specific embodiment, the process of executing step S2 may specifically include the following steps: The POE power supply parameters in the initial test data are numerically classified and segmented according to the 15.4W threshold of the IEEE802.3af standard and the 30W threshold of the IEEE802.3at standard to obtain the power supply level interval data; Based on the power supply level interval data, the power supply parameters of each POE port are standardized and calculated to obtain the port power supply reference value, and the port power supply reference values ​​are arranged in the order of port numbers. A 16×3-dimensional power supply parameter matrix is ​​generated through matrix operation to obtain the POE power supply reference data; Extract the Auto MDI / MDI-X status data in the port status matrix, verify the negotiation capability of each port through the port isolation function, and obtain the port negotiation status data; Combine and analyze the port negotiation state data and the IEEE802.3X flow control state, generate negotiation benchmark parameters for each POE port through a state mapping table, and obtain negotiation state benchmark data; The temperature distribution data of key points are divided into statistical partitions according to the positions of power modules, PSE controllers and Ethernet chips, and the temperature distribution characteristics are generated by temperature gradient calculation to obtain temperature benchmark data; Arrange the POE power supply benchmark data, negotiation status benchmark data and temperature benchmark data in a two-dimensional matrix form, generate a hierarchical feature matrix through linear transformation, and obtain test level data; The test hierarchical data is restructured, and the test parameters of the power supply layer, negotiation layer, and temperature layer are integrated through hierarchical mapping rules to obtain a hierarchical test benchmark matrix.

[0025] Specifically, the POE power supply parameters in the initial test data are numerically classified. The 15.4W threshold of the IEEE802.3af standard and the 30W threshold of the IEEE802.3at standard are used for segmentation. The power supply status under different power is divided into several level intervals. Two classification thresholds are set according to different standards of power supply - 15.4W corresponds to the IEEE802.3af standard, and 30W is the IEEE802.3at standard. The generation process of power supply level interval data is expressed by the following formula: ; in, Indicates the power supply level interval, which distinguishes the power supply type of the POE port by different power ranges. After classification, the power supply level interval provides an identifier for each POE port for easy standardization and analysis. Based on the power supply level interval data, the power supply parameters of each POE port are standardized and calculated to eliminate the differences between different ports caused by different voltages or powers, so that the data of different ports can be comparable. Standardization uses a linear standardization formula: ; in, Represents the standardized power supply parameters, is the actual measured voltage or power value, is the average value of the power supply parameters of all ports, is the standard deviation. Through standardization, the deviation of voltage and power data of different ports is eliminated, making the power supply parameters of all POE ports comparable. Arrange the power supply reference value of each POE port in the order of port number. Assuming that each port has three key parameters (for example, voltage, current, power), a 16×3-dimensional power supply parameter matrix is ​​generated through matrix operation. Each row represents a POE port, and each column represents a power supply parameter of the port. The matrix form is expressed as: ; in, Representative The first power supply parameters. Through matrix operations, a POE power supply benchmark data set that fully reflects the power supply status of the POE port is obtained. The Auto MDI / MDI-X status data in the port status matrix is ​​extracted. Auto MDI / MDI-X is the automatic detection function of the Ethernet port, which can automatically determine the type of network connected to the port and the way to exchange data. The negotiation capability of each port is verified through the port isolation function to obtain the port negotiation status data. The port negotiation status reflects the working status of the port when connected to different devices, ensuring the stability and flexibility of network interconnection. The port negotiation status is represented by a binary value, for example, 1 indicates successful negotiation and 0 indicates failed negotiation. These data are converted and analyzed through the state mapping table to generate the negotiation benchmark parameters for each POE port. For each port, the negotiation status benchmark data is expressed as: }; in, Indicates the port negotiation status and reflects the negotiation capability of the port in actual work. Processes the temperature distribution data of key points. Temperature distribution is a very critical indicator in the test process, reflecting the thermal performance of the device under different workloads. The temperature values ​​of the power module, PSE controller and Ethernet chip are obtained through temperature sensors, and then the regions are divided and the temperature gradient is calculated based on these data to obtain the temperature distribution characteristics. The temperature gradient calculation formula is expressed as: ; in, represents the temperature gradient, and are the highest and lowest temperatures in the measured area, is the distance between temperature sensors. This calculation helps the system understand the heat distribution generated by different components during operation. Arrange the POE power supply benchmark data, negotiation status benchmark data, and temperature benchmark data in the form of a two-dimensional matrix. The two-dimensional matrix contains data on power supply, negotiation, temperature, etc. A hierarchical feature matrix is ​​generated through linear transformation to obtain test level data. The test level data is restructured through hierarchical mapping rules. The test parameters of the power supply layer, negotiation layer, and temperature layer are integrated through hierarchical mapping rules to obtain a hierarchical test benchmark matrix.

[0026] In a specific embodiment, the process of executing step S3 may specifically include the following steps: The first layer test is performed based on the power layer parameters in the layered test benchmark matrix, and a single POE port is subjected to a rated load of 15.4W for 8 hours to obtain the single-port rated load data; Perform the first-layer progressive test based on the single-port rated load data, apply a 30W maximum load to a single POE port for 8 hours to obtain the single-port maximum load data; Based on the single-port maximum load data, the first-layer full-load test is performed, and a total power of 240W is applied to all POE ports for 24 hours to obtain full-port full-load test data; Perform the second layer test based on the performance layer parameters in the layered test benchmark matrix, isolate the data flow of all ports through the port isolation function, and obtain the port isolation configuration data; Perform the second layer progressive test according to the port isolation configuration data, perform concurrent data transmission on all isolated ports through IEEE802.3X flow control, and obtain data throughput test data; The third layer test is performed based on the temperature layer parameters in the layered test benchmark matrix, and all ports are kept running at 30% load for 4 hours at a temperature of -10°C to obtain low temperature test data; Perform the third-layer progressive test based on the low-temperature test data, keep all ports running at 30% load for 4 hours at a temperature of 55°C, and obtain the high-temperature test data; The full-port full-load test data, data throughput test data, low-temperature test data, and high-temperature test data are integrated according to the time series relationship to obtain the full test data set.

[0027] Specifically, the first layer of testing is performed based on the power layer parameters in the layered test benchmark matrix. Evaluate the performance of a single POE port under rated load to ensure that each port can maintain stable power supply under typical working conditions. Apply a rated load of 15.4W to each port and continue to power it for 8 hours to simulate the ability of a POE switch to power devices under normal use. In this test, the voltage change, power output, and current fluctuation of each port within 8 hours are recorded. The formula is expressed as: ; in, is the rated load power, is the port output voltage, is the port output current. Through this formula, the actual power output of the port when a 15.4W load is applied is calculated, and its voltage stability is monitored. Perform the first-layer progressive test based on the single-port rated load data, increase the load, apply a maximum load of 30W, and maintain power supply for 8 hours. Simulate the working ability of the POE switch under overload conditions and evaluate its power supply stability and performance under maximum load. During the test, record parameters such as voltage, current, and power, and compare and analyze their fluctuations, especially whether the system can remain within a reasonable range. The power calculation formula is as follows: ; in, is the maximum load power, and They are the port output voltage and current respectively. When performing the maximum load test, pay attention to the stability of the system under a long-term load, and whether there will be abnormal conditions such as voltage drop or excessive current. Based on the single-port maximum load data, perform the first-layer full load test. Apply a total power of 240W to all POE ports and continue to supply power for 24 hours. Simulate the long-term working state of the device under maximum load to ensure that all ports can operate stably under extreme conditions. Calculate the total power using the following formula: ; in, is the total power of all 16 ports, Indicates The power of each port. The test data includes the voltage, current, power of each port, and stability analysis within 24 hours to verify the durability and stability of the POE switch. Perform the second layer test based on the performance layer parameters in the hierarchical test benchmark matrix to perform port isolation test. The port isolation function is used to isolate the data streams of all ports to ensure that the performance of each port can be evaluated independently. This operation can effectively eliminate the influence of mutual interference between ports and ensure the accuracy of data transmission tests. After isolation, the configuration data of each port is recorded, and the second layer progressive test is performed on this basis. In the second layer progressive test, IEEE802.3X flow control is used to perform concurrent data transmission on all isolated ports to test their data throughput. IEEE802.3X flow control can control the transmission rate of data streams to avoid network congestion and ensure that the load and data transmission performance of each port are not affected. The throughput test involves key indicators such as the port's data packet transmission rate, delay, and packet loss rate. Assume that the throughput is , the throughput is calculated by the following formula: ; in, is the data throughput, is the total number of packets transmitted, is the total time of the test. By analyzing the data throughput, the processing capacity and network performance of the port under high load are evaluated. The third layer test is performed based on the temperature layer parameters in the layered test benchmark matrix. The working stability and reliability of the POE switch in extreme temperature environments are evaluated. In the low temperature test, the temperature is set to -10°C, and all ports are kept running at 30% load for 4 hours to simulate the working performance of the device in a cold environment, and the voltage, current and power of the port are recorded, and whether there is performance degradation caused by low temperature is analyzed. The voltage deviation in the low temperature test data is calculated by the following formula: ; in, is the voltage deviation, and are the voltage values ​​at the beginning and end of the test, respectively. According to the low-temperature test data, a high-temperature test is performed, the temperature is raised to 55°C, and all ports are kept running at 30% load for 4 hours. The test simulates the working state of the device in a high-temperature environment to verify its heat resistance and long-term stability. In the high-temperature test, the port's voltage, current, power, and temperature changes are recorded, and the performance stability of the device at high temperatures is evaluated. The full-port full-load test data, data throughput test data, low-temperature test data, and high-temperature test data are integrated according to the timing relationship to obtain a complete full-volume test data set. By analyzing these data, the performance of the POE switch in long-term work and the possible risk of failure can be effectively judged. For example, by comparing the voltage changes and data throughput changes under different temperature environments, the stability of the device under different working environments can be evaluated, the service life of the device can be predicted, and feedback can be provided for subsequent optimization design.

[0028] In a specific embodiment, the process of executing step S4 may specifically include the following steps: The voltage data in the full-port full-load test data is normalized, and the voltage stability value is calculated by the voltage fluctuation under 240W full-load conditions to obtain the power supply fluctuation characteristic data; The POE port power supply parameters are analyzed based on the power supply fluctuation characteristic data, and the PSE power supply quality data is obtained by calculating the voltage ripple coefficient and power factor of the 52V power output terminal; Based on the data throughput test data, the MAC address learning rate test is performed on each POE port, and the address processing rate data is obtained by calculating the address update time in IEEE802.3X full-duplex mode; Based on the address processing rate data, statistical calculations are performed on the MAC address aging time and failure probability of each POE port to obtain address aging feature data; Based on the low-temperature test data and high-temperature test data, the slope of the temperature rise curve of the power module, PSE controller and Ethernet chip is calculated to obtain the temperature change characteristic data; According to the correlation analysis of PSE power supply quality data and temperature change characteristic data, the power supply state characteristic vector is obtained by calculating the coupling coefficient between power supply parameters and temperature change; The performance score of the address aging feature data is calculated, and the port performance feature vector is obtained through the data forwarding efficiency and address table utilization in the port isolation mode; The power supply status feature vector and the port performance feature vector are feature combined, and multiple device status feature vectors are generated according to the classification structure of power supply features, aging features and performance features.

[0029] Specifically, the voltage data in the full-port full-load test data is normalized to eliminate the deviation caused by different test environments and ensure that the data can be compared and analyzed on a unified scale. Normalization is achieved by dividing the original voltage data by the maximum voltage value to scale the data to the interval [0,1]. Use the following formula for normalization: ; in, is the original voltage value, and are the minimum and maximum values ​​in the test data, respectively. is the normalized voltage value. Based on the normalized voltage data, the voltage fluctuation of all ports is analyzed to calculate the voltage stability. Voltage fluctuation is an important indicator reflecting the stability of the power supply system, which is obtained by calculating the standard deviation of the voltage. The smaller the standard deviation, the smaller the voltage fluctuation and the more stable the power supply system. Voltage fluctuation is calculated using the following formula: ; in, is the standard deviation of voltage fluctuation, It is The normalized voltage value of each port, is the mean value of all port voltages, is the number of ports. Convert voltage fluctuations into power supply fluctuation characteristic data to evaluate voltage stability. Based on the power supply fluctuation characteristic data, analyze the power supply quality of the POE port and measure it by calculating the voltage ripple coefficient and power factor. The voltage ripple coefficient reflects the ratio of AC signal to DC signal in the voltage output, and the calculation formula is: ; in, is the AC component of the voltage, It is the DC component of the voltage. The power factor reflects the ratio of the effective power to the total power of the power system and is calculated by the following formula: ; in, is the effective power, is the total power. The closer the power factor is to 1, the higher the power efficiency and the better the power quality. Based on the data throughput test data, a MAC address learning rate test is performed on each POE port. The MAC address learning rate test evaluates the processing capacity of a port by recording the speed at which the port learns MAC addresses. In IEEE802.3X full-duplex mode, each address update takes a certain amount of time. By calculating the number of MAC addresses that can be learned per second, the address processing rate is obtained. Assume that the number of addresses learned per second is , the address learning rate is calculated by the following formula: ; in, is the total number of learned MAC addresses, is the total test time. Through this step, the MAC address learning rate of each port is obtained, and then its data processing capacity is evaluated. Based on the address processing rate data, the MAC address aging time and failure probability of each POE port are statistically calculated. MAC address aging means that if a MAC address has not been communicated within a certain period of time, it will be deleted from the address table. By counting the aging time of each port within a certain period of time and combining the port usage, the failure probability is calculated. Assume that the MAC address aging time of the port is , then the failure probability is expressed by the following formula: ; in, is the probability of a MAC address failure, is the aging time of the MAC address, is the maximum aging time. This data is used to evaluate the stability and long-term operation capability of the port. Based on the low-temperature test data and high-temperature test data, the slope of the temperature rise curve of the power module, PSE controller and Ethernet chip is calculated. The temperature rise curve reflects the temperature change of the device during operation, and the slope is a measure of the temperature rise rate. The thermal stability of the device under different temperature environments can be judged by the size of the slope. The calculation formula for the temperature rise slope is: ; in, is the temperature rise slope, is the temperature change, It is the time variation. By analyzing the temperature rise curves of different components (such as power modules, PSE controllers, and Ethernet chips), we can obtain temperature variation characteristic data and evaluate the performance of the equipment under different temperature conditions. We can perform correlation analysis based on the PSE power quality data and temperature variation characteristic data. By calculating the coupling coefficient between power supply parameters and temperature variation, we can obtain the relationship between power supply stability and equipment temperature. The coupling coefficient is calculated using the following formula: ; in, is the coupling coefficient, and Respectively represent the data of power supply parameters and temperature changes, and is its mean. The calculation of the coupling coefficient can reveal the correlation between power supply quality and temperature change. The performance score is calculated for the address aging feature data. The performance of the port is evaluated by the data forwarding efficiency and address table utilization in port isolation mode. The data forwarding efficiency is calculated by the following formula: ; in, is the data forwarding efficiency, is the amount of data successfully forwarded, is the total amount of data. The power supply status feature vector and the port performance feature vector are combined. By splicing feature vectors of different dimensions according to the classification structure of power supply characteristics, aging characteristics and performance characteristics, multiple device status feature vectors are generated to reflect the performance of the POE switch under different working conditions, providing a basis for subsequent fault prediction and performance optimization. The device status feature vector is synthesized by linear combination or weighted summation.

[0030] In a specific embodiment, the process of executing step S5 may specifically include the following steps: The power supply status feature vectors in the multiple device status feature vectors are input into the PSE power supply weak classifier. The PSE power supply weak classifier includes a feature extraction layer, a timing analysis layer and a status prediction layer. The feature extraction layer adopts a three-layer fully connected network structure, the timing analysis layer adopts a bidirectional LSTM structure, and the status prediction layer adopts a Softmax classifier to obtain the PSE power supply degradation score; the three-layer fully connected network in the PSE power supply weak classifier performs feature dimensionality reduction of 512, 256, and 128 dimensions in turn, and processes the output of each layer through the ReLU activation function and the Dropout layer. The bidirectional LSTM contains 64 hidden units to obtain the PSE timing features; The port performance feature vectors in multiple device status feature vectors are input into the port performance weak classifier. The port performance weak classifier includes a data preprocessing layer, a feature enhancement layer, and a classification output layer. The data preprocessing layer adopts a batch normalization structure, the feature enhancement layer adopts a residual network structure, and the classification output layer adopts a cross entropy loss function to obtain the port performance degradation score. The residual network structure of the port performance weak classifier is a three-layer stacked structure, each layer includes two 3x3 convolutional layers and a short-circuit connection, and the feature map is processed by the LeakyReLU activation function to obtain the port performance timing characteristics. The temperature change feature data is input into the temperature feature weak classifier. The temperature feature weak classifier includes a temperature curve analysis layer, a trend extraction layer, and a result output layer. The temperature curve analysis layer uses a one-dimensional convolutional network, and the trend extraction layer uses an attention mechanism to obtain a temperature degradation score. The one-dimensional convolutional network of the temperature feature weak classifier sets 32 convolution kernels with a convolution kernel size of 3. The feature dimension is compressed through a maximum pooling layer. The attention mechanism uses a scaled dot-product structure to obtain the temperature change time series characteristics. Based on the PSE timing characteristics, port performance timing characteristics and temperature change timing characteristics, the PSE power supply degradation score, port performance degradation score and temperature degradation score are weighted and fused through the AdaBoost algorithm to obtain the equipment degradation prediction index.

[0031] Specifically, the power supply status feature vectors in the multiple device status feature vectors are input into the PSE power supply weak classifier. The structure of the PSE power supply weak classifier includes a feature extraction layer, a timing analysis layer, and a state prediction layer. The feature extraction layer uses a three-layer fully connected network structure to process the input power supply status features. The output of each layer of the network is nonlinearly transformed through the ReLU activation function and regularized using the Dropout layer to prevent overfitting. In the first layer, the dimension of the fully connected network is set to 512, the second layer to 256, and the third layer to 128. The output of each layer is converted through the ReLU activation function and processed through the Dropout layer to enhance the generalization ability of the model. Assume that the input power supply status feature is , then the output of the feature extraction layer is expressed as: ; in, is the weight matrix of the fully connected layer, is the bias term. After being processed by the three-layer fully connected network, the extracted power supply features are obtained The timing analysis layer of the PSE power supply weak classifier adopts a bidirectional LSTM (long short-term memory) structure. The bidirectional LSTM can capture the timing features in the input sequence from both the forward and reverse directions and understand the dynamic changes in the data. The number of hidden units of the bidirectional LSTM is set to 64. For the input features , bidirectional LSTM generates a time series feature : ; Among them, Bi-LSTM represents a bidirectional LSTM network. Capture the dynamic information of power supply characteristics changing over time. In the state prediction layer, a Softmax classifier is used to classify the time series features. Classify and output the PSE power supply degradation score. The Softmax function converts the input timing features into category probability distribution. Set the output of the classifier to ,but: ; in, is the weight matrix of the Softmax layer, is a bias term. The PSE power supply degradation score is obtained, which reflects the health of the device power supply status. The port performance feature vectors in the multiple device status feature vectors are input to the port performance weak classifier. The structure of the port performance weak classifier includes a data preprocessing layer, a feature enhancement layer, and a classification output layer. In the data preprocessing layer, batch normalization is used to process the input data to accelerate training and improve the stability of the model. Assume that the input port performance feature is , then the output of the batch normalization layer is: ; In the feature enhancement layer, the residual network structure is used to improve the representation ability of the model. The residual network alleviates the gradient vanishing problem in the deep network by introducing skip connections. The residual network structure is a three-layer stacked structure, each layer contains two 3x3 convolutional layers and a short-circuit connection. Assume that the output of the feature enhancement layer is , then it is expressed as: ; ResNet represents the residual network. Through the feature enhancement layer, the enhanced port performance characteristics are obtained. In the classification output layer, the cross entropy loss function is used to calculate the port performance degradation score. The calculation formula of the cross entropy loss function for multi-class classification problems is: ; in, is the actual label, is the predicted probability. Through this process, we get the port performance degradation score . Input the temperature change feature data into the temperature feature weak classifier. The structure of the temperature feature weak classifier includes a temperature curve analysis layer, a trend extraction layer, and a result output layer. In the temperature curve analysis layer, a one-dimensional convolutional network (1D ConvNet) is used to analyze the temporal characteristics of temperature changes. The one-dimensional convolutional network processes the time series data by sliding the convolution kernel to extract local features from it. Set the input to the temperature feature , after the convolution operation, the temperature time series characteristics are obtained : ; The size of the convolution kernel is 3, the number of convolution kernels is set to 32, and the dimension reduction is performed through the maximum pooling layer. In the trend extraction layer, the attention mechanism is used to focus on the important change areas in the temperature curve. The attention mechanism dynamically adjusts the model's attention to different inputs by weighted summation. The features after setting the attention mechanism are , expressed as: ; In the result output layer, the temperature change features are converted into temperature degradation scores through the Softmax classifier. Based on the PSE timing characteristics, port performance timing characteristics and temperature change timing characteristics, the AdaBoost algorithm is used to perform weighted fusion on the PSE power supply degradation score, port performance degradation score and temperature degradation score to obtain the equipment degradation prediction index. The AdaBoost algorithm combines the outputs of multiple classifiers by weighted average to obtain a comprehensive prediction result. Assume that the weight of each score is , then the equipment degradation prediction index for: ; Through weighted fusion, the equipment degradation prediction index is obtained, and the health status of the equipment can be judged based on this index, and fault warning and maintenance decisions can be made.

[0032] In a specific embodiment, the process of executing step S6 may specifically include the following steps: Performing a first time segmentation on the PSE timing characteristics to obtain PSE sequence data; performing a second time segmentation on the port performance timing characteristics to obtain port sequence data; performing a third time segmentation on the temperature change timing characteristics to obtain temperature sequence data; The PSE sequence data, port sequence data and temperature sequence data are time stamp aligned, and a multimodal feature sequence with a uniform sampling interval is generated by a cubic spline interpolation algorithm to obtain aligned feature data; Perform the first stage feature fusion on the aligned feature data, and obtain the first fusion weight coefficient by calculating the PSE power supply-temperature coupling coefficient and the port performance-temperature coupling coefficient; The first fusion weight coefficient is input into the first-level classifier of the improved AdaBoost algorithm, and the PSE power supply degradation score and the port performance degradation score are weighted by introducing a weak classifier group with a temperature compensation factor to obtain a first-stage degradation index; The second stage feature fusion is performed on the first stage degradation index and temperature degradation score, and the final weight distribution is calculated by introducing a multi-level weighted method with an adaptive temperature threshold to obtain the second fusion weight coefficient; The first-stage degradation index and the second fusion weight coefficient are weighted and calculated, and the equipment degradation prediction index is obtained by setting the grading standard of [0.3, 0.6) as mild degradation, [0.6, 0.8) as moderate degradation, and [0.8, 1.0] as severe degradation.

[0033] Specifically, the PSE time series feature is first segmented into a data sequence of multiple time periods according to a fixed time window. For example, assuming that the data of the PSE time series feature is , by time step Split and obtain multiple subsequences: ; in, Indicates The data sequence after time series segmentation, is the total number after segmentation. Similarly, the port performance timing characteristics and temperature change timing characteristics are also segmented for the second and third time series respectively to obtain the port sequence data and temperature series data ,Right now: ; ; The cubic spline interpolation algorithm is used to smoothly connect multiple data sequences with inconsistent timestamps through the interpolation function to obtain a uniform sampling interval. Suppose there are three incompletely aligned time series data and , find a common time axis for each sequence, that is, adjust the timestamps of these data through cubic spline interpolation so that all data sequences are aligned on the same time axis to obtain aligned feature data: ; Among them, SplineInterpolation represents the cubic spline interpolation operation, is the aligned multimodal feature data. The first stage feature fusion is performed on the aligned feature data. The first fusion weight coefficient is obtained by calculating the coupling coefficient between PSE power supply and temperature and the coupling coefficient between port performance and temperature. The coupling coefficient reflects the degree of mutual influence between two different features. Assume Represents the PSE power supply characteristics, Represents the temperature characteristics, Represents the port performance characteristics, and the coupling coefficient between PSE and temperature, and port performance and temperature is obtained by calculating the Pearson correlation coefficient: ; ; in, represents the covariance, , , are the standard deviations of PSE, port and temperature characteristics respectively. Through these coupling coefficients, the fusion weight coefficient of the first stage is calculated : ; The weight coefficient Input into the first-level classifier of the improved AdaBoost algorithm. The AdaBoost algorithm improves the accuracy of the model by weighted combination of multiple weak classifiers. The first-level classifier weights the PSE power supply degradation score and the port performance degradation score by introducing a weak classifier group with a temperature compensation factor to obtain the first-stage degradation index: ; in, and Represent the PSE power supply score and port performance score respectively. The first stage degradation index is weighted and fused with the temperature degradation score. An adaptive temperature threshold is introduced, and the final weight distribution is calculated through a multi-level weighting method. This means that temperature changes not only affect the PSE power supply and port performance, but also affect the final equipment degradation prediction results. By calculating the adaptive weight coefficient , optimize the fusion process: ; The first-stage degradation index and the second-stage fusion weight coefficient are weighted to obtain the final equipment degradation prediction index. : ; By setting the classification standard of equipment degradation, [0.3, 0.6) is mild degradation, [0.6, 0.8) is moderate degradation, and [0.8, 1.0] is severe degradation, the final equipment degradation prediction index Determine the health status of the device.

[0034] The above describes the aging test method of the POE switch for security in the embodiment of the present invention. The following describes the aging test device of the POE switch for security in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, an aging test device for a POE switch for security includes: The acquisition module is used to fix the POE switch to be tested on the test platform, apply standard loads to the POE power supply ports through the load simulator, obtain power supply parameters and port status, and obtain initial test data; A classification module is used to classify the initial test data according to POE power supply parameters, port negotiation status and temperature distribution data to generate a hierarchical test benchmark matrix; The test module is used to perform POE port full load test, port isolation data flow test and automatic negotiation interaction test respectively through the intelligent PSE controller based on the hierarchical test benchmark matrix, and collect the full test data set in a hierarchical progressive manner; A calculation module is used to calculate the PSE power supply characteristics, MAC address aging characteristics and port performance characteristics of the full test data set to generate multiple device status feature vectors; The processing module is used to input multiple equipment state feature vectors into the aging prediction model set to calculate the equipment degradation trend and obtain the equipment degradation prediction index.

[0035] Through the coordinated cooperation of the above components and a hierarchical and progressive testing strategy, a comprehensive test of the POE switch's power supply capacity, network performance and environmental adaptability is achieved, thereby improving the test coverage. An intelligent PSE controller and multi-dimensional data fusion technology are used to establish a device status feature vector, making the test results more objective and accurate. The introduction of a deep learning-based aging prediction model set, combined with the weighted fusion mechanism of the AdaBoost algorithm, improves the accuracy of device degradation trend prediction. Through a dynamic test parameter adjustment mechanism, the test process can be adaptively optimized according to the device status, reducing the waste of test resources. A complete multi-modal feature sequence analysis system is established, which realizes the correlation analysis of the multi-dimensional performance parameters of the device, providing a reliable basis for equipment maintenance decisions. Through a graded early warning mechanism and a temperature compensation strategy, the adaptability and prediction accuracy of the test method in extreme environments are enhanced.

[0036] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0037] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0038] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0039] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0041] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0042] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A POE switch aging test method for security, characterized in that: The method comprises: The POE switch to be tested is fixed on the test platform, and a standard load is applied to the POE power supply port through a load simulator to obtain power supply parameters and port status to obtain initial test data; Classifying the initial test data according to POE power supply parameters, port negotiation status and temperature distribution data to generate a hierarchical test benchmark matrix; Based on the hierarchical test benchmark matrix, the POE port full load test, the port isolation data flow test and the automatic negotiation interaction test are respectively performed by the intelligent PSE controller, and the full test data set is collected in a hierarchical progressive manner; Perform PSE power supply feature calculation, MAC address aging feature calculation and port performance feature calculation on the full test data set to generate multiple device status feature vectors; The multiple equipment state feature vectors are input into an aging prediction model set to calculate equipment degradation trends, thereby obtaining equipment degradation prediction indicators.

2. The aging test method for a POE switch for security according to claim 1, characterized in that: The POE switch to be tested is fixed on the test platform, and a standard load is applied to the POE power supply port through a load simulator to obtain power supply parameters and port status, and obtain initial test data, including: The POE switch to be tested is fixed on a standard 13-inch rack, and the physical ports of the POE switch to be tested are numbered and identified by a scanner to obtain port position mapping data; The 16 POE ports in the port location mapping data are respectively configured with a load simulator of the IEEE802.3af / at standard, and the voltage value of the 52V power output terminal is collected by a digital multimeter to obtain the initial voltage data of the power supply port; The initial voltage data of the power supply port is input into the voltage regulation controller, and the output voltage of each POE port is scanned in the range of 0-30W by PWM wave modulation to obtain the port power supply curve data; Performing threshold comparison on the port power supply curve data, setting the power supply reference value and voltage deviation value of each POE port through a voltage comparator to obtain port power supply reference data, and based on the port power supply reference data, performing an Auto MDI / MDI-X automatic flip test on each POE port through an intelligent PSE controller to obtain port line pair identification data; Perform cross-matrix analysis on the port line pair identification data, generate a cross-correlation table between ports through Boolean algebra operations, obtain a port state matrix, apply a 15.4W standard load to each POE port in the port state matrix, collect temperature values ​​of the power module, PSE controller and Ethernet chip through a temperature sensor, and obtain target point temperature distribution data; The initial voltage data of the power supply port, the port power supply curve data, the port state matrix and the target point temperature distribution data are fused to obtain initial test data.

3. The aging test method for a POE switch for security use according to claim 2, characterized in that: The initial test data is classified according to POE power supply parameters, port negotiation status and temperature distribution data to generate a hierarchical test benchmark matrix, including: Numerical classification is performed on the POE power supply parameters in the initial test data, and segmentation is performed according to the 15.4W threshold value of the IEEE802.3af standard and the 30W threshold value of the IEEE802.3at standard to obtain power supply level interval data; Based on the power supply level interval data, the power supply parameters of each POE port are standardized and calculated to obtain a port power supply reference value, and the port power supply reference values ​​are arranged in the order of port numbers, and a 16×3-dimensional power supply parameter matrix is ​​generated through matrix operation to obtain POE power supply reference data; Extracting the Auto MDI / MDI-X status data in the port status matrix, verifying the negotiation capability of each port through the port isolation function, and obtaining the port negotiation status data; Combine and analyze the port negotiation state data and the IEEE802.3X flow control state, generate negotiation reference parameters for each POE port through a state mapping table, and obtain negotiation state reference data; The temperature distribution data of the key points are divided into statistical partitions according to the positions of the power module, the PSE controller and the Ethernet chip, and the temperature distribution characteristics are generated by temperature gradient calculation to obtain temperature reference data; Arrange the POE power supply reference data, the negotiation state reference data and the temperature reference data in a two-dimensional matrix form, generate a hierarchical feature matrix through linear transformation, and obtain test level data; The test hierarchical data is restructured, and the test parameters of the power supply layer, the negotiation layer and the temperature layer are integrated through a hierarchical mapping rule to obtain a hierarchical test reference matrix.

4. The aging test method for a POE switch for security use according to claim 3, characterized in that: Based on the hierarchical test benchmark matrix, the POE port full load test, the port isolation data flow test and the automatic negotiation interaction test are respectively performed by the intelligent PSE controller, and the full test data set is collected in a hierarchical progressive manner, including: Performing a first layer test based on the power supply layer parameters in the hierarchical test benchmark matrix, applying a 15.4W rated load to a single POE port for continuous power supply for 8 hours, and obtaining single-port rated load data; Perform a first-layer progressive test according to the single-port rated load data, apply a 30W maximum load to a single POE port for continuous power supply for 8 hours, and obtain the single-port maximum load data; Based on the single-port maximum load data, a first-layer full load test is performed, and a total power of 240W is applied to all POE ports for 24 hours to obtain full-port full load test data; Performing a second layer test based on the performance layer parameters in the hierarchical test benchmark matrix, isolating data flows of all ports through a port isolation function, and obtaining port isolation configuration data; Perform a layer 2 progressive test according to the port isolation configuration data, perform concurrent data transmission on all isolated ports through IEEE802.3X flow control, and obtain data throughput test data; Performing a third layer test based on the temperature layer parameters in the layered test benchmark matrix, maintaining 30% load operation of all ports for 4 hours at a temperature of -10°C, and obtaining low temperature test data; Perform the third-layer progressive test according to the low-temperature test data, keep all ports running at 30% load for 4 hours at a temperature of 55°C, and obtain high-temperature test data; The full-port full-load test data, the data throughput test data, the low-temperature test data and the high-temperature test data are integrated according to a time sequence relationship to obtain a full test data set.

5. The aging test method for a POE switch for security use according to claim 4, characterized in that: The PSE power supply feature calculation, MAC address aging feature calculation and port performance feature calculation are performed on the full test data set to generate multiple device status feature vectors, including: The voltage data in the full-port full-load test data is normalized, and the voltage stability value is obtained by calculating the voltage fluctuation under the 240W full-load condition to obtain the power supply fluctuation characteristic data; Analyze the POE port power supply parameters according to the power supply fluctuation characteristic data, and obtain PSE power supply quality data by calculating the voltage ripple coefficient and power factor of the 52V power supply output end; Perform a MAC address learning rate test on each POE port based on the data throughput test data, and obtain address processing rate data by calculating the address update time in IEEE802.3X full-duplex mode; Based on the address processing rate data, statistical calculations are performed on the MAC address aging time and failure probability of each POE port to obtain address aging feature data; Based on the low temperature test data and the high temperature test data, the slope of the temperature rise curves of the power module, the PSE controller and the Ethernet chip is calculated to obtain temperature change characteristic data; Performing correlation analysis on the PSE power supply quality data and the temperature change characteristic data, and obtaining a power supply state characteristic vector by calculating a coupling coefficient between power supply parameters and temperature change; Performing performance score calculation on the address aging feature data, and obtaining a port performance feature vector through data forwarding efficiency and address table item utilization in a port isolation mode; The power supply status feature vector and the port performance feature vector are feature combined to generate a plurality of device status feature vectors according to the classification structure of power supply feature, aging feature and performance feature.

6. The aging test method for a POE switch for security use according to claim 5, characterized in that: The step of inputting the plurality of equipment state feature vectors into the aging prediction model set to calculate equipment degradation trends and obtain equipment degradation prediction indicators includes: Input the power supply state feature vectors in the multiple device state feature vectors into the PSE power supply weak classifier, the PSE power supply weak classifier comprises a feature extraction layer, a timing analysis layer and a state prediction layer, the feature extraction layer adopts a three-layer fully connected network structure, the timing analysis layer adopts a bidirectional LSTM structure, and the state prediction layer adopts a Softmax classifier to obtain a PSE power supply degradation score; the three-layer fully connected network in the PSE power supply weak classifier performs feature dimension reduction of 512, 256, and 128 dimensions in turn, processes the output of each layer through a ReLU activation function and a Dropout layer, and the bidirectional LSTM comprises 64 hidden units to obtain PSE timing features; Input the port performance feature vectors in the multiple device status feature vectors into a port performance weak classifier, the port performance weak classifier comprises a data preprocessing layer, a feature enhancement layer and a classification output layer, the data preprocessing layer adopts a batch normalization structure, the feature enhancement layer adopts a residual network structure, and the classification output layer adopts a cross entropy loss function to obtain a port performance degradation score; the residual network structure of the port performance weak classifier is a three-layer stacked structure, each layer comprises two 3x3 convolutional layers and a short-circuit connection, and the feature map is processed by a LeakyReLU activation function to obtain the port performance timing characteristics; The temperature change feature data is input into a temperature feature weak classifier, which includes a temperature curve analysis layer, a trend extraction layer and a result output layer. The temperature curve analysis layer adopts a one-dimensional convolutional network, and the trend extraction layer adopts an attention mechanism to obtain a temperature degradation score. The one-dimensional convolutional network of the temperature feature weak classifier is set with 32 convolution kernels, and the convolution kernel size is 3. The feature dimension is compressed through a maximum pooling layer. The attention mechanism adopts a scaled dot-product structure to obtain the temperature change time series feature. Based on the PSE timing characteristics, the port performance timing characteristics and the temperature change timing characteristics, the PSE power supply degradation score, the port performance degradation score and the temperature degradation score are weightedly fused through the AdaBoost algorithm to obtain a device degradation prediction index.

7. The aging test method for a POE switch for security use according to claim 6, characterized in that: Based on the PSE timing characteristics, the port performance timing characteristics and the temperature change timing characteristics, the PSE power supply degradation score, the port performance degradation score and the temperature degradation score are weighted and integrated by the AdaBoost algorithm to obtain the equipment degradation prediction index, including: Performing a first time segmentation on the PSE timing characteristics to obtain PSE sequence data; performing a second time segmentation on the port performance timing characteristics to obtain port sequence data; performing a third time segmentation on the temperature change timing characteristics to obtain temperature sequence data; Performing time stamp alignment on the PSE sequence data, the port sequence data and the temperature sequence data, generating a multimodal feature sequence with a uniform sampling interval by a cubic spline interpolation algorithm, and obtaining aligned feature data; Performing a first-stage feature fusion on the alignment feature data, and obtaining a first fusion weight coefficient by calculating a PSE power supply-temperature coupling coefficient and a port performance-temperature coupling coefficient; Inputting the first fusion weight coefficient into the first-level classifier of the improved AdaBoost algorithm, weighting the PSE power supply degradation score and the port performance degradation score by introducing a weak classifier group with a temperature compensation factor, and obtaining a first-stage degradation index; Performing second-stage feature fusion on the first-stage degradation index and the temperature degradation score, calculating the final weight distribution by introducing a multi-level weighting method with an adaptive temperature threshold, and obtaining a second fusion weight coefficient; The first stage degradation index and the second fusion weight coefficient are weightedly calculated, and the equipment degradation prediction index is obtained by setting the grading standards of [0.3, 0.6) as mild degradation, [0.6, 0.8) as moderate degradation, and [0.8, 1.0] as severe degradation.

8. A POE switch aging test device for security, characterized in that: Used to perform the aging test method for a POE switch for security according to any one of claims 1 to 7, the aging test device for a POE switch for security comprises: The acquisition module is used to fix the POE switch to be tested on the test platform, apply standard loads to the POE power supply ports through the load simulator, obtain power supply parameters and port status, and obtain initial test data; A classification module, used to classify the initial test data according to POE power supply parameters, port negotiation status and temperature distribution data to generate a hierarchical test reference matrix; A test module is used to perform a POE port full load test, a port isolation data flow test and an automatic negotiation interaction test respectively through an intelligent PSE controller based on the hierarchical test benchmark matrix, and collect a full test data set in a hierarchical progressive manner; A calculation module, used to perform PSE power supply feature calculation, MAC address aging feature calculation and port performance feature calculation on the full test data set to generate multiple device status feature vectors; The processing module is used to input the multiple equipment state feature vectors into the aging prediction model set to calculate the equipment degradation trend and obtain the equipment degradation prediction index.

9. A computer device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and is characterized in that when the processor executes the computer program, the aging test method for a POE switch for security as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is enabled to execute the aging test method for a POE switch for security according to any one of claims 1 to 7.

Images