A server case management method and system based on data monitoring

Abstract

The application is suitable for the technical field of case data monitoring, and provides a server case management method and system based on data monitoring.The method comprises the following steps: in the starting stage when a target unit starts to execute a reloading task, the specific type of the reloading task and the real-time noise average amplitude of the power supply path of the target unit are determined, and the preliminary risk prediction value matched with the target unit and the historical execution record are obtained.The application realizes the accurate identification of the noise interference caused by the change of the parasitic parameter of the PCB wiring by collecting the noise data of the power supply path of the target unit in real time, combining the historical execution record to establish a standard noise amplitude interval, and using the dynamic frequency spectrum generated by the transient current fluctuation test, so that the correction factor is generated by comprehensively calculating the similar trend and amplitude deviation to dynamically correct the preliminary risk prediction value.

Description

Technical Field

[0001] This invention belongs to the field of chassis data monitoring technology, and in particular relates to a server chassis management method and system based on data monitoring. Background Technology

[0002] Currently, server chassis are a crucial component of data center and cloud computing infrastructure, and their stability and security directly impact overall system efficiency. Existing technologies primarily rely on monitoring conventional parameters such as current, voltage, and temperature for risk prediction and management of server chassis. However, in practical applications, these parameters often fail to fully reveal potential hazards arising from minute changes within the electrical system. In particular, the parasitic parameters of PCB traces change over long-term use, leading to abnormal fluctuations in noise along the power supply path.

[0003] Such noise anomalies may conceal potential electrical fault risks in the early stages of high-load operations. Moreover, their variation amplitude and dynamic characteristics are usually quite weak, making it difficult for traditional monitoring methods to capture and correct this hidden danger in a timely manner. This results in insufficient accuracy of risk assessment and affects the overall effectiveness of early warning and intelligent operation and maintenance.

[0004] Furthermore, existing management systems lack in-depth analysis methods for noise characteristics in data processing and dynamic risk correction, resulting in delays and missed detections in the initial detection of potential risks, thus hindering the improvement of the overall security and stability of the server chassis. Summary of the Invention

[0005] The purpose of this invention is to provide a server chassis management method and system based on data monitoring, which aims to solve the problems mentioned in the background art.

[0006] This invention is implemented as follows: a server chassis management method based on data monitoring, the method comprising:

[0007] At the initial stage of the target unit starting to perform heavy load operations, the specific type of heavy load operation and the real-time average noise amplitude of the target unit's power supply path are determined, and preliminary risk prediction values ​​and historical execution records matching the target unit are obtained.

[0008] Analyze historical execution records to determine the standard noise amplitude range when the target unit performs a specific type of heavy-load operation, and determine whether the real-time average noise amplitude is within the standard noise amplitude range. If so, perform several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period.

[0009] The test noise amplitude and parasitic parameter variation values ​​are obtained during each transient current fluctuation test, and a first dynamic spectrum diagram and a second dynamic spectrum diagram are plotted accordingly. The proportion of similar trend points in the first dynamic spectrum diagram and the second dynamic spectrum diagram is compared to whether it is greater than a preset threshold.

[0010] If the proportion of similar trend points is determined to be greater than a preset threshold, then the set of key frequency points is determined based on the first dynamic spectrum, and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point are determined.

[0011] Based on the proportion of similar trend points and the baseline noise amplitude and actual noise amplitude corresponding to each key frequency point in the key frequency point set, the preliminary risk prediction value is comprehensively revised.

[0012] As a further limitation of the technical solution of this embodiment of the invention, the steps of parsing historical execution records, determining the standard noise amplitude range when the target unit performs a specific type of heavy-load operation, and determining whether the real-time average noise amplitude is within the standard noise amplitude range, and if so, performing several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period include:

[0013] Analyze historical execution records and filter out a predetermined number of secondary execution records that are consistent with a specific type and have not experienced any anomalies during operation;

[0014] Each secondary execution record is analyzed to determine its corresponding standard noise amplitude. The obtained standard noise amplitude is then denoised and smoothed. The maximum and minimum values ​​among the processed standard noise amplitudes are used as the upper and lower bounds to generate the standard noise amplitude range.

[0015] Determine whether the real-time average noise amplitude is within the standard noise amplitude range. If so, perform several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period.

[0016] As a further limitation of the technical solution of this invention, the step of obtaining the test noise amplitude and parasitic parameter variation values ​​during each transient current fluctuation test, and plotting a first dynamic spectrum diagram and a second dynamic spectrum diagram accordingly, and comparing whether the proportion of similar trend points in the first dynamic spectrum diagram and the second dynamic spectrum diagram is greater than a preset threshold includes:

[0017] During each transient current fluctuation test, a high-speed data acquisition device is used to collect the test noise amplitude and parasitic parameter variation values ​​in real time, as well as the frequency range of each test.

[0018] A first dynamic spectrum diagram is constructed based on the test noise amplitude and frequency range, and a second dynamic spectrum diagram is constructed based on the parasitic parameter variation value and frequency range.

[0019] By comparing and analyzing the first dynamic spectrum and the second dynamic spectrum, the correlation coefficient of the signal amplitude changes in the two spectra within each frequency interval is calculated. When the correlation coefficient exceeds the preset value, the frequency interval is regarded as a similar trend point. The proportion of similar trend points in the total key frequency interval is statistically analyzed, and it is determined whether the proportion is greater than the preset threshold.

[0020] As a further limitation of the technical solution of this embodiment of the invention, if it is determined that the proportion of similar trend points is greater than a preset threshold, then the step of determining the set of key frequency points based on the first dynamic spectrum and determining the reference noise amplitude and actual noise amplitude corresponding to each key frequency point includes:

[0021] Analyze the first dynamic spectrum diagram to determine several key frequency points and their corresponding actual noise amplitudes in the first dynamic spectrum diagram, and then form a set of key frequency points from these key frequency points.

[0022] The predetermined number of secondary execution records are analyzed, and several noise amplitude data that are consistent with each key frequency point are selected. The average value of several noise amplitudes corresponding to each key frequency point is calculated and used as the reference noise amplitude for each key frequency point.

[0023] As a further limitation of the technical solution of this invention, the step of comprehensively correcting the preliminary risk prediction value based on the proportion of similar trend points and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point in the key frequency point set includes:

[0024] The first correction factor is generated based on the proportion of similar trend points, and the second correction factor is generated based on the reference noise amplitude and the actual noise amplitude corresponding to each key frequency point in the key frequency point set.

[0025] The preset correction formula is retrieved, and the first correction factor and the second correction factor are combined and applied to the preliminary risk prediction value to achieve a comprehensive correction of the preliminary risk prediction value.

[0026] As a further limitation of the technical solution of this embodiment of the invention, the modified formula is as follows: ,in This refers to the revised risk forecast value. This refers to the preliminary risk forecast value. This refers to the first correction factor. This refers to the second correction factor;

[0027] In the corrected formula, ,in This refers to the calibration coefficient that adjusts the influence of the first correction factor on the weights. This refers to the proportion of similar trend points;

[0028] ,in This refers to the calibration coefficient that adjusts the influence of the second correction factor on the weights. It refers to the set of key frequency points. This refers to belonging to the set of key frequency points. A key frequency point in the, Refers to key frequency points The corresponding actual noise amplitude, Refers to key frequency points The corresponding reference noise amplitude, Refers to key frequency points The corresponding weights.

[0029] A server chassis management system based on data monitoring, the system comprising: a data acquisition module, a transient testing module, a spectrum plotting module, an arithmetic set generation module, and a prediction value correction module, wherein:

[0030] The data acquisition module is used to determine the specific type of heavy-load operation and the real-time average noise amplitude of the power supply path of the target unit at the initial stage of the heavy-load operation of the target unit, and at the same time acquire the preliminary risk prediction value and historical execution records that match the target unit.

[0031] The transient test module is used to analyze historical execution records, determine the standard noise amplitude range when the target unit performs a specific type of heavy-load operation, and determine whether the real-time average noise amplitude is within the standard noise amplitude range. If it is determined to be within the standard noise amplitude range, the PCB wiring of the target unit will be subjected to several transient current fluctuation tests within a preset time period.

[0032] The spectrum plotting module is used to obtain the test noise amplitude and parasitic parameter variation value during each transient current fluctuation test, and plot the first dynamic spectrum plot and the second dynamic spectrum plot accordingly, and compare whether the proportion of similar trend points in the first dynamic spectrum plot and the second dynamic spectrum plot is greater than a preset threshold.

[0033] The set generation module is used to determine the set of key frequency points based on the first dynamic spectrum if the proportion of similar trend points is greater than a preset threshold, and to determine the reference noise amplitude and actual noise amplitude corresponding to each key frequency point.

[0034] The prediction correction module is used to comprehensively correct the preliminary risk prediction value based on the proportion of similar trend points and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point in the key frequency point set.

[0035] As a further limitation of the technical solution of this embodiment of the invention, the transient test module specifically includes:

[0036] The execution record parsing unit is used to parse historical execution records and filter out a predetermined number of secondary execution records that are consistent with a specific type and have not experienced any abnormalities during operation.

[0037] The amplitude range generation unit is used to analyze each secondary execution record, determine its corresponding standard noise amplitude, perform noise reduction and smoothing processing on the obtained standard noise amplitude, and generate standard noise amplitude range based on the maximum and minimum values ​​among the processed standard noise amplitudes as the upper and lower bounds, respectively.

[0038] The test execution unit is used to determine whether the real-time average noise amplitude is within the standard noise amplitude range. If it is, it performs several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period.

[0039] As a further limitation of the technical solution of this embodiment of the invention, the spectrum plotting module specifically includes:

[0040] The data acquisition unit is used to acquire the test noise amplitude and parasitic parameter variation values ​​in real time, as well as the frequency range of each test, using a high-speed data acquisition device during each transient current fluctuation test.

[0041] The spectrum plotting unit is used to construct a first dynamic spectrum plot based on the test noise amplitude and frequency range, and to construct a second dynamic spectrum plot based on the parasitic parameter variation value and frequency range.

[0042] The spectrum analysis unit is used to compare and analyze the first dynamic spectrum and the second dynamic spectrum. By calculating the correlation coefficient of the amplitude changes of the two spectra in each frequency interval, it determines that when the correlation coefficient exceeds the preset value, the frequency interval is regarded as a similar trend point. It also calculates the proportion of similar trend points in the total key frequency interval and determines whether the proportion is greater than the preset threshold.

[0043] As a further limitation of the technical solution of this embodiment of the invention, the set generation module specifically includes:

[0044] The set generation unit is used to analyze the first dynamic spectrum diagram, determine several key frequency points and their corresponding actual noise amplitudes in the first dynamic spectrum diagram, and form a set of key frequency points from the several key frequency points.

[0045] The reference amplitude calculation unit is used to parse a predetermined number of secondary execution records, filter out several noise amplitude data that are consistent with each key frequency point, calculate the average value of several noise amplitudes corresponding to each key frequency point, and use it as the reference noise amplitude corresponding to each key frequency point.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] This invention collects noise data from the power supply path of the target unit in real time, establishes a standard noise amplitude range by combining it with historical execution records, and uses a dynamic spectrum generated by transient current fluctuation testing to accurately identify noise interference caused by changes in parasitic parameters of PCB wiring. Then, by comprehensively calculating similar trends and amplitude deviations, a correction factor is generated to dynamically correct the preliminary risk prediction value.

[0048] This dynamic correction mechanism can not only reflect the potential risks of the electrical system in the early stage of heavy-load operation in a timely manner, improving the accuracy and real-time nature of risk assessment, but also provide quantitative basis for system early warning and intelligent operation and maintenance, effectively reduce the failure rate caused by noise interference, improve the overall stability and security of the server chassis, optimize maintenance strategies, and reduce operation and maintenance costs, with significant engineering applications and economic benefits. Attached Figure Description

[0049] Figure 1 A flowchart of the method provided in the embodiments of the present invention;

[0050] Figure 2 This is a flowchart illustrating the transient current fluctuation test performed on the PCB wiring of the target unit in the method provided by the embodiments of the present invention;

[0051] Figure 3 This is a flowchart illustrating the comparison of a first dynamic spectrogram and a second dynamic spectrogram in the method provided in this embodiment of the invention.

[0052] Figure 4 This is a flowchart illustrating the parsing of the first dynamic spectrum in the method provided by an embodiment of the present invention;

[0053] Figure 5 This is a flowchart illustrating the comprehensive correction of preliminary risk prediction values ​​in the method provided in this embodiment of the invention;

[0054] Figure 6 Application architecture diagram of the system provided in the embodiments of the present invention;

[0055] Figure 7 This is a structural block diagram of the transient test module in the system provided in the embodiment of the present invention;

[0056] Figure 8 This is a structural block diagram of the spectrum plotting module in the system provided in the embodiments of the present invention;

[0057] Figure 9 This is a structural block diagram of the set generation module in the system provided in the embodiments of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0059] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0060] Specifically, a server chassis management method based on data monitoring includes the following steps:

[0061] Step S100: At the initial stage of the target unit starting to perform heavy load operation, determine the specific type of heavy load operation and the real-time average noise amplitude of the target unit's power supply path, and at the same time obtain the preliminary risk prediction value and historical execution record that match the target unit.

[0062] In this embodiment of the invention, the target unit refers to a key module within the server chassis, whose operating status has a significant impact on the overall stability of the machine. Heavy load operation refers to the workload experienced by the target unit when performing high-load tasks, while the "initial phase" refers to a short period after the target unit begins heavy load operation, a period sufficient to reflect whether the noise amplitude of the power supply path is within normal limits.

[0063] The real-time average noise amplitude refers to the average noise amplitude obtained after processing (e.g., filtering and averaging) the noise signal data continuously collected by sensors installed on the power supply path during a short period of time. This parameter is used to determine whether the noise level in the current power supply path is abnormal.

[0064] In this embodiment, the power supply path is defined as the physical line that provides power to the target unit, including power lines and related connectors, but excluding PCB traces.

[0065] The preliminary risk prediction value is a risk index calculated using existing mature technical means (based on conventional parameters such as current and voltage), which is used as the initial assessment basis for the potential electrical fault risk of the target unit during heavy-load operation.

[0066] Historical execution records refer to operational and sensor data collected over a long period of time by the monitoring system and operation and maintenance logs during heavy-load operations on the target unit. This includes noise amplitude data, task type information, and related anomaly records measured by the target unit's power supply path during heavy-load operations.

[0067] Furthermore, the server chassis management method based on data monitoring also includes the following steps:

[0068] Step S200: Analyze the historical execution records, determine the standard noise amplitude range when the target unit performs a specific type of heavy-load operation, and determine whether the real-time average noise amplitude is within the standard noise amplitude range. If so, perform several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period.

[0069] Specifically, Figure 2 A flowchart is shown for performing transient current fluctuation tests on the PCB routing of the target cell.

[0070] The process of analyzing historical execution records to determine the standard noise amplitude range of the target unit when performing a specific type of heavy-load operation, and determining whether the real-time average noise amplitude is within the standard noise amplitude range, includes the following steps:

[0071] Step S201: Analyze the historical execution records and filter out a predetermined number of secondary execution records that are consistent with a specific type and have not experienced any abnormalities during operation;

[0072] Step S202: Analyze each secondary execution record to determine its corresponding standard noise amplitude, perform noise reduction and smoothing processing on the obtained standard noise amplitude, and generate standard noise amplitude intervals based on the maximum and minimum values ​​among the processed standard noise amplitudes as upper and lower bounds respectively.

[0073] Step S203: Determine whether the real-time average noise amplitude is within the standard noise amplitude range. If so, perform several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period.

[0074] In this embodiment of the invention, setting a predetermined number is of great significance. Its purpose is to ensure that sufficient representative sample data is collected to reflect the stable noise characteristics of the target unit when performing specific types of heavy-load operations, while avoiding the introduction of redundant data due to an excessive number of records, which could interfere with subsequent analysis. The predetermined number is generally determined based on the statistical characteristics of historical data and actual operating conditions, ensuring that the selected records accurately reflect the noise level of the system under normal conditions.

[0075] When analyzing each secondary execution record, the raw noise data is first preprocessed, using filtering and smoothing algorithms to remove occasional noise and external interference signals. Then, techniques such as Fast Fourier Transform (FFT) are used to convert the time-domain signal into frequency-domain data, thereby extracting the standard noise amplitude of the target unit under specific heavy-load operating conditions. Next, the standard noise amplitude obtained from each record is denoised and smoothed, and its maximum and minimum values ​​are taken as the upper and lower bounds, respectively, to generate a standard noise amplitude range. This range reflects the fluctuation range of power supply path noise of the target unit under normal operating conditions, providing a reference standard for judging whether the real-time average noise amplitude is abnormal.

[0076] Determining whether the real-time average noise amplitude falls within the aforementioned standard noise amplitude range is significant in verifying whether the noise level of the current target unit's power supply path is normal. Although a real-time average noise amplitude within the standard range indicates that there is no apparent noise interference risk on the power supply path, the parasitic parameters of the PCB wiring, which is closely related to the power supply path, may cause abnormal noise due to large current fluctuations during heavy-load operations, thus posing potential electrical risks.

[0077] Therefore, when the real-time average noise amplitude is within the standard range, several transient current fluctuation tests need to be performed on the PCB routing of the target unit within a preset time period. The transient current fluctuation test generates short-term current fluctuations through a preset control method (for example, using a programmable power supply module combined with a preset timing controller to precisely control the current output within a predetermined time period via pulse width modulation, thereby achieving short-term current fluctuations). A high-speed data acquisition device is used to record the noise amplitude and parasitic parameter variations during the test, thereby assessing the adverse effects of parasitic parameter changes on the power supply path noise that may occur during heavy-load operations. This step provides crucial data support for subsequent dynamic spectrum plotting and risk correction.

[0078] Furthermore, the server chassis management method based on data monitoring also includes the following steps:

[0079] Step S300: Obtain the test noise amplitude and parasitic parameter variation value during each transient current fluctuation test, and draw the first dynamic spectrum diagram and the second dynamic spectrum diagram accordingly. Compare whether the proportion of similar trend points in the first dynamic spectrum diagram and the second dynamic spectrum diagram is greater than a preset threshold.

[0080] Specifically, Figure 3 A flowchart comparing the first dynamic spectrogram with the second dynamic spectrogram is shown.

[0081] The process of acquiring the test noise amplitude and parasitic parameter variation values ​​during each transient current fluctuation test, and drawing a first dynamic spectrum and a second dynamic spectrum accordingly, and comparing whether the proportion of similar trend points in the first dynamic spectrum and the second dynamic spectrum is greater than a preset threshold, specifically includes the following steps:

[0082] Step S301: During each transient current fluctuation test, a high-speed data acquisition device is used to collect the test noise amplitude and parasitic parameter variation values ​​in real time, as well as the frequency range of each test.

[0083] Step S302: Construct a first dynamic spectrum diagram based on the test noise amplitude and frequency range, and construct a second dynamic spectrum diagram based on the parasitic parameter variation value and frequency range;

[0084] Step S303: Compare and analyze the first dynamic spectrum diagram and the second dynamic spectrum diagram. Calculate the correlation coefficient of the amplitude changes of the two spectra within each frequency interval. Determine that when the correlation coefficient exceeds a preset value, the frequency interval is considered a similar trend point. Statistically calculate the proportion of similar trend points in the total key frequency intervals and determine whether the proportion is greater than a preset threshold.

[0085] In this embodiment of the invention, during each transient current fluctuation test, a high-speed data acquisition device is used to collect the test noise amplitude, parasitic parameter variation, and frequency range of each test in real time. To this end, a high-precision sensor and high-speed ADC technology are used to capture the target signal, which is then preprocessed (e.g., filtering, denoising, and normalization) to ensure the accuracy and stability of the acquired data. Next, based on the acquired test noise amplitude and frequency range, a first dynamic spectrum is constructed using digital signal processing techniques (e.g., Fast Fourier Transform and window function processing). Simultaneously, using the same or similar frequency domain analysis techniques, a second dynamic spectrum is generated based on the parasitic parameter variation and frequency range. These two spectra reflect the dynamic changes of test noise and parasitic parameter variation in different frequency ranges, thus providing a reliable data foundation for subsequent analysis.

[0086] Next, the first and second dynamic spectrum diagrams are compared and analyzed. The Pearson correlation coefficient is used as a quantitative indicator to calculate the correlation coefficient of the signal amplitude changes in each frequency interval. This correlation coefficient is used to assess the degree of linear correlation between the test noise amplitude and parasitic parameter variations within that frequency interval. When the calculated correlation coefficient exceeds a preset value, it is considered that the two have a similar trend within that frequency interval, and that frequency interval is regarded as a similar trend point. Statistical analysis of the proportion of these similar trend points in the total critical frequency intervals reflects the degree of correlation between noise fluctuations caused by parasitic parameter changes in the PCB routing of the target unit under heavy-load operating conditions. A higher proportion of similar trend points indicates that parasitic parameter changes have a significant impact on noise amplitude within the critical frequency interval, suggesting potential electrical risks in subsequent work.

[0087] The setting of preset thresholds is usually based on statistical analysis and experimental calibration of historical data. By comparing the proportion of similar trends under normal operating conditions with the changing patterns under abnormal conditions, a critical value that distinguishes between normal and abnormal conditions is determined, thus providing a basis for risk correction. This proportion and its threshold not only help to identify potential hazards revealed by PCB wiring transient current fluctuation tests when the noise level on the power supply path surface does not show abnormalities, but also provide quantitative data support for subsequent risk correction.

[0088] Furthermore, the server chassis management method based on data monitoring also includes the following steps:

[0089] Step S400: If the proportion of similar trend points is greater than a preset threshold, then the set of key frequency points is determined based on the first dynamic spectrum, and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point are determined.

[0090] Specifically, Figure 4 A flowchart for analyzing the first dynamic spectrogram is shown.

[0091] If the proportion of similar trend points is determined to be greater than a preset threshold, then the set of key frequency points is determined based on the first dynamic spectrum, and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point are determined, specifically including the following steps:

[0092] Step S401: Analyze the first dynamic spectrum diagram, determine several key frequency points and their corresponding actual noise amplitudes in the first dynamic spectrum diagram, and form a set of key frequency points from the several key frequency points.

[0093] Step S402: parse a predetermined number of secondary execution records, filter out several noise amplitude data that are consistent with each key frequency point, calculate the average value of several noise amplitudes corresponding to each key frequency point, and use it as the reference noise amplitude corresponding to each key frequency point.

[0094] In this embodiment of the invention, when the proportion of similar trend points exceeds a preset threshold, the system first extracts key frequency points from the first dynamic spectrum. These key frequency points are determined by analyzing the obvious peaks, stability, and noise characteristics in the spectrum, representing the inherent noise characteristics during the operation of the target unit. The actual noise amplitude corresponding to each key frequency point in the first dynamic spectrum is the noise amplitude measured in real time at that frequency point, reflecting the actual noise performance of the system under the current test conditions.

[0095] Next, by analyzing a predetermined number of secondary execution records, noise amplitude data consistent with each key frequency point is selected from historical data. Specifically, the noise amplitude corresponding to the key frequency point is extracted from each secondary execution record, and this data is denoised, smoothed, and then averaged. This average value is defined as the baseline noise amplitude for the corresponding key frequency point. The baseline noise amplitude represents the standard noise level of the target unit at that key frequency point when performing a specific type of heavy-load operation and the system is operating normally, providing a quantitative reference for subsequent risk assessment and risk correction.

[0096] Furthermore, the server chassis management method based on data monitoring also includes the following steps:

[0097] Step S500: Based on the proportion of similar trend points and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point in the key frequency point set, the preliminary risk prediction value is comprehensively corrected.

[0098] Specifically, Figure 5 A flowchart is shown for the comprehensive revision of the initial risk forecast values.

[0099] The process of revising the preliminary risk prediction value based on the proportion of similar trend points and the baseline and actual noise amplitudes corresponding to each key frequency point in the key frequency point set includes the following steps:

[0100] Step S501: Calculate and generate a first correction factor based on the proportion of similar trend points, and calculate and generate a second correction factor based on the reference noise amplitude and the actual noise amplitude corresponding to each key frequency point in the key frequency point set.

[0101] Step S502: Retrieve the preset correction formula and combine the first correction factor with the second correction factor to apply to the preliminary risk prediction value, thereby achieving a comprehensive correction of the preliminary risk prediction value.

[0102] The corrected formula is: ,in This refers to the revised risk forecast value. This refers to the preliminary risk forecast value. This refers to the first correction factor. This refers to the second correction factor;

[0103] In the corrected formula, ,in This refers to the calibration coefficient that adjusts the influence of the first correction factor on the weights. This refers to the proportion of similar trend points;

[0104] ,in This refers to the calibration coefficient that adjusts the influence of the second correction factor on the weights. It refers to the set of key frequency points. This refers to belonging to the set of key frequency points. A key frequency point in the, Refers to key frequency points The corresponding actual noise amplitude, Refers to key frequency points The corresponding reference noise amplitude, Refers to key frequency points The corresponding weights.

[0105] In this embodiment of the invention, the first correction factor mainly reflects the proportion of similar trend points in the first dynamic spectrum and the second dynamic spectrum. This proportion reflects the overall correlation between the changes in parasitic parameters of PCB wiring and the dynamic changes in the noise amplitude of the power supply path during heavy-load operation of the target unit. If the proportion of similar trends is high, it indicates that the noise changes and parasitic parameter changes are highly consistent in the critical frequency region, suggesting that the electrical risk may be relatively large.

[0106] The second correction factor quantifies the deviation between the actual noise amplitude at key frequency points and the predetermined reference noise amplitude, describing from a microscopic perspective the degree of deviation between the current noise level and the noise performance under normal operating conditions.

[0107] Combining the first and second correction factors to comprehensively revise the initial risk prediction value takes into account both the consistency of the overall trend and the specific amplitude deviations at key frequencies, thus more accurately reflecting the potential electrical risks caused by changes in PCB wiring parasitic parameters. The synergistic effect between the two factors effectively compensates for the limitations of a single indicator in risk prediction, thereby improving the accuracy and reliability of the entire risk assessment model.

[0108] Furthermore, Figure 6 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0109] In another preferred embodiment of the present invention, a server chassis management system based on data monitoring includes:

[0110] The data acquisition module 100 is used to determine the specific type of heavy-load operation and the real-time average noise amplitude of the power supply path of the target unit at the initial stage of the target unit starting to execute heavy-load operation, and at the same time acquire the preliminary risk prediction value and historical execution records that match the target unit.

[0111] In this embodiment of the invention, the target unit refers to a key module within the server chassis, whose operating status has a significant impact on the overall stability of the machine. Heavy load operation refers to the workload experienced by the target unit when performing high-load tasks, while the "initial phase" refers to a short period after the target unit begins heavy load operation, a period sufficient to reflect whether the noise amplitude of the power supply path is within normal limits.

[0112] The real-time average noise amplitude refers to the average noise amplitude obtained after processing (e.g., filtering and averaging) the noise signal data continuously collected by sensors installed on the power supply path during a short period of time. This parameter is used to determine whether the noise level in the current power supply path is abnormal.

[0113] In this embodiment, the power supply path is defined as the physical line that provides power to the target unit, including power lines and related connectors, but excluding PCB traces.

[0114] The preliminary risk prediction value is a risk index calculated using existing mature technical means (based on conventional parameters such as current and voltage), which is used as the initial assessment basis for the potential electrical fault risk of the target unit during heavy-load operation.

[0115] Historical execution records refer to operational and sensor data collected over a long period of time by the monitoring system and operation and maintenance logs during heavy-load operations on the target unit. This includes noise amplitude data, task type information, and related anomaly records measured by the target unit's power supply path during heavy-load operations.

[0116] Furthermore, the server chassis management system based on data monitoring also includes:

[0117] The transient test module 200 is used to parse historical execution records, determine the standard noise amplitude range when the target unit performs a specific type of heavy-load operation, and determine whether the real-time average noise amplitude is within the standard noise amplitude range. If it is determined to be within the standard noise amplitude range, the transient current fluctuation test is performed on the PCB wiring of the target unit several times within a preset time period.

[0118] Specifically, Figure 7 A structural block diagram of the transient test module 200 in the system provided in an embodiment of the present invention is shown.

[0119] In a preferred embodiment provided by the present invention, the transient testing module 200 specifically includes:

[0120] The execution record parsing unit 201 is used to parse historical execution records and filter out a predetermined number of secondary execution records that are consistent with a specific type and have not experienced any abnormalities during operation.

[0121] The amplitude interval generation unit 202 is used to analyze each secondary execution record, determine its corresponding standard noise amplitude, perform noise reduction and smoothing processing on the obtained standard noise amplitude, and generate a standard noise amplitude interval based on the maximum and minimum values ​​among the processed standard noise amplitudes as the upper and lower bounds, respectively.

[0122] Test execution unit 203 is used to determine whether the real-time noise average amplitude is within the standard noise amplitude range. If it is determined to be within the range, it performs several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period.

[0123] In this embodiment of the invention, setting a predetermined number is of great significance. Its purpose is to ensure that sufficient representative sample data is collected to reflect the stable noise characteristics of the target unit when performing specific types of heavy-load operations, while avoiding the introduction of redundant data due to an excessive number of records, which could interfere with subsequent analysis. The predetermined number is generally determined based on the statistical characteristics of historical data and actual operating conditions, ensuring that the selected records accurately reflect the noise level of the system under normal conditions.

[0124] When analyzing each secondary execution record, the raw noise data is first preprocessed, using filtering and smoothing algorithms to remove occasional noise and external interference signals. Then, techniques such as Fast Fourier Transform (FFT) are used to convert the time-domain signal into frequency-domain data, thereby extracting the standard noise amplitude of the target unit under specific heavy-load operating conditions. Next, the standard noise amplitude obtained from each record is denoised and smoothed, and its maximum and minimum values ​​are taken as the upper and lower bounds, respectively, to generate a standard noise amplitude range. This range reflects the fluctuation range of power supply path noise of the target unit under normal operating conditions, providing a reference standard for judging whether the real-time average noise amplitude is abnormal.

[0125] Determining whether the real-time average noise amplitude falls within the aforementioned standard noise amplitude range is significant in verifying whether the noise level of the current target unit's power supply path is normal. Although a real-time average noise amplitude within the standard range indicates that there is no apparent noise interference risk on the power supply path, the parasitic parameters of the PCB wiring, which is closely related to the power supply path, may cause abnormal noise due to large current fluctuations during heavy-load operations, thus posing potential electrical risks.

[0126] Therefore, when the real-time average noise amplitude is within the standard range, several transient current fluctuation tests must be performed on the PCB routing of the target unit within a preset time period. The transient current fluctuation test generates short-term current fluctuations through a preset control method and uses a high-speed data acquisition device to record the noise amplitude and parasitic parameter changes during the test, thereby assessing the adverse effects of parasitic parameter changes on the power supply path noise that may occur during heavy-load operations. This step provides crucial data support for subsequent dynamic spectrum plotting and risk correction.

[0127] Furthermore, the server chassis management system based on data monitoring also includes:

[0128] The spectrum plotting module 300 is used to obtain the test noise amplitude and parasitic parameter variation value during each transient current fluctuation test, and plot the first dynamic spectrum plot and the second dynamic spectrum plot accordingly, and compare whether the proportion of similar trend points in the first dynamic spectrum plot and the second dynamic spectrum plot is greater than a preset threshold.

[0129] Specifically, Figure 8 The diagram shows a structural block diagram of the spectrum plotting module 300 in the system provided in an embodiment of the present invention.

[0130] In a preferred embodiment of the present invention, the spectrum plotting module 300 specifically includes:

[0131] The data acquisition unit 301 is used to acquire the test noise amplitude and parasitic parameter variation values, as well as the frequency range of each test, in real time using a high-speed data acquisition device during each transient current fluctuation test.

[0132] The spectrum plotting unit 302 is used to construct a first dynamic spectrum plot based on the test noise amplitude and frequency range, and to construct a second dynamic spectrum plot based on the parasitic parameter variation value and frequency range.

[0133] The spectrum analysis unit 303 is used to compare and analyze the first dynamic spectrum and the second dynamic spectrum. By calculating the correlation coefficient of the amplitude changes of the two spectrum signals in each frequency interval, it determines that when the correlation coefficient exceeds the preset value, the frequency interval is regarded as a similar trend point. It also calculates the proportion of similar trend points in the total key frequency interval and determines whether the proportion is greater than the preset threshold.

[0134] In this embodiment of the invention, during each transient current fluctuation test, a high-speed data acquisition device is used to collect the test noise amplitude, parasitic parameter variation, and frequency range of each test in real time. To this end, a high-precision sensor and high-speed ADC technology are used to capture the target signal, which is then preprocessed (e.g., filtering, denoising, and normalization) to ensure the accuracy and stability of the acquired data. Next, based on the acquired test noise amplitude and frequency range, a first dynamic spectrum is constructed using digital signal processing techniques (e.g., Fast Fourier Transform and window function processing). Simultaneously, using the same or similar frequency domain analysis techniques, a second dynamic spectrum is generated based on the parasitic parameter variation and frequency range. These two spectra reflect the dynamic changes of test noise and parasitic parameter variation in different frequency ranges, thus providing a reliable data foundation for subsequent analysis.

[0135] Next, the first and second dynamic spectrum diagrams are compared and analyzed. The Pearson correlation coefficient is used as a quantitative indicator to calculate the correlation coefficient of the signal amplitude changes in each frequency interval. This correlation coefficient is used to assess the degree of linear correlation between the test noise amplitude and parasitic parameter variations within that frequency interval. When the calculated correlation coefficient exceeds a preset value, it is considered that the two have a similar trend within that frequency interval, and that frequency interval is regarded as a similar trend point. Statistical analysis of the proportion of these similar trend points in the total critical frequency intervals reflects the degree of correlation between noise fluctuations caused by parasitic parameter changes in the PCB routing of the target unit under heavy-load operating conditions. A higher proportion of similar trend points indicates that parasitic parameter changes have a significant impact on noise amplitude within the critical frequency interval, suggesting potential electrical risks in subsequent work.

[0136] The setting of preset thresholds is usually based on statistical analysis and experimental calibration of historical data. By comparing the proportion of similar trends under normal operating conditions with the changing patterns under abnormal conditions, a critical value that distinguishes between normal and abnormal conditions is determined, thus providing a basis for risk correction. This proportion and its threshold not only help to identify potential hazards revealed by PCB wiring transient current fluctuation tests when the noise level on the power supply path surface does not show abnormalities, but also provide quantitative data support for subsequent risk correction.

[0137] Furthermore, the server chassis management system based on data monitoring also includes:

[0138] The set generation module 400 is used to determine a set of key frequency points based on the first dynamic spectrum if the proportion of similar trend points is greater than a preset threshold, and to determine the reference noise amplitude and actual noise amplitude corresponding to each key frequency point.

[0139] Specifically, Figure 9A structural block diagram of the set generation module 400 in the system provided by an embodiment of the present invention is shown.

[0140] In a preferred embodiment provided by the present invention, the set generation module 400 specifically includes:

[0141] The set generation unit 401 is used to analyze the first dynamic spectrum diagram, determine several key frequency points and their corresponding actual noise amplitudes in the first dynamic spectrum diagram, and form a set of key frequency points from the several key frequency points.

[0142] The reference amplitude calculation unit 402 is used to parse a predetermined number of secondary execution records, filter out several noise amplitude data that are consistent with each key frequency point, calculate the average value of several noise amplitudes corresponding to each key frequency point, and use it as the reference noise amplitude corresponding to each key frequency point.

[0143] In this embodiment of the invention, when the proportion of similar trend points exceeds a preset threshold, the system first extracts key frequency points from the first dynamic spectrum. These key frequency points are determined by analyzing the obvious peaks, stability, and noise characteristics in the spectrum, representing the inherent noise characteristics during the operation of the target unit. The actual noise amplitude corresponding to each key frequency point in the first dynamic spectrum is the noise amplitude measured in real time at that frequency point, reflecting the actual noise performance of the system under the current test conditions.

[0144] Next, by analyzing a predetermined number of secondary execution records, noise amplitude data consistent with each key frequency point is selected from historical data. Specifically, the noise amplitude corresponding to the key frequency point is extracted from each secondary execution record, and this data is denoised, smoothed, and then averaged. This average value is defined as the baseline noise amplitude for the corresponding key frequency point. The baseline noise amplitude represents the standard noise level of the target unit at that key frequency point when performing a specific type of heavy-load operation and the system is operating normally, providing a quantitative reference for subsequent risk assessment and risk correction.

[0145] Furthermore, the server chassis management system based on data monitoring also includes:

[0146] The prediction correction module 500 is used to comprehensively correct the preliminary risk prediction value based on the proportion of similar trend points and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point in the key frequency point set.

[0147] In this embodiment of the invention, the first correction factor mainly reflects the proportion of similar trend points in the first dynamic spectrum and the second dynamic spectrum. This proportion reflects the overall correlation between the changes in parasitic parameters of PCB wiring and the dynamic changes in the noise amplitude of the power supply path during heavy-load operation of the target unit. If the proportion of similar trends is high, it indicates that the noise changes and parasitic parameter changes are highly consistent in the critical frequency region, suggesting that the electrical risk may be relatively large.

[0148] The second correction factor quantifies the deviation between the actual noise amplitude at key frequency points and the predetermined reference noise amplitude, describing from a microscopic perspective the degree of deviation between the current noise level and the noise performance under normal operating conditions.

[0149] Combining the first and second correction factors to comprehensively revise the initial risk prediction value takes into account both the consistency of the overall trend and the specific amplitude deviations at key frequencies, thus more accurately reflecting the potential electrical risks caused by changes in PCB wiring parasitic parameters. The synergistic effect between the two factors effectively compensates for the limitations of a single indicator in risk prediction, thereby improving the accuracy and reliability of the entire risk assessment model.

[0150] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0151] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0152] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0153] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0154] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A server chassis management method based on data monitoring, characterized in that, The method includes: At the initial stage of the target unit starting to perform heavy load operations, the specific type of heavy load operation and the real-time average noise amplitude of the target unit's power supply path are determined, and preliminary risk prediction values ​​and historical execution records matching the target unit are obtained. Analyze historical execution records to determine the standard noise amplitude range when the target unit performs a specific type of heavy-load operation, and determine whether the real-time average noise amplitude is within the standard noise amplitude range. If so, perform several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period. The test noise amplitude and parasitic parameter variation values ​​are obtained during each transient current fluctuation test, and a first dynamic spectrum diagram and a second dynamic spectrum diagram are plotted accordingly. The proportion of similar trend points in the first dynamic spectrum diagram and the second dynamic spectrum diagram is compared to see if it is greater than a preset threshold. The first dynamic spectrum diagram is constructed based on the test noise amplitude and frequency range, and the second dynamic spectrum diagram is constructed based on the parasitic parameter variation values ​​and frequency range. If the proportion of similar trend points is determined to be greater than a preset threshold, then the set of key frequency points is determined based on the first dynamic spectrum, and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point are determined. Based on the proportion of similar trend points and the baseline noise amplitude and actual noise amplitude corresponding to each key frequency point in the key frequency point set, the preliminary risk prediction value is comprehensively revised.

2. The server chassis management method based on data monitoring according to claim 1, characterized in that, The steps of analyzing historical execution records to determine the standard noise amplitude range of the target unit when performing a specific type of heavy-load operation, and determining whether the real-time average noise amplitude is within the standard noise amplitude range, and if so, performing several transient current fluctuation tests on the PCB layout of the target unit within a preset time period, include: Analyze historical execution records and filter out a predetermined number of secondary execution records that are consistent with a specific type and have not experienced any anomalies during operation; Each secondary execution record is analyzed to determine its corresponding standard noise amplitude. The obtained standard noise amplitude is then denoised and smoothed. The maximum and minimum values ​​among the processed standard noise amplitudes are used as the upper and lower bounds to generate the standard noise amplitude range. Determine whether the real-time average noise amplitude is within the standard noise amplitude range. If so, perform several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period.

3. The server chassis management method based on data monitoring according to claim 1, characterized in that, The steps of acquiring the test noise amplitude and parasitic parameter variation values ​​during each transient current fluctuation test, and plotting a first dynamic spectrum and a second dynamic spectrum accordingly, and comparing whether the proportion of similar trend points in the first dynamic spectrum and the second dynamic spectrum is greater than a preset threshold, include: During each transient current fluctuation test, a high-speed data acquisition device is used to collect the test noise amplitude and parasitic parameter variation values ​​in real time, as well as the frequency range of each test. By comparing and analyzing the first dynamic spectrum and the second dynamic spectrum, the correlation coefficient of the signal amplitude changes in the two spectra within each frequency interval is calculated. When the correlation coefficient exceeds the preset value, the frequency interval is regarded as a similar trend point. The proportion of similar trend points in the total key frequency interval is statistically analyzed, and it is determined whether the proportion is greater than the preset threshold.

4. The server chassis management method based on data monitoring according to claim 2, characterized in that, If the proportion of similar trend points is determined to be greater than a preset threshold, the steps for determining the set of key frequency points based on the first dynamic spectrum and determining the reference noise amplitude and actual noise amplitude corresponding to each key frequency point include: Analyze the first dynamic spectrum diagram to determine several key frequency points and their corresponding actual noise amplitudes in the first dynamic spectrum diagram, and then form a set of key frequency points from these key frequency points. The predetermined number of secondary execution records are analyzed, and several noise amplitude data that are consistent with each key frequency point are selected. The average value of several noise amplitudes corresponding to each key frequency point is calculated and used as the reference noise amplitude for each key frequency point.

5. The server chassis management method based on data monitoring according to claim 4, characterized in that, The steps for revising the preliminary risk prediction value based on the proportion of similar trend points and the baseline and actual noise amplitudes corresponding to each key frequency point in the key frequency point set include: The first correction factor is generated based on the proportion of similar trend points, and the second correction factor is generated based on the reference noise amplitude and the actual noise amplitude corresponding to each key frequency point in the key frequency point set. The preset correction formula is retrieved, and the first correction factor and the second correction factor are combined and applied to the preliminary risk prediction value to achieve a comprehensive correction of the preliminary risk prediction value.

6. The server chassis management method based on data monitoring according to claim 5, characterized in that, The corrected formula is: ,in This refers to the revised risk forecast value. This refers to the preliminary risk forecast value. This refers to the first correction factor. This refers to the second correction factor; In the corrected formula, ,in This refers to the calibration coefficient that adjusts the influence of the first correction factor on the weights. This refers to the proportion of similar trend points; ,in This refers to the calibration coefficient that adjusts the influence of the second correction factor on the weights. It refers to the set of key frequency points. This refers to belonging to the set of key frequency points. A key frequency point in the, Refers to key frequency points The corresponding actual noise amplitude, Refers to key frequency points The corresponding reference noise amplitude, Refers to key frequency points The corresponding weights.

7. A server chassis management system based on data monitoring, characterized in that, The system includes: a data acquisition module, a transient testing module, a spectrum plotting module, an ensemble generation module, and a prediction correction module, wherein: The data acquisition module is used to determine the specific type of heavy-load operation and the real-time average noise amplitude of the power supply path of the target unit at the initial stage of the heavy-load operation of the target unit, and at the same time acquire the preliminary risk prediction value and historical execution records that match the target unit. The transient test module is used to analyze historical execution records, determine the standard noise amplitude range when the target unit performs a specific type of heavy-load operation, and determine whether the real-time average noise amplitude is within the standard noise amplitude range. If it is determined to be within the standard noise amplitude range, the PCB wiring of the target unit will be subjected to several transient current fluctuation tests within a preset time period. The spectrum plotting module is used to obtain the test noise amplitude and parasitic parameter variation value during each transient current fluctuation test, and plot the first dynamic spectrum plot and the second dynamic spectrum plot accordingly, and compare whether the proportion of similar trend points in the first dynamic spectrum plot and the second dynamic spectrum plot is greater than a preset threshold. The spectrum plotting module includes: a spectrum plotting unit, used to construct a first dynamic spectrum plot based on the test noise amplitude and frequency range, and to construct a second dynamic spectrum plot based on the parasitic parameter variation value and frequency range; The set generation module is used to determine the set of key frequency points based on the first dynamic spectrum if the proportion of similar trend points is greater than a preset threshold, and to determine the reference noise amplitude and actual noise amplitude corresponding to each key frequency point. The prediction correction module is used to comprehensively correct the preliminary risk prediction value based on the proportion of similar trend points and the reference noise amplitude and actual noise amplitude corresponding to each key frequency point in the key frequency point set.

8. The server chassis management system based on data monitoring according to claim 7, characterized in that, The transient testing module specifically includes: The execution record parsing unit is used to parse historical execution records and filter out a predetermined number of secondary execution records that are consistent with a specific type and have not experienced any abnormalities during operation. The amplitude range generation unit is used to analyze each secondary execution record, determine its corresponding standard noise amplitude, perform noise reduction and smoothing processing on the obtained standard noise amplitude, and generate standard noise amplitude range based on the maximum and minimum values ​​among the processed standard noise amplitudes as the upper and lower bounds, respectively. The test execution unit is used to determine whether the real-time average noise amplitude is within the standard noise amplitude range. If it is, it performs several transient current fluctuation tests on the PCB wiring of the target unit within a preset time period.

9. The server chassis management system based on data monitoring according to claim 8, characterized in that, The spectrum plotting module further includes: The data acquisition unit is used to acquire the test noise amplitude and parasitic parameter variation values ​​in real time, as well as the frequency range of each test, using a high-speed data acquisition device during each transient current fluctuation test. The spectrum analysis unit is used to compare and analyze the first dynamic spectrum and the second dynamic spectrum. By calculating the correlation coefficient of the amplitude changes of the two spectra in each frequency interval, it determines that when the correlation coefficient exceeds the preset value, the frequency interval is regarded as a similar trend point. It also calculates the proportion of similar trend points in the total key frequency interval and determines whether the proportion is greater than the preset threshold.

10. The server chassis management system based on data monitoring according to claim 9, characterized in that, The set generation module specifically includes: The set generation unit is used to analyze the first dynamic spectrum diagram, determine several key frequency points and their corresponding actual noise amplitudes in the first dynamic spectrum diagram, and form a set of key frequency points from the several key frequency points. The reference amplitude calculation unit is used to parse a predetermined number of secondary execution records, filter out several noise amplitude data that are consistent with each key frequency point, calculate the average value of several noise amplitudes corresponding to each key frequency point, and use it as the reference noise amplitude corresponding to each key frequency point.

Images