IT equipment asset maintenance intelligent management method and system

Abstract

The invention discloses an intelligent management method and system for IT equipment asset maintenance, and relates to the technical field of intelligent management. During system operation, multi-dimensional parameters of IT equipment are collected in real time and transmitted to a data processing module, the collected data are preprocessed, the current state of the equipment is comprehensively analyzed, and the health state coefficient Hstate of the equipment is calculated; the method comprises the following steps: acquiring a current equipment operation state, performing baseline establishment on historical operation data of the equipment, comparing the current state with the historical data, analyzing the performance trend and change of the equipment, calculating to obtain a trend analysis coefficient Ttend, and identifying potential problems and performance reduction trend of the equipment through long-term data accumulation. And calculating a final fault prediction probability index Pfault, comparing the final fault prediction probability index Pfault with a set threshold value, obtaining a grade prediction scheme, generating early warning information, prompting a system administrator to sort and distribute according to the urgency and priority of tasks, automatically generating a comprehensive report by the system, and providing decision support for the administrator.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to an IT equipment asset maintenance intelligent management method and system. Background Art

[0002] In the context of modern enterprise information management, information technology (IT) has become an important driving force for business growth and efficiency. With the expansion of enterprise scale and diversification of business, enterprises often rely on a large number of IT equipment (such as servers, storage devices, network devices, etc.) to support their daily operations. These devices play a key role in processing data, maintaining network connections and storing information. However, as the number of devices increases, the complexity of management and maintenance also increases. In order to ensure the normal operation and efficient performance of these devices, enterprises urgently need to conduct intelligent monitoring and maintenance of their IT infrastructure.

[0003] Currently, many companies still rely on traditional manual management methods or simple monitoring tools to manage the status of IT equipment. This method is not only inefficient, but also unable to obtain the multi-dimensional operating parameters of the equipment in real time, making it difficult to identify potential equipment failures in a timely manner. In addition, the existing management system is also insufficient in data processing and analysis capabilities, unable to effectively integrate and analyze the operating data of the equipment, resulting in inaccurate assessment of the health status of the equipment and inability to formulate corresponding maintenance strategies in a timely manner. This situation not only increases the risk of equipment failure, but may also lead to business interruption and economic losses.

[0004] The above shortcomings are mainly due to the lack of systematic and intelligent solutions for the monitoring and management of IT equipment. When equipment failures are not discovered in time, it may lead to unpredictable equipment downtime, seriously affecting the company's operational efficiency and productivity. In addition, due to the long-term lack of effective performance analysis and trend prediction of equipment, it is difficult for companies to formulate reasonable maintenance plans, resulting in increased maintenance costs and waste of resources. At the same time, due to the lack of in-depth analysis of the operating status of equipment, companies are often unable to respond and handle sudden failures quickly, which affects customer satisfaction and the overall image of the company. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an IT equipment asset maintenance intelligent management method and system, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an IT equipment asset maintenance intelligent management system, including a data acquisition module, a data processing module, an equipment status analysis module, a historical data comparison module, an intelligent prediction module and a result report generation module; The data acquisition module is used to collect multi-dimensional parameters of IT equipment in real time, including cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , and transmit it to the data processing module; The data processing module is used to pre-process the collected data, including data cleaning, removal of outliers, filling of missing values, noise reduction, unit standardization and data filtering to ensure the accuracy and consistency of the data; The equipment status analysis module is used to comprehensively analyze the current status of the equipment based on the collected multi-source data and calculate the health status coefficient H of the equipment. state , get the current device running status; The historical data comparison module is used to establish a baseline for the historical operation data of the equipment, compare the current status with the historical data, analyze the performance trend and change of the equipment, and obtain the trend analysis coefficient T after calculation: trend , through the accumulation of long-term data, identify potential problems and performance degradation trends of equipment; The intelligent prediction module is used to calculate the final fault prediction probability index P based on the analysis of equipment status and historical data using machine learning algorithms and historical data. failure , and compare it with the set threshold to obtain the level prediction plan, predict the failure time and type of the equipment in the future time period, and generate early warning information to prompt the system administrator to sort and allocate tasks according to the urgency and priority; The result report generation module is used for the system to automatically generate a comprehensive report on equipment status, trend analysis, fault prediction and maintenance tasks, including the current health status of the equipment, maintenance history, fault prediction, trend analysis and maintenance task execution status, to provide decision support for managers.

[0007] Preferably, the data acquisition module includes a temperature sensor unit, a network monitoring unit and a storage read-write monitoring unit; The temperature sensor unit is used to collect the operating status data of the equipment cooling system, including the inlet and outlet temperature difference, fan speed, and obtain the cooling efficiency E of the equipment. cool , ensure that the equipment works at an appropriate temperature; The network monitoring unit is used to monitor the network connection status of the device, collect the communication delay and packet loss rate between the device and other nodes, and obtain the network delay response rate L net , helps evaluate the network performance and response speed of the device; The storage read / write monitoring unit is used to monitor the read / write speed fluctuation of the device hard disk or storage device, and obtain the hard disk read / write delay fluctuation V disk , reflects the IO performance of the storage device; The above collected parameters are transmitted to the data processing module for processing.

[0008] Preferably, the data processing module includes a data cleaning unit and a data standardization unit; The data cleaning unit is used to clean the original data, remove abnormal values, fill missing values ​​and perform noise reduction processing, automatically identify and delete obviously abnormal device data by defining thresholds or using statistical methods, fill missing values ​​in the data by using interpolation or historical data averaging, and remove noise in the collection process by using filtering algorithms; The data standardization unit is used to perform unit standardization and data filtering to ensure that data from different sources and different magnitudes are uniformly processed and analyzed.

[0009] Preferably, the equipment status analysis module includes a health status assessment unit; The health status evaluation unit is used to collect the cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , calculate the health status coefficient H of the equipment state , get the current device running status; The health status coefficient H of the equipment state Calculated by the following formula: ; In the formula, E cool Indicates cooling efficiency, L net Represents the network delay response rate, V disk Indicates the hard disk read and write delay fluctuation, V max Indicates the maximum fluctuation of hard disk read and write delay. Respectively represent the cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk The proportionality factor.

[0010] Preferably, the historical data comparison module includes a baseline establishment unit, a real-time data comparison unit and a trend analysis unit; The baseline establishment unit is used to extract the cooling efficiency E from the historical data. cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , generate a historical benchmark curve; The real-time data comparison unit is used to compare the current operating status of the device with the historical baseline, and to compare the real-time health status coefficient H of the device with the historical baseline. state Data, difference analysis with historical baseline; The trend analysis unit is used to analyze the performance change trend of the equipment by comparing historical data, and to perform linear regression or other statistical analysis based on the long-term historical data of the equipment, to extract the trend change of the equipment performance, and to calculate the trend analysis coefficient T trend , predicting potential performance degradation or problems.

[0011] Preferably, the trend analysis coefficient T trend Calculated by the following formula: ; Where, T trend represents the trend analysis coefficient, X current,i Indicates the value of the i-th key parameter at the current time point, X history,i Indicates the i-th key parameter value of historical data at the same time point.

[0012] Preferably, the intelligent prediction module includes a fault prediction unit and a level prediction unit; The fault prediction unit is used to analyze the real-time collected equipment data based on the equipment status and historical data through training models, and apply machine learning algorithms to generate a fault prediction probability index P failure ; The failure prediction probability index P failure Calculated by the following formula: ; In the formula, Indicates the rate of change of the equipment health status over time, H state Represents the health status coefficient, T trend represents the trend analysis coefficient, Represents the health status coefficient H state , Trend analysis coefficient T trend and The proportionality factor.

[0013] Preferably, the level prediction unit is used to calculate the fault prediction probability index P failure Compare with the preset first fault threshold M and the preset second fault threshold N, classify the equipment faults according to the fault prediction probability and historical data, and put forward corresponding processing suggestions to obtain the grade evaluation plan: Failure prediction probability index P failure <The preset first fault threshold M indicates that the equipment is operating normally and there is no immediate risk of failure; Preset the first fault threshold M≤fault prediction probability index P failure <The second fault threshold N is preset, indicating that there is a potential problem with the equipment. Re-check the equipment, analyze the indicators with increased fault probability, and find out the root cause of the potential problem; Failure prediction probability index P failure ≥The preset second fault threshold N indicates that the equipment is faulty. It is recommended to shut down the equipment immediately for comprehensive inspection and maintenance to prevent accidents during operation.

[0014] Preferably, the result report generating module comprises a report content generating unit and a report output unit; The report content generation unit is responsible for summarizing and integrating information from various data sources, extracting current health status and performance indicators from the equipment status analysis module, summarizing historical maintenance records and task execution status, integrating fault prediction results and trend analysis information, and forming structured report content; The report output unit is used to format the generated report content, including charts and data visualization, and select the output method of the report according to user needs and permission settings, including email sending, system viewing or downloading.

[0015] An IT equipment asset maintenance intelligent management method comprises the following steps: Step 1: Real-time collection of multi-dimensional parameters of IT equipment, including cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , and transmit it to the data processing module; Step 2: Preprocess the collected data, including data cleaning, removing outliers, filling missing values, noise reduction, unit standardization and data filtering to ensure the accuracy and consistency of the data; Step 3: Based on the collected multi-source data, comprehensively analyze the current status of the equipment and calculate the health status coefficient H of the equipment state , get the current device running status; Step 4: Establish a baseline for the historical operation data of the equipment, compare the current status with the historical data, analyze the performance trend and changes of the equipment, and obtain the trend analysis coefficient T after calculation: trend , through the accumulation of long-term data, identify potential problems and performance degradation trends of equipment; Step 5: Based on the analysis of equipment status and historical data, use machine learning algorithms and historical data to calculate the final fault prediction probability index P failure , and compare it with the set threshold to obtain the level prediction plan, predict the failure time and type of the equipment in the future time period, and generate early warning information to prompt the system administrator to sort and allocate tasks according to the urgency and priority; Step 6: The system automatically generates a comprehensive report on equipment status, trend analysis, fault prediction and maintenance tasks, including the current health status of the equipment, maintenance history, fault prediction, trend analysis and maintenance task execution, to provide decision support for managers.

[0016] The present invention provides an IT equipment asset maintenance intelligent management method and system, which has the following beneficial effects: (1) When the system is running, the multi-dimensional parameters of IT equipment are collected in real time and transmitted to the data processing module, which pre-processes the collected data, comprehensively analyzes the current status of the equipment, and calculates the health status coefficient H of the equipment. state , obtain the current equipment operation status, establish a baseline for the equipment's historical operation data, compare the current status with historical data, analyze the equipment's performance trends and changes, and calculate and obtain: trend analysis coefficient T trend Through the accumulation of long-term data, potential problems and performance degradation trends of equipment are identified, and the final failure prediction probability index P is calculated. failure , and at the same time compare it with the set threshold, obtain the level prediction plan, and generate early warning information, prompting the system administrator to sort and allocate tasks according to the urgency and priority of the tasks. The system automatically generates a comprehensive report to provide decision support for managers.

[0017] (2) Through the construction of an intelligent management system for IT equipment asset maintenance, the system effectively integrates six modules: data collection, processing, status analysis, historical data comparison, intelligent prediction, and result report generation, enabling enterprises to achieve systematic and intelligent improvements in the management and maintenance of IT equipment. The various modules work together to ensure real-time collection and analysis of the multi-dimensional operating parameters of the equipment, thereby fully understanding the health status and performance indicators of the equipment. This comprehensive management model can not only identify potential faults in a timely manner, but also effectively improve the operating efficiency of the equipment, completing the full-cycle management task of equipment monitoring and maintenance.

[0018] (3) Compared with traditional equipment management methods, the introduction of intelligent management systems has brought significant technical improvements. Traditional methods often rely on manual monitoring, which is inefficient and prone to omissions. Through the preprocessing and standardization functions of the data processing module, the system can ensure the accuracy and consistency of the data. In addition, the intelligent prediction module combined with the machine learning algorithm can accurately calculate the fault prediction probability index and send early warning information to the administrator in a timely manner. Such improvements have significantly shortened the time for equipment fault identification and processing, thereby minimizing equipment downtime and maintenance costs.

[0019] (4) Through the implementation of this intelligent management system, the overall effect of the enterprise in equipment maintenance has been significantly improved. It not only realizes real-time monitoring and accurate evaluation of equipment status, but also provides data support and decision-making basis for management based on maintenance history records and trend analysis. This scientific and systematic management method not only improves the reliability and performance of equipment, but also enhances the enterprise's adaptability and response speed in market competition. Through continuous technical optimization and data accumulation, the enterprise can maintain continuous competitive advantages and achieve long-term sustainable development in the face of future challenges. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a block diagram of an IT equipment asset maintenance intelligent management system of the present invention; Figure 2 A schematic diagram of the steps of an IT equipment asset maintenance intelligent management method of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Example 1 The present invention provides an IT equipment asset maintenance intelligent management system, please refer to Figure 1 , including data acquisition module, data processing module, equipment status analysis module, historical data comparison module, intelligent prediction module and result report generation module; The data acquisition module is used to collect multi-dimensional parameters of IT equipment in real time, including cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , and transmit it to the data processing module; The data processing module is used to pre-process the collected data, including data cleaning, removal of outliers, filling of missing values, noise reduction, unit standardization and data filtering to ensure the accuracy and consistency of the data; The equipment status analysis module is used to comprehensively analyze the current status of the equipment based on the collected multi-source data and calculate the health status coefficient H of the equipment. state , get the current device running status; The historical data comparison module is used to establish a baseline for the historical operation data of the equipment, compare the current status with the historical data, analyze the performance trend and change of the equipment, and obtain the trend analysis coefficient T after calculation:trend , through the accumulation of long-term data, identify potential problems and performance degradation trends of equipment; The intelligent prediction module is used to calculate the final fault prediction probability index P based on the analysis of equipment status and historical data using machine learning algorithms and historical data. failure , and compare it with the set threshold to obtain the level prediction plan, predict the failure time and type of the equipment in the future time period, and generate early warning information to prompt the system administrator to sort and allocate tasks according to the urgency and priority; The result report generation module is used for the system to automatically generate a comprehensive report on equipment status, trend analysis, fault prediction and maintenance tasks, including the current health status of the equipment, maintenance history, fault prediction, trend analysis and maintenance task execution status, to provide decision support for managers.

[0023] In this embodiment, multi-dimensional parameters of IT equipment are collected in real time, including cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , and transmit it to the data processing module to pre-process the collected data, comprehensively analyze the current status of the equipment, and calculate the health status coefficient H of the equipment state , obtain the current equipment operation status, establish a baseline for the equipment's historical operation data, compare the current status with historical data, analyze the equipment's performance trends and changes, and calculate and obtain: trend analysis coefficient T trend Through the accumulation of long-term data, potential problems and performance degradation trends of equipment are identified, and the final failure prediction probability index P is calculated. failure , and compare it with the set threshold to obtain the grade prediction plan, predict the failure time and type of equipment in the future time period, and generate early warning information to prompt the system administrator to sort and allocate tasks according to the urgency and priority of the task. The system automatically generates a comprehensive report on equipment status, trend analysis, fault prediction and maintenance tasks to provide decision support for managers.

[0024] Example 2 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes a temperature sensor unit, a network monitoring unit and a storage read-write monitoring unit; The temperature sensor unit is used to collect the operating status data of the equipment cooling system, including the inlet and outlet temperature difference, fan speed, and obtain the cooling efficiency E of the equipment. cool , ensure that the equipment works at an appropriate temperature; The network monitoring unit is used to monitor the network connection status of the device, collect the communication delay and packet loss rate between the device and other nodes, and obtain the network delay response rate L net , helps evaluate the network performance and response speed of the device; The storage read / write monitoring unit is used to monitor the read / write speed fluctuation of the device hard disk or storage device, and obtain the hard disk read / write delay fluctuation V disk , reflects the IO performance of the storage device; The above collected parameters are transmitted to the data processing module for processing.

[0025] The data processing module includes a data cleaning unit and a data standardization unit; The data cleaning unit is used to clean the original data, remove abnormal values, fill missing values ​​and perform noise reduction processing, automatically identify and delete obviously abnormal device data by defining thresholds or using statistical methods, fill missing values ​​in the data by using interpolation or historical data averaging, and remove noise in the collection process by using filtering algorithms; The data standardization unit is used to perform unit standardization and data filtering to ensure that data from different sources and different magnitudes are uniformly processed and analyzed.

[0026] In this embodiment, the data acquisition module of the system comprehensively monitors the key parameters of the equipment operation through the organic combination of the temperature sensor unit, the network monitoring unit and the storage read-write monitoring unit. The temperature sensor unit obtains the equipment cooling efficiency E cool , ensuring that the equipment operates within an appropriate temperature range, effectively preventing performance degradation or damage caused by overheating; the network monitoring unit obtains the network delay response rate L by monitoring communication delay and packet loss rate net , helping to evaluate the network connection performance of the device in real time and ensure efficient and stable network communication; the storage read and write monitoring unit obtains the hard disk read and write delay fluctuation V by monitoring the IO performance of the storage device. disk , and can promptly detect storage system performance degradation or potential failures. These parameters provide comprehensive data support for device status evaluation and maintenance, ensuring that all aspects of device performance are maintained in optimal condition.

[0027] Example 3 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the equipment status analysis module includes a health status assessment unit; The health status evaluation unit is used to collect the cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , calculate the health status coefficient H of the equipment state, get the current device running status; The health status coefficient H of the equipment state Calculated by the following formula: ; In the formula, E cool Indicates cooling efficiency, L net Represents the network delay response rate, V disk Indicates the hard disk read and write delay fluctuation, V max Indicates the maximum fluctuation of hard disk read and write delay. Respectively represent the cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk The proportionality factor.

[0028] The historical data comparison module includes a baseline establishment unit, a real-time data comparison unit and a trend analysis unit; The baseline establishment unit is used to extract the cooling efficiency E from the historical data. cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , generate a historical benchmark curve; The real-time data comparison unit is used to compare the current operating status of the device with the historical baseline, and to compare the real-time health status coefficient H of the device with the historical baseline. state Data, difference analysis with historical baseline; The trend analysis unit is used to analyze the performance change trend of the equipment by comparing historical data, and to perform linear regression or other statistical analysis based on the long-term historical data of the equipment, to extract the trend change of the equipment performance, and to calculate the trend analysis coefficient T trend , predicting potential performance degradation or problems.

[0029] The trend analysis coefficient T trend Calculated by the following formula: ; Where, T trend represents the trend analysis coefficient, X current,i Indicates the value of the i-th key parameter at the current time point, X history,i Indicates the i-th key parameter value of historical data at the same time point.

[0030] The intelligent prediction module includes a fault prediction unit and a level prediction unit; The fault prediction unit is used to analyze the real-time collected equipment data based on the equipment status and historical data through training models, and apply machine learning algorithms to generate a fault prediction probability index P failure ; The failure prediction probability index P failure Calculated by the following formula: ; In the formula, Indicates the rate of change of the equipment health status over time, H state Represents the health status coefficient, T trend represents the trend analysis coefficient, Represents the health status coefficient H state , Trend analysis coefficient T trend and The proportionality factor.

[0031] In this embodiment, the equipment status analysis module of the system uses a health status evaluation unit to calculate the cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk The module not only quickly reflects the current health status of the equipment, but also ensures that key performance indicators are within the normal range through comprehensive analysis of cooling, network and storage performance, thereby helping to prevent equipment failure and performance degradation. In the historical data comparison module, through the baseline establishment unit and the real-time data comparison unit, the system can compare the current equipment operating status with the historical baseline to identify differences and changing trends in equipment performance. The trend analysis unit analyzes the long-term performance data of the equipment through statistical methods such as linear regression and calculates the trend analysis coefficient T. trend , thereby identifying potential performance degradation or problems of the equipment. This dual analysis method based on historical and real-time data significantly improves the accuracy and foresight of equipment status monitoring.

[0032] Example 4 This embodiment is explained in Example 1, please refer to Figure 1 Specifically: the level prediction unit is used to calculate the fault prediction probability index P failure Compare with the preset first fault threshold M and the preset second fault threshold N, classify the equipment faults according to the fault prediction probability and historical data, and put forward corresponding processing suggestions to obtain the grade evaluation plan: Failure prediction probability index P failure <The preset first fault threshold M indicates that the equipment is operating normally and there is no immediate risk of failure. The equipment should be regularly maintained and inspected to ensure that it operates in the best condition. Key performance indicators should be continuously monitored and daily operation data should be recorded so that the equipment performance can be evaluated at any time, the operation data can be analyzed, and the equipment configuration or parameters can be adjusted to ensure that it is always in an efficient operating state; Preset the first fault threshold M≤fault prediction probability index P failure <Preset the second fault threshold N, indicating that there is a potential problem with the device. Re-check the device, analyze the indicators with increased probability of failure, find out the root cause of the potential problem, increase the monitoring frequency of the device, especially the monitoring of cooling efficiency, network latency and hard disk performance, so as to detect abnormalities earlier, formulate a temporary maintenance plan for the device, and assign maintenance tasks to prioritize the parts that may fail; Failure prediction probability index P failure ≥The preset second fault threshold N indicates equipment failure. It is recommended to shut down the equipment immediately for comprehensive inspection and maintenance to prevent accidents during equipment operation. Emergency maintenance plans should be quickly formulated and implemented, with high-risk components shown in the prediction results given priority. Historical data should be deeply analyzed to identify the specific reasons for the increased probability of failure, so as to facilitate subsequent improvements and avoid the recurrence of similar problems.

[0033] The result report generation module includes a report content generation unit and a report output unit; The report content generation unit is responsible for summarizing and integrating information from various data sources, extracting current health status and performance indicators from the equipment status analysis module, summarizing historical maintenance records and task execution status, integrating fault prediction results and trend analysis information, and forming structured report content; The report output unit is used to format the generated report content, including charts and data visualization, and select the output method of the report according to user needs and permission settings, including email sending, system viewing or downloading.

[0034] In this embodiment, the level prediction unit of the system calculates the fault prediction probability index P failureBy comparing with the preset fault threshold, hierarchical management of equipment faults can be achieved. When the predicted fault probability is lower than the first threshold M, the equipment operates normally, avoiding unnecessary maintenance and downtime; when the fault probability is between M and N, the system will prompt potential problems and recommend detailed inspections to timely discover and solve hidden dangers; and when the fault probability exceeds the second threshold N, the system will recommend immediate shutdown for comprehensive maintenance to prevent equipment failure accidents. This fault level classification mechanism effectively optimizes the allocation of maintenance resources and improves the accuracy and efficiency of equipment maintenance. In the result report generation module, the system automatically summarizes the current health status, historical maintenance records and fault prediction results of the equipment, and displays the data in a visual way to help users fully understand the operating status and potential risks of the equipment. Through the report content generation unit, managers can quickly obtain detailed reports on the health status, trend analysis and fault prediction of the equipment, which facilitates more scientific decision-making. The report output unit supports multiple output methods to meet the needs of different scenarios, making the transmission and use of reports more convenient. Through this module, the system can not only provide real-time status feedback for equipment management, but also provide optimized maintenance suggestions based on fault prediction and historical data, thereby improving the reliability and safety of equipment operation and avoiding production interruptions and losses caused by equipment failures. This automated and intelligent report generation and output significantly improves the operability and management efficiency of the system.

[0035] Example 5 An intelligent management method for IT equipment asset maintenance, please refer to Figure 2 , specifically: including the following steps: Step 1: Real-time collection of multi-dimensional parameters of IT equipment, including cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , and transmit it to the data processing module; Step 2: Preprocess the collected data, including data cleaning, removing outliers, filling missing values, noise reduction, unit standardization and data filtering to ensure the accuracy and consistency of the data; Step 3: Based on the collected multi-source data, comprehensively analyze the current status of the equipment and calculate the health status coefficient H of the equipment state , get the current device running status; Step 4: Establish a baseline for the historical operation data of the equipment, compare the current status with the historical data, analyze the performance trend and changes of the equipment, and obtain the trend analysis coefficient T after calculation: trend , through the accumulation of long-term data, identify potential problems and performance degradation trends of equipment; Step 5: Based on the analysis of equipment status and historical data, use machine learning algorithms and historical data to calculate the final fault prediction probability index P failure , and compare it with the set threshold to obtain the level prediction plan, predict the failure time and type of the equipment in the future time period, and generate early warning information to prompt the system administrator to sort and allocate tasks according to the urgency and priority; Step 6: The system automatically generates a comprehensive report on equipment status, trend analysis, fault prediction and maintenance tasks, including the current health status of the equipment, maintenance history, fault prediction, trend analysis and maintenance task execution, to provide decision support for managers.

[0036] In this embodiment, through the above six steps, the system can achieve comprehensive monitoring and intelligent maintenance of IT equipment. First, real-time collection of multi-dimensional parameters (such as cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk ), ensuring the accurate reflection of the equipment status, and then cleaning and standardizing the data through the data processing module to ensure the accuracy and consistency of the basic data for analysis. state The system can instantly reflect the current operating status of the equipment and promptly identify potential problems, which helps improve the operating reliability of the equipment. Secondly, the historical data comparison and trend analysis function can identify the performance change trend of the equipment through baseline establishment and data comparison, and calculate the trend analysis coefficient T trend , and then predict the potential performance degradation trend. This trend analysis based on historical data helps to discover equipment hidden dangers in advance and prevent the equipment from gradually deteriorating. In addition, the intelligent prediction module uses machine learning algorithms and combines the historical data of the equipment to predict the probability of failure and generate a fault level assessment plan, making equipment maintenance more scientific and accurate. Through this prediction mechanism, the system can significantly reduce the risk of sudden equipment failure. Finally, the system's automatic report generation function provides managers with visual reports by integrating equipment health status, trend analysis and fault prediction results. The report not only includes the current status and historical data, but also provides suggestions for maintenance tasks to help managers efficiently allocate maintenance resources. Overall, the system has shown significant improvements in improving equipment stability, extending equipment life, and optimizing resource management. Compared with the traditional manual maintenance mode, the system has significantly improved the operating efficiency and safety of IT equipment through intelligent and automated means.

[0037] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An IT equipment asset maintenance intelligent management system, characterized by: It includes data acquisition module, data processing module, equipment status analysis module, historical data comparison module, intelligent prediction module and result report generation module; The data acquisition module is used to collect multi-dimensional parameters of IT equipment in real time, including cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , and transmit it to the data processing module; The data processing module is used to pre-process the collected data, including data cleaning, removal of outliers, filling of missing values, noise reduction, unit standardization and data filtering to ensure the accuracy and consistency of the data; The equipment status analysis module is used to comprehensively analyze the current status of the equipment based on the collected multi-source data and calculate the health status coefficient H of the equipment. state , get the current device running status; The historical data comparison module is used to establish a baseline for the historical operation data of the equipment, compare the current status with the historical data, analyze the performance trend and change of the equipment, and obtain the trend analysis coefficient T after calculation: trend , through the accumulation of long-term data, identify potential problems and performance degradation trends of equipment; The intelligent prediction module is used to calculate the final fault prediction probability index P based on the analysis of equipment status and historical data using machine learning algorithms and historical data. failure , and compare it with the set threshold to obtain the level prediction plan, predict the failure time and type of the equipment in the future time period, and generate early warning information to prompt the system administrator to sort and allocate tasks according to the urgency and priority; The result report generation module is used for the system to automatically generate a comprehensive report on equipment status, trend analysis, fault prediction and maintenance tasks, including the current health status of the equipment, maintenance history, fault prediction, trend analysis and maintenance task execution status, to provide decision support for managers.

2. The IT equipment asset maintenance intelligent management system according to claim 1, characterized in that: The data acquisition module includes a temperature sensor unit, a network monitoring unit and a storage read-write monitoring unit; The temperature sensor unit is used to collect the operating status data of the equipment cooling system, including the inlet and outlet temperature difference, fan speed, and obtain the cooling efficiency E of the equipment. cool , ensure that the equipment works at an appropriate temperature; The network monitoring unit is used to monitor the network connection status of the device, collect the communication delay and packet loss rate between the device and other nodes, and obtain the network delay response rate L net , helps evaluate the network performance and response speed of the device; The storage read / write monitoring unit is used to monitor the read / write speed fluctuation of the device hard disk or storage device, and obtain the hard disk read / write delay fluctuation V disk , reflects the IO performance of the storage device; The above collected parameters are transmitted to the data processing module for processing.

3. The IT equipment asset maintenance intelligent management system according to claim 1, characterized in that: The data processing module includes a data cleaning unit and a data standardization unit; The data cleaning unit is used to clean the original data, remove abnormal values, fill missing values ​​and perform noise reduction processing, automatically identify and delete obviously abnormal device data by defining thresholds or using statistical methods, fill missing values ​​in the data by using interpolation or historical data averaging, and remove noise in the collection process by using filtering algorithms; The data standardization unit is used to perform unit standardization and data filtering to ensure that data from different sources and different magnitudes are uniformly processed and analyzed.

4. The IT equipment asset maintenance intelligent management system according to claim 2, characterized in that: The equipment status analysis module includes a health status assessment unit; The health status evaluation unit is used to collect the cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , calculate the health status coefficient H of the equipment state , get the current device running status; The health status coefficient H of the equipment state Calculated by the following formula: ； In the formula, E cool Indicates cooling efficiency, L net Represents the network delay response rate, V disk Indicates the hard disk read and write delay fluctuation, V max Indicates the maximum fluctuation of hard disk read and write delay. Respectively represent the cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk The proportionality factor.

5. The IT equipment asset maintenance intelligent management system according to claim 2, characterized in that: The historical data comparison module includes a baseline establishment unit, a real-time data comparison unit and a trend analysis unit; The baseline establishment unit is used to extract the cooling efficiency E from the historical data. cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , generate a historical benchmark curve; The real-time data comparison unit is used to compare the current operating status of the device with the historical baseline, and to compare the real-time health status coefficient H of the device with the historical baseline. state Data, difference analysis with historical baseline; The trend analysis unit is used to analyze the performance change trend of the equipment by comparing historical data, and to perform linear regression or other statistical analysis based on the long-term historical data of the equipment, to extract the trend change of the equipment performance, and to calculate the trend analysis coefficient T trend , predicting potential performance degradation or problems.

6. The IT equipment asset maintenance intelligent management system according to claim 5, characterized in that: The trend analysis coefficient T trend Calculated by the following formula: ； Where, T trend represents the trend analysis coefficient, X current,i Indicates the value of the i-th key parameter at the current time point, X history,i Indicates the i-th key parameter value of historical data at the same time point.

7. The IT equipment asset maintenance intelligent management system according to claim 5, characterized in that: The intelligent prediction module includes a fault prediction unit and a level prediction unit; The fault prediction unit is used to analyze the real-time collected equipment data based on the equipment status and historical data through training models, and apply machine learning algorithms to generate a fault prediction probability index P failure ; The failure prediction probability index P failure Calculated by the following formula: ； In the formula, Indicates the rate of change of the equipment health status over time, H state Represents the health status coefficient, T trend represents the trend analysis coefficient, Represents the health status coefficient H state , Trend analysis coefficient T trend and The proportionality factor.

8. The IT equipment asset maintenance intelligent management system according to claim 7, characterized in that: The level prediction unit is used to calculate the fault prediction probability index P failure Compare with the preset first fault threshold M and the preset second fault threshold N, classify the equipment faults according to the fault prediction probability and historical data, and put forward corresponding processing suggestions to obtain the grade evaluation plan: Failure prediction probability index P failure <The preset first fault threshold M indicates that the equipment is operating normally and there is no immediate risk of failure; Preset the first fault threshold M≤fault prediction probability index P failure <The second fault threshold N is preset, indicating that there is a potential problem with the equipment. Re-check the equipment, analyze the indicators with increased fault probability, and find out the root cause of the potential problem; Failure prediction probability index P failure ≥The preset second fault threshold N indicates that the equipment is faulty. It is recommended to shut down the equipment immediately for comprehensive inspection and maintenance to prevent accidents during operation.

9. The IT equipment asset maintenance intelligent management system according to claim 1, characterized in that: The result report generation module includes a report content generation unit and a report output unit; The report content generation unit is responsible for summarizing and integrating information from various data sources, extracting current health status and performance indicators from the equipment status analysis module, summarizing historical maintenance records and task execution status, integrating fault prediction results and trend analysis information, and forming structured report content; The report output unit is used to format the generated report content, including charts and data visualization, and select the output method of the report according to user needs and permission settings, including email sending, system viewing or downloading.

10. An IT equipment asset maintenance intelligent management method, applied to an IT equipment asset maintenance intelligent management system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Real-time collection of multi-dimensional parameters of IT equipment, including cooling efficiency E cool , network delay response rate L net And hard disk read and write delay fluctuation V disk , and transmit it to the data processing module; Step 2: Preprocess the collected data, including data cleaning, removing outliers, filling missing values, noise reduction, unit standardization and data filtering to ensure the accuracy and consistency of the data; Step 3: Based on the collected multi-source data, comprehensively analyze the current status of the equipment and calculate the health status coefficient H of the equipment state , get the current device running status; Step 4: Establish a baseline for the historical operation data of the equipment, compare the current status with the historical data, analyze the performance trend and changes of the equipment, and obtain the trend analysis coefficient T after calculation: trend , through the accumulation of long-term data, identify potential problems and performance degradation trends of equipment; Step 5: Based on the analysis of equipment status and historical data, use machine learning algorithms and historical data to calculate the final fault prediction probability index P failure , and compare it with the set threshold to obtain the level prediction plan, predict the failure time and type of the equipment in the future time period, and generate early warning information to prompt the system administrator to sort and allocate tasks according to the urgency and priority; Step 6: The system automatically generates a comprehensive report on equipment status, trend analysis, fault prediction and maintenance tasks, including the current health status of the equipment, maintenance history, fault prediction, trend analysis and maintenance task execution, to provide decision support for managers.

Images