Network server cabinet fault processing system and method

Abstract

The invention discloses a network server cabinet fault processing system and method, relates to the technical field of fault processing, and solves the technical problem that the analysis result of the cabinet fault is inaccurate because the influence of weather on the operation of a server cabinet is not considered in the prior art. The method comprises the following steps: collecting fault data of a server, collecting environment data of a server cabinet through a sensor, collecting weather data, and extracting historical server data of the server and historical environment data of the server cabinet from a database; a server operation range is set based on historical server data, when an external fault occurs, statistical analysis is performed on historical environment data to obtain an environment threshold range, and the environment data is compared with the set environment threshold range to obtain a fault state. Combining the environment data corresponding to the fault state with the environment threshold range to obtain specific fault data; and optimizing the specific fault data based on the weather data to obtain optimized fault data, and checking an optimization effect.

Description

Technical Field

[0001] The invention belongs to the field of fault processing, relates to Internet of Things technology, and specifically provides a network server cabinet fault processing system and method. Background Art

[0002] Data centers are one of the core infrastructures of modern enterprises, supporting critical business applications and data processing. Server cabinets provide physical protection for servers and network equipment to prevent physical damage such as dust and collisions, and manage the temperature inside the cabinets through built-in fans or cooling systems. As the number of servers increases, fault handling becomes more complicated, and enterprises need to respond to faults quickly to minimize downtime and economic losses.

[0003] The invention patent with application number CN2023115821857 discloses a method, device, terminal and medium for monitoring and processing faults of a rod control and rod position system. The invention obtains the operating status of the cabinet by analyzing the operating information of the cabinet in the system. When the operating status is a fault state, the fault information is extracted and a fault solution is configured according to the fault information. After executing the fault solution, the operating information of the cabinet is obtained again and the operating status of the cabinet is analyzed to ensure that the operating status of the cabinet is not a fault state. When processing the fault status of the cabinet, the invention only processes it according to the operating fault information of the cabinet. Different weather will also affect the operation of the cabinet. If the ventilation or cooling system of the cabinet fails, the weather will have a greater impact on the cabinet and may endanger the server.

[0004] The present invention provides a network server cabinet fault processing system and method to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a network server cabinet fault processing system and method, which are used to solve the technical problem in the prior art that the analysis results of cabinet faults are inaccurate due to not taking into account the impact of weather on the operation of the server cabinet.

[0006] To achieve the above-mentioned object, a first aspect of the present invention provides a network server cabinet fault processing system, comprising: a database, a data collection module, a fault diagnosis module and a fault optimization module;

[0007] Data collection module: used to collect environmental data of storage server cabinets and cabinet fault data, collect current weather data, and extract historical server data and cabinet historical environmental data from the database;

[0008] Fault diagnosis module: used to set the server operation range based on historical server data; obtain specific fault types based on fault data and server operation range analysis; obtain specific fault data by analyzing specific fault types based on environmental data and historical environmental data; wherein specific fault types include external faults and internal faults;

[0009] Fault optimization module: used to optimize specific fault data based on weather data to obtain optimized fault data and to verify the optimization effect of the optimized fault data.

[0010] Preferably, setting the server operation range based on historical server data includes:

[0011] Extracting historical server data; the historical server data includes historical operation data and operation type of the server;

[0012] The historical server data is preprocessed to obtain standard historical server data; the standard historical server data is statistically analyzed, and the server operation range is obtained according to the standard value of the standard historical server data without abnormalities.

[0013] Preferably, the specific fault type is obtained by analyzing the fault data and the server operation range, including:

[0014] Extracting fault data and server operating range; the fault data includes health monitoring records and event logs of the server;

[0015] Determine whether the health monitoring record contains abnormal records; if yes, mark the log record in the event log corresponding to the abnormal record as an abnormal log, and combine the abnormal record with the abnormal log to obtain abnormal data; if no, continue to monitor the server;

[0016] Compare the abnormal data with the corresponding normal operating range to obtain the specific fault type.

[0017] Preferably, the step of comparing the abnormal data with the corresponding normal operating range to obtain the specific fault type includes:

[0018] Extract abnormal data and normal operating range;

[0019] Determine whether the sub-data in the abnormal data conforms to the corresponding sub-data operating range in the normal operating range; if so, mark the corresponding sub-data as external fault data, and mark the fault corresponding to the external fault data as an external fault; if not, mark the corresponding sub-data as internal fault data, and mark the fault corresponding to the internal fault data as an internal fault.

[0020] Preferably, the analyzing of the specific fault type based on the environmental data and the historical environmental data to obtain the specific fault data includes:

[0021] Extracting environmental data and historical environmental data; the environmental data includes temperature, humidity and airflow of the cabinet;

[0022] Performing statistical analysis on historical environmental data to obtain environmental threshold ranges; the environmental threshold ranges include temperature threshold ranges, humidity threshold ranges, and airflow threshold ranges;

[0023] Determine whether the temperature meets the temperature threshold range; if yes, mark the temperature state as normal; if no, mark the temperature state as abnormal;

[0024] Determine whether the humidity meets the humidity threshold range; if yes, mark the humidity state as normal humidity state; if no, mark the humidity state as abnormal humidity state;

[0025] Determine whether the airflow meets the airflow threshold range; if yes, mark the airflow state as a normal airflow state; if no, mark the airflow state as an abnormal airflow state;

[0026] The temperature abnormal state, humidity abnormal state and airflow abnormal state are marked as fault states, and the environmental data corresponding to the fault state is combined with the environmental threshold range to obtain specific fault data.

[0027] Preferably, the step of optimizing the specific fault data based on the weather data to obtain optimized fault data and verifying the optimization effect of the optimized fault data includes:

[0028] Extract weather data and specific fault data; obtain seasonal environmental data based on weather data analysis, obtain phase difference environmental data based on seasonal environmental data and specific fault data, adjust the indoor environment of the server according to the phase difference environmental data, obtain optimized fault data through sensor measurement after the adjustment is completed, and obtain optimization effect based on the optimized fault data and the phase difference environmental data inspection; the optimization effect includes normal effect and abnormal effect.

[0029] Preferably, the seasonal environmental data is obtained according to the weather data analysis, including:

[0030] A1: extract weather data; the weather data includes the current season and season time; the season time includes the first half of the month, the middle half of the month and the last half of the month;

[0031] A2: Determine whether the current time is the early part of the current season; if yes, mark the current environment time as the early part of the season; if no, jump to A3;

[0032] A3: Determine whether the current time is the middle of the current season. If yes, mark the current environment time as the middle of the season; if no, mark the current environment time as the end of the season.

[0033] Obtain the environmental data of the current environmental time for nearly n days, take the sub-environmental data corresponding to the specific fault data, and take the average value of the sub-environmental data to obtain the seasonal environmental data.

[0034] Preferably, obtaining the difference environment data based on the seasonal environment data and the specific fault data includes:

[0035] B1: Extract seasonal environmental data and specific fault data;

[0036] B2: marking the absolute value of the difference between the seasonal environmental data and the specific fault data as an environmental difference value; setting an environmental difference threshold; the environmental difference threshold is set based on the environmental data of the current season; the environmental difference threshold includes an environmental first threshold and an environmental second threshold;

[0037] B3: Determine whether the environmental difference value is greater than the first environmental threshold; if yes, mark the phase difference state as a high difference state; if no, jump to B4;

[0038] B4: Determine whether the environmental difference value is greater than the second environmental threshold; if yes, mark the phase difference state as a medium difference state; if no, mark the phase difference state as a small difference state;

[0039] The corresponding phase difference coefficient is set according to the phase difference state, and the phase difference coefficient is combined with the environmental difference value to obtain the phase difference environmental data.

[0040] Preferably, the optimization effect is obtained by checking the optimized fault data and the phase difference environment data, including:

[0041] S1: Extract optimized fault data and phase difference environment data;

[0042] S2: Determine whether the difference between the optimized fault data and the specific fault data is greater than the difference in environmental data; if yes, mark the optimization effect as an abnormal effect; if no, jump to S3;

[0043] S3: Compare the difference between the optimized fault data and the specific fault data with the environmental threshold to determine whether the phase difference state is a small gap state; if yes, mark the optimization effect as a normal effect; if no, mark the optimization effect as an abnormal effect.

[0044] A network server cabinet fault processing method is applied to the network server cabinet fault processing system, and is characterized by comprising:

[0045] Step 1: Collect environmental data of the storage server cabinet, cabinet fault data and weather data; extract historical server data and cabinet historical environmental data from the database;

[0046] Step 2: Set the server operation range based on historical server data; obtain the specific fault type based on the fault data and the server operation range analysis; and obtain the specific fault data by analyzing the specific fault type based on the environmental data and historical environmental data;

[0047] Step 3: Optimize the specific fault data based on weather data to obtain optimized fault data and verify the optimization effect of the optimized fault data.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. The present invention collects server fault data, collects server cabinet environmental data through sensors, collects weather data, and extracts server historical data and server cabinet historical environmental data from a database, which can reveal the impact of the external environment on the internal environment of the server cabinet, and performs corresponding optimization by analyzing the historical data of performance indicators; setting the server operation range based on historical server data can improve data quality, and using historical data as a reference can better match the status of the corresponding server, making the result more accurate; judging whether the fault data contains abnormal records, if it contains abnormal records, then the fault and fault type can be quickly located, and the problem can be solved more quickly and specifically to prevent the fault from affecting the server, and Eliminate internal faults that are caused by the server's own faults rather than the cabinet. When an external fault occurs, statistical analysis of historical environmental data is performed to obtain the environmental threshold range, which can better standardize and discover the fault. The environmental data is compared with the set environmental threshold range to obtain the fault status. The environmental data corresponding to the fault status is combined with the environmental threshold range to obtain specific fault data, which can quickly determine the specific abnormal data in the cabinet. Based on weather data, the specific fault data is optimized to obtain optimized fault data and verify the optimization effect. By optimizing the specific fault data based on the impact of weather data on the environmental data of the server cabinet, the impact of weather data on the cabinet environment can be further eliminated, making the results more accurate.

[0050] 2. When optimizing specific fault data based on weather data, the present invention takes the data of adjacent weather as seasonal environmental data, and calculates the absolute value of the difference between the seasonal environmental data and the specific fault data, so as to preliminarily obtain the difference between the environmental data of the cabinet and the external environmental data, wherein the difference is caused by the fault in the cabinet; a phase difference coefficient is set according to the comparison result of the environmental difference value and the environmental threshold, and the phase difference coefficient is used to optimize the environmental data in the cabinet, and the greater the temperature difference, the greater the effect of the fault impact; the phase difference environmental data is obtained according to the environmental difference value and the phase difference coefficient, and the optimization effect is verified based on the phase difference environmental data. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 The following is a flowchart of an embodiment of the present invention.

[0053] Figure 2 It is a system composition diagram of the present invention.

[0054] Figure 3 The figure is a complete flow chart of obtaining the fault status in one embodiment of the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0056] See also Figure 1-Figure 3 , the first aspect of the present invention provides a network server cabinet fault processing system, including: a database, a data collection module, a fault diagnosis module and a fault optimization module;

[0057] Data collection module: used to collect environmental data of storage server cabinets and cabinet fault data, collect current weather data, and extract historical server data and cabinet historical environmental data from the database.

[0058] Exemplarily, environmental data of the server cabinet is collected by installing temperature sensors, humidity sensors and airflow sensors in the server cabinet, and fault data of the cabinet is collected through the server operation log. It is collected that the current season is summer, and historical server data and historical environmental data of the server are extracted from the server operation database.

[0059] Fault diagnosis module: used to set the server operating range based on historical server data; obtain specific fault types based on fault data and server operating range analysis; obtain specific fault data by analyzing specific fault types based on environmental data and historical environmental data; wherein specific fault types include external faults and internal faults.

[0060] Exemplarily, abnormal values ​​are detected and cleared from historical server data in sequence, and the historical server data is standardized to convert the data into a unified format; the historical server data includes the input and output voltage of the power supply, the hard disk read and write rate, and the amount of data entering and leaving the server at historical moments; the historical server data at moments without abnormalities are selected and counted, and the average input voltage range, average output voltage range, average hard disk read and write rate range, and average range of the amount of data entering and leaving the power supply at historical moments are counted, and the average input voltage range, average output voltage range, average hard disk read and write rate range, and average range of the amount of data entering and leaving the server are combined to obtain the server operation range.

[0061] Determine whether the health monitoring record in the server fault data contains abnormal records, where the abnormal records may be error logs, abnormal data, etc. It is determined that abnormal data has appeared in the current server and the read and write rate of the hard disk is low, then the low read and write rate of the hard disk and the corresponding time log are marked as abnormal logs, and the abnormal record is combined with the abnormal log to obtain the abnormal data; determine whether the sub-data in the abnormal data conforms to the corresponding sub-data operating range in the normal operating range. In this embodiment, the abnormal data is the low hard disk read and write rate, then the sub-data extracted from the abnormal data is the hard disk read and write rate = 100MB / S, and the corresponding average hard disk read and write rate range in the normal operating range is 90-190MB / S, then it is determined that the hard disk read and write rate is external fault data, and the low hard disk read and write rate is an external fault.

[0062] In this embodiment, the environmental data of the server cabinet includes a temperature of 25 degrees, a humidity of 60%, and an airflow of 1 meter per second; the historical environmental data is counted, and the temperature threshold range of the temperature in the historical environmental data is 20 degrees to 40 degrees, the humidity threshold range of the humidity is 50% to 70%, and the airflow threshold range of the airflow is 3 meters per second to 5 meters per second; it is determined whether the temperature meets the temperature threshold range, and if it is determined that the temperature meets the temperature threshold range, the temperature state is marked as a normal temperature state; it is determined whether the humidity meets the humidity threshold range, and if it is determined that the humidity meets the humidity threshold range, the humidity state is marked as a normal humidity state; it is determined whether the airflow meets the airflow threshold range, and if it is determined that the airflow does not meet the airflow threshold range, the airflow state is marked as an abnormal airflow state, and the fault state is an abnormal airflow state. The specific fault data is that the airflow is low, which is 1 meter per second, and the airflow threshold range is 3 meters per second to 5 meters per second.

[0063] Fault optimization module: used to optimize specific fault data based on weather data to obtain optimized fault data and to verify the optimization effect of the optimized fault data.

[0064] Exemplarily, the current time is June, which belongs to summer; determine whether the current time is the early morning of the current season. If it is not the early morning of summer, then continue to determine whether the current time is the middle of the current season. If it is the middle of summer, then mark the current environmental time as the middle of the season; collect environmental data for the current environmental time for nearly 5 days. In this embodiment, the specific fault data is airflow, and the average value of the airflow in the past 5 days is extracted to be 3 meters per second.

[0065] The absolute value of the difference between the seasonal environmental data and the specific fault data is marked as the environmental difference value, and the environmental difference value is obtained as 2; in this embodiment, the first environmental threshold is set to 1, and the second environmental threshold is set to 0.5, and it is judged whether the environmental difference value is greater than the first environmental threshold. If the environmental difference value is greater than the first environmental threshold, the phase difference state is a high gap state; the phase difference coefficient corresponding to the high gap state is set to 0.8 to obtain the phase difference environmental data.

[0066] It should be noted that for different specific fault data, the set environmental thresholds are different, and the set phase difference coefficients are also different. For example, when the specific fault data is temperature, the first environmental threshold can be set to 5 degrees, and the second environmental threshold can be set to 3 degrees; if the number of specific fault data sub-data is more than one item, the corresponding environmental thresholds are set for comparison to obtain the corresponding phase difference state.

[0067] Adjust the wind speed in the bellows cabinet in the server cabinet. In this embodiment, the difference environmental data is that the airflow is smaller than the airflow in the environmental data. Multiply the difference coefficient and the difference value to obtain the optimized data to be optimized as 1.6, then increase the airflow speed by 1.6 meters per second. Remeasure the airflow in the cabinet with the airflow sensor to be 2 meters per second. Determine whether the difference between the optimized fault data and the specific fault data is greater than the difference environmental data. If the difference between the optimized fault data and the specific fault data is smaller than the difference environmental data, continue to determine whether the difference state is a small gap state. If the optimized difference state is determined to be a medium gap state, the optimization effect is an abnormal effect, and the optimization effect does not achieve the expected effect.

[0068] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0069] Working principle of the present invention:

[0070] The present invention collects the fault data of the server, collects the environmental data of the server cabinet through sensors, collects weather data, extracts the historical server data of the server and the historical environmental data of the server cabinet from a database; judges whether the fault data contains abnormal records, if it contains abnormal records, a fault occurs in the server, compares the abnormal data with the corresponding server operation range, and obtains a specific fault type, an internal fault is a fault caused by a problem in the server program itself, and an external fault is a fault caused by a problem in the cabinet; when an external fault occurs, statistical analysis is performed on the historical environmental data to obtain an environmental threshold range, the environmental data is compared with the set environmental threshold range to obtain a fault state, and the environmental data corresponding to the fault state is combined with the environmental threshold range to obtain specific fault data; the data of adjacent weather is taken as seasonal environmental data, and the absolute value of the difference between the seasonal environmental data and the specific fault data is calculated as an environmental difference value, and a phase difference coefficient is set according to the comparison result of the environmental difference value and the environmental threshold value, and the phase difference coefficient is used to optimize the environmental data in the cabinet and verify the optimization effect.

[0071] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A network server cabinet fault handling system, characterized in that: include: Database, data collection module, fault diagnosis module and fault optimization module; Data collection module: used to collect environmental data of storage server cabinets and cabinet fault data, collect current weather data, and extract historical server data and cabinet historical environmental data from the database; Fault diagnosis module: used to set the server operation range based on historical server data; obtain specific fault types based on fault data and server operation range analysis; obtain specific fault data by analyzing specific fault types based on environmental data and historical environmental data; wherein specific fault types include external faults and internal faults; Fault optimization module: used to optimize specific fault data based on weather data to obtain optimized fault data and to verify the optimization effect of the optimized fault data.

2. A network server cabinet fault handling system according to claim 1, characterized in that: The step of setting the server operation range based on historical server data includes: Extracting historical server data; the historical server data includes historical operation data and operation type of the server; The historical server data is preprocessed to obtain standard historical server data; the standard historical server data is statistically analyzed, and the server operation range is obtained according to the standard value of the standard historical server data without abnormalities.

3. A network server cabinet fault handling system according to claim 1, characterized in that: The specific fault type obtained by analyzing the fault data and the server operation range includes: Extracting fault data and server operating range; the fault data includes health monitoring records and event logs of the server; Determine whether the health monitoring record contains abnormal records; if yes, mark the log record in the event log corresponding to the abnormal record as an abnormal log, and combine the abnormal record with the abnormal log to obtain abnormal data; if no, continue to monitor the server; Compare the abnormal data with the corresponding normal operating range to obtain the specific fault type.

4. A network server cabinet fault handling system according to claim 3, characterized in that: The specific fault type is obtained by comparing the abnormal data with the corresponding normal operating range, including: Extract abnormal data and normal operating range; Determine whether the sub-data in the abnormal data conforms to the corresponding sub-data operating range in the normal operating range; if so, mark the corresponding sub-data as external fault data, and mark the fault corresponding to the external fault data as an external fault; if not, mark the corresponding sub-data as internal fault data, and mark the fault corresponding to the internal fault data as an internal fault.

5. A network server cabinet fault handling system according to claim 1, characterized in that: The specific fault data is obtained by analyzing the specific fault type based on the environmental data and the historical environmental data, including: Extracting environmental data and historical environmental data; the environmental data includes temperature, humidity and airflow of the cabinet; Performing statistical analysis on historical environmental data to obtain an environmental threshold range; the environmental threshold range includes a temperature threshold range, a humidity threshold range, and an airflow threshold range; Determine whether the temperature meets the temperature threshold range; if yes, mark the temperature state as normal; if no, mark the temperature state as abnormal; Determine whether the humidity meets the humidity threshold range; if yes, mark the humidity state as normal humidity state; if no, mark the humidity state as abnormal humidity state; Determine whether the airflow meets the airflow threshold range; if yes, mark the airflow state as a normal airflow state; if no, mark the airflow state as an abnormal airflow state; The temperature abnormal state, humidity abnormal state and airflow abnormal state are marked as fault states, and the environmental data corresponding to the fault state is combined with the environmental threshold range to obtain specific fault data.

6. A network server cabinet fault handling system according to claim 1, characterized in that: The step of optimizing the specific fault data based on the weather data to obtain optimized fault data and verifying the optimization effect of the optimized fault data includes: Extract weather data and specific fault data; obtain seasonal environmental data based on weather data analysis, obtain phase difference environmental data based on seasonal environmental data and specific fault data, adjust the indoor environment of the server according to the phase difference environmental data, obtain optimized fault data through sensor measurement after the adjustment is completed, and obtain optimization effect based on the optimized fault data and the phase difference environmental data inspection; the optimization effect includes normal effect and abnormal effect.

7. A network server cabinet fault handling system according to claim 6, characterized in that: The seasonal environmental data obtained by analyzing the weather data includes: A1: extract weather data; the weather data includes the current season and season time; the season time includes the first half of the month, the middle half of the month and the last half of the month; A2: Determine whether the current time is the early part of the current season; if yes, mark the current environment time as the early part of the season; if no, jump to A3; A3: Determine whether the current time is the middle of the current season. If yes, mark the current environment time as the middle of the season; if no, mark the current environment time as the end of the season. Obtain the environmental data of the current environmental time for nearly n days, take the sub-environmental data corresponding to the specific fault data, and take the average value of the sub-environmental data to obtain the seasonal environmental data.

8. A network server cabinet fault handling system according to claim 6, characterized in that: The step of obtaining the difference environment data based on the seasonal environment data and the specific fault data includes: B1: Extract seasonal environmental data and specific fault data; B2: marking the absolute value of the difference between the seasonal environmental data and the specific fault data as an environmental difference value; setting an environmental difference threshold; the environmental difference threshold is set based on the environmental data of the current season; the environmental difference threshold includes an environmental first threshold and an environmental second threshold; B3: Determine whether the environmental difference value is greater than the first environmental threshold; if yes, mark the phase difference state as a high difference state; if no, jump to B4; B4: Determine whether the environmental difference value is greater than the second environmental threshold; if yes, mark the phase difference state as a medium difference state; if no, mark the phase difference state as a small difference state; The corresponding phase difference coefficient is set according to the phase difference state, and the phase difference coefficient is combined with the environmental difference value to obtain the phase difference environmental data.

9. A network server cabinet fault handling system according to claim 6, characterized in that: The optimization effect is obtained by checking the optimized fault data and the phase difference environment data, including: S1: Extract optimized fault data and phase difference environment data; S2: Determine whether the difference between the optimized fault data and the specific fault data is greater than the difference in environmental data; if yes, mark the optimization effect as an abnormal effect; if no, jump to S3; S3: Compare the difference between the optimized fault data and the specific fault data with the environmental threshold to determine whether the phase difference state is a small gap state; if yes, mark the optimization effect as a normal effect; if no, mark the optimization effect as an abnormal effect.

10. A network server cabinet fault processing method, applied to a network server cabinet fault processing system according to any one of claims 1 to 9, characterized in that: include: Step 1: Collect environmental data of the storage server cabinet, cabinet fault data and weather data; Extract historical server data of the server and historical environment data of the cabinet from the database; Step 2: Set the server operation range based on historical server data; obtain the specific fault type based on the fault data and the server operation range analysis; and obtain the specific fault data by analyzing the specific fault type based on the environmental data and historical environmental data; Step 3: Optimize the specific fault data based on weather data to obtain optimized fault data and verify the optimization effect of the optimized fault data.

Images