Machine room operation and maintenance inspection method and system based on machine learning

Abstract

The invention relates to the technical field of machine room operation and maintenance inspection, and particularly discloses a machine room operation and maintenance inspection method and system based on machine learning. The system comprises a temperature abnormity equipment judgment module, a cooling fan rotating speed adjustment module, a temperature continuous abnormity equipment judgment module, a cooling abnormity operation and maintenance scheme providing module, a database, a fault equipment judgment module and a routing inspection route optimization module. According to the method, secondary inspection is performed on each abnormal inspection point in the target machine room, whether the temperature continuously abnormal equipment exists or not is judged, if yes, the heat dissipation abnormity reason is confirmed, an operation and maintenance scheme is provided for the heat dissipation abnormity, and meanwhile, the preset inspection route of the target machine room is optimized by combining the actual state of the equipment of the target machine room in the current period; the timeliness of finding and processing the temperature abnormity of the equipment is improved, the risk of equipment damage is reduced, meanwhile, the situation that the inspection robot neglects a key area and repeatedly inspects a normal area is avoided, and precious inspection time is saved.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer room operation and maintenance inspection, and relates to a computer room operation and maintenance inspection method and system based on machine learning. Background Art

[0002] With the deepening of digital transformation, the operation and maintenance inspection of computer rooms, as key facilities for enterprise IT services, has become increasingly important. However, the traditional manual inspection method has problems such as low inspection efficiency, easy missed inspections, and false inspections, which not only increases labor costs, but also may bring safety and economic risks. Therefore, it is particularly important to develop an efficient, accurate, and automated computer room inspection method and system.

[0003] The existing operation and maintenance inspection methods for computer rooms still have the following problems: 1. The temperature abnormalities that still exist in the computer room during the first inspection are not inspected for the second time, and the temperature abnormalities that still exist are not analyzed in detail in the second inspection, which reduces the timeliness of the discovery and handling of equipment temperature abnormalities, increases the risk of equipment damage, and thus increases the operation and maintenance costs of the enterprise.

[0004] 2. The inspection route of the current inspection robot in the computer room is set unchanged. The inspection route is not dynamically adjusted based on the actual status of the equipment in the computer room during the current cycle. This may cause the inspection robot to ignore key areas and repeatedly check normal areas, wasting precious inspection time and resources, failing to meet new inspection needs in the computer room, and affecting the overall operation and maintenance level of the computer room. Summary of the invention

[0005] In view of this, in order to solve the problems raised in the above background technology, a computer room operation and maintenance inspection method and system based on machine learning are proposed.

[0006] The purpose of the present invention can be achieved through the following technical solutions: The first aspect of the present invention provides a computer room operation and maintenance inspection method based on machine learning, including: S1, temperature abnormal equipment judgment: the preset inspection route of the target computer room is input into the target inspection robot background. When the target inspection robot inspects according to the preset inspection route, the thermal image of each device within the range of each inspection point in the inspection route is collected to determine whether there is temperature abnormal equipment within the range of each inspection point in the inspection route. If so, execute step S2. If not, it indicates that the equipment heat dissipation is normal.

[0007] S2. Adjust the speed of cooling fans: confirm each abnormal inspection point in the inspection route, extract the current speed of the cooling fans corresponding to the range of each abnormal inspection point, adjust the speed of the cooling fans corresponding to the range of each abnormal inspection point, and execute step S3.

[0008] S3. Judgment of equipment with continuously abnormal temperature: After the target inspection robot completes the first inspection, the location of each abnormal inspection point is sent to the target inspection robot background for a second inspection. The thermal images of each equipment with abnormal temperature within the range of each abnormal inspection point in the second inspection are collected to determine whether there is equipment with continuously abnormal temperature within the range of each abnormal inspection point. If so, execute step S4. If not, it indicates that the equipment temperature has returned to normal.

[0009] S4. Providing an abnormal heat dissipation operation and maintenance plan: record the equipment with continuously abnormal temperature as the target equipment, collect the heat dissipation grid image of each target equipment within the range of each abnormal inspection point and the corresponding cooling fan image of each abnormal inspection point, and collect the ambient temperature of each monitoring point corresponding to the target computer room, the air circulation speed of the heat dissipation port and the speed of the cooling fan, confirm the cause of the heat dissipation abnormality of each target equipment, and provide an operation and maintenance plan for the heat dissipation abnormality.

[0010] S5. Faulty equipment judgment: Collect the fault indicator light colors of each device within the scope of each inspection point in the inspection route, and judge whether there is a faulty device within the scope of each inspection point. If so, provide faulty equipment feedback.

[0011] S6. Inspection route optimization: Count the number of devices with abnormal temperature, the number of target devices, and the number of faulty devices within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, and optimize the preset inspection route of the target computer room.

[0012] The second aspect of the present invention provides a computer room operation and maintenance inspection system based on machine learning, including: a temperature abnormality equipment judgment module, which is used to input the preset inspection route of the target computer room into the target inspection robot background. When the target inspection robot inspects according to the preset inspection route, it collects thermal images of each device within the range of each inspection point in the inspection route, and determines whether there is temperature abnormality equipment within the range of each inspection point in the inspection route.

[0013] The cooling fan speed adjustment module is used to confirm each abnormal inspection point in the inspection route, extract the current speed of the cooling fan corresponding to the range of each abnormal inspection point, and adjust the speed of the cooling fan corresponding to the range of each abnormal inspection point.

[0014] The module for judging equipment with continuously abnormal temperature is used to send the location of each abnormal inspection point to the background of the target inspection robot for a second inspection after the first inspection of the target inspection robot is completed, collect the thermal images of each equipment with abnormal temperature within the range of each abnormal inspection point in the second inspection, and judge whether there is equipment with continuously abnormal temperature within the range of each abnormal inspection point.

[0015] The module for providing operation and maintenance solutions for abnormal heat dissipation is used to record devices with continuously abnormal temperatures as target devices, collect heat dissipation grid images of each target device within the range of each abnormal inspection point and images of the corresponding cooling fans within the range of each abnormal inspection point, and collect the ambient temperature of each monitoring point corresponding to the target computer room, the air circulation speed of the heat dissipation port and the speed of the cooling fan, confirm the cause of the abnormal heat dissipation of each target device, and provide operation and maintenance solutions for the abnormal heat dissipation.

[0016] The database is used to store the appropriate cooling fan speed corresponding to each temperature anomaly index, and to store the required compensation speed of the cooling fan corresponding to the abnormal heat dissipation deviation of the unit computer room.

[0017] The faulty equipment judgment module is used to collect the color of the fault indicator lights of each device within the range of each inspection point in the inspection route, and judge whether there is a faulty equipment within the range of each inspection point.

[0018] The inspection route optimization module is used to count the number of devices with abnormal temperature, the number of target devices, and the number of faulty devices within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, and optimize the preset inspection route of the target computer room.

[0019] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0020] (1) The present invention conducts secondary inspections on each abnormal inspection point in the target computer room to determine whether there is equipment with continuous abnormal temperature within the range of each abnormal inspection point. If so, the cause of the heat dissipation abnormality is confirmed, and an operation and maintenance plan is provided for the heat dissipation abnormality, thereby improving the timeliness of discovering and handling equipment temperature abnormalities, reducing the risk of equipment damage, and thus reducing the operation and maintenance costs of the enterprise.

[0021] (2) The present invention optimizes the preset inspection route of the target computer room by counting the number of devices with abnormal temperature, the number of target devices, and the number of faulty devices that appear within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, thereby avoiding the inspection robot ignoring key areas and repeatedly inspecting normal areas, saving precious inspection time and resources, meeting new inspection needs in the computer room, and improving the overall operation and maintenance level of the computer room. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0023] Figure 1The figure is a schematic flow chart of the method steps of the present invention.

[0024] Figure 2 It is a schematic diagram of the system structure connection of the present invention.

[0025] Figure 3 This is a flow chart of the abnormal temperature inspection of equipment according to the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] See also Figure 1 As shown, the first aspect of the present invention provides a computer room operation and maintenance inspection method based on machine learning, including: S1, temperature abnormal equipment judgment: the preset inspection route of the target computer room is input into the target inspection robot background, when the target inspection robot inspects according to the preset inspection route, it collects thermal images of each device within the range of each inspection point in the inspection route, and judges whether there is temperature abnormal equipment within the range of each inspection point in the inspection route. If so, execute step S2, if not, it indicates that the equipment heat dissipation is normal.

[0028] It should be noted that the thermal images of each device within the range of each inspection point in the inspection route are collected by a thermal imager installed on the target inspection robot.

[0029] In a specific embodiment of the present invention, the specific process of determining whether there is a device with abnormal temperature within the range of each inspection point in the inspection route is as follows: A1, locating the temperature value corresponding to each temperature distribution area from the thermal image of each device within the range of each inspection point in the inspection route, and calculating the average value thereof to obtain the average temperature of each device within the range of each inspection point, recorded as Wherein, i represents the number of the inspection point, i=1,2,...,n, and j represents the number of the equipment, j=1,2,...,m.

[0030] A2. Extract the maximum value from the temperature values ​​corresponding to each temperature distribution area of ​​each device within the range of each inspection point in the inspection route and record it as

[0031] A3. Calculate the temperature anomaly index β of each device within the range of each inspection point ij , Wherein, W′ represents the device temperature of the set reference, and e represents the natural constant.

[0032] A4. Compare the temperature anomaly index of each device within the range of each inspection point with the set reference temperature anomaly index. If the temperature anomaly index of a device within the range of a certain inspection point is greater than or equal to the set reference temperature anomaly index, the device is recorded as a temperature anomaly device. Therefore, it is determined whether there is a temperature anomaly device within the range of each inspection point in the inspection route.

[0033] S2. Adjust the speed of cooling fans: confirm each abnormal inspection point in the inspection route, extract the current speed of the cooling fans corresponding to the range of each abnormal inspection point, adjust the speed of the cooling fans corresponding to the range of each abnormal inspection point, and execute step S3.

[0034] It should be noted that the method of confirming each abnormal inspection point in the inspection route is: when there is any device with abnormal temperature within the range of a certain inspection point in the inspection route, the inspection point is recorded as an abnormal inspection point.

[0035] In a specific embodiment of the present invention, the specific process of adjusting the speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs is as follows: B1, the current speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs is recorded as v g , where g represents the number of the abnormal inspection point, g = 1, 2, ..., p.

[0036] B2. Extract the maximum value from the temperature anomaly index of each temperature abnormal device within the range of each abnormal inspection point, and compare it with the appropriate cooling fan speed corresponding to each temperature anomaly index stored in the database to obtain the appropriate cooling fan speed corresponding to the range of each abnormal inspection point, and record it as

[0037] B3. Set the required increase in speed of the cooling fan corresponding to the range of each abnormal inspection point.

[0038]

[0039] S3. Judgment of equipment with continuously abnormal temperature: After the target inspection robot completes the first inspection, the location of each abnormal inspection point is sent to the target inspection robot background for a second inspection. The thermal images of each equipment with abnormal temperature within the range of each abnormal inspection point in the second inspection are collected to determine whether there is equipment with continuously abnormal temperature within the range of each abnormal inspection point. If so, execute step S4. If not, it indicates that the equipment temperature has returned to normal.

[0040] It should be noted that the thermal images of each device with abnormal temperature within the range of each abnormal inspection point in the secondary inspection are also collected by the thermal imager installed on the target inspection robot.

[0041] In a specific embodiment of the present invention, the method for judging whether there is a device with continuously abnormal temperature within the range to which each abnormal inspection point belongs is: based on the thermal images of each device with continuously abnormal temperature within the range to which each abnormal inspection point belongs in the secondary inspection, the method of judging whether there is a device with continuously abnormal temperature within the range to which each inspection point belongs in the inspection route is used to judge whether there is a device with continuously abnormal temperature within the range to which each abnormal inspection point belongs.

[0042] S4. Providing an abnormal heat dissipation operation and maintenance plan: record the equipment with continuously abnormal temperature as the target equipment, collect the heat dissipation grid image of each target equipment within the range of each abnormal inspection point and the corresponding cooling fan image of each abnormal inspection point, and collect the ambient temperature of each monitoring point corresponding to the target computer room, the air circulation speed of the heat dissipation port and the speed of the cooling fan, confirm the cause of the heat dissipation abnormality of each target equipment, and provide an operation and maintenance plan for the heat dissipation abnormality.

[0043] It should be noted that the heat dissipation grid images of each target device within the range of each abnormal inspection point and the cooling fan images corresponding to the range of each abnormal inspection point are collected by the installed high-definition cameras, the ambient temperature of each monitoring point corresponding to the target computer room and the air circulation speed of the heat dissipation port are collected by temperature sensors and anemometers respectively, and the rotation speed of the cooling fan is extracted from the cooling fan display screen.

[0044] In a specific embodiment of the present invention, the specific process of confirming the cause of the heat dissipation abnormality of each target device is as follows: C1, based on the heat dissipation grid image of each target device within the range to which each abnormal inspection point belongs, calculate the heat dissipation grid abnormality index χ of each target device within the range to which each abnormal inspection point belongs gf , where f represents the number of the target device, f=1,2,...,z.

[0045] It should be noted that the specific process of calculating the heat dissipation grid abnormality index of each target device within the range to which each abnormal inspection point belongs is: the leftmost heat dissipation grid in the heat dissipation grid image of each target device within the range to which each abnormal inspection point belongs is recorded as the target heat dissipation grid, and the other heat dissipation grids are recorded as reference heat dissipation grids.

[0046] Each detection point is arranged from top to bottom in the target heat dissipation grid of each target device within the range of each abnormal inspection point, and is recorded as each target detection point. Each target detection point is mapped to each reference heat dissipation grid to obtain the mapping point corresponding to each target detection point in each reference heat dissipation grid, and then the distance between each target detection point in the target heat dissipation grid of each target device within the range of each abnormal inspection point and the mapping point corresponding to each target detection point in each reference heat dissipation grid is obtained, which is recorded as Wherein, q represents the number of the reference heat sink grid, q=1, 2, ..., k, and u represents the number of the mapping point, u=1, 2, ..., x.

[0047] Calculate the heat dissipation grid abnormality index χ of each target device within the range of each abnormal inspection point gf , Wherein, ΔL′ represents the horizontal spacing deviation between the reference heat dissipation grids, and q+1 represents the q+1th reference heat dissipation grid.

[0048] C2. Based on the cooling fan images corresponding to the range to which each abnormal inspection point belongs, calculate the cooling fan abnormality index δ corresponding to the range to which each abnormal inspection point belongs g .

[0049] It should be noted that the specific process of calculating the abnormal index of the cooling fan corresponding to the range to which each abnormal inspection point belongs is: locating the number of dirt spots and the dirt area corresponding to each dirt spot from the cooling fan image corresponding to the range to which each abnormal inspection point belongs.

[0050] The number of dirt spots on the cooling fan corresponding to the range of each abnormal inspection point is recorded as σ g .

[0051] The dirt areas corresponding to the dirt locations of the cooling fans corresponding to the range of each abnormal inspection point are accumulated to obtain the total dirt area of ​​the cooling fans corresponding to the range of each abnormal inspection point, and recorded as S g .

[0052] Calculate the cooling fan abnormality index δ corresponding to the range of each abnormal inspection point g , Wherein, σ′ and S′ represent the number of dirt sites and the dirt area of ​​the set reference, respectively.

[0053] C3. Calculate the heat dissipation anomaly index ω of the target computer room based on the ambient temperature of each monitoring point corresponding to the target computer room and the air circulation speed of the heat dissipation outlet.

[0054] It should be noted that the specific process of calculating the heat dissipation anomaly index of the target computer room is: average the ambient temperatures of the monitoring points corresponding to the target computer room to obtain the ambient temperature corresponding to the target computer room, and record it as W.

[0055] The air flow velocity of the heat dissipation outlet corresponding to the target computer room is recorded as v.

[0056] Calculate the heat dissipation anomaly index of the target computer room Wherein, W″ and v′ represent the reference ambient temperature and air flow velocity, respectively.

[0057] C4. When the heat dissipation grid abnormality index of a target device within the range of a certain abnormal inspection point is greater than the set reference heat dissipation grid abnormality index, the heat dissipation abnormality cause of the target device is recorded as its own heat dissipation grid cause; if the heat dissipation fan abnormality index corresponding to the range of the abnormal inspection point is greater than the set reference heat dissipation fan abnormality index, the heat dissipation abnormality cause of the target device is recorded as the heat dissipation fan cause; if the heat dissipation abnormality index of the target computer room is greater than the set reference heat dissipation abnormality index, the heat dissipation abnormality cause of the target device is recorded as the computer room heat dissipation cause.

[0058] In a specific embodiment of the present invention, the specific process of providing an operation and maintenance solution for heat dissipation anomalies is as follows: D1. If the heat dissipation anomaly of a target device is caused by its own heat dissipation grid, heat dissipation grid anomaly feedback is performed.

[0059] D2. If the abnormal heat dissipation of a target device is caused by the cooling fan, the cooling fan abnormality feedback is performed.

[0060] D3. If the cause of the abnormal heat dissipation of a target device is the heat dissipation of the computer room, the speed of the cooling fan corresponding to the target computer room is recorded as v 目 , extract the required compensation speed of the cooling fan corresponding to the abnormal heat dissipation deviation of the unit room from the database and record it as v 0 , set the appropriate speed v of the cooling fan corresponding to the target computer room 适 , and adjust the speed of the cooling fan corresponding to the target room to an appropriate speed, where: Indicates the heat dissipation abnormality index for setting reference.

[0061] The embodiment of the present invention performs secondary inspections on each abnormal inspection point in the target computer room to determine whether there is equipment with continuously abnormal temperature within the range of each abnormal inspection point. If so, the cause of the heat dissipation abnormality is confirmed, and an operation and maintenance plan is provided for the heat dissipation abnormality, thereby improving the timeliness of discovering and handling equipment temperature abnormalities, reducing the risk of equipment damage, and thus reducing the operation and maintenance costs of the enterprise.

[0062] S5. Faulty equipment judgment: Collect the fault indicator light colors of each device within the scope of each inspection point in the inspection route, and judge whether there is a faulty device within the scope of each inspection point. If so, provide faulty equipment feedback.

[0063] It should be noted that the color of the fault indicator light of each device within the range of each inspection point in the inspection route is obtained by collecting the corresponding fault indicator light image through a camera installed on the target inspection robot, and identifying the color of the fault indicator light from the fault indicator light image.

[0064] In a specific embodiment of the present invention, the specific method for determining whether there is a faulty device within the range of each inspection point is: comparing the color of the fault indicator light of each device within the range of each inspection point in the inspection route with the fault color displayed by the indicator light stored in the database; if the color of the fault indicator light of a device is consistent with the fault color displayed by the indicator light, the device is recorded as a faulty device.

[0065] S6. Inspection route optimization: Count the number of devices with abnormal temperature, the number of target devices, and the number of faulty devices within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, and optimize the preset inspection route of the target computer room.

[0066] In a specific embodiment of the present invention, the specific process of optimizing the inspection route preset for the target computer room is as follows: E1, based on the number of temperature abnormal devices, the number of target devices and the number of faulty devices that appear within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, calculate the frequency of abnormal occurrence of each inspection point in the inspection route in the current inspection cycle.

[0067] In a specific embodiment of the present invention, the specific process of calculating the frequency of abnormal occurrence of each inspection point in the inspection route in the current inspection cycle is as follows: F1, the number of temperature abnormal devices, the number of target devices and the number of faulty devices that appear within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle are recorded as and Wherein, r represents the number of the inspection day, r = 1, 2, ..., w.

[0068] F2. Calculate the frequency of abnormal occurrence of each inspection point in the inspection route during the current inspection cycle Among them, K 1 , K 2 and K 3 They respectively represent the proportion of devices with abnormal temperature, the proportion of target devices, and the proportion of faulty devices of the set reference. m represents the number of devices, z represents the number of target devices, and w represents the number of inspection days.

[0069] E2. Sort the frequency of abnormal occurrence of each inspection point in the inspection route in the current inspection cycle from large to small, obtain the order of the frequency of abnormal occurrence of the inspection points, and connect the inspection points in sequence according to the order of the frequency of abnormal occurrence to obtain the inspection route corresponding to the target computer room in the next inspection cycle.

[0070] The embodiment of the present invention optimizes the preset inspection route of the target computer room by counting the number of abnormal temperature devices, the number of target devices and the number of faulty devices that appear within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, so as to avoid the inspection robot ignoring key areas and repeatedly checking normal areas, thereby saving precious inspection time and resources, meeting new inspection needs in the computer room, and improving the overall operation and maintenance level of the computer room.

[0071] Reference Figure 2 As shown, the second aspect of the present invention provides a computer room operation and maintenance inspection system based on machine learning, including: a temperature abnormality equipment judgment module, a cooling fan speed adjustment module, a temperature continuous abnormality equipment judgment module, a cooling abnormality operation and maintenance solution providing module, a database, a faulty equipment judgment module and an inspection route optimization module.

[0072] The temperature abnormality equipment judgment module is connected to the cooling fan speed adjustment module, the temperature continuous abnormality equipment judgment module is connected to the cooling abnormality operation and maintenance solution providing module, the cooling fan speed adjustment module and the cooling abnormality operation and maintenance solution providing module are both connected to the database, and the temperature abnormality equipment judgment module, the temperature continuous abnormality equipment judgment module and the faulty equipment judgment module are all connected to the inspection route optimization module.

[0073] The temperature abnormality equipment judgment module is used to input the preset inspection route of the target computer room into the target inspection robot background. When the target inspection robot inspects according to the preset inspection route, it collects thermal images of each device within the range of each inspection point in the inspection route to determine whether there is temperature abnormality equipment within the range of each inspection point in the inspection route.

[0074] The cooling fan speed adjustment module is used to confirm each abnormal inspection point in the inspection route, extract the current speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs, and adjust the speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs.

[0075] The module for judging equipment with continuously abnormal temperature is used to send the location of each abnormal inspection point to the background of the target inspection robot for a second inspection after the first inspection of the target inspection robot is completed, collect thermal images of each equipment with abnormal temperature within the range of each abnormal inspection point in the second inspection, and judge whether there is equipment with continuously abnormal temperature within the range of each abnormal inspection point.

[0076] The heat dissipation abnormality operation and maintenance solution providing module is used to record devices with continuously abnormal temperatures as target devices, collect heat dissipation grid images of each target device within the range of each abnormal inspection point and the cooling fan images corresponding to the range of each abnormal inspection point, and at the same time collect the ambient temperature of each monitoring point corresponding to the target computer room, the air circulation speed of the heat dissipation port and the speed of the cooling fan, confirm the cause of the heat dissipation abnormality of each target device, and provide an operation and maintenance solution for the heat dissipation abnormality.

[0077] The database is used to store the appropriate cooling fan speed corresponding to each temperature anomaly index, and to store the required compensation speed of the cooling fan corresponding to the abnormal cooling deviation of the unit computer room.

[0078] Table 1 shows the data sources in the database of this embodiment.

[0079]

[0080] The faulty equipment judgment module is used to collect the color of the fault indicator lights of each device within the range of each inspection point in the inspection route, and judge whether there is a faulty equipment within the range of each inspection point.

[0081] The inspection route optimization module is used to count the number of devices with abnormal temperature, the number of target devices and the number of faulty devices within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, and optimize the inspection route preset for the target computer room.

[0082] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A machine room operation and maintenance inspection method based on machine learning, characterized in that: include: S1. Determine the device with abnormal temperature: input the preset inspection route of the target room into the background of the target inspection robot. When the target inspection robot inspects according to the preset inspection route, it collects the thermal images of each device within the range of each inspection point in the inspection route, and determines whether there is a device with abnormal temperature within the range of each inspection point in the inspection route. If so, execute step S2. If not, it indicates that the heat dissipation of the device is normal. S2, cooling fan speed adjustment: confirm each abnormal inspection point in the inspection route, extract the current speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs, adjust the speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs, and execute step S3; S3, determination of equipment with continuous abnormal temperature: after the target inspection robot completes the first inspection, the location of each abnormal inspection point is sent to the target inspection robot backend for a second inspection, and the thermal images of each equipment with abnormal temperature within the range of each abnormal inspection point in the second inspection are collected to determine whether there is equipment with continuous abnormal temperature within the range of each abnormal inspection point. If so, execute step S4; if not, it indicates that the equipment temperature has returned to normal; S4. Provide an abnormal heat dissipation operation and maintenance plan: record the equipment with continuous abnormal temperature as the target equipment, collect the heat dissipation grid image of each target equipment within the range of each abnormal inspection point and the corresponding heat dissipation fan image of each abnormal inspection point, and collect the ambient temperature of each monitoring point corresponding to the target computer room, the air circulation speed of the heat dissipation port and the speed of the heat dissipation fan, confirm the cause of the heat dissipation abnormality of each target equipment, and provide an operation and maintenance plan for the heat dissipation abnormality; S5. Faulty equipment judgment: Collect the fault indicator light colors of each device within the range of each inspection point in the inspection route, and judge whether there is a faulty device within the range of each inspection point. If so, provide faulty equipment feedback; S6. Inspection route optimization: Count the number of devices with abnormal temperature, the number of target devices, and the number of faulty devices within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, and optimize the preset inspection route of the target computer room.

2. According to a machine learning-based computer room operation and maintenance inspection method according to claim 1, it is characterized in that: The specific process of determining whether there is equipment with abnormal temperature within the range of each inspection point in the inspection route is as follows: A1. Locate the temperature values ​​corresponding to each temperature distribution area from the thermal images of each device within the range of each inspection point in the inspection route, calculate the average value, and obtain the average temperature of each device within the range of each inspection point, recorded as Where i represents the number of the inspection point, i=1,2,...,n, j represents the number of the equipment, j=1,2,...,m; A2. Extract the maximum value from the temperature values ​​corresponding to each temperature distribution area of ​​each device within the range of each inspection point in the inspection route and record it as A3. Calculate the temperature anomaly index β of each device within the range of each inspection point ij , Where W′ represents the device temperature of the set reference, and e represents the natural constant; A4. Compare the temperature anomaly index of each device within the range of each inspection point with the set reference temperature anomaly index. If the temperature anomaly index of a device within the range of a certain inspection point is greater than or equal to the set reference temperature anomaly index, the device is recorded as a temperature anomaly device. Therefore, it is determined whether there is a temperature anomaly device within the range of each inspection point in the inspection route.

3. The machine room operation and maintenance inspection method based on machine learning according to claim 2 is characterized in that: The specific process of adjusting the speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs is as follows: B1. The current speed of the cooling fan corresponding to the range of each abnormal inspection point is recorded as v g , where g represents the number of the abnormal inspection point, g = 1, 2, ..., p; B2. Extract the maximum value from the temperature anomaly index of each temperature abnormal device within the range of each abnormal inspection point, and compare it with the appropriate cooling fan speed corresponding to each temperature anomaly index stored in the database to obtain the appropriate cooling fan speed corresponding to the range of each abnormal inspection point, and record it as B3. Set the required increase in speed of the cooling fan corresponding to the range of each abnormal inspection point.

4. The machine room operation and maintenance inspection method based on machine learning according to claim 2 is characterized in that: The method for judging whether there is a device with continuously abnormal temperature within the range of each abnormal inspection point is as follows: based on the thermal images of each device with continuously abnormal temperature within the range of each abnormal inspection point in the secondary inspection, judging whether there is a device with continuously abnormal temperature within the range of each abnormal inspection point in the inspection route in the same way as judging whether there is a device with continuously abnormal temperature within the range of each inspection point.

5. The machine room operation and maintenance inspection method based on machine learning according to claim 3 is characterized in that: The specific process of confirming the cause of abnormal heat dissipation of each target device is as follows: C1. Based on the heat dissipation grid images of each target device within the range of each abnormal inspection point, calculate the heat dissipation grid abnormality index χ of each target device within the range of each abnormal inspection point. gf , where f represents the number of the target device, f = 1, 2, ..., z; C2. Based on the cooling fan images corresponding to the range to which each abnormal inspection point belongs, calculate the cooling fan abnormality index δ corresponding to the range to which each abnormal inspection point belongs g ; C3. Calculate the heat dissipation anomaly index of the target computer room based on the ambient temperature of each monitoring point and the air circulation speed of the heat dissipation outlet corresponding to the target computer room C4. When the heat dissipation grid abnormality index of a target device within the range of a certain abnormal inspection point is greater than the set reference heat dissipation grid abnormality index, the heat dissipation abnormality cause of the target device is recorded as its own heat dissipation grid cause; if the heat dissipation fan abnormality index corresponding to the range of the abnormal inspection point is greater than the set reference heat dissipation fan abnormality index, the heat dissipation abnormality cause of the target device is recorded as the heat dissipation fan cause; if the heat dissipation abnormality index of the target computer room is greater than the set reference heat dissipation abnormality index, the heat dissipation abnormality cause of the target device is recorded as the computer room heat dissipation cause.

6. The machine room operation and maintenance inspection method based on machine learning according to claim 5 is characterized in that: The specific process of providing an operation and maintenance solution for heat dissipation anomalies is as follows: D1. If the heat dissipation abnormality of a target device is caused by its own heat dissipation grid, feedback on the heat dissipation grid abnormality is performed; D2. If the heat dissipation abnormality of a target device is caused by the cooling fan, then feedback on the cooling fan abnormality is provided; D3. If the cause of the abnormal heat dissipation of a target device is the heat dissipation of the computer room, the speed of the cooling fan corresponding to the target computer room is recorded as v 目 , extract the required compensation speed of the cooling fan corresponding to the abnormal heat dissipation deviation of the unit computer room from the database, and record it as v0, and set the appropriate speed v of the cooling fan corresponding to the target computer room 适 , and adjust the speed of the cooling fan corresponding to the target room to an appropriate speed, where: Indicates the heat dissipation abnormality index for setting reference.

7. The method for machine room operation and maintenance inspection based on machine learning according to claim 5 is characterized in that: The specific method for determining whether there is a faulty device within the range of each inspection point is: comparing the color of the fault indicator light of each device within the range of each inspection point in the inspection route with the fault color displayed by the indicator light stored in the database; if the color of the fault indicator light of a device is consistent with the fault color displayed by the indicator light, the device is recorded as a faulty device.

8. The machine room operation and maintenance inspection method based on machine learning according to claim 7 is characterized in that: The specific process of optimizing the inspection route preset in the target computer room is as follows: E1. Based on the number of devices with abnormal temperature, the number of target devices, and the number of faulty devices that appear within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, calculate the frequency of abnormal occurrence of each inspection point in the inspection route in the current inspection cycle. E2. Sort the frequency of abnormal occurrence of each inspection point in the inspection route in the current inspection cycle from large to small, obtain the order of the frequency of abnormal occurrence of the inspection points, and connect the inspection points in sequence according to the order of the frequency of abnormal occurrence to obtain the inspection route corresponding to the target computer room in the next inspection cycle.

9. The machine room operation and maintenance inspection method based on machine learning according to claim 8 is characterized in that: The specific process of calculating the frequency of abnormal occurrence of each inspection point in the inspection route in the current inspection cycle is as follows: F1. Record the number of devices with abnormal temperature, the number of target devices, and the number of faulty devices within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle as and Where r represents the number of the inspection day, r = 1, 2, ..., w; F2. Calculate the frequency of abnormal occurrence of each inspection point in the inspection route during the current inspection cycle Among them, K1, K2 and K3 respectively represent the proportion of temperature abnormal devices, target devices and faulty devices of the set reference, m represents the number of devices, z represents the number of target devices, and w represents the number of inspection days.

10. A machine room operation and maintenance inspection system based on machine learning, characterized in that: include: The temperature abnormal equipment judgment module is used to input the preset inspection route of the target room into the target inspection robot background. When the target inspection robot inspects according to the preset inspection route, it collects the thermal images of each device within the range of each inspection point in the inspection route, and judges whether there is a temperature abnormal device within the range of each inspection point in the inspection route; The cooling fan speed adjustment module is used to confirm each abnormal inspection point in the inspection route, extract the current speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs, and adjust the speed of the cooling fan corresponding to the range to which each abnormal inspection point belongs; The module for judging the equipment with continuous abnormal temperature is used to send the position of each abnormal inspection point to the background of the target inspection robot for a second inspection after the first inspection of the target inspection robot is completed, collect the thermal images of each equipment with abnormal temperature within the range of each abnormal inspection point in the second inspection, and judge whether there is equipment with continuous abnormal temperature within the range of each abnormal inspection point; The module for providing operation and maintenance solutions for abnormal heat dissipation is used to record devices with continuously abnormal temperatures as target devices, collect heat dissipation grid images of each target device within the range of each abnormal inspection point and the corresponding heat dissipation fan images within the range of each abnormal inspection point, and collect the ambient temperature of each monitoring point corresponding to the target computer room, the air circulation speed of the heat dissipation port, and the speed of the heat dissipation fan, confirm the cause of the heat dissipation abnormality of each target device, and provide operation and maintenance solutions for the heat dissipation abnormality; A database is used to store the appropriate cooling fan speed corresponding to each temperature anomaly index, and to store the required compensation speed of the cooling fan corresponding to the abnormal cooling deviation of the unit computer room; The faulty equipment judgment module is used to collect the fault indicator light colors of each device within the range of each inspection point in the inspection route, and judge whether there is a faulty equipment within the range of each inspection point; The inspection route optimization module is used to count the number of devices with abnormal temperature, the number of target devices, and the number of faulty devices within the range of each inspection point in the inspection route corresponding to each inspection day in the current inspection cycle, and optimize the preset inspection route of the target computer room.

Images