A monitoring method and system for intelligent power distribution cabinet

Abstract

The present invention discloses a monitoring method and system for an intelligent power distribution cabinet, which relates to the technical field of power distribution cabinet monitoring, including: periodically detecting the humidity Sd of the power distribution cabinet; i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i ; Get the usage time Sy of the power distribution cabinet j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j ; Use the camera to collect the internal image of the distribution cabinet with high rust risk, and calculate the grayscale mean value Jph of the internal image of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ ; Calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , judge whether each component is rusted, and discover and deal with rust problems in time.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution cabinet monitoring, and in particular to a monitoring method and system for an intelligent power distribution cabinet. Background Art

[0002] With the continuous development of science and technology, intelligent distribution cabinets have been widely used in power systems. Intelligent distribution cabinets have the characteristics of automation and intelligence, and can realize real-time monitoring, data collection, fault diagnosis and other functions of the distribution system. However, there are still some problems in the existing intelligent distribution cabinet monitoring system, such as inaccurate data collection and incomplete fault diagnosis, which brings safety hazards to the stable operation of the power system. Therefore, it is particularly important to develop a more accurate intelligent distribution cabinet monitoring method and system.

[0003] In the Chinese invention application with application publication number CN110264679A, a distribution cabinet monitoring system and method are disclosed, including a fault detection module, an intelligent fire protection module and a main control platform; the fault detection module is used to perform real-time data monitoring and fault analysis on the distribution cabinet, and the main control center receives power equipment fault information, and starts the alarm module A according to the fault location, controls the intelligent fire protection module to start the alarm unit B and the fire control unit, controls the actuator on the distribution cabinet site, controls the automatic adjustment of the temperature and humidity inside the distribution cabinet, controls the disconnection of the distribution cabinet circuit power supply and the automatic start of the fire protection equipment.

[0004] In the above invention application, by monitoring the operating data of the distribution cabinet and analyzing faults, it is possible to achieve automatic adjustment of the internal temperature and humidity, control the disconnection of the distribution cabinet circuit power supply, and automatically start the fire-fighting equipment. However, only basic operating data is monitored, and accidents cannot be avoided. Often, a response can only be made after an accident occurs. Many distribution cabinet accidents are often caused by rusting of the distribution cabinet due to long-term use, resulting in poor contact of wires, short circuits and leakage problems. Especially in the south where the humidity is high during the return of the south wind, the distribution cabinet often trips frequently due to rust during use.

[0005] To this end, the present invention provides a monitoring method and system for an intelligent power distribution cabinet. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the deficiencies in the prior art, the present invention provides a monitoring method and system for an intelligent distribution cabinet. The present invention first analyzes the humidity of the distribution cabinet to preliminarily determine whether the distribution cabinet has a risk of rusting, and then specifically analyzes each component inside the distribution cabinet with a high risk of rusting. The rust condition of each component can be accurately determined, the rust problem can be discovered and dealt with in time, the service life of the distribution cabinet and its internal components can be extended, maintenance resources can be reasonably allocated, high-risk equipment can be given priority, and the maintenance efficiency of the distribution cabinet can be improved, thereby solving the technical problems recorded in the background technology.

[0008] (II) Technical solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: A monitoring method for an intelligent power distribution cabinet comprises the following steps:

[0010] Periodically check the humidity Sd of the power distribution cabinet i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i , when the predicted humidity value of the distribution cabinet Yc i When the humidity is >75, an alarm will be issued to indicate that the humidity is above the standard, and the SPR-CN-S1 intelligent dehumidifier will be activated to reduce the humidity in the power distribution cabinet.

[0011] Get the usage time of the power distribution cabinet Sy j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j , when the distribution cabinet rusts, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting, and an analysis command is issued;

[0012] Use the camera to collect the internal image of the distribution cabinet with high rust risk, and calculate the grayscale mean value Jph of the internal image of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ ;

[0013] Get the grayscale mean Jph of the image inside the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ , calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , based on the size relationship between the two, determine whether each component is rusted and select the corresponding safety warning processing strategy.

[0014] Furthermore, an electronic humidity sensor is used to periodically detect the humidity Sd of the distribution cabinet. i After linear normalization, the humidity change rate Bs is calculated. i , the corresponding humidity change rate Bs iThe calculation formula is as follows:

[0015]

[0016] Wherein, i represents the time sequence number of the humidity data of the distribution cabinet, i=1, 2, ..., m, m is a positive integer, and the periodic detection time can be any one of 1, 2, ..., 6 hours.

[0017] It should be noted that when the ambient humidity is greater than 75%, steel is prone to rust, and the thickness of the water film on the metal surface increases, which is conducive to the formation and expansion of corrosion products. SPR-CN-S1 intelligent dehumidifier is a high-tech product specially used for dehumidification of electrical cabinets. Through semiconductor refrigeration technology, it creates condensation conditions locally, so that the humid air in the cabinet condenses into water and is directly discharged outside the cabinet, quickly and effectively reducing the humidity in the electrical cabinet.

[0018] Furthermore, the humidity Sd of the power distribution cabinet is obtained. i and humidity change rate Bs i After linear normalization, the predicted value of humidity in the power distribution cabinet Yc is calculated. i , the corresponding distribution cabinet humidity prediction value Yc i The calculation formula is as follows:

[0019]

[0020] When the predicted humidity value of the distribution cabinet is Yc i When the humidity is >75, an alarm will be issued and the SPR-CN-S1 intelligent dehumidifier will be started to reduce the humidity in the distribution cabinet.

[0021] Furthermore, the use time Sy of the power distribution cabinet is obtained based on the work record of the power distribution cabinet. j And humidity warning times Cs j , combined with the distribution cabinet humidity Sd ij After linear normalization, the rust risk weight coefficients k1, k2 and k3 are calculated. The corresponding calculation formulas of the rust risk weight coefficients k1, k2 and k3 are as follows:

[0022]

[0023] Wherein, j represents the sequential number of all distribution cabinets, j=1, 2, ..., n, and n is a positive integer.

[0024] It should be noted that the service life of the distribution cabinet is 15-20 years. When the service life of the distribution cabinet expires, its main conductive parts are prone to damage and cannot meet the power distribution needs. The distribution cabinet needs to be replaced in time to prevent the occurrence of power safety accidents.

[0025] Furthermore, the use time Sy of the power distribution cabinet is obtained based on the work record of the power distribution cabinet.j And humidity warning times Cs j After linear normalization, the rust risk index Wx of the distribution cabinet is calculated. j :

[0026]

[0027] When the distribution cabinet is rusted, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting and an analysis command is issued.

[0028] Furthermore, a camera is used to collect images of the interior of the distribution cabinet with a high risk of rust, and image processing software is used to obtain the grayscale value Zh of all pixels in the image of the interior of the distribution cabinet. αβ , calculate the grayscale mean Jph of the internal image of the distribution cabinet α , the corresponding grayscale mean value Jph of the internal image of the power distribution cabinet α The calculation formula is as follows:

[0029]

[0030] Wherein, α represents the sequential number of all images inside the distribution cabinet, α=1, 2, ..., b, and β represents the sequential number of all pixels in the image inside the distribution cabinet.

[0031] Furthermore, the electrical component recognition algorithm is used to extract the feature map of each component from the internal image of the distribution cabinet, and the total number of pixels γ of each component feature map and the grayscale value Y corresponding to each pixel are obtained. jαδγ , calculate the grayscale mean Jhj of each component feature map αδ :

[0032]

[0033] Among them, δ represents the sequential numbering of all components inside the distribution cabinet, and γ represents the sequential numbering of all pixel points in the feature map of each component.

[0034] It should be noted that the electrical component recognition algorithm can refer to the following literature: Research on electrical component recognition method based on transfer learning; Application of light color identification method in electrical components; Electrical component symbol recognition algorithm based on deep neural network; Research on electrical component image recognition method based on multi-view learning;

[0035] Furthermore, the grayscale mean Jph of the internal image of the power distribution cabinet is obtained. α And the grayscale mean Jhj of each component feature map αδ After linear normalization, the rust degree index Csd of each component is calculated. αδ and the normal grayscale threshold ΔH of each element δ :

[0036]

[0037] Corresponding rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ The calculation formula is as above.

[0038] Further, the rust degree index Csd of each component is obtained αδ and the normal grayscale threshold ΔH of each element δ , based on the size relationship between the two, determine whether each component is rusted, and select the corresponding safety warning processing strategy, specifically:

[0039] When Csd αδ <ΔH δ When the component is not rusted, it will be fed back that no measures are needed and the monitoring will continue to be carried out to prevent any abnormal situation.

[0040] When 2ΔH δ >Csd αδ ≥ΔH δ When the current component is rusted, the feedback is that the rust degree is low, the nozzle is started to spray the rust remover to the corresponding component, and the monitoring is continued;

[0041] When 2ΔH δ ≤Csd αδ When the current component is rusted and the degree of rust is high, it will feedback that the corresponding component rust warning is sent out, indicating that the component needs to be replaced to eliminate safety hazards.

[0042] A monitoring system for an intelligent power distribution cabinet, comprising:

[0043] Distribution cabinet humidity analysis module, periodically detects the distribution cabinet humidity Sd i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i , when the predicted humidity value of the distribution cabinet Yc i When the humidity is >75, an alarm will be issued to indicate that the humidity is above the standard, and the SPR-CN-S1 intelligent dehumidifier will be activated to reduce the humidity in the power distribution cabinet.

[0044] The rust analysis module of the power distribution cabinet obtains the usage time Sy of the power distribution cabinet j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j , when the distribution cabinet rusts, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting, and an analysis command is issued;

[0045] The component grayscale analysis module uses a camera to collect images of the interior of the distribution cabinet with a high risk of rust, and calculates the grayscale mean Jph of the images of the interior of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ ;

[0046] Component rust processing module, obtains the grayscale mean Jph of the internal image of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ , calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , based on the size relationship between the two, determine whether each component is rusted and select the corresponding safety warning processing strategy.

[0047] (III) Beneficial effects

[0048] The present invention provides a monitoring method and system for an intelligent power distribution cabinet, which has the following beneficial effects:

[0049] 1. Periodically detect the humidity Sd of the power distribution cabinet i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i , when the predicted humidity value of the distribution cabinet Yc i When the humidity exceeds 75%, an alarm of excessive humidity is issued and the SPR-CN-S1 intelligent dehumidifier is started to reduce the humidity in the distribution cabinet. By timely monitoring and reducing the humidity and maintaining the appropriate humidity in the distribution cabinet, the normal operation of electrical equipment can be ensured, and short circuits caused by excessive humidity can be avoided, thus preventing accidents.

[0050] 2. Obtain the usage time Sy of the power distribution cabinet j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j , when the distribution cabinet rusts, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting. An analysis command is issued to analyze the historical working status of the distribution cabinet first, and preliminarily determine whether the distribution cabinet has a risk of rusting. Maintenance resources can be reasonably allocated, high-risk equipment can be given priority, and the maintenance efficiency of the distribution cabinet can be improved.

[0051] 3. Use the camera to collect the internal image of the distribution cabinet with high rust risk, and calculate the grayscale mean value Jph of the internal image of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ ,Automated image acquisition and grayscale mean calculation can reduce the frequency of manual inspection and ,recording, and reduce labor costs. ,The collected images and calculation results can be recorded and stored, ,which can provide data support for fault prediction and ,maintenance.

[0052] 4. Get the grayscale mean Jph of the internal image of the power distribution cabinet α And the grayscale mean Jhj of each component feature map αδ , calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ According to the size relationship between the two, it is possible to judge whether each component is rusted and select the corresponding safety warning processing strategy. This can accurately judge the rust condition of each component, timely discover and deal with rust problems, and extend the service life of the distribution cabinet and internal components. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A flow chart of a monitoring method for an intelligent power distribution cabinet according to the present invention;

[0054] Figure 2 The present invention is a structural schematic diagram of a monitoring system for an intelligent power distribution cabinet. DETAILED DESCRIPTION

[0055] 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.

[0056] See also Figure 1 The present invention provides a monitoring method for an intelligent power distribution cabinet, comprising the following steps:

[0057] Step 1: Periodically check the humidity Sd of the power distribution cabinet i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i , when the predicted humidity value of the distribution cabinet Yc i When the humidity is >75, an alarm will be issued and the SPR-CN-S1 intelligent dehumidifier will be started to reduce the humidity in the distribution cabinet.

[0058] The step 1 includes the following contents:

[0059] Step 101: Use an electronic humidity sensor to periodically detect and obtain the humidity Sd of the power distribution cabinet. i After linear normalization, the humidity change rate Bs is calculated. i , the corresponding humidity change rate Bs i The calculation formula is as follows:

[0060]

[0061] Wherein, i represents the time sequence number of the humidity data of the distribution cabinet, i=1, 2, ..., m, m is a positive integer, and the periodic detection time can be any one of 1, 2, ..., 6 hours.

[0062] Step 102: Obtain the humidity Sd of the power distribution cabinet i and humidity change rate Bs i After linear normalization, the predicted value of humidity in the power distribution cabinet Yc is calculated. i , the corresponding distribution cabinet humidity prediction value Yc i The calculation formula is as follows:

[0063]

[0064] When the predicted humidity value of the distribution cabinet is Yc i When the humidity is >75, an alarm will be issued and the SPR-CN-S1 intelligent dehumidifier will be started to reduce the humidity in the distribution cabinet.

[0065] It should be noted that when the ambient humidity is greater than 75%, steel is prone to rust, and the thickness of the water film on the metal surface increases, which is conducive to the formation and expansion of corrosion products. SPR-CN-S1 intelligent dehumidifier is a high-tech product specially used for dehumidification of electrical cabinets. Through semiconductor refrigeration technology, it creates condensation conditions locally, so that the humid air in the cabinet condenses into water and is directly discharged outside the cabinet, quickly and effectively reducing the humidity in the electrical cabinet.

[0066] When using, combine the contents in steps 101 and 102:

[0067] By periodically detecting the humidity Sd of the distribution cabinet i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i , when the predicted humidity value of the distribution cabinet Yc i When the humidity exceeds 75%, an alarm of excessive humidity is issued and the SPR-CN-S1 intelligent dehumidifier is started to reduce the humidity in the distribution cabinet. By timely monitoring and reducing the humidity and maintaining the appropriate humidity in the distribution cabinet, the normal operation of electrical equipment can be ensured, and short circuits caused by excessive humidity can be avoided, thus preventing accidents.

[0068] Step 2: Get the usage time Sy of the power distribution cabinet j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j , when the distribution cabinet rusts, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting and an analysis command is issued.

[0069] The step 2 includes the following contents:

[0070] Step 201: Obtain the usage time Sy of the power distribution cabinet according to the power distribution cabinet work record j And humidity warning times Cs j , combined with the distribution cabinet humidity Sd i j, after linear normalization, the rust risk weight coefficients k1, k2 and k3 are calculated. The corresponding calculation formulas of the rust risk weight coefficients k1, k2 and k3 are as follows:

[0071]

[0072] Wherein, j represents the sequential number of all distribution cabinets, j=1, 2, ..., n, and n is a positive integer.

[0073] It should be noted that the service life of the distribution cabinet is 15-20 years. When the service life of the distribution cabinet expires, its main conductive parts are prone to damage and cannot meet the power distribution needs. The distribution cabinet needs to be replaced in time to prevent the occurrence of power safety accidents.

[0074] Step 202: Obtain the usage time Sy of the power distribution cabinet according to the power distribution cabinet work record j And humidity warning times Cs j After linear normalization, the rust risk index Wx of the distribution cabinet is calculated. j :

[0075]

[0076] When the distribution cabinet is rusted, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting and an analysis command is issued.

[0077] When using, combine the contents in steps 201 and 202:

[0078] By obtaining the usage time Sy of the distribution cabinet j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j , when the distribution cabinet rusts, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting. An analysis command is issued to analyze the historical working status of the distribution cabinet first, and preliminarily determine whether the distribution cabinet has a risk of rusting. Maintenance resources can be reasonably allocated, high-risk equipment can be given priority, and the maintenance efficiency of the distribution cabinet can be improved.

[0079] Step 3: Use the camera to collect images of the interior of the distribution cabinet with a high risk of rust, and calculate the grayscale mean Jph of the image of the interior of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ .

[0080] The step three includes the following contents:

[0081] Step 301: Use a camera to collect images of the interior of a distribution cabinet with a high risk of rust, and use image processing software to obtain the grayscale values ​​Zh of all pixels in the image of the interior of the distribution cabinet. αβ , calculate the grayscale mean Jph of the internal image of the distribution cabinet α , the corresponding grayscale mean value Jph of the internal image of the power distribution cabinet α The calculation formula is as follows:

[0082]

[0083] Wherein, α represents the sequential number of all images inside the distribution cabinet, α=1, 2, ..., b, and β represents the sequential number of all pixels in the image inside the distribution cabinet.

[0084] Step 302: Use the electrical component recognition algorithm to extract the feature map of each component from the internal image of the distribution cabinet, and obtain the total number of pixels γ of each component feature map and the gray value Yj corresponding to each pixel αδγ , calculate the grayscale mean Jhj of each component feature map αδ :

[0085]

[0086] Among them, δ represents the sequential numbering of all components inside the distribution cabinet, and γ represents the sequential numbering of all pixel points in the feature map of each component.

[0087] It should be noted that the electrical component recognition algorithm can refer to the following literature: Research on electrical component recognition method based on transfer learning; Application of light color identification method in electrical components; Electrical component symbol recognition algorithm based on deep neural network; Research on electrical component image recognition method based on multi-view learning;

[0088] When used, combine the contents in steps 301 and 302:

[0089] By using a camera to collect images of the interior of the distribution cabinet with a high risk of rust, the grayscale mean value Jph of the image of the interior of the distribution cabinet is calculated α And the grayscale mean Jhj of each component feature map αδ ,Automated image acquisition and grayscale mean calculation can reduce the frequency of manual inspection and ,recording, and reduce labor costs. ,The collected images and calculation results can be recorded and stored, ,which can provide data support for fault prediction and ,maintenance.

[0090] Step 4: Get the grayscale mean Jph of the internal image of the power distribution cabinet α And the grayscale mean Jhj of each component feature map αδ, calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , based on the size relationship between the two, determine whether each component is rusted and select the corresponding safety warning processing strategy.

[0091] The step 4 includes the following contents:

[0092] Step 401: Obtain the grayscale mean value Jph of the internal image of the power distribution cabinet α And the grayscale mean Jhj of each component feature map αδ After linear normalization, the rust degree index Csd of each component is calculated. αδ and the normal grayscale threshold ΔH of each element δ :

[0093]

[0094] Corresponding rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ The calculation formula is as above.

[0095] Step 402: Obtain the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , based on the size relationship between the two, determine whether each component is rusted, and select the corresponding safety warning processing strategy, specifically:

[0096] When Csd αδ <ΔH δ When the component is not rusted, it is fed back that no action is needed and monitoring should be continued to prevent any abnormal situation.

[0097] When 2ΔH δ >Csd αδ ≥ΔH δ When the current component is rusted, the feedback is that the rust degree is low, and the nozzle is started to spray the rust remover to the corresponding component, and the monitoring is continued.

[0098] When 2ΔH δ ≤Csd αδ When the current component is rusted and the degree of rust is high, it will feedback that the corresponding component rust warning is sent out, indicating that the component needs to be replaced to eliminate safety hazards.

[0099] When using, combine the contents in steps 401 and 402:

[0100] Get the grayscale mean Jph of the image inside the distribution cabinet α And the grayscale mean Jhj of each component feature mapαδ , calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ According to the size relationship between the two, it is possible to judge whether each component is rusted and select the corresponding safety warning processing strategy. This can accurately judge the rust condition of each component, timely discover and deal with rust problems, and extend the service life of the distribution cabinet and internal components.

[0101] See also Figure 2 The present invention provides a monitoring system for an intelligent power distribution cabinet, comprising:

[0102] Distribution cabinet humidity analysis module, periodically detects the distribution cabinet humidity Sd i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i , when the predicted humidity value of the distribution cabinet Yc i When the humidity is >75, an alarm will be issued and the SPR-CN-S1 intelligent dehumidifier will be started to reduce the humidity in the distribution cabinet.

[0103] The rust analysis module of the power distribution cabinet obtains the usage time Sy of the power distribution cabinet j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j , when the distribution cabinet rusts, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting and an analysis command is issued.

[0104] The component grayscale analysis module uses a camera to collect images of the interior of the distribution cabinet with a high risk of rust, and calculates the grayscale mean Jph of the images of the interior of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ .

[0105] Component rust processing module, obtains the grayscale mean Jph of the internal image of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ , calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , based on the size relationship between the two, determine whether each component is rusted and select the corresponding safety warning processing strategy.

[0106] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A monitoring method for an intelligent power distribution cabinet, characterized in that: The steps include: Periodically check the humidity Sd of the power distribution cabinet i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i , when the predicted humidity value of the distribution cabinet Yc i When the humidity is >75%, an alarm will be issued to the outside and the humidity of the power distribution cabinet will be reduced; Get the usage time of the power distribution cabinet Sy j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j , when the distribution cabinet rusts, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting, and an analysis command is issued; Use the camera to collect the internal image of the distribution cabinet with high rust risk, and calculate the grayscale mean value Jph of the internal image of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ ; Get the grayscale mean Jph of the image inside the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ , calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , according to the size relationship between the two, determine whether each component is rusted, and select the corresponding safety warning processing strategy; Among them, the use time Sy of the distribution cabinet is obtained based on the distribution cabinet work record j And humidity warning times Cs j , combined with the distribution cabinet humidity Sd ij After linear normalization, the rust risk weight coefficients k1, k2 and k3 are calculated. The corresponding calculation formulas of the rust risk weight coefficients k1, k2 and k3 are as follows: Wherein, j represents the sequential number of all distribution cabinets, j=1, 2, ..., n, and n is a positive integer; Get the usage time Sy of the distribution cabinet based on the distribution cabinet work record j And humidity warning times Cs j After linear normalization, the rust risk index Wx of the distribution cabinet is calculated. j : When the distribution cabinet is rusted, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting and an analysis command is issued.

2. The monitoring method of an intelligent power distribution cabinet according to claim 1, characterized in that: Use electronic humidity sensors to periodically detect and obtain the humidity Sd of the distribution cabinet i After linear normalization, the humidity change rate Bs is calculated. i , the corresponding humidity change rate Bs i The calculation formula is as follows: Wherein, i represents the time sequence number of the humidity data of the distribution cabinet, i=1, 2, ..., m, m is a positive integer, and the periodic detection time can be any one of 1, 2, ..., 6 hours.

3. The monitoring method of an intelligent power distribution cabinet according to claim 2, characterized in that: Get the humidity Sd of the power distribution cabinet i and humidity change rate Bs i After linear normalization, the predicted value of humidity in the power distribution cabinet Yc is calculated. i , the corresponding distribution cabinet humidity prediction value Yc i The calculation formula is as follows: When the predicted humidity value of the distribution cabinet is Yc i When the humidity is >75, an alarm will be issued and the SPR-CN-S1 intelligent dehumidifier will be started to reduce the humidity in the distribution cabinet.

4. The monitoring method of an intelligent power distribution cabinet according to claim 1, characterized in that: Use a camera to collect images of the interior of a distribution cabinet with a high risk of rust, and use image processing software to obtain the grayscale value Zh of all pixels in the image of the interior of the distribution cabinet αβ , calculate the grayscale mean Jph of the internal image of the distribution cabinet α , the corresponding grayscale mean value Jph of the internal image of the power distribution cabinet α The calculation formula is as follows: Wherein, α represents the sequential number of all images inside the distribution cabinet, α=1, 2, ..., b, and β represents the sequential number of all pixels in the image inside the distribution cabinet.

5. The monitoring method of an intelligent power distribution cabinet according to claim 4, characterized in that: Use the electrical component recognition algorithm to extract the feature map of each component from the internal image of the distribution cabinet, and obtain the total number of pixels γ of each component feature map and the grayscale value Yj corresponding to each pixel αδγ , calculate the grayscale mean Jhj of each component feature map αδ : Among them, δ represents the sequential numbering of all components inside the distribution cabinet, and γ represents the sequential numbering of all pixel points in the feature map of each component.

6. The monitoring method of an intelligent power distribution cabinet according to claim 5, characterized in that: Get the grayscale mean Jph of the image inside the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ After linear normalization, the rust degree index Csd of each component is calculated. αδ and the normal grayscale threshold ΔH of each element δ : Corresponding rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ The calculation formula is as above.

7. The monitoring method of an intelligent power distribution cabinet according to claim 6, characterized in that: Get the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , based on the size relationship between the two, determine whether each component is rusted, and select the corresponding safety warning processing strategy, specifically: When Csd αδ <ΔH δ When the component is not rusted, it is fed back that no action is needed and the monitoring shall continue; When 2ΔH δ >Csd αδ ≥ΔH δ When the current component is rusted, the feedback is that the rust degree is low, the nozzle is started to spray the rust remover to the corresponding component, and the monitoring is continued; When 2ΔH δ ≤Csd αδ When the current component is rusted and the degree of rust is high, it will feedback that the corresponding component rust warning is sent out and the component is replaced.

8. A monitoring system for an intelligent power distribution cabinet, characterized in that: include: Distribution cabinet humidity analysis module, periodically detects the distribution cabinet humidity Sd i , calculate and obtain the predicted value of humidity in the power distribution cabinet Yc i , when the predicted humidity value of the distribution cabinet Yc i When the humidity is >75, an alarm will be issued to indicate that the humidity is above the standard, and the SPR-CN-S1 intelligent dehumidifier will be activated to reduce the humidity in the power distribution cabinet. The rust analysis module of the power distribution cabinet obtains the usage time Sy of the power distribution cabinet j And humidity warning times Cs j , calculate the rust risk index Wx of the power distribution cabinet j , when the distribution cabinet rusts, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting, and an analysis command is issued; The component grayscale analysis module uses a camera to collect images of the interior of the distribution cabinet with a high risk of rust, and calculates the grayscale mean Jph of the images of the interior of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ ; Component rust processing module, obtains the grayscale mean Jph of the internal image of the distribution cabinet α And the grayscale mean Jhj of each component feature map αδ , calculate the rust degree index Csd of each component αδ and the normal grayscale threshold ΔH of each element δ , according to the size relationship between the two, determine whether each component is rusted, and select the corresponding safety warning processing strategy; Among them, the use time Sy of the distribution cabinet is obtained based on the distribution cabinet work record j And humidity warning times Cs j , combined with the humidity Sd of the power distribution cabinet ij After linear normalization, the rust risk weight coefficients k1, k2 and k3 are calculated. The corresponding calculation formulas of the rust risk weight coefficients k1, k2 and k3 are as follows: Wherein, j represents the sequential number of all distribution cabinets, j=1, 2, ..., n, and n is a positive integer; Get the usage time Sy of the distribution cabinet based on the distribution cabinet work record j And humidity warning times Cs j After linear normalization, the rust risk index Wx of the distribution cabinet is calculated. j : When the distribution cabinet is rusted, the risk index is Wx j When >0, it indicates that the current distribution cabinet has a high risk of rusting and an analysis command is issued.

Images