A switch cabinet monitoring system and monitoring method thereof

Abstract

The present invention discloses a switch cabinet monitoring system and a monitoring method thereof, which belongs to the field of switch cabinet monitoring, and includes a self-checking module, a monitoring processing module, a communication module and a monitoring terminal, wherein the self-checking module is connected to the monitoring processing module, and the monitoring processing module communicates with the monitoring terminal via the communication module; the self-checking module is used to collect the state information of the switch cabinet, and send the state information of the switch cabinet, the operation information of the information acquisition module and the state information of the information acquisition module to the monitoring processing module; the monitoring processing module includes a component state parameter simulation unit, a component geometric model establishment unit, a simulation model establishment unit, a diagnosis unit and an alarm unit connected in sequence. The present invention adopts the above switch cabinet monitoring system and the monitoring method thereof, and only needs to set a camera module to monitor the operation state of the components in the switch cabinet, thereby simplifying the line layout.

Description

Technical Field

[0001] The present invention relates to the technical field of switch cabinet state monitoring, and in particular to a switch cabinet monitoring system and a monitoring method thereof. Background Art

[0002] As one of the important electrical equipment in the distribution network, the switchgear is mainly used to open and close, control and protect electrical equipment during the process of power generation, transmission, distribution and energy conversion in the power system. Its safe operation will directly affect people's work, study and quality of life.

[0003] At the same time, the switch cabinet is equipped with multiple electronic devices such as circuit breakers, isolating switches, load switches, operating mechanisms, transformers and various protective devices, which are prone to failure. Once a failure occurs, it will affect the normal power supply.

[0004] To solve the above problems, the traditional method generally adopts manual regular inspection, that is, using operation and maintenance personnel to inspect and test personnel to conduct regular random inspections. This method requires a lot of manpower and material resources, and the operation and maintenance personnel may have false reports and missed reports when conducting inspections. At the same time, traditional status detection and analysis methods include ultrasonic partial discharge, infrared temperature measurement, on-site environmental observation, etc. However, in recent years, with the continuous increase in the number of switch cabinets and the increase in equipment capacity, the traditional equipment inspection and maintenance methods can no longer meet the actual needs of the safe operation of modern power equipment. It is difficult to truly reflect the operating status and fault status of various types of power equipment, and there are great limitations.

[0005] To this end, the market has further emerged to replace regular maintenance with condition-based maintenance, which can avoid or reduce equipment damage and unplanned power outages caused by faults. Existing condition detection mostly adopts the form of arranging a large number of sensors and monitors in the switch cabinet, so there are problems such as redundant lines, chaotic management, inconvenient communication connections, and difficult maintenance for patrol personnel, which will lead to equipment loss, failures, low voltage quality, and poor stability of the distribution network due to untimely maintenance. Summary of the invention

[0006] In order to solve the above problems, the present invention provides a switch cabinet monitoring system and a monitoring method thereof, which only requires setting up a camera module to monitor the operating status of components in the switch cabinet, thereby simplifying the line layout.

[0007] A switch cabinet monitoring system includes a self-checking module, a monitoring processing module, a communication module and a monitoring terminal, wherein the self-checking module is connected to the monitoring processing module, and the monitoring processing module communicates with the monitoring terminal via the communication module;

[0008] The self-check module is used to collect the status information of the switch cabinet, and send the status information of the switch cabinet, the operation information of the information collection module and the status information of the information collection module to the monitoring processing module;

[0009] The monitoring and processing module includes a component state parameter simulation unit, a component geometric model establishment unit, a simulation model establishment unit, a diagnosis unit and an alarm unit which are connected in sequence, wherein the component state parameter simulation unit is used to simulate and parameterize the state information of the switch cabinet to obtain operation simulation parameters; the component model establishment unit is used to establish a geometric simulation model for the monitored component; the simulation model establishment unit is used to obtain a coupling simulation model based on the simulation parameters and the geometric simulation model; the diagnosis unit is used to compare the coupling simulation model after running for a set time with the initial coupling simulation model, and drive the alarm unit to send an alarm signal when the comparison result exceeds a set threshold.

[0010] Preferably, the self-inspection module includes a camera module and an image recognition unit which are vertically slidably arranged inside the switch cabinet through a linear module. The camera module includes an infrared camera and an RGB camera. The RGB camera is used to capture images of components inside the switch cabinet and send the component images to the image recognition unit; the image recognition unit is used to identify the components to be inspected in the captured component images; the infrared camera is used to capture the operating simulation parameters of the components to be monitored.

[0011] Preferably, the infrared camera and the RGB camera are both connected to the linear module via a mounting plate, and a lighting lamp and a charging power supply are also provided on the mounting plate. The lighting lamp, the infrared camera and the RGB camera are all electrically connected to the charging power supply via a time relay.

[0012] A monitoring method for a switch cabinet monitoring system comprises the following steps:

[0013] S1. Parameter initialization:

[0014] According to the camera range value of the camera module and the speed value of the linear module, the trigger time of the time relay is set so that within a travel range of the linear module, the image captured by the camera module covers all components in the switch cabinet;

[0015] S2, using a camera module to capture multiple local images in a travel interval of the linear module, and splicing the multiple local images in the same travel interval to obtain an overall image in the travel interval;

[0016] S3, identifying the components to be monitored based on the acquired overall image;

[0017] S4, establishing a coupled simulation model for the identified components to be inspected;

[0018] S5. Diagnose the coupled simulation model after running for a set time and the initial coupled simulation model, and drive the alarm unit to send out an alarm signal when the diagnosis result exceeds a set threshold.

[0019] Preferably, step S2 specifically includes the following steps:

[0020] S21. Extracting splicing features of the captured image based on a deep learning neural network model to obtain splicing features of the captured image;

[0021] S22, using the Euclidean distance to determine the similarity of the splicing features of the images taken at two adjacent moments, and deleting them when the similarity is lower than a set value, otherwise retaining them;

[0022] S23, stitching the images taken at two moments after being processed in step S22 to obtain a composite image.

[0023] Preferably, step S3 specifically includes the following steps:

[0024] S31, collecting existing image data of components to be monitored, and annotating and classifying them to form a data set for model training;

[0025] S32, training the deep learning network model using the labeled image data of the component to be monitored until convergence;

[0026] S32: Input the synthetic image obtained in step S2 into the deep learning network model to identify the components to be monitored.

[0027] Preferably, step S4 specifically includes the following steps:

[0028] S41, parameterizing the state information of the switch cabinet to obtain operation simulation parameters;

[0029] S42. Establishing a geometric simulation model for the identified components to be monitored

[0030] S43, obtaining a coupled simulation model according to the simulation parameters and the geometric simulation model.

[0031] Preferably, in step S41, the acquired operation simulation parameters include thermal parameter variable values ​​of the components to be monitored;

[0032] The specific steps to obtain it are as follows:

[0033] Temperature rise tests will be conducted on the monitored components in different working environments, working conditions under different workloads and when failures occur, to extract the thermal parameter variables of the monitored components.

[0034] The present invention has the following beneficial effects:

[0035] It is only necessary to set up a camera module to monitor the operating status of the components inside the switch cabinet, which simplifies the line layout.

[0036] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure is a structural block diagram of a switch cabinet monitoring system of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages disclosed in the embodiments of the present invention clearer, the embodiments of the present invention are further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention and are not intended to limit the embodiments of the present invention. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions.

[0039] It should be noted that the terms "include", "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or devices.

[0040] Like reference numerals and letters denote similar items in the following drawings, and thus, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0041] In the description of the present invention, it should be noted that the terms "upper", "lower", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, or are directions or positional relationships in which the product of the invention is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the present invention.

[0042] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "setting", "installation" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0043] like Figure 1As shown, a switch cabinet monitoring system includes a self-checking module, a monitoring processing module, a communication module and a monitoring terminal, wherein the self-checking module is connected to the monitoring processing module, and the monitoring processing module communicates with the monitoring terminal via the communication module; the self-checking module is used to collect the status information of the switch cabinet, and send the status information of the switch cabinet, the operation information of the information acquisition module and the status information of the information acquisition module to the monitoring processing module; the monitoring processing module includes a component status parameter simulation unit, a component geometric model establishment unit, a simulation model establishment unit, a diagnosis unit and an alarm unit connected in sequence, wherein the component status parameter simulation unit is used to simulate and parameterize the status information of the switch cabinet to obtain the operation simulation parameters; the component model establishment unit is used to establish a geometric simulation model for the component to be monitored; the simulation model establishment unit is used to obtain a coupling simulation model according to the simulation parameters and the geometric simulation model; the diagnosis unit is used to compare the coupling simulation model after the set operation time with the initial coupling simulation model, and drive the alarm unit to send an alarm signal when the comparison result exceeds the set threshold value. In this embodiment, the alarm unit is an audible and visual alarm, which realizes the on-site audible and visual alarm, and at the same time remotely transmits the alarm signal to the monitoring terminal via the communication module for storage.

[0044] The self-inspection module includes a camera module and an image recognition unit which are vertically slidably arranged inside the switch cabinet via a linear module. The camera module includes an infrared camera and an RGB camera. The RGB camera is used to collect images of components inside the switch cabinet and send the component images to the image recognition unit. The image recognition unit is used to identify the components to be detected in the collected component images. The infrared camera is used to collect the operation simulation parameters of the components to be monitored. The infrared camera and the RGB camera are both connected to the linear module via a mounting plate. A lighting lamp and a charging power supply are also arranged on the mounting plate. The lighting lamp, the infrared camera and the RGB camera are all electrically connected to the charging power supply via a time relay. By setting the time relay to intermittently trigger the lighting lamp, the infrared camera and the RGB camera, energy can be saved. By setting the trigger time of the time relay, repeated shooting of components can be reduced, thereby reducing the processing of repeated data.

[0045] A monitoring method for a switch cabinet monitoring system comprises the following steps:

[0046] S1. Parameter initialization:

[0047] According to the camera range value of the camera module and the speed value of the linear module, the trigger time of the time relay is set so that within a travel range of the linear module, the image captured by the camera module covers all components in the switch cabinet;

[0048] S2, using a camera module to capture multiple local images in a travel interval of the linear module, and splicing the multiple local images in the same travel interval to obtain an overall image in the travel interval;

[0049] Step S2 specifically includes the following steps:

[0050] S21. Extracting splicing features of the captured image based on a deep learning neural network model to obtain splicing features of the captured image;

[0051] S22, using the Euclidean distance to determine the similarity of the splicing features of the images taken at two adjacent moments, and deleting them when the similarity is lower than a set value, otherwise retaining them;

[0052] S23, stitching the images taken at two moments after being processed in step S22 to obtain a composite image.

[0053] S3, identifying the components to be monitored based on the acquired overall image;

[0054] Step S3 specifically includes the following steps:

[0055] S31, collecting existing image data of components to be monitored, and annotating and classifying them to form a data set for model training;

[0056] S32, training the deep learning network model using the labeled image data of the component to be monitored until convergence;

[0057] S32: Input the synthetic image obtained in step S2 into the deep learning network model to identify the components to be monitored.

[0058] S4, establishing a coupled simulation model for the identified components to be inspected;

[0059] Step S4 specifically includes the following steps:

[0060] S41, parameterizing the state information of the switch cabinet to obtain operation simulation parameters;

[0061] In step S41, the obtained operation simulation parameters include the thermal parameter variable values ​​of the components to be monitored;

[0062] The specific steps to obtain it are as follows:

[0063] Temperature rise tests will be conducted on the monitored components in different working environments, working conditions under different workloads and when failures occur, to extract the thermal parameter variables of the monitored components.

[0064] S42. Establishing a geometric simulation model for the identified components to be monitored

[0065] S43, obtaining a coupled simulation model according to the simulation parameters and the geometric simulation model.

[0066] S5. Diagnose the coupled simulation model after running for a set time and the initial coupled simulation model, and drive the alarm unit to send out an alarm signal when the diagnosis result exceeds a set threshold.

[0067] Therefore, the present invention adopts the above-mentioned switch cabinet monitoring system and monitoring method, and only needs to set up a camera module to monitor the operating status of the components in the switch cabinet, which simplifies the line layout.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A switch cabinet monitoring system, characterized in that: It includes a self-checking module, a monitoring processing module, a communication module and a monitoring terminal, wherein the self-checking module is connected to the monitoring processing module, and the monitoring processing module communicates with the monitoring terminal via the communication module; The self-check module is used to collect the status information of the switch cabinet, and send the status information of the switch cabinet, the operation information of the information collection module and the status information of the information collection module to the monitoring processing module; The monitoring processing module includes a component state parameter simulation unit, a component geometric model establishment unit, a simulation model establishment unit, a diagnosis unit and an alarm unit connected in sequence, wherein the component state parameter simulation unit is used to simulate and parameterize the state information of the switch cabinet to obtain the operation simulation parameters; the component model establishment unit is used to establish a geometric simulation model of the monitored component; the simulation model establishment unit is used to obtain a coupled simulation model according to the simulation parameters and the geometric simulation model; The diagnosis unit is used to compare the coupling simulation model after running for a set time with the initial coupling simulation model, and drive the alarm unit to send an alarm signal when the comparison result exceeds a set threshold; The self-inspection module includes a camera module and an image recognition unit which are vertically slidably arranged inside the switch cabinet via a linear module. The camera module includes an infrared camera and an RGB camera. The RGB camera is used to collect images of components inside the switch cabinet and send the component images to the image recognition unit. The image recognition unit is used to recognize the component to be detected in the collected component image; The infrared camera is used to collect the operation simulation parameters of the components to be monitored; The infrared camera and the RGB camera are both connected to the linear module via a mounting plate, and a lighting lamp and a charging power supply are also provided on the mounting plate. The lighting lamp, the infrared camera and the RGB camera are all electrically connected to the charging power supply via a time relay; A monitoring method for a switch cabinet monitoring system comprises the following steps: S1. Parameter initialization: According to the camera range value of the camera module and the speed value of the linear module, the trigger time of the time relay is set so that within a travel range of the linear module, the image captured by the camera module covers all components in the switch cabinet; S2, using a camera module to capture multiple local images in a travel interval of the linear module, and splicing the multiple local images in the same travel interval to obtain an overall image in the travel interval; Step S2 specifically includes the following steps: S21. Extracting splicing features of the captured image based on a deep learning neural network model to obtain splicing features of the captured image; S22, using the Euclidean distance to determine the similarity of the splicing features of the images taken at two adjacent moments, and deleting them when the similarity is lower than a set value, otherwise retaining them; S23, stitching the images taken at two moments after being processed in step S22 to obtain a composite image; S3, identifying the components to be monitored based on the acquired overall image; S4, establishing a coupled simulation model for the identified components to be inspected; S5. Diagnose the coupled simulation model after running for a set time and the initial coupled simulation model, and drive the alarm unit to send out an alarm signal when the diagnosis result exceeds a set threshold.

2. A switch cabinet monitoring system according to claim 1, characterized in that: Step S3 specifically includes the following steps: S31, collecting existing image data of components to be monitored, and annotating and classifying them to form a data set for model training; S32, training the deep learning network model using the labeled image data of the component to be monitored until convergence; S32: Input the synthetic image obtained in step S2 into the deep learning network model to identify the components to be monitored.

3. A switch cabinet monitoring system according to claim 2, characterized in that: Step S4 The specific steps include: S41, parameterizing the state information of the switch cabinet to obtain operation simulation parameters; S42. Establishing a geometric simulation model for the identified components to be monitored S43, obtaining a coupled simulation model according to the simulation parameters and the geometric simulation model.

4. A switch cabinet monitoring system according to claim 3, characterized in that: In step S41, the obtained operation simulation parameters include the thermal parameter variable values ​​of the components to be monitored; The specific steps to obtain it are as follows: Temperature rise tests will be conducted on the monitored components in different working environments, working conditions under different workloads and when failures occur, to extract the thermal parameter variables of the monitored components.

Images