A switch cabinet health status evaluation method and device
By analyzing the historical sensor data of the switch cabinet, building a health evaluation model, evaluating the current health, solving the problem of unreasonable maintenance time in the existing technology, and achieving fine management and resource optimization of the switch cabinet.
Patent Information
- Application Number
- CN202411241367.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-05
AI Technical Summary
The health status of the switch cabinet cannot be effectively grasped in the prior art, resulting in unreasonable maintenance time and wasted resources and costs.
By acquiring and analyzing the historical sensor data of the switch cabinet, building a health evaluation model, evaluating the health of the current time point, and determining whether maintenance is needed.
It has achieved a fine maintenance plan based on the health of the switch cabinet, avoiding unnecessary maintenance and waste, and improving the targeted and efficient maintenance.
Smart Images

Figure CN118760864B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of electrical equipment, and in particular to a method and a device for evaluating the health status of a switch cabinet. Background Art
[0002] Switchgear is an important part of the power system, which contains many high-voltage electrical equipment. In addition, the operating environment of switchgear is complex and is greatly affected by environmental factors such as temperature and humidity. Therefore, it is necessary to monitor the switch to detect abnormal conditions in time, so as to take measures to deal with them quickly, avoid sudden equipment failures, and improve the reliability and safety of the power system.
[0003] The existing switch cabinet maintenance is generally carried out regularly, for example, once every three months or six months. However, the usage conditions of different switch cabinets are actually different. Some switch cabinets work in a more suitable environment, so the actual maintenance time interval required is longer, while some switch cabinets work in a harsh environment and a high load environment, so the actual maintenance time required is shorter. Therefore, the use of fixed maintenance time in the prior art will cause some switch cabinets to not receive the necessary maintenance, while the maintenance time of some switch cabinets is too frequent, wasting maintenance resources and costs. In view of this, it is necessary to grasp the health status of the switch cabinet and provide it to maintenance personnel for reference. However, in the prior art, there is no switch cabinet health status evaluation method specifically provided to maintenance personnel. Summary of the invention
[0004] In view of this, an object of the present invention is to provide a method and device for evaluating the health status of a switch cabinet, so as to solve the problem in the prior art that it is impossible to determine whether the switch cabinet needs maintenance.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions:
[0006] A switch cabinet health status evaluation method of the present invention comprises the following steps:
[0007] Acquire historical sensor data of the switch cabinet in multiple historical maintenance cycles, wherein the historical sensor data includes values of sensor parameters corresponding to multiple detection time points in the historical maintenance cycle, and the sensor parameters include temperature, humidity, dust accumulation, main line current, main line voltage, and fan operation noise level;
[0008] Performing distribution characteristic analysis on the sensor data of the plurality of maintenance cycles, and taking the sensor parameters satisfying the target characteristics as the target parameters, wherein the target characteristics include: the value of the sensor parameter increases or decreases over time;
[0009] Building a health evaluation model based on the values of the target parameters of the switch cabinet in multiple maintenance cycles, wherein the health evaluation model represents the corresponding relationship between the value of the target parameter and the health of the switch cabinet;
[0010] The value of the target parameter at the current time point is obtained, and the health of the switch cabinet at the current time point is determined based on the value of the target parameter at the current time point and the health assessment model.
[0011] In one embodiment of the present application, it also includes:
[0012] The health of the switch cabinet at the current time point is compared with a preset threshold, and when the health of the switch cabinet at the current time point is greater than the preset threshold, an alarm message is sent to the target object.
[0013] In one embodiment of the present application, the process of obtaining the dust accumulation amount includes:
[0014] Acquire an image of a target area in the switch cabinet, wherein the target area includes a circuit board, a heat sink, a plug-in part, and an area where a vent is located;
[0015] Converting the image of the target area into a grayscale image;
[0016] Dust accumulation is identified on the grayscale image based on a pre-built dust recognition model to obtain dust accumulation, wherein the dust recognition model is obtained by training an artificial neural network with image samples of the interior of the switch cabinet with different degrees of dust accumulation.
[0017] In one embodiment of the present application, performing distribution characteristic analysis on the sensor data of the multiple maintenance cycles includes:
[0018] Performing distribution feature analysis on sensor data of a single cycle, wherein the distribution features of sensor data of a single cycle include increasing trend, decreasing trend and no increasing or decreasing trend;
[0019] When the value trend of the sensor parameter in the historical maintenance cycle that exceeds the preset proportional threshold is decreasing, it is determined that the value trend of the sensor parameter is decreasing; when the value trend of the sensor parameter in the historical maintenance cycle that exceeds the preset proportional threshold is increasing, it is determined that the value trend of the sensor parameter is increasing.
[0020] In one embodiment of the present application, the distribution characteristics analysis of the sensor data of a single cycle includes:
[0021] Mapping the values of the sensor parameters at multiple detection time points in a single historical maintenance cycle into a two-dimensional coordinate system to obtain data coordinates, wherein the abscissa of the two-dimensional coordinate system is time and the ordinate is the value;
[0022] Calculate the data coordinates in front The average value and average time of the data points, and the The average and average time of the data points are based on the previous The average value and average time of the data points form the starting reference point , and based on the The average of the data points and the average time end reference point ;
[0023] Use a straight line to separate the starting reference point and the end reference point Connect to get the trend reference line ;
[0024] Calculate the coordinates of each data point and the trend reference line The vertical difference, where the trend is above the reference line The data points and the trend reference line The vertical difference is positive and below the trend reference line The data points and the trend reference line The vertical difference is negative;
[0025] Calculate the variance of multiple vertical difference values, when the variance is less than a preset threshold, and When , it is determined that the value trend of the sensor parameter of the current historical maintenance cycle is decreasing; when the variance is less than the preset threshold, and When , the value trend of the sensor parameter in the historical maintenance cycle is determined to be increasing, where is a scale parameter with a value greater than 1, and Starting reference point The value of End reference point The value of .
[0026] In one embodiment of the present application, a health assessment model is constructed based on the values of target parameters of the switch cabinet in multiple maintenance cycles, including:
[0027] Calculate each target parameter in Maintenance cycle rate of change ,in, ,in, For the Starting reference point for a maintenance cycle The value of For the End reference point of a maintenance cycle The value of For the The duration of each maintenance cycle;
[0028] Determine a relevance weight for each target parameter based on a change rate of each target parameter over a plurality of maintenance cycles;
[0029] Calculate the sum of the relevance weights of all target parameters, and calculate the ratio of the relevance weight of the target parameter to the sum of the weights;
[0030] When the ratio of the relevance weight of any target parameter to the total weight exceeds a preset ratio value, a single-factor health evaluation model is established based on the target parameter whose ratio exceeds the preset ratio value;
[0031] When the ratio of the relevance weight of any target parameter to the total weight exceeds a preset ratio value, a multi-factor health evaluation model is established based on the relevance weights of multiple target parameters.
[0032] In one embodiment of the present application, the relevance weight of each target parameter is determined based on the change rate of each target parameter in multiple maintenance cycles, including:
[0033] Calculate target parameters Rate of change over multiple maintenance cycles The average and variance ;
[0034] Based on the average and the variance Calculate the relevance index of the target parameter , ,in, is the first weight, is the second weight;
[0035] Relevance index for all target parameters Perform normalization to obtain the relevance weight of each target parameter .
[0036] In one embodiment of the present application, a single-factor health assessment model is established based on a target parameter whose ratio exceeds a preset ratio value, including:
[0037] Obtain the reference value of the target parameter when the ratio exceeds the preset ratio value during maintenance and the average value of the starting reference point of multiple maintenance cycles ;
[0038] Based on the reference value And the average value of the starting reference points of multiple maintenance cycles is used to construct a single-factor health evaluation model, wherein the mathematical expression of the health evaluation model is:
[0039]
[0040] in, The value of the target parameter at the current time point whose ratio exceeds the preset ratio value. The health of the switchgear.
[0041] In one embodiment of the present application, a multi-factor health assessment model is established based on the correlation weights of multiple target parameters, including:
[0042] Get reference values of multiple target parameters during maintenance and the average value of the starting reference point of multiple maintenance cycles for multiple target parameters ;
[0043] Reference values based on multiple target parameters during maintenance And the average values of the starting reference points of multiple maintenance cycles of multiple target parameters are used to construct a multi-factor health assessment model, wherein the mathematical expression of the health assessment model is:
[0044]
[0045] in, For the The value of the target parameter at the current time point, The health of the switchgear, is the number of target parameters.
[0046] The present application also provides a switch cabinet health status evaluation device, comprising:
[0047] An acquisition module is used to acquire historical sensor data of the switch cabinet in multiple historical maintenance cycles, wherein the historical sensor data includes values of sensor parameters at multiple detection time points in the corresponding maintenance cycle, and the sensor parameters include temperature, humidity, dust accumulation, main line current, main line voltage, and fan operation noise level;
[0048] A feature analysis module, used to perform distribution feature analysis on the sensor data of the plurality of maintenance cycles, and use sensor parameters that meet target features as target parameters, wherein the target features include: a value of the sensor parameter that increases or decreases over time;
[0049] A model building module, used to build a health evaluation model based on the values of the target parameters of the switch cabinet in multiple maintenance cycles, wherein the health evaluation model represents the corresponding relationship between the value of the target parameter and the health of the switch cabinet;
[0050] The evaluation module is used to obtain the value of the target parameter at the current time point, and determine the health of the switch cabinet at the current time point based on the value of the target parameter at the current time point and the health evaluation model. The present invention also provides a storage medium, which stores a computer program, and when the computer program is loaded and executed by a processor, a switch cabinet health status evaluation method as described above is implemented.
[0051] The present invention also provides an electronic device, comprising: a processor and a memory; wherein the memory is used to store a computer program; the processor is used to load and execute the computer program so that the electronic device executes a switch cabinet health status evaluation method as described above.
[0052] The beneficial effects of the present invention are as follows: a method and device for evaluating the health status of a switch cabinet of the present invention obtains target parameters related to maintenance by performing trend analysis on historical sensor data. In the present application, the target parameters can be used as indicators to measure whether the switch cabinet needs maintenance. Therefore, a health evaluation model is constructed based on the target parameters, so that the value of the target parameters at the current time point can be evaluated to judge the health of the switch cabinet at the current time point. It is used as a criterion for judging whether the switch cabinet needs maintenance. The present application can help maintenance personnel understand the health status of the switch cabinet. For switch cabinets in various working environments, the health status can be determined separately according to their target parameters, so that a maintenance plan can be formulated according to their health status instead of regular calculations, so as to achieve fine management of the switch cabinet. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:
[0054] Figure 1 is a flow chart of a switch cabinet health status evaluation method shown in an embodiment of the present application;
[0055] Figure 2 It is a structural diagram of a switch cabinet health status evaluation device shown in an embodiment of the present application. DETAILED DESCRIPTION
[0056] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.
[0057] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show the layers related to the present invention rather than being drawn according to the number, shape and size of the layers in actual implementation. In actual implementation, the type, quantity and proportion of each layer may be changed arbitrarily, and the layer layout may also be more complicated.
[0058] In the following description, numerous details are discussed to provide a more thorough explanation of embodiments of the present invention; however, it is apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details.
[0059] In this application, temperature sensors, humidity sensors, dust concentration sensors, cameras, current transformers, voltage transformers, microphones and other sensors are pre-installed inside the switch cabinet to collect various parameters of the switch cabinet when it is working.
[0060] In each maintenance cycle in the early stage, various parameters in the switch cabinet will be collected regularly, which will serve as the basic data for building a health evaluation model. In this application, the intrinsic relationship between various parameters and switch cabinet maintenance is found based on the above historical data. In this way, reference guidance work can be performed in subsequent maintenance work. The specific process is as follows:
[0061] Figure 1 is a flow chart of a switch cabinet health status evaluation method shown in an embodiment of the present application. Figure 1 As shown: A switch cabinet health status evaluation method of this embodiment may include steps S110 to S140:
[0062] S110, obtaining historical sensor data of the switch cabinet in multiple historical maintenance cycles, wherein the historical sensor data includes values of sensor parameters corresponding to multiple detection time points in the historical maintenance cycle, and the sensor parameters include temperature, humidity, dust accumulation, main line current, main line voltage, and fan operation noise level;
[0063] Among them, before conducting a health evaluation, this application needs to collect a large amount of historical data to build an evaluation model. Generally speaking, as the operating time of the switch cabinet increases, multiple parameters may change. These changes are usually related to the aging, wear, environmental factors and changes in electrical performance of the equipment. Specifically including:
[0064] (1) Temperature and humidity. When the switch cabinet is working for a long time, dust accumulates on the heat dissipation port, making it difficult for hot air to be discharged in time. Heat accumulation causes the internal temperature to rise. At the same time, the performance of the sealing strip is reduced, which easily causes water vapor to enter the switch cabinet, causing the humidity to rise.
[0065] (2) Dust accumulation: After long-term operation of the switch cabinet, dust will accumulate on the surface of insulators and busbars, radiators and fan blades, terminals and connectors, internal corners and gaps, cabinet doors and side panels, vents and heat dissipation holes, mounting bases and brackets, etc. This will increase the heat generated by internal components and weaken their performance.
[0066] (3) The main line current and main line voltage in the switch cabinet may change due to temperature or component aging.
[0067] (4) Fan operating noise level. As the temperature inside the switch cabinet rises, in order to enhance heat dissipation, the corresponding fan operating noise level will also increase under the control of the temperature control system.
[0068] In this application, temperature, humidity, main line current, main line voltage, and fan operation noise level can be directly collected by sensors. However, dust accumulation cannot be directly collected by sensors. Therefore, this application uses a deep learning recognition model to identify the dust accumulation in the switch cabinet. Specifically, it includes:
[0069] S111, acquiring an image of a target area in the switch cabinet, wherein the target area includes an area where a circuit board, a heat sink, a plug-in part, and a vent are located;
[0070] Among them, dust accumulation in the circuit board, heat sink, plug-in part and ventilation opening area will affect the performance of components inside the switch cabinet. Therefore, the camera of this application mainly monitors these locations.
[0071] S112, converting the image of the target area into a grayscale image; in addition, high-pass filtering is also required.
[0072] S113, performing dust accumulation recognition on the grayscale image based on a pre-built dust recognition model to obtain dust accumulation, wherein the dust recognition model is obtained by training an artificial neural network with image samples of the interior of the switch cabinet with different degrees of dust accumulation.
[0073] Specifically, the training process of the dust recognition model includes:
[0074] Collect a large number of sample images, wherein the sample images include images of dust accumulation inside the switch cabinet;
[0075] Convert the sample image to grayscale and high-pass filter it to preserve the outlines of the dust areas.
[0076] The processed images are labeled, for example, 10%, 20%... The more dust is accumulated, the larger the labeled number is.
[0077] The processed images are divided into a training set, a test set and a validation set, and the artificial neural network is trained to obtain a dust recognition model.
[0078] S120, performing distribution characteristic analysis on the sensor data of the plurality of maintenance cycles, and taking the sensor parameters satisfying the target characteristics as the target parameters, wherein the target characteristics include: the value of the sensor parameter increases or decreases over time;
[0079] In this application, by analyzing the distribution characteristics of sensor data of multiple maintenance cycles, we can find out which sensor parameters will change unidirectionally with the increase of usage time, so as to serve as a standard for measuring the health of the switch cabinet.
[0080] For example, as dust accumulates, the temperature will gradually rise after a period of time (the cooling fan cannot dissipate heat in time), so it tends to increase. In order to correspond to the gradually rising internal temperature, the fan will gradually increase its power, causing the magnitude of the fan running noise to increase (but it may also be affected by the air conditioning system). Therefore, although in theory the above sensor parameters can be used as reference factors to measure the health of the switch cabinet. However, due to external conditions, the values of some sensor parameters cannot show the theoretical unidirectional trend and cannot be used as reliable evaluation factors.
[0081] Therefore, in order to find out which parameter factors can be used as reliable evaluation factors, this application adopts the following process to perform distribution feature analysis, specifically including:
[0082] S121, performing distribution feature analysis on the sensor data of a single period, wherein the distribution features of the sensor data of a single period include an increasing trend, a decreasing trend, and no increasing or decreasing trend;
[0083] S122, when the value trend of the sensor parameter in the historical maintenance period that exceeds the preset proportion threshold is decreasing, determine that the value trend of the sensor parameter is decreasing; when the value trend of the sensor parameter in the historical maintenance period that exceeds the preset proportion threshold is increasing, determine that the value trend of the sensor parameter is increasing.
[0084] First, perform a single-cycle trend analysis on each sensor parameter, and then perform statistics. If a certain parameter has an increasing or decreasing trend in more than 95% of the cycles, it can be determined that under the current environmental conditions, this sensor parameter is likely to have an increasing or decreasing trend in a maintenance cycle. This avoids the situation where some sensor parameters are easily affected by external conditions and cannot be used as reference factors.
[0085] The trend analysis method for a single period is as follows:
[0086] S1211, mapping the values of the sensor parameters at multiple detection time points in a single historical maintenance cycle to a two-dimensional coordinate system to obtain data coordinates, wherein the abscissa of the two-dimensional coordinate system is time and the ordinate is the value; so as to facilitate data statistics and processing;
[0087] S1212, calculate the front of the data coordinates The average value and average time of the data points, and the The average and average time of the data points are based on the previous The average value and average time of the data points form the starting reference point , and based on the The average of the data points and the average time end reference point ;
[0088] This application calculates the average of the first 3 data points as the starting reference point for the current maintenance cycle The vertical axis of the graph is the average time of the graph, and the average time is used as the starting reference point. This application calculates the average of the last three data points as the end reference point of the current maintenance cycle. The vertical axis of the The abscissa of . Taking the average value can effectively reduce the reference point error caused by the sensor data error.
[0089] S1213, using a straight line to separate the starting reference point and the end reference point Connect to get the trend reference line ;
[0090] S1214, calculating the distance between each data point in the data coordinates and the trend reference line The vertical difference, where the trend is above the reference line The data points and the trend reference line The vertical difference is positive and below the trend reference line The data points and the trend reference line The vertical difference is negative;
[0091] The vertical difference is the value of each data point to the trend reference line The vertical difference of all data points is used to reflect the distance of multiple data points along the trend reference line. The degree of distribution.
[0092] S1215, calculating the variance of the plurality of vertical difference values, where the variance is less than a preset threshold, and When , it is determined that the value trend of the sensor parameter of the current historical maintenance cycle is decreasing; when the variance is less than the preset threshold, and When , the value trend of the sensor parameter in the historical maintenance cycle is determined to be increasing, where is a scale parameter with a value greater than 1, and Starting reference point The value of End reference point The value of .
[0093] This application determines multiple data points along the trend reference line based on variance The degree of distribution. If the variance is small, it means that multiple data points are along the trend reference line. If the variance is large, it means that the distribution of multiple data points is disorderly and irregular, and it is impossible to determine the upward or downward trend.
[0094] In addition, in order to ensure that multiple data points have an obvious upward or downward trend, this application sets two screening conditions, namely or . and the variance is less than a preset threshold.
[0095] S130, constructing a health evaluation model based on the values of the target parameters of the switch cabinet in multiple maintenance cycles, wherein the health evaluation model represents the corresponding relationship between the value of the target parameter and the health of the switch cabinet;
[0096] After the target parameters are screened, in order to quickly evaluate the health of the switch cabinet, this application performs health evaluation by constructing a health evaluation model.
[0097] Specifically include:
[0098] S1301, calculate each target parameter in the Maintenance cycle rate of change ,in, ,in, For the Starting reference point for a maintenance cycle The value of For the End reference point of a maintenance cycle The value of For the The duration of each maintenance cycle;
[0099] Different target parameters have different values and regularity during the maintenance cycle. Therefore, in order to unify the dimensions, this application calculates the value of each target parameter in the first Maintenance cycle rate of change , where the rate of change Refers to the rate of change per unit time. For example, 2% / month. Then based on its rate of change and regularity to determine the relevance weights of different target parameters.
[0100] S1302, determining a relevance weight of each target parameter based on a change rate of each target parameter in a plurality of maintenance cycles;
[0101] The process of determining the relevance weight includes:
[0102] S13021, calculate target parameters Rate of change over multiple maintenance cycles The average and variance ;
[0103] S13022, based on the average and the variance Calculate the relevance index of the target parameter , ,in, is the first weight, is the second weight;
[0104] Among them, the rate of change The larger the target parameter is, the As the usage time increases, it is easier to be discovered. Therefore, the higher the weight, the smaller the variance, which means the rate of change The more stable it is, the more regular it is. Therefore, this application introduces the change rate and the rate of change The variance is used to calculate the correlation.
[0105] S13023, correlation index for all target parameters Perform normalization to obtain the relevance weight of each target parameter .
[0106] Finally, normalization is performed so that all the correlation weights The sum is 1, which is convenient for subsequent processing and calculation.
[0107] S1303, calculating the sum of the relevance weights of all target parameters, and calculating the ratio of the relevance weights of the target parameters to the sum of the weights;
[0108] S1304, when the ratio of the relevance weight of any target parameter to the total weight exceeds a preset ratio value, a single-factor health assessment model is established based on the target parameter whose ratio exceeds the preset ratio value;
[0109] In some cases, if the relevance weight of a target parameter is particularly high, accounting for more than 50%, then the model can be simplified and a single-factor model can be established. While ensuring the accuracy of the evaluation, the model is concise and not affected by other factors.
[0110] (1) The construction methods of the single factor model include:
[0111] (1-1) Obtain reference values for target parameters whose ratios exceed the preset ratios during maintenance and the average value of the starting reference point of multiple maintenance cycles ;
[0112] (1-2) Based on the reference value And the average value of the starting reference points of multiple maintenance cycles is used to construct a single-factor health evaluation model, wherein the mathematical expression of the health evaluation model is:
[0113]
[0114] in, The value of the target parameter at the current time point whose ratio exceeds the preset ratio value. The health of the switchgear.
[0115] Among them, due to the average It is determined based on the typical value at the beginning of each maintenance cycle. The beginning of each maintenance cycle is also the end of the previous maintenance cycle (that is, the completion of the previous maintenance). Therefore, the performance indicators of the switch cabinet just after maintenance are almost the same, so the average value All are for reference only. Determined by expert opinion.
[0116] Represents: The value of the target parameter changes from the beginning of the maintenance period When the switch is damaged, it is likely that maintenance will be required. It indicates the actual change of the target parameter value compared with the initial value. The ratio of the two can be used to know the usage degree (percentage), and then the difference between them and 1 can be used to get the health degree.
[0117] S1305: When the ratio of the relevance weight to the total weight of any target parameter does not exceed a preset ratio value, a multi-factor health assessment model is established based on the relevance weights of multiple target parameters.
[0118] (2) The construction methods of multi-factor models include:
[0119] (2-1) Obtain reference values for multiple target parameters during maintenance and the average value of the starting reference point of multiple maintenance cycles for multiple target parameters ;
[0120] (2-2) Reference values based on multiple target parameters during maintenance And the average values of the starting reference points of multiple maintenance cycles of multiple target parameters are used to construct a multi-factor health assessment model, wherein the mathematical expression of the health assessment model is:
[0121]
[0122] in, For the The value of the target parameter at the current time point, The health of the switchgear, is the number of target parameters.
[0123] The principle of the multi-factor model is the same as that of the single-factor model, except that the weights calculated in the previous article are introduced. The weighted sum of the usage levels corresponding to the various target parameters is taken to obtain the overall usage percentage. Finally, the difference between the sum and 1 is used to obtain the health level.
[0124] S140, obtaining a value of a target parameter at a current time point, and determining a health of the switch cabinet at the current time point based on the value of the target parameter at the current time point and the health evaluation model.
[0125] Specifically, the health of the switch cabinet at the current time point can be determined by substituting the value of the target parameter at the current time point into the corresponding formula.
[0126] S150, comparing the health of the switch cabinet at the current time point with a preset threshold, and sending an alarm message to a target object when the health of the switch cabinet at the current time point is greater than the preset threshold.
[0127] Finally, if the health level is less than 10%, an alarm message can be sent to the maintenance personnel to prompt that the current switch cabinet needs maintenance.
[0128] A method for evaluating the health status of a switch cabinet of the present invention performs trend analysis on historical sensor data to obtain target parameters related to maintenance. In the present application, the target parameters can be used as indicators to measure whether the switch cabinet needs maintenance. Therefore, a health evaluation model is constructed based on the target parameters, so that the value of the target parameters at the current time point can be evaluated to determine the health of the switch cabinet at the current time point. This is used as a criterion for determining whether the switch cabinet needs maintenance. The present application can help maintenance personnel understand the health status of the switch cabinet. For switch cabinets in various working environments, the health status can be determined separately according to their target parameters, so that a maintenance plan can be formulated based on their health status instead of regular calculations, thereby achieving fine management of the switch cabinet.
[0129] The present application also provides a switch cabinet health status evaluation device, comprising:
[0130] An acquisition module is used to acquire historical sensor data of the switch cabinet in multiple historical maintenance cycles, wherein the historical sensor data includes values of sensor parameters at multiple detection time points in the corresponding maintenance cycle, and the sensor parameters include temperature, humidity, dust accumulation, main line current, main line voltage, and fan operation noise level;
[0131] A feature analysis module, used to perform distribution feature analysis on the sensor data of the plurality of maintenance cycles, and use sensor parameters that meet target features as target parameters, wherein the target features include: a value of the sensor parameter that increases or decreases over time;
[0132] A model building module, used to build a health evaluation model based on the values of the target parameters of the switch cabinet in multiple maintenance cycles, wherein the health evaluation model represents the corresponding relationship between the value of the target parameter and the health of the switch cabinet;
[0133] The evaluation module is used to obtain the value of the target parameter at the current time point, and determine the health of the switch cabinet at the current time point based on the value of the target parameter at the current time point and the health evaluation model. The present invention also provides a storage medium, which stores a computer program, and when the computer program is loaded and executed by a processor, a switch cabinet health status evaluation method as described above is implemented.
[0134] A switch cabinet health status evaluation device of the present invention obtains target parameters related to maintenance by performing trend analysis on historical sensor data. In the present application, the target parameters can be used as indicators to measure whether the switch cabinet needs maintenance. Therefore, a health evaluation model is constructed based on the target parameters, so that the value of the target parameters at the current time point can be evaluated to judge the health of the switch cabinet at the current time point. It is used as a criterion for judging whether the switch cabinet needs maintenance. The present application can help maintenance personnel understand the health status of the switch cabinet. For switch cabinets in various working environments, the health status can be judged separately according to their target parameters, so that a maintenance plan can be formulated according to their health status instead of regular calculations, so as to achieve fine management of the switch cabinet.
[0135] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, any one of the methods in this embodiment is implemented, wherein the method is the execution logic of this system.
[0136] This embodiment also provides an electronic terminal, including: a processor and a memory;
[0137] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.
[0138] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.
[0139] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes each step of the above method.
[0140] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0141] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0142] In the above-mentioned embodiments, although the present invention has been described in conjunction with the specific embodiments of the present invention, many replacements, modifications and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. The embodiments of the present invention are intended to cover all such replacements, modifications and variations falling within the broad scope of the appended claims.
[0143] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.
Claims
1. A switchgear health status evaluation method, It is characterized in that Includes steps: Acquire historical sensor data of the switch cabinet in multiple historical maintenance cycles, wherein the historical sensor data includes values of sensor parameters corresponding to multiple detection time points in the historical maintenance cycle, and the sensor parameters include temperature, humidity, dust accumulation, main line current, main line voltage, and fan operation noise level; Performing distribution characteristic analysis on the sensor data of the multiple maintenance cycles, and taking the sensor parameters that meet the target characteristics as target parameters, wherein the target characteristics include: the value of the sensor parameter increases or decreases over time; performing distribution characteristic analysis on the sensor data of the multiple maintenance cycles, including: performing distribution characteristic analysis on the sensor data of a single cycle, wherein the distribution characteristics of the sensor data of a single cycle include increasing trend, decreasing trend and no increasing or decreasing trend; when the value trend of the sensor parameter of the historical maintenance cycle exceeding a preset proportion threshold is decreasing, determining that the value trend of the sensor parameter is decreasing; when the value trend of the sensor parameter of the historical maintenance cycle exceeding a preset proportion threshold is increasing, determining that the value trend of the sensor parameter is increasing; performing distribution characteristic analysis on the sensor data of a single cycle, including: mapping the values of the sensor parameters of multiple detection time points in a single historical maintenance cycle to a two-dimensional coordinate system to obtain data coordinates, wherein the horizontal coordinate of the two-dimensional coordinate system is time and the vertical coordinate is value; calculating the previous value in the data coordinates The average value and average time of the data points, and the The average and average time of the data points are based on the previous The average value and average time of the data points form the starting reference point , and based on the The average of the data points and the average time end reference point ; Use a straight line to separate the starting reference point and the end reference point Connect to get the trend reference line ; Calculate the relationship between each data point in the data coordinates and the trend reference line The vertical difference, where the trend is above the reference line The data points and the trend reference line The vertical difference is positive and below the trend reference line The data points and the trend reference line The vertical difference is negative; calculating the variance of multiple vertical differences, where the variance is less than a preset threshold, and When , it is determined that the value trend of the sensor parameter of the current historical maintenance cycle is decreasing; when the variance is less than the preset threshold, and When , the value trend of the sensor parameter in the historical maintenance cycle is determined to be increasing, where is a scale parameter with a value greater than 1, and Starting reference point The value of End reference point The value of A health evaluation model is constructed based on the values of target parameters of the switch cabinet in multiple maintenance cycles, wherein the health evaluation model represents the corresponding relationship between the value of the target parameter and the health of the switch cabinet; a health evaluation model is constructed based on the values of the target parameters of the switch cabinet in multiple maintenance cycles, including: calculating each target parameter in the first Maintenance cycle rate of change ,in, ,in, For the Starting reference point for a maintenance cycle The value of For the End reference point of a maintenance cycle The value of For the The method comprises the following steps: determining the duration of a maintenance cycle; determining the relevance weight of each target parameter based on the rate of change of each target parameter in multiple maintenance cycles; calculating the sum of the weights of the relevance weights of all target parameters, and calculating the ratio of the relevance weights of the target parameters to the sum of the weights; when the ratio of the relevance weight of any target parameter to the sum of the weights exceeds a preset ratio value, establishing a single-factor health evaluation model based on the target parameter whose ratio exceeds the preset ratio value; establishing a multi-factor health evaluation model based on the relevance weights of multiple target parameters when the ratio of the relevance weight of no target parameter to the sum of the weights does not exceed a preset ratio value; determining the relevance weight of each target parameter based on the rate of change of each target parameter in multiple maintenance cycles, including: calculating the target parameter Rate of change over multiple maintenance cycles The average and variance ; Based on the average and the variance Calculate the relevance index of the target parameter , ,in, is the first weight, is the second weight; the relevance index for all target parameters Perform normalization to obtain the relevance weight of each target parameter ; The value of the target parameter at the current time point is obtained, and the health of the switch cabinet at the current time point is determined based on the value of the target parameter at the current time point and the health assessment model.
2. A switch cabinet health status evaluation method according to claim 1, It is characterized in that Also includes: The health of the switch cabinet at the current time point is compared with a preset threshold, and when the health of the switch cabinet at the current time point is greater than the preset threshold, an alarm message is sent to the target object.
3. A switch cabinet health status evaluation method according to claim 1, It is characterized in that The process of obtaining the dust accumulation amount includes: Acquire an image of a target area in the switch cabinet, wherein the target area includes a circuit board, a heat sink, a plug-in part, and an area where a vent is located; Converting the image of the target area into a grayscale image; Dust accumulation is identified on the grayscale image based on a pre-built dust recognition model to obtain dust accumulation, wherein the dust recognition model is obtained by training an artificial neural network with image samples of the interior of the switch cabinet with different degrees of dust accumulation.
4. A switch cabinet health status evaluation method according to claim 1, It is characterized in that A single-factor health assessment model is established based on the target parameter whose ratio exceeds the preset ratio value, including: Obtain the reference value of the target parameter when the ratio exceeds the preset ratio value during maintenance and the average value of the starting reference point of multiple maintenance cycles ; Based on the reference value And the average value of the starting reference points of multiple maintenance cycles is used to construct a single-factor health evaluation model, wherein the mathematical expression of the health evaluation model is: in, The value of the target parameter at the current time point whose ratio exceeds the preset ratio value. The health of the switchgear.
5. A switch cabinet health status evaluation method according to claim 1, It is characterized in that A multi-factor health evaluation model is established based on the correlation weights of multiple target parameters, including: Get reference values of multiple target parameters during maintenance and the average value of the starting reference point of multiple maintenance cycles for multiple target parameters ; Reference values based on multiple target parameters during maintenance And the average values of the starting reference points of multiple maintenance cycles of multiple target parameters are used to construct a multi-factor health assessment model, wherein the mathematical expression of the health assessment model is: in, For the The value of the target parameter at the current time point, The health of the switchgear, is the number of target parameters.
6. A switch cabinet health status evaluation device, It is characterized in that include: An acquisition module is used to acquire historical sensor data of the switch cabinet in multiple historical maintenance cycles, wherein the historical sensor data includes values of sensor parameters at multiple detection time points in the corresponding maintenance cycle, and the sensor parameters include temperature, humidity, dust accumulation, main line current, main line voltage, and fan operation noise level; A feature analysis module is used to perform distribution feature analysis on the sensor data of the multiple maintenance cycles, and use the sensor parameters that meet the target features as target parameters, wherein the target features include: the value of the sensor parameter increases or decreases over time; the distribution feature analysis of the sensor data of the multiple maintenance cycles includes: distribution feature analysis on the sensor data of a single cycle, wherein the distribution features of the sensor data of a single cycle include increasing trends, decreasing trends, and no increasing or decreasing trends; when the value trend of the sensor parameter of the historical maintenance cycle exceeding a preset ratio threshold is decreasing, it is determined that the value trend of the sensor parameter is decreasing; when the value trend of the sensor parameter of the historical maintenance cycle exceeding a preset ratio threshold is increasing, it is determined that the value trend of the sensor parameter is increasing; the distribution feature analysis of the sensor data of a single cycle includes: mapping the values of the sensor parameters of multiple detection time points in a single historical maintenance cycle to a two-dimensional coordinate system to obtain data coordinates, wherein the horizontal coordinate of the two-dimensional coordinate system is time and the vertical coordinate is value; calculating the previous value in the data coordinates The average value and average time of the data points, and the The average and average time of the data points are based on the previous The average value and average time of the data points form the starting reference point , and based on the The average of the data points and the average time end reference point ; Use a straight line to separate the starting reference point and the end reference point Connect to get the trend reference line ; Calculate the relationship between each data point in the data coordinates and the trend reference line The vertical difference, where the trend is above the reference line The data points and the trend reference line The vertical difference is positive and below the trend reference line The data points and the trend reference line The vertical difference is negative; calculating the variance of multiple vertical differences, where the variance is less than a preset threshold, and When , it is determined that the value trend of the sensor parameter of the current historical maintenance cycle is decreasing; when the variance is less than the preset threshold, and When , the value trend of the sensor parameter in the historical maintenance cycle is determined to be increasing, where is a scale parameter with a value greater than 1, and Starting reference point The value of End reference point The value of A model building module is used to build a health evaluation model based on the values of the target parameters of the switch cabinet in multiple maintenance cycles, wherein the health evaluation model represents the corresponding relationship between the value of the target parameter and the health of the switch cabinet; building a health evaluation model based on the values of the target parameters of the switch cabinet in multiple maintenance cycles includes: calculating each target parameter in the first Maintenance cycle rate of change ,in, ,in, For the Starting reference point for a maintenance cycle The value of For the End reference point of a maintenance cycle The value of For the The method comprises the following steps: determining the duration of a maintenance cycle; determining the relevance weight of each target parameter based on the rate of change of each target parameter in multiple maintenance cycles; calculating the sum of the weights of the relevance weights of all target parameters, and calculating the ratio of the relevance weights of the target parameters to the sum of the weights; when the ratio of the relevance weight of any target parameter to the sum of the weights exceeds a preset ratio value, establishing a single-factor health evaluation model based on the target parameter whose ratio exceeds the preset ratio value; establishing a multi-factor health evaluation model based on the relevance weights of multiple target parameters when the ratio of the relevance weight of no target parameter to the sum of the weights does not exceed a preset ratio value; determining the relevance weight of each target parameter based on the rate of change of each target parameter in multiple maintenance cycles, including: calculating the target parameter Rate of change over multiple maintenance cycles The average and variance ; Based on the average and the variance Calculate the relevance index of the target parameter , ,in, is the first weight, is the second weight; the relevance index for all target parameters Perform normalization to obtain the relevance weight of each target parameter ; The evaluation module is used to obtain the value of the target parameter at the current time point, and determine the health of the switch cabinet at the current time point based on the value of the target parameter at the current time point and the health evaluation model.
Citation Information
Patent Citations
Medium-voltage switch cabinet health degree evaluation method, device and system
CN110826934A
Illuminating lamp control method and device, illuminating lamp and storage medium
CN116095922A
Method and system for evaluating performance degradation of cable joint of switch cabinet based on Internet of Things perception
CN116611028A
Low-voltage apparatus real-time optimization control method based on Internet of Things
CN117555237A
