A method and system for real-time monitoring of distribution cabinet operation data

Abstract

The present invention relates to the field of power fault monitoring, and in particular to a method and system for real-time monitoring of distribution cabinet operation data. The method comprises: using a temperature sensor and a current sensor to respectively collect the ambient temperature and actual current of the distribution cabinet; using a first long short-term memory network model to calculate the first fault probability of the distribution cabinet under ambient temperature, and using a second long short-term memory network model to calculate the second fault probability of the distribution cabinet under actual current; using evidence theory to integrate the first fault probability, the second fault probability, the first weight of the temperature sensor and the second weight of the current sensor, and calculate the comprehensive trust of the distribution cabinet fault. When the comprehensive trust is greater than a threshold, a fault warning is issued; when the ambient temperature is outside the operating temperature range of the current sensor, static abnormality and dynamic abnormality are introduced to characterize the second weight. The present invention effectively solves the problem that the existing technology cannot monitor the operation data of the distribution cabinet in real time to timely and accurately discover the fault of the distribution cabinet.

Description

Technical Field

[0001] The present invention relates to the field of power fault monitoring, and more specifically, to a method and system for real-time monitoring of operating data of a power distribution cabinet. Background Art

[0002] Distribution cabinets, which are divided into power distribution cabinets, lighting distribution cabinets, and metering cabinets, are the final stage of the power distribution system. A general term for motor control centers, distribution cabinets are suitable for applications with dispersed loads and a small number of circuits. Motor control centers are used in applications with concentrated loads and a large number of circuits. They distribute power from a circuit in the upper-level distribution equipment to the nearest load. In daily life, distribution cabinets require monitoring during use. Traditional monitoring methods may not provide real-time fault information or early warning of potential problems. Real-time collection, remote monitoring, and intelligent analysis of distribution cabinet operating data can improve the timeliness and accuracy of fault monitoring, reduce maintenance costs, ensure stable operation of the power system, and ultimately enhance the reliability and safety of power supply, thereby preventing safety incidents.

[0003] At present, the patent application document with the publication number "CN106291272A" and the name "A high-voltage switch cabinet fault monitoring device" discloses a method of using an air pump to extract the gas in each area of the switch cabinet through a gas pipeline, and then using a gas detector to detect the changes in the concentration of O3, NO, N2O, NO2, NO3, CO, and N2O5 in the gas to monitor the switch cabinet.

[0004] Gas detection is easily affected by the internal structure and environment of the distribution cabinet, so indirect monitoring of distribution cabinet faults often cannot detect faults in a timely and accurate manner. Summary of the Invention

[0005] In order to solve the problem in the prior art that a distribution cabinet fault cannot be detected promptly and accurately, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for real-time monitoring of operating data of a power distribution cabinet, comprising:

[0007] A temperature sensor and a current sensor are used to collect the ambient temperature and actual current of the distribution cabinet respectively; a first long short-term memory network model is used to calculate the first fault probability of the distribution cabinet under the ambient temperature, and a second long short-term memory network model is used to calculate the second fault probability of the distribution cabinet under the actual current; the first fault probability, the second fault probability, the first weight of the temperature sensor and the second weight of the current sensor are integrated using evidence theory to calculate the comprehensive confidence of the distribution cabinet fault, and when the comprehensive confidence of the distribution cabinet fault is greater than a threshold, a fault warning is issued; wherein, when the ambient temperature is within the operating temperature range of the current sensor, the first weight and the second weight in the evidence theory are the same; when the ambient temperature is outside the operating temperature range of the current sensor, the first weight is preset to calculate the second weight, and the second weight is positively correlated with the first weight and the credibility of the current sensor at the ambient temperature; the credibility of the current sensor at the ambient temperature is related to the static abnormality and dynamic abnormality of the current sensor; the static abnormality is used to characterize the difference between the current ambient temperature and the operating temperature of the current sensor; the dynamic abnormality is used to characterize the difference between the fluctuation of the actual current and the fluctuation of the current of the current sensor at the operating temperature.

[0008] The reliability of the current sensor in collecting current can be characterized from two aspects: the operating temperature and the degree of fluctuation of the collected current. Therefore, static abnormality and dynamic abnormality are introduced to calculate the credibility of the current sensor at ambient temperature. Then, evidence theory is introduced, and the first fault probability and the second fault probability are used as evidence. The first weight of the temperature sensor is used as the weight of the first fault probability, and the second weight of the current sensor is used as the weight of the second fault probability. The second weight is positively correlated with the aforementioned credibility. At the same time, the reliability of the data collected by the temperature sensor and the current sensor is taken into account, as well as the probability of failure caused by the ambient temperature and the actual current. In addition, the temperature sensor and the current sensor can directly and accurately reflect the circuit conditions in the distribution cabinet. Therefore, the invention can timely and accurately detect distribution cabinet failures through real-time monitoring of the distribution cabinet operation data.

[0009] Preferably, after the current sensor collects the actual current of the power distribution cabinet, the method further includes: performing difference completion processing on the actual current.

[0010] In some cases, the data collected by the current sensor may be missing, and difference completion can fill in these missing values to make the calculation more accurate.

[0011] Preferably, the static abnormality of the current sensor includes: ,in, represents the static abnormality, Indicates the lower limit of the operating temperature of the current sensor, Indicates the upper limit of the operating temperature of the current sensor, Indicates the ambient temperature.

[0012] Current sensors generally have an operating temperature range. When the upper limit is exceeded, the upper limit temperature is used to represent the difference between the current ambient temperature and the current sensor's operating temperature. When the lower limit is below the lower limit, the lower limit temperature is used to represent the difference between the current ambient temperature and the current sensor's operating temperature. This can avoid the problem of a large static anomaly even though the temperature difference between the operating temperature range is small.

[0013] Preferably, the dynamic abnormality of the current sensor includes: , Indicates the dynamic abnormality, Indicates the actual current fluctuation value of the current sensor at the ambient temperature. represents the current fluctuation value of the current sensor at the lower limit of the operating temperature, t represents the ambient temperature, Indicates the lower limit of the operating temperature of the current sensor; Indicates the current fluctuation value of the current sensor at the upper limit of the operating temperature. Indicates the upper limit of the operating temperature of the current sensor.

[0014] The current fluctuation value collected by the current sensor at the upper and lower limits of the operating temperature is generally also the upper and lower limits of the fluctuation. Therefore, the dynamic abnormality is divided into two cases to better characterize the difference between the actual current fluctuation and the current fluctuation of the current sensor at the operating temperature.

[0015] Preferably, the current fluctuation value is the standard deviation of the current collected at the corresponding temperature.

[0016] Preferably, the credibility of the current sensor at the ambient temperature is related to the static abnormality and dynamic abnormality of the current sensor, specifically: ,in, Indicates the reliability of the current sensor at this ambient temperature. represents a natural constant, Indicates the static abnormality of the current sensor. Indicates the dynamic abnormality of the current sensor, is an empirical constant.

[0017] The comprehensive static abnormality and dynamic abnormality are equivalent to reflecting the reliability of the current sensor from the perspective of temperature and fluctuation, thereby enhancing the accuracy of the reliability.

[0018] Preferably, when the ambient temperature is outside the operating temperature range, the weight of the temperature sensor is preset, and the weight of the current sensor is calculated according to the weight of the temperature sensor and the credibility of the current sensor at the ambient temperature, specifically: ,in, represents the second weight of the current sensor, Indicates the reliability of the current sensor at this ambient temperature. represents a first weight of the temperature sensor, where the weight of the temperature sensor is greater than 1 / 3.

[0019] Preferably, the first long-short-term memory network model includes: collecting historical ambient temperatures and corresponding distribution cabinet status labels as samples, the distribution cabinet status labels are divided into normal and faulty, constructing a long-short-term memory network model, the input layer is used to input historical ambient temperatures, the hidden layer is used to learn the historical ambient temperature characteristics and their relationship with distribution cabinet failures, the output layer uses a Sigmoid activation function to output the distribution cabinet failure probability, and uses a cross-entropy loss function to measure the difference between the distribution cabinet failure probability and the distribution cabinet status label. The constructed long-short-term memory network model is trained using the samples to obtain a trained first long-short-term memory network model.

[0020] In a second aspect, the present invention also provides a real-time monitoring system for distribution cabinet operation data, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned real-time monitoring method for distribution cabinet operation data.

[0021] The beneficial effects of the present invention are as follows: the reliability of the current collected by the current sensor can be characterized from two aspects: the operating temperature and the degree of fluctuation of the collected current. Therefore, static abnormality and dynamic abnormality are introduced to calculate the credibility of the current sensor at ambient temperature. Then, evidence theory is introduced to calculate the first fault probability and the second fault probability using the first long short-term memory network and the second long short-term memory network. The first fault probability and the second fault probability are used as evidence. The first weight of the temperature sensor is used as the weight of the first fault probability, and the second weight of the current sensor is used as the weight of the second fault probability. The second weight is positively correlated with the aforementioned credibility. At the same time, the reliability of the data collected by the temperature sensor and the current sensor is taken into account, as well as the probability of failure caused by the ambient temperature and the actual current. Moreover, the temperature sensor and the current sensor can directly and accurately reflect the circuit conditions in the distribution cabinet. Therefore, the present invention can detect distribution cabinet failures in a timely and accurate manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0023] Figure 1 This is a flow chart of a method for real-time monitoring of power distribution cabinet operation data provided by an embodiment of the present invention;

[0024] Figure 2This is a block diagram of a real-time monitoring system for distribution cabinet operation data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0026] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1 This is a flow chart of a method for real-time monitoring of power distribution cabinet operation data according to an embodiment of the present invention, comprising the following steps:

[0028] S101, using a temperature sensor and a current sensor to collect the ambient temperature and actual current of the power distribution cabinet respectively;

[0029] In some embodiments, to avoid missing data collected by the current sensor, after the current sensor collects the actual current of the power distribution cabinet, the current sensor further includes: performing difference filling processing on the actual current. Generally, interpolation methods such as linear interpolation and polynomial interpolation can be used.

[0030] S102. Calculate a first failure probability of the power distribution cabinet at ambient temperature using a first long short-term memory network model, and calculate a second failure probability of the power distribution cabinet at actual current using a second long short-term memory network model.

[0031] Generally speaking, the first long short-term memory network model can be a long short-term memory network model trained based on historical ambient temperature and corresponding distribution cabinet status, and the second long short-term memory network model can be a long short-term memory network model trained based on historical current and corresponding distribution cabinet status.

[0032] In some embodiments, the first long-short-term memory network model includes: collecting historical ambient temperatures and corresponding distribution cabinet status labels as samples, where the distribution cabinet status labels are divided into normal and faulty, constructing a long-short-term memory network model, an input layer for inputting historical ambient temperatures, a hidden layer for learning historical ambient temperature characteristics and their relationship with distribution cabinet failures, an output layer using a Sigmoid activation function to output the probability of distribution cabinet failure, a cross-entropy loss function for measuring the difference between the distribution cabinet failure probability and the distribution cabinet status label, and using the samples to train the constructed long-short-term memory network model to obtain a trained first long-short-term memory network model. The specific process of training the second long-short-term memory network model is basically the same as the process of training the first long-short-term memory network model described above and will not be repeated here.

[0033] S103. Utilize evidence theory to integrate the first fault probability, the second fault probability, the first weight of the temperature sensor, and the second weight of the current sensor to calculate the comprehensive confidence level of the distribution cabinet fault. When the comprehensive confidence level of the distribution cabinet fault is greater than a threshold, issue a fault warning.

[0034] For example, the specific process of calculating the comprehensive confidence level of a power distribution cabinet fault according to evidence theory includes the following steps:

[0035] Step 1: Define the framework;

[0036] In this embodiment, the state is defined : The power distribution cabinet fails; status : The power distribution cabinet is not faulty.

[0037] Step 2: Build a trust function;

[0038] For temperature sensors, their supported status Trust , its support status Trust , where a is the first weight and A is the first fault probability; for the current sensor, its support state Trust , its support status Trust , where b is the second weight and B is the second failure probability.

[0039] Step 3: Calculate the comprehensive confidence level of the power distribution cabinet failure;

[0040] , K is the conflict coefficient, which indicates the state of the temperature sensor and the current sensor and status The trust conflict is as follows: ,therefore .

[0041] The comprehensive confidence level of the distribution cabinet failure is calculated and compared with the preset threshold. For example, if the comprehensive confidence level of the distribution cabinet failure is 90% and the preset threshold is 80%, it can be considered that the distribution cabinet has failed and a fault warning is issued.

[0042] In some embodiments, when the ambient temperature is within the operating temperature range of the current sensor, the first weight and the second weight in the evidence theory are the same, and a=b=0.5 can generally be preset.

[0043] In other embodiments, when the ambient temperature is outside the operating temperature range of the current sensor, a first weight is preset to calculate a second weight, and the second weight is positively correlated with the first weight and the credibility of the current sensor at the ambient temperature; the credibility of the current sensor at the ambient temperature is related to the static abnormality and dynamic abnormality of the current sensor; the static abnormality is used to characterize the difference between the current ambient temperature and the operating temperature of the current sensor; the dynamic abnormality is used to characterize the difference between the fluctuation of the actual current and the fluctuation of the current of the current sensor at the operating temperature.

[0044] The static abnormality is used to characterize the difference between the current ambient temperature and the operating temperature of the current sensor. Therefore, in some embodiments, the static abnormality of the current sensor is ,in, represents the static abnormality, Indicates the lower limit of the operating temperature of the current sensor, Indicates the upper limit of the operating temperature of the current sensor, Indicates the ambient temperature. For example, the operating temperature of the current sensor is a℃-b℃. If the current temperature is x℃ and x>b, then the static abnormality of the current sensor is = If the current temperature is y℃ and y<a, then the static abnormality of the current sensor is = If the current temperature is within the operating temperature range of the current sensor, it means that the current sensor is very reliable and there is no static abnormality. 0.

[0045] The dynamic abnormality is used to characterize the difference between the actual current fluctuation and the current fluctuation of the current sensor at the working temperature. Therefore, in some embodiments, the dynamic abnormality of the current sensor is , Indicates the dynamic abnormality, Indicates the actual current fluctuation value of the current sensor at the ambient temperature. represents the current fluctuation value of the current sensor at the lower limit of the operating temperature, t represents the ambient temperature, Indicates the lower limit of the operating temperature of the current sensor; Indicates the current fluctuation value of the current sensor at the upper limit of the operating temperature. Indicates the upper limit of the operating temperature of the current sensor. If the ambient temperature is within the operating temperature range of the current sensor, the current fluctuation value can be considered normal, that is, there is no abnormality, and the dynamic abnormality degree = 0. Since the power demand is different at different times, even if the upper or lower limit of the operating temperature of the power distribution cabinet is the same, the current fluctuation value may be different. Therefore, in some embodiments, Refers to the current fluctuation value of the current sensor at the lower limit of the operating temperature at the most recent time from the moment the current ambient temperature is collected. It refers to the current fluctuation value of the current sensor at the upper limit of the operating temperature at the most recent time since the current ambient temperature was collected. For example, the operating temperature range of the current sensor is -10℃-100℃. There are several groups of data in chronological order, with the content in brackets being (time, ambient temperature, current fluctuation value): (17:48:30, 82℃, 10A), (17:48:40, 92℃, 12A), (17:48:45, 100℃, 12A), (17:48:55, 100℃, 15A), (17:49:05, 105℃, 16A). Obviously, the current ambient temperature is 105℃, which exceeds the upper limit of the current sensor's operating temperature. The most recent current fluctuation value of the current sensor at the upper limit of 100℃ was 15A. Therefore, the dynamic abnormality of the current sensor at this time is .

[0046] In order to better and more accurately describe the current fluctuation, in some embodiments, the current fluctuation value is the standard deviation of the current collected at the corresponding temperature. For example, when the ambient temperature is 80°C, n current data I1, I2, I3, ... I n , calculate the average value of these currents , and then calculate the standard deviation of these currents , the standard deviation That is, it is the current fluctuation value of the actual current collected at the ambient temperature.

[0047] The reliability of the current sensor at the ambient temperature is obtained. After obtaining the static abnormality and dynamic abnormality of the current sensor, the reliability of the current sensor at the ambient temperature can be further calculated. The specific calculation formula is: ,in, Indicates the reliability of the current sensor at this ambient temperature. represents a natural constant, Indicates the static abnormality of the current sensor. Indicates the dynamic abnormality of the current sensor, is an empirical constant.

[0048] When the ambient temperature is outside the operating temperature range, the weight of the temperature sensor is preset, and the weight of the current sensor is calculated based on the weight of the temperature sensor and the credibility of the current sensor at the ambient temperature, specifically: ,in, represents the second weight of the current sensor, Indicates the reliability of the current sensor at this ambient temperature. represents a first weight of the temperature sensor, where the weight of the temperature sensor is greater than 1 / 3.

[0049] In other embodiments of the present invention, the ambient temperature of the distribution cabinet can be collected by using a temperature sensor, and the actual voltage of the distribution cabinet can be collected by using a voltage sensor. Then, a long short-term memory network model is used to calculate the first failure probability of the distribution cabinet at the ambient temperature and the third failure probability of the distribution cabinet at the actual voltage. The first failure probability, the third failure probability, the first weight of the temperature sensor, and the third weight of the voltage sensor are integrated using evidence theory to calculate the comprehensive confidence of the distribution cabinet failure. When the comprehensive confidence of the distribution cabinet failure is greater than a threshold, a fault warning is issued. The method of calculating the third weight of the voltage sensor is similar to the method of calculating the second weight of the current sensor, and will not be repeated here.

[0050] In other embodiments of the present invention, in order to make fault monitoring more accurate, temperature, current and voltage can also be considered at the same time. That is, the ambient temperature of the distribution cabinet is collected by a temperature sensor, the actual current of the distribution cabinet is collected by a current sensor, and the actual voltage of the distribution cabinet is collected by a voltage sensor. Then, the first fault probability of the distribution cabinet under the ambient temperature, the second fault probability of the distribution cabinet under the actual current, and the third fault probability of the distribution cabinet under the actual voltage are calculated. The first fault probability, the second fault probability, the third fault probability, the first weight of the temperature sensor, the second weight of the current sensor and the third weight of the voltage sensor are integrated using evidence theory to calculate the comprehensive trust of the distribution cabinet fault. When the comprehensive trust of the distribution cabinet fault is greater than the threshold, a fault warning is issued. It should be noted that in this embodiment, when the ambient temperature is within the operating temperature range of the current sensor and the voltage sensor, the first weight, the second weight and the third weight in the evidence theory are all 1 / 3; when the ambient temperature is not within the operating temperature range of the current sensor and the voltage sensor, the method of calculating the second weight of the current sensor and the third weight of the voltage sensor is different, specifically: ,in, represents the second weight of the current sensor, represents the third weight of the current sensor, Indicates the reliability of the current sensor at this ambient temperature. Indicates the reliability of the voltage sensor at this ambient temperature. The calculation method is the same as above The calculation method is the same as represents the first weight of the temperature sensor; when the ambient temperature is not within the operating temperature range of the current sensor but within the operating temperature range of the voltage sensor, or when the ambient temperature is within the operating temperature range of the current sensor but not within the operating temperature range of the voltage sensor, the weight of the sensor that is not within the operating temperature range can be calculated preferentially, and the weight of the other sensor can be calculated by subtracting the first weight of the temperature sensor and the weight of the sensor that is not within the operating temperature range from 1. For example, when the ambient temperature is not within the operating temperature range of the current sensor but within the operating temperature range of the voltage sensor, .

[0051] The above-mentioned method for real-time monitoring of distribution cabinet operation data provided by an embodiment of the present invention takes into account the reliability of data collected by temperature sensors and current sensors, and also takes into account the probability of failure caused by ambient temperature and actual current. Moreover, the temperature sensor and current sensor can directly and accurately reflect the circuit conditions in the distribution cabinet. Therefore, the invention can detect distribution cabinet failures in a timely and accurate manner.

[0052] The present invention also provides a real-time monitoring system for distribution cabinet operation data. Figure 2 As shown, the system includes a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, a real-time monitoring method for operating data of a distribution cabinet described in the present invention is implemented.

[0053] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of, accessible to, or connectable to a device. Any application or module described in the present invention can be implemented using computer-readable / executable instructions that can be stored or otherwise maintained by such a computer-readable medium.

[0054] In the description of this specification, "multiple" and "several" mean at least two, such as two, three or more, unless otherwise clearly defined.

[0055] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. A method for real-time monitoring of distribution cabinet operation data, characterized in that: include: Use temperature sensors and current sensors to collect the ambient temperature and actual current of the distribution cabinet respectively; The first long short-term memory network model is used to calculate the first failure probability of the distribution cabinet under ambient temperature, and the second long short-term memory network model is used to calculate the second failure probability of the distribution cabinet under actual current; The first fault probability, the second fault probability, the first weight of the temperature sensor, and the second weight of the current sensor are integrated using evidence theory to calculate the comprehensive trust level of the distribution cabinet fault, including: Define the state The power distribution cabinet fails. The power distribution cabinet has no faults; Build a trust function for the temperature sensor: Its support status Trust , Its support status Trust , where a is the first weight and A is the first failure probability; For current sensors: Its support status Trust , Its support status Trust , where b is the second weight and B is the second failure probability; Calculate the comprehensive confidence level of power distribution cabinet failure; ， Among them, K is the conflict coefficient, which represents the state of the temperature sensor and the current sensor. and status The trust conflict is: ， Correspondingly, ; When the comprehensive confidence level of the power distribution cabinet fault is greater than the threshold, a fault warning is issued; Among them, when the ambient temperature is within the operating temperature range of the current sensor, the first weight and the second weight in the evidence theory are the same; when the ambient temperature is outside the operating temperature range of the current sensor, the first weight is preset to calculate the second weight, and the second weight is positively correlated with the first weight and the credibility of the current sensor at the ambient temperature; the credibility of the current sensor at the ambient temperature is related to the static abnormality and dynamic abnormality of the current sensor, specifically: ,in, Indicates the reliability of the current sensor at this ambient temperature. represents a natural constant, Indicates the static abnormality of the current sensor. Indicates the dynamic abnormality of the current sensor, is an empirical constant; The static abnormality degree is used to characterize the difference between the current ambient temperature and the operating temperature of the current sensor, including: ,in, Indicates the lower limit of the operating temperature of the current sensor, Indicates the upper limit of the operating temperature of the current sensor, Indicates the ambient temperature; The dynamic abnormality is used to characterize the difference between the actual current fluctuation and the current fluctuation of the current sensor at the operating temperature, including: , Indicates the actual current fluctuation value of the current sensor at the ambient temperature. represents the current fluctuation value of the current sensor at the lower limit of the operating temperature, Indicates the lower limit of the operating temperature of the current sensor; Indicates the current fluctuation value of the current sensor at the upper limit of the operating temperature. Indicates the upper limit of the operating temperature of the current sensor.

2. The method for real-time monitoring of distribution cabinet operation data according to claim 1, characterized in that: After the current sensor collects the actual current of the power distribution cabinet, the method further includes: performing difference completion processing on the actual current.

3. The method for real-time monitoring of distribution cabinet operation data according to claim 2, characterized in that: The current fluctuation value is the standard deviation of the current collected at the corresponding temperature.

4. The method for real-time monitoring of distribution cabinet operation data according to claim 2, characterized in that: When the ambient temperature is outside the operating temperature range, the weight of the temperature sensor is preset, and the weight of the current sensor is calculated based on the weight of the temperature sensor and the credibility of the current sensor at the ambient temperature, specifically: ,in, represents the second weight of the current sensor, Indicates the reliability of the current sensor at this ambient temperature. represents a first weight of the temperature sensor, where the weight of the temperature sensor is greater than 1 / 3.

5. The method for real-time monitoring of distribution cabinet operation data according to claim 1, characterized in that: The first long short-term memory network model includes: Historical ambient temperatures and corresponding distribution cabinet status labels are collected as samples. The distribution cabinet status labels are divided into normal and faulty. A long short-term memory network model is constructed. The input layer is used to input historical ambient temperatures, and the hidden layer is used to learn the historical ambient temperature characteristics and their relationship with distribution cabinet failures. The output layer uses a Sigmoid activation function to output the distribution cabinet failure probability. The cross-entropy loss function is used to measure the difference between the distribution cabinet failure probability and the distribution cabinet status label. The constructed long short-term memory network model is trained using the samples to obtain a trained first long short-term memory network model.

6. A real-time monitoring system for distribution cabinet operation data, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for real-time monitoring of distribution cabinet operation data according to any one of claims 1 to 5.

Images