Fault monitoring system for electric meter box based on multi-source data fusion

Abstract

The application relates to the technical field of electric meter box fault monitoring, in particular to an electric meter box fault monitoring system based on multi-source data fusion. The system comprises a data acquisition module, which is used for acquiring internal and external temperature data of an electric meter box, total load power of the electric meter box and heat dissipation power of a heat dissipation system thereof; a temperature analysis module, which is used for setting a sliding window to synchronously slide on the internal temperature data, the external temperature data, the heat dissipation power and the total load power respectively, so as to obtain a temperature drop coefficient and a heat dissipation effect correction value; a power analysis module, which is used for calculating a heat dissipation power characteristic value based on the heat dissipation power in a current sliding window, obtaining a working efficiency conversion coefficient of the heat dissipation system, and then obtaining a corrected working efficiency conversion coefficient; and a prewarning analysis module, which is used for obtaining a prewarning index based on the corrected working efficiency conversion coefficients corresponding to the sliding windows; and the electric meter box fault is prewarned according to the prewarning index. The application can improve the accuracy of electric meter box fault monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric meter box fault monitoring, and particularly relates to an electric meter box fault monitoring system based on multi-source data fusion. BACKGROUND

[0002] With the rapid development of urban power grids and the continuous growth of residential power loads, the electric meter box as a key node in the low-voltage distribution system, its operating state is directly related to the safety of user power consumption and the stability of the power supply system. In the actual operation process, the electric meter box is easily affected by environmental changes, equipment aging, power anomalies and other factors, thereby causing the equipment to have faults such as overload, high temperature rise and burning. Since the electric meter box fault may be caused by multiple factors or joint action, therefore, using the method of multi-source data fusion to realize the monitoring of the electric meter box fault has an important role and significance for timely and accurate early warning of the electric meter box fault.

[0003] The existing electric meter box fault monitoring is mostly based on single data source analysis, often ignoring the comprehensive influence of multi-source data such as environmental factors, voltage, current and other factors on the equipment operating state. For example, in the monitoring process of the electric meter box heat dissipation system fault, the voltage fluctuation of the electric meter box, the current load and the temperature of the environment where the electric meter box is located, etc. Factors may have an important influence on the operation effect of the heat dissipation system. If only a single parameter is relied on for judgment, it is easy to cause the monitoring result to be distorted or the fault to be not accurately recognized, and it is difficult to realize comprehensive analysis and accurate early warning of the fault. SUMMARY

[0004] In order to solve the above technical problems, the purpose of the present application is to provide an electric meter box fault monitoring system based on multi-source data fusion, and the technical scheme adopted is as follows:

[0005] One embodiment of the present application provides an electric meter box fault monitoring system based on multi-source data fusion, which comprises:

[0006] A data acquisition module is configured to acquire internal temperature data, external temperature data, total load power of the electric meter box and heat dissipation power of the heat dissipation system of the electric meter box.

[0007] A temperature analysis module is configured to set a sliding window to synchronously slide on the internal temperature data, the external temperature data, the heat dissipation power and the total load power, respectively; acquire a temperature drop coefficient according to the internal temperature data in the current sliding window; and correct the temperature drop coefficient by using the external temperature data in the current sliding window to acquire a heat dissipation effect correction value.

[0008] The power analysis module is configured to calculate a heat dissipation power characteristic value based on heat dissipation power in the current sliding window; obtain a working efficiency conversion coefficient of the heat dissipation system by comparing the heat dissipation effect correction value and the heat dissipation power characteristic value; calculate a correction coefficient based on total load power in the current sliding window, and correct the working efficiency conversion coefficient to obtain a corrected working efficiency conversion coefficient.

[0009] The early warning analysis module is configured to obtain a warning index based on the corrected working efficiency conversion coefficient corresponding to each sliding window; and perform early warning on the meter box fault based on the warning index.

[0010] Preferably, the temperature drop coefficient is obtained based on internal temperature data in the current sliding window, including:

[0011] The difference between the first internal temperature data and the second internal temperature data of two adjacent internal temperature data in the current sliding window is obtained, and an exponential function with a natural constant as the base is used to map the difference to obtain a temperature change characteristic value corresponding to the two adjacent internal temperature data; and the mean value of the temperature change characteristic values corresponding to each two adjacent internal temperature data is calculated to obtain the temperature drop coefficient corresponding to the current sliding window.

[0012] Preferably, the heat dissipation effect correction value is obtained by correcting the temperature drop coefficient based on external temperature data in the current sliding window, including:

[0013] The temperature drop coefficient corresponding to the external temperature is obtained based on the external temperature data in the current sliding window; the temperature drop coefficient obtained based on the internal temperature data in the current sliding window is compared with the temperature drop coefficient corresponding to the external temperature to obtain a first ratio; the last external temperature data in the current sliding window is compared with the last internal temperature data to obtain a second ratio; the first external temperature data in the current sliding window is compared with the first internal temperature data to obtain a third ratio; the second ratio is compared with the third ratio, and the first ratio is multiplied to obtain the heat dissipation effect correction value.

[0014] Preferably, the heat dissipation power characteristic value is calculated based on the heat dissipation power in the current sliding window, including:

[0015] The temperature drop coefficient corresponding to the heat dissipation power is calculated based on the heat dissipation power in the current sliding window by using the method for obtaining the temperature drop coefficient; and the first heat dissipation power in the current sliding window is multiplied by the reciprocal of the temperature drop coefficient corresponding to the heat dissipation power to obtain the heat dissipation power characteristic value.

[0016] Preferably, the correction coefficient is calculated based on the total load power in the current sliding window, including:

[0017] The method for calculating the computational heat dissipation power eigenvalue calculates a total load power eigenvalue based on the total load power in the current sliding window; obtains the standard deviation of all total load powers in the current sliding window after first-order difference, and maps the standard deviation using an exponential function with a natural constant as the base to obtain a fluctuation characteristic index; and multiplies the total load power eigenvalue and the fluctuation characteristic index to obtain a correction coefficient.

[0018] Preferably, the work efficiency conversion coefficient is corrected to obtain a corrected work efficiency conversion coefficient, including:

[0019] The preset value is added to the corrected work efficiency conversion coefficient, and then multiplied by the work efficiency conversion coefficient to obtain the corrected work efficiency conversion coefficient.

[0020] Preferably, the warning index is obtained based on the corrected work efficiency conversion coefficients corresponding to each sliding window, including:

[0021] The corrected work efficiency conversion coefficients corresponding to each sliding window form a first sequence, wherein the last corrected work efficiency conversion coefficient in the first sequence is the corrected work efficiency conversion coefficient corresponding to the current sliding window; the first corrected work efficiency conversion coefficient in the first sequence is divided by the sum of the corrected work efficiency conversion coefficient corresponding to the current sliding window and a hyperparameter to obtain a first index; a drop coefficient of the corrected work efficiency conversion coefficient corresponding to the current sliding window is calculated based on the corrected work efficiency conversion coefficient corresponding to the current sliding window and the previous corrected work efficiency conversion coefficient in the first sequence using the method for obtaining the temperature drop coefficient; a drop coefficient corresponding to two adjacent corrected work efficiency conversion coefficients is calculated based on the two adjacent corrected work efficiency conversion coefficients using the method for obtaining the temperature drop coefficient; the average of the drop coefficients corresponding to each two adjacent corrected work efficiency conversion coefficients in the first sequence except the corrected work efficiency conversion coefficient corresponding to the current sliding window is calculated, and is recorded as a drop coefficient average; the drop coefficient of the corrected work efficiency conversion coefficient corresponding to the current sliding window is divided by the sum of the drop coefficient average and the hyperparameter to obtain a second index; and the sum of the first index and the second index is mapped using a hyperbolic tangent function to obtain the warning index.

[0022] Preferably, the meter box fault is warned according to the warning index, including:

[0023] If the warning index is greater than a reference threshold, the meter box is warned of a fault.

[0024] The application has at least the following beneficial effects: the application collects multiple-source data related to the heat dissipation of the electric meter box, including internal temperature data of the electric meter box, external temperature data, total load power of the electric meter box and heat dissipation power of the heat dissipation system, considers the influence of multiple factors on the heat dissipation of the electric meter box, improves the information quantity, and increases the accuracy of the electric meter box heat dissipation fault monitoring; then the sliding window is used to synchronously slide on the internal temperature data, the external temperature data, the heat dissipation power and the total load power, the internal temperature data in the current sliding window and the external temperature data in the current sliding window are analyzed to obtain a heat dissipation effect correction value; then the working power (heat dissipation power) of the heat dissipation system is analyzed to obtain a heat dissipation power characteristic value, and the heat dissipation power characteristic value is combined with the heat dissipation effect correction value to obtain a working efficiency conversion coefficient of the heat dissipation system, the total load power of the electric meter box as a whole and the influence of the fluctuation of the total load power on the working efficiency conversion coefficient of the heat dissipation system are considered, the total load power in the current sliding window is further analyzed to obtain a correction coefficient, and the working efficiency conversion coefficient is corrected to obtain a corrected working efficiency conversion coefficient; finally, the warning index is obtained based on the corrected working efficiency conversion coefficient corresponding to each sliding window, and the electric meter box fault warning is performed, the relationship between the internal and external temperature, the heat dissipation power and the total power is considered, and the heat dissipation fault of the electric meter box can be more accurately monitored and warned. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, a brief introduction will be given to the drawings required in the embodiments or the prior art description. Obviously, the drawings in the following description only show some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0026] Figure 1 A system block diagram of the electric meter box fault monitoring system based on multi-source data fusion provided by the embodiments of the present application. DETAILED DESCRIPTION

[0027] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the specific embodiments, structure, features and effects of the electric meter box fault monitoring system based on multi-source data fusion according to the present application are described in detail as follows by combining with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0029] The application provides a specific scheme of a fault monitoring system for an electric meter box based on multi-source data fusion.

[0030] Embodiment:

[0031] The application mainly applies to analyzing the internal temperature of the electric meter box, the external environmental temperature, the working power of the heat dissipation system and the total load power of the electric meter box, thereby preventing heat dissipation problems of the electric meter box and ensuring normal operation of the electric meter box.

[0032] Please refer to Figure 1 which shows a system block diagram of a fault monitoring system for an electric meter box based on multi-source data fusion, and the system comprises the following modules:

[0033] The data acquisition module is used for acquiring internal temperature data of the electric meter box, external temperature data, total load power of the electric meter box and heat dissipation power of the heat dissipation system thereof.

[0034] The application mainly monitors the fault of the electric meter box, so voltage, current and temperature sensors need to be arranged in the electric meter box, and a temperature sensor also needs to be arranged outside the electric meter box. Thus, the internal temperature data of the electric meter box and the external temperature data of the electric meter box can be acquired, wherein the external temperature data of the electric meter box refers to the external environmental temperature, because the internal and external temperature difference has a certain influence on heat dissipation, so the external temperature data needs to be acquired.

[0035] Further, the voltage and current data of the heat dissipation system of the electric meter box when working are acquired by the voltage and current sensors, thereby the heat dissipation power of the heat dissipation system of the electric meter box is obtained, and the total current and total voltage of all devices in the electric meter box when working are acquired (the sensors can be arranged at the access position of the bus to acquire), thereby the total load power of the electric meter box is obtained. It should be noted that the acquisition frequency of these data (the implementer can adjust according to the actual situation) is the same, and the data is acquired in real time, and the latest acquisition time is the current time. Thus, the internal temperature data of the electric meter box, the external temperature data, the total load power of the electric meter box and the heat dissipation power of the heat dissipation system thereof can be acquired.

[0036] The temperature analysis module is used for setting a sliding window to synchronously slide on the internal temperature data, the external temperature data, the heat dissipation power and the total load power respectively; acquiring a temperature drop coefficient according to the internal temperature data in the current sliding window; and correcting the temperature drop coefficient by using the external temperature data in the current sliding window to acquire a heat dissipation effect correction value.

[0037] The heat dissipation system of the electric meter box is mainly used for adjusting and controlling the temperature inside the box body, ensuring that the electric meter and its supporting electrical elements operate stably within a safe temperature range, while reducing the aging of internal equipment and lines due to long-term high temperature. Therefore, it is particularly important to monitor the failure of the heat dissipation system of the electric meter box.

[0038] The temperature change inside the electric meter box is mainly determined by the heat generated by the internal equipment and lines of the electric meter box, the heat dissipated by the heat dissipation system of the electric meter box, and the ambient temperature. In order to more accurately monitor the heat dissipation failure of the electric meter system by combining the above data sources, a sliding window is established to slide synchronously on each data for analysis. The length of the sliding window is a set time length, and the reference value is 10 minutes. Then, with a set sliding step (reference value is 8 minutes) as a step, the internal temperature data, external temperature data, total load power of the electric meter box and heat dissipation power of the heat dissipation system are synchronously slid. The set sliding step is determined according to the monitoring accuracy requirement, and the shorter the step, the higher the monitoring accuracy. When the sliding window slides to the current time, it is recorded as the current sliding window, that is, the last time in the sliding window is the current time.

[0039] For any sliding window, the heat dissipation system of the electric meter box may carry away part of the heat inside the electric meter box when it is working, thereby reducing the internal temperature. Therefore, in order to obtain the heat dissipation performance of the heat dissipation system during work, the subsequent heat dissipation failure can be accurately monitored.

[0040] First, the internal temperature of the electric meter box monitored by the heat dissipation system in the current sliding window is analyzed to obtain the temperature drop speed during heat dissipation. The temperature drop coefficient is obtained according to the internal temperature data in the current sliding window. Specifically, the difference between the first internal temperature data and the second internal temperature data of the two adjacent internal temperature data in the current sliding window is obtained, and the difference is mapped using an exponential function with a natural constant as the base to obtain the temperature change characteristic value corresponding to the two adjacent internal temperature data. The mean value of the temperature change characteristic value corresponding to each two adjacent internal temperature data is obtained to obtain the temperature drop coefficient corresponding to the current sliding window.

[0041] The specific calculation model of the temperature drop coefficient is:

[0042]

[0043] wherein, Q(T S ) represents the temperature drop coefficient corresponding to the current sliding window, T S represents the sequence composed of the internal temperature data in the current sliding window, m represents the number of internal temperature data in the current sliding window, e represents the natural constant, T i , Ti+1 These represent the i-th and (i+1)-th internal temperature data points within the meter box in the current sliding window. This represents the temperature change characteristic value corresponding to the i-th and (i+1)-th adjacent internal temperature data; This represents the temperature difference inside the meter box at adjacent moments within the current sliding window. It is used as the independent variable of an exponential function with the natural constant as its base. The mean of all exponential function values ​​with the natural constant as their base is summed to make it positive, which facilitates subsequent analysis and description. The larger this value is, the faster the temperature drops within the sliding window.

[0044] During the operation of the meter box's heat dissipation system, changes in ambient temperature have a significant impact on its heat dissipation efficiency. Normally, the meter box transfers internal heat to the external environment through natural heat dissipation or active cooling by the system. However, when the external ambient temperature rises, the temperature difference between the meter box and the environment decreases, and the heat transfer rate slows down, leading to reduced heat dissipation efficiency. Conversely, when the external ambient temperature is low, a larger temperature difference exists between the box and the outside, which facilitates rapid heat release and improves the efficiency of the heat dissipation system. Therefore, changes in ambient temperature not only affect the heat exchange capacity of the heat dissipation system but also directly relate to the safe operation of the electrical equipment inside the meter box. When designing fault monitoring and thermal management strategies for the meter box's heat dissipation system, this critical factor of ambient temperature must be fully considered. To eliminate the influence of environmental factors, the heat dissipation effect value of the heat dissipation system within an arbitrary sliding window is obtained by combining the outdoor ambient temperature.

[0045] The heat dissipation effect correction value is obtained by correcting the temperature drop coefficient using the external temperature data within the current sliding window. Specifically, the temperature drop coefficient corresponding to the external temperature is obtained using the external temperature data within the current sliding window; the temperature drop coefficient obtained using the internal temperature data within the current sliding window is compared with the temperature drop coefficient corresponding to the external temperature to obtain a first ratio; the last external temperature data in the current sliding window is compared with the last internal temperature data to obtain a second ratio; the first external temperature data in the current sliding window is compared with the first internal temperature data to obtain a third ratio; the second ratio and the third ratio are compared and multiplied by the first ratio to obtain the heat dissipation effect correction value.

[0046] The calculation model for the heat dissipation effect correction value is as follows:

[0047]

[0048] Where M represents the heat dissipation effect correction value corresponding to the current sliding window; Q(T) S Q(T) represents the temperature drop coefficient obtained using the internal temperature data within the current sliding window. E) represents the temperature drop coefficient corresponding to the external temperature obtained by using the external temperature data in the current sliding window, which is obtained in the same way, represents the first ratio value, the larger the value, the better the heat dissipation effect of the heat dissipation system in the current sliding window combined with the environment. and respectively represent the last external temperature data obtained in the current sliding window and the last internal temperature data, represents the second ratio value; and respectively represent the initial external temperature data and the internal temperature data in the current sliding window, that is, the first external temperature data obtained in the current sliding window and the first internal temperature data, represents the third ratio value, the larger the value, the better the heat dissipation effect of the heat dissipation system in the current sliding window combined with the environment, represents the ratio of the ratio of the external environment temperature to the internal temperature of the electric meter box at the end time in the current sliding window to the ratio of the external environment temperature to the internal temperature of the electric meter box at the initial time in the current sliding window, the larger the value, the better the active heat dissipation effect of the electric meter box in the current sliding window, because the larger the ratio, the lower the internal temperature of the electric meter box relative to the external environment temperature in the time period, or the larger the drop, and the initial external temperature is lower than the internal temperature, the heat exchange effect is good, indicating that the electric meter box has good active heat dissipation effect under the tail external environment.

[0049] The power analysis module is configured to calculate a heat dissipation power characteristic value based on the heat dissipation power in the current sliding window, calculate a work efficiency conversion coefficient of the heat dissipation system by comparing the heat dissipation effect correction value and the heat dissipation power characteristic value, calculate a correction coefficient based on the total load power in the current sliding window, and correct the work efficiency conversion coefficient to obtain a corrected work efficiency conversion coefficient.

[0050] The heat dissipation effect correction value of the heat dissipation system in any sliding window can be obtained by the above method, but the heat dissipation effect correction value of the heat dissipation system in different sliding windows has a direct positive correlation with the power of the heat dissipation system, for example, when the heat dissipation power of the heat dissipation system is increased, the heat dissipation effect may be better, and vice versa.

[0051] Therefore, it is necessary to further analyze the heat dissipation power value of the heat dissipation system, calculate a heat dissipation power characteristic value based on the heat dissipation power in the current sliding window. Specifically, a heat dissipation power drop coefficient corresponding to the heat dissipation power is calculated based on the heat dissipation power in the current sliding window by using the method for obtaining the temperature drop coefficient; the heat dissipation power characteristic value is obtained by multiplying the first heat dissipation power in the current sliding window by the reciprocal of the heat dissipation power drop coefficient.

[0052] The calculation model of the heat dissipation power characteristic value is:

[0053]

[0054] wherein R S represents the heat dissipation power characteristic value corresponding to the current sliding window, represents the first heat dissipation power in the current sliding window, that is, the heat dissipation power of the heat dissipation system at the initial time point in the time period corresponding to the current sliding window, the greater the value, the greater the working power characteristic value of the system during heat dissipation, P S represents a sequence composed of heat dissipation powers at each time point in the current sliding window, Q(P S ) represents the descending coefficient of the sequence composed of heat dissipation powers of the heat dissipation system in the current sliding window, and the acquisition method is the same as that of the temperature drop coefficient according to the internal temperature data in the current sliding window, the smaller the value, the greater the value, the greater the degree of increase of the heat dissipation power during this period, and the greater the characteristic value.

[0055] If the electric meter box and its heat dissipation system are working normally, the heat dissipation efficiency is also stable. Therefore, for any sliding window, the ratio of the heat dissipation effect correction value of the heat dissipation system to the heat dissipation power characteristic value of the heat dissipation system can represent the working efficiency conversion coefficient of the heat dissipation system in the sliding window. That is, when the heat source is constant, the heat dissipation system under normal circumstances theoretically presents a certain stable positive correlation between the performance of the heat dissipation system and the power of the heat dissipation system, that is, the heat dissipation effect correction value (ignoring the influence of the environment at this time) and the heat dissipation power characteristic value of the heat dissipation system are a relatively constant relationship.

[0056] The working efficiency conversion coefficient of the heat dissipation system in the current sliding window is calculated as follows: X represents the working efficiency conversion coefficient of the heat dissipation system in the current sliding window, M represents the heat dissipation effect correction value corresponding to the current sliding window, R S represents the heat dissipation power characteristic value corresponding to the current sliding window.

[0057] ​However, the electric meter box can also generate a constant heat in the process of heat dissipation. Because the equipment in the electric meter box generates heat due to current passing during operation, the heat generated is usually proportional to the power load. When the total power of the equipment is large, the heat generated is also increased. Meanwhile, the greater the total load power fluctuation, the more unstable the instantaneous energy consumption of the equipment, which causes current change, thereby increasing the amplitude of the conversion of electric energy into heat energy, resulting in abnormal increase of heat. Therefore, in this case, even if the heat dissipation system itself has strong heat dissipation efficiency, but generates a constant heat in the process of heat dissipation, which can cause the working efficiency coefficient of the heat dissipation system to decrease during this period. Therefore, when evaluating the actual working efficiency of the heat dissipation system of the electric meter box, the load state of the equipment and the power fluctuation condition need to be further combined for comprehensive analysis to accurately determine whether the temperature rise is caused by the performance decrease of the heat dissipation system and the like, thereby improving the accuracy of the fault monitoring of the heat dissipation system.

[0058] The correction coefficient is calculated according to the total load power in the current sliding window. Specifically, the total load power characteristic value is calculated based on the total load power in the current sliding window by using the method of calculating the heat dissipation power characteristic value; the standard deviation of all total load powers after first-order difference in the current sliding window is obtained, and the fluctuation characteristic index is obtained by mapping the standard deviation using the exponential function with the natural constant; and the total load power characteristic value and the fluctuation characteristic index are multiplied to obtain the correction coefficient.

[0059] The calculation model of the correction coefficient is:

[0060]

[0061] Wherein, G represents the correction coefficient of the working efficiency conversion coefficient of the heat dissipation system of the electric meter box in the current sliding window, R C represents the total load power characteristic value calculated based on all total load powers in the electric meter box in the current sliding window by using the above method of calculating the heat dissipation power characteristic value. The greater the value, the greater the heat generated during this period; e represents the natural constant; ΔP C represents a sequence composed of all total load powers after first-order difference in the current sliding window; f(ΔP C ) represents the standard deviation of elements in the sequence composed of all total load powers after first-order difference in the current sliding window. The greater the value, the greater the power fluctuation of all total loads of the equipment in the electric meter box, and the greater the heat generated in the electric meter box.

[0062] The correction coefficient of the working efficiency conversion coefficient corresponding to the current sliding window can be obtained by the above, and then the correction coefficient is used to correct the working efficiency conversion coefficient. Specifically, the correction working efficiency conversion coefficient is obtained by adding the preset value to the correction coefficient and multiplying the working efficiency conversion coefficient.

[0063] The specific calculation model is:

[0064] X' = X x (1 + G),

[0065] X' represents the correction working efficiency conversion coefficient of the heat dissipation system of the current sliding window. The greater G is, the greater the heat generated by the electric meter during this period is, which may result in a smaller working efficiency conversion coefficient of the heat dissipation system and a greater correction degree.

[0066] Thus, the corrected working efficiency conversion coefficient, i.e., the correction working efficiency conversion coefficient, can be obtained.

[0067] The early warning analysis module is configured to obtain a warning index based on the correction working efficiency conversion coefficient corresponding to each sliding window, and to perform early warning on the electric meter box fault according to the warning index.

[0068] The correction working efficiency conversion coefficient of the heat dissipation system in any sliding window can be obtained by the above, and then the correction working efficiency conversion coefficient sequence of the current heat dissipation system can be obtained based on the historical data. If the correction working efficiency conversion coefficient of the heat dissipation system in the current sliding window is smaller than the correction working efficiency conversion coefficient corresponding to the initial sliding window, it means that the probability of the heat dissipation system having a heat dissipation fault at the current time is greater, or the greater the decrease amplitude of the correction working efficiency conversion coefficient of the heat dissipation system compared with the historical data, the greater the probability of the heat dissipation system having a fault.

[0069] The early warning index is obtained based on the modified work efficiency conversion coefficients corresponding to each sliding window. Specifically, the modified work efficiency conversion coefficients corresponding to each sliding window are composed into a first sequence, wherein the last modified work efficiency conversion coefficient in the first sequence is the modified work efficiency conversion coefficient corresponding to the current sliding window; the first modified work efficiency conversion coefficient in the first sequence is divided by the sum of the modified work efficiency conversion coefficient corresponding to the current sliding window and a hyperparameter to obtain a first index; a drop coefficient of the modified work efficiency conversion coefficient corresponding to the current sliding window is calculated based on the modified work efficiency conversion coefficient corresponding to the current sliding window and the previous modified work efficiency conversion coefficient in the first sequence by using the method for obtaining a temperature drop coefficient; a drop coefficient corresponding to two adjacent modified work efficiency conversion coefficients is calculated based on the two adjacent modified work efficiency conversion coefficients by using the method for obtaining a temperature drop coefficient; a mean value of the drop coefficients corresponding to each two adjacent modified work efficiency conversion coefficients in the first sequence except the modified work efficiency conversion coefficient corresponding to the current sliding window is calculated, and is denoted as a drop coefficient mean value; the drop coefficient of the modified work efficiency conversion coefficient corresponding to the current sliding window is divided by the sum of the drop coefficient mean value and the hyperparameter to obtain a second index; the sum of the first index and the second index is mapped by using a hyperbolic tangent function to obtain the early warning index.

[0070] The specific calculation model of the early warning index is as follows:

[0071]

[0072] Y n represents the early warning index corresponding to the current sliding window, that is, the early warning index corresponding to the current time; tanh represents a hyperbolic tangent function, which is used for normalization operation; c represents a hyperparameter, which prevents the denominator from being 0, and the reference value is 0.001; X'0 represents the first modified work efficiency conversion coefficient in the first sequence, that is, the modified work efficiency conversion coefficient of the heat dissipation system in the initial sliding window, because the heat dissipation efficiency of the heat dissipation system may decrease and the probability of heat dissipation failure gradually increases along with the dust accumulation in the electric meter box and the aging of the line, the modified work efficiency conversion coefficient of the heat dissipation system corresponding to the initial state is selected as the reference value; X' n represents the modified work efficiency conversion coefficient of the heat dissipation system in the current sliding window;

[0073] Q(X' n ) represents the drop coefficient of the modified work efficiency conversion coefficient corresponding to the current sliding window obtained based on the modified work efficiency conversion coefficient corresponding to the current sliding window and the previous modified work efficiency conversion coefficient in the first sequence by using the method for obtaining a temperature drop coefficient; represents the average of the drop coefficients corresponding to every two adjacent modified work efficiency conversion coefficients in the first sequence except the modified work efficiency conversion coefficient corresponding to the current sliding window, that is, the overall drop coefficient average, represents the overall drop of the integrated heat dissipation performance;

[0074] represents the ratio between the modified work efficiency conversion coefficient corresponding to the current sliding window of the heat dissipation system of the electric meter box and the reference value of the modified work efficiency conversion coefficient of the heat dissipation system of the electric meter box. The larger the value is, the worse the heat dissipation efficiency at the current moment is, and the greater the possibility of heat dissipation system failure or internal heating abnormality of the electric meter box is. represents the ratio between the drop coefficient of the modified work efficiency conversion coefficient corresponding to the current sliding window and the average of the drop coefficients of the modified work efficiency conversion coefficients in history. The larger the value is, the greater the mutation degree of the work efficiency of the heat dissipation system at the current moment is, that is, the more unstable the heat dissipation of the heat dissipation system is, and the greater the probability of sudden failure of the heat dissipation system is.

[0075] Through the above, the early warning index of the heat dissipation system of the electric meter box corresponding to the current sliding window (current moment) is obtained, a reference threshold T is set, which is set to 0.2 (empirical value) here, and the implementer can adjust it according to the actual situation. When Y n >T, it means that the heat dissipation system may have a heat dissipation deficiency or a serious heating failure at this time, and timely early warning is needed at this time to remind the operation and maintenance personnel to further check and maintain the failure.

[0076] In summary, the present application considers that the failure of the heat dissipation system of the electric meter box may be affected by multiple factors, so the accuracy of the failure judgment of the heat dissipation system of the electric meter box is improved by combining multiple source data for comprehensive analysis.

[0077] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments. The above describes a specific embodiment of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or may be advantageous.

[0078] Each embodiment in the present application is described in a progressive manner, and the same or similar parts of each embodiment can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0079] The above only describes the preferred embodiments of the present application and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A fault monitoring system for electric meter boxes based on multi-source data fusion, characterized in that, The system includes: The data acquisition module is used to acquire internal temperature data, external temperature data, total load power of the meter box, and heat dissipation power of its heat dissipation system. The temperature analysis module is used to set a sliding window to slide synchronously on internal temperature data, external temperature data, heat dissipation power, and total load power; to obtain the temperature drop coefficient based on the internal temperature data in the current sliding window; and to obtain a heat dissipation effect correction value by using the external temperature data in the current sliding window to correct the temperature drop coefficient. The power analysis module is used to calculate the heat dissipation power characteristic value based on the heat dissipation power within the current sliding window; compare the heat dissipation effect correction value with the heat dissipation power characteristic value to obtain the working efficiency conversion coefficient of the heat dissipation system; calculate the correction coefficient based on the total load power within the current sliding window, and correct the working efficiency conversion coefficient to obtain the corrected working efficiency conversion coefficient; The early warning analysis module is used to obtain early warning indicators based on the corrected working efficiency conversion coefficient corresponding to each sliding window; and to issue early warnings for meter box malfunctions based on the early warning indicators. The method of obtaining early warning indicators based on the modified work efficiency conversion coefficient corresponding to each sliding window includes: The modified efficiency conversion coefficients corresponding to each sliding window are grouped into a first sequence, where the last modified efficiency conversion coefficient in the first sequence is the modified efficiency conversion coefficient corresponding to the current sliding window. The first modified efficiency conversion coefficient in the first sequence is divided by the sum of the modified efficiency conversion coefficient corresponding to the current sliding window and the hyperparameter to obtain the first index. The decrease coefficient of the modified efficiency conversion coefficient corresponding to the current sliding window is calculated based on the modified efficiency conversion coefficient corresponding to the current sliding window and its previous modified efficiency conversion coefficient in the first sequence using the method of obtaining the temperature drop coefficient. The decrease coefficient corresponding to two adjacent modified efficiency conversion coefficients is calculated based on two adjacent modified efficiency conversion coefficients using the method of obtaining the temperature drop coefficient. The mean of the decrease coefficients corresponding to every two adjacent modified efficiency conversion coefficients in the first sequence, excluding the modified efficiency conversion coefficient corresponding to the current sliding window, is calculated and denoted as the mean decrease coefficient. The decrease coefficient of the modified efficiency conversion coefficient corresponding to the current sliding window is divided by the sum of the mean decrease coefficient and the hyperparameter to obtain the second index. The sum of the first index and the second index is mapped using the hyperbolic tangent function to obtain the warning index.

2. The meter box fault monitoring system based on multi-source data fusion according to claim 1, characterized in that, The step of obtaining the temperature drop coefficient based on the internal temperature data within the current sliding window includes: Obtain the difference between the first and second internal temperature data points in two adjacent internal temperature data points within the current sliding window, and use an exponential function with the natural constant as the base to map the difference to obtain the temperature change characteristic value corresponding to these two adjacent internal temperature data points; calculate the mean value of the temperature change characteristic value corresponding to each pair of adjacent internal temperature data points to obtain the temperature drop coefficient corresponding to the current sliding window.

3. The meter box fault monitoring system based on multi-source data fusion according to claim 1, characterized in that, The step of using external temperature data within the current sliding window to correct the temperature drop coefficient and obtain a heat dissipation effect correction value includes: The temperature drop coefficient corresponding to the external temperature is obtained using the external temperature data within the current sliding window; the temperature drop coefficient obtained using the internal temperature data within the current sliding window is compared with the temperature drop coefficient corresponding to the external temperature to obtain a first ratio; the last external temperature data and the last internal temperature data within the current sliding window are compared to obtain a second ratio; the first external temperature data and the first internal temperature data within the current sliding window are compared to obtain a third ratio; the second ratio and the third ratio are compared and multiplied by the first ratio to obtain the heat dissipation effect correction value.

4. The meter box fault monitoring system based on multi-source data fusion according to claim 1, characterized in that, The calculation of heat dissipation power characteristic values ​​based on the heat dissipation power within the current sliding window includes: The method of obtaining the temperature drop coefficient is used to calculate the decrease coefficient corresponding to the heat dissipation power based on the heat dissipation power in the current sliding window; the characteristic value of heat dissipation power is obtained by multiplying the first heat dissipation power in the current sliding window with the reciprocal of the decrease coefficient corresponding to the heat dissipation power.

5. The meter box fault monitoring system based on multi-source data fusion according to claim 1, characterized in that, The calculation of the correction coefficient based on the total load power within the current sliding window includes: The method of calculating the characteristic value of heat dissipation power is used to calculate the characteristic value of total load power based on the total load power in the current sliding window; the standard deviation of all total load power in the current sliding window is obtained after first difference, and the standard deviation is mapped to the fluctuation characteristic index using an exponential function with the natural constant as the base; the total load power characteristic value is multiplied by the fluctuation characteristic index to obtain the correction coefficient.

6. The meter box fault monitoring system based on multi-source data fusion according to claim 1, characterized in that, The process of correcting the work efficiency conversion coefficient to obtain the corrected work efficiency conversion coefficient includes: The corrected work efficiency conversion coefficient is obtained by adding the preset value and the correction coefficient, and then multiplying the result by the work efficiency conversion coefficient.

7. The meter box fault monitoring system based on multi-source data fusion according to claim 1, characterized in that, The method of issuing early warnings for meter box malfunctions based on early warning indicators includes: If the warning indicator is greater than the reference threshold, a fault warning will be issued for the meter box.

Images