Intelligent electric leakage detection alarm method of distribution box and distribution box

Abstract

The invention relates to the technical field of electrical variable measurement, in particular to an intelligent electric leakage detection alarm method for a distribution box and the distribution box, and the method comprises the steps: obtaining the current and voltage of each element in a to-be-detected distribution box in a current time period, and equally dividing the current time period and a preset time period; determining the operating power and the isolated abnormal value of each element in each sub-time period; determining parameter excess of each element in each preset time period, and screening out a heat source element; predicting to obtain a parameter excess predicted value of each heat source element in each preset future time period; and based on the heat accumulation effect values corresponding to all the heat source elements, predicting whether the to-be-detected distribution box has an electric leakage phenomenon, and if the to-be-detected distribution box is predicted to have the electric leakage phenomenon, sending alarm information for reminding and preventing electric leakage abnormity. According to the invention, the electric leakage detection of the distribution box is realized by measuring the current and the voltage, so that the timeliness of electric leakage detection of the distribution box is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of measuring electric variables, and in particular to an intelligent leakage detection and alarm method for a distribution box and a distribution box. Background Art

[0002] The distribution box can be divided into power distribution box, lighting distribution box and metering box, which is the final equipment of the distribution system. The distribution box is a general term for the motor control center. The distribution box can be used in places where the load is relatively dispersed and there are fewer circuits. The distribution box can distribute the power of a circuit of the upper-level distribution equipment to the nearest load. This level of equipment can provide protection, monitoring and control for the load. Secondly, the distribution box is often small in size, easy to install, special in technical performance, fixed in position, unique in configuration function, not restricted by the site, widely used, stable and reliable in operation, high in space utilization, small in footprint and environmentally friendly.

[0003] The leakage of the distribution box is a common safety hazard of electricity use. Therefore, it is very important to detect the leakage of the distribution box. At present, the method commonly used to detect the leakage of the distribution box is to use a residual current device (RCD) to detect the leakage of the distribution box.

[0004] However, when the leakage protection device is used to detect the leakage of the distribution box, the following technical problems often occur: The leakage protector will often automatically cut off the power supply after the distribution box has leakage to prevent further leakage of current. Therefore, it is often difficult to identify the leakage trend in time through the leakage protector, resulting in poor timeliness of leakage detection of the distribution box, which in turn makes it difficult to reduce the occurrence of leakage. Summary of the invention

[0005] In order to solve the technical problem of poor timeliness in leakage detection of a distribution box, the present invention proposes an intelligent leakage detection alarm method for a distribution box and a distribution box.

[0006] In a first aspect, the present invention provides an intelligent leakage detection and alarm method for a distribution box, the method comprising: Obtain the current and voltage of each component in the distribution box to be tested in the current time period, divide the current time period equally to obtain a preset time period, and divide the preset time period equally to obtain sub-time periods; Determine the operating power of each component in each sub-time period based on the current and voltage of each component in each sub-time period, and determine an isolated outlier value of each component in each sub-time period based on the operating powers of all components in each sub-time period; Determine the parameter excess of each component in each preset time period according to the distribution change of the operating power and isolated abnormal values ​​of each component in all sub-time periods in each preset time period, and screen out the heat source component from all components based on the parameter excess; According to the parameter excess of each heat source element in all preset time periods within the current time period, the parameter excess predicted value of each heat source element in each preset future time period is predicted to form a parameter excess predicted value sequence corresponding to each heat source element; Determine the heat accumulation effect value corresponding to each heat source element according to the parameter excess prediction value sequence corresponding to each heat source element; Based on the heat accumulation effect values ​​corresponding to all heat source elements, it is predicted whether the distribution box to be tested will have leakage. If it is predicted that the distribution box to be tested will have leakage, an alarm message is sent to remind and prevent leakage anomalies.

[0007] In combination with the first aspect above, in a possible implementation manner, after sending the alarm information for reminding to prevent leakage abnormality, the method further includes: Select a preset number of heat source elements with the largest corresponding heat accumulation effect values ​​from all heat source elements as possible leakage abnormal elements; According to the heat accumulation effect value corresponding to each possible leakage abnormality component and the accumulated value of the heat accumulation effect values ​​corresponding to all heat source components, the heat loss possibility corresponding to each possible leakage abnormality component is determined, wherein the heat accumulation effect value corresponding to the possible leakage abnormality component is positively correlated with the corresponding heat loss possibility, and the accumulated value of the heat accumulation effect values ​​corresponding to all heat source components is positively correlated with the heat loss possibility; If the heat loss probability corresponding to the leakage abnormality possible component is greater than a preset heat loss threshold, it is predicted that the leakage abnormality possible component will have a leakage phenomenon within a preset future time period.

[0008] In combination with the first aspect, in a possible implementation manner, determining the operating power of each component in each sub-time period based on the current and voltage of each component in each sub-time period includes: The product of the current and the voltage of each element at each moment in each sub-time period is determined as the initial power of each element at each moment in each sub-time period; The average of the initial powers of each component at all times in each sub-time period is determined as the operating power of each component in each sub-time period.

[0009] In combination with the first aspect, in a possible implementation manner, determining the isolated abnormal value of each component in each sub-time period based on the operating power of all components in each sub-time period includes: Based on the operating power of each component in all sub-time periods, the anomaly score of each component in each sub-time period is determined as an isolated outlier through the isolation forest algorithm.

[0010] In combination with the first aspect, in a possible implementation, determining the parameter excess of each component in each preset time period according to the distribution change of the operating power and isolated abnormal values ​​of each component in all sub-time periods in each preset time period includes: The product of the operating power of each component in each sub-time period and the isolated outlier value is determined as the possible initial heat loss factor of each component in each sub-time period; The parameter excess of each component in each preset time period is determined based on the average of the initial heat loss possibility factors of each component in all sub-time periods in each preset time period and the difference between the initial heat loss possibility factors of each component in different sub-time periods in each preset time period.

[0011] In combination with the first aspect above, in a possible implementation manner, the formula corresponding to the parameter excess of the component within the preset time period is: ;in, is the parameter excess of the ath component in the tth preset time period; a is the serial number of the component in the distribution box to be detected; t is the number of preset time periods in the current time period; is the normalization function; is the mean value of the initial heat loss possible factor of the ath element in all sub-time periods in the tth preset time period; It is the possible factor of initial heat loss of the ath element in the first sub-time period within the tth preset time period.

[0012] In combination with the first aspect, in a possible implementation, the step of selecting heat source elements from all elements based on parameter excess includes: The parameter excess of each component in all preset time periods in the current time period is used to form a parameter excess set corresponding to each component; The maximum value in the parameter excess set corresponding to each element is determined as the parameter representative excess corresponding to each element; If the parameter corresponding to the element represents an excess greater than a preset heat source excess threshold, the element is determined as a heat source element.

[0013] In combination with the first aspect above, in a possible implementation, the formula corresponding to the heat accumulation effect value corresponding to the heat source element is: ;in, is the heat accumulation effect value corresponding to the bth heat source element; b is the serial number of the heat source element; is a natural exponential function; It is the absolute value function; It is the mean of all parameter excess prediction values ​​in the parameter excess prediction value sequence corresponding to the bth heat source element.

[0014] In combination with the first aspect above, in a possible implementation, predicting whether leakage will occur in the distribution box to be detected based on the heat accumulation effect values ​​corresponding to all heat source elements includes: If the average of the heat accumulation effect values ​​corresponding to all heat source elements is greater than the preset heat accumulation threshold, it is predicted that the distribution box to be tested will have a leakage phenomenon.

[0015] In the second aspect, the present invention provides a distribution box, which includes a protective cover, a current sensor, a voltage sensor, an infrared thermal imaging device and a processing module, and the bent edge on the shell of the distribution box is facing the outside of the box body, and the processing module is used to implement the method in the above-mentioned first aspect or any possible implementation method of the first aspect.

[0016] In a third aspect, a server is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the method in the first aspect or any possible implementation of the first aspect.

[0017] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0018] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0019] In a sixth aspect, a smart leakage detection and alarm system for a distribution box is provided, the system comprising: An acquisition and equal division module is used to obtain the current and voltage of each component in the distribution box to be detected in the current time period, divide the current time period into equal parts to obtain a preset time period, and divide the preset time period into equal parts to obtain sub-time periods; A power and abnormality determination module, used to determine the operating power of each component in each sub-time period based on the current and voltage of each component in each sub-time period, and determine the isolated abnormal value of each component in each sub-time period based on the operating power of all components in each sub-time period; A determination screening module is used to determine the parameter excess of each element in each preset time period according to the distribution change of the operating power and isolated abnormal values ​​of each element in all sub-time periods in each preset time period, and screen out the heat source element from all elements based on the parameter excess; A parameter excess prediction module is used to predict the parameter excess prediction value of each heat source element in each preset future time period according to the parameter excess of each heat source element in all preset time periods in the current time period, so as to form a parameter excess prediction value sequence corresponding to each heat source element; An effect value determination module is used to determine the heat accumulation effect value corresponding to each heat source element according to the parameter excess prediction value sequence corresponding to each heat source element; The prediction and sending module is used to predict whether the distribution box to be tested will have leakage based on the thermal accumulation effect values ​​corresponding to all heat source elements. If it is predicted that the distribution box to be tested will have leakage, an alarm message is sent to remind and prevent leakage anomalies.

[0020] The present invention has the following beneficial effects: The intelligent leakage detection and alarm method of a distribution box of the present invention realizes leakage detection of the distribution box by measuring current and voltage, solves the technical problem of poor timeliness of leakage detection of the distribution box, and thus improves the timeliness of leakage detection of the distribution box. Compared with leakage detection of the distribution box through a leakage protector, the present invention comprehensively considers multiple indicators related to the leakage occurrence trend, such as operating power, isolated abnormal values ​​and parameter excess, thereby predicting multiple indicators related to future leakage conditions, such as parameter excess prediction value and thermal accumulation effect value, and then realizes the prediction of whether leakage phenomena will occur in the future, thereby improving the timeliness of leakage detection of the distribution box, and to a certain extent, can prevent future leakage phenomena, thereby reducing the occurrence of leakage phenomena. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 It is a flow chart of a smart leakage detection and alarm method for a distribution box of the present invention; Figure 2 A schematic diagram of the structure of an intelligent leakage detection and alarm system for a distribution box of the present invention; Figure 3The figure is a schematic diagram of the structure of a computer device of the present invention. DETAILED DESCRIPTION

[0023] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0024] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0025] refer to Figure 1 , showing the process of some embodiments of a smart leakage detection and alarm method for a distribution box of the present invention. The smart leakage detection and alarm method for a distribution box comprises the following steps: Step S1, obtaining the current and voltage of each component in the distribution box to be detected in the current time period, dividing the current time period equally to obtain a preset time period, and dividing the preset time period equally to obtain sub-time periods.

[0026] Among them, the distribution box to be detected can be a distribution box for leakage prediction, which can include a protective cover, a current sensor, a voltage sensor, an infrared thermal imaging device and a processing module, and the bent edge on the shell of the distribution box can be oriented toward the outside of the box. The protective cover can be used as the upper cover of the distribution box, which is mainly used to reduce the damage to the distribution box by external force, and can reduce the dust from entering the distribution box to a certain extent. The current sensor can be used to collect current. The voltage sensor can be used to collect voltage. The infrared thermal imaging device can be used to collect infrared images. The processing module can be used to implement the intelligent leakage detection alarm method of the distribution box. The components in the distribution box, also known as the components in the distribution box, can be contactors, fuses, capacitors or transformers. The current time period can represent a period of time with the current moment as the end moment. The duration corresponding to the preset time period can be less than the duration corresponding to the current time period. The duration corresponding to the preset time period can be greater than the duration corresponding to the sub-time period. For example, the duration corresponding to the current time period can be 5 minutes, the duration corresponding to the preset time period can be 1 minute, and the duration corresponding to the sub-time period can be 1 second.

[0027] It should be noted that the improvement of the distribution box of the present invention is mainly that, on the basis of the existing distribution box, a protective cover is added as the upper cover of the distribution box, and the direction of the bent edge on the distribution box shell that is facing the inner side of the box body is updated to face the outer side of the box body. A zero-ground row structure is often provided in the distribution box, but the existing distribution box often does not have a corresponding protective structure. The protective cover provided in the embodiment of the present invention can play a role in protecting the distribution box to a certain extent. The bent edges on the existing distribution box shell are often facing the inner side of the box body. After long-term use, dust often accumulates in the bent edges, which is not easy to clean. The embodiment of the present invention updates its direction to face the outer side of the box body, which can reduce dust deposition to a certain extent.

[0028] As an example, this step may include the following steps: The first step is to obtain the current and voltage of each component in the distribution box to be tested in the current time period.

[0029] For example, for any component in the distribution box to be detected, during the current time period, the current of the component can be collected every 0.1 second through a current sensor, and the voltage of the component can be collected every 0.1 second through a voltage sensor.

[0030] The second step is to divide the current time period into equal parts to obtain a preset time period, and to divide the preset time period into equal parts to obtain sub-time periods.

[0031] For example, if the current time period is 10 minutes, the preset time period is 1 minute, and the sub-time period is 1 second, the current time period can be divided into 10 preset time periods, and each preset time period can be divided into 60 sub-time periods.

[0032] Step S2, determining the operating power of each component in each sub-time period based on the current and voltage of each component in each sub-time period, and determining the isolated abnormal value of each component in each sub-time period based on the operating power of all components in each sub-time period.

[0033] As an example, this step may include the following steps: In the first step, the product of the current and the voltage of each component at each moment in each sub-time period is determined as the initial power of each component at each moment in each sub-time period.

[0034] In the second step, the average of the initial power of each component at all times in each sub-time period is determined as the operating power of each component in each sub-time period.

[0035] In the third step, based on the operating power of each component in all sub-time periods, the anomaly score of each component in each sub-time period is determined as an isolated outlier through the isolation forest algorithm.

[0036] Among them, the anomaly score is also called the isolation score.

[0037] It should be noted that if the isolated abnormal value of a component in a sub-time period is larger, it often means that the operating power of the component in the sub-time period is less similar to its operating power in other sub-time periods. In actual situations, the operating power distribution of normal components in a shorter operating time is often more uniform. Since the current time period can represent the current shorter time. Therefore, the larger the isolated abnormal value of a component in a sub-time period, it often means that the power of the component in the sub-time period is more abnormal.

[0038] Step S3, determining the parameter excess of each component in each preset time period according to the distribution changes of the operating power and isolated abnormal values ​​of each component in all sub-time periods in each preset time period, and screening out the heat source component from all components based on the parameter excess.

[0039] As an example, this step may include the following steps: In the first step, the product of the operating power of each component in each sub-time period and the isolated outlier value is determined as the possible initial heat loss factor of each component in each sub-time period.

[0040] For example, the formula corresponding to the possible factor of the initial heat loss of the component in the sub-time period can be: ;in, is the possible factor of initial heat loss of the ath component in the jth sub-time period in the tth preset time period. a is the serial number of the component in the distribution box to be detected. t is the number of preset time periods in the current time period. j is the serial number of the sub-time period in the tth preset time period. is the operating power of the ath element in the jth sub-time period within the tth preset time period. It is the isolated outlier value of the a-th element in the j-th sub-time period within the t-th preset time period.

[0041] It should be noted that when When it is larger, it often means that the operating power of the ath component in the jth sub-time period is higher, the operating intensity of the ath component in the jth sub-time period is greater, and the heat generated by the ath component in the jth sub-time period may be more, which often accelerates the damage and aging of the component. The larger the value is, the more likely it is that the operating power of the ath component in the jth sub-time period is abnormal. The larger it is, the more likely it is that the operating power of the a-th component in the j-th sub-time period will suddenly increase, the more likely it is that there will be abnormalities in the operation of the a-th component in the j-th sub-time period, the more likely it is that the a-th component will be damaged in the j-sub-time period, and the operation of the a-th component in the j-sub-time period will increase the risk of leakage in the next time period.

[0042] In the second step, the parameter excess of each component in each preset time period is determined based on the average of the initial heat loss possible factors of each component in all sub-time periods in each preset time period and the difference between the initial heat loss possible factors of each component in different sub-time periods in each preset time period.

[0043] For example, the formula corresponding to determining the parameter excess of a component within a preset time period may be: ;in, is the parameter excess of the ath component in the tth preset time period. a is the serial number of the component in the distribution box to be detected. t is the number of preset time periods in the current time period. is a normalization function. It is the average value of the initial heat loss possible factor of the a-th element in all sub-time periods within the t-th preset time period. is the possible factor of initial heat loss of the ath element in the first sub-period within the tth preset time period. The first sub-period within the preset time period may be the earliest sub-period within the preset time period.

[0044] It should be noted that when When the value is larger, it often indicates that the operating power of the ath component in the tth preset time period is more likely to have a sudden increase, and it often indicates that the operation of the ath component in the tth preset time period is more likely to increase the risk of leakage in the next time period. When the value is larger, it often means that the operating power of the ath component in the tth preset time period is more likely to show an increasing trend, and the degree of increase in the operating power is greater; it often means that the operation of the ath component in the tth preset time period is more abnormal, it often means that the ath component is more likely to be damaged in the tth preset time period, it often means that the aging of the ath component is more likely to be accelerated in the tth preset time period, and it often means that the operation of the ath component in the tth preset time period is more likely to increase the risk of leakage in the next time period. Therefore, when The larger the value, the more likely it is that the operation of the ath component in the tth preset time period will increase the risk of leakage in the next time period.

[0045] In the third step, the parameter excess of each component in all preset time periods within the current time period is combined to form a parameter excess set corresponding to each component.

[0046] In the fourth step, the maximum value in the parameter excess set corresponding to each component is determined as the representative excess of the parameter corresponding to each component.

[0047] In the fifth step, if the parameter corresponding to the component represents an excess greater than a preset heat source excess threshold, the component is determined as a heat source component.

[0048] The preset heat source excess threshold may be a pre-set threshold, which may be 0.8.

[0049] It should be noted that heat source components are often components with relatively high operating intensity and relatively high abnormal heat generation. Since abnormal heat tends to accelerate component aging, the risk of leakage in heat source components is relatively high.

[0050] Step S4, predicting the parameter excess predicted value of each heat source element in each preset future time period based on the parameter excess of each heat source element in all preset time periods within the current time period, and forming a parameter excess predicted value sequence corresponding to each heat source element.

[0051] The preset future time period may be a preset time period after the current time period. The number of preset future time periods may be 10, and the start time of the first preset future time period may be the end time of the current time period. The parameter excess prediction value is the parameter excess prediction value. The parameter excess prediction value sequence may be a time series. The parameter excess prediction value sequence corresponding to the heat source element may include: the parameter excess prediction value of the heat source element in all preset future time periods.

[0052] As an example, based on the parameter excess of each heat source element in all preset time periods within the current time period, the random forest algorithm is used to predict the predicted value of the parameter excess of each heat source element in each preset future time period as the parameter excess predicted value.

[0053] It should be noted that since parameter excess can characterize the abnormal heat accumulation to a certain extent, the parameter excess prediction value of the heat source element in the preset future time period can characterize the abnormal heat accumulation of the heat source element in the preset future time period to a certain extent. The larger the value, the higher the leakage risk of the heat source element in the preset future time period.

[0054] Step S5, determining the heat accumulation effect value corresponding to each heat source element according to the parameter excess prediction value sequence corresponding to each heat source element.

[0055] As an example, the formula for determining the heat accumulation effect value corresponding to the heat source element may be: ;in, is the heat accumulation effect value corresponding to the bth heat source element. b is the serial number of the heat source element. is a natural exponential function. It is the absolute value function. It is the mean of all parameter excess prediction values ​​in the parameter excess prediction value sequence corresponding to the bth heat source element.

[0056] It should be noted that since the range of the excess parameter is [0, 1], the range of the predicted excess parameter is also [0, 1]. The bigger, that is to say The closer it is to 1, the greater the abnormal heat accumulation of the bth heat source element in the preset future time period is likely to be, and the greater the possibility of leakage of the bth heat source element in the preset future time period is likely to be. The larger the value is, the greater the possibility that the bth heat source element will leak electricity within the preset future time period.

[0057] Step S6, based on the heat accumulation effect values ​​corresponding to all heat source elements, predict whether the distribution box to be tested will have leakage. If it is predicted that the distribution box to be tested will have leakage, an alarm message for reminding to prevent leakage anomalies is sent.

[0058] As an example, if the average of the heat accumulation effect values ​​corresponding to all heat source elements is greater than a preset heat accumulation threshold, it is predicted that a leakage phenomenon will occur in the distribution box to be detected.

[0059] The preset heat accumulation threshold may be a pre-set threshold, which may be 0.6.

[0060] It should be noted that when the mean value of the heat accumulation effect values ​​corresponding to all heat source elements is large, it often means that the abnormal heat accumulation degree of the elements in the distribution box to be tested may be large within the preset future time period, which often means that the distribution box to be tested is likely to have a leakage within the preset future time period, which often means that an alarm message should be sent to the staff to remind them to prevent leakage in the distribution box.

[0061] Optionally, after sending the alarm information for reminding to prevent leakage anomaly, the embodiment of the present invention may further include the following steps: In the first step, a preset number of heat source elements with the largest corresponding thermal accumulation effect values ​​are selected from all heat source elements as possible leakage anomaly elements.

[0062] The preset number may be a pre-set number, which may be 3.

[0063] It should be noted that the component with a possible leakage anomaly may represent a component that has a high probability of leakage occurring within a preset future time period.

[0064] The second step is to determine the heat loss possibility corresponding to each possible leakage abnormality component based on the heat accumulation effect value corresponding to each possible leakage abnormality component and the accumulated value of the heat accumulation effect values ​​corresponding to all heat source components.

[0065] The heat accumulation effect value corresponding to the leakage abnormality possible element may be positively correlated with the corresponding heat loss possibility. The accumulated value of the heat accumulation effect values ​​corresponding to all heat source elements may be positively correlated with the heat loss possibility.

[0066] For example, the formula for determining the heat loss probability corresponding to the component with leakage anomaly can be: ;in, is the heat loss probability corresponding to the kth possible leakage abnormal component. k is the serial number of the possible leakage abnormal component. is a normalization function. is the thermal accumulation effect value corresponding to the kth possible leakage abnormal component. G is the cumulative value of the thermal accumulation effect values ​​corresponding to all heat source components.

[0067] It should be noted that when When G is larger, it often indicates that the kth leakage abnormal component is more likely to leak in the preset future time period. When G is larger, it often indicates that all heat source components as a whole are more likely to leak in the preset future time period, and it often indicates that the kth leakage abnormal component belonging to the heat source component is more likely to leak in the preset future time period. Therefore, when The larger the value is, the greater the possibility that the kth leakage abnormal component will leak in the preset future time period.

[0068] In the third step, if the heat loss possibility corresponding to the leakage abnormality possible component is greater than a preset heat loss threshold, it is predicted that the leakage abnormality possible component will have leakage in a preset future time period.

[0069] The preset heat loss threshold may be a pre-set threshold, which may be 0.7.

[0070] It should be noted that the greater the possibility of heat loss corresponding to the component with leakage anomaly, the greater the possibility of leakage in the preset future time period. Therefore, based on the possibility of heat loss corresponding to the component with leakage anomaly, the component that may cause leakage in the preset future time period can be located relatively accurately, which can facilitate the staff to inspect and repair the components with leakage in a timely manner to prevent leakage of components in the distribution box. Secondly, in order to improve the positioning of components that may cause leakage in the preset future time period, infrared images collected by infrared thermal imaging equipment can be combined for analysis, where infrared images often contain the temperature conditions of different components in the distribution box.

[0071] The present invention provides a distribution box, which includes a protective cover, a current sensor, a voltage sensor, an infrared thermal imaging device and a processing module, and the bent edge on the shell of the distribution box faces the outside of the box body, and the processing module is used to implement any one of the above-mentioned intelligent leakage detection and alarm methods for the distribution box.

[0072] refer to Figure 2 Based on the same inventive concept as the above method embodiment, the present invention provides a smart leakage detection and alarm system for a distribution box, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the above computer program is executed by the processor, the steps of implementing a smart leakage detection and alarm method for a distribution box may specifically include: The acquisition and equal division module 201 is used to obtain the current and voltage of each component in the distribution box to be detected in the current time period, divide the current time period into equal parts to obtain a preset time period, and divide the preset time period into equal parts to obtain sub-time periods; A power and abnormality determination module 202, configured to determine the operating power of each component in each sub-time period based on the current and voltage of each component in each sub-time period, and to determine an isolated abnormal value of each component in each sub-time period based on the operating powers of all components in each sub-time period; A determination and screening module 203 is used to determine the parameter excess of each element in each preset time period according to the distribution change of the operating power and isolated abnormal values ​​of each element in all sub-time periods in each preset time period, and screen out the heat source element from all elements based on the parameter excess; The parameter excess prediction module 204 is used to predict the parameter excess prediction value of each heat source element in each preset future time period according to the parameter excess of each heat source element in all preset time periods in the current time period, so as to form a parameter excess prediction value sequence corresponding to each heat source element; The effect value determination module 205 is used to determine the heat accumulation effect value corresponding to each heat source element according to the parameter excess prediction value sequence corresponding to each heat source element; The prediction and sending module 206 is used to predict whether the distribution box to be tested will have leakage based on the heat accumulation effect values ​​corresponding to all heat source elements. If it is predicted that the distribution box to be tested will have leakage, an alarm message for reminding to prevent leakage abnormalities is sent.

[0073] Figure 3 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any one of the intelligent leakage detection and alarm methods for the distribution box introduced above.

[0074] Based on the same inventive concept as the above method embodiment, the present invention provides a server, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes any of the above intelligent leakage detection and alarm methods for distribution boxes.

[0075] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, it enables the computer to execute any one of the above-mentioned intelligent leakage detection and alarm methods for distribution boxes.

[0076] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned intelligent leakage detection and alarm methods for a distribution box.

[0077] In summary, compared with the leakage detection of the distribution box through the leakage protector, the present invention comprehensively considers multiple indicators related to the leakage trend, such as operating power, isolated outliers and parameter excess, and predicts multiple indicators related to future leakage conditions, such as parameter excess prediction value and thermal accumulation effect value, and then realizes the prediction of whether leakage phenomena will occur in the future, thereby improving the timeliness of leakage detection of the distribution box, and to a certain extent, it can achieve the prevention of future leakage phenomena, thereby reducing the occurrence of leakage phenomena.

[0078] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A smart leakage detection and alarm method for a distribution box, characterized in that: The following steps are involved: Obtain the current and voltage of each component in the distribution box to be tested in the current time period, divide the current time period equally to obtain a preset time period, and divide the preset time period equally to obtain sub-time periods; Determine the operating power of each component in each sub-time period based on the current and voltage of each component in each sub-time period, and determine an isolated outlier value of each component in each sub-time period based on the operating powers of all components in each sub-time period; Determine the parameter excess of each component in each preset time period according to the distribution change of the operating power and isolated abnormal values ​​of each component in all sub-time periods in each preset time period, and screen out the heat source component from all components based on the parameter excess; According to the parameter excess of each heat source element in all preset time periods within the current time period, the parameter excess predicted value of each heat source element in each preset future time period is predicted to form a parameter excess predicted value sequence corresponding to each heat source element; Determine the heat accumulation effect value corresponding to each heat source element according to the parameter excess prediction value sequence corresponding to each heat source element; Based on the heat accumulation effect values ​​corresponding to all heat source elements, it is predicted whether the distribution box to be tested will have leakage. If it is predicted that the distribution box to be tested will have leakage, an alarm message is sent to remind and prevent leakage anomalies.

2. The intelligent leakage detection and alarm method for a distribution box according to claim 1 is characterized in that: After sending the alarm information for reminding to prevent leakage abnormality, it also includes: Select a preset number of heat source elements with the largest corresponding heat accumulation effect values ​​from all heat source elements as possible leakage abnormal elements; According to the heat accumulation effect value corresponding to each possible leakage abnormality component and the accumulated value of the heat accumulation effect values ​​corresponding to all heat source components, the heat loss possibility corresponding to each possible leakage abnormality component is determined, wherein the heat accumulation effect value corresponding to the possible leakage abnormality component is positively correlated with the corresponding heat loss possibility, and the accumulated value of the heat accumulation effect values ​​corresponding to all heat source components is positively correlated with the heat loss possibility; If the heat loss probability corresponding to the leakage abnormality possible component is greater than a preset heat loss threshold, it is predicted that the leakage abnormality possible component will have a leakage phenomenon within a preset future time period.

3. The intelligent leakage detection and alarm method for a distribution box according to claim 1 is characterized in that: The step of determining the operating power of each component in each sub-time period based on the current and voltage of each component in each sub-time period comprises: The product of the current and the voltage of each element at each moment in each sub-time period is determined as the initial power of each element at each moment in each sub-time period; The average of the initial powers of each component at all times in each sub-time period is determined as the operating power of each component in each sub-time period.

4. The intelligent leakage detection and alarm method for a distribution box according to claim 1 is characterized in that: The step of determining an isolated abnormal value of each component in each sub-time period based on the operating power of all components in each sub-time period comprises: Based on the operating power of each component in all sub-time periods, the anomaly score of each component in each sub-time period is determined as an isolated outlier through the isolation forest algorithm.

5. The intelligent leakage detection and alarm method for a distribution box according to claim 1 is characterized in that: Determining the parameter excess of each component in each preset time period according to the distribution change of the operating power and isolated abnormal values ​​of each component in all sub-time periods in each preset time period includes: The product of the operating power of each component in each sub-time period and the isolated outlier value is determined as the possible initial heat loss factor of each component in each sub-time period; The parameter excess of each component in each preset time period is determined based on the average of the initial heat loss possibility factors of each component in all sub-time periods in each preset time period and the difference between the initial heat loss possibility factors of each component in different sub-time periods in each preset time period.

6. The intelligent leakage detection and alarm method for a distribution box according to claim 5 is characterized in that: The formula corresponding to the parameter excess of the component within the preset time period is: ;in, is the parameter excess of the ath component in the tth preset time period; a is the serial number of the component in the distribution box to be detected; t is the number of preset time periods in the current time period; is the normalization function; is the mean value of the initial heat loss possible factor of the ath element in all sub-time periods in the tth preset time period; It is the possible factor of initial heat loss of the ath element in the first sub-time period within the tth preset time period.

7. The intelligent leakage detection and alarm method for a distribution box according to claim 1 is characterized in that: Based on the parameter excess, the heat source components are screened out from all components, including: The parameter excess of each component in all preset time periods in the current time period is used to form a parameter excess set corresponding to each component; The maximum value in the parameter excess set corresponding to each element is determined as the parameter representative excess corresponding to each element; If the parameter corresponding to the element represents an excess greater than a preset heat source excess threshold, the element is determined as a heat source element.

8. The intelligent leakage detection and alarm method for a distribution box according to claim 1 is characterized in that: The formula corresponding to the heat accumulation effect value of the heat source element is: ;in, is the heat accumulation effect value corresponding to the bth heat source element; b is the serial number of the heat source element; is a natural exponential function; It is the absolute value function; It is the mean of all parameter excess prediction values ​​in the parameter excess prediction value sequence corresponding to the bth heat source element.

9. The intelligent leakage detection and alarm method for a distribution box according to claim 1 is characterized in that: The method of predicting whether leakage will occur in the distribution box to be tested based on the heat accumulation effect values ​​corresponding to all heat source elements includes: If the average of the heat accumulation effect values ​​corresponding to all heat source elements is greater than the preset heat accumulation threshold, it is predicted that the distribution box to be tested will have a leakage phenomenon.

10. A distribution box, characterized in that: It includes a protective cover, a current sensor, a voltage sensor, an infrared thermal imaging device and a processing module, and the bent edge on the shell of the distribution box faces the outside of the box body. The processing module is used to implement an intelligent leakage detection and alarm method for a distribution box as described in any one of claims 1-9.

Images