Electric leakage detection early warning system adaptive to operation of distribution box

Abstract

The invention belongs to the field of electric leakage detection, relates to a data analysis technology, is used for solving the problem that dynamic threshold distribution cannot be performed through a scene recognition result in the prior art, and particularly relates to an electric leakage detection early warning system adaptive to operation of a distribution box, which comprises a scene recognition module, an electric leakage detection module and a prediction analysis module which are connected in sequence, the scene recognition module, the electric leakage detection module and the prediction analysis module are all in communication connection with the database; the scene identification module is used for identifying and analyzing an operation scene of the distribution box: marking the distribution box as a detection object, marking a key node in the detection object as an identification object, and judging whether the identification object is in a temperature abnormal scene, a load abnormal scene and a cable abnormal scene; according to the invention, electric leakage detection analysis can be carried out on the distribution box, a dynamic detection threshold value is generated according to a scene identification result, value reduction processing is carried out on the electric leakage threshold value in an abnormal scene, and the identification success rate of an electric leakage fault is improved.

Description

Technical Field

[0001] The invention belongs to the field of leakage detection and relates to data analysis technology, and specifically is a leakage detection and early warning system suitable for the operation of a distribution box. Background Art

[0002] The distribution box leakage detection and early warning system is an intelligent electrical safety monitoring device designed specifically for the distribution box environment. It can monitor key parameters such as leakage current, temperature, and voltage in real time, and issue multi-level early warnings when an abnormality is detected, effectively preventing electrical fires, equipment damage, and electric shock accidents, and ensuring electricity safety.

[0003] The invention patent with announcement number CN116930816B discloses a leakage detection method, device, distribution box and storage medium for a distribution box. The detection method can determine that the eddy current effect generated by the leakage of the convergence module of the metal backplane causes a temperature rise phenomenon, thereby realizing the monitoring of leakage in the distribution box, and using the temperature to reflect the leakage fault of the distribution box, effectively improving the reliability, sensitivity and anti-interference ability of leakage detection, and having universal application; however, the detection method cannot perform dynamic threshold allocation through scene recognition results, and the same standard is used for leakage detection in scenarios with different leakage hazards, resulting in low accuracy of the leakage detection results; at the same time, it is impossible to combine the scene recognition results with the leakage detection results for predictive analysis, resulting in the inability to effectively curb leakage faults and fire accidents in the distribution box.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a leakage detection and early warning system adapted for the operation of a distribution box, which is used to solve the problem that the prior art cannot dynamically allocate thresholds through scene recognition results; The technical problem to be solved by the present invention is: how to provide a leakage detection and early warning system suitable for the operation of a distribution box, which can dynamically allocate thresholds based on scene recognition results.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A leakage detection and early warning system adapted for operation of a distribution box, comprising a scene recognition module, a leakage detection module and a prediction and analysis module connected in sequence, wherein the scene recognition module, the leakage detection module and the prediction and analysis module are all connected to a database for communication; The scene recognition module is used to identify and analyze the operation scene of the distribution box: mark the distribution box as a detection object, mark the key nodes inside the detection object as identification objects, and determine whether the identification object is in a temperature abnormality scene, a load abnormality scene, and a cable abnormality scene; The leakage detection module is used to detect and analyze the leakage of the distribution box: determine whether there is an identified object in the temperature anomaly scenario, load anomaly scenario or cable anomaly scenario in the detection object. If not, obtain the leakage threshold from the database and mark the leakage threshold as the detection threshold. If so, obtain the leakage threshold from the database and perform a proportional reduction process on the leakage threshold to obtain the detection threshold. Obtain the leakage current of the identified object and mark it as the detection value, compare the detection value with the detection threshold, and determine whether there is a leakage fault in the detection object based on the comparison result. The prediction and analysis module is used to regularly perform leakage prediction and analysis on the distribution box.

[0007] Further, the specific process of determining whether the identified object is in the temperature anomaly scenario includes: obtaining the air temperature value of the space where the identified object is located in real time and marking it as the temperature detection data, retrieving the temperature detection range from the database, and determining whether the temperature detection data of the identified object is within the temperature detection range. If so, it is determined that the identified object is in the normal temperature scenario. If not, it is determined that the identified object is in the temperature anomaly scenario. The specific process of determining whether the identified object is in the load anomaly scenario includes: obtaining the distribution load of the identification node in real time and marking it as the load data, retrieving the load range from the database, and determining whether the load data of the identified object is within the load range. If so, it is determined that the identified object is in the normal load scenario. If not, it is determined that the identified object is in the load anomaly scenario.

[0008] Further, the specific process of determining whether the identified object is in the cable anomaly scenario includes: taking an image of the cable connected to the identified object to obtain a corrosion detection image, magnifying the corrosion detection image into a pixel grid image and performing gray-scale transformation, obtaining the corrosion gray-scale range and the corrosion warning threshold from the database, marking the pixel grids with gray-scale values within the corrosion gray-scale range in the corrosion detection image as corrosion grids, marking the ratio of the number of corrosion grids to the total number of pixel grids in the corrosion detection image as the corrosion coefficient of the identified object, and comparing the corrosion coefficient with the corrosion warning threshold. If the corrosion coefficient is less than the corrosion warning threshold, it is determined that the identified object is in the normal cable scenario. If the corrosion coefficient is greater than or equal to the corrosion warning threshold, it is determined that the identified object is in the cable anomaly scenario, and at the same time, a cable replacement signal is generated and sent to the mobile terminal of the management personnel.

[0009] Further, the process of proportional reduction is: multiplying the value of the leakage threshold by the proportional coefficient t1 to obtain the value of the detection threshold, and the value range of t1 is (0.85, 0.95).

[0010] Furthermore, the specific process of the predictive analysis module for regularly performing leakage prediction analysis on the distribution box includes: performing predictive analysis once every L1 seconds: generating a temperature detection sequence, a load sequence, a corrosion sequence, and a detection sequence; performing numerical processing on the sequence numbers of all identified objects in the temperature detection sequence, the load sequence, the corrosion sequence, and the detection sequence to obtain a prediction coefficient; and determining whether there is a leakage hazard for the detected object based on the prediction coefficient.

[0011] Furthermore, the generation process of the temperature detection sequence, the load sequence, the corrosion sequence, and the detection sequence includes: arranging all identified objects in descending order of temperature detection data to obtain the temperature detection sequence, arranging all identified objects in descending order of load data to obtain the load sequence, arranging all identified objects in descending order of corrosion coefficient to obtain the corrosion sequence, and arranging all identified objects in descending order of detection value to obtain the detection sequence.

[0012] Furthermore, the process of obtaining the prediction coefficient includes: marking the absolute value of the difference between the sequence number of the identified object in the temperature detection sequence and the sequence number in the detection sequence as the temperature detection coincidence value of the identified object, summing and averaging the temperature detection coincidence values of all identified objects to obtain the temperature detection coincidence data, marking the absolute value of the difference between the sequence number of the identified object in the load sequence and the sequence number in the detection sequence as the load coincidence value, summing and averaging the load coincidence values of all identified objects to obtain the load coincidence data, marking the absolute value of the difference between the sequence number of the identified object in the corrosion sequence and the sequence number in the detection sequence as the corrosion coincidence value, summing and averaging the corrosion coincidence values of all identified objects to obtain the corrosion coincidence data, and performing numerical calculation on the temperature detection coincidence data, the load coincidence data, and the corrosion coincidence data to obtain the prediction coefficient.

[0013] Furthermore, the specific process of determining whether there is a leakage hazard for the detected object includes: obtaining the prediction threshold through the database, comparing the prediction coefficient with the prediction threshold: if the prediction coefficient is less than or equal to the prediction threshold, it is determined that the detected object has a leakage hazard, generating a prediction warning signal and sending the prediction warning signal to the mobile terminal of the management personnel; if the prediction coefficient is greater than the prediction threshold, it is determined that the detected object does not have a leakage hazard.

[0014] The present invention has the following beneficial effects: 1. Through the scenario recognition module, the operation scenario of the distribution box can be recognized and analyzed. After collecting and processing various hidden danger parameters of the identified object, multiple abnormal scenarios of the identified object can be recognized and marked, providing data support for the leakage detection process; 2. The leakage detection module can detect and analyze the leakage of the distribution box, generate a dynamic detection threshold according to the scene recognition result, reduce the value of the leakage threshold in abnormal scenarios, improve the recognition success rate of leakage faults, and perform power-off processing in a timely manner, thereby reducing the severity of the accident impact when a leakage fault occurs in abnormal scenarios; 3. The prediction analysis module can regularly perform leakage prediction analysis on the distribution box, comprehensively analyze the parameter values in the scene recognition process and the detection values in the leakage detection process to obtain a prediction coefficient, and determine whether the severity of the operating scenario in the high-leakage fault probability area is higher through the prediction coefficient, so as to identify leakage hidden dangers according to the prediction coefficient and reduce the actual leakage fault probability of the distribution box. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a system block diagram of Embodiment 1 of the present invention; Figure 2 It is a method flow chart of Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following will clearly and completely describe the technical solutions of the present invention in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0018] Embodiment 1: As Figure 1 shown, a leakage detection and early warning system adapted to the operation of the distribution box includes a scene recognition module, a leakage detection module, and a prediction analysis module connected in sequence. The scene recognition module, the leakage detection module, and the prediction analysis module are all communicatively connected to the database.

[0019] The scene recognition module is used to identify and analyze the operating scene of the distribution box: mark the distribution box as the detection object, and mark the key nodes inside the detection object as the recognition objects.

[0020] Obtain the air temperature value of the space where the recognition object is located in real time and mark it as temperature detection data. The air temperature value is collected by a thermocouple temperature sensor. A thermocouple is a temperature sensor based on the Seebeck Effect. When two different metal conductors form a closed loop, if there is a temperature difference at both ends, an electromotive force (thermoelectric potential) will be generated in the loop. This phenomenon is called the thermoelectric effect. Retrieve the temperature detection range from the database to determine whether the temperature detection data of the recognition object is within the temperature detection range: If so, it is determined that the recognition object is in a normal temperature scenario; if not, it is determined that the recognition object is in an abnormal temperature scenario. Obtain the power distribution load of the recognition node in real time and mark it as load data. Retrieve the load range from the database to determine whether the load data of the recognition object is within the load range: If so, it is determined that the recognition object is in a normal load scenario; if not, it is determined that the recognition object is in an abnormal load scenario. Take an image of the cable connected to the recognition object to obtain a corrosion detection image. Enlarge the corrosion detection image into a pixel grid image and perform gray-scale transformation. Obtain the corrosion gray-scale range and the corrosion warning threshold from the database. Mark the pixel grids in the corrosion detection image whose gray-scale values are within the corrosion gray-scale range as corrosion grids. Mark the ratio of the number of corrosion grids to the total number of pixel grids in the corrosion detection image as the corrosion coefficient of the recognition object. Compare the corrosion coefficient with the corrosion warning threshold: If the corrosion coefficient is less than the corrosion warning threshold, it is determined that the recognition object is in a normal cable scenario; if the corrosion coefficient is greater than or equal to the corrosion warning threshold, it is determined that the recognition object is in an abnormal cable scenario, and at the same time, a cable replacement signal is generated and sent to the mobile terminal of the management personnel. Identify and analyze the operation scenario of the distribution box. After collecting and processing the hidden danger parameters of the recognition object, identify and mark multiple abnormal scenarios of the recognition object to provide data support for the leakage detection process.

[0021] The leakage detection module is used to perform leakage detection and analysis on the distribution box: Determine whether there is a recognition object in the abnormal temperature scenario, abnormal load scenario, or abnormal cable scenario within the detection object. If not, obtain the leakage threshold from the database and mark it as the detection threshold. If so, obtain the leakage threshold from the database and perform an equal-proportion value reduction process on the leakage threshold to obtain the detection threshold. The equal-proportion value reduction process is: Multiply the value of the leakage threshold by the proportionality coefficient t1 to obtain the value of the detection threshold. The value range of t1 is (0.85, 0.95). This process is to dynamically allocate the numerical value of the detection threshold and optimize the detection standard of the leakage current in the presence of abnormal scenarios (high probability of leakage failure and high severity during failure). Obtain the leakage current of the identified object and mark it as the detected value. The leakage current is collected by a residual current sensor. A residual current sensor, also known as a leakage current sensor, is a dedicated sensor for detecting the residual current (leakage current) in a circuit and is the core detection element in an electrical safety protection system. Compare the detected value with the detection threshold: If the detected values of all identified objects are less than the detection threshold, it is determined that there is no leakage fault in the detected object; otherwise, it is determined that there is a leakage fault in the detected object. The power distribution box is powered off through a circuit breaker, and at the same time, a leakage fault signal is generated and sent to the mobile terminal of the management personnel. Conduct a leakage detection and analysis of the power distribution box, generate a dynamic detection threshold according to the scene recognition result, reduce the leakage threshold value in an abnormal scene, improve the recognition success rate of leakage faults, and perform a power-off process in a timely manner, thereby reducing the severity of the accident impact when a leakage fault occurs in an abnormal scene.

[0022] The prediction and analysis module is used to regularly conduct a leakage prediction and analysis of the power distribution box: perform a prediction and analysis every L1 seconds. Arrange all identified objects in descending order of temperature detection data to obtain a temperature detection sequence, arrange all identified objects in descending order of load data to obtain a load sequence, arrange all identified objects in descending order of corrosion coefficient to obtain a corrosion sequence, and arrange all identified objects in descending order of detected value to obtain a detection sequence. L1 is a numerical constant, and the specific value of L1 is set by the management personnel themselves. Mark the absolute value of the difference between the sequence number of the identified object in the temperature detection sequence and the sequence number in the detection sequence as the temperature detection coincidence value of the identified object. Sum and average the temperature detection coincidence values of all identified objects to obtain temperature detection coincidence data. Mark the absolute value of the difference between the sequence number of the identified object in the load sequence and the sequence number in the detection sequence as the load coincidence value. Sum and average the load coincidence values of all identified objects to obtain load coincidence data. Mark the absolute value of the difference between the sequence number of the identified object in the corrosion sequence and the sequence number in the detection sequence as the corrosion coincidence value. Sum and average the corrosion coincidence values of all identified objects to obtain corrosion coincidence data. After assigning weight coefficients k1, k2, and k3 to the temperature detection coincidence data, load coincidence data, and corrosion coincidence data respectively, perform a weighted summation calculation to obtain a prediction coefficient, where k1 > k2 > k3. Obtain the prediction threshold through the database, and compare the prediction coefficient with the prediction threshold: If the prediction coefficient is less than or equal to the prediction threshold, it is determined that there is a potential leakage hazard in the detection object, a prediction warning signal is generated and sent to the mobile terminal of the management personnel; if the prediction coefficient is greater than the prediction threshold, it is determined that there is no potential leakage hazard in the detection object; Regularly conduct leakage prediction analysis on the distribution box, comprehensively analyze the parameter values in the scenario recognition process and the detection values in the leakage detection process to obtain the prediction coefficient, and determine whether the severity of the operating scenario in the high leakage fault probability area is higher through the prediction coefficient, so as to identify potential leakage hazards according to the prediction coefficient and reduce the actual leakage fault probability of the distribution box.

[0023] Embodiment 2: As Figure 2 shown, a leakage detection and warning method adapted to the operation of a distribution box includes the following steps: Step 1: Identify and analyze the operating scenario of the distribution box: Mark the distribution box as the detection object, mark the key nodes inside the detection object as the identification objects, and identify and mark the abnormal scenarios of the identification objects; Step 2: Conduct leakage detection and analysis on the distribution box: Obtain the leakage current of the identification object and mark it as the detection value, mark the detection threshold through the abnormal scenario recognition results of all identification objects, compare the detection value with the detection threshold, and determine whether there is a leakage fault in the detection object based on the comparison result; Step 3: Regularly conduct leakage prediction analysis on the distribution box: Conduct a prediction analysis every L1 seconds and obtain the prediction coefficient of the detection object, compare the prediction coefficient with the prediction threshold, and determine whether there is a potential leakage hazard in the detection object based on the comparison result.

[0024] A leakage detection and warning system adapted to the operation of a distribution box, when working, marks the distribution box as the detection object, marks the key nodes inside the detection object as the identification objects, and identifies and marks the abnormal scenarios of the identification objects; obtains the leakage current of the identification object and marks it as the detection value, marks the detection threshold through the abnormal scenario recognition results of all identification objects, compares the detection value with the detection threshold, and determines whether there is a leakage fault in the detection object based on the comparison result; conducts a prediction analysis every L1 seconds and obtains the prediction coefficient of the detection object, compares the prediction coefficient with the prediction threshold, and determines whether there is a potential leakage hazard in the detection object based on the comparison result.

[0025] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of this technology make various modifications or supplements to the described specific embodiments or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined by this claim book, they should all belong to the protection scope of the present invention.

[0026] In the description of this specification, the descriptions referring to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples.

[0027] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific embodiments. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A leakage detection and warning system adapted to the operation of a distribution box, characterized in that, It includes a scene recognition module, a leakage detection module, and a prediction analysis module connected in sequence. The scene recognition module, the leakage detection module, and the prediction analysis module are all communicatively connected to the database; The scene recognition module is used to identify and analyze the operating scene of the distribution box: mark the distribution box as the detection object, mark the key nodes inside the detection object as the recognition objects, and determine whether the recognition objects are in the temperature anomaly scene, the load anomaly scene, and the cable anomaly scene; The leakage detection module is used to detect and analyze the leakage of the distribution box: determine whether there are recognition objects in the temperature anomaly scene, the load anomaly scene, or the cable anomaly scene in the detection object. If not, obtain the leakage threshold from the database and mark the leakage threshold as the detection threshold; if so, obtain the leakage threshold from the database and perform an equal-proportion value reduction process on the leakage threshold to obtain the detection threshold; obtain the leakage current of the recognition object and mark it as the detection value, compare the detection value with the detection threshold, and determine whether there is a leakage fault in the detection object based on the comparison result; The prediction analysis module is used to regularly perform leakage prediction analysis on the distribution box.

2. The leakage detection and early warning system adapted to the operation of the distribution box according to claim 1, characterized in that, The specific process of determining whether the recognition object is in the temperature anomaly scene includes: obtaining the air temperature value of the space where the recognition object is located in real time and marking it as the temperature detection data, retrieving the temperature detection range from the database, and determining whether the temperature detection data of the recognition object is within the temperature detection range. If so, it is determined that the recognition object is in the normal temperature scene; if not, it is determined that the recognition object is in the temperature anomaly scene; The specific process of determining whether the recognition object is in the load anomaly scene includes: obtaining the distribution load of the recognition node in real time and marking it as the load data, retrieving the load range from the database, and determining whether the load data of the recognition object is within the load range. If so, it is determined that the recognition object is in the normal load scene; if not, it is determined that the recognition object is in the load anomaly scene.

3. The leakage detection and early warning system adapted to the operation of the distribution box according to claim 2, characterized in that The specific process of determining whether the recognition object is in the cable anomaly scene includes: taking an image of the cable connected to the recognition object to obtain a corrosion detection image, magnifying the corrosion detection image into a pixel grid image and performing gray-scale transformation, obtaining the corrosion gray-scale range and the corrosion warning threshold from the database, marking the pixel grids with gray-scale values within the corrosion gray-scale range in the corrosion detection image as corrosion grids, marking the ratio of the number of corrosion grids to the total number of pixel grids in the corrosion detection image as the corrosion coefficient of the recognition object, and comparing the corrosion coefficient with the corrosion warning threshold. If the corrosion coefficient is less than the corrosion warning threshold, it is determined that the recognition object is in the normal cable scene; if the corrosion coefficient is greater than or equal to the corrosion warning threshold, it is determined that the recognition object is in the cable anomaly scene, and at the same time, a cable replacement signal is generated and sent to the mobile terminal of the management personnel.

4. A leakage detection and warning system adapted to the operation of a distribution box according to claim 3, characterized in that, The process of equal-proportion value reduction is: multiplying the value of the leakage threshold by the proportionality coefficient t1 to obtain the value of the detection threshold, and the value range of t1 is (0.85, 0.95).

5. The leakage detection and warning system adapted to the operation of the distribution box according to claim 4, characterized in that, The specific process of the predictive analysis module for regularly conducting leakage prediction and analysis on the distribution box includes: performing prediction and analysis every L1 seconds, generating a temperature detection sequence, a load sequence, a corrosion sequence, and a detection sequence, numerically processing the sequence numbers of all identified objects in the temperature detection sequence, the load sequence, the corrosion sequence, and the detection sequence to obtain a prediction coefficient, and determining whether there is a leakage hazard for the detected object based on the prediction coefficient.

6. The leakage detection and warning system adapted to the operation of the distribution box according to claim 5, wherein The generation process of the temperature detection sequence, the load sequence, the corrosion sequence, and the detection sequence includes: arranging all identified objects in descending order of temperature detection data to obtain the temperature detection sequence, arranging all identified objects in descending order of load data to obtain the load sequence, arranging all identified objects in descending order of corrosion coefficient to obtain the corrosion sequence, and arranging all identified objects in descending order of detection value to obtain the detection sequence.

7. The leakage detection and warning system adapted to the operation of the distribution box according to claim 6, characterized in that, The process of obtaining the prediction coefficient includes: marking the absolute value of the difference between the sequence number of the identified object in the temperature detection sequence and the sequence number in the detection sequence as the temperature detection coincidence value of the identified object, summing and averaging the temperature detection coincidence values of all identified objects to obtain the temperature detection coincidence data, marking the absolute value of the difference between the sequence number of the identified object in the load sequence and the sequence number in the detection sequence as the load coincidence value, summing and averaging the load coincidence values of all identified objects to obtain the load coincidence data, marking the absolute value of the difference between the sequence number of the identified object in the corrosion sequence and the sequence number in the detection sequence as the corrosion coincidence value, summing and averaging the corrosion coincidence values of all identified objects to obtain the corrosion coincidence data, and performing numerical calculations on the temperature detection coincidence data, the load coincidence data, and the corrosion coincidence data to obtain the prediction coefficient.

8. The leakage detection and warning system adapted to the operation of the distribution box according to claim 7, wherein, The specific process of determining whether there is a leakage hazard for the detected object includes: obtaining the prediction threshold through the database, comparing the prediction coefficient with the prediction threshold. If the prediction coefficient is less than or equal to the prediction threshold, it is determined that there is a leakage hazard for the detected object, a prediction warning signal is generated and sent to the mobile terminal of the management personnel. If the prediction coefficient is greater than the prediction threshold, it is determined that there is no leakage hazard for the detected object.

Images