A leakage detection method and device for distribution box, distribution box and storage medium

Abstract

The present invention relates to a leakage detection method for a distribution box, and the technical field of leakage of distribution boxes includes the following steps: S1: real-time acquisition of current signals of each line in the distribution box, using a current transformer or a Hall effect sensor to acquire data; S2: using an adaptive sensitivity adjustment algorithm to automatically adjust the threshold of leakage detection according to real-time environmental parameters and historical data; S3: fast Fourier transform processing of the collected data; S4: when a suspected leakage event is initially detected, a secondary verification procedure is immediately started; S5: after confirming the leakage, the power supply is quickly cut off and an alarm message is sent to a user terminal. The present invention maintains optimal sensitivity and accuracy under different working conditions, avoiding the problem of missed detection or false alarm that may be caused by the traditional fixed threshold method in a complex environment.

Description

Technical Field

[0001] The present invention relates to the technical field of leakage current of a distribution box, and in particular to a leakage current detection method and device for a distribution box, a distribution box and a storage medium. Background Art

[0002] The distribution box leakage detection system plays a vital role in modern power systems. It is mainly used to monitor and detect leakage in the distribution network in real time, ensure the safe operation of electrical equipment, protect personnel from electric shock, and prevent safety accidents such as fire caused by leakage. By timely detecting and handling leakage problems, the system helps to improve the reliability and stability of power supply and reduce unnecessary power outages and maintenance costs.

[0003] Traditional leakage detection systems usually use fixed thresholds to determine whether there is leakage. However, the current fluctuations in the actual working environment are complex and are affected by many factors such as temperature, humidity, and load changes. The fixed threshold method cannot adapt to these dynamic changes, resulting in the system being unable to capture small but important leakage signals in a timely manner in some cases (such as in a humid environment or when the load suddenly increases).

[0004] Failure to detect leakage in time can lead to serious safety hazards, such as electric shock accidents or electrical fires. Once such an accident occurs, it will not only cause property damage, but also endanger the safety of personnel. Leakage that remains undetected for a long time may gradually damage electrical equipment, shorten its service life, and lead to higher repair and replacement costs. For example: In an industrial plant, due to high air humidity, a slight leakage occurs at some electrical joints. If the leakage detection system used is not sensitive enough, it may not detect this. As the leakage persists, local heating increases, which may eventually cause aging of the insulation material or even cause an electrical fire. Summary of the invention

[0005] The purpose of the present invention is to address the deficiencies in the prior art and provide a leakage detection method, device, distribution box and storage medium for a distribution box, which can well solve the above problems.

[0006] In order to achieve the above requirements, the technical solution adopted by the present invention to solve its technical problems is:

[0007] A method for detecting leakage of a distribution box is provided, comprising the following steps:

[0008] S1: collect current signals of each line in the distribution box in real time, and use current transformers or Hall effect sensors to obtain data;

[0009] S2: The adaptive sensitivity adjustment algorithm is used to automatically adjust the threshold of leakage detection according to real-time environmental parameters and historical data. The ASA algorithm uses a machine learning model to analyze the differences in current characteristics between past leakage cases and non-leakage cases, thereby distinguishing normal small fluctuations from abnormal leakage phenomena.

[0010] S3: Perform fast Fourier transform processing on the collected data to convert the time domain signal into the frequency domain signal to identify the characteristic spectrum that may be caused by leakage, and match these characteristics with the preset model. The preset model is established based on a large number of actual leakage cases and covers many different types of leakage modes;

[0011] S4: When a suspected leakage event is initially detected, a secondary verification procedure is immediately initiated, which triggers an additional sampling cycle, compares the results of multiple samplings to confirm whether leakage actually exists, and records the specific time and conditions of each sampling;

[0012] S5: After confirming the leakage, the power supply is quickly cut off and an alarm message is sent to the user terminal. The alarm content includes the specific leakage location, timestamp and recommended emergency measures.

[0013] Preferably, the detection method uses a deep learning algorithm to train historical leakage data and establish a prediction model, which can evaluate the probability distribution of leakage occurrence and provide a more refined risk assessment.

[0014] Preferably, the detection method of the present solution also includes an intelligent diagnosis system, which can generate detailed fault reports based on current and past operating states and provide targeted repair suggestions, while supporting natural language processing technology to make the output information easy to understand and execute.

[0015] In this embodiment, the adaptive sensitivity adjustment algorithm (ASA) in S2 includes an innovative formula for calculating the optimal threshold T opt ,Right now:

[0016] T opt =α·σ+β·I avg

[0017] Among them, T opt It represents the threshold value set for the best detection effect. α and β are proportional coefficients, which reflect the influence of environmental factors on the threshold value. They are usually determined by experiments. σ is the standard deviation of current fluctuations over a period of time, which is used to measure the degree of current change. avg It is the average current intensity over the same period of time and represents the current level expected under normal operating conditions.

[0018] Preferably, the detection method also includes a wireless communication module, which allows remote monitoring of the status of the distribution box and data sharing and command transmission through an Internet platform. The module supports common communication protocols such as Wi-Fi and Bluetooth, and is also compatible with low-power wide area network (LPWAN) protocols such as ZigBee and LoRaWAN.

[0019] In the preferred embodiment of the present invention, a new probability evaluation function P(e|d) is introduced in the secondary verification process of the suspected leakage event in the detection method to quantify the possibility that each detection result is a true positive. The function is defined as follows:

[0020]

[0021] Among them, P(e|d) represents the probability that the detection result is a real leakage, D represents the consistency of several consecutive detection results, that is, the measure of the similarity between multiple measurements, γ and δ are empirical parameters, usually obtained through a large number of experiments, which are used to adjust the sensitivity and specificity of the formula. When P(e|d) exceeds a certain set threshold, it is considered that actual leakage has occurred.

[0022] Preferably, the detection method further comprises a modular design, so that different functional components can be interchanged or upgraded, each module is equipped with a standardized interface, and hot-swap technology is adopted between the modules.

[0023] A leakage detection device for a distribution box, according to the detection method, the device at least comprises:

[0024] High-precision current sensors for precisely measuring current changes in each line;

[0025] Microprocessor unit, responsible for executing all the algorithms and logic operations mentioned above;

[0026] Large capacity memory to store required program codes, historical records and setting parameters;

[0027] Display screen or indicator light, providing an intuitive user interface;

[0028] Network connection module supports multiple communication protocols to ensure seamless connection with external systems;

[0029] The power management circuit ensures the stable power supply of the system and has a built-in backup battery.

[0030] A distribution box, comprising the leakage detection device, further comprising:

[0031] Built-in redundant protection module, even if the main control unit fails, it can maintain basic safety performance;

[0032] High-efficiency heat dissipation module ensures long-term working stability, and uses a combination of thermal conductive materials and fans to effectively remove heat;

[0033] Electromagnetic compatibility, reducing the impact of external interference, after rigorous testing, in line with international EMC standards;

[0034] Supports multi-level permission management, only authorized personnel can change key configurations, and built-in identity authentication module ensures the security of operations.

[0035] A computer-readable storage medium stores a computer program, which, when executed by a computer, enables the computer to execute the distribution box leakage detection method.

[0036] The beneficial effects of the present invention are:

[0037] The leakage detection method, device, distribution box, and storage medium of the distribution box, the ASA algorithm can automatically adjust the detection threshold according to real-time environmental parameters (such as temperature, humidity) and historical data. This enables the system to maintain optimal sensitivity and accuracy under different working conditions, avoiding the problems of missed detection or false alarms that may be caused by traditional fixed threshold methods in complex environments. ASA uses a machine learning model to analyze the differences in current characteristics between past leakage cases and non-leakage cases to ensure that it only responds to real leakage events, thereby greatly reducing false alarms caused by environmental factors or line noise.

[0038] By performing FFT processing on the collected data and converting the time domain signal into a frequency domain signal, the characteristic spectrum caused by leakage can be more accurately identified. This frequency component analysis method is more sensitive than traditional time domain analysis and can capture small and complex current fluctuations, improving the accuracy and reliability of detection. FFT processing not only helps confirm whether there is leakage, but also assists in determining the specific location of the leakage, providing important clues for subsequent maintenance work.

[0039] When a suspected leakage event is initially detected, the system immediately starts additional sampling cycles and compares the results of multiple samplings to confirm whether there is indeed a leakage phenomenon. This process effectively avoids the possible errors of a single detection point and greatly reduces the risk of misjudgment. Combined with the probability evaluation function P(e|d), the probability of each test result being a true positive is quantified, which further enhances the confidence in the leakage judgment and enables users to take more timely and effective countermeasures. Once the leakage is confirmed, the system can quickly cut off the power supply of the relevant lines to prevent further damage or danger. This rapid response mechanism greatly protects personnel safety and equipment integrity. At the same time, the system sends detailed alarm information to the user terminal, including the specific leakage location, timestamp, and recommended emergency measures. This instant notification and guidance function helps users take quick action to reduce losses and speed up the recovery process.

[0040] The system is able to self-optimize during operation by continuously adjusting the detection threshold through the ASA algorithm and generating detailed fault reports in conjunction with the intelligent diagnostic system. Over time, it can not only more accurately identify leakage events, but also better predict potential problems and provide more effective repair suggestions. This self-learning capability is rare in existing technologies and can significantly improve the long-term performance of the system. Even if the main control unit fails, the built-in redundant protection mechanism can still maintain basic safety performance. When a leakage is detected, the system quickly cuts off the power supply to prevent further damage or danger. This dual safety measure greatly improves the reliability of the system and ensures the safety of users, especially in extreme situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be further described below in conjunction with the accompanying drawings and embodiments. The drawings described below 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 work:

[0042] Figure 1 It is a flow chart of the leakage detection method of the distribution box of the present invention;

[0043] Figure 2 It is a further flow chart of the leakage detection method of the distribution box of the present invention. DETAILED DESCRIPTION

[0044] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present invention and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0045] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] "Multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0047] Moreover, the terms "up, down, left, right, upper end, lower end, longitudinal" and the like indicating directions are all based on the posture and position of the device or equipment described in this solution during normal use.

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the following will be described clearly and completely in combination with the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are partial embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.

[0049] This embodiment discloses Figure 1 and Figure 2 A leakage detection method for a distribution box is shown, comprising the following steps:

[0050] S1: Real-time collection of current signals of each line in the distribution box, using high-precision current transformers or Hall effect sensors for data acquisition; Use high-precision current transformers or Hall effect sensors connected to each line, sample current values ​​at a millisecond frequency, convert the analog signal output by the sensor into a digital signal, and input it into the microprocessor through an ADC (analog-to-digital converter);

[0051] S2: Use the adaptive sensitivity adjustment algorithm (ASA) to automatically adjust the threshold of leakage detection according to real-time environmental parameters (such as temperature and humidity) and historical data. The ASA algorithm analyzes the difference in current characteristics between past leakage cases and non-leakage cases through a machine learning model, thereby distinguishing normal small fluctuations from abnormal leakage phenomena. When the system is initialized, a pre-trained machine learning model is loaded. The model is based on a large amount of historical data (including normal and abnormal current patterns under ambient temperature and humidity conditions). At regular time intervals (for example, every minute), the ASA algorithm adjusts the threshold according to the current environmental parameters and recent historical data.

[0052] S3: Perform fast Fourier transform (FFT) processing on the collected data to convert the time domain signal into a frequency domain signal to identify the characteristic spectrum that may be caused by leakage, and match these characteristics with the preset model. The preset model is established based on a large number of actual leakage cases and covers many different types of leakage modes; Apply fast Fourier transform (FFT) to the collected current data to convert the time domain signal into a frequency domain signal, analyze the specific frequency components in the spectrum diagram, and identify the characteristic spectrum (such as high-frequency noise) that may be caused by leakage. If an abnormal spectrum is found, further analysis is triggered. For example, if an abnormally high energy level is detected in the frequency band above 50Hz, it is considered to be a leakage phenomenon;

[0053] S4: When a suspected leakage event is initially detected, a secondary verification program is immediately started, which triggers an additional sampling cycle to compare the results of multiple samplings to confirm whether there is indeed a leakage phenomenon, and records the specific time and conditions of each sampling; When a suspected leakage event is initially detected, an additional sampling cycle is immediately started (such as 10 consecutive samplings, each with an interval of 1 second), and the consistency of these 10 measurement results is calculated, and the probability evaluation function P(e|d) is applied to calculate the probability that each detection result is a real leakage. If it exceeds the set threshold (such as 0.9), it is confirmed to be a leakage;

[0054] S5: After confirming the leakage, the power supply is quickly cut off and an alarm message is sent to the user terminal. The alarm content includes the specific leakage location, timestamp and recommended emergency measures; after confirming the leakage, the microprocessor quickly cuts off the power supply of the relevant lines through the relay to prevent further damage or danger. At the same time, an alarm message is sent to the user terminal through the wireless communication module, including the specific leakage location, timestamp and recommended emergency measures.

[0055] In this embodiment, the detection method uses a deep learning algorithm to train historical leakage data and establish a prediction model. This model is not limited to a simple binary classification problem, but can evaluate the probability distribution of leakage occurrence and provide a more sophisticated risk assessment. The algorithm will continuously update its own weights, optimize the prediction accuracy with the addition of new data, reduce the false alarm rate and improve the accuracy of early warning. Build a deep neural network (DNN) and use the historical leakage data set for training. The data set should include normal working conditions and various types of leakage conditions. In the feature engineering stage, useful features such as current mean, variance, peak value, etc. are extracted and used as data for the input layer. The output layer uses a softmax activation function to output the probability distribution of various types of leakage. Update the model weights regularly, and optimize the prediction accuracy through online learning or batch learning as new data is added. For example: the trained model can predict the probability of leakage in a specific line within the next 24 hours, helping users take preventive measures in advance.

[0056] In this embodiment, the detection method also includes an intelligent diagnosis system, which can generate detailed fault reports based on the current and past operating status, and give targeted repair suggestions, while supporting natural language processing technology, so that the output information is easy to understand and execute. In addition, it also has self-learning capabilities, and can learn from each maintenance feedback, gradually improving the accuracy of diagnosis and the effectiveness of suggestions. The intelligent diagnosis system is built based on fault tree analysis (FTA) and generates detailed fault reports for different types of problems. The self-learning mechanism is implemented through a reinforcement learning algorithm. Whenever the user executes the recommended repair measures, the system will record the effect and adjust the future diagnostic logic accordingly. For example: If the user replaces an aging component as recommended by the system, and the same problem does not occur again afterwards, the system will increase the confidence in recommending this solution for this type of problem.

[0057] In this embodiment, the adaptive sensitivity adjustment algorithm (ASA) in S2 includes an innovative formula for calculating the optimal threshold T opt ,Right now:

[0058] T opt =α·σ+β·I avg

[0059] Among them, T opt It represents the threshold value set for the best detection effect. α and β are proportional coefficients, which reflect the influence of environmental factors on the threshold value. They are usually determined by experiments. σ is the standard deviation of current fluctuations over a period of time, which is used to measure the degree of current change. avgIt is the average current intensity during the same period of time, representing the expected current level under normal working conditions. This formula is designed to dynamically balance the relationship between high sensitivity and low false alarm rate, ensuring that leakage can be effectively detected without excessive false alarms under any circumstances.

[0060] In this embodiment, the detection method also includes a wireless communication module, which allows remote monitoring of the status of the distribution box and data sharing and command transmission through the Internet platform. The module supports common communication protocols such as Wi-Fi and Bluetooth, and is also compatible with low-power wide area network (LPWAN) protocols such as ZigBee and LoRaWAN to ensure good compatibility with other smart devices. In addition, the module also provides a security authentication mechanism to protect the security and privacy of communication data. The user device needs to pass identity authentication to establish a connection with the distribution box. The verification method can be a username and password, certificate or other strong authentication means. For example: the user can remotely view the status of the distribution box through an application on a smartphone. All communications are encrypted and protected, and the correct username and password must be entered when connecting for the first time.

[0061] In this embodiment, a new probability evaluation function P(e|d) is introduced in the secondary verification process of the suspected leakage event in the detection method to quantify the possibility that each detection result is a true positive. The function is defined as follows:

[0062]

[0063] Among them, P(e|d) represents the probability that the detection result is a real leakage, D represents the consistency of several consecutive detection results, that is, the measure of the similarity between multiple measurements, γ and δ are empirical parameters, usually obtained through a large number of experiments, used to adjust the sensitivity and specificity of the formula, when P(e|d) exceeds a certain set threshold, it is considered that actual leakage has occurred. This formula smoothly maps the detection results to a probability value between 0 and 1 in the form of a Sigmoid function, which helps to reduce the false alarm rate.

[0064] In this embodiment, the detection method also includes a modular design, so that different functional components can be easily interchanged or upgraded, and each module is equipped with a standardized interface, which is convenient for third-party developers to expand new features or services. In addition, the modules use hot-swap technology, which can replace or add modules without affecting the operation of the system, greatly improving the flexibility and maintainability of the system.

[0065] A leakage detection device for a distribution box, according to the detection method, the device at least comprises:

[0066] High-precision current sensors are used to accurately measure current changes in each line. The sensors have a wide frequency response range to ensure that tiny current fluctuations can be captured;

[0067] The microprocessor unit is responsible for executing all the algorithms and logic operations mentioned above. It has high-performance computing capabilities and low power consumption, and is suitable for long-term stable operation.

[0068] Large-capacity memory to store the required program code, historical records and setting parameters, and support long-term data recording for subsequent analysis;

[0069] Display screen or indicator light provides an intuitive user interface to display current status, alarm information and operation prompts;

[0070] Network connection module supports multiple communication protocols to ensure seamless connection with external systems;

[0071] The power management circuit ensures a stable power supply to the system, and the built-in backup battery maintains basic functions when the main power is disconnected.

[0072] High-precision current sensors accurately measure current changes, microprocessors are responsible for data processing and algorithm execution, large-capacity memory stores data, displays or indicator lights show status, network connection modules enable remote monitoring, and power management circuits ensure stable power supply. The components work closely together through wiring on the PCB board or dedicated connectors to form an efficient and stable system. For example: users can view the current value in real time through the LCD display, while the system background continuously monitors and records data for subsequent analysis.

[0073] A distribution box, comprising the leakage detection device, further comprising:

[0074] Built-in redundant protection module, which can maintain basic safety performance even if the main control unit fails, such as physical isolation through mechanical switches; redundant protection mechanism includes dual power input, backup battery and mechanical switch to ensure that basic functions can be maintained when the main control unit fails;

[0075] High-efficiency heat dissipation module ensures long-term working stability. It uses a combination of thermal conductive materials and fans to effectively remove heat and keep the internal temperature within a safe range.

[0076] Electromagnetic compatibility (EMC), reducing the impact of external interference, has been rigorously tested and complies with international EMC standards;

[0077] Supports multi-level permission management, only authorized personnel can change key configurations, built-in identity authentication module to ensure the security of operations. For example: when a user logs in to the distribution box management system, he must enter the correct user name and password and select the corresponding operation permission level.

[0078] A computer-readable storage medium having a computer program stored thereon, which, when executed by a computer, enables the computer to execute the distribution box leakage detection method. The storage medium can be any non-transient medium, such as a hard disk drive, a solid-state drive, a flash memory card, etc., and should include a complete software development kit (SDK) to facilitate integration into existing or future distribution management systems. In addition, the storage medium also includes a detailed user manual and technical documentation to help users better understand how to install, configure and use the solution provided by the present invention. A complete SDK is provided, including API documentation, sample code and developer guides, to help third parties integrate new technologies. The technical support document details the installation steps, configuration options and FAQs to ensure that users can smoothly deploy and use the system. For example: The SDK contains an API for creating new leakage detection rules, and users can write scripts according to their needs to expand the functionality of the system.

[0079] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all these improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. A method for detecting leakage of a distribution box, characterized in that: The following steps are involved: S1: collect current signals of each line in the distribution box in real time, and use current transformers or Hall effect sensors to obtain data; S2: The adaptive sensitivity adjustment algorithm is used to automatically adjust the threshold of leakage detection according to real-time environmental parameters and historical data. The ASA algorithm uses a machine learning model to analyze the differences in current characteristics between past leakage cases and non-leakage cases, thereby distinguishing normal small fluctuations from abnormal leakage phenomena. S3: Perform fast Fourier transform processing on the collected data to convert the time domain signal into the frequency domain signal to identify the characteristic spectrum that may be caused by leakage, and match these characteristics with the preset model. The preset model is established based on a large number of actual leakage cases and covers many different types of leakage modes; S4: When a suspected leakage event is initially detected, a secondary verification procedure is immediately initiated, which triggers an additional sampling cycle, compares the results of multiple samplings to confirm whether leakage actually exists, and records the specific time and conditions of each sampling; S5: After confirming the leakage, the power supply is quickly cut off and an alarm message is sent to the user terminal. The alarm content includes the specific leakage location, timestamp and recommended emergency measures.

2. The method for detecting leakage of a distribution box according to claim 1, characterized in that: The detection method uses a deep learning algorithm to train historical leakage data and establish a prediction model, which can evaluate the probability distribution of leakage occurrence and provide a more refined risk assessment.

3. The method for detecting leakage of a distribution box according to claim 2, characterized in that: The detection method also includes an intelligent diagnostic system that can generate detailed fault reports based on current and past operating states and provide targeted repair suggestions, while supporting natural language processing technology to make the output information easy to understand and execute.

4. The method for detecting leakage of a distribution box according to claim 3, characterized in that: The adaptive sensitivity adjustment algorithm (ASA) in S2 contains an innovative formula for calculating the optimal threshold T opt ,Right now: T opt =a·s+b·I avg Among them, T opt It represents the threshold value set for the best detection effect. α and β are proportional coefficients, which reflect the influence of environmental factors on the threshold value. They are usually determined by experiments. σ is the standard deviation of current fluctuations over a period of time, which is used to measure the degree of current change. avg It is the average current intensity over the same period of time and represents the current level expected under normal operating conditions.

5. The method for detecting leakage of a distribution box according to claim 4, characterized in that: The detection method also includes a wireless communication module, which allows remote monitoring of the status of the distribution box and realizes data sharing and command transmission through an Internet platform. The module supports common communication protocols such as Wi-Fi and Bluetooth.

6. A method for detecting leakage of a distribution box according to claim 5, characterized in that: The detection method introduces a new probability evaluation function P(e|d) in the secondary verification process of suspected leakage events to quantify the possibility of each detection result being a true positive. The function is defined as follows: Among them, P(e|d) represents the probability that the detection result is a real leakage, D represents the consistency of several consecutive detection results, that is, the measure of the similarity between multiple measurements, γ and δ are empirical parameters, usually obtained through a large number of experiments, which are used to adjust the sensitivity and specificity of the formula. When P(e|d) exceeds a certain set threshold, it is considered that actual leakage has occurred.

7. A method for detecting leakage of a distribution box according to claim 6, characterized in that: The detection method also includes a modular design, so that different functional components can be interchanged or upgraded, each module is equipped with a standardized interface, and hot-swap technology is used between modules.

8. A leakage detection device for a distribution box, according to the detection method according to any one of claims 1 to 7, characterized in that: The device comprises at least: High-precision current sensors for precisely measuring current changes in each line; Microprocessor unit, responsible for executing all the algorithms and logic operations mentioned above; Large capacity memory to store required program codes, historical records and setting parameters; Display screen or indicator light, providing an intuitive user interface; Network connection module supports multiple communication protocols to ensure seamless connection with external systems; The power management circuit ensures the stable power supply of the system and has a built-in backup battery.

9. A distribution box, comprising the leakage detection device according to claim 8, characterized in that: Also includes: Built-in redundant protection module, even if the main control unit fails, it can maintain basic safety performance; High-efficiency heat dissipation module ensures long-term working stability, and uses a combination of thermal conductive materials and fans to effectively remove heat; Electromagnetic compatibility, reducing the impact of external interference, after rigorous testing, in line with international EMC standards; Supports multi-level permission management, only authorized personnel can change key configurations, and built-in identity authentication module ensures the security of operations.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a computer, enables the computer to execute the method for detecting leakage of a distribution box according to any one of claims 1 to 7.

Images