Interlocking remote control system and method based on low-voltage power distribution cabinet

Abstract

The invention discloses an interlocking remote control system based on a low-voltage power distribution cabinet. The interlocking remote control system comprises a data acquisition module for acquiring operation data of the power distribution cabinet in real time; the edge calculation unit is used for data preprocessing, interlocking logic calculation and anomaly detection; the interlocking control execution module is used for receiving a control signal of the edge computing unit and realizing protective disconnection and restart of the equipment; the communication module supports two-way transmission of data in the data acquisition module, the edge computing unit and the cloud; the interlocking remote control method based on the low-voltage power distribution cabinet comprises the following steps: S1, system architecture design; s2, data acquisition and preprocessing; s3, constructing a self-adaptive interlocking logic control algorithm; s4, edge calculation and cloud collaboration; and S5, verifying and optimizing system functions. According to the invention, the health state of the equipment can be monitored, faults can be rapidly identified, the equipment is protected through an interlocking control mechanism, the operation efficiency of the low-voltage power distribution cabinet is effectively improved, the equipment safety is improved, faults are reduced, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of power distribution cabinet control, and in particular to a remote control system based on a low-voltage power distribution cabinet interlocking and a method thereof. Background Art

[0002] Low-voltage distribution cabinets are important equipment in power systems and are widely used in various types of industrial, commercial and residential power distribution. Traditional distribution cabinet control systems usually rely on fixed control logic and lack real-time monitoring and dynamic response capabilities for operating status, which limits the flexibility and stability of the system. Especially in abnormal conditions, they cannot respond in time, which may cause equipment damage or operation interruption. In order to improve the reliability and intelligence level of low-voltage distribution cabinets, in recent years, intelligent distribution control systems based on emerging technologies such as the Internet of Things, big data, edge computing and cloud computing have gradually been widely used. The introduction of these technologies enables distribution cabinets to achieve more efficient and precise control and monitoring.

[0003] In the existing technology, although the model of edge computing and cloud collaboration has been applied, many intelligent control systems still face the following challenges: First, the interlocking control logic often relies on historical data or empirical rules and cannot flexibly adjust the control strategy according to real-time data; second, the system usually has problems of insufficient computing power or response delay, which makes it impossible for the distribution cabinet to respond quickly when an abnormality occurs. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above-mentioned problems existing in the existing low-voltage distribution cabinet interlocking remote control system and method thereof, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a remote control system based on low-voltage distribution cabinet interlocking and a method thereof, which is suitable for solving the problem that the interlocking control logic often relies on historical data or empirical rules and cannot flexibly adjust the control strategy according to real-time data.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: based on the low-voltage distribution cabinet interlocking remote control system, comprising:

[0008] Data acquisition module: collects the operation data of the power distribution cabinet in real time;

[0009] Edge computing unit: data preprocessing, interlocking logic calculation and anomaly detection;

[0010] Interlocking control execution module: receives control signals from the edge computing unit to implement protective disconnection and restart of the equipment;

[0011] Communication module: supports two-way data transmission between data acquisition module, edge computing unit and cloud;

[0012] Cloud server: optimizes the interlocking strategy based on historical data and sends the optimized model to the edge computing unit;

[0013] User terminal: provides human-computer interaction interface.

[0014] Based on the low-voltage distribution cabinet interlocking remote control method, the control method is applicable to the above control system, and the control method includes the following steps:

[0015] S1: System architecture design;

[0016] S2: Data collection and preprocessing;

[0017] S3: Construction of adaptive interlocking logic control algorithm;

[0018] S4: Edge computing and cloud collaboration;

[0019] S5: System function verification and optimization.

[0020] As a preferred solution of the low-voltage distribution cabinet interlocking remote control method of the present invention, the construction of the adaptive interlocking logic control algorithm is achieved by the following steps:

[0021] S31: Setting of initial logic rules;

[0022] S32: Use the edge computing module to update the machine learning model in real time, build a comprehensive scoring formula for multi-dimensional operation data deviation, adjust the weight and priority of the interlocking logic according to the collected data, and use the deep learning algorithm to optimize the machine learning model;

[0023] S33: Based on real-time data, the edge computing module dynamically generates the optimal interlocking decision tree and quickly adjusts the logic rules;

[0024] The multi-dimensional operation data deviation comprehensive scoring formula is as follows:

[0025]

[0026] Among them, S k Indicates the comprehensive deviation score of device k at the current time, reflecting its overall operational health status. represents the i-th operation data of device k, μ i is the historical mean of the i-th item of equipment operation data, which is used to measure the normal operation status, σ irepresents the historical standard deviation of the ith item of equipment operation data, which is used to characterize the fluctuation range, w i Represents the weight coefficient of each running data, which is dynamically adjusted by the machine learning model to reflect the importance of different data items. k Represents the model bias term of device k, which is used to correct the overall score.

[0027] As a preferred solution of the low-voltage distribution cabinet interlocking remote control method described in the present invention, a comprehensive deviation threshold S is constructed in the output result of the multi-dimensional operation data deviation comprehensive scoring formula. t ;

[0028] If S k ≤S t , it means the device is operating normally;

[0029] If S k >S t , indicating that the device is operating abnormally and requires further in-depth analysis.

[0030] As a preferred solution of the low-voltage distribution cabinet interlocking remote control method described in the present invention, a deep learning interlocking abnormality threshold evaluation formula is constructed according to the output result of the multi-dimensional operation data deviation from the comprehensive scoring formula, and the deep learning interlocking abnormality threshold evaluation formula is as follows:

[0031]

[0032] Among them, T k represents the deep learning anomaly score of device k, which is used for the final interlocking judgment. λ represents the adjustment parameter of the deep learning model, which is used to control the score growth rate. β k Represents the score offset of device k, which is used to adjust the threshold sensitivity according to device characteristics.

[0033] As a preferred solution of the low-voltage distribution cabinet interlocking remote control method described in the present invention, the deep learning anomaly scoring threshold T is constructed according to the output result of the deep learning interlocking anomaly threshold evaluation formula. t ;

[0034] If T k ≤T t , indicating that the equipment is operating normally and no interlocking adjustment is required;

[0035] If T k >T t , indicating that the equipment is operating abnormally, triggering interlocking logic adjustment and protective action.

[0036] As a preferred solution of the low-voltage distribution cabinet interlocking remote control method described in the present invention, the edge computing and cloud collaboration are implemented through the following steps:

[0037] S41: In high-priority tasks, the edge computing module directly executes interlocking logic based on local data and builds edge computing formulas;

[0038] S42: The cloud regularly analyzes historical operation data to identify potential patterns or hidden dangers;

[0039] S43: The global strategy optimized on the cloud is periodically synchronized to the edge computing module.

[0040] As a preferred solution of the low-voltage distribution cabinet interlocking remote control method described in the present invention, the edge calculation formula is as follows:

[0041]

[0042] Among them, T' k Indicates the real-time operating status value of device k, which is used to determine whether it exceeds the threshold. Indicates real-time operating data, including the current and voltage parameters currently collected, μ k is the historical mean, which is the statistical mean of the equipment’s operating data over the past period of time. k It represents the historical standard deviation, which is the fluctuation range of the equipment operating parameters. θ is the adjustment coefficient provided by the cloud model, which is dynamically adjusted according to the long-term optimized strategy to enhance adaptability.

[0043] As a preferred solution of the low-voltage distribution cabinet interlocking remote control method according to the present invention, the third threshold value T3 and the dynamic adjustment threshold value T3 are set in the output result of the edge calculation formula. D ;

[0044] When T' k ≤T3, indicating that the equipment operates within the historical reference range and the interlocking logic remains unchanged;

[0045] When T' k >T3, the equipment deviates from the historical reference value, there is a fault or risk, triggering the following measures:

[0046] Real-time protective disconnection to prevent equipment damage;

[0047] Interlocking logic is adjusted first to avoid affecting other equipment;

[0048] Upload data to the cloud to further optimize the model;

[0049] In addition, when the equipment is running at high load, increasing T D , reduce false triggering;

[0050] When the equipment is running at low load, reduce T D , enhance sensitivity.

[0051] As a preferred solution of the low-voltage distribution cabinet interlocking remote control method of the present invention, wherein: S1 includes the following steps:

[0052] S11: Equipped with a high-performance edge computing unit, it supports real-time data collection, interlocking logic processing, and anomaly detection;

[0053] S12: Deploy large-scale computing resources in the cloud to be responsible for long-term data storage, model training, and strategy optimization.

[0054] The beneficial effects of the present invention are as follows: by collecting the operating data of the distribution cabinet in real time, the system can monitor the health status of the equipment, quickly identify faults, and protect the equipment through an interlocking control mechanism. Under abnormal circumstances, the system can automatically disconnect or restart operations to effectively avoid equipment damage or larger-scale power failures. The edge computing unit performs preliminary processing and abnormality detection on the data, and combines the optimization function of the cloud server to achieve the coordination of global optimization and real-time response. This process can continuously optimize the interlocking strategy based on historical data to ensure that the system can flexibly adjust according to environmental changes in actual operation, and can dynamically adjust the interlocking logic and priority based on real-time data, thereby improving the system's adaptability under different working conditions. Through historical data analysis and optimization on the cloud, the system can continuously improve its control strategy to ensure high efficiency and reliability in long-term operation. In summary, the present invention can effectively improve the operating efficiency of low-voltage distribution cabinets, improve equipment safety, reduce the occurrence of faults, and reduce maintenance costs, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work. Among them:

[0056] Figure 1 This is a schematic diagram of the overall framework of the low-voltage distribution cabinet interlocking remote control system proposed by the present invention;

[0057] Figure 2 The present invention is a schematic diagram of the implementation steps of the low-voltage distribution cabinet interlocking remote control method. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0061] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0062] Embodiment 1

[0063] Reference Figure 1-Figure 2 , is an embodiment of the present invention, providing a remote control system based on low-voltage distribution cabinet interlocking, including:

[0064] Data acquisition module: includes a variety of sensors, such as current sensors, voltage sensors, temperature sensors, vibration sensors, etc., to collect the operation data of the power distribution cabinet in real time. It is responsible for collecting the operation data of the power distribution cabinet in real time. It introduces various types of sensors including temperature sensors and vibration sensors to realize multi-dimensional collection of operation data. The real-time and richness of this multi-dimensional data provides a reliable data foundation for subsequent complex analysis based on edge computing and machine learning, which helps to improve the accuracy of anomaly detection and the efficiency of interlocking logic optimization;

[0065] Edge computing unit: equipped with high-performance computing hardware, data preprocessing, interlocking logic calculation and anomaly detection, including built-in lightweight machine learning model to optimize interlocking control logic in real time;

[0066] Through real-time data preprocessing and anomaly detection of edge computing units, combined with deep learning algorithms to optimize interlocking control logic, the system can achieve dynamic adjustment and avoid the problem of relying on fixed rules in traditional control systems. This adaptive control can better cope with complex and changing working environments and improve the intelligence level of the system;

[0067] Interlocking control execution module: includes circuit breakers, relays and actuators, used to execute interlocking actions, receive control signals from edge computing units, and realize protective disconnection and restart of equipment;

[0068] Communication module: including local communication interface (such as RS485, CAN bus) and remote communication interface (such as 4G / 5G module, Ethernet interface), supporting two-way transmission of data between data acquisition module, edge computing unit and cloud;

[0069] Through the two-way data transmission supported by the communication module, the system can realize remote control and fault diagnosis, providing a convenient remote operation platform for power system operation and maintenance. On the basis of traditional communication methods, it adds support for 5G technology, significantly improves the data transmission rate and bandwidth, adapts to the needs of large-scale real-time data transmission, provides a local and remote collaborative communication architecture, and effectively integrates data transmission needs at different levels;

[0070] Cloud server: deploys machine learning model training and long-term data storage systems, optimizes interlocking strategies based on historical data, and sends the optimized models to edge computing units, realizing historical data-driven interlocking strategy optimization. The optimized models can be sent to edge computing units for real-time decision-making. The cloud is responsible for the accumulation of long-term data and the training of complex models, while the edge unit focuses on real-time and efficiency, forming a complementary computing architecture. The optimization results of historical data can dynamically adjust real-time strategies through cloud-edge collaboration to build a closed-loop optimization system.

[0071] User terminal: includes monitoring center workstations and mobile devices (such as mobile phones or tablets), providing a human-computer interaction interface through which users can view operating status and issue remote commands.

[0072] Based on the low-voltage distribution cabinet interlocking remote control method, the control method is applicable to the above control system, and the control method includes the following steps:

[0073] S1: System architecture design;

[0074] S11: Equipped with a high-performance edge computing unit, it supports real-time data acquisition, interlocking logic processing, and anomaly detection. It provides a high-speed communication interface to connect multiple sensors and actuators to achieve millisecond-level data acquisition and interlocking response.

[0075] S12: Deploys large-scale computing resources in the cloud, responsible for long-term data storage, model training, and strategy optimization, provides high-speed communication interfaces, connects multiple sensors and actuators, and achieves millisecond-level data collection and interlocking response.

[0076] S2: Data collection and preprocessing;

[0077] A variety of sensors (current, voltage, temperature, vibration, etc.) are installed in the low-voltage distribution cabinet to regularly collect equipment operation status data and transmit it to the edge computing unit. The edge computing module is used to clean the collected raw data, remove noise or outliers, and extract key features (such as load rate, voltage fluctuation, vibration spectrum, etc.) to provide support for the optimization of interlocking logic.

[0078] S3: Construction of adaptive interlocking logic control algorithm;

[0079] The construction of the adaptive interlocking logic control algorithm is achieved through the following steps:

[0080] S31: Setting of initial logic rules;

[0081] S32: Use the edge computing module to update the machine learning model in real time, build a comprehensive scoring formula for multi-dimensional operation data deviation, adjust the weight and priority of the interlocking logic according to the collected data, and use the deep learning algorithm to optimize the machine learning model;

[0082] S33: Based on real-time data, the edge computing module dynamically generates the optimal interlocking decision tree and quickly adjusts the logic rules;

[0083] The comprehensive scoring formula for multi-dimensional operation data deviation is as follows:

[0084]

[0085] Among them, S k Indicates the comprehensive deviation score of device k at the current time, reflecting its overall operational health status. represents the i-th operation data of device k, μ i is the historical mean of the i-th item of equipment operation data, which is used to measure the normal operation status, σ i represents the historical standard deviation of the ith item of equipment operation data, which is used to characterize the fluctuation range, w i Represents the weight coefficient of each running data, which is dynamically adjusted by the machine learning model to reflect the importance of different data items. k Represents the model bias term of device k, which is used to correct the overall score.

[0086] Construct a comprehensive deviation threshold S from the output results of the multi-dimensional operation data deviation comprehensive scoring formula t ;

[0087] If S k ≤S t , it means the device is operating normally;

[0088] If S k >S t , indicating that the device is operating abnormally and requires further in-depth analysis.

[0089] A deep learning interlocking anomaly threshold evaluation formula is constructed based on the output result of the multi-dimensional operation data deviation comprehensive scoring formula, and the deep learning interlocking anomaly threshold evaluation formula is as follows:

[0090]

[0091] Among them, T k represents the deep learning anomaly score of device k, which is used for the final interlocking judgment. λ represents the adjustment parameter of the deep learning model, which is used to control the score growth rate. β k Represents the score offset of device k, which is used to adjust the threshold sensitivity according to device characteristics.

[0092] Construct a deep learning anomaly scoring threshold T based on the output of the deep learning interlocking anomaly threshold evaluation formula t ;

[0093] If T k ≤T t , indicating that the equipment is operating normally and no interlocking adjustment is required;

[0094] If T k >T t , indicating that the equipment is operating abnormally, triggering interlocking logic adjustment and protective action.

[0095] S4: Edge computing and cloud collaboration;

[0096] Edge computing and cloud collaboration are achieved through the following steps:

[0097] S41: In high-priority tasks, the edge computing module directly executes interlocking logic based on local data and builds edge computing formulas;

[0098] S42: The cloud regularly analyzes historical operation data to identify potential patterns or hidden dangers;

[0099] S43: The global strategy optimized on the cloud is regularly synchronized to the edge computing module, and edge computing is used to achieve high real-time interlocking control. At the same time, the global performance is improved by combining the large-scale optimization model on the cloud.

[0100] The edge computing formula is as follows:

[0101]

[0102] Among them, T' k Indicates the real-time operating status value of device k, which is used to determine whether it exceeds the threshold. Indicates real-time operating data, including the current and voltage parameters currently collected, μ k is the historical mean, which is the statistical mean of the equipment’s operating data over the past period of time. kIt represents the historical standard deviation, which is the fluctuation range of the equipment operating parameters. θ is the adjustment coefficient provided by the cloud model, which is dynamically adjusted according to the long-term optimized strategy to enhance adaptability.

[0103] The third threshold T3 and the dynamic adjustment threshold T are set in the output result of the edge calculation formula. D ;

[0104] When T' k ≤T3, indicating that the equipment operates within the historical reference range and the interlocking logic remains unchanged;

[0105] When T' k >T3, the equipment deviates from the historical reference value, there is a fault or risk, triggering the following measures:

[0106] Real-time protective disconnection to prevent equipment damage;

[0107] Interlocking logic is adjusted first to avoid affecting other equipment;

[0108] Upload data to the cloud to further optimize the model;

[0109] In addition, when the equipment is running at high load, increasing T D , reduce false triggering;

[0110] When the equipment is running at low load, reduce T D , enhance sensitivity.

[0111] S5: System function verification and optimization;

[0112] In the experimental environment, various scenarios such as equipment failure and overload are simulated to verify the effect of dynamic optimization of interlocking logic and test the response time of edge modules to ensure that they meet the expected performance indicators.

[0113] The machine learning model parameters are adjusted according to the test results, and the adaptive capability of the interlocking logic is gradually optimized through a closed-loop feedback mechanism. The system provides a user terminal as a human-computer interaction interface, allowing operators to easily view the operating status of the distribution cabinet and deal with any problems that arise in a timely manner.

[0114] In the present invention, by collecting the operating data of the distribution cabinet in real time, the system can monitor the health status of the equipment, quickly identify faults, and protect the equipment through an interlocking control mechanism. Under abnormal circumstances, the system can automatically disconnect or restart operations to effectively avoid equipment damage or larger-scale power failures. The edge computing unit performs preliminary processing and abnormality detection on the data, and combines the optimization function of the cloud server to achieve the coordination of global optimization and real-time response. This process can continuously optimize the interlocking strategy based on historical data to ensure that the system can flexibly adjust according to environmental changes in actual operation, and can dynamically adjust the interlocking logic and priority based on real-time data, thereby improving the system's adaptability under different working conditions. Through historical data analysis and optimization on the cloud, the system can continuously improve its control strategy to ensure high efficiency and reliability in long-term operation. In summary, the present invention can effectively improve the operating efficiency of low-voltage distribution cabinets, improve equipment safety, reduce the occurrence of faults, and reduce maintenance costs, and has broad application prospects.

[0115] Embodiment 2

[0116] Referring to Tables 1 to 3, which are the second embodiment of the present invention, this embodiment is different from the first embodiment in that, in order to verify its beneficial effects, experimental comparison data between the present invention and the prior art are provided.

[0117] In order to verify the performance of the interlocking remote control system based on the low-voltage distribution cabinet, we designed the following test process. The test was carried out in the actual operating environment of a low-voltage distribution cabinet. The equipment used in the test included a data acquisition module (equipped with current sensors, voltage sensors, temperature sensors and vibration sensors), an edge computing unit (integrated with high-performance hardware and lightweight machine learning models), an interlocking control execution module (circuit breakers and relays), a communication module (supporting RS485 and 5G communications), a cloud server, and a monitoring center workstation and a mobile terminal.

[0118] Implementation process:

[0119] The system architecture includes the hardware and software configuration of the distribution cabinet. The data acquisition module is installed in the distribution cabinet. The sensor monitors the operating status in real time and transmits it to the edge computing unit. The communication module realizes a two-way connection with the cloud through the 5G network.

[0120] The data acquisition module collects three types of data: electrical parameters (such as current and voltage), environmental parameters (such as temperature and vibration), and historical abnormal data;

[0121] The interlocking logic is based on a deep learning algorithm and uses a dynamic weight mechanism to adjust the control strategy. The model combines historical data and real-time data to calculate whether the current state needs to trigger a protective disconnection.

[0122] The cloud server trains complex machine learning models, optimizes control strategies based on historical data, and sends the optimized models to the edge units, which execute decisions in real time and upload new data for cloud training;

[0123] The system function test is divided into two parts: normal operation and abnormal situation simulation. We compared the differences between the traditional fixed rule control system and the control system of the present invention in fault detection rate, response time and equipment protection effect. The experimental results are recorded in three tables, as shown below.

[0124] Table 1: Data acquisition module performance comparison table

[0125]

[0126] Table 2: Fault detection and response performance comparison

[0127] System Type Fault detection rate (%) Average response time (ms) False alarm rate (%) Traditional control system 78 450 12 Control system of the present invention 95 120 4

[0128] Table 3: Comparison of interlocking control execution effects

[0129]

[0130]

[0131] It can be concluded from the experimental data in Table 1, Table 2 and Table 3 that the control system and control method of the present invention are superior to the traditional control system in terms of data acquisition frequency, fault detection rate, response time and protection function coverage. The following is an analysis of the three tables:

[0132] According to Table 1, the data acquisition module of the present invention significantly improves the acquisition frequency, especially the real-time monitoring of temperature and vibration parameters, fills the gap in the environmental parameter acquisition of the traditional system, and provides more comprehensive basic data for subsequent abnormality detection;

[0133] Referring to Table 2 for analysis: Through the edge computing unit and the adaptive interlocking logic algorithm, the fault detection rate of the system of the present invention is increased by 17%, the average response time is shortened to 1 / 4 of the traditional system, and the false alarm rate is reduced to 1 / 3 of the original, which shows that the present invention not only improves the detection efficiency, but also greatly reduces the unnecessary downtime caused by false alarms during system operation;

[0134] Referring to Table 3 for analysis: the system of the present invention shows superior performance in short circuit, overload and overheating protection, especially in overheating protection, which has achieved an innovative breakthrough from scratch. This result shows that the interlocking control strategy of the present invention has stronger adaptability and effectiveness in complex environments.

[0135] In summary, the present invention significantly improves the intelligence level and operation safety of low-voltage distribution cabinets by optimizing data acquisition, multi-dimensional real-time analysis, adaptive interlocking logic control and cloud-edge collaborative architecture, and solves the technical problems of slow response, low detection rate and imperfect protection function of traditional systems.

[0136] It should be noted that 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. Based on the low-voltage distribution cabinet interlocking remote control system, it is characterized by: include: Data acquisition module: collects the operation data of the power distribution cabinet in real time; Edge computing unit: data preprocessing, interlocking logic calculation and anomaly detection; Interlocking control execution module: receives control signals from the edge computing unit to implement protective disconnection and restart of the equipment; Communication module: supports two-way transmission of data between the data acquisition module, edge computing unit and the cloud; Cloud server: optimizes the interlocking strategy based on historical data and sends the optimized model to the edge computing unit; User terminal: provides human-computer interaction interface.

2. A remote control method based on low-voltage distribution cabinet interlocking, which is applicable to the above control system, is characterized in that: The control method comprises the following steps: S1: System architecture design; S2: Data collection and preprocessing; S3: Construction of adaptive interlocking logic control algorithm; S4: Edge computing and cloud collaboration; S5: System function verification and optimization.

3. The remote control method based on low-voltage distribution cabinet interlocking according to claim 2 is characterized in that: The construction of the adaptive interlocking logic control algorithm is achieved by the following steps: S31: Setting of initial logic rules; S32: Use the edge computing module to update the machine learning model in real time, build a comprehensive scoring formula for multi-dimensional operation data deviation, adjust the weight and priority of the interlocking logic according to the collected data, and use the deep learning algorithm to optimize the machine learning model; S33: Based on real-time data, the edge computing module dynamically generates the optimal interlocking decision tree and quickly adjusts the logic rules; The multi-dimensional operation data deviation comprehensive scoring formula is as follows: Among them, S k Indicates the comprehensive deviation score of device k at the current time, reflecting its overall operational health status. represents the i-th item of operation data of device k, μ i is the historical mean of the i-th item of equipment operation data, which is used to measure the normal operation status, σ i represents the historical standard deviation of the ith item of equipment operation data, which is used to characterize the fluctuation range, w i Represents the weight coefficient of each running data, which is dynamically adjusted by the machine learning model to reflect the importance of different data items. k Represents the model bias term of device k, which is used to correct the overall score.

4. The low-voltage distribution cabinet interlocking remote control method according to claim 3 is characterized in that: Construct a comprehensive deviation threshold S from the output results of the multi-dimensional operation data deviation comprehensive scoring formula t ; If S k ≤S t , it means the device is operating normally; If S k >S t , indicating that the device is operating abnormally and requires further in-depth analysis.

5. The remote control method based on low-voltage distribution cabinet interlocking according to claim 3 is characterized in that: A deep learning interlocking anomaly threshold evaluation formula is constructed based on the output result of the multi-dimensional operation data deviation comprehensive scoring formula, and the deep learning interlocking anomaly threshold evaluation formula is as follows: Among them, T k represents the deep learning anomaly score of device k, which is used for the final interlocking judgment. λ represents the adjustment parameter of the deep learning model, which is used to control the score growth rate. β k Represents the score offset of device k, which is used to adjust the threshold sensitivity according to device characteristics.

6. The low-voltage distribution cabinet interlocking remote control method according to claim 5 is characterized in that: Construct a deep learning anomaly scoring threshold T based on the output of the deep learning interlocking anomaly threshold evaluation formula t ; If T k ≤T t , indicating that the equipment is operating normally and no interlocking adjustment is required; If T k >T t , indicating that the equipment is operating abnormally, triggering interlocking logic adjustment and protective action.

7. The remote control method based on low-voltage distribution cabinet interlocking according to claim 2 is characterized in that: The edge computing and cloud collaboration are achieved through the following steps: S41: In high-priority tasks, the edge computing module directly executes interlocking logic based on local data and builds edge computing formulas; S42: The cloud regularly analyzes historical operation data to identify potential patterns or hidden dangers; S43: The global strategy optimized on the cloud is periodically synchronized to the edge computing module.

8. The low-voltage distribution cabinet interlocking remote control method according to claim 7 is characterized in that: The edge calculation formula is as follows: Among them, T' k Indicates the real-time operating status value of device k, which is used to determine whether it exceeds the threshold. Indicates real-time operating data, including the current and voltage parameters currently collected, μ k is the historical mean, which is the statistical mean of the equipment’s operating data over the past period of time. k It represents the historical standard deviation, which is the fluctuation range of the equipment operating parameters. θ is the adjustment coefficient provided by the cloud model, which is dynamically adjusted according to the long-term optimized strategy to enhance adaptability.

9. The low-voltage distribution cabinet interlocking remote control method according to claim 8 is characterized in that: The third threshold T3 and the dynamic adjustment threshold T are set in the output result of the edge calculation formula. D ; When T' k ≤T3, indicating that the equipment operates within the historical reference range and the interlocking logic remains unchanged; When t' k >T3, the equipment deviates from the historical reference value, there is a fault or risk, triggering the following measures: Real-time protective disconnection to prevent equipment damage; Interlocking logic is adjusted first to avoid affecting other equipment; Upload data to the cloud to further optimize the model; In addition, when the equipment is running at high load, increasing T D , reduce false triggering; When the equipment is running at low load, reduce T D , enhance sensitivity.

10. The remote control method based on low-voltage distribution cabinet interlocking according to claim 2 is characterized in that: The S1 comprises the following steps: S11: Equipped with a high-performance edge computing unit, it supports real-time data collection, interlocking logic processing, and anomaly detection; S12: Deploy large-scale computing resources in the cloud to be responsible for long-term data storage, model training, and strategy optimization.

Images