A low voltage power equipment monitoring system and method

Abstract

The application discloses a kind of low-voltage power equipment monitoring system and method, system includes grid connection module, terminal docking module connected in turn, comprehensive networking processing module, management platform module and loss supervision module;Grid connection module is connected with management platform module, grid connection respectively, terminal docking module is connected with multiple low-voltage power equipment, management platform module communication respectively;Grid connection module, terminal docking module obtains key electrical parameter, equipment location characteristic data, grid load historical data of grid;Comprehensive networking processing module generates multiple target electrical data, identifier timestamp data;Management platform module generates electrical sequence data according to each equipment location characteristic data, each identifier timestamp data, each target electrical data and grid load historical data;Loss supervision module generates power equipment exception result according to electrical sequence data;Solve the technical problem that the existing low-voltage power equipment monitoring mode leads to monitoring effect is not ideal.

Description

Technical Field

[0001] This invention relates to the field of power equipment technology, and in particular to a low-voltage power equipment monitoring system and method. Background Technology

[0002] Low-voltage power systems refer to circuit or equipment management systems with a rated voltage of 1000 volts or less. In low-voltage power systems, electrical energy is stepped down by transformers and then reliably transmitted to users' terminal equipment through transmission lines and distribution equipment.

[0003] With the continuous development of the power industry, more and more low-voltage power equipment is being put into various parts of the low-voltage power system. The stable operation of low-voltage power equipment is an important guarantee for the stable operation of the low-voltage power system. Due to the special nature of the power industry, low-voltage power equipment often operates continuously for long periods of time, and any small fault or instability can cause huge losses. Therefore, the monitoring of power equipment is particularly critical.

[0004] The existing methods for monitoring low-voltage power equipment mostly involve operators using handheld detectors to conduct regular on-site inspections and then analyzing and diagnosing the stored test data on a PC in the background. This method relies too heavily on technical personnel and is susceptible to fatigue and experience, which inevitably leads to missed scans and misjudgments. It also fails to detect faults in low-voltage power equipment in a timely manner, resulting in unsatisfactory monitoring results. Summary of the Invention

[0005] This invention provides a low-voltage power equipment monitoring system and method to solve the technical problem that existing low-voltage power equipment monitoring methods result in unsatisfactory monitoring effects.

[0006] The first aspect of the present invention provides a low-voltage power equipment monitoring system, the system comprising a power grid connection module and a terminal docking module, an integrated network processing module, a management platform module and a loss monitoring module connected in sequence;

[0007] The power grid connection module is connected to the management platform module and the power grid respectively, and the terminal docking module is communicatively connected to multiple low-voltage power devices and the management platform module respectively.

[0008] The terminal docking module is used to acquire key electrical parameters and equipment location feature data of each of the low-voltage power devices, and transmit the key electrical parameters and equipment location feature data to the integrated network processing module and the equipment location feature data to the management platform module;

[0009] The power grid connection module is used to acquire historical power grid load data of the power grid and transmit it to the management platform module;

[0010] The integrated network processing module is used to convert the data of each key electrical parameter, generate corresponding initial electrical data and perform verification and comparison respectively, determine multiple target electrical data, generate corresponding identifier timestamp data according to the location feature data of each device, and transmit each target electrical data and each identifier timestamp data to the management platform module.

[0011] The management platform module is used to generate and store electrical sequence data based on the location feature data of each device, the electrical data of each target, the historical data of the power grid load, and the timestamp data of each identifier.

[0012] The loss monitoring module is used to call the electrical sequence data in the management platform module and generate power equipment abnormality results based on the electrical sequence data.

[0013] Optionally, the integrated network processing module includes an interconnection processing module and an IoT management module connected in sequence;

[0014] The interconnection processing module is connected to the terminal interface module, and the IoT management module is connected to the management platform module;

[0015] The interconnection processing module is used to perform data conversion and first checksum on each of the key electrical parameters, generate each of the initial electrical data and the corresponding first check code, generate corresponding identifier timestamp data according to each of the device location feature data, and transmit each of the identifier timestamp data, each of the initial electrical data and the corresponding first check code to the IoT management module.

[0016] The IoT management module is used to perform a second checksum on each of the initial electrical data, generate a second check code corresponding to each of the initial electrical data, and perform consistency comparison on each of the first check code and the corresponding second check code, and transmit any initial electrical data that matches the comparison as the target electrical data to the management platform module.

[0017] Optionally, the terminal docking module includes a device docking module, a sensor module, a network upload module, and a tag processing module;

[0018] The network upload module is connected to the tag processing module, the device docking module, and the sensor module, respectively;

[0019] The device docking module is communicatively connected to each of the low-voltage power devices, and the network upload module is communicatively connected to the interconnection processing module and the management platform module, respectively.

[0020] The sensor module is used to acquire key electrical parameters of each of the low-voltage power devices and transmit them to the interconnection processing module through the network upload module;

[0021] The tagging processing module is used to acquire the equipment location feature data of each of the low-voltage power devices and transmit it to the management platform module and the interconnection processing module through the network upload module.

[0022] Optionally, the interconnection processing module includes an architecture model module and, in sequence, an upload and receive module, an architecture detection module, a model invocation module, a protocol adjustment module, and an adjustment output module;

[0023] The model calling module is connected to the architecture model module, and the adjustment output module is communicatively connected to the IoT management module;

[0024] The network upload module is communicatively connected to the upload receiving module and the adjustment output module, respectively.

[0025] The architecture detection module is used to detect the protocol type of each key electrical parameter transmitted by the upload and receive module, output the protocol type data corresponding to each key electrical parameter, and transmit each key electrical parameter and the corresponding protocol type data to the model call module.

[0026] The model invocation module is used to invoke the protocol conversion model corresponding to each of the protocol type data in the architecture model module, and transmit each of the key electrical parameters and the corresponding protocol conversion model to the protocol adjustment module;

[0027] The protocol adjustment module is used to preprocess each of the key electrical parameters, output corresponding coded electrical data, use each of the protocol conversion models to convert the corresponding coded electrical data into a protocol format, generate corresponding electrical conversion data, and transmit it to the adjustment output module.

[0028] The adjustment output module is used to generate corresponding identifier timestamp data based on the device feature information in each device location feature data when it receives each electrical conversion data and each device location feature data transmitted by the network upload module; generate multiple initial electrical data using each electrical conversion data and each identifier timestamp data; perform a first checksum on each initial electrical data to generate a first checksum corresponding to the initial electrical data; and transmit the initial electrical data and the corresponding first checksum to the IoT management module.

[0029] Optionally, the management platform module includes an AI model module and a platform transmission module, a data integration module, a model analysis module, and a storage module connected in sequence;

[0030] The platform transmission module is communicatively connected to the power grid connection module, the IoT management module, and the storage module, respectively.

[0031] The AI ​​model module is connected to the model analysis module, and the storage module is communicatively connected to the loss monitoring module.

[0032] The data integration module is used to filter multiple device location feature data based on each target electrical data, determine the target device data corresponding to each target electrical data, perform data cleaning and data integration on the device location coordinates in the power grid load historical data, each target electrical data and the corresponding target device data, output multiple electrical integrated data, normalize each electrical integrated data, generate corresponding electrical normalized data and transmit it to the model analysis module;

[0033] The model analysis module is used to call the statistical model in the AI ​​model module, take each of the electrical normalized data as input to the statistical model, output electrical sequence data and transmit it to the storage module;

[0034] The repository module is used to store the electrical sequence data.

[0035] Optionally, the abnormal power equipment results include the location of abnormal low-voltage power equipment and the correlation data of abnormal itemsets; the electrical sequence data includes the probability density value of electrical data points corresponding to each of the electrical normalized data; the loss monitoring module includes an auxiliary analysis module, a loss calculation module, and a data extraction module, a loss determination module, and a source detection module connected in sequence.

[0036] The loss calculation module is connected to the auxiliary analysis module and the loss determination module, respectively.

[0037] The data extraction module is communicatively connected to the storage module and the auxiliary analysis module, respectively.

[0038] The data extraction module is used to call the electrical sequence data in the storage module and transmit it to the loss determination module and the auxiliary analysis module respectively.

[0039] The loss determination module is used to determine whether the probability density value of each electrical data point in the electrical sequence data is within a preset density range. The electrical normalized data corresponding to any electrical data point probability density value that is not within the preset density range is taken as abnormal electrical data and transmitted to the source detection module and the loss calculation module respectively.

[0040] The source detection module is used to determine the location of the corresponding abnormal low-voltage power equipment based on the target equipment location feature data corresponding to each of the abnormal electrical data.

[0041] The loss calculation module is used to perform quantitative analysis on each of the abnormal electrical data and the preset normal state electrical data, determine the additional loss corresponding to each of the abnormal electrical data, and transmit it to the auxiliary analysis module.

[0042] The auxiliary analysis module is used to generate corresponding abnormal itemset association data based on each of the additional loss amounts and the electrical sequence data using a pre-set association rule learning algorithm.

[0043] Optionally, the system further includes an information visualization module; the loss monitoring module further includes an anomaly feedback module.

[0044] The anomaly feedback module is connected to the source detection module and the auxiliary analysis module, respectively.

[0045] The exception feedback module is communicatively connected to the repository module;

[0046] The information visualization module is connected to the IoT management module;

[0047] The anomaly feedback module is used to receive the location data of each of the abnormal low-voltage power devices sent by the source detection module and the association data of each of the abnormal itemsets sent by the auxiliary analysis module, and transmit the location data of each of the abnormal low-voltage power devices and the association data of each of the abnormal itemsets to the repository module;

[0048] The repository module is also used to transmit the received location data of each of the abnormal low-voltage power devices and the association data of each of the abnormal itemsets to the IoT management module through the platform transmission module;

[0049] The information visualization module is used to receive and display the location data of each abnormal low-voltage power device and the association data of each abnormal item set transmitted by the IoT management module.

[0050] A second aspect of the present invention provides a method for monitoring low-voltage power equipment, comprising:

[0051] Acquire key electrical parameters and equipment location characteristics of multiple low-voltage power devices, as well as historical grid load data of the power grid;

[0052] The key electrical parameters are converted to generate corresponding initial electrical data, which are then verified and compared to determine multiple target electrical data.

[0053] Based on the location feature data of each device, the electrical data of each target, and the historical load data of the power grid, generate electrical sequence data;

[0054] Based on the electrical sequence data, generate abnormal results for power equipment.

[0055] A computer device provided in a third aspect of the present invention includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the low-voltage power equipment monitoring method described above.

[0056] The fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the low-voltage power equipment monitoring method as described above.

[0057] As can be seen from the above technical solutions, the present invention has the following advantages:

[0058] The first aspect of the technical solution of the present invention provides a low-voltage power equipment monitoring system. This system includes a power grid connection module and, sequentially connected, a terminal docking module, an integrated network processing module, a management platform module, and a loss monitoring module. The power grid connection module is connected to both the management platform module and the power grid. The terminal docking module is communicatively connected to multiple low-voltage power devices and the management platform module. Specifically, the terminal docking module acquires key electrical parameters and device location feature data for each low-voltage power device, and transmits these data to the integrated network processing module and the management platform module. The power grid connection module acquires historical power grid load data and transmits it to the management platform module. The integrated network processing module performs data conversion on each key electrical parameter, generates corresponding initial electrical data, and performs verification and comparison to determine multiple target power devices. Based on the location characteristics of each device, corresponding identifier timestamp data is generated, and the target electrical data and identifier timestamp data are transmitted to the management platform module. The management platform module generates and stores electrical sequence data based on the location characteristics of each device, the target electrical data, historical grid load data, and identifier timestamp data. The loss monitoring module calls the electrical sequence data in the management platform module and generates power equipment anomaly results based on the electrical sequence data. Based on the above scheme, the process of converting and verifying the key electrical parameters obtained by the integrated network processing module, determining multiple target electrical data, and then processing them sequentially through the management platform module and the loss monitoring module to generate power equipment anomaly results can replace the method of operators using handheld detectors for regular on-site inspections, thereby timely detecting faults in low-voltage power equipment and further improving the monitoring effect.

[0059] The second aspect of the above-mentioned technical solution of the present invention provides a method for monitoring low-voltage power equipment. First, it acquires key electrical parameters and equipment location characteristic data of multiple low-voltage power devices, as well as historical grid load data. Next, it performs data conversion on each key electrical parameter to generate corresponding initial electrical data, which is then verified and compared to determine multiple target electrical data. Based on the equipment location characteristic data, the target electrical data, and the historical grid load data, it generates electrical sequence data. Finally, it generates power equipment anomaly results based on the electrical sequence data. Compared to the existing method of operators periodically inspecting the site with handheld detectors and analyzing and diagnosing the stored detection data on a background PC, this method can replace the method of operators periodically inspecting the site with handheld detectors, reducing reliance on technical personnel and further improving monitoring effectiveness. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This is a first structural schematic diagram of a low-voltage power equipment monitoring system provided in Embodiment 1 of the present invention;

[0062] Figure 2 This is a schematic diagram of the second structure of a low-voltage power equipment monitoring system provided in Embodiment 1 of the present invention;

[0063] Figure 3 This is a schematic diagram of the terminal docking module provided in Embodiment 1 of the present invention;

[0064] Figure 4 This is a schematic diagram of the interconnection processing module provided in Embodiment 1 of the present invention;

[0065] Figure 5 This is a schematic diagram of the structure of the management platform module provided in Embodiment 1 of the present invention;

[0066] Figure 6 This is a schematic diagram of the loss monitoring module provided in Embodiment 1 of the present invention;

[0067] Figure 7 This is a flowchart illustrating the steps of a low-voltage power equipment monitoring method provided in Embodiment 2 of the present invention;

[0068] The meanings of the labels in the attached figures are as follows:

[0069] 1. Terminal Interconnection Module; 2. Interconnection Processing Module; 3. IoT Management Module; 4. Management Platform Module; 5. Power Grid Connection Module; 6. Loss Monitoring Module; 7. Information Visualization Module; 11. Daily Monitoring Module; 12. Equipment Interconnection Module; 13. Sensor Module; 14. Network Upload Module; 15. Tagging Processing Module; 16. Network Detection Module; 21. Cloud Connection Module; 22. Information Processing Module; 23. Architecture Model Module; 24. Model Call Module; 25. Architecture Detection Module; 26. Upload and Receive Module; 27. Protocol Adjustment Module; 28. Adjustment Output Module; 41. Model Iteration Module; 42. AI Model Module; 43. Model Analysis Module; 44. Data Integration Module; 45. Platform Transmission Module; 46. Storage Module; 61. Data Extraction Module; 62. Loss Determination Module; 63. Source Detection Module; 64. Anomaly Feedback Module; 65. Loss Calculation Module; 66. Auxiliary Analysis Module. Detailed Implementation

[0070] This invention provides a low-voltage power equipment monitoring system and method to solve the technical problem that existing low-voltage power equipment monitoring methods result in unsatisfactory monitoring effects.

[0071] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0072] Please see Figure 1 , Figure 1 This is a schematic diagram of a low-voltage power equipment monitoring system provided in Embodiment 1 of the present invention.

[0073] The present invention provides a low-voltage power equipment monitoring system, which includes a power grid connection module 5 and a terminal docking module 1, an integrated network processing module, a management platform module 4 and a loss monitoring module 6 connected in sequence; the power grid connection module 5 is connected to the management platform module 4 and the power grid respectively, and the terminal docking module 1 is communicatively connected to multiple low-voltage power equipment and the management platform module 4 respectively.

[0074] The integrated network processing module includes an interconnection processing module 2 and an IoT management module 3 connected in sequence.

[0075] It should be noted that you should refer to [link / reference]. Figures 1-2Terminal docking module 1 controls the connection to interconnection processing module 2, interconnection processing module 2 controls the connection to IoT management module 3, IoT management module 3 controls the connection to management platform module 4 and information visualization module 7, management platform module 4 controls the connection to power grid connection module 5 and loss monitoring module 6 respectively; power grid connection module 5 is electrically connected to the power grid, and terminal docking module 1 is communicatively connected to multiple low-voltage power devices and management platform module 4 respectively.

[0076] Terminal docking module 1 is used to acquire key electrical parameters and equipment location feature data of each low-voltage power equipment, and transmit the key electrical parameters and equipment location feature data to the integrated network processing module and the equipment location feature data to the management platform module 4;

[0077] Equipment location feature data includes the equipment location coordinates and equipment feature information of low-voltage power equipment. Among them, the equipment feature information includes the equipment model, serial number ID, manufacturer, etc.

[0078] It should be noted that the terminal docking module 1 consists of a daily monitoring module 11, an equipment docking module 12, a sensor module 13, a network upload module 14, a tag processing module 15, and a network detection module 16. The daily monitoring module 11 controls the connection to the equipment docking module 12 and the sensor module 13 respectively. The equipment docking module 12 and the sensor module 13 both control the connection to the network upload module 14. The network upload module 14 controls the connection to the daily monitoring module 11, the tag processing module 15, and the network detection module 16 respectively.

[0079] The power grid connection module 5 is used to acquire historical power grid load data and transmit it to the management platform module 4;

[0080] It should be noted that the power grid connection module 5 connects to the power grid output device and transmits the historical data of the power grid output load, i.e., the historical data of the power grid load, to the management platform module 4, so that it can be called and analyzed later through the model analysis module 43 in the management platform module 4.

[0081] The integrated network processing module is used to convert data of each key electrical parameter, generate corresponding initial electrical data and verify and compare them respectively, determine multiple target electrical data, generate corresponding identifier timestamp data based on the location feature data of each device, and transmit each target electrical data and each identifier timestamp data to the management platform module 4.

[0082] Management platform module 4 is used to generate and store electrical sequence data based on the location feature data of each device, the electrical data of each target, the historical data of the power grid load, and the timestamp data of each identifier.

[0083] It should be noted that the management platform module 4 consists of a model iteration module 41, an AI model module 42, a model analysis module 43, a data integration module 44, a platform transmission module 45, and a storage module 46. The model iteration module 41 is an important component responsible for managing and maintaining the AI ​​model. It is mainly used to periodically adjust the built-in parameters of the AI ​​model and the feature weights of the processor to ensure the computational accuracy of the model. The model iteration module 41 controls the connection to the AI ​​model module 42. The AI ​​model module 42 controls the connection to the model analysis module 43. The model analysis module 43 controls the connection to the data integration module 44, the platform transmission module 45, and the storage module 46. The storage module 46 and the data integration module 44 both control the connection to the platform transmission module 45.

[0084] Loss monitoring module 6 is used to call electrical sequence data in the management platform module and generate abnormal results for power equipment based on the electrical sequence data.

[0085] It should be noted that the loss monitoring module 6 consists of a data extraction module 61, a loss determination module 62, a source detection module 63, an anomaly feedback module 64, a loss calculation module 65, and an auxiliary analysis module 66. The data extraction module 61 controls and connects to the loss determination module 62, the loss determination module 62 controls and connects to the source detection module 63, the source detection module 63 controls and connects to the anomaly feedback module 64, the anomaly feedback module 64 controls and connects to the auxiliary analysis module 66, the auxiliary analysis module 66 controls and connects to the loss calculation module 65, and the loss calculation module 65 controls and connects to the loss determination module 62. The loss determination module 62 is used to determine whether the power loss is normal by combining the captured data.

[0086] As a further improvement, the integrated network processing module includes an interconnection processing module 2 and an IoT management module 3 connected in sequence; the interconnection processing module 2 is connected to the terminal interface module 1, and the IoT management module 3 is connected to the management platform module 4.

[0087] The interconnection processing module 2 is used to perform data conversion and first checksum on each key electrical parameter, generate each initial electrical data and corresponding first check code, generate corresponding identifier timestamp data based on the location feature data of each device, and transmit each identifier timestamp data, each initial electrical data and corresponding first check code to the IoT management module 3.

[0088] It should be noted that the interconnection processing module 2 consists of a cloud connection module 21, an information processing module 22, an architecture model module 23, a model invocation module 24, an architecture detection module 25, an upload and receive module 26, a protocol adjustment module 27, and an adjustment output module 28. The cloud connection module 21 is used to connect to the IoT cloud data layer, find and receive the corresponding cloud big data architecture model, and then the information is screened, integrated, and organized by the information processing module 22. The cloud connection module 21 controls the connection to the information processing module 22, the information processing module 22 controls the connection to the architecture model module 23, the architecture model module 23 controls the connection to the model invocation module 24, the model invocation module 24 controls the connection to the architecture detection module 25, the architecture detection module 25 controls the connection to the upload and receive module 26, the model invocation module 24 controls the connection to the protocol adjustment module 27, and the protocol adjustment module 27 controls the connection to the adjustment output module 28. The interconnection processing module 2 generates identifier timestamp data by using the device feature information in the device location feature data and the timestamp data of the current time.

[0089] The IoT management module 3 is used to perform a second checksum on each initial electrical data, generate a second check code corresponding to each initial electrical data, and perform consistency comparison on each first check code and the corresponding second check code. Any initial electrical data that matches the comparison is used as the target electrical data and transmitted to the management platform module 4.

[0090] It should be noted that the IoT management module 3, as the system's data transfer and management unit, acts as a transmission channel during system data transmission. The IoT management module 3 receives data and feeds it back to the management platform module 4. The IoT management module 3 performs a second checksum on each initial electrical data, generating a second checksum corresponding to each initial electrical data. The consistency of the first and second checksums corresponding to each initial electrical data is compared to verify the data's integrity. If they match, it indicates that the initial electrical data has not changed during transmission or storage, maintaining its original integrity and accuracy. If the comparison is inconsistent, the corresponding initial electrical data is discarded. The checksum ensures that the data used by the AI ​​model analysis module 43 in the management platform module 4 is complete and tamper-proof, enhancing the data's value and thus improving the training and inference performance of the AI ​​model.

[0091] Furthermore, checksums can be implemented in various ways, including simple summation checksums, XOR checksums, and Cyclic Redundancy Check (CRC). Different implementations have different characteristics and applicable scopes. For example, the Modbus protocol includes three message types: ASCII, RTU, and TCP. In ASCII mode, LRC (Longitudinal Redundancy Check) can be used for verification, calculating the checksum value by performing an XOR operation on the data. In RTU mode, a 16-bit CRC (Cyclic Redundancy Check) can be used, calculating the checksum value by performing a polynomial division operation on the data. (The Modbus-TCP protocol does not specify an additional checksum method.)

[0092] As a further improvement, the terminal docking module 1 includes an equipment docking module 12, a sensor module 13, a network upload module 14, and a tag processing module 15; the network upload module 14 is connected to the tag processing module 15, the equipment docking module 12, and the sensor module 13 respectively; the equipment docking module 12 is communicatively connected to each low-voltage power device, and the network upload module 14 is communicatively connected to the interconnection processing module 2 and the management platform module 4 respectively; the sensor module 13 is used to acquire key electrical parameters of each low-voltage power device and transmit them to the interconnection processing module 2 through the network upload module; the tag processing module 15 is used to acquire equipment location feature data of each low-voltage power device and transmit them to the management platform module 4 and the interconnection processing module 2 through the network upload module 14.

[0093] It should be noted that you should refer to [link / reference]. Figure 3The device docking module 12 and sensor module 13 work together. When the system starts, the device docking module 12 first connects multiple low-voltage power devices. The sensor module 13 acquires the key electrical parameters of each low-voltage power device and then transmits this electrical data (key electrical parameters) to the network upload module 14 in real time. Simultaneously, the tagging processing module 15 tags the characteristics and transmission location information of each low-voltage power device, acquiring the device location characteristic data of each device to ensure data integrity and traceability. This facilitates more efficient identification and utilization of this information by the source detection module in subsequent anomaly detection, enabling precise device positioning and control optimization. The data is then also transmitted to the network upload module 14. During system operation, the daily monitoring module 11 is responsible for inspecting the operating status of the power devices to monitor their operating condition and performance. The network detection module 16 detects the connection stability of the system network. Both modules also send the detected data to the network upload module 14 in real time. Finally, the network upload module 14 integrates and packages the collected data (key electrical parameters and equipment location characteristic data) and sends it to the interconnection processing module 2 and the management platform module 4 for further analysis, processing and application.

[0094] As a further improvement, the interconnection processing module 2 includes an architecture model module 23 and, in sequence, an upload / receive module 26, an architecture detection module 25, a model invocation module 24, a protocol adjustment module 27, and an adjustment output module 28; the model invocation module 24 is connected to the architecture model module 23, and the adjustment output module 28 is communicatively connected to the IoT management module 3; the network upload module 14 is communicatively connected to the upload / receive module 26 and the adjustment output module 28, respectively.

[0095] The architecture detection module 25 is used to detect the protocol type of each key electrical parameter transmitted by the upload and receive module 26, output the protocol type data corresponding to each key electrical parameter, and transmit each key electrical parameter and the corresponding protocol type data to the model call module 24.

[0096] The model calling module 24 is used to call the protocol conversion model corresponding to each protocol type data in the architecture model module 23, and transmit each key electrical parameter and the corresponding protocol conversion model to the protocol adjustment module 27;

[0097] Protocol adjustment module 27 is used to preprocess each key electrical parameter, output the corresponding coded electrical data, use each protocol conversion model to convert the corresponding coded electrical data into protocol format, generate the corresponding electrical conversion data and transmit it to adjustment output module 28;

[0098] The adjustment output module 28 is used to generate corresponding identifier timestamp data based on the device feature information in each device location feature data when it receives each electrical conversion data and each device location feature data transmitted by the network upload module 14. It generates multiple initial electrical data using each electrical conversion data and each identifier timestamp data, performs a first checksum on each initial electrical data, generates a first check code corresponding to the initial electrical data, and transmits the initial electrical data and the corresponding first check code to the IoT management module 3.

[0099] Identifier timestamp data includes device identifiers and timestamp data.

[0100] It should be noted that you should refer to [link / reference]. Figure 4 The collected data (key electrical parameters and equipment location feature data) is transmitted to the interconnection processing module 2 via the network upload module 14. The upload receiving module 26 and the adjustment output module 28 receive the data. Then, the architecture detection module 25 verifies the electrical data source protocol type of the key electrical parameters transmitted by the network upload module 14. After the detection is completed, the corresponding protocol conversion model is called from the protocol library of the architecture model module 23 through the model call module 24. The key electrical parameters are preprocessed by the protocol adjustment module 27. The preprocessing process includes parsing, splitting, mapping, aggregation, and encryption. Finally, the data is re-encoded to obtain coded electrical data. The corresponding protocol conversion model for each coded electrical data is used to convert the corresponding coded electrical data from the original protocol format to the target protocol format required for IoT cloud data communication. The above source and target protocol formats include Modbus, ZigBee, LoRa, TCP / UDP, MQTT, CoAP, DDS, HTTP, etc. After the data format conversion is completed, the output module 28 is used to add device identifiers and timestamps to the electrical conversion data. That is, firstly, based on the device feature information in each device location feature data, the corresponding identifier timestamp data is generated. Then, each electrical conversion data and the corresponding identifier timestamp data are used to generate the corresponding initial electrical data. After verification and summation, the data is sent to the Internet of Things.

[0101] Furthermore, the adjustment output module 28 performs a checksum on each initial electrical data and performs a specific mathematical operation (such as summation, XOR operation, etc.) on each byte or bit of each initial electrical data to generate a short, fixed-length first checksum. Its main function is to detect whether errors or damage have occurred in the data during transmission or storage in subsequent modules.

[0102] As a further improvement, the management platform module 4 includes an AI model module 42 and a platform transmission module 45, a data integration module 44, a model analysis module 43, and a storage module 46 connected in sequence; the platform transmission module 45 is communicatively connected to the power grid connection module 5, the IoT management module 3, and the storage module 46 respectively; the AI ​​model module 42 is connected to the model analysis module 43, and the storage module 46 is communicatively connected to the loss monitoring module 6.

[0103] The data integration module 44 is used to filter multiple equipment location feature data based on each target electrical data, determine the target equipment data corresponding to each target electrical data, clean and integrate the equipment location coordinates in the historical power grid load data, each target electrical data and the corresponding target equipment data, output multiple electrical integrated data, normalize each electrical integrated data, generate corresponding electrical normalized data and transmit it to the model analysis module 43.

[0104] The model analysis module 43 is used to call the statistical model in the AI ​​model module 42, take each electrical normalized data as input to the statistical model, output electrical sequence data and transmit it to the storage module 46;

[0105] The repository module 46 is used to store electrical sequence data.

[0106] It should be noted that you should refer to [link / reference]. Figure 5The platform transmission module 45 in the management platform module 4 receives the data, including target electrical data, equipment location feature data, and historical grid load data. After receiving the data, the data integration module 44 filters the equipment location feature data, retaining only the equipment location feature data corresponding to the target electrical data and deleting the rest. Next, the data integration module 44 cleans, integrates, and normalizes the collected historical grid power output load data and the electrical data of each low-voltage power device (the location coordinates of the low-voltage power devices in the target electrical data and the corresponding target device data). This involves processing the historical grid load data, the target electrical data, and the equipment location coordinates in the target device data. The data cleaning and integration process involves, for example, obtaining electrical data for three low-voltage electrical devices. This data is then cleaned, integrated, and normalized with historical power grid output load data to obtain three integrated electrical datasets. These datasets cover various aspects, including historical power grid output load, equipment operating parameters, and energy consumption. Next, the model analysis module 43 calls the statistical model in the AI ​​model module 42 to process the normalized electrical data, outputting electrical sequence data. This data is used to process time-series data, capture complex patterns of load changes, predict power load conditions and voltage and current parameters, and analyze the power grid load in real time. Input data is also mapped to predefined category labels, facilitating subsequent data correlation analysis of loss causes by the auxiliary analysis module 66. Finally, the electrical sequence data output by the model analysis module 43 is stored in the storage module 46. The statistical models include LSTM and RNN, which are types of AI models and are stored in the AI ​​model module 42. Because these two models can learn to make predictions or classifications based on the statistical characteristics of the input data (such as trends, periodicity, etc.), I will refer to LSTM and RNN collectively as statistical models in this article.

[0107] As a further improvement, the abnormal power equipment results include the location of abnormal low-voltage power equipment and the correlation data of abnormal itemsets; the electrical sequence data includes the probability density values ​​of electrical data points corresponding to each electrical normalized data; the loss monitoring module 6 includes an auxiliary analysis module 66, a loss calculation module 65, and a data extraction module 61, a loss determination module 62, and a source detection module 63 connected in sequence; the loss calculation module 65 is connected to the auxiliary analysis module 66 and the loss determination module 62 respectively; the data extraction module 61 is communicatively connected to the storage module 46 and the auxiliary analysis module 66 respectively.

[0108] Data extraction module 61 is used to call electrical sequence data in storage module 46 and transmit it to loss determination module 62 and auxiliary analysis module 66 respectively;

[0109] The loss determination module 62 is used to determine whether the probability density value of each electrical data point in the electrical sequence data is within a preset density range. The electrical normalized data corresponding to the probability density value of any electrical data point that is not within the preset density range is taken as abnormal electrical data and transmitted to the source detection module 63 and the loss calculation module 65 respectively.

[0110] Source detection module 63 is used to determine the location of the corresponding abnormal low-voltage power equipment based on the target equipment location feature data corresponding to each abnormal electrical data;

[0111] The loss calculation module 65 is used to perform quantitative analysis on various abnormal electrical data and preset normal state electrical data, determine the additional loss corresponding to each abnormal electrical data, and transmit it to the auxiliary analysis module 66.

[0112] The auxiliary analysis module 66 is used to generate corresponding abnormal itemset association data based on each additional loss and electrical sequence data using a preset association rule learning algorithm.

[0113] It should be noted that you should refer to [link / reference]. Figure 6During the monitoring process, the data extraction module 61 accesses and calls the electrical sequence data in the storage module 46 of the management platform module 4. The loss determination module 62 determines whether there is an abnormal loss in the electrical normalized data based on the probability density of each electrical data point in the electrical sequence data, that is, the probability density value of the electrical data point corresponding to each electrical normalized data, according to the preset density range value of historical data. If the probability density value of the electrical data point is within the preset density range value, it indicates that the electrical normalized data is normal. If the probability density value of the electrical data point is not within the preset density range value, it indicates that the electrical normalized data is abnormal. After determining the abnormality, the source detection module 63 combines the electrical equipment characteristics and location information data marked in the marking processing module 15, that is, the target equipment data corresponding to the electrical normalized data. The system traces the source of anomalies by using equipment location coordinates and equipment identifiers in timestamp data to pinpoint the location of abnormal power equipment and achieve precise location of the corresponding abnormal low-voltage power equipment. Simultaneously, the loss calculation module 65 performs quantitative analysis by comparing loss data under normal conditions (preset normal electrical data) and loss data under abnormal conditions (abnormal electrical data) to calculate the additional losses caused by the anomaly. Then, the auxiliary analysis module 66 uses preset association rule learning algorithms, such as Apriori or FP-Growth, to analyze the relationships between itemsets (such as historical data, equipment electrical parameters, current operating status, etc.) in the output sequence data, i.e., anomaly itemset association data, to identify possible combinations of factors that may cause abnormal losses and to preliminarily analyze the causes of power equipment anomalies. Finally, the anomaly feedback module 64 provides real-time feedback to the system and records these anomaly data in detail in the repository module 46 of the management platform. Anomalies occurring during the monitoring process are transmitted dual-channel to the management platform module 4 for anomaly feedback and storage, facilitating later feedback retrieval and improving the accuracy and efficiency of the system's anomaly handling.

[0114] As a further improvement, the system also includes an information visualization module; the loss monitoring module also includes an anomaly feedback module; the anomaly feedback module is connected to the source detection module and the auxiliary analysis module respectively; the anomaly feedback module is communicatively connected to the storage module; and the information visualization module is connected to the IoT management module.

[0115] The anomaly feedback module is used to receive the location data of each abnormal low-voltage power equipment sent by the source detection module and the correlation data of each abnormal itemset sent by the auxiliary analysis module, and transmit the location data of each abnormal low-voltage power equipment and the correlation data of each abnormal itemset to the repository module.

[0116] The repository module is also used to transmit the received data on the location of each abnormal low-voltage power device and the correlation data of each abnormal item set to the IoT management module through the platform transmission module;

[0117] The information visualization module is used to receive and display the location data of each abnormal low-voltage power device and the correlation data of each abnormal item set transmitted by the IoT management module.

[0118] It should be noted that the system's operating status and abnormal data information are ultimately displayed in the information visualization module 7, facilitating visual monitoring and processing of data by management personnel. The information visualization module 7 interfaces with the IoT management module 3, receiving system data from the IoT management module 3 in real time and presenting the system's operating status and data changes in a visual manner. This includes information such as daily equipment monitoring data collected from the terminal interface module 1, system network connection status, characteristics of electrical equipment terminals, and loss anomaly feedback from the loss monitoring module 6. This ensures that management personnel can promptly understand the latest system situation, providing a basis for power optimization, optimizing power network performance, and improving system energy efficiency and reliability.

[0119] For comparison of technical effects, existing technologies can be referenced. A low-voltage power management system refers to a circuit or equipment management system with a rated voltage of 1000 volts or less. In a low-voltage power management system, electrical energy is stepped down by transformers and then reliably transmitted to user terminal equipment via transmission lines and distribution equipment. In residential and commercial environments, low-voltage power is typically used to supply electricity for lighting and household appliances, improving grid efficiency and reliability while reducing energy consumption and emissions. Existing low-voltage power equipment monitoring systems can generally meet daily usage needs, but their intelligence level is low, failing to detect power consumption patterns based on actual consumption and provide a basis for power optimization. Furthermore, it is difficult to pinpoint the source of abnormal consumption in cases of abnormal power data, thus prolonging grid outage maintenance time and affecting the stability of power supply. Moreover, existing systems have low adaptability; data protocol conversion according to platform architecture is required during terminal connection, making network operation cumbersome and affecting system usability. Therefore, designing an intelligent low-voltage power management system is essential.

[0120] To address the aforementioned issues, this invention proposes a low-voltage power equipment monitoring system. This system collects power consumption data via sensor modules and transmits it to the Internet of Things (IoT). Then, it uses statistical models to monitor power load conditions and voltage and current parameters, analyzes the grid load in real time, and automatically detects power consumption patterns, providing a basis for power optimization and improving the performance of the power network, thereby enhancing the system's energy efficiency and reliability. A loss monitoring module automatically locates the source of abnormal power consumption and provides feedback to the system, facilitating maintenance personnel in troubleshooting. An interconnection processing module automatically converts the received data into the system's protocol format, eliminating the need for professional data conversion and architecture adjustments, thus improving the system's practicality.

[0121] Furthermore, by connecting to power sensing devices via sensor modules, the system collects detailed electricity consumption data from terminals and transmits it to the IoT management module. During management, the model analysis module calls statistical models from the AI ​​model module to monitor power load and voltage / current parameters, analyzing the grid load in real time. Simultaneously, it combines historical information from the storage module to statistically analyze historical load data, automatically detecting power consumption patterns and providing a basis for power optimization. This optimizes power network performance and improves system energy efficiency and reliability. The loss monitoring module automatically locates the source of abnormal consumption and feeds it back to the system, facilitating maintenance and reducing downtime in abnormal situations, ensuring power supply stability. The interconnection processing module connects to the terminal's sensor data and, using the conversion model in the architecture model module, automatically converts the data format into the system's protocol format without requiring specialized personnel. The data conversion and architecture adjustment facilitate network management for small and medium-sized power-consuming industries, improving the system's practicality. Simultaneously, the low-voltage power equipment monitoring system proposed in this invention can automatically convert to the system's protocol format, eliminating the need for professional personnel to perform data conversion and architecture adjustments, further enhancing system usability. The management platform module, based on location coordinate data, target electrical data, and historical grid load data, calls statistical models to generate electrical sequence data and predict power load conditions and voltage and current parameters. It analyzes the grid load in real time, automatically detects power consumption patterns, provides adjustment basis for power optimization, and optimizes power network performance. The loss monitoring module generates abnormal power equipment results based on electrical sequence data, automatically locates the source of abnormal consumption, and feeds back to the system, facilitating maintenance personnel's repairs. This solves the technical problem of unsatisfactory monitoring results caused by existing low-voltage power equipment abnormality monitoring methods.

[0122] In this embodiment of the invention, a low-voltage power equipment monitoring system is provided. The system includes a power grid connection module and, sequentially connected, a terminal docking module, an integrated network processing module, a management platform module, and a loss monitoring module. The power grid connection module is connected to both the management platform module and the power grid. The terminal docking module is communicatively connected to multiple low-voltage power devices and the management platform module. The terminal docking module acquires key electrical parameters and device location feature data for each low-voltage power device, and transmits the key electrical parameters to the integrated network processing module and the device location feature data to the management platform module. The power grid connection module acquires historical power grid load data and transmits it to the management platform module. The integrated network processing module performs data conversion on the key electrical parameters to generate corresponding initial... The process involves several steps: First, electrical data is collected and verified. Multiple target electrical data are then transmitted to the management platform module. The management platform module generates and stores electrical sequence data based on the location characteristics of each device, the target electrical data, and historical grid load data. Second, a loss monitoring module retrieves the electrical sequence data from the management platform module and generates abnormal power equipment results based on this data. This process, where a comprehensive network processing module converts and verifies the acquired key electrical parameters, determines multiple target electrical data, and then sequentially processes this data through the management platform module and the loss monitoring module to generate abnormal power equipment results, replaces the traditional method of operators using handheld detectors for regular on-site inspections. This allows for timely detection of low-voltage power equipment faults and further improves monitoring effectiveness.

[0123] Please see Figure 7 , Figure 7 This is a flowchart illustrating the steps of a low-voltage power equipment monitoring method provided in Embodiment 2 of the present invention.

[0124] This invention provides a method for monitoring low-voltage power equipment, comprising:

[0125] Step 701: Obtain key electrical parameters and equipment location characteristic data of multiple low-voltage power devices and historical grid load data of the power grid.

[0126] In this embodiment, key electrical parameters and equipment location feature data of multiple low-voltage power devices and historical grid load data of the power grid are obtained.

[0127] Step 702: Convert the data of each key electrical parameter to generate the corresponding initial electrical data and perform verification and comparison to determine multiple target electrical data.

[0128] In this embodiment, data conversion is performed on each key electrical parameter to generate corresponding initial electrical data, which are then verified and compared to determine multiple target electrical data.

[0129] Step 703: Generate electrical sequence data based on the location feature data of each device, the electrical data of each target, and the historical data of the power grid load.

[0130] In this embodiment, electrical sequence data is generated based on the location feature data of each device, the electrical data of each target, and the historical data of the power grid load.

[0131] Step 704: Generate power equipment anomaly results based on electrical sequence data.

[0132] In this embodiment, anomaly results for power equipment are generated based on electrical sequence data.

[0133] In this embodiment of the invention, a method for monitoring low-voltage power equipment is provided. First, key electrical parameters and location feature data of multiple low-voltage power devices, along with historical grid load data, are acquired. Next, the key electrical parameters are converted to generate corresponding initial electrical data, which are then verified and compared to determine multiple target electrical data. Based on the location feature data of each device, the target electrical data, and the historical grid load data, electrical sequence data is generated. Finally, based on the electrical sequence data, abnormal results of the power equipment are generated. Compared to the existing method of operators periodically conducting on-site inspections with handheld detectors and analyzing and diagnosing the stored detection data on a PC in the background, this method can replace the method of operators periodically conducting on-site inspections with handheld detectors, reducing reliance on technical personnel and further improving monitoring effectiveness.

[0134] This invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program; when the computer program is executed by the processor, the processor performs the steps of the low-voltage power equipment monitoring method as described in Embodiment 2 above.

[0135] This invention also provides a computer-readable storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the steps of the low-voltage power equipment monitoring method as described in Embodiment 2 above.

[0136] This invention also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the low-voltage power equipment monitoring method as described in Embodiment 2 above.

[0137] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0138] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0139] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A low-voltage power equipment monitoring system, characterized in that, The system includes a power grid connection module and a terminal docking module, an integrated network processing module, a management platform module, and a loss monitoring module connected in sequence. The power grid connection module is connected to the management platform module and the power grid respectively, and the terminal docking module is communicatively connected to multiple low-voltage power devices and the management platform module respectively. The terminal docking module is used to acquire key electrical parameters and equipment location feature data of each of the low-voltage power devices, and transmit the key electrical parameters and equipment location feature data to the integrated network processing module and the equipment location feature data to the management platform module; The power grid connection module is used to acquire historical power grid load data of the power grid and transmit it to the management platform module; The integrated network processing module is used to convert the data of each key electrical parameter, generate corresponding initial electrical data and perform verification and comparison respectively, determine multiple target electrical data, generate corresponding identifier timestamp data according to the location feature data of each device, and transmit each target electrical data and each identifier timestamp data to the management platform module. The management platform module is used to generate and store electrical sequence data based on the location feature data of each device, the electrical data of each target, the historical data of the power grid load, and the timestamp data of each identifier. The loss monitoring module is used to call the electrical sequence data in the management platform module and generate power equipment abnormality results based on the electrical sequence data; The integrated network processing module includes an interconnection processing module and an IoT management module connected in sequence. The interconnection processing module is connected to the terminal interface module, and the IoT management module is connected to the management platform module; The interconnection processing module is used to perform data conversion and first checksum on each of the key electrical parameters, generate each of the initial electrical data and the corresponding first check code, generate corresponding identifier timestamp data according to each of the device location feature data, and transmit each of the identifier timestamp data, each of the initial electrical data and the corresponding first check code to the IoT management module. The IoT management module is used to perform a second checksum on each of the initial electrical data, generate a second check code corresponding to each of the initial electrical data, and perform consistency comparison on each of the first check code and the corresponding second check code, and transmit any initial electrical data that matches the comparison as the target electrical data to the management platform module.

2. The low-voltage power equipment monitoring system according to claim 1, characterized in that, The terminal docking module includes a device docking module, a sensor module, a network upload module, and a tag processing module; The network upload module is connected to the tag processing module, the device docking module, and the sensor module, respectively; The device docking module is communicatively connected to each of the low-voltage power devices, and the network upload module is communicatively connected to the interconnection processing module and the management platform module, respectively. The sensor module is used to acquire key electrical parameters of each of the low-voltage power devices and transmit them to the interconnection processing module through the network upload module; The tagging processing module is used to acquire the equipment location feature data of each of the low-voltage power devices and transmit it to the management platform module and the interconnection processing module through the network upload module.

3. The low-voltage power equipment monitoring system according to claim 2, characterized in that, The interconnection processing module includes an architecture model module and, in sequence, an upload and receive module, an architecture detection module, a model invocation module, a protocol adjustment module, and an adjustment output module. The model calling module is connected to the architecture model module, and the adjustment output module is communicatively connected to the IoT management module; The network upload module is communicatively connected to the upload receiving module and the adjustment output module, respectively. The architecture detection module is used to detect the protocol type of each key electrical parameter transmitted by the upload and receive module, output the protocol type data corresponding to each key electrical parameter, and transmit each key electrical parameter and the corresponding protocol type data to the model call module. The model invocation module is used to invoke the protocol conversion model corresponding to each of the protocol type data in the architecture model module, and transmit each of the key electrical parameters and the corresponding protocol conversion model to the protocol adjustment module; The protocol adjustment module is used to preprocess each of the key electrical parameters, output corresponding coded electrical data, use each of the protocol conversion models to convert the corresponding coded electrical data into a protocol format, generate corresponding electrical conversion data, and transmit it to the adjustment output module. The adjustment output module is used to generate corresponding identifier timestamp data based on the device feature information in each device location feature data when it receives each electrical conversion data and each device location feature data transmitted by the network upload module; generate multiple initial electrical data using each electrical conversion data and each identifier timestamp data; perform a first checksum on each initial electrical data to generate a first checksum corresponding to the initial electrical data; and transmit the initial electrical data and the corresponding first checksum to the IoT management module.

4. The low-voltage power equipment monitoring system according to claim 3, characterized in that, The management platform module includes an AI model module and, in sequence, a platform transmission module, a data integration module, a model analysis module, and a storage module. The platform transmission module is communicatively connected to the power grid connection module, the IoT management module, and the storage module, respectively. The AI ​​model module is connected to the model analysis module, and the storage module is communicatively connected to the loss monitoring module. The data integration module is used to filter multiple device location feature data based on each target electrical data, determine the target device data corresponding to each target electrical data, perform data cleaning and data integration on the device location coordinates in the power grid load historical data, each target electrical data and the corresponding target device data, output multiple electrical integrated data, normalize each electrical integrated data, generate corresponding electrical normalized data and transmit it to the model analysis module; The model analysis module is used to call the statistical model in the AI ​​model module, take each of the electrical normalized data as input to the statistical model, output electrical sequence data and transmit it to the storage module; The repository module is used to store the electrical sequence data.

5. The low-voltage power equipment monitoring system according to claim 4, characterized in that, The abnormal power equipment results include the location of abnormal low-voltage power equipment and the correlation data of abnormal itemsets; the electrical sequence data includes the probability density value of electrical data points corresponding to each of the electrical normalized data; the loss monitoring module includes an auxiliary analysis module, a loss calculation module, and a data extraction module, a loss determination module, and a source detection module connected in sequence. The loss calculation module is connected to the auxiliary analysis module and the loss determination module, respectively. The data extraction module is communicatively connected to the storage module and the auxiliary analysis module, respectively. The data extraction module is used to call the electrical sequence data in the storage module and transmit it to the loss determination module and the auxiliary analysis module respectively. The loss determination module is used to determine whether the probability density value of each electrical data point in the electrical sequence data is within a preset density range. The electrical normalized data corresponding to any electrical data point probability density value that is not within the preset density range is taken as abnormal electrical data and transmitted to the source detection module and the loss calculation module respectively. The source detection module is used to determine the location of the corresponding abnormal low-voltage power equipment based on the target equipment location feature data corresponding to each of the abnormal electrical data. The loss calculation module is used to perform quantitative analysis on each of the abnormal electrical data and the preset normal state electrical data, determine the additional loss corresponding to each of the abnormal electrical data, and transmit it to the auxiliary analysis module. The auxiliary analysis module is used to generate corresponding abnormal itemset association data based on each of the additional loss amounts and the electrical sequence data using a pre-set association rule learning algorithm.

6. The low-voltage power equipment monitoring system according to claim 5, characterized in that, The system also includes an information visualization module; the loss monitoring module also includes an anomaly feedback module. The anomaly feedback module is connected to the source detection module and the auxiliary analysis module, respectively. The exception feedback module is communicatively connected to the repository module; The information visualization module is connected to the IoT management module; The anomaly feedback module is used to receive the location data of each of the abnormal low-voltage power devices sent by the source detection module and the association data of each of the abnormal itemsets sent by the auxiliary analysis module, and transmit the location data of each of the abnormal low-voltage power devices and the association data of each of the abnormal itemsets to the repository module; The repository module is also used to transmit the received location data of each of the abnormal low-voltage power devices and the association data of each of the abnormal itemsets to the IoT management module through the platform transmission module; The information visualization module is used to receive and display the location data of each abnormal low-voltage power device and the association data of each abnormal item set transmitted by the IoT management module.

7. A method for monitoring low-voltage power equipment, applied to the low-voltage power equipment monitoring system of claim 1, characterized in that, include: Acquire key electrical parameters and equipment location characteristics of multiple low-voltage power devices, as well as historical grid load data of the power grid; The key electrical parameters are converted to generate corresponding initial electrical data, which are then verified and compared to determine multiple target electrical data. Based on the location feature data of each device, the electrical data of each target, and the historical load data of the power grid, generate electrical sequence data; Based on the electrical sequence data, generate power equipment anomaly results.

8. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the low-voltage power equipment monitoring method as described in claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the low-voltage power equipment monitoring method as described in claim 7.

Images