Electrical safety monitoring method, apparatus, computer device and storage medium

Abstract

The application relates to an electrical safety monitoring method and device, computer equipment and a storage medium. The method relates to the field of artificial intelligence and comprises the following steps: acquiring a three-dimensional space model corresponding to a building, the three-dimensional space model being generated according to the deployment positions of electrical equipment in the building and the line connection relationships between the electrical equipment, the electrical equipment comprising a line monitor and electrical equipment; receiving target line data collected by a target line monitor; obtaining an operation state detection result of a target line where the target line monitor is located according to the three-dimensional space model and the target line data by using a trained electrical safety monitoring model based on a neural network; when the operation state detection result indicates that the target line is in an abnormal operation state, determining target electrical equipment related to the target line, and generating a control instruction for shutting down the target electrical equipment. The method can automatically adjust the operation of the electrical equipment and reduce the loss caused by the power failure of the entire region due to abnormalities.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to an electrical safety monitoring method and device, computer equipment and storage medium. BACKGROUND

[0002] Electrical safety monitoring is an important part of smart building construction. In order to ensure the safety of electricity inside the building and the normal operation of each electrical equipment, the electrical safety inside the building needs to be monitored.

[0003] At present, the electrical safety monitoring inside the building mainly adopts the following two ways: the first is the traditional fuse, which can automatically cut off the power supply when the current is too large to produce high temperature and the fuse is blown, so as to prevent the occurrence of fire accidents; the second is to configure air switch for electrical equipment, which will automatically disconnect as long as the current in the circuit exceeds the rated current, so as to shut down the electrical equipment.

[0004] The above two ways can only harshly and directly shut down the operation of electrical equipment, which not only affects the normal operation of the power system inside the building, but also brings great inconvenience to the user, such as data loss and so on. SUMMARY

[0005] Therefore, it is necessary to provide an electrical safety monitoring method, device, computer equipment and storage medium which can intelligently monitor the electrical operation state inside the building and dynamically adjust the operation of electrical equipment when an abnormality occurs.

[0006] A three-dimensional space model corresponding to the building is obtained, which is generated according to the deployment position of the electrical equipment inside the building and the line connection relationship between each electrical equipment, and the electrical equipment includes line monitor and electrical equipment;

[0007] Target line data collected by a target line monitor is received;

[0008] Through the trained electrical safety monitoring model based on neural network, the running state detection result of the target line where the target line monitor is located is obtained according to the three-dimensional space model and the target line data;

[0009] When the running state detection result indicates that the target line is in an abnormal running state, a target electrical equipment related to the target line is determined, and a control instruction for shutting down the target electrical equipment is generated.

[0010] In one embodiment, the three-dimensional space model corresponding to the building is obtained, including:

[0011] Obtaining a building information model corresponding to the building;

[0012] Map the deployment positions of the electrical equipment in the building and the line connection relationship between the electrical equipment to the building information model, and obtain a three-dimensional space model corresponding to the building.

[0013] In one embodiment, the method further comprises:

[0014] Receiving sample line data reported by a sample line monitor;

[0015] Obtaining rated electrical parameters corresponding to the electrical equipment in the building;

[0016] Calculating actual electrical parameters of the line where the sample line monitor is located according to the sample line data;

[0017] When the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitor is located exceeds a threshold value within a preset time length, determining that the running state annotation data of the line where the sample line monitor is located is abnormal.

[0018] In one embodiment, the method further comprises:

[0019] When the sample line monitor is located on the line of a monitored electrical equipment, the sample line data includes at least one of actual voltage, actual current, and actual temperature, and the actual working power of the electrical equipment is calculated according to the actual voltage and the actual current;

[0020] The method further comprises:

[0021] When at least one of the difference between the actual voltage and the rated voltage of the electrical equipment, the difference between the actual current and the rated current of the electrical equipment, the difference between the actual working power and the rated power of the electrical equipment, and the difference between the actual temperature and the normal working temperature exceeds a threshold value within a preset time length, determining that the running state annotation data of the electrical equipment is abnormal.

[0022] In one embodiment, the method further comprises:

[0023] When the sample line monitor is used to monitor a line, the sample line data includes at least one of actual voltage, actual current, and actual temperature, and the actual line loss of the monitored line is calculated according to the resistivity of the line at the actual temperature, the actual current, and the actual voltage.

[0024] the difference between the actual electrical parameter and the rated electrical parameter of the line monitored by the sample line monitor exceeds a threshold value within a preset time length, it is determined that the running state label data of the line monitored by the sample line monitor is abnormal.

[0025] When the difference between the actual line loss and the standard line loss exceeds a threshold value within a preset time length, it is determined that the running state label data of the monitored line is abnormal.

[0026] In one embodiment, the training step of the electrical safety monitoring model comprises:

[0027] Obtain training samples, the training samples comprising sample line data monitored by a sample line monitor in the building and corresponding running state label data;

[0028] Input the sample line data and the three-dimensional space model into an initial neural network model, and perform transformation processing on the three-dimensional space model and the sample line data through the current first connection weight between the input layer and the hidden layer of the initial neural network model, to obtain hidden layer features;

[0029] Fuse the hidden layer features after transformation processing through the current second connection weight between the hidden layer and the output layer of the initial neural network model, to obtain a predicted running state;

[0030] Construct an error function according to the running state label data and the predicted running state, minimize the error function, and determine updated first connection weight and updated second connection weight;

[0031] After updating the initial neural network model according to the updated first connection weight and the updated second connection weight, return to the step of obtaining training samples for continuous training until a training end condition is met, and obtain the electrical safety monitoring model.

[0032] In one embodiment, the running state detection result of the target line monitored by the target line monitor is obtained according to the three-dimensional space model and the target line data through the trained neural network-based electrical safety monitoring model, comprising:

[0033] Input the three-dimensional space model and the target line data into the trained neural network-based electrical safety monitoring model;

[0034] Perform transformation processing on the three-dimensional space model and the target line data through the first connection weight between the input layer and the hidden layer of the electrical safety monitoring model, to obtain hidden layer features;

[0035] By using the second connection weight between the hidden layer and the output layer of the electrical safety monitoring model, the features of each hidden layer are transformed and then fused to obtain the operating status detection result of the target line where the target line monitor is located.

[0036] In one embodiment, obtaining the operational status detection result of the target line where the target line monitoring instrument is located, based on the three-dimensional spatial model and the target line data, using a trained neural network-based electrical safety monitoring model, includes:

[0037] The data acquisition time is used to determine the target line data.

[0038] The acquisition time, the three-dimensional spatial model, and the target line data are input into a trained neural network-based electrical safety monitoring model, and the electrical safety monitoring model outputs the operating status detection results of the target line where the target line monitoring instrument is located.

[0039] The method further includes:

[0040] When the operation status detection result indicates that the target line is in normal operation and the collection time is within the peak power consumption period, the target electrical equipment related to the target line is identified, and peak-shaving operation information about the target electrical equipment is generated.

[0041] In one embodiment, determining the target electrical equipment associated with the target line includes:

[0042] Obtain the deployment location of the target line monitoring device in the three-dimensional spatial model;

[0043] The target electrical equipment associated with the target line is determined based on the deployment location.

[0044] In one embodiment, determining the target electrical equipment associated with the target line based on the deployment location includes:

[0045] Based on the deployment location, identify multiple electrical devices related to the target line;

[0046] Obtain the preset power priority level corresponding to the device type;

[0047] The priority level of electricity consumption is determined based on the equipment type of each of the plurality of electrical devices;

[0048] The electrical device with the lowest power priority among the multiple electrical devices is selected as the target electrical device.

[0049] In one embodiment, the method further includes:

[0050] When the dynamic adjustment function for the power transmission lines of the building has been activated, then

[0051] The step of generating a control command for shutting down the target electrical equipment is executed, and the control command is sent to the target electrical equipment to stop the target electrical equipment from operating.

[0052] When the dynamic adjustment function for the power transmission lines of the building is not activated, then

[0053] Generate a control command to disconnect the target line; or

[0054] Based on the operational status detection results, the abnormality type of the target electrical equipment is determined;

[0055] Anomaly warning information is generated based on the anomaly type and the deployment location of the target electrical equipment.

[0056] In one embodiment, the method further includes:

[0057] When the operational status detection result indicates that the target electrical equipment associated with the target line has stopped operating, the target line is in an abnormal operational state.

[0058] Generate control commands to disconnect the target line.

[0059] In one embodiment, the method further includes:

[0060] Persist the target line data and the operation status detection results;

[0061] The target line data and the operation status detection results are used as training sample data;

[0062] The electrical safety monitoring model is trained offline using the training sample data and the three-dimensional spatial model.

[0063] An electrical safety monitoring device, the device comprising:

[0064] The acquisition module is used to acquire a three-dimensional spatial model of the building. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes a wiring monitor and electrical appliances.

[0065] The receiving module is used to receive target line data collected by the target line monitor.

[0066] The prediction module is used to obtain the operating status detection result of the target line where the target line monitor is located by using a trained neural network-based electrical safety monitoring model, based on the three-dimensional spatial model and the target line data.

[0067] The control module is used to determine the target electrical equipment related to the target line and generate a control command to shut down the target electrical equipment when the operation status detection result indicates that the target line is in an abnormal operation state.

[0068] An electrical safety monitoring system includes a target line monitor, target electrical equipment, and a server, wherein:

[0069] The server is used to obtain a three-dimensional spatial model of the building. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes a wiring monitor and electrical appliances.

[0070] The target line monitor is used to collect target line data of the target line where the target electrical equipment is located, and to report the target line data to the server.

[0071] The server is used to receive target line data collected by the target line monitor; and to obtain the operating status detection result of the target line where the target line monitor is located based on the three-dimensional spatial model and the target line data through a trained neural network-based electrical safety monitoring model.

[0072] The server is also configured to, when the operating status detection result indicates that the target line is in an abnormal operating state, determine the target electrical equipment related to the target line and generate a control command for shutting down the target electrical equipment;

[0073] The target electrical equipment is used to stop operating after receiving a control command from the server.

[0074] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0075] A three-dimensional spatial model of the building is obtained. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes a wiring monitor and electrical appliances.

[0076] Receive target line data collected by the target line monitoring instrument;

[0077] By using a trained neural network-based electrical safety monitoring model, the operating status detection results of the target line where the target line monitoring instrument is located are obtained based on the three-dimensional spatial model and the target line data.

[0078] When the operation status detection result indicates that the target line is in an abnormal operation state, the target electrical equipment related to the target line is identified, and a control command for shutting down the target electrical equipment is generated.

[0079] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0080] A three-dimensional spatial model of the building is obtained. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes a wiring monitor and electrical appliances.

[0081] Receive target line data collected by the target line monitoring instrument;

[0082] By using a trained neural network-based electrical safety monitoring model, the operating status detection results of the target line where the target line monitoring instrument is located are obtained based on the three-dimensional spatial model and the target line data.

[0083] When the operation status detection result indicates that the target line is in an abnormal operation state, the target electrical equipment related to the target line is identified, and a control command for shutting down the target electrical equipment is generated.

[0084] A computer program comprising computer instructions stored in a computer-readable storage medium, wherein a processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions to cause the computer device to perform the steps of the above-described electrical safety monitoring method.

[0085] The aforementioned electrical safety monitoring methods, systems, devices, computer equipment, and storage media, on the one hand, generate a three-dimensional spatial model of the building based on the deployment location of electrical equipment within the building and the complex wiring connections between various electrical equipment, which can assist in monitoring the electrical safety inside the building; on the other hand, through a trained neural network-based electrical safety monitoring model, they can intelligently predict the operating status of transmission lines, enabling real-time understanding of the electrical operating status and safety hazards of the entire building. Furthermore, when the predicted operating status detection results indicate that the transmission line is abnormal, they can determine the specific location of the abnormality and the target electrical equipment related to the abnormality. Under the premise of ensuring safety, they can generate control commands to shut down the target electrical equipment, automatically adjusting the operating status of the electrical equipment and reducing losses caused by power outages in the entire area due to abnormalities. Attached Figure Description

[0086] Figure 1 This is a diagram illustrating the application environment of an electrical safety monitoring method in one embodiment;

[0087] Figure 2 This is a flowchart illustrating an electrical safety monitoring method in one embodiment;

[0088] Figure 3 This is a schematic diagram of a line monitoring device deployed on a transmission line in one embodiment;

[0089] Figure 4 This is a schematic diagram illustrating the generation of a three-dimensional spatial model in one embodiment;

[0090] Figure 5 This is a schematic diagram of obtaining an electrical safety monitoring model in one embodiment;

[0091] Figure 6 This is a flowchart illustrating the process of obtaining the running status detection result in one embodiment;

[0092] Figure 7 This is a flowchart illustrating the electrical safety monitoring method in another embodiment;

[0093] Figure 8 This is a flowchart of an electrical safety monitoring method in one embodiment;

[0094] Figure 9 This is a structural block diagram of an electrical safety monitoring device in one embodiment;

[0095] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0096] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0097] The electrical safety monitoring method provided in this application involves Artificial Intelligence (AI) technology. AI utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to obtain optimal results—theories, methods, technologies, and application systems. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce new intelligent machines capable of reacting in a manner similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess perception, reasoning, and decision-making capabilities.

[0098] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, machine learning, and deep learning.

[0099] Machine Learning (ML) is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and instructional learning.

[0100] Figure 1 This is a diagram illustrating the application environment of an electrical safety monitoring method in one embodiment. (Refer to...) Figure 1 The electrical safety monitoring method provided in this application can be applied to, for example, Figure 1 In the application environment shown, the electrical equipment inside the building communicates with the server via a network. The electrical equipment includes a line monitor 102 and electrical equipment 104, which communicate with the server 106 via the network.

[0101] Line monitoring devices are deployed on the power transmission lines inside the building. These devices can be deployed on the branch lines of each electrical device to monitor the operating status of each device; they can also be deployed on the branch lines of multiple electrical devices to monitor the operating status of that branch.

[0102] Server 106 first needs to train an initial neural network based on multiple training samples. Each training sample includes sample line data monitored by the sample line monitoring device within the building and corresponding operating status annotation data. After training, an electrical safety monitoring model is obtained. Then, the computer equipment can generate a three-dimensional spatial model of the building based on the deployment location of electrical equipment within the building and the line connection relationships between each electrical device. After receiving target line data collected by the target line monitoring device within the building, server 106 uses the trained neural network-based electrical safety monitoring model to obtain the operating status detection result of the target line monitoring device 102's line based on the three-dimensional spatial model and the target line data. When the operating status detection result indicates that the target line is in an abnormal operating state, the server identifies the target electrical equipment 104 related to the target line and generates a control command to shut down the target electrical equipment 104.

[0103] The line monitor 102 can be, but is not limited to, various sensors, such as Hall voltage sensors, Hall current sensors, resistance sensors, temperature sensors, etc. The electrical equipment 104 can be, but is not limited to, various computer equipment, home appliances, server clusters, mechanical equipment, etc. The server 106 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. The line monitor 102 and the electrical equipment 104 can be directly or indirectly connected to the server 106 via wired or wireless communication methods; this application does not impose any restrictions.

[0104] In one embodiment, such as Figure 2 As shown, an electrical safety monitoring method is provided, which is applied to... Figure 1 Taking server 106 as an example, the explanation includes the following steps:

[0105] Step 202: Obtain the three-dimensional spatial model corresponding to the building. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes wiring monitoring instruments and electrical appliances.

[0106] Buildings, in this context, refer to structures requiring electrical monitoring, such as office buildings, factories, construction sites, schools, and stadiums. A building's 3D spatial model represents its internal structure and the layout of power transmission lines. Electrical equipment within a building is a collective term for any equipment that requires electricity; it can be categorized based on whether it consumes electrical energy into electrical appliances and line monitoring devices. Electrical appliances can include home appliances, server clusters, machinery, and so on. Line monitoring devices are used to monitor the operational status of power transmission lines and can be Hall effect voltage sensors, Hall effect current sensors, resistance sensors, temperature sensors, and so on.

[0107] In order to monitor the operating status of electrical equipment and power transmission lines within buildings, line monitoring devices need to be pre-deployed on the power transmission lines. For example... Figure 3 The diagram shown is a schematic of a line monitoring device deployed on a transmission line in one embodiment. (Refer to...) Figure 3 Line monitor A is located on branch 302, which contains multiple electrical devices, and can be used to monitor the operating status of that line. Line monitor B is located on branch 304, which contains electrical devices 4 and 5, and can be used to monitor the operating status of electrical devices 4 and 5. In addition, the line monitors also have the ability to communicate with an external server to report the monitored line data to the server in real time.

[0108] Specifically, the server can generate a three-dimensional spatial model of the building in advance based on the deployment location of electrical equipment inside the building and the wiring connections between the various electrical equipment. This three-dimensional spatial model can be used to help predict the operating status of the power transmission lines inside the building.

[0109] In one embodiment, the deployment location of electrical equipment can be represented by at least one of the geographical coordinates and indoor spatial coordinates of the electrical equipment. Geographical coordinates represent the geographical location of the electrical equipment on the Earth's surface, i.e., latitude and longitude coordinates. The latitude and longitude coordinates of different electrical equipment can reflect the layout of the equipment within the building, making these coordinates one of the features for monitoring electrical safety. Indoor spatial coordinates represent the spatial layout of the electrical equipment within the building, for example, A101 in section A on the 5th floor. This reflects the specific location and label of the electrical equipment within the indoor space, and these indoor spatial coordinates can be one of the features for determining the location of anomalies after monitoring electrical safety. Therefore, the server can generate a three-dimensional spatial model of the building based on the geographical coordinates or indoor spatial coordinates of the electrical equipment, as well as the wiring connections between these coordinates, and use this three-dimensional spatial model to assist in the monitoring of electrical safety throughout the building.

[0110] In one embodiment, step 202, obtaining the three-dimensional spatial model corresponding to the building, includes: obtaining the building information model corresponding to the building; mapping the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical equipment to the building information model to obtain the three-dimensional spatial model corresponding to the building.

[0111] Building Information Modeling (BIM) represents a 3D design model of a building's internal structure, providing a visual and realistic representation of its internal components. The server can then bind the locations of electrical equipment and power lines within the building to this BIM model, thereby obtaining a corresponding 3D spatial model of the building. Specifically, the server needs to obtain the location and wiring connections of each electrical device within the building and bind these locations and connections to the BIM model—in other words, map the location and wiring connections of each electrical device into the BIM model to obtain the building's 3D spatial model.

[0112] like Figure 4 The image shown is a schematic diagram illustrating the generation of a three-dimensional spatial model in one embodiment. (Refer to...) Figure 4 The server can first obtain the building information model of the building, and then obtain a three-dimensional spatial model based on the geographical coordinates and indoor spatial coordinates of each electrical device and line in the building.

[0113] In one embodiment, the three-dimensional spatial model can also be displayed to the staff responsible for the electrical safety maintenance inside the building via a display screen. When receiving the abnormal results from the server, the abnormality can be visualized at the corresponding location in the three-dimensional spatial model according to the location where the abnormality occurred. This can help the staff to discover the location of the abnormality in a timely manner and take corresponding measures to improve the effectiveness of electrical safety monitoring.

[0114] Step 204: Receive the target line data collected by the target line monitoring instrument.

[0115] The target line monitoring device can be any line monitoring device deployed inside the building. Each line monitoring device can report the collected line data to the server in real time, or periodically report the line data collected over a period of time to the server at preset time intervals. Line data can include voltage, resistance, current, temperature, etc.

[0116] In one embodiment, to ensure information security within the building, the target line monitoring device can also use a security encryption algorithm to encrypt the target line data before reporting it to the server. The server receives the encrypted target line data and decrypts it to obtain the decrypted target line data.

[0117] Step 206: Using the trained neural network-based electrical safety monitoring model, obtain the operating status detection results of the target line where the target line monitoring instrument is located based on the three-dimensional spatial model and the target line data.

[0118] The electrical safety monitoring model is a model obtained by training an initial neural network using multiple training samples. Each training sample includes sample line data monitored by a sample line monitoring instrument within the building and corresponding operational status annotation data. The electrical safety monitoring model is a neural network model capable of predicting the operational status of transmission lines. The server can obtain an initial neural network model based on the neural network model structure beforehand, and then train the initial neural network model using multiple training samples to obtain the model parameters of the electrical safety monitoring model. Each training sample includes sample line data monitored by a sample line monitoring instrument within the building and corresponding operational status annotation data, as well as a three-dimensional spatial model reflecting the building's internal structure and electrical layout. The model obtained through training with the training sample data has the ability to predict the operational status of transmission lines. When it is necessary to predict the operational status of transmission lines, the trained model parameters can be obtained and then imported into the initial neural network model to obtain the electrical safety monitoring model.

[0119] Specifically, when monitoring electrical safety within a building, a three-dimensional spatial model reflecting the building's internal structure and electrical layout, along with target line data collected by a target line monitor, can be input into a pre-trained electrical safety monitoring model. The electrical safety monitoring model can then make predictions based on this information to obtain the operational status detection results of the target line where the target line monitor is located.

[0120] The server obtains operational status detection results including probabilities for various operational status categories. These categories can include overheating, overvoltage, overcurrent, and normal, with overheating, overvoltage, and overcurrent being abnormal states. Abnormal states can also include aging lines, poor line connections, etc. An electrical safety monitoring model can be trained based on actual conditions to enable it to detect these anomalies. Since the deployment locations of electrical equipment and line connections in the 3D spatial model reflect the electrical equipment and lines connected to the target line, and the target line data reflects its current operational status, these two elements can be used as features to predict whether the target line is in a normal or abnormal operational state.

[0121] Step 208: When the operation status detection result indicates that the target line is in an abnormal operation state, identify the target electrical equipment related to the target line and generate a control command to shut down the target electrical equipment.

[0122] Specifically, the target monitoring device is pre-embedded in the target line. When the server indicates that the target line is in an abnormal operating state based on the operation status detection results output by the electrical safety monitoring model, the server can determine the target electrical equipment related to the target line according to the deployment location of each electrical device and line in the three-dimensional spatial model, generate a control command to shut down the target electrical equipment, and send the control command to the target electrical equipment. This can automatically adjust the operation of the target electrical equipment and the target line, avoiding the loss caused by directly disconnecting the entire target line due to abnormality.

[0123] In one embodiment, determining the target electrical equipment associated with the target line includes: obtaining the deployment location of the target line monitor in a three-dimensional spatial model; and determining the target electrical equipment associated with the target line based on the deployment location.

[0124] In one embodiment, determining the target electrical equipment related to the target line based on the deployment location includes: determining multiple electrical equipment related to the target line based on the deployment location; obtaining a preset power priority level corresponding to the equipment type; determining the power priority level based on the equipment type of each of the multiple electrical equipment; and selecting the electrical equipment with the lowest power priority level among the multiple electrical equipment as the target electrical equipment.

[0125] In this embodiment, the server can also obtain the device priorities set in advance by the staff. Different priority levels are set for different types of devices or devices with different uses. In the event of an anomaly, the server can determine the target device from multiple devices based on the power consumption priority and shut it down first. For example, when the target line is overloaded, the devices related to the target line include the server room and the air conditioning room. To avoid data loss, the air conditioning room can be shut down first based on priority, thus avoiding the loss caused by directly disconnecting the entire target line.

[0126] In one embodiment, the method further includes: when the dynamic adjustment function of the building's power transmission lines has been activated, performing a step of generating a control command for shutting down the target electrical equipment and sending the control command to the target electrical equipment to stop the target electrical equipment from operating; when the dynamic adjustment function of the building's power transmission lines has not been activated, generating a control command to disconnect the target line; or determining the abnormal type of the target electrical equipment based on the operating status detection results; and generating abnormal warning information according to the abnormal type and the deployment location of the target electrical equipment.

[0127] Specifically, building electrical safety management personnel can manage all electrical equipment within the building through a unified management platform. When personnel activate the automatic adjustment function of the circuit, the server directly sends control commands to the target electrical equipment. When personnel do not activate the automatic adjustment function, the server can directly generate a control command to disconnect the target circuit. The target circuit monitor deployed on the target circuit can receive this control command and disconnect the entire target circuit accordingly. The server can also generate abnormal warning information based on the anomaly type and the deployment location of the target electrical equipment, and report it to the personnel, who can then handle the abnormal state themselves.

[0128] In one embodiment, the method further includes: when the operation status detection result indicates that the target line is in an abnormal operation state after the target electrical equipment associated with the target line stops operating, a control command for disconnecting the target line is generated.

[0129] In this embodiment, when the server determines that an abnormal state cannot be avoided by dynamically adjusting, i.e., shutting down a certain target electrical device related to the target line, it can directly generate a control command to disconnect the entire target line. The target line monitoring device deployed on the target line can receive this control command and disconnect the entire target line accordingly.

[0130] In one embodiment, a trained neural network-based electrical safety monitoring model is used to obtain the operational status detection result of the target line where the target line monitoring instrument is located, based on a three-dimensional spatial model and target line data. This includes: determining the data acquisition time of the target line; inputting the acquisition time, three-dimensional spatial model, and target line data into the trained neural network-based electrical safety monitoring model, and outputting the operational status detection result of the target line where the target line monitoring instrument is located through the electrical safety monitoring model. The method further includes: when the operational status detection result indicates that the target line is in normal operation and the acquisition time is within the peak electricity consumption period, identifying the target electrical equipment related to the target line, and generating peak-shaving operation information for the target electrical equipment.

[0131] In this embodiment, the collection time and temperature are used as features to predict the operating status of the target line. Under normal operating conditions, early warning information about the target electrical equipment can also be generated. For example, if a brief overcurrent occurs in line A1 of area A on the 18th floor, it is recommended not to turn on the air conditioner and refrigerator at the same time.

[0132] In one embodiment, the target line data also includes the service life of the transmission line. A trained neural network-based electrical safety monitoring model is used to obtain the operational status detection results of the target line where the target line monitoring device is located, based on the three-dimensional spatial model and the target line data. This includes: determining the service life of the target line; inputting the service life, the three-dimensional spatial model, and the target line data into the electrical safety monitoring model; and outputting the operational status detection results of the target line where the target line monitoring device is located through the electrical safety monitoring model. When the operational status detection results indicate that the target line is in an aging operational state, a warning message indicating that the target line needs maintenance or replacement is generated.

[0133] In the aforementioned electrical safety monitoring method, on the one hand, a three-dimensional spatial model of the building is generated based on the deployment location of electrical equipment within the building and the complex wiring connections between various electrical equipment, which can assist in monitoring the electrical safety inside the building; on the other hand, a trained neural network-based electrical safety monitoring model is used to intelligently predict the operating status of transmission lines, enabling real-time understanding of the electrical operating status and safety hazards of the entire building. Furthermore, when the predicted operating status detection results indicate that the transmission line is abnormal, the specific location of the abnormality and the target electrical equipment related to the abnormality can be determined. Under the premise of ensuring safety, a control command to shut down the target electrical equipment can be generated, which can automatically adjust the operating status of the electrical equipment and reduce the losses caused by power outages in the entire area due to abnormalities.

[0134] In one embodiment, the server needs to train the initial neural network model beforehand to obtain the electrical safety monitoring model. The method also includes the step of obtaining training samples: receiving sample line data reported by the sample line monitor; obtaining the rated electrical parameters corresponding to the electrical equipment in the building; calculating the actual electrical parameters of the line where the sample line monitor is located based on the sample line data; and determining that the operating status label data of the line where the sample line monitor is located is abnormal when the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitor is located exceeds a threshold within a preset time period.

[0135] Specifically, to obtain sample data for training the electrical safety monitoring model, the server needs to acquire knowledge based on some examples beforehand. The server can initially use some circuit monitoring devices within the building as sample circuit monitoring devices, and the circuit data reported by these devices as sample circuit data. The server also needs to obtain the rated electrical parameters of each electrical device within the building. Based on the received sample circuit data and specific circuit knowledge, the server calculates the actual electrical parameters of the circuit where the sample circuit monitoring device is located. When the difference between the actual electrical parameters and the rated electrical parameters continuously exceeds a threshold, the operating status of the circuit where the sample circuit monitoring device is located is marked as abnormal. In this way, based on the sample circuit data and the corresponding detection results, the server has the sample data for training the model.

[0136] In one embodiment, calculating the actual electrical parameters of the line where the sample line monitor is located based on sample line data includes: when the sample line monitor is located on the line of the monitored electrical equipment, the sample line data includes at least one of actual voltage, actual current, and actual temperature; calculating the actual operating power of the monitored electrical equipment based on the actual voltage and actual current; when the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitor is located exceeds a threshold within a preset time period, the operating status label data of the line where the sample line monitor is located is determined to be abnormal, including: when at least one of the differences between the actual voltage and the rated voltage of the electrical equipment, the difference between the actual current and the rated current of the electrical equipment, the difference between the actual operating power and the rated power of the electrical equipment, and the difference between the actual temperature and the normal operating temperature exceeds a threshold within a preset time period, the operating status label data of the electrical equipment is determined to be abnormal.

[0137] It is understood that in this embodiment, the sample line tester is used to monitor electrical equipment. When the difference between the actual voltage of the electrical equipment and the rated voltage of the electrical equipment exceeds a threshold within a preset time period, the corresponding operating status label data is overvoltage. When the difference between the actual current and the rated current of the electrical equipment exceeds a threshold within a preset time period, the corresponding operating status label data is overcurrent. When the difference between the actual operating power and the rated power of the electrical equipment exceeds a threshold within a preset time period, the corresponding operating status label data is overload. When the difference between the actual temperature and the normal operating temperature exceeds a threshold within a preset time period, the corresponding operating status label data is overheating.

[0138] In this embodiment, the corresponding detection results are determined by the sample line data of the electrical equipment monitored by the sample line monitor, thus providing the sample data for training the model.

[0139] In one embodiment, calculating the actual electrical parameters of the line where the sample line monitor is located based on sample line data includes: when the sample line monitor is used to monitor the line, the sample line data includes at least one of actual voltage, actual current, and actual temperature; calculating the actual line loss of the monitored line based on the resistivity, actual current, and actual voltage of the monitored line at the actual temperature; and determining that the operating status label data of the line where the sample line monitor is located is abnormal when the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitor is located exceeds a threshold within a preset time period, including: when the difference between the actual line loss and the standard line loss exceeds a threshold within a preset time period, determining that the operating status label data of the monitored line is abnormal.

[0140] It is understood that in this embodiment, the sample line detector is used to monitor the line. When the difference between the actual line loss and the standard line loss exceeds a threshold within a preset time period, the operating status label data of the monitored line is determined to be excessively damaged, thereby obtaining real sample data.

[0141] like Figure 5 The diagram shown is a schematic representation of obtaining an electrical safety monitoring model in one embodiment. (Refer to...) Figure 5 The server first obtains training sample data based on instances inside the building. After preprocessing, feature selection, and extraction of the training sample data, it trains an initial neural network model, enabling the model to learn the ability to predict the operating status based on real-time line data, thus obtaining an electrical safety monitoring model. When the server receives target line data reported by the target line monitor, it can preprocess, select, and extract the target line data in the same way, and then use the electrical safety monitoring model to obtain the corresponding operating status detection results.

[0142] In one embodiment, to enable the electrical safety monitoring model to provide solutions when an anomaly is detected, the server can also use real-world solutions to resolve the anomaly as supervisory information to train the model. That is, each training sample includes sample line data, operational status annotation data, and the corresponding solution when the operational status annotation data is abnormal. In this way, the trained electrical safety monitoring model can directly provide solutions when an anomaly is detected, achieving automated and intelligent monitoring of the electrical operating status within the building and dynamically adjusting the operation of electrical equipment when an anomaly occurs.

[0143] In some embodiments, the server can also extract new training sample data based on the target line data reported by the line monitor and the corresponding operational status detection results, and perform offline training on the electrical safety monitoring model. Specifically, the server can persist the target line data and operational status detection results; use the target line data and operational status detection results as training sample data; and use the training sample data and the three-dimensional spatial model to perform offline training on the electrical safety monitoring model. It is understandable that as the amount of training sample data increases, the accuracy of the electrical safety monitoring model becomes higher, providing more reasonable electrical safety monitoring information for personnel responsible for electrical safety management within the building.

[0144] In one embodiment, after the server obtains training sample data, the training steps of the electrical safety monitoring model include: acquiring training samples, which include a three-dimensional spatial model corresponding to the building, sample line data monitored by the sample line monitoring instrument in the building, and corresponding operating status annotation data; inputting the training samples into an initial neural network model; transforming the three-dimensional spatial model and sample line data using the current first connection weights between the input layer and hidden layer of the initial neural network model to obtain hidden layer features; transforming and fusing the hidden layer features using the current second connection weights between the hidden layer and output layer of the initial neural network model to obtain the predicted operating status; constructing an error function based on the operating status annotation data and the predicted operating status, minimizing the error function, and determining the updated first connection weights and updated second connection weights; updating the initial neural network model based on the updated first connection weights and updated second connection weights, and then returning to the step of acquiring training samples to continue training until the training termination condition is met, thus obtaining the electrical safety monitoring model.

[0145] The initial neural network model consists of an input layer, hidden layers, and an output layer. The connection between the input layer and the hidden layer can be fully connected, with the connection weights being the first connection weights. The connection between the hidden layer and the output layer can also be fully connected, with the connection weights being the second connection weights. During training, for each training sample, the predicted running state is obtained by calculating the current first and second connection weights of the model. This predicted running state is determined based on the current model parameters. Before training is complete, the difference between the predicted running state and the labeled running state is significant. However, as the training progresses and the model parameters are continuously adjusted, the difference between the predicted running state of the training samples and the labeled running state gradually decreases.

[0146] The error function is used to evaluate the difference between the predicted running state output by the model based on the current training samples and the labeled running state data. The adjustment direction of the model parameters, namely the first and second connection weights, can be determined based on the constructed difference function. The error function can be the mean squared error function or the cross-entropy loss function. For each training sample or each batch of training samples, the model parameters obtained when the loss is minimized are taken as the updated model parameters. Then, based on the updated model parameters, predictions are made on the next training sample to continue training the model parameters until the obtained model parameters make the model stable or the training iterations reach a preset number, at which point training ends.

[0147] In this embodiment, the model is trained using training samples, so that the obtained electrical safety monitoring model can be directly used to predict the operating status of electrical equipment with high accuracy and strong reference value.

[0148] like Figure 6 As shown, in one embodiment, step 206, using a trained neural network-based electrical safety monitoring model, obtains the operational status detection result of the target line where the target line monitoring instrument is located based on the three-dimensional spatial model and target line data, specifically including:

[0149] Step 602: Input the three-dimensional spatial model and target line data into the trained neural network-based electrical safety monitoring model.

[0150] Step 604: By using the first connection weight between the input layer and the hidden layer of the electrical safety monitoring model, the three-dimensional spatial model and the target line data are transformed to obtain the hidden layer features.

[0151] Step 606: By using the second connection weight between the hidden layer and the output layer of the electrical safety monitoring model, the features of each hidden layer are transformed and then fused to obtain the operating status detection result of the target line where the target line monitor is located.

[0152] The electrical safety monitoring model comprises an input layer, a hidden layer, and an output layer. The connection between the input layer and the hidden layer can be fully connected, as can the connection between the hidden layer and the output layer. The connection weight between the input layer and the hidden layer is the first connection weight, and the connection weight between the hidden layer and the output layer is the second connection weight. The 3D spatial model and target line data acquired by the input layer are multiplied by the first connection weight to obtain the corresponding hidden layer features. These hidden layer features are then multiplied by the second connection weight and fused to obtain the operational status detection result of the target line where the target line monitoring instrument is located.

[0153] In this embodiment, compared to monitoring electrical safety manually, the pre-trained electrical safety monitoring model predicts the operating status of transmission lines based on the line monitoring data reported by the line monitoring instrument and the three-dimensional spatial model inside the building. This not only achieves automated monitoring but also has a high accuracy rate.

[0154] like Figure 7 The diagram shown is a flowchart of an electrical safety monitoring method in one embodiment. (Refer to...) Figure 7The target line monitor reports the real-time data of the target line to the server. The server stores the target line data in real time. At the same time, using a trained electrical safety monitoring model, it predicts the operating status detection results of the target line where the monitor is located based on the three-dimensional spatial model and the reported target line data. When the operating status detection results indicate that the target line is in an abnormal operating state, it determines whether the abnormality can be resolved by dynamic adjustment. If not, it generates a control command to disconnect the target line. If yes, it further determines whether the staff has enabled the automatic adjustment function. If not, it generates a control command to disconnect the target line. If yes, it identifies multiple electrical devices related to the target line, determines the target electrical device according to the device priority, and generates a control command to shut down the target electrical device.

[0155] like Figure 8 The diagram shown is a flowchart of an electrical safety monitoring method in one embodiment. (Refer to...) Figure 8 The line monitoring device collects line data, encrypts it using a security encryption algorithm, and sends the encrypted line data to the server. The server uses this line data and a 3D spatial model of the building to make predictions and obtain the operating status detection results of the target line where the target line monitoring device is located. At the same time, the server stores this line data to generate training sample data for offline training of the electrical safety monitoring model. When the operating status detection results indicate that the target line is in an abnormal operating state, the server identifies the target electrical equipment related to the target line, generates control commands to shut down the target electrical equipment, and sends the encrypted control commands to the target electrical equipment.

[0156] In one specific embodiment, the electrical safety monitoring method includes the following steps:

[0157] 1. Receive sample line data reported by the sample line monitoring instrument.

[0158] 2. Obtain the rated electrical parameters of the electrical equipment in the building.

[0159] 3. Calculate the actual electrical parameters of the line where the sample line monitoring instrument is located based on the sample line data.

[0160] 4. When the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitor is located exceeds the threshold within a preset time period, the operating status label data of the line where the sample line monitor is located is determined to be abnormal.

[0161] 5. Obtain the building information model corresponding to the building.

[0162] 6. Map the deployment locations of electrical equipment within the building and the wiring connections between each piece of electrical equipment to the building information model to obtain a three-dimensional spatial model of the building; electrical equipment includes wiring monitors and electrical appliances.

[0163] 7. Using sample line data, corresponding operating status annotation data, and three-dimensional spatial model as training sample data, train the initial neural network model to obtain an electrical safety monitoring model.

[0164] 8. Receive target line data collected by the target line monitoring instrument.

[0165] 9. Input the three-dimensional spatial model and target line data into the electrical safety monitoring model.

[0166] 10. By using the first connection weight between the input layer and the hidden layer of the electrical safety monitoring model, the three-dimensional spatial model and the target line data are transformed to obtain the hidden layer features.

[0167] 11. By using the second connection weight between the hidden layer and the output layer of the electrical safety monitoring model, the features of each hidden layer are transformed and then fused to obtain the operating status detection results of the target line where the target line monitor is located.

[0168] 12. When the operation status detection result indicates that the target line is in an abnormal operation state, obtain the deployment location of the target line monitoring instrument in the three-dimensional space model.

[0169] 13. Identify multiple electrical devices related to the target line based on their deployment locations.

[0170] 14. Obtain the preset power priority level corresponding to the device type.

[0171] 15. Determine the power consumption priority level based on the equipment type of each of the multiple electrical devices; select the electrical device with the lowest power consumption priority level as the target electrical device.

[0172] 16. When the dynamic adjustment function of the building's power transmission lines has been activated, a control command is generated to shut down the target electrical equipment, and the control command is sent to the target electrical equipment to stop its operation.

[0173] 17. When the dynamic adjustment function of the building's power transmission lines is not activated, a control command to disconnect the target line is generated; or based on the operation status detection results, the abnormality type of the target electrical equipment is determined; and abnormality warning information is generated according to the abnormality type and the deployment location of the target electrical equipment.

[0174] The aforementioned electrical safety monitoring method, on the one hand, generates a three-dimensional spatial model of the building based on the deployment location of electrical equipment within the building and the complex wiring connections between these devices, which can assist in monitoring electrical safety within the building; on the other hand, it intelligently predicts the operating status of transmission lines through the electrical safety monitoring model, enabling real-time understanding of the electrical operating status and safety hazards of the entire building. Furthermore, when the predicted operating status detection results indicate that the transmission line is abnormal, it can determine the specific location of the abnormality and the target electrical equipment related to the abnormality. Under the premise of ensuring safety, it generates control commands to shut down the target electrical equipment, which can automatically adjust the operating status of the electrical equipment and reduce the losses caused by power outages in the entire area due to abnormalities.

[0175] The method provided in this application can intelligently control the safe operation of power transmission lines by binding the complex wiring and electrical equipment of high-rise buildings to a three-dimensional spatial model. It enables real-time monitoring of the electrical operating status and potential safety hazards of the entire building. When power transmission line anomalies occur, the method can automatically adjust equipment operation while ensuring safety, reducing losses caused by power outages in the entire area due to circuit abnormalities. It can also effectively prevent fires caused by malfunctions in concealed power transmission lines. Furthermore, the generated electrical safety monitoring model can provide long-term management recommendations for the wiring and electrical equipment within the entire building. With long-term monitoring, it can predict changes in the lifespan of lines over time, anticipating when power lines will need repair or replacement, providing timely warnings and reasonable, constructive suggestions to administrators.

[0176] This solution describes an intelligent electrical monitoring method based on a three-dimensional spatial model of a building. The three-dimensional spatial model represents the layout of the building's internal structure, electrical equipment, and power transmission lines. This method can be extended to intelligent monitoring of natural gas lines, intelligent monitoring of water supply pipelines, and so on within buildings.

[0177] It should be understood that, although Figure 2 , Figure 6 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 , Figure 6 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0178] In one embodiment, an electrical safety monitoring system is provided, which can, as Figure 1 As shown, the electrical safety monitoring system includes a target line monitor 102, a target electrical device 104, and a server 106, wherein:

[0179] Server 106 is used to obtain the three-dimensional spatial model of the building. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes wiring monitoring instruments and electrical appliances.

[0180] The target line monitor 102 is used to collect target line data of the target line where the target electrical equipment 104 is located, and to report the target line data to the server 106.

[0181] Server 106 is used to receive target line data collected by target line monitor 102; and obtain the operation status detection results of the target line where the target line monitor 102 is located based on the three-dimensional spatial model and the target line data through a trained neural network-based electrical safety monitoring model.

[0182] The server 106 is also used to determine the target electrical equipment 104 related to the target line and generate a control command to shut down the target electrical equipment 104 when the operation status detection result indicates that the target line is in an abnormal operation state.

[0183] The target electrical equipment 104 is used to stop operating after receiving a control command from the server 106. Specific limitations regarding the electrical safety monitoring system can be found in the limitations of the electrical safety monitoring method described above, and will not be repeated here.

[0184] In one embodiment, such as Figure 9 As shown, an electrical safety monitoring device 900 is provided. This device can be a software module, a hardware module, or a combination of both as part of a computer device. Specifically, the device includes: an acquisition module 902, a receiving module 904, a prediction module 906, and a control module 908, wherein:

[0185] The acquisition module 902 is used to acquire the three-dimensional spatial model of the building. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes wiring monitors and electrical appliances.

[0186] Receiver module 904 is used to receive target line data collected by the target line monitor;

[0187] The prediction module 906 is used to obtain the operating status detection results of the target line where the target line monitor is located by using a trained neural network-based electrical safety monitoring model, based on the three-dimensional spatial model and the target line data.

[0188] The control module 908 is used to determine the target electrical equipment related to the target line and generate a control command to shut down the target electrical equipment when the operation status detection result indicates that the target line is in an abnormal operation state. In one embodiment, the electrical safety monitoring model is a model obtained by training an initial neural network using multiple training samples. Each training sample includes sample line data monitored by a sample line monitoring instrument in the building and the corresponding operation status label data.

[0189] In one embodiment, the acquisition module 902 is further used to acquire the building information model corresponding to the building; map the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical equipment to the building information model to obtain the three-dimensional spatial model corresponding to the building.

[0190] In one embodiment, the device further includes a training sample data acquisition module, used to receive sample line data reported by the sample line monitor; acquire the rated electrical parameters corresponding to the electrical equipment in the building; calculate the actual electrical parameters of the line where the sample line monitor is located based on the sample line data; and determine that the operating status label data of the line where the sample line monitor is located is abnormal when the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitor is located exceeds a threshold within a preset time period.

[0191] In one embodiment, the training sample data acquisition module is further configured to, when the sample line monitor is located on the line of the monitored electrical equipment, include at least one of actual voltage, actual current, and actual temperature, calculate the actual operating power of the monitored electrical equipment based on the actual voltage and actual current; and determine that the operating status label data of the electrical equipment is abnormal when at least one of the following exceeds a threshold within a preset time period: the difference between the actual voltage and the rated voltage of the electrical equipment, the difference between the actual current and the rated current of the electrical equipment, the difference between the actual operating power and the rated power of the electrical equipment, or the difference between the actual temperature and the normal operating temperature.

[0192] In one embodiment, the training sample data acquisition module is further configured to, when the sample line monitor is used to monitor the line, include at least one of actual voltage, actual current and actual temperature, calculate the actual line loss of the monitored line based on the resistivity, actual current and actual voltage of the monitored line at the actual temperature; and determine that the operating status label data of the monitored line is abnormal when the difference between the actual line loss and the standard line loss exceeds a threshold within a preset time period.

[0193] In one embodiment, the above-mentioned device further includes a model training module for acquiring training samples, the training samples including sample line data monitored by the sample line monitoring instrument in the building and corresponding operating status annotation data; inputting the sample line data and the three-dimensional spatial model into an initial neural network model; transforming the three-dimensional spatial model and the sample line data using the current first connection weights between the input layer and the hidden layer of the initial neural network model to obtain hidden layer features; transforming and fusing each hidden layer feature using the current second connection weights between the hidden layer and the output layer of the initial neural network model to obtain a predicted operating status; constructing an error function based on the operating status annotation data and the predicted operating status; minimizing the error function to determine updated first connection weights and updated second connection weights; updating the initial neural network model based on the updated first connection weights and the updated second connection weights; and returning to the step of acquiring training samples to continue training until the training termination condition is met to obtain the electrical safety monitoring model.

[0194] In one embodiment, the prediction module 906 is further configured to input the three-dimensional spatial model and target line data into a trained neural network-based electrical safety monitoring model; transform the three-dimensional spatial model and target line data through the first connection weights between the input layer and the hidden layer of the electrical safety monitoring model to obtain hidden layer features; and transform and fuse the hidden layer features through the second connection weights between the hidden layer and the output layer of the electrical safety monitoring model to obtain the operating status detection result of the target line where the target line monitoring instrument is located.

[0195] In one embodiment, the prediction module 906 is further configured to determine the acquisition time when the target line data is collected; input the acquisition time, three-dimensional spatial model and target line data into a trained neural network-based electrical safety monitoring model, and output the operation status detection result of the target line where the target line monitor is located through the electrical safety monitoring model; the control module is further configured to determine the target electrical equipment related to the target line and generate peak-shifting operation information about the target electrical equipment when the operation status detection result indicates that the target line is in normal operation and the acquisition time is within the peak electricity consumption period.

[0196] In one embodiment, the control module 908 is further configured to obtain the deployment location of the target line monitor in a three-dimensional spatial model; and determine the target electrical equipment related to the target line based on the deployment location.

[0197] In one embodiment, the control module 908 is further configured to determine multiple electrical devices related to the target line based on the deployment location; obtain a preset power priority level corresponding to the device type; determine the power priority level based on the device type of each of the multiple electrical devices; and select the electrical device with the lowest power priority level among the multiple electrical devices as the target electrical device.

[0198] In one embodiment, the control module 908 is further configured to generate a control command to shut down the target electrical equipment when the dynamic adjustment function of the power transmission line of the building has been activated, and send the control command to the target electrical equipment to stop the operation of the target electrical equipment; generate a control command to disconnect the target line when the dynamic adjustment function of the power transmission line of the building has not been activated; or determine the abnormal type of the target electrical equipment based on the operation status detection result; and generate abnormal warning information according to the abnormal type and the deployment location of the target electrical equipment.

[0199] In one embodiment, the control module 908 is further configured to generate a control command to disconnect the target line when the operation status detection result indicates that the target line is in an abnormal operation state after the target electrical equipment associated with the target line stops operating.

[0200] In one embodiment, the device further includes a storage module for persistently storing target line data and operational status detection results; using the target line data and operational status detection results as training sample data; and using the training sample data and the three-dimensional spatial model to perform offline training on the electrical safety monitoring model.

[0201] The aforementioned electrical safety monitoring device 900, on the one hand, generates a three-dimensional spatial model of the building based on the deployment location of electrical equipment within the building and the complex wiring connections between various electrical equipment, which can assist in monitoring the electrical safety inside the building; on the other hand, it can intelligently predict the operating status of transmission lines through the electrical safety monitoring model, enabling real-time understanding of the electrical operating status and safety hazards of the entire building, and when the predicted operating status detection results indicate that the transmission line is abnormal, it can determine the specific location of the abnormality and the target electrical equipment related to the abnormality, and generate control commands to shut down the target electrical equipment while ensuring safety, which can automatically adjust the operating status of the electrical equipment and reduce the losses caused by power outages in the entire area due to abnormalities.

[0202] Specific limitations regarding the electrical safety monitoring device 900 can be found in the limitations of the electrical safety monitoring method described above, and will not be repeated here. Each module in the aforementioned electrical safety monitoring device 900 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in a computer device, or stored in software in the memory of a computer device, so that the processor can call and execute the operations corresponding to each module.

[0203] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements an electrical safety monitoring method.

[0204] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0205] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0206] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0207] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0208] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0209] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0210] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. An electrical safety monitoring method, comprising: A three-dimensional spatial model of the building is obtained. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes a wiring monitor and electrical appliances. Receive target line data collected by the target line monitoring instrument; The three-dimensional spatial model and the target line data are input into the trained neural network-based electrical safety monitoring model; By using the first connection weight between the input layer and the hidden layer of the electrical safety monitoring model, the three-dimensional spatial model and the target line data are transformed to obtain the hidden layer features; By using the second connection weight between the hidden layer and the output layer of the electrical safety monitoring model, the features of each hidden layer are transformed and then fused to obtain the operating status detection result of the target line where the target line monitor is located. When the operation status detection result indicates that the target line is in an abnormal operation state, the target electrical equipment related to the target line is identified, and a control command for shutting down the target electrical equipment is generated.

2. The method according to claim 1, characterized in that, The process of obtaining the three-dimensional spatial model corresponding to the building includes: Obtain the building information model corresponding to the building; The deployment locations of electrical equipment within the building and the wiring connections between the electrical equipment are mapped to the building information model to obtain a three-dimensional spatial model of the building.

3. The method according to claim 1, characterized in that, The method further includes: Receive sample line data reported by the sample line monitoring instrument; Obtain the rated electrical parameters of the electrical equipment within the building; Calculate the actual electrical parameters of the line where the sample line monitor is located based on the sample line data; When the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitoring instrument is located exceeds a threshold within a preset time period, the operating status label data of the line where the sample line monitoring instrument is located is determined to be abnormal.

4. The method according to claim 3, characterized in that, The step of calculating the actual electrical parameters of the line where the sample line monitoring instrument is located based on the sample line data includes: When the sample line monitor is located on the line of the monitored electrical equipment, the sample line data includes at least one of actual voltage, actual current and actual temperature, and the actual operating power of the monitored electrical equipment is calculated based on the actual voltage and the actual current. When the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitoring instrument is located exceeds a threshold within a preset time period, the operating status label data of the line where the sample line monitoring instrument is located is determined to be abnormal, including: If at least one of the following—the difference between the actual voltage and the rated voltage of the electrical equipment, the difference between the actual current and the rated current of the electrical equipment, the difference between the actual operating power and the rated power of the electrical equipment, and the difference between the actual temperature and the normal operating temperature—exceeds a threshold within a preset time period, then the operating status label data of the electrical equipment is determined to be abnormal.

5. The method according to claim 3, characterized in that, The step of calculating the actual electrical parameters of the line where the sample line monitoring instrument is located based on the sample line data includes: When the sample line monitor is used to monitor a line, the sample line data includes at least one of actual voltage, actual current and actual temperature, and the actual line loss of the monitored line is calculated based on the resistivity of the monitored line at the actual temperature, the actual current and the actual voltage. When the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitoring instrument is located exceeds a threshold within a preset time period, the operating status label data of the line where the sample line monitoring instrument is located is determined to be abnormal, including: When the difference between the actual line loss and the standard line loss exceeds a threshold within a preset time period, the monitored line operation status label data is determined to be abnormal.

6. The method according to claim 1, characterized in that, The training steps for the electrical safety monitoring model include: Acquire training samples, which include sample line data monitored by the sample line monitoring device in the building and corresponding operating status label data; The sample line data and the three-dimensional spatial model are input into the initial neural network model. The three-dimensional spatial model and the sample line data are transformed by the current first connection weight between the input layer and the hidden layer of the initial neural network model to obtain the hidden layer features. By transforming and fusing the features of each hidden layer through the current second connection weights between the hidden layer and the output layer of the initial neural network model, the predicted running state is obtained. An error function is constructed based on the labeled running status data and the predicted running status. The error function is minimized to determine the updated first connection weight and the updated second connection weight. After updating the initial neural network model according to the updated first connection weight and the updated second connection weight, the process returns to the step of obtaining training samples to continue training until the training termination condition is met, thus obtaining the electrical safety monitoring model.

7. The method according to claim 1, characterized in that, The method further includes: The acquisition time of the target line data is determined, and the input data of the trained neural network-based electrical safety monitoring model also includes the acquisition time; When the operation status detection result indicates that the target line is in normal operation and the collection time is within the peak power consumption period, the target electrical equipment related to the target line is identified, and peak-shaving operation information about the target electrical equipment is generated.

8. The method according to claim 1, characterized in that, The method further includes: When the dynamic adjustment function for the power transmission lines of the building has been activated, then The step of generating a control command for shutting down the target electrical equipment is executed, and the control command is sent to the target electrical equipment to stop the target electrical equipment from operating. When the dynamic adjustment function for the power transmission lines of the building is not activated, then Generate a control command to disconnect the target line; or Based on the operational status detection results, the abnormality type of the target electrical equipment is determined; Anomaly warning information is generated based on the anomaly type and the deployment location of the target electrical equipment.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: When the operational status detection result indicates that the target electrical equipment associated with the target line has stopped operating, the target line is in an abnormal operational state. Generate control commands to disconnect the target line.

10. An electrical safety monitoring system, comprising a target line monitor, a target electrical equipment, and a server, wherein: The server is used to obtain a three-dimensional spatial model of the building. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes a wiring monitor and electrical appliances. The target line monitor is used to collect target line data of the target line where the target electrical equipment is located, and to report the target line data to the server. The server is used to receive target line data collected by the target line monitor. The three-dimensional spatial model and the target line data are input into a trained neural network-based electrical safety monitoring model. The three-dimensional spatial model and the target line data are transformed by the first connection weight between the input layer and the hidden layer of the electrical safety monitoring model to obtain hidden layer features. The hidden layer features are then transformed and fused by the second connection weight between the hidden layer and the output layer of the electrical safety monitoring model to obtain the operating status detection result of the target line where the target line monitoring instrument is located. The server is also configured to, when the operating status detection result indicates that the target line is in an abnormal operating state, determine the target electrical equipment related to the target line and generate a control command for shutting down the target electrical equipment; The target electrical equipment is used to stop operating after receiving a control command from the server.

11. An electrical safety monitoring device, characterized in that, The device includes: The acquisition module is used to acquire a three-dimensional spatial model of the building. The three-dimensional spatial model is generated based on the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device. The electrical equipment includes a wiring monitor and electrical appliances. The receiving module is used to receive target line data collected by the target line monitor. The prediction module is used to input the three-dimensional spatial model and the target line data into a trained neural network-based electrical safety monitoring model, transform the three-dimensional spatial model and the target line data through the first connection weight between the input layer and the hidden layer of the electrical safety monitoring model to obtain hidden layer features, and then transform and fuse the hidden layer features through the second connection weight between the hidden layer and the output layer of the electrical safety monitoring model to obtain the operating status detection result of the target line where the target line monitoring instrument is located. The control module is used to determine the target electrical equipment related to the target line and generate a control command to shut down the target electrical equipment when the operation status detection result indicates that the target line is in an abnormal operation state.

12. The apparatus according to claim 11, characterized in that, The acquisition module is further configured to acquire the building information model corresponding to the building, map the deployment location of electrical equipment in the building and the wiring connection relationship between each electrical device to the building information model, and obtain the three-dimensional spatial model corresponding to the building.

13. The apparatus according to claim 11, characterized in that, The device further includes: The training sample data acquisition module is used to receive sample line data reported by the sample line monitoring instrument; acquire the rated electrical parameters corresponding to the electrical equipment in the building; calculate the actual electrical parameters of the line where the sample line monitoring instrument is located based on the sample line data; and determine that the operating status label data of the line where the sample line monitoring instrument is located is abnormal when the difference between the actual electrical parameters and the rated electrical parameters of the line where the sample line monitoring instrument is located exceeds a threshold within a preset time period.

14. The apparatus according to claim 13, characterized in that, The training sample data acquisition module is also used to calculate the actual operating power of the monitored electrical equipment based on the actual voltage and the actual current when the sample line monitor is located on the line of the monitored electrical equipment. If at least one of the following—the difference between the actual voltage and the rated voltage of the electrical equipment, the difference between the actual current and the rated current of the electrical equipment, the difference between the actual operating power and the rated power of the electrical equipment, and the difference between the actual temperature and the normal operating temperature—exceeds a threshold within a preset time period, then the operating status label data of the electrical equipment is determined to be abnormal.

15. The apparatus according to claim 13, characterized in that, The training sample data acquisition module is also used to calculate the actual line loss of the monitored line based on the resistivity of the monitored line at the actual temperature, the actual current and the actual temperature when the sample line monitor is used to monitor the line. When the difference between the actual line loss and the standard line loss exceeds a threshold within a preset time period, the monitored line operation status label data is determined to be abnormal.

16. The apparatus according to claim 11, characterized in that, The device further includes: The model training module is used to acquire training samples, which include sample line data and corresponding operating status annotation data monitored by the sample line monitoring instrument in the building. The sample line data and the three-dimensional spatial model are input into an initial neural network model. The three-dimensional spatial model and the sample line data are transformed using the current first connection weights between the input and hidden layers of the initial neural network model to obtain hidden layer features. The hidden layer features are then transformed and fused using the current second connection weights between the hidden and output layers of the initial neural network model to obtain a predicted operating status. An error function is constructed based on the operating status annotation data and the predicted operating status. The error function is minimized to determine updated first and second connection weights. The initial neural network model is updated based on the updated first and second connection weights, and the process returns to the step of acquiring training samples to continue training until the training termination condition is met, thus obtaining the electrical safety monitoring model.

17. The apparatus according to claim 11, characterized in that, The prediction module is also used to determine the acquisition time of the target line data, and the input data of the trained neural network-based electrical safety monitoring model also includes the acquisition time; When the operation status detection result indicates that the target line is in normal operation and the collection time is within the peak power consumption period, the target electrical equipment related to the target line is identified, and peak-shaving operation information about the target electrical equipment is generated.

18. The apparatus according to claim 11, characterized in that, The control module is further configured to, when the dynamic adjustment function for the power transmission lines of the building has been activated, execute the step of generating a control command to shut down the target electrical equipment and send the control command to the target electrical equipment to stop the target electrical equipment from operating; when the dynamic adjustment function for the power transmission lines of the building has not been activated, generate a control command to disconnect the target line; or determine the abnormal type of the target electrical equipment based on the operating status detection result. Anomaly warning information is generated based on the anomaly type and the deployment location of the target electrical equipment.

19. The apparatus according to any one of claims 11 to 18, characterized in that, The control module is further configured to generate a control command to disconnect the target line when the operation status detection result indicates that the target line is in an abnormal operation state after the target electrical equipment related to the target line stops operating.

20. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

21. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

22. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images