Electric power data management system and method based on artificial intelligence

Abstract

The invention discloses an electric power data management system and method based on artificial intelligence, and the system comprises a data preparation module which is used for preparing various source data in the aspect of electric power and storing the data in a database; the classification module is used for dividing various source data in the aspect of electric power into text data and image data; the first power failure prediction module is used for receiving the text data and performing power failure prediction; the second power failure prediction module is used for receiving the image data and performing power failure prediction; the first real-time monitoring module is used for receiving the text data and carrying out power anomaly identification through a first anomaly identification model; the second real-time monitoring module is used for receiving the image data and carrying out power anomaly identification through a second anomaly identification model; and the automatic adjusting module is used for automatically adjusting the corresponding equipment and generating a corresponding adjusting scheme. According to the invention, corresponding equipment is automatically adjusted and a corresponding adjustment scheme is generated, so that power supply can be supplemented in time.

Description

Technical Field

[0001] The present invention relates to an electric power data management system and method, and in particular to an electric power data management system and method based on artificial intelligence. Background Art

[0002] As an important infrastructure of modern society, the power system provides services for production and life, and its safe and stable operation is of vital importance. With the continuous expansion of the scale of the power grid and the continuous growth of electricity demand, the complexity and uncertainty of the power system are also increasing, which brings huge challenges to power operation and maintenance.

[0003] A Chinese patent with application publication number CN118917840A discloses an intelligent data optimization management platform based on power operation and maintenance, including: a relationship network construction module, used to obtain the installation information of all equipment and the historical operation records of all equipment, the operation records include operation data and status data, and the equipment relationship network is constructed according to the installation information and the historical operation data; a model construction and training module, used to train a state recognition model for identifying the equipment state according to the historical operation data of the equipment; a data acquisition and processing module, used to collect the real-time operation data of each equipment through a sensor, pre-process the collected operation data, and store the pre-processed operation data after adding a timestamp; a data analysis module, used to obtain the stored operation data according to the equipment relationship network at a preset frequency and analyze whether the operation data is abnormal; a state recognition module, used to obtain the corresponding operation data and input the operation data into the state recognition model to obtain the equipment state when the data analysis module analyzes that the operation data is abnormal; if there is a direct circuit connection or communication connection, it is used to monitor the real-time operation data obtained, and alarm when the operation data exceeding the preset threshold is monitored, and also used to monitor and output the equipment state recognized by the state recognition model.

[0004] The above patent has the following problems:

[0005] First, although the above patented technology can alarm for abnormal situations, it takes a certain amount of time from the alarm to the processing, and there is a certain lag. For example, if there is a fault in the generator or transformer station, it takes a certain amount of time to check and repair after the alarm, which will cause a certain amount of power loss, which may cause power outages for enterprises and daily life, and ultimately cause certain economic losses;

[0006] Second, the above patented technology only collects, analyzes, identifies, and monitors electricity, but does not effectively manage electricity, such as adjusting or dispatching electricity, or formulating electricity consumption plans;

[0007] Third, the above patented technology only collects the real-time operation data of each device through sensors. During the data collection process, the sensors will be affected by environmental factors, such as temperature, humidity, electromagnetic interference, etc., which may cause deviations in the data collected by the sensors. In addition, the accuracy and stability of the sensor itself will also affect the accuracy of data collection, thereby affecting the accuracy of subsequent analysis and recognition. Moreover, the collected data is single and all text data, which will also affect the accuracy and limitations of subsequent operations. Summary of the invention

[0008] In view of the above situation, in order to solve the technical problems of the prior art, the present invention provides an artificial intelligence-based power data management system and method.

[0009] The present invention solves the above technical problems through the following technical solutions: an artificial intelligence-based power data management system, characterized in that the artificial intelligence-based power data management system comprises:

[0010] A data preparation module prepares data from various sources related to electricity and stores them in a database;

[0011] A classification module that classifies the various sources of electricity data into text data and image data;

[0012] A first power fault prediction module, which receives text data and performs power fault prediction through a first power fault prediction model to obtain a first prediction result, and determines whether there will be a fault in the future according to the first prediction result. If there is a fault, an early warning is issued and a first fault elimination plan is generated;

[0013] A second power fault prediction module, which receives the image data and performs power fault prediction through a second power fault prediction model to obtain a second prediction result, and determines whether there will be a fault in the future according to the second prediction result. If there is a fault, an early warning is issued and a second fault elimination plan is generated;

[0014] A first real-time monitoring module, which receives text data and identifies power anomalies through a first anomaly recognition model, and if an anomaly is identified, an alarm is issued and a first anomaly elimination plan is generated;

[0015] A second real-time monitoring module, which receives the image data and identifies power anomalies through a second anomaly recognition model, and if an abnormality is identified, an alarm is issued and a second anomaly elimination plan is generated;

[0016] An automatic adjustment module, if the automatic adjustment module receives a warning from the first power fault prediction module or a warning from the second power fault prediction module or an alarm from the first real-time monitoring module or an alarm from the second real-time monitoring module, it automatically adjusts the corresponding equipment and generates a corresponding adjustment plan.

[0017] Preferably, the first power fault prediction model adopts a trained RF-TCN model, specifically using a random forest algorithm to filter out key features of text data and reduce the dimension of text data, and then using TCN for learning and prediction, first undergoing data dimensionality reduction processing before making predictions; the second power fault prediction model adopts a trained multi-scale convolutional neural network.

[0018] Preferably, the first abnormality recognition model uses the LSTM algorithm for recognition, by comparing the power operation data monitored in real time by the first real-time monitoring module with the pre-set threshold one by one to determine whether it is abnormal and extract abnormal information; the second abnormality recognition model uses the support vector machine model and the abnormality detection deep learning network model for recognition to obtain abnormal recognition information of the image.

[0019] Preferably, the artificial intelligence-based power data management system also includes a scenario construction module, which receives the warning of the first power fault prediction module, the warning of the second power fault prediction module, the alarm of the first real-time monitoring module, and the alarm of the second real-time monitoring module. The scenario construction module is used to construct models of the warning area and the alarm area to generate a scenario and generate a simulation scene graph. The types of scenes include three types: mobile terminal scene, computer terminal scene, and large-screen terminal scene.

[0020] Preferably, the data preparation module includes:

[0021] The data collection module collects data from various sources of electricity in real time. The data from various sources of electricity include sensor data, equipment data, user electricity data, historical operation data, monitoring images, and equipment failure logs. Sensor data, equipment data, user electricity data, historical operation data, and equipment failure logs belong to text data, and monitoring images belong to image data.

[0022] The filtering and repairing module performs noise filtering and missing value repair on the various sources of power data from the data acquisition module;

[0023] The normalization processing module normalizes the filtered and repaired text data and image data respectively.

[0024] Preferably, the formula for normalizing the text data is as follows:

[0025]

[0026] Among them, y0 represents the result of normalization of text data, y represents the original text data, u represents the average value of the original text data, and δ represents the standard deviation of the original text data.

[0027] Preferably, the formula for normalizing the image data is as follows:

[0028]

[0029] Among them, c0 represents the result of image pixel normalization processing, c represents the image pixel value, max represents the maximum value of the image pixel, and min represents the minimum value of the image pixel.

[0030] The present invention also provides an artificial intelligence-based power data management method, which comprises the following steps:

[0031] Prepare and store data from various sources on electricity in a database;

[0032] Divide the various sources of data on electricity into text data and image data;

[0033] Receiving text data through a first power fault prediction module and performing power fault prediction through a first power fault prediction model to obtain a first prediction result, determining whether there will be a fault in the future according to the first prediction result, and issuing an early warning and generating a first fault elimination plan if there is a fault;

[0034] Receiving image data through a second power fault prediction module and performing power fault prediction through a second power fault prediction model to obtain a second prediction result, determining whether there will be a fault in the future according to the second prediction result, and issuing an early warning and generating a second fault elimination plan if there is a fault;

[0035] Receiving text data through a first real-time monitoring module and identifying power anomalies through a first anomaly recognition model, and if an anomaly is identified, giving an alarm and generating a first anomaly elimination plan;

[0036] Receiving image data through a second real-time monitoring module and identifying power anomalies through a second anomaly recognition model, and if an abnormality is identified, giving an alarm and generating a second anomaly elimination plan;

[0037] If an automatic adjustment module receives a warning from the first power fault prediction module or a warning from the second power fault prediction module or an alarm from the first real-time monitoring module or an alarm from the second real-time monitoring module, it automatically adjusts the corresponding equipment and generates a corresponding adjustment plan.

[0038] The positive and progressive effects of the present invention are:

[0039] 1. When the present invention receives a warning from the first power fault prediction module or a warning from the second power fault prediction module or an alarm from the first real-time monitoring module or an alarm from the second real-time monitoring module through the automatic adjustment module, the corresponding equipment is automatically adjusted and a corresponding adjustment plan is generated to supplement power supply in time to ensure that power is efficiently and safely transmitted to the user end without power outages, thereby preventing economic losses.

[0040] Second, the present invention collects data from multiple sources in the field of electricity, including text data and image data, to prevent errors in single data and improve the accuracy of data collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 The figure is a principle block diagram of the power data management system based on artificial intelligence of the present invention.

[0042] Figure 2 This is a principle block diagram of the data preparation module in the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0044] Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0045] In the description of the present invention, it is necessary to understand that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0046] Embodiment 1

[0047] like Figure 1 As shown, the power data management system based on artificial intelligence of the present invention includes:

[0048] A data preparation module prepares data from various sources related to electricity and stores them in a database;

[0049] A classification module that classifies the various sources of electricity data into text data and image data;

[0050] A first power fault prediction module, which receives text data and performs power fault prediction through a first power fault prediction model to obtain a first prediction result, and determines whether there will be a fault in the future according to the first prediction result. If there is a fault, an early warning is issued and a first fault elimination plan is generated;

[0051] A second power fault prediction module, which receives the image data and performs power fault prediction through a second power fault prediction model to obtain a second prediction result, and determines whether there will be a fault in the future according to the second prediction result. If there is a fault, an early warning is issued and a second fault elimination plan is generated;

[0052] A first real-time monitoring module, which receives text data and identifies power anomalies through a first anomaly recognition model, and if an anomaly is identified, an alarm is issued and a first anomaly elimination plan is generated;

[0053] A second real-time monitoring module, which receives the image data and identifies power anomalies through a second anomaly recognition model, and if an abnormality is identified, an alarm is issued and a second anomaly elimination plan is generated;

[0054] An automatic adjustment module, if the automatic adjustment module receives a warning from the first power fault prediction module or a warning from the second power fault prediction module or an alarm from the first real-time monitoring module or an alarm from the second real-time monitoring module, it automatically adjusts the corresponding equipment and generates a corresponding adjustment plan.

[0055] For example, if the first power fault prediction module predicts that a generator set of a power station has a fault, the automatic adjustment module will give a specific solution and issue an early warning at the same time. Depending on the specific situation of the fault, whether to shut down the generator set that may have a fault for inspection, if it needs to be shut down for inspection and repair, the automatic adjustment module will immediately formulate a power plan and notify other power stations to increase power supply or dispatch other power generation energy sources (such as wind power generation, photovoltaic power generation, etc.). If the first real-time monitoring module detects that a generator set of a power station has an abnormality, the automatic adjustment module will immediately formulate a power plan, notify other power stations to increase power supply or dispatch other power generation energy sources (such as wind power generation, photovoltaic power generation, etc.), shut down and repair the abnormal generator set, and supplement the power supply in time to ensure that the power is efficiently and safely delivered to the user end, and there will be no power outages to prevent economic losses.

[0056] The first power fault prediction model adopts the trained RF-TCN model. Specifically, the random forest (RF) algorithm is used to screen out key features of text data and reduce the dimension of text data, and then TCN (Temporal Convolutional Network) is used for learning and prediction. The prediction efficiency can be improved by first performing data dimensionality reduction processing and then performing prediction. The second power fault prediction model adopts the trained multi-scale convolutional neural network (MS-CNN). Compared with similar algorithm models, it helps to identify large-scale objects, can more comprehensively cover the object scale range, and improve the comprehensiveness and accuracy of the prediction.

[0057] The core technology of TCN (Temporal Convolutional Network) is to use causal dilated convolution as the temporal convolution layer to extract the temporal features of the time series. In causal convolution, all data in the time dimension follow strict causal relationships. This design ensures the order of time series information. TCN is composed of stacked residual blocks, each of which is composed of two identical convolution units, and each convolution unit is composed of causal dilated convolution, weight normalization unit, ReLU unit, and Dropout unit. In order to solve the gradient vanishing problem of deep neural networks, residual connections are introduced in the residual blocks, and the residual connections are used to sum the input data and the output of the deep neural network as the input of the next stage.

[0058] The first abnormality recognition model uses the LSTM (Long Short-Term Memory) algorithm for recognition. It compares the power operation data monitored in real time by the first real-time monitoring module with the pre-set threshold one by one to determine whether it is abnormal and extract abnormal information, so that the automatic adjustment module can make corresponding automatic adjustments based on the abnormal information; the second abnormality recognition model uses the support vector machine model and the abnormality detection deep learning network model for recognition to obtain the abnormality recognition information of the image, thereby achieving fast and accurate recognition.

[0059] The artificial intelligence-based power data management system of the present invention also includes a scenario construction module, which receives the warning of the first power fault prediction module, the warning of the second power fault prediction module, the alarm of the first real-time monitoring module, and the alarm of the second real-time monitoring module. The scenario construction module is used to construct models of the warning area and the alarm area to generate a scene, that is, to generate a simulation scene graph. The types of scenes include three types: mobile terminal scenes, computer terminal scenes, and large-screen terminal scenes, which are convenient for different users to understand specific situations such as faults and abnormalities in real time, making the target location more accurate and able to make timely judgments and guide on-site operations.

[0060] Specifically, Figure 2 As shown, the data preparation module includes:

[0061] The data acquisition module collects data from various sources of electricity in real time. The data from various sources of electricity include sensor data, equipment data, user electricity usage data, historical operation data, monitoring images, and equipment failure logs. Sensor data, equipment data, user electricity usage data, historical operation data, and equipment failure logs are text data, and monitoring images are image data. The present invention adopts text data and image data to prevent errors in single data and improve the accuracy of data acquisition.

[0062] The filtering and repairing module performs noise filtering and missing value repair on the various sources of power data from the data acquisition module;

[0063] The normalization processing module normalizes the filtered and repaired text data and image data respectively, so that the data can converge faster during model optimization;

[0064] The formula for normalizing text data is as follows:

[0065]

[0066] Among them, y0 represents the result of normalization of text data, y represents the original text data, u represents the average value of the original text data, and δ represents the standard deviation of the original text data.

[0067] The formula for normalizing image data is as follows:

[0068]

[0069] Among them, c0 represents the result of image pixel normalization processing, c represents the image pixel value, max represents the maximum value of the image pixel, and min represents the minimum value of the image pixel.

[0070] Among them, the normalization processing module can adopt data processing methods such as SQL or python, and the data processing method can be saved as a pre-set method for the same type of data processing.

[0071] Embodiment 2

[0072] The present invention also provides an artificial intelligence-based power data management method, which comprises the following steps:

[0073] Prepare and store data from various sources on electricity in a database;

[0074] Divide the various sources of data on electricity into text data and image data;

[0075] Receiving text data through a first power fault prediction module and performing power fault prediction through a first power fault prediction model to obtain a first prediction result, determining whether there will be a fault in the future according to the first prediction result, and issuing an early warning and generating a first fault elimination plan if there is a fault;

[0076] Receiving image data through a second power fault prediction module and performing power fault prediction through a second power fault prediction model to obtain a second prediction result, determining whether there will be a fault in the future according to the second prediction result, and issuing an early warning and generating a second fault elimination plan if there is a fault;

[0077] Receiving text data through a first real-time monitoring module and identifying power anomalies through a first anomaly recognition model, and if an anomaly is identified, giving an alarm and generating a first anomaly elimination plan;

[0078] Receiving image data through a second real-time monitoring module and identifying power anomalies through a second anomaly recognition model, and if an abnormality is identified, giving an alarm and generating a second anomaly elimination plan;

[0079] If an automatic adjustment module receives a warning from the first power fault prediction module or a warning from the second power fault prediction module or an alarm from the first real-time monitoring module or an alarm from the second real-time monitoring module, it automatically adjusts the corresponding equipment and generates a corresponding adjustment plan.

[0080] In addition, an embodiment of the present invention provides an electronic device, which includes: a memory and a processor;

[0081] The memory is used to store computer programs;

[0082] The processor is used to implement the method in the above embodiment when executing the computer program.

[0083] In addition, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method in the above embodiment is implemented.

[0084] Based on the method in the above embodiment, an embodiment of the present invention provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0085] Based on the method in the above embodiment, the embodiment of the present invention further provides a chip, including one or more processors and an interface circuit. Optionally, the chip may also include a bus. Among them:

[0086] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, a digital communicator (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods and steps in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0087] The interface circuit can be used to send or receive data, instructions or information. The processor can use the data, instructions or other information received by the interface circuit to process it, and can send the processing completion information through the interface circuit.

[0088] Optionally, the chip further includes a memory, which may include a read-only memory and a random access memory, and provides operation instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory (NVRAM).

[0089] Optionally, the memory stores executable software modules or data structures, and the processor can perform corresponding operations by calling operation instructions stored in the memory (the operation instructions can be stored in the operating system).

[0090] Optionally, the interface circuit can be used to output the execution result of the processor.

[0091] It should be noted that the corresponding functions of the processor and the interface circuit can be implemented through hardware design, software design, or a combination of hardware and software, and there is no limitation here.

[0092] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or a software-based instruction in a processor.

[0093] It is understandable that the size of the sequence number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. In addition, in some possible implementations, each step in the above embodiment can be selectively executed according to actual conditions, and can be partially executed or fully executed, which is not limited here.

[0094] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0095] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0096] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state disk (SSD)), etc.

[0097] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An artificial intelligence-based power data management system, characterized in that: The artificial intelligence-based power data management system includes: A data preparation module prepares data from various sources related to electricity and stores them in a database; A classification module that classifies the various sources of electricity data into text data and image data; A first power fault prediction module, which receives text data and performs power fault prediction through a first power fault prediction model to obtain a first prediction result, and determines whether there will be a fault in the future according to the first prediction result. If there is a fault, an early warning is issued and a first fault elimination plan is generated; A second power fault prediction module, which receives the image data and performs power fault prediction through a second power fault prediction model to obtain a second prediction result, and determines whether there will be a fault in the future according to the second prediction result. If there is a fault, an early warning is issued and a second fault elimination plan is generated; A first real-time monitoring module, which receives text data and identifies power anomalies through a first anomaly recognition model, and if an anomaly is identified, an alarm is issued and a first anomaly elimination plan is generated; A second real-time monitoring module, which receives the image data and identifies power anomalies through a second anomaly recognition model, and if an abnormality is identified, an alarm is issued and a second anomaly elimination plan is generated; An automatic adjustment module, if the automatic adjustment module receives a warning from the first power fault prediction module or a warning from the second power fault prediction module or an alarm from the first real-time monitoring module or an alarm from the second real-time monitoring module, it automatically adjusts the corresponding equipment and generates a corresponding adjustment plan.

2. The power data management system based on artificial intelligence according to claim 1, characterized in that: The first power fault prediction model adopts the trained RF-TCN model, specifically, the random forest algorithm is used to filter out key features of text data and reduce the dimension of text data, and then TCN is used for learning and prediction, and the data is first subjected to dimensionality reduction processing before prediction; the second power fault prediction model adopts the trained multi-scale convolutional neural network.

3. The power data management system based on artificial intelligence according to claim 1, characterized in that: The first abnormality recognition model uses the LSTM algorithm to perform recognition, by comparing the power operation data monitored in real time by the first real-time monitoring module with the preset threshold value one by one to determine whether it is abnormal and extract abnormal information; The second anomaly recognition model uses a support vector machine model and an anomaly detection deep learning network model to perform recognition and obtain anomaly recognition information of the image.

4. The power data management system based on artificial intelligence according to claim 1, characterized in that: The artificial intelligence-based power data management system also includes a scenario construction module, which receives the warning of the first power fault prediction module, the warning of the second power fault prediction module, the alarm of the first real-time monitoring module, and the alarm of the second real-time monitoring module. The scenario construction module is used to construct models of the warning area and the alarm area to generate a scenario and generate a simulation scene graph. The types of scenes include three types: mobile terminal scene, computer terminal scene, and large-screen terminal scene.

5. The power data management system based on artificial intelligence according to claim 1, characterized in that: The data preparation module includes: The data collection module collects data from various sources of electricity in real time. The data from various sources of electricity include sensor data, equipment data, user electricity data, historical operation data, monitoring images, and equipment failure logs. Sensor data, equipment data, user electricity data, historical operation data, and equipment failure logs belong to text data, and monitoring images belong to image data. The filtering and repairing module performs noise filtering and missing value repair on the various sources of power data from the data acquisition module; The normalization processing module normalizes the filtered and repaired text data and image data respectively.

6. The power data management system based on artificial intelligence as claimed in claim 5, characterized in that: The formula for normalizing the text data is as follows: Among them, y0 represents the result of normalization of text data, y represents the original text data, u represents the average value of the original text data, and δ represents the standard deviation of the original text data.

7. The power data management system based on artificial intelligence as claimed in claim 5, characterized in that: The formula for normalizing the image data is as follows: Among them, c0 represents the result of image pixel normalization processing, c represents the image pixel value, max represents the maximum value of the image pixel, and min represents the minimum value of the image pixel.

8. An artificial intelligence-based power data management method, characterized in that: It includes the following steps: Prepare and store data from various sources on electricity in a database; Divide the various sources of data on electricity into text data and image data; Receiving text data through a first power fault prediction module and performing power fault prediction through a first power fault prediction model to obtain a first prediction result, determining whether there will be a fault in the future according to the first prediction result, and issuing an early warning and generating a first fault elimination plan if there is a fault; Receiving image data through a second power fault prediction module and performing power fault prediction through a second power fault prediction model to obtain a second prediction result, determining whether there will be a fault in the future according to the second prediction result, and issuing an early warning and generating a second fault elimination plan if there is a fault; Receiving text data through a first real-time monitoring module and identifying power anomalies through a first anomaly recognition model, and if an anomaly is identified, giving an alarm and generating a first anomaly elimination plan; Receiving image data through a second real-time monitoring module and identifying power anomalies through a second anomaly recognition model, and if an abnormality is identified, giving an alarm and generating a second anomaly elimination plan; If an automatic adjustment module receives a warning from the first power fault prediction module or a warning from the second power fault prediction module or an alarm from the first real-time monitoring module or an alarm from the second real-time monitoring module, it automatically adjusts the corresponding equipment and generates a corresponding adjustment plan.

Images