Electric power monitoring system based on artificial intelligence

Abstract

The invention discloses an electric power monitoring system based on artificial intelligence, relates to the technical field of electric power monitoring, and solves the technical problem of low fault detection efficiency of an existing electric power system. Comprising the following steps: collecting resident electricity consumption and real-time data of power equipment through a data collection module, and preprocessing to obtain power data; the monitoring prediction module judges whether the power equipment is abnormal or not according to the power data, if yes, an early warning signal is generated, a reason is analyzed, abnormal data is marked as a sequence, the sequence is input into the power monitoring model to obtain an abnormal label, and then the abnormal reason is matched; predicting future electricity consumption according to the historical electricity consumption; and the early warning feedback module sends an early warning signal and an abnormal reason to a manager so as to dispatch a technician to check and maintain, and the user interaction interface displays related information and provides functions of checking historical records and the like, so that accurate fault detection and intelligent prediction of power consumption can be realized, and the operation efficiency and safety of a power system are improved.

Description

Technical Field

[0001] The present invention belongs to the field of power system monitoring, and in particular is an artificial intelligence-based power monitoring system. Background Art

[0002] Artificial intelligence has many beneficial effects in power monitoring systems. It uses a variety of technical means to efficiently process large amounts of complex data in the power system. Through in-depth learning and analysis of these data, it can accurately distinguish different types of faults, and then adjust maintenance strategies, reasonably arrange resources and time, and ensure the reliable operation of power equipment.

[0003] The prior art (the invention patent application with the publication number CN118508381A) discloses a comprehensive relay protection and management system based on an intelligent algorithm, which includes a data exchange unit, a programmable logic controller (PLC), an intelligent data processing unit and a touch screen device. The data exchange unit is responsible for bidirectional data exchange with sensors and equipment of the power system to ensure the real-time collection of system data and the effective transmission of relay protection control signals. The PLC receives and processes these data and generates relay protection control signals according to the instructions of the intelligent data processing unit. The intelligent data processing unit preprocesses, analyzes and predicts the collected data, and provides the PLC with logic control instructions based on deep learning to optimize the relay protection action. Finally, the touch screen device displays the real-time operating status and fault analysis results of the power system, and provides a user interaction interface. However, the prior art does not judge whether the system data is abnormal, but directly inputs the collected system data into the neural network model after preprocessing, which reduces the operating efficiency of the model.

[0004] The present invention provides an artificial intelligence-based power monitoring system to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an artificial intelligence-based power monitoring system to solve the technical problem of low efficiency of fault detection in the existing power system.

[0006] To achieve the above object, the present invention provides an artificial intelligence-based power monitoring system, comprising:

[0007] Monitoring and prediction module, as well as the data collection module, early warning feedback module and user interaction interface connected to it;

[0008] Data collection module: collects residents' daily electricity consumption through electric meters and stores it in the database; collects real-time data of power equipment through data sensors, and pre-processes the real-time data to obtain power data; the power data includes: real-time voltage, real-time current, power factor, equipment temperature, and equipment operation time;

[0009] Monitoring and prediction module: determines whether the power equipment has abnormality based on the power data. If yes, it generates an early warning signal and analyzes the cause of the abnormality; if no, it continues to detect the power data; and

[0010] Obtain the user's historical electricity consumption, predict the user's electricity consumption based on the historical electricity consumption to obtain the predicted electricity consumption, and adjust the power generation of the power equipment based on the predicted electricity consumption;

[0011] Early warning feedback module: sends early warning signals and abnormal reasons to corresponding managers, who dispatch technicians to inspect and repair power equipment based on the abnormal reasons;

[0012] The user interaction interface is used to display real-time power data, predicted power consumption, abnormal fault information and early warning signals, and also allows users to view historical records.

[0013] Preferably, the preprocessing of the real-time data to obtain the power data includes:

[0014] Retrieve real-time data and determine whether the real-time data contains sub-data of all data types. If yes, keep the corresponding real-time data; if no, supplement the real-time data manually.

[0015] Determine whether the real-time data is repeated. If so, remove the corresponding repeated real-time data. If not, retain the corresponding real-time data.

[0016] The retained real-time data and the supplemented real-time data are marked as power data.

[0017] It should be noted that the sub-data of the real-time data are real-time voltage, real-time current, power factor, device temperature or device operating time, and the data type of the power data is consistent with the real-time data.

[0018] The present invention ensures the accuracy and integrity of power data by performing integrity judgment, supplementation and duplicate data elimination operations on real-time data.

[0019] Preferably, judging whether the power equipment is abnormal based on the power data includes:

[0020] Retrieve power data, obtain the standard range of power equipment, and compare the power data with the corresponding standard range;

[0021] It is determined whether the power data are all within the corresponding standard range. If yes, it is determined that there is no abnormality in the power equipment; if not, it is determined that there is an abnormality in the power equipment.

[0022] The present invention can clearly judge whether an abnormality occurs in the power equipment by comparing the power data with the standard range, thereby reducing the possibility of human judgment errors and improving judgment efficiency.

[0023] Preferably, the analysis of the cause of the abnormality includes:

[0024] Retrieve abnormal power data and mark the abnormal power data as an abnormal input sequence;

[0025] Retrieve the power monitoring model, input the abnormal input sequence into the power monitoring model, and obtain the abnormal label;

[0026] The corresponding abnormal cause is matched according to the abnormal label; wherein the abnormal label is set to a positive integer, and the power monitoring model is built based on the artificial intelligence model.

[0027] The present invention obtains abnormal labels through an electric power monitoring model constructed based on an artificial intelligence model, and then matches the corresponding abnormal causes. It uses artificial intelligence technology to process a large amount of electric power data, adapts to various types of abnormal situation analysis, and improves the accuracy and speed of abnormal cause analysis.

[0028] Preferably, the power monitoring model is constructed based on an artificial intelligence model, including:

[0029] Acquire a standard data set; wherein the standard data set includes standard input data consistent with the content attributes of the abnormal input sequence, and standard output data consistent with the content attributes of the abnormal input sequence;

[0030] The standard data set is divided into a training set and a validation set. The training set is used to train the artificial intelligence model, and the validation set is used to evaluate the performance of the artificial intelligence model. When the artificial intelligence model meets the standards, the artificial intelligence model is marked as an electric power monitoring model; wherein the artificial intelligence model includes a convolutional neural network model or a generative adversarial network model.

[0031] Preferably, the step of predicting the user's power consumption based on historical power consumption to obtain predicted power consumption includes:

[0032] Retrieve the historical electricity consumption for the same period as the forecast period, divide the historical electricity consumption according to the historical date, and calculate the working day average value GJZ of the historical electricity consumption on working days and the rest day average value XJZ of the historical electricity consumption on rest days;

[0033] Retrieve the working days GZ and rest days XR of the forecast period; calculate the forecast power consumption of the forecast period by the formula YDL=α×(GZ×GJZ+XR×XJZ); wherein α is the proportionality coefficient, and the value range is 1 to 1.5.

[0034] The present invention divides historical electricity consumption into working days and rest days according to historical dates and calculates the mean value separately, fully considering the differences in electricity consumption patterns under different date types, introducing the proportional coefficient α and combining the working day and rest day data of the prediction period for calculation, so that the prediction results can adapt to different electricity consumption scenarios and changing trends, providing a reference basis for power supply and management.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] (1) The present invention realizes the integrated operation of power data collection, abnormality analysis, power forecasting and user interaction, providing a strong guarantee for the stable operation of power equipment and the rational allocation of power resources.

[0037] (2) The present invention is comprehensive and accurate in data collection and can effectively pre-process data to ensure data quality; before inputting the power data into the artificial intelligence model, it is first judged, thereby improving the prediction efficiency of the subsequent model; in terms of power consumption prediction, the differences between different dates are considered to achieve reasonable predictions to guide the adjustment of power generation of power equipment; at the same time, the user interaction interface is used to allow users to understand the system operation status in real time and independently participate in configuration and view historical records, thereby ensuring the stable and efficient operation of the power system and bringing a good experience to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 is a flow chart of the present invention;

[0040] Figure 2 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] See also Figure 1-Figure 2 , an embodiment of the present invention provides an artificial intelligence-based power monitoring system, comprising:

[0043] Monitoring and prediction module, as well as the data collection module, early warning feedback module and user interaction interface connected to it;

[0044] Data collection module: collects residents' daily electricity consumption through electric meters and stores it in the database; collects real-time data of power equipment through data sensors, and pre-processes the real-time data to obtain power data; the power data includes: real-time voltage, real-time current, power factor, equipment temperature, and equipment operation time;

[0045] Preprocessing the real-time data to obtain power data includes: retrieving the real-time data, determining whether the real-time data contains sub-data of all data types, if yes, retaining the corresponding real-time data, if no, supplementing the real-time data manually;

[0046] Determine whether the real-time data is repeated. If so, remove the corresponding repeated real-time data. If not, retain the corresponding real-time data.

[0047] The retained real-time data and the supplemented real-time data are marked as power data.

[0048] Monitoring and prediction module: determines whether the power equipment has abnormality based on the power data. If yes, it generates an early warning signal and analyzes the cause of the abnormality; if no, it continues to detect the power data; and

[0049] Obtain the user's historical electricity consumption, predict the user's electricity consumption based on the historical electricity consumption to obtain the predicted electricity consumption, and adjust the power generation of the power equipment based on the predicted electricity consumption;

[0050] Analyze the causes of the abnormality, including:

[0051] Retrieve abnormal power data and mark the abnormal power data as an abnormal input sequence;

[0052] Retrieve the power monitoring model, input the abnormal input sequence into the power monitoring model, and obtain the abnormal label;

[0053] Match the corresponding abnormal cause according to the abnormal label; wherein the abnormal label is set to a positive integer, and the power monitoring model is built based on the artificial intelligence model;

[0054] Assume that the abnormal label is 3, and the corresponding abnormal reason is the equipment current overload. For example, when a large motor is running, the data acquisition module detects that the real-time current suddenly rises sharply, exceeding the normal working current range. The abnormal current data is marked as an abnormal input sequence and input into the power monitoring model, and the abnormal label is 3. After analysis, it is found that another device fails, causing the motor to bear additional load, thus causing current overload. The technicians found the faulty device through inspection and repaired it, solving the current overload problem.

[0055] Built on artificial intelligence models, including:

[0056] Acquire a standard data set; wherein the standard data set includes standard input data consistent with the content attributes of the abnormal input sequence, and standard output data consistent with the content attributes of the abnormal input sequence;

[0057] The standard data set is divided into a training set and a validation set. The training set is used to train the artificial intelligence model, and the validation set is used to evaluate the performance of the artificial intelligence model. When the artificial intelligence model meets the standards, the artificial intelligence model is marked as an electric power monitoring model; wherein the artificial intelligence model includes a convolutional neural network model or a generative adversarial network model.

[0058] The user's electricity consumption is predicted based on historical electricity consumption to obtain the predicted electricity consumption, including:

[0059] Retrieve the historical electricity consumption for the same period as the forecast period, divide the historical electricity consumption according to the historical date, and calculate the working day average value GJZ of the historical electricity consumption on working days and the rest day average value XJZ of the historical electricity consumption on rest days;

[0060] Retrieve the working days GZ and rest days XR of the forecast period; calculate the forecast power consumption of the forecast period by the formula YDL=α×(GZ×GJZ+XR×XJZ); wherein α is the proportionality coefficient, and the value range is 1 to 1.5.

[0061] Assume that the historical data of a user is as follows: In the past few months, the historical power consumption data of working days are: 6 degrees, 8 degrees, 10 degrees, 9 degrees, and 7 degrees, respectively. The average value of working days GJZ = (6 + 8 + 10 + 9 + 7) ÷ 5 = 8 degrees. The historical power consumption data of rest days are: 11 degrees, 10 degrees, and 13 degrees, respectively. The average value of rest days XJZ = (11 + 10 + 13) ÷ 3 = 11.33 degrees. The current situation in the forecast period is: there are 5 working days GZ and 2 rest days XR, and the proportional coefficient α is 1.2. If the forecast period is in the cold winter or hot summer, the power consumption will usually increase due to the increased frequency of use of high-power electrical appliances such as air conditioners and heating equipment. It may be appropriate to take 1.2 to appropriately increase the predicted power consumption to adapt to the seasonal power consumption growth. Then according to the formula YDL = α × (GZ × GJZ + XR × XJZ), we can get: YDL = 1.2 × (5 × 8 + 2 × 11.33) = 1.2 × (40 + 22.66) = 1.2 × 62.66 ≈ 75.2 kWh. Therefore, the predicted power consumption during the forecast period is about 75.2 kWh.

[0062] Early warning feedback module: sends early warning signals and abnormal reasons to corresponding managers, who dispatch technicians to inspect and repair power equipment based on the abnormal reasons;

[0063] The user interaction interface is used to display real-time power data, predicted power consumption, abnormal fault information and early warning signals, and also provides a way to view historical records.

[0064] Working principle of the present invention: The present invention collects the real-time data of residents' electricity consumption and power equipment through the electric meter and data sensor of the data acquisition module, and stores them in the database after preprocessing them into power data. The monitoring and prediction module determines whether the power equipment is abnormal based on the power data. If it is abnormal, an early warning signal is generated and the cause is analyzed. The reason for the analysis is that the abnormal data is marked as a sequence input into the power monitoring model built based on the artificial intelligence model to obtain the abnormal label and then match the abnormal cause. The mean is calculated according to the historical electricity consumption and the electricity consumption is predicted in combination with the formula. The early warning feedback module sends the early warning signal and the abnormal cause to the management personnel so as to dispatch technicians to inspect and repair. The user interaction interface displays relevant information and provides users with functions such as configuring parameters and viewing historical records.

[0065] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An artificial intelligence-based power monitoring system, characterized in that: include: Monitoring and prediction module, as well as the data collection module, early warning feedback module and user interaction interface connected to it; Data collection module: collects residents’ daily electricity consumption through electricity meters and stores it in the database; The real-time data of the power equipment is collected through data sensors, and the real-time data is pre-processed to obtain power data; wherein the power data includes: real-time voltage, real-time current, power factor, equipment temperature and equipment operation time; Monitoring and prediction module: determines whether the power equipment has abnormality based on the power data. If yes, it generates an early warning signal and analyzes the cause of the abnormality; if no, it continues to detect the power data; and Obtain the user's historical electricity consumption, predict the user's electricity consumption based on the historical electricity consumption to obtain the predicted electricity consumption, and adjust the power generation of the power equipment based on the predicted electricity consumption; Early warning feedback module: sends early warning signals and abnormal reasons to corresponding managers, who dispatch technicians to inspect and repair power equipment based on the abnormal reasons; The user interaction interface is used to display real-time power data, predicted power consumption, abnormal fault information and early warning signals, and also allows users to view historical records.

2. The power monitoring system based on artificial intelligence according to claim 1, characterized in that: The preprocessing of the real-time data to obtain the power data includes: Retrieve real-time data and determine whether the real-time data contains sub-data of all data types. If yes, keep the corresponding real-time data; if no, supplement the real-time data manually. Determine whether the real-time data is repeated. If so, remove the corresponding repeated real-time data. If not, retain the corresponding real-time data. The retained real-time data and the supplemented real-time data are marked as power data.

3. The power monitoring system based on artificial intelligence according to claim 1 is characterized in that: The determining whether the power equipment is abnormal according to the power data includes: Retrieve power data, obtain the standard range of power equipment, and compare the power data with the corresponding standard range; It is determined whether the power data are all within the corresponding standard range. If yes, it is determined that there is no abnormality in the power equipment; if not, it is determined that there is an abnormality in the power equipment.

4. The power monitoring system based on artificial intelligence according to claim 3 is characterized in that: The analysis of the abnormal cause includes: Retrieve abnormal power data and mark the abnormal power data as an abnormal input sequence; Retrieve the power monitoring model, input the abnormal input sequence into the power monitoring model, and obtain the abnormal label; The corresponding abnormal cause is matched according to the abnormal label; wherein the abnormal label is set to a positive integer, and the power monitoring model is built based on the artificial intelligence model.

5. The power monitoring system based on artificial intelligence according to claim 1 is characterized in that: The power monitoring model is constructed based on an artificial intelligence model and includes: Acquire a standard data set; wherein the standard data set includes standard input data consistent with the content attributes of the abnormal input sequence, and standard output data consistent with the content attributes of the abnormal input sequence; The standard data set is divided into a training set and a validation set. The training set is used to train the artificial intelligence model, and the validation set is used to evaluate the performance of the artificial intelligence model. When the artificial intelligence model meets the standards, the artificial intelligence model is marked as an electric power monitoring model; wherein the artificial intelligence model includes a convolutional neural network model or a generative adversarial network model.

6. The power monitoring system based on artificial intelligence according to claim 1 is characterized in that: The step of predicting the user's power consumption according to the historical power consumption to obtain the predicted power consumption includes: Retrieve the historical electricity consumption for the same period as the forecast period, divide the historical electricity consumption according to the historical date, and calculate the working day average value GJZ of the historical electricity consumption on working days and the rest day average value XJZ of the historical electricity consumption on rest days; Retrieve the working days GZ and rest days XR of the forecast period; calculate the forecast power consumption of the forecast period by the formula YDL=α×(GZ×GJZ+XR×XJZ); wherein α is the proportionality coefficient, and the value range is 1 to 1.5.

Images