Specialty variable electric energy management and early warning method and system based on multi-sensor fusion

Abstract

The application discloses a method and system for special transformer power management and early warning based on multi-sensor fusion, which includes real-time collection of power data of the transformer, data fusion and error correction, continuous monitoring of power usage, identification of abnormalities and reporting, prediction of faults through data analysis, optimization of power management, visualization and real-time monitoring of data through local and remote communication, and regular generation of power and equipment operation reports. The application improves the accuracy and timeliness of data collection, combines big data analysis and machine learning algorithms to achieve early prediction of faults and optimization of power management, and avoids the lag and inaccuracy of traditional methods. The system has automatic early warning, remote monitoring and real-time data visualization functions, significantly improving the operation efficiency and safety of the power system.

Description

Technical Field

[0001] This invention relates to the field of power system management and monitoring technology, specifically to a method and system for dedicated transformer power management and early warning based on multi-sensor fusion. Background Technology

[0002] With the continuous development and digital transformation of power systems, transformers, as key power equipment in the power grid, require real-time monitoring and management of their operating status and power consumption. Traditional transformer monitoring methods mainly rely on single-sensor monitoring or periodic manual inspections. This approach not only provides limited monitoring information and makes it difficult to comprehensively acquire transformer operating status data, but also suffers from insufficient timeliness and inaccurate data. In recent years, with the advancement of the Internet of Things, big data analytics, and intelligent sensing technologies, multi-sensor fusion technology has been gradually applied to power systems. By integrating multiple sensors (such as voltage, current, and power sensors), more comprehensive, real-time, and accurate equipment status monitoring has been achieved. The combination of these technologies greatly improves the automation level of power equipment management and enables multi-dimensional analysis of power equipment operation through advanced algorithms for data fusion processing.

[0003] However, existing multi-sensor monitoring technologies still have some shortcomings. First, although multi-sensor systems can achieve real-time data acquisition, the data fusion algorithms often suffer from high complexity and low computational efficiency, especially in data error correction and anomaly detection, where efficient real-time processing cannot be guaranteed, easily leading to lag in monitoring information. Second, the anomaly detection and early warning capabilities of power equipment are limited. Existing systems can usually only detect specific types of faults and are unable to effectively identify complex power consumption anomalies, such as illegal power consumption or abnormal load fluctuations. In addition, most current fault prediction systems are based on preset fixed thresholds, lacking flexible intelligent processing and unable to adaptively adjust according to dynamic changes in equipment operating status, resulting in delayed early warning information or frequent false alarms. These shortcomings limit the application of existing technologies in complex power grid environments, especially under high load operation or load imbalance conditions, where traditional power management and fault early warning methods are difficult to achieve refined management. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that in existing power systems, although multi-sensor technology is used for monitoring, the complexity and low computational efficiency of data fusion algorithms result in insufficient real-time data processing, making it impossible to quickly respond to changes in equipment status. In existing technologies, data collected by multiple sensors is often affected by factors such as environmental noise and equipment failures. Error correction algorithms cannot effectively eliminate these errors, leading to inaccurate monitoring data and affecting the judgment of equipment operating status. Most existing power management systems can only detect specific fault types, such as overload or short circuit, lacking the ability to identify complex power usage anomalies (such as illegal electricity use, load imbalance, etc.), and thus cannot comprehensively monitor the operating status of transformers. Traditional fault prediction technologies typically rely on fixed threshold settings, lacking the ability to dynamically adjust based on equipment operating status, resulting in delayed fault prediction, and even false alarms or missed alarms, reducing the system's early warning effectiveness.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for special transformer power management and early warning based on multi-sensor fusion, comprising: real-time acquisition of transformer power data, data fusion and error correction;

[0007] Continuously monitor power usage, identify anomalies, and report them.

[0008] Predict faults and optimize power management through data analysis;

[0009] Data visualization and real-time monitoring are achieved through local and remote communication;

[0010] Regularly generate reports on power consumption and equipment operation.

[0011] As a preferred embodiment of the multi-sensor fusion-based power management and early warning method for dedicated transformers described in this invention, the real-time acquisition of transformer power data includes real-time acquisition of phase voltage, phase current, phase and total active power, phase and total reactive power, phase and total apparent power, phase and total power factor, and grid frequency of the dedicated transformer equipment through current, voltage, and power sensors.

[0012] As a preferred embodiment of the multi-sensor fusion-based power management and early warning method for dedicated transformers described in this invention, the data fusion and error correction include: correcting errors in the collected data; performing longitudinal and horizontal multi-dimensional analysis on the real-time power data of the transformer; comparing data collected by the same sensor at different time points in the longitudinal analysis; and comprehensively comparing data collected by different sensors at the same time point in the horizontal analysis. By combining historical data and real-time data, error correction is performed on the collected power data to ensure the accuracy and consistency of the data.

[0013] As a preferred embodiment of the multi-sensor fusion-based special transformer power management and early warning method described in this invention, the method of identifying and reporting anomalies includes continuously measuring current, voltage, and power data, calculating positive and negative active power, positive and negative reactive power, and four-quadrant reactive power data, monitoring the user's power usage in real time, and wirelessly uploading the relevant data to a remote server via a 4G / 5G network to achieve effective real-time monitoring of power.

[0014] The system uses intelligent drop-out fuses to collect operational data in real time and store electrical energy data periodically. If abnormal situations occur during transformer shutdown or capacity reduction, the program will automatically enter an alarm state, automatically identify whether the user has violated electricity usage regulations, and proactively report the abnormal status.

[0015] As a preferred embodiment of the multi-sensor fusion-based power management and early warning method for dedicated transformers described in this invention, the optimized power management includes: conducting big data analysis on historical power data and real-time operating data collected by multiple sensors to establish a mathematical model of equipment operating status, monitoring the voltage, current, and power change trends of the equipment, and identifying potential fault symptoms; when abnormal fluctuations and abnormal operating modes are detected, combining machine learning algorithms to predict the equipment operating status and generate fault early warning information;

[0016] The power allocation strategy is dynamically adjusted based on the forecast results to optimize load management and ensure that power resources are scheduled before a fault occurs.

[0017] As a preferred embodiment of the multi-sensor fusion-based power management and early warning method for dedicated transformers described in this invention, the following steps are included: Visualizing and monitoring the data in real time, which involves uploading the transformer's power data and operating status to a remote server or cloud platform and synchronizing it to a mobile terminal; the system provides a graphical user interface, which uses data visualization technology to present the real-time monitored current, voltage, and power data in the form of charts and curves.

[0018] The data visualization platform supports real-time monitoring of equipment status, querying and analysis of historical data. Users can view the current status and early warning information of the equipment at any time through remote terminals or mobile applications, and receive equipment operation reports and power consumption analysis reports generated by the system.

[0019] As a preferred embodiment of the multi-sensor fusion-based power management and early warning method for dedicated transformer power as described in this invention, the periodic generation of power and equipment operation reports includes: based on real-time monitored current, voltage, and power data, combined with historical data, and through big data analysis and prediction models, periodically generating equipment operation status reports and power consumption analysis reports; the report content includes equipment working efficiency, fault early warning information, power consumption pattern analysis, energy consumption statistics, and abnormal power consumption;

[0020] The system automatically pushes reports to the maintenance personnel's management platform, helping managers make decisions based on equipment operation and energy consumption.

[0021] A dedicated power substation energy management and early warning system based on multi-sensor fusion, characterized in that it includes:

[0022] Data acquisition and fusion module: Real-time acquisition of transformer power data, data fusion and error correction;

[0023] Anomaly detection module: continuously monitors power usage, identifies anomalies, and reports them;

[0024] Intelligent fault prediction module: Predicts faults through data analysis to optimize power management;

[0025] Data communication and visualization module: Enables data visualization and real-time monitoring through local and remote communication;

[0026] Report generation module: Regularly generates reports on power and equipment operation.

[0027] The beneficial effects of this invention are as follows: This invention can process multiple data sources such as current, voltage, and power more efficiently and perform precise error correction, ensuring the accuracy of monitoring data and helping to promptly grasp the operating status of transformers. Through big data analysis and intelligent algorithms, it can identify complex abnormal power usage situations, such as illegal power use and load imbalance, and can quickly respond to and report abnormal states, ensuring the comprehensiveness and safety of power management. Through machine learning and big data analysis models, this invention can dynamically adjust fault prediction strategies, providing early warnings of potential faults based on changes in equipment operating status, reducing the risk of fault occurrence and improving system stability. Combining predictive analysis and load management, it can optimize power allocation and resource scheduling strategies based on actual power usage, improving the efficiency of power management and reducing unnecessary energy consumption. Through local and remote communication technologies, this invention can transmit power usage data to a monitoring platform or mobile terminal in real time and present it in a visual form, providing maintenance personnel with a more intuitive and convenient management tool, effectively improving the efficiency of equipment maintenance and management. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0029] Figure 1The flowchart shows the method for special substation power management and early warning based on multi-sensor fusion provided in the first embodiment of the present invention. Detailed Implementation

[0030] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0031] Example 1, referring to Figure 1 As one embodiment of the present invention, a method for dedicated power transformer energy management and early warning based on multi-sensor fusion is provided, including:

[0032] S1: Real-time acquisition of transformer power data, data fusion and error correction.

[0033] The system uses current, voltage, and power sensors to collect real-time data on the phase voltage, phase current, phase and total active power, phase and total reactive power, phase and total apparent power, phase and total power factor, and grid frequency of the dedicated transformer equipment.

[0034] The collected data undergoes error correction, and the real-time power data of the transformer is analyzed in multiple dimensions, both longitudinally and laterally. The longitudinal analysis compares data collected by the same sensor at different time points, while the lateral analysis comprehensively compares data collected by different sensors at the same time point. By combining historical and real-time data, the collected power data is corrected for errors to ensure the accuracy and consistency of the data.

[0035] It should be noted that in the data fusion section, this invention proposes a "vertical and horizontal multi-dimensional analysis" method, which is a key innovation in solving the problems of isolated data and one-sided analysis in traditional monitoring systems. Vertical analysis involves comparing data from the same sensor at different points in time, aiming to capture dynamic changes in equipment operating status. This method has significant technical advantages: by analyzing long-term series data, it can accurately identify gradual faults in equipment operation (such as gradually increasing load or voltage fluctuations), thereby preventing the accumulation of potential problems. Furthermore, horizontal analysis involves comprehensively comparing data from different sensors at the same point in time, compensating for the inability of a single sensor to fully describe the equipment status. This multi-sensor horizontal comparison method is particularly suitable for monitoring complex states in power systems. For example, if changes in the power factor are not synchronized with fluctuations in current and voltage, it may indicate power loss or equipment abnormalities; these potential problems can be detected promptly through horizontal data analysis.

[0036] Error correction is a crucial step in ensuring data accuracy. This invention combines historical and real-time data for correction, ensuring that data errors in the monitoring system are minimized. This error correction strategy has significant advantages over traditional methods: by combining historical data, it can effectively identify and eliminate the impact of occasional or short-term noise. For example, short-term current fluctuations may be caused by external interference or temporary load changes. By comparing with historical data, the system can identify such anomalies and correct them, avoiding false alarms or misjudgments. Furthermore, longitudinal analysis combined with historical data can more accurately identify trend changes, while lateral analysis, by simultaneously comparing data from different sensors, further improves the accuracy of error correction.

[0037] S2: Continuously monitor power usage, identify anomalies, and report them.

[0038] It continuously measures current, voltage, and power data, and calculates positive and negative active energy, positive and negative reactive energy, and four-quadrant reactive energy data to monitor users' power consumption in real time. It also wirelessly uploads the relevant data to a remote server via 4G / 5G network to achieve effective real-time monitoring of power consumption.

[0039] The system uses intelligent drop-out fuses to collect operational data in real time and store electrical energy data periodically. If abnormal situations occur during transformer shutdown or capacity reduction, the program will automatically enter an alarm state, automatically identify whether the user has violated electricity usage regulations, and proactively report the abnormal status.

[0040] It should be noted that the use of 4G / 5G networks to wirelessly upload relevant data to a remote server makes the transmission of monitoring data more efficient and timely. This not only improves the real-time performance of data transmission but also enhances the system's flexibility, enabling maintenance personnel to remotely monitor power usage in real time. Traditional monitoring systems typically require manual inspections or a fixed network environment, while this invention, through the application of mobile communication technology, greatly improves the convenience and efficiency of data uploading.

[0041] In terms of anomaly monitoring and identification, this invention uses an "intelligent drop-out fuse" as the core device to collect operational data in real time and store electrical energy data periodically. The beneficial effect of this method is that the intelligent drop-out fuse not only possesses the protection functions of a traditional fuse, but also automatically enters an "alert state" when encountering abnormal situations such as transformer shutdowns or capacity reductions. At this time, the system intelligently identifies whether the user has engaged in illegal electricity use based on a comparison of historical and real-time data. The rationale for this automatic identification mechanism lies in the fact that traditional monitoring systems often require manual intervention, resulting in insufficient timeliness in responding to violations. This invention, through automated monitoring and intelligent analysis, improves the speed and accuracy of response to illegal electricity use.

[0042] S3: Predict faults through data analysis and optimize power management.

[0043] By conducting big data analysis on historical power data and real-time operation data collected by multiple sensors, a mathematical model of equipment operation status is established to monitor the voltage, current and power change trends of the equipment and identify potential fault signs. When abnormal fluctuations and abnormal operation modes are detected, machine learning algorithms are used to predict the equipment operation status and generate fault warning information.

[0044] The power allocation strategy is dynamically adjusted based on the forecast results to optimize load management and ensure that power resources are scheduled before a fault occurs.

[0045] It should be noted that by monitoring the "voltage, current, and power change trends" of the equipment, the system can promptly identify potential fault signs. The rationale behind this process lies in the fact that, through the establishment of mathematical models, the operating status of the equipment can be quantified, and abnormal fluctuations and patterns can be identified through comparative analysis. When abnormal operating patterns occur, such as voltage fluctuations inconsistent with load changes, the system can react quickly. This invention combines "machine learning algorithms" for equipment status prediction, further enhancing the intelligence level of fault detection. The beneficial effect of this method is that machine learning algorithms can identify complex patterns and relationships in massive amounts of data, enabling the system to learn the dynamic changes of the equipment under normal and abnormal states, rather than relying on fixed rules for fault prediction. This dynamic learning capability allows the system to gradually improve the accuracy of predictions over time and generate "fault warning information" in a timely manner when abnormal fluctuations are detected, providing strong decision support for maintenance personnel.

[0046] Finally, based on the fault prediction results, the system can "dynamically adjust the power distribution strategy" to optimize load management. The rationale behind this strategy lies in the fact that, through real-time fault prediction, the system can effectively avoid wasting power resources and overloading equipment, ensuring reasonable resource scheduling before a fault occurs. For example, when an impending overload is detected in a transformer, the system can automatically adjust power distribution to reduce the load on that equipment, thereby mitigating the risk of failure. Compared to traditional passive response methods, this proactive management strategy significantly improves the stability and security of the power system.

[0047] S4: Enables data visualization and real-time monitoring through local and remote communication.

[0048] The system uploads the transformer's power data and operating status to a remote server or cloud platform and synchronizes it to mobile terminals. It provides a graphical user interface and uses data visualization technology to present the real-time monitored current, voltage, and power data in the form of charts and curves.

[0049] The data visualization platform supports real-time monitoring of equipment status, querying and analysis of historical data. Users can view the current status and early warning information of the equipment at any time through remote terminals or mobile applications, and receive equipment operation reports and power consumption analysis reports generated by the system.

[0050] It should be noted that by using data visualization technology to present real-time monitoring data such as current, voltage, and power in the form of charts and curves, not only is the readability of the data improved, but users can also quickly grasp the operating status of the equipment. The rationale behind this design is that data visualization can transform complex data into intuitive graphics, helping users quickly understand the operating trends and status changes of the equipment. This is especially important in scenarios where rapid decision-making is required.

[0051] The visualization platform supports real-time monitoring of equipment status and querying and analysis of historical data, providing comprehensive management functions. This ensures that maintenance personnel can view the current status of equipment and early warning information at any time via remote terminals or mobile applications. This ability to instantly acquire and query data is crucial for improving equipment management efficiency. For example, when a device experiences abnormal fluctuations, maintenance personnel can immediately obtain real-time data through the platform, quickly analyze the problem, and take corresponding measures to reduce the impact of the fault on the overall power system. Users can also receive system-generated equipment operation reports and energy consumption analysis reports, providing data support for long-term management. These reports not only help users understand the historical operating conditions and power consumption patterns of the equipment but also provide a basis for developing future maintenance plans and energy efficiency optimization strategies. Through the analysis of historical data, users can identify long-term potential problems and trends, providing a reference for system improvement and equipment maintenance.

[0052] S5: Regularly generate reports on power and equipment operation.

[0053] Based on real-time monitored current, voltage, and power data, combined with historical data, the system regularly generates equipment operation status reports and power consumption analysis reports through big data analysis and prediction models. The reports include equipment operating efficiency, fault warning information, power consumption pattern analysis, energy consumption statistics, and abnormal power consumption.

[0054] The system automatically pushes reports to the maintenance personnel's management platform, helping managers make decisions based on equipment operation and energy consumption.

[0055] It should be noted that, in terms of report generation, this invention employs a "big data analysis and prediction model" to periodically generate "equipment operation status reports and power consumption analysis reports." The beneficial effect of this process is that big data analysis can process massive amounts of information, extracting deep insights into the equipment's operating status and helping to identify potential failure trends. For example, by analyzing current fluctuations and voltage changes, the system can provide early warnings of possible equipment failures, preventing sudden equipment shutdowns. Simultaneously, combined with the prediction model, future energy consumption trends can be assessed, providing a scientific basis for decision-making.

[0056] Example 2 is the second embodiment of the present invention, which differs from the previous embodiment in that:

[0057] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art or the current technical solution, can be embodied in the form of a software product. This current computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0058] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, system, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, system, or device). For the purposes of this specification, "computer-readable medium" can mean any system that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, system, or device.

[0059] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic systems) with one or more wires, portable computer disk drives (magnetic systems), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic systems, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0060] Example 3, an embodiment of the present invention, provides a dedicated power management and early warning system based on multi-sensor fusion, characterized in that it includes a data acquisition and fusion module, an anomaly detection module, an intelligent fault prediction module, and a report generation module.

[0061] Data acquisition and fusion module: Real-time acquisition of transformer power data, data fusion and error correction.

[0062] Anomaly detection module: continuously monitors power usage, identifies anomalies, and reports them.

[0063] Intelligent fault prediction module: Predicts faults through data analysis and optimizes power management.

[0064] Data communication and visualization module: Enables data visualization and real-time monitoring through local and remote communication.

[0065] Report generation module: Regularly generates reports on power and equipment operation.

[0066] Example 4 is an embodiment of the present invention, which provides a method for special transformer power management and early warning based on multi-sensor fusion. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation / comparative experiments.

[0067] In this embodiment, six transformers were selected as test subjects to evaluate the effectiveness and innovation of the proposed multi-sensor fusion-based power management and early warning system under China's national conditions. Test preparation included installing multiple sensors (current sensors, voltage sensors, and power sensors) on each transformer to ensure high accuracy and rapid response capabilities for real-time monitoring of power data.

[0068] After the test began, the equipment was calibrated first to ensure the accuracy of the sensor measurements. Next, using the installed sensors, parameters such as phase voltage, phase current, and power factor of each transformer were continuously monitored, collecting active and reactive power data. The data was uploaded to the cloud platform in real time via 4G / 5G network, ensuring the immediacy and visualization of the information. The system generates a real-time monitoring interface, displaying the dynamic changes in power data, enabling maintenance personnel to quickly respond to potential problems.

[0069] During the test, different load conditions were set, and the power data under normal and abnormal conditions were monitored. Through data monitoring and analysis, abnormal states were found in transformers D and F under specific loads. The system promptly identified these potential fault signs and automatically generated fault warning information. This process demonstrates the innovation and effectiveness of this invention in power monitoring and fault early warning. Data details can be found in Table 1.

[0070] Table 1 Experimental Data

[0071]

[0072] Analysis of the data in the above tables clearly reveals the innovation and advantages demonstrated in the implementation of this invention. Firstly, considering parameters such as phase voltage, phase current, and power factor, all transformers maintain a voltage of 230V under normal conditions, while the current and power parameters fluctuate within a reasonable range, demonstrating the stability of the equipment under normal load. Transformers A through C all perform well, with power factors close to 1, indicating good energy utilization efficiency.

[0073] However, it is worth noting that transformers D and F were identified as exhibiting abnormal conditions during the monitoring process. This demonstrates that the real-time monitoring system based on multi-sensor fusion can effectively capture early signs of potential faults, and that the system's automated early warning mechanism is both practical and efficient. Compared to traditional monitoring technologies, which often rely on periodic inspections or manual intervention and fail to promptly reflect abnormal equipment conditions, potential faults may go undetected.

[0074] This invention utilizes machine learning algorithms to automatically identify abnormal fluctuations during equipment operation by comparing real-time and historical data. This technological advantage not only improves the timeliness of fault identification but also significantly reduces economic losses caused by equipment failures. Specifically, abnormal conditions in transformers D and F are captured by the system and fed back to maintenance personnel within minutes of their occurrence, facilitating rapid assessment and corrective action.

[0075] In summary, this embodiment, through specific data monitoring and analysis, clarifies the innovation and practicality of a multi-sensor fusion-based power management and early warning system in improving the timeliness of fault warnings and enhancing monitoring accuracy. This not only provides an effective solution for the intelligent management of power systems but also lays the foundation for ensuring the safety and stability of power supply.

[0076] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for dedicated power substation energy management and early warning based on multi-sensor fusion, characterized in that, include: Real-time acquisition of transformer power data, followed by data fusion and error correction; Continuously monitor power usage, identify anomalies, and report them. Predict faults and optimize power management through data analysis; Data visualization and real-time monitoring are achieved through local and remote communication; Regularly generate power and equipment operation reports; The real-time acquisition of transformer power data includes the real-time acquisition of phase voltage, phase current, phase and total active power, phase and total reactive power, phase and total apparent power, phase and total power factor, and grid frequency of the special transformer equipment through current, voltage and power sensors. The data fusion and error correction process includes correcting errors in the collected data, performing multi-dimensional longitudinal and horizontal analysis on the real-time power data of the transformer, comparing data collected by the same sensor at different time points in the longitudinal analysis, and comprehensively comparing data collected by different sensors at the same time point in the horizontal analysis; and correcting errors in the collected power data by combining historical data and real-time data to ensure the accuracy and consistency of the data. The identification and reporting of anomalies includes continuously measuring current, voltage and power data, and calculating positive and negative active energy, positive and negative reactive energy and four-quadrant reactive energy data to monitor the user's power consumption in real time. The relevant data is wirelessly uploaded to a remote server via 4G / 5G network to achieve effective real-time monitoring of power consumption. The system uses intelligent drop-out fuses to collect operational data in real time and store electrical energy data periodically. If abnormal situations occur during transformer shutdown or capacity reduction, the program will automatically enter an alarm state, automatically identify whether the user has violated electricity usage regulations, and proactively report the abnormal status. The optimized power management includes: conducting big data analysis on historical power data and real-time operating data collected by multiple sensors to establish a mathematical model of equipment operating status; monitoring the voltage, current and power change trends of the equipment; identifying potential fault signs; and when abnormal fluctuations and abnormal operating modes are detected, using machine learning algorithms to predict the equipment operating status and generate fault warning information. The power allocation strategy is dynamically adjusted based on the forecast results, and the load management is optimized to ensure that power resources are scheduled before a fault occurs. The visualization and real-time monitoring of the data includes uploading the transformer's power data and operating status to a remote server or cloud platform and synchronizing it to a mobile terminal; The system provides a graphical user interface and uses data visualization technology to present real-time monitored current, voltage, and power data in the form of charts and curves. The data visualization platform supports real-time monitoring of equipment status, querying and analysis of historical data. Users can view the current status and early warning information of the equipment at any time through remote terminals or mobile applications, and receive equipment operation reports and power consumption analysis reports generated by the system.

2. The method for dedicated power substation energy management and early warning based on multi-sensor fusion as described in claim 1, characterized in that: The periodic generation of power and equipment operation reports includes generating equipment operation status reports and power consumption analysis reports periodically based on real-time monitored current, voltage, and power data, combined with historical data, through big data analysis and prediction models; the report content includes equipment working efficiency, fault early warning information, power consumption pattern analysis, energy consumption statistics, and abnormal power consumption; The system automatically pushes reports to the maintenance personnel's management platform, helping managers make decisions based on equipment operation and energy consumption.

3. A dedicated power substation energy management and early warning system based on multi-sensor fusion, employing the method described in any one of claims 1-2, characterized in that: Data acquisition and fusion module: Real-time acquisition of transformer power data, data fusion and error correction; Anomaly detection module: continuously monitors power usage, identifies anomalies, and reports them; Intelligent fault prediction module: Predicts faults through data analysis to optimize power management; Data communication and visualization module: Enables data visualization and real-time monitoring through local and remote communication; Report generation module: Regularly generates reports on power and equipment operation.

4. 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 2.

5. A computer-readable storage medium having a computer program stored thereon, 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 2.

Images