Special power transformation electric energy management and early warning method and system based on multi-sensor fusion

Abstract

The invention discloses a special power transformation electric energy management and early warning method and system based on multi-sensor fusion, and the method comprises the steps: collecting the electric power data of a transformer in real time, and carrying out the data fusion and error correction; electric energy use is continuously monitored, and abnormity is identified and reported; faults are predicted through data analysis, and electric energy management is optimized. Through local and remote communication, visualization and real-time monitoring of data are realized; and periodically generating an electric energy and equipment operation report. According to the method, the accuracy and timeliness of data acquisition are improved, big data analysis and a machine learning algorithm are combined, early prediction of faults and optimization of electric energy management are realized, and hysteresis and inaccuracy in a traditional method are avoided. The system has the functions of automatic early warning, remote monitoring and real-time data visualization, and the operation efficiency and safety of a power system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system management and monitoring technology, and specifically to a special transformer power management and early warning method and system based on multi-sensor fusion. Background Art

[0002] With the continuous development and digital transformation of the power system, the real-time monitoring and management of the operating status and power usage of transformers, as key power equipment in the power grid, has become particularly important. Traditional transformer monitoring methods mainly rely on the monitoring of a single sensor or manual regular inspections. This method not only has limited monitoring information and is difficult to fully obtain the operating status data of the transformer, but also has problems such as insufficient timeliness and inaccurate data. In recent years, with the advancement of the Internet of Things, big data analysis, and intelligent sensing technology, multi-sensor fusion technology has gradually been applied to power systems. By integrating multiple sensors (such as voltage, current, power sensors, etc.), more comprehensive, real-time, and accurate equipment status monitoring has been achieved. The combination of these technologies has greatly improved the degree of automation in power equipment management, and through advanced algorithms, data fusion processing has been carried out to achieve multi-dimensional analysis of the operation of power equipment.

[0003] However, the existing multi-sensor monitoring technology still has some shortcomings. First, although the multi-sensor system can realize real-time data collection, the data fusion algorithm often has problems such as high complexity and low computational efficiency, especially in terms of data error correction and anomaly detection, it cannot guarantee efficient real-time processing, which easily leads to monitoring information lag. Secondly, the abnormal detection and early warning capabilities of power equipment are limited. The existing system can usually only detect specific types of faults and it is difficult to effectively identify complex power consumption anomalies, such as illegal power consumption or abnormal load fluctuations. In addition, most of the current fault prediction systems are based on preset fixed thresholds, lack flexible intelligent processing, and cannot be adaptively adjusted according to the dynamic changes in the operating status of the equipment, resulting in delayed early warning information or frequent false alarms. These shortcomings limit the application of existing technologies in complex power grid environments, especially in the case of high-load operation or load imbalance, 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 the present invention is: in the existing power system, although multi-sensor technology is used for monitoring, due to the complexity of the data fusion algorithm and the low computational efficiency, the real-time performance of data processing is insufficient, and the change of equipment status cannot be responded to quickly. In the prior art, the data collected by multiple sensors are often affected by factors such as environmental noise and equipment failure. The error correction algorithm cannot effectively eliminate these errors, resulting in inaccurate monitoring data, which affects the judgment of the equipment operation status. Most of the existing power management systems can only detect specific fault types, such as overload or short circuit, lack the ability to identify complex abnormalities in the use of electric energy (such as illegal electricity use, load imbalance, etc.), and cannot fully monitor the operation status of the transformer. Traditional fault prediction technology usually relies on fixed threshold settings and lacks the ability to dynamically adjust according to the equipment operation status, resulting in delayed prediction of faults, and even false alarms or omissions, which reduces the early warning effect of the system.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a special transformer power management and early warning method based on multi-sensor fusion, comprising: real-time collection 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] Realize data visualization and real-time monitoring through local and remote communications;

[0010] Generate regular reports on power and equipment operation.

[0011] As a preferred solution of the special transformer power management and early warning method based on multi-sensor fusion described in the present invention, the real-time collection of transformer power data includes real-time collection 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.

[0012] As a preferred solution of the special transformer power management and early warning method based on multi-sensor fusion described in the present invention, the data fusion and error correction include: performing error correction on the collected data, and performing vertical and horizontal multi-dimensional analysis on the real-time power data of the transformer. The vertical analysis is to compare the data collected by the same sensor at different time points, and the horizontal analysis is to conduct a comprehensive comparison of the data collected by different sensors at the same time point; by combining historical data and real-time data, the collected power data is error corrected to ensure the accuracy and consistency of the data.

[0013] As a preferred solution of the dedicated transformer power management and early warning method based on multi-sensor fusion described in the present invention, wherein: the identification and reporting of abnormalities includes continuously measuring current, voltage and power data, and calculating positive and negative active power, positive and negative reactive power and four-quadrant reactive power data, real-time monitoring of the user's power usage, and wirelessly uploading relevant data to a remote server through a 4G / 5G network, so as to realize effective real-time monitoring of power;

[0014] Intelligent drop-out fuses are used to collect operating data in real time and store power data at regular intervals. If an abnormal situation occurs during transformer suspension and capacity reduction, the program automatically enters an alert state, automatically identifies whether the user has violated electricity usage regulations, and proactively reports abnormal conditions.

[0015] As a preferred solution of the special transformer power management and early warning method based on multi-sensor fusion described in the present invention, wherein: the optimized power management includes, by performing big data analysis on historical power data and real-time operation data collected by multiple sensors, establishing a mathematical model of the equipment operation status, monitoring the voltage, current and power change trends of the equipment, and identifying potential fault signs; when abnormal fluctuations and abnormal operation modes are detected, combining machine learning algorithms, predicting the equipment operation status and generating fault warning information;

[0016] Dynamically adjust the power distribution strategy based on the prediction results, optimize load management, and ensure that power resources are dispatched before a fault occurs.

[0017] As a preferred solution of the special transformer power management and early warning method based on multi-sensor fusion described in the present invention, wherein: the realization of data visualization and real-time monitoring includes uploading the power data and operating status of the transformer to a remote server or cloud platform, and synchronizing to a mobile terminal; the system provides a graphical user interface, and through data visualization technology, the real-time monitored current, voltage, and power data are presented in the form of charts and curves;

[0018] The data visualization platform supports real-time monitoring of equipment status, query and analysis of historical data. Users can view the current status and 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 solution of the dedicated transformer power management and early warning method based on multi-sensor fusion described in the present invention, wherein: the periodic generation of power and equipment operation reports includes, based on the real-time monitored current, voltage, power data, combined with historical data, regularly generating equipment operation status reports and power consumption analysis reports through big data analysis and prediction models; the report content includes equipment work efficiency, fault warning information, power consumption law analysis, energy consumption statistics and abnormal power consumption;

[0020] The report is automatically pushed to the management platform of the operation and maintenance personnel to help managers make decisions based on the operation status and energy consumption of the equipment.

[0021] The special transformer power management and early warning system based on multi-sensor fusion is characterized by: including:

[0022] Data acquisition and fusion module: collects transformer power data in real time, performs data fusion and error correction;

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

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

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

[0026] Report generation module: Generate power and equipment operation reports regularly.

[0027] Beneficial effects of the present invention: The present invention can process multiple data sources such as current, voltage, power, etc. more efficiently, and perform accurate error correction to ensure the accuracy of monitoring data, which helps to timely grasp the operating status of the transformer. Through big data analysis and intelligent algorithms, complex abnormal situations of power use, such as illegal power use, load imbalance, etc., can be identified, and abnormal conditions can be quickly responded to and reported to ensure the comprehensiveness and safety of power management. Through machine learning and big data analysis models, the present invention can dynamically adjust the fault prediction strategy, warn of potential faults in advance according to changes in the operating status of the equipment, reduce the risk of faults, and improve the stability of system operation. Combined with predictive analysis and load management, it can optimize power distribution and resource scheduling strategies according to actual power usage, improve the efficiency of power management, and reduce unnecessary energy consumption. Through local and remote communication technologies, the present invention can transmit power usage data to a monitoring platform or mobile terminal in real time, and present it in a visual form, providing more intuitive and convenient management means for operation and maintenance personnel, and effectively improving the efficiency of equipment maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the figures required for use in the description of the embodiments will be briefly introduced below. Obviously, the figures described below are only some embodiments of the present invention. For ordinary technicians in this field, other figures can be obtained based on these figures without paying creative work.

[0029] Figure 1A flow chart of a dedicated transformer power management and early warning method based on multi-sensor fusion provided for the first embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the specification drawings. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0031] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a special transformer power management and early warning method based on multi-sensor fusion, including:

[0032] S1: Collect transformer power data in real time, perform data fusion and error correction.

[0033] Through current, voltage and power sensors, 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 special transformer equipment are collected in real time.

[0034] The collected data is error-corrected, and the real-time power data of the transformer is subjected to multi-dimensional vertical and horizontal analysis. The vertical analysis is to compare the data collected by the same sensor at different time points, and the horizontal analysis is to conduct a comprehensive comparison of the data collected by different sensors at the same time point. By combining historical data and real-time data, the collected power data is error-corrected to ensure the accuracy and consistency of the data.

[0035] It should be noted that in the data fusion part, the present invention proposes a "vertical and horizontal multi-dimensional analysis" method, which is a key innovation to solve the problem of data isolation and one-sided analysis in traditional monitoring systems. Vertical analysis involves comparing the data of the same sensor at different time points, with the aim of capturing the dynamic changes in the operating status of the equipment. This method has obvious technical advantages: by analyzing long time series data, gradual faults in equipment operation (such as gradually excessive load or voltage fluctuations) can be accurately identified, thereby preventing the accumulation of potential problems. In addition, horizontal analysis is a comprehensive comparison of data from different sensors at the same time point, which makes up for the insufficiency of a single sensor being unable to fully describe the status of the equipment. This multi-sensor horizontal comparison method is particularly suitable for complex state monitoring in power systems. For example, if the change in power factor is not synchronized with the fluctuations in current and voltage, it may indicate power loss or equipment abnormality, and these potential problems can be discovered in a timely manner through horizontal data analysis.

[0036] Error correction is an important part of ensuring data accuracy. The present invention combines historical data with real-time data for correction to ensure that the data error of the monitoring system is minimized. This error correction strategy has significant advantages over traditional methods: by combining historical data, it can effectively identify and eliminate the impact of sporadic 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 make corrections to avoid false alarms or misjudgments. In addition, longitudinal analysis combined with historical data can more accurately identify trend changes, while horizontal analysis further improves the accuracy of error correction by comparing different sensor data at the same time.

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

[0038] Continuously measure current, voltage and power data, and calculate the forward and reverse active energy, forward and reverse reactive energy and four-quadrant reactive energy data to monitor the user's energy usage in real time. Through the 4G / 5G network, the relevant data is wirelessly uploaded to the remote server to achieve effective real-time monitoring of electricity.

[0039] Intelligent drop-out fuses are used to collect operating data in real time and store power data at regular intervals. If an abnormal situation occurs during transformer suspension and capacity reduction, the program automatically enters an alert state, automatically identifies whether the user has violated electricity usage regulations, and proactively reports abnormal conditions.

[0040] It should be noted that the communication method of "wirelessly uploading relevant data to a remote server via 4G / 5G network" makes the transmission of monitoring data more efficient and timely. This character selection not only improves the real-time nature of data transmission, but also enhances the flexibility of the system, allowing operation and maintenance personnel to remotely monitor power usage in real time. This usually requires manual inspections or the support of a fixed network environment in traditional monitoring systems, and the present invention greatly improves the convenience and efficiency of data upload through the application of mobile communication technology.

[0041] In terms of abnormal monitoring and identification, the present invention uses "intelligent drop-out fuses" as core equipment to collect operating data in real time and store electric energy data at regular intervals. The beneficial effect of this method is that the intelligent drop-out fuse not only has the protection function of a traditional fuse, but can also automatically enter an "alert state" when encountering abnormal conditions during transformer suspension and capacity reduction. At this time, the system will intelligently identify whether the user has violated the regulations on electricity use based on the comparison of historical and real-time data. The rationality of this automatic identification mechanism lies in the fact that traditional monitoring systems often require manual intervention, resulting in insufficient response to violations, while the present invention improves the response speed and accuracy to illegal electricity use through automated monitoring and intelligent analysis.

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

[0043] By performing big data analysis on historical power data and real-time operation data collected by multiple sensors, a mathematical model of the equipment's operating status is established, the equipment's voltage, current, and power change trends are monitored, and potential signs of failure are identified. When abnormal fluctuations and abnormal operating modes are detected, the equipment's operating status is predicted in combination with machine learning algorithms, and fault warning information is generated.

[0044] Dynamically adjust the power distribution strategy based on the prediction results, optimize load management, and ensure that power resources are dispatched 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 signs of faults. The rationality of this process lies in that, through the establishment of a mathematical model, the operating status of the equipment can be quantified, and abnormal fluctuations and patterns can be identified through comparative analysis. When an abnormal mode of equipment operation occurs, such as voltage fluctuations that do not match load changes, the system can respond quickly. The present invention combines "machine learning algorithms" to predict equipment status, further enhancing the level of intelligence in fault detection. The beneficial effect of this method is that machine learning algorithms can identify complex patterns and relationships in massive data, so that the system not only relies on fixed rules when predicting faults, but can learn the dynamic changes of equipment in normal and abnormal states. This dynamic learning capability enables the system to gradually improve the accuracy of predictions over time, and to generate "fault warning information" in a timely manner when abnormal fluctuations are detected, providing powerful decision-making support for operation and maintenance personnel.

[0046] Finally, based on the fault prediction results, the system can "dynamically adjust the power distribution strategy" to optimize load management. The rationality of this strategy lies in that through real-time fault prediction, the system can effectively avoid the waste of power resources and equipment overload, and ensure reasonable resource scheduling before the fault occurs. For example, when it is detected that a transformer is about to be overloaded, the system can automatically adjust the power distribution to reduce the load on the equipment, thereby reducing the risk of failure. Compared with the traditional passive response method, this active management strategy significantly improves the stability and safety of the power system.

[0047] S4: Data visualization and real-time monitoring are achieved through local and remote communications.

[0048] The power data and operating status of the transformer are uploaded to a remote server or cloud platform and synchronized to a mobile terminal. The system provides a graphical user interface and presents real-time monitored current, voltage, and power data in the form of charts and curves through data visualization technology.

[0049] The data visualization platform supports real-time monitoring of equipment status, query and analysis of historical data. Users can view the current status and 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 through data visualization technology, real-time monitoring data such as current, voltage, and power are presented in the form of "charts and curves", which not only improves the readability of the data, but also enables users to quickly grasp the operating status of the equipment. The rationality of this design lies in the fact that data visualization can convert complex data into intuitive graphics, which helps users quickly understand the operating trends and status changes of the equipment. Intuitive visual information is particularly important in scenarios where quick decisions need to be made.

[0051] The visualization platform supports "real-time monitoring of equipment status, query and analysis of historical data", which provides comprehensive management functions to ensure that operation and maintenance personnel can view the current status and warning information of the equipment at any time through remote terminals or mobile applications. This ability to obtain and query instantly is of great significance to improving the efficiency of equipment management. For example, when an abnormal fluctuation occurs in a certain equipment, the operation and 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 power consumption analysis reports", which provides data support for long-term management. These reports not only help users understand the historical operation and power consumption patterns of the equipment, but also provide a basis for formulating future operation and maintenance plans and energy efficiency optimization strategies. Through the analysis of historical data, users can identify long-standing potential problems and trends, and provide references for system improvements and equipment maintenance.

[0052] S5: Generate power and equipment operation reports regularly.

[0053] Based on the real-time monitored current, voltage and power data, combined with historical data, the equipment operation status report and power consumption analysis report are regularly generated through big data analysis and prediction models; the report content includes equipment work efficiency, fault warning information, power consumption pattern analysis, energy consumption statistics and abnormal power consumption;

[0054] The report is automatically pushed to the management platform of the operation and maintenance personnel to help managers make decisions based on the operation status and energy consumption of the equipment.

[0055] It should be noted that in terms of report generation, the present invention uses "big data analysis and prediction models" to regularly 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, extract deep insights into the operation status of equipment, and help identify potential failure trends. For example, by analyzing current fluctuations and voltage changes, the system can warn of possible equipment failures in advance and avoid sudden equipment shutdowns. At the same time, combined with the prediction model, future energy consumption trends can be evaluated to provide a scientific basis for decision-making.

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

[0057] If the functions are implemented in the form of 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 the present invention, or the part that contributes to the prior art or the part of the current technical solution, can be embodied in the form of a software product. The current computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

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

[0059] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic systems), a portable computer disk case (magnetic systems), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber system, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0060] Example 3 is an embodiment of the present invention, which provides a special transformer 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: collects transformer power data in real time, performs 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: realize data visualization and real-time monitoring through local and remote communication.

[0065] Report generation module: Generate power and equipment operation reports regularly.

[0066] Example 4 is an embodiment of the present invention, which provides a special transformer power management and early warning method 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 example, six transformers were selected as test objects to evaluate the effectiveness and innovation of the mentioned power management and early warning system based on multi-sensor fusion under China's national conditions. The test preparation work includes installing multiple sensors (current sensor, voltage sensor, power sensor) on each transformer to ensure that they have high accuracy and fast response capabilities to monitor power data in real time.

[0068] After the test begins, the equipment is calibrated first to ensure that the sensor's measurement data is accurate. Then, the installed sensors are used to continuously monitor the phase voltage, phase current, power factor and other parameters of each transformer, and collect active power and reactive power data. The data is uploaded to the cloud platform in real time via the 4G / 5G network to ensure the immediacy and visualization of information. The system generates a real-time monitoring interface to display the dynamic changes in power data, allowing operation and 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, it was found that transformer D and transformer F were in abnormal conditions 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 the present invention in power monitoring and fault warning. The data content can be referred to Table 1.

[0070] Table 1 Experimental data table

[0071]

[0072] By analyzing the above table data, the innovation and advantages shown in the implementation of the present invention can be clearly identified. First, from the perspective of parameters such as phase voltage, phase current and power factor, the voltage of all transformers under normal conditions is maintained at 230V, and the current and power parameters fluctuate within a reasonable range, showing the stability of the equipment under normal load. Transformers A to C all perform well, with a power factor close to 1, showing good energy utilization efficiency.

[0073] However, it is worth noting that transformer D and transformer F were identified as having abnormal conditions during the monitoring process. This situation shows that the real-time monitoring system based on multi-sensor fusion can effectively capture the early signs of potential faults, and the system's automated early warning mechanism is practical and efficient. Compared with traditional monitoring technologies, traditional methods often rely on regular inspections or manual intervention, and fail to reflect the abnormal status of the equipment in a timely manner, resulting in possible faults not being discovered in time.

[0074] The present invention uses machine learning algorithms to automatically identify abnormal fluctuations during equipment operation by comparing real-time data with historical data. This technical advantage not only improves the timeliness of fault identification, but also significantly reduces the economic losses caused by equipment failure. Specifically, the abnormal conditions of transformers D and F were captured by the system within minutes of occurrence and fed back to the operation and maintenance personnel, allowing them to quickly judge and take measures.

[0075] In summary, this embodiment, through specific data monitoring and analysis, clarifies the innovation and practicality of the power management and early warning system based on multi-sensor fusion in improving the timeliness of fault warning and enhancing monitoring accuracy. This not only provides an effective solution for the intelligent management of the power system, 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 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 solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A special transformer power management and early warning method based on multi-sensor fusion, characterized in that: include: Collect transformer power data in real time, perform data fusion and error correction; Continuously monitor power usage, identify anomalies and report them; Predict faults and optimize power management through data analysis; Realize data visualization and real-time monitoring through local and remote communications; Generate regular reports on power and equipment operation.

2. The method for managing and warning power of a dedicated transformer based on multi-sensor fusion according to claim 1 is characterized in that: The real-time collection of transformer power data includes real-time collection of the special transformer equipment's 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 through current, voltage and power sensors.

3. The method for managing and warning power of a special transformer based on multi-sensor fusion according to claim 2 is characterized in that: The data fusion and error correction include performing error correction on the collected data and performing vertical and horizontal multi-dimensional analysis on the real-time power data of the transformer. The vertical analysis is to compare the data collected by the same sensor at different time points, and the horizontal analysis is to perform a comprehensive comparison on the data collected by different sensors at the same time point. By combining historical data and real-time data, the collected power data is error corrected to ensure the accuracy and consistency of the data.

4. The method for managing and warning power of a special transformer based on multi-sensor fusion according to claim 3 is characterized in that: The identification and reporting of abnormalities includes continuously measuring current, voltage and power data, and calculating forward and reverse active energy, forward and reverse reactive energy and four-quadrant reactive energy data, real-time monitoring of the user's energy usage, and wirelessly uploading relevant data to a remote server through a 4G / 5G network, thereby realizing effective real-time monitoring of electricity; Intelligent drop-out fuses are used to collect operating data in real time and store power data at regular intervals. If an abnormal situation occurs during transformer suspension and capacity reduction, the program automatically enters an alert state, automatically identifies whether the user has violated electricity usage regulations, and proactively reports abnormal conditions.

5. The method for managing and warning power of a special transformer based on multi-sensor fusion according to claim 4 is characterized in that: The optimized power management includes: establishing a mathematical model of the equipment operation status by performing big data analysis on historical power data and real-time operation data collected by multiple sensors, monitoring the voltage, current and power change trends of the equipment, and identifying potential fault signs; when abnormal fluctuations and abnormal operation modes are detected, combining machine learning algorithms to predict the equipment operation status and generate fault warning information; Dynamically adjust the power distribution strategy based on the prediction results, optimize load management, and ensure that power resources are dispatched before a fault occurs.

6. The method for managing and warning power of a special transformer based on multi-sensor fusion according to claim 5 is characterized in that: The realization of data visualization and real-time monitoring includes uploading the power data and operating status of the transformer to a remote server or cloud platform, and synchronizing them 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; The data visualization platform supports real-time monitoring of equipment status, query and analysis of historical data. Users can view the current status and 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.

7. The method for managing and warning power of a special transformer based on multi-sensor fusion according to claim 6 is characterized in that: The periodic generation of power and equipment operation reports includes periodically generating equipment operation status reports and power consumption analysis reports based on real-time monitored current, voltage, and power data in combination with historical data through big data analysis and prediction models; the report content includes equipment work efficiency, fault warning information, power consumption law analysis, energy consumption statistics, and abnormal power consumption; The report is automatically pushed to the management platform of the operation and maintenance personnel to help managers make decisions based on the operation status and energy consumption of the equipment.

8. A dedicated transformer power management and early warning system based on multi-sensor fusion using the method according to any one of claims 1 to 7, characterized in that: Data acquisition and fusion module: collects transformer power data in real time, performs data fusion and error correction; Anomaly detection module: continuously monitors power usage, identifies anomalies and reports them; Intelligent fault prediction module: predict faults through data analysis and optimize power management; Data communication and visualization module: realize data visualization and real-time monitoring through local and remote communication; Report generation module: Generate power and equipment operation reports regularly.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images