A method and device for detecting over-temperature of high-power terminals based on dedicated transformer data acquisition terminals

Abstract

This application provides a method and device for detecting over-temperature of high-power terminals based on a dedicated transformer acquisition terminal. The method includes: acquiring electrical and environmental parameters through a multi-parameter fusion sensor, acquiring temperature distribution data through a distributed optical fiber sensor, and inputting the electrical parameters, environmental parameters, and temperature distribution data into a preset neural network model. The preset neural network model obtains the temperature change trend of the high-power terminals and the probability of over-temperature occurrence within a preset time period based on different parameter combinations. Parameters are acquired from multiple dimensions and deep analysis is performed based on the preset neural network model. The preset neural network model is trained based on various sample data combinations and corresponding terminal temperature data, enabling accurate and timely over-temperature detection. This allows for timely implementation of subsequent protection measures or problem-solving based on the temperature change trend and the probability of over-temperature occurrence.

Description

Technical Field

[0001] This application relates to the field of dedicated transformer data acquisition terminal technology, and more specifically, to a method and device for detecting over-temperature of high-power wiring terminals based on dedicated transformer data acquisition terminals. Background Technology

[0002] In power systems, dedicated transformer data acquisition terminals serve as the core equipment for collecting and managing electricity consumption information from dedicated transformer users. Their internal high-power terminals bear the responsibility of transmitting high voltage and high current. Due to long-term exposure to load surges, environmental corrosion, and mechanical vibrations, the terminals are prone to abnormal heating due to increased contact resistance. If not detected and intervened in a timely manner, this can lead to serious accidents such as terminal burn-out, short circuits, or even equipment fires, directly threatening the safe operation of the power grid.

[0003] Currently, the over-temperature detection of high-power terminals in dedicated transformer data acquisition terminals mainly adopts either the direct sensing temperature method or the indirect electrical parameter estimation method. The direct sensing temperature method directly collects the temperature through the sensor, which is prone to wear and tear over time, thus affecting the detection accuracy. In addition, it requires manual reading, which is inefficient. The indirect electrical parameter estimation method calculates the contact resistance based on the voltage error across the terminal and the line current, and then uses Joule's law to estimate the temperature. However, it has a large error under complex operating conditions, which affects the detection accuracy. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for detecting over-temperature of high-power terminals based on a dedicated transformer acquisition terminal, in order to address the shortcomings of the prior art and solve the problems of large over-temperature detection errors and low efficiency in the prior art.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0006] In a first aspect, one embodiment of this application provides a method for detecting over-temperature of high-power terminals based on a dedicated transformer data acquisition terminal. This method is applied to the controller of the dedicated transformer data acquisition terminal. Multiple multi-parameter fusion sensors and distributed fiber optic sensors are arranged around the high-power terminals within the dedicated transformer data acquisition terminal. Both the multi-parameter fusion sensors and the distributed fiber optic sensors are communicatively connected to the controller. The method includes:

[0007] Electrical and environmental parameters are acquired through the multi-parameter fusion sensor, and temperature distribution data is acquired through the distributed optical fiber sensor. The electrical parameters include: terminal temperature, current flowing through the terminal, voltage across the terminal, and terminal vibration parameters. The environmental parameters include: ambient humidity and ambient temperature information.

[0008] The electrical parameters, environmental parameters, and temperature distribution data are input into a preset neural network model. The preset neural network model obtains the temperature change trend of the high-power terminal block and the probability of overheating within a preset time period based on different parameter combinations. The preset neural network model is trained based on multiple sample data combinations and corresponding terminal block temperature data. The multiple sample data combinations include different combinations of sample electrical parameters, sample environmental parameters, and sample temperature distribution data.

[0009] Optionally, the temperature change trend of the high-power terminal block and the probability of overheating are obtained through the preset neural network model based on different parameter combinations within a future preset time period, including:

[0010] The preset neural network model obtains and evaluates the current health status of the high-power terminal block based on different parameter combinations;

[0011] If the current health status indicates normal, the preset neural network model outputs the temperature change trend of the high-power terminal block and the probability of overheating within a future preset time period based on different parameter combinations and stored historical data for a preset time period.

[0012] Optionally, the method further includes:

[0013] If the current health status indicates a health warning, and / or the temperature change trend is abnormal or the probability of overheating is greater than a preset probability, then a warning message is sent to the remote terminal and an alarm is activated.

[0014] Optionally, the warning information includes multiple levels of warning information:

[0015] A Level 1 warning includes: the temperature trend is upward within a preset time period, and the rate of increase is within a preset range;

[0016] Level 2 warning includes: the current temperature is higher than the normal operating temperature but lower than the overheating temperature, and the probability of overheating occurring within a preset time period is greater than the preset probability;

[0017] Level 3 warning includes: the current temperature is higher than the over-temperature temperature.

[0018] Optionally, after outputting the temperature change trend of the high-power terminal block and the probability of overheating within a preset future time period, the method further includes:

[0019] Based on the temperature change trend of the high-power terminal block and the probability of overheating within a future preset time period, and a preset analysis model, the causes of overheating are analyzed and obtained. The preset analysis model is trained based on the temperature change trend of historical time periods and the corresponding overheating faults and causes. The causes of overheating include any of the following: poor contact, overload, and abnormal ambient temperature.

[0020] Optionally, the method further includes:

[0021] If the data monitored by the target sensor in the multi-parameter fusion sensor or the distributed optical fiber sensor deviates from the data monitored by other surrounding sensors by a preset value, then the target sensor is determined to be a faulty sensor, and the data monitored by the faulty sensor is removed.

[0022] Optionally, after determining that the target sensor is a faulty sensor and removing the data monitored by the faulty sensor, the method further includes:

[0023] Based on the location information of the multi-parameter fusion sensor and the distributed optical fiber sensor, the data of the N sensors closest to the faulty sensor are obtained, and the replacement data of the faulty sensor is calculated using an interpolation algorithm, where N is an integer greater than 0.

[0024] Secondly, another embodiment of this application provides a high-power terminal over-temperature detection device based on a dedicated transformer data acquisition terminal, applied to the controller of the dedicated transformer data acquisition terminal. Multiple multi-parameter fusion sensors and distributed fiber optic sensors are arranged around the high-power terminal inside the dedicated transformer data acquisition terminal. Both the multi-parameter fusion sensors and the distributed fiber optic sensors are communicatively connected to the controller. The device includes:

[0025] The acquisition module is used to acquire electrical parameters and environmental parameters through the multi-parameter fusion sensor and to acquire temperature distribution data through the distributed optical fiber sensor; wherein, the electrical parameters include: terminal temperature, current flowing through the terminal, voltage across the terminal, and terminal vibration parameters; the environmental parameters include: ambient humidity information and ambient temperature information;

[0026] The analysis module is used to input the electrical parameters, the environmental parameters, and the temperature distribution data into a preset neural network model. The preset neural network model obtains the temperature change trend of the high-power terminal block and the probability of overheating within a preset time period based on different parameter combinations. The preset neural network model is trained based on multiple sample data combinations and corresponding terminal block temperature data. The multiple sample data combinations include different combinations of sample electrical parameters, sample environmental parameters, and sample temperature distribution data.

[0027] Thirdly, another embodiment of this application provides a dedicated transformer data acquisition terminal, including: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the dedicated transformer data acquisition terminal is running, the processor executes the machine-readable instructions to perform the steps of any of the methods described in the first aspect above.

[0028] Fourthly, another embodiment of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of any of the methods described in the first aspect above.

[0029] The beneficial effects of this application are:

[0030] Electrical and environmental parameters are acquired through multi-parameter fusion sensors, and temperature distribution data is acquired through distributed fiber optic sensors. The electrical, environmental, and temperature distribution data are then input into a pre-defined neural network model. This model uses different parameter combinations to determine the temperature change trend of high-power terminals and the probability of overheating within a preset time period. By collecting parameters from multiple dimensions and performing in-depth analysis based on the pre-defined neural network model, which is trained using various sample data combinations and corresponding terminal temperature data, accurate and timely overheat detection can be achieved. This allows for timely implementation of subsequent protective measures or problem-solving based on temperature change trends and the probability of overheating. Attached Figure Description

[0031] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 A flowchart illustrating a high-power terminal over-temperature detection method based on a dedicated transformer acquisition terminal, provided in an embodiment of this application;

[0033] Figure 2 A flowchart illustrating a high-power terminal over-temperature detection method based on a dedicated transformer acquisition terminal, provided for another embodiment of this application;

[0034] Figure 3 A schematic diagram of a high-power terminal over-temperature detection device based on a dedicated transformer acquisition terminal provided in this application embodiment;

[0035] Figure 4 This is a schematic diagram of the structure of a dedicated transformer data acquisition terminal provided in an embodiment of this application. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0037] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0038] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0039] This application proposes a more flexible and timely method to address the over-temperature detection problem of high-power terminals in dedicated transformer data acquisition terminals.

[0040] Figure 1 This is a flowchart illustrating an embodiment of a high-power terminal over-temperature detection method based on a dedicated transformer data acquisition terminal. The method is applied to the controller of the dedicated transformer data acquisition terminal. Multiple multi-parameter fusion sensors and distributed fiber optic sensors are arranged around the high-power terminal within the dedicated transformer data acquisition terminal, wherein both the multi-parameter fusion sensors and the distributed fiber optic sensors are communicatively connected to the controller.

[0041] The high-power terminals in the embodiments of this application can be busbar connection terminals, cable connection terminals or fuse connection terminals, and are not specifically limited here.

[0042] It should be noted that multi-parameter fusion sensors can be used to collect real-time data from multiple dimensions, such as terminal temperature, current flowing through the terminal, voltage across the terminal, localized minor vibrations at the terminal, and ambient humidity inside the equipment. Distributed fiber optic sensors can be deployed along high-power terminals and their connecting lines, for example, at corresponding collection points with uniform intervals, to collect temperature distribution data. This enables continuous, long-distance temperature monitoring of the entire terminal block, avoiding the blind spots of traditional point sensors. Taking busbar connection terminals as an example, distributed fiber optic sensors can be deployed along the busbar; there are no specific limitations here.

[0043] Specifically, the method includes:

[0044] S101: Electrical and environmental parameters are acquired through multi-parameter fusion sensors, and temperature distribution data is acquired through distributed fiber optic sensors.

[0045] The electrical parameters include: terminal temperature, current flowing through the terminal, voltage across the terminal, and terminal vibration parameters; the environmental parameters include: ambient humidity information and ambient temperature information.

[0046] It should be noted that, based on the distribution of these sensors, electrical parameters, environmental parameters, and temperature distribution data corresponding to each high-power terminal can be obtained.

[0047] S102. Input electrical parameters, environmental parameters, and temperature distribution data into a preset neural network model. The preset neural network model obtains the temperature change trend of high-power terminals and the probability of overheating within a preset time period based on different parameter combinations.

[0048] Optionally, before inputting the preset neural network model, the collected electrical parameters, environmental parameters, and temperature distribution data can be preprocessed, such as denoising, normalizing, and aligning timestamps on the raw data. In this embodiment, since there are two types of sensors, spatiotemporal fusion of the data collected by the multi-parameter fusion sensor and the distributed fiber optic sensor is also required. Specifically, the data can be organized according to the location information of each sensor and the timestamp of the collected data. This allows for the acquisition of data from the surrounding area of ​​each high-power terminal block and the integration of data within the same time window to ensure the accuracy of subsequent analysis.

[0049] The pre-defined neural network model is trained based on various combinations of sample data and corresponding terminal temperature data. These combinations include different combinations of sample electrical parameters, sample environmental parameters, and sample temperature distribution data. The sample electrical parameters, sample environmental parameters, and sample temperature distribution data can be data collected over historical time periods. This data can also carry timestamp information, allowing for the labeling of the corresponding terminal temperatures based on the recorded information at that time. Furthermore, it can be further labeled with the scene or operating condition at that time.

[0050] Because the power environment is complex and involves many parameters, the training process considers not only all sample data but also different combinations of sample data. For example, {terminal temperature, current flowing through the terminal, voltage across the terminal, and temperature distribution data} is one combination, and {ambient humidity information, ambient temperature information, current flowing through the terminal, and voltage across the terminal} is another. This can be categorized according to the actual power environment or operating conditions. Multiple combinations of sample data can be added to the sample dataset for training. The more combinations available, the more accurate the pre-set neural network model will be, and the more scenarios and operating conditions it can adapt to. This embodiment does not impose specific limitations.

[0051] For example, the preset neural network model in the embodiments of this application can be a neural network model with learning capabilities, such as a convolutional neural network (CNN) or a multilayer perceptron (MLP), etc., without any specific limitations.

[0052] Before training, the collected sample electrical parameters, sample environmental parameters, and sample temperature distribution data are combined to obtain a large number of sample datasets with different combinations. The more combinations, the more patterns the neural network model can learn in various scenarios. Furthermore, the data in the sample datasets can be preprocessed, such as standardizing units and data formats (e.g., retaining two decimal places), etc., without specific restrictions here.

[0053] The "multiple combinations of sample data and corresponding terminal temperature data" from the sample dataset are then fed into a pre-defined neural network model for training. For example, this model may include an input layer, hidden layers, and an output layer. The output layer, upon receiving the sample data combinations, performs simple processing and feeds it to the hidden layer. The hidden layer, the core of the entire neural network model, learns the complex patterns between the various sample data combinations and the terminal temperature data. Finally, the output layer outputs the predicted results. The pre-defined neural network model can employ different feature extractors for different data combinations; no specific limitations are specified here. It can learn the terminal temperature data corresponding to different data combinations. Correspondingly, in subsequent use, different data combinations can be collected based on actual conditions. The pre-defined neural network model matches the input data combination with the learned data combination, further extracts features for analysis, and obtains the corresponding temperature.

[0054] The prediction results can be the temperature change trend of the high-power terminal block and the probability of overheating within a future preset time period. More specifically, the preset neural network model can output a large number of temperature values ​​and corresponding probabilities based on learning. By further organizing the predicted timeline, the temperature change trend of the high-power terminal block and the probability of overheating within the future preset time period can be obtained.

[0055] In this embodiment, electrical and environmental parameters are acquired through multi-parameter fusion sensors, and temperature distribution data is acquired through distributed fiber optic sensors. The electrical parameters, environmental parameters, and temperature distribution data are input into a preset neural network model. This preset neural network model obtains the temperature change trend of high-power terminals and the probability of overheating within a preset time period based on different parameter combinations. In particular, parameters are collected from multiple dimensions and deep analysis is performed based on the preset neural network model. Furthermore, the preset neural network model is trained based on various sample data combinations and corresponding terminal temperature data, which can achieve accurate and timely overheat detection. Subsequent protective measures or problem-solving can be implemented in a timely manner based on the temperature change trend and the probability of overheating.

[0056] Figure 2 A flowchart illustrating another embodiment of this application provides a method for detecting over-temperature of high-power terminals based on a dedicated transformer acquisition terminal, as shown below. Figure 2 As shown, the above-mentioned electrical parameters, environmental parameters, and temperature distribution data are input into a preset neural network model. This preset neural network model obtains the temperature change trend of high-power terminals and the probability of overheating within a preset time period based on different parameter combinations, including:

[0057] S201. The current health status of high-power terminals is obtained and evaluated based on different parameter combinations using a preset neural network model.

[0058] S202. If the current health status indicates normal, the preset neural network model outputs the temperature change trend of the high-power terminal block and the probability of overheating within a future preset time period based on different parameter combinations and historical data stored for a preset time period.

[0059] It should be noted that, in order to detect problems with high-power terminals more promptly, an assessment can be conducted in two steps. The first step is to assess the current health status of the high-power terminals. Specifically, based on the above parameter combination, information such as ambient humidity, ambient temperature, and terminal temperature can be obtained to determine whether the current ambient temperature exceeds the normal range, whether the current terminal temperature exceeds the normal terminal temperature (it may not have reached overheating), and whether the current ambient humidity does not conform to the normal humidity range. If any of these problems occur, the current health status of the high-power terminals can be considered abnormal, and feedback can be provided directly.

[0060] If the initial assessment indicates that the current health status is normal, further analysis is conducted based on different parameter combinations and stored historical data for a preset time period to obtain the temperature change trend of the high-power terminal block and the probability of overheating within a future preset time period.

[0061] Accordingly, based on the above embodiments, if the current health status indicates a health warning, and / or the temperature change trend is abnormal and the probability of overheating is greater than a preset probability, then a warning message is sent to the remote terminal and an alarm is activated.

[0062] In other words, the first step is to send a warning message to the remote terminal if the current health status indicates a health warning. For example, if the high-power terminal is currently in an unhealthy state based on parameters such as ambient humidity, ambient temperature, and terminal temperature, a warning message can be sent to the remote terminal. For example, a text message can be sent to the remote terminal to indicate that the current health status is at risk, so as to attract the attention of technicians. In addition, the dedicated transformer data acquisition terminal itself can also activate an alarm, such as an alarm light or an alarm sound. There are no specific restrictions here.

[0063] The second step, in the scenario where the current health status indicates normal, further if the temperature change trend is abnormal and / or the probability of overheating is greater than the preset probability, then, as above, a warning message is also sent to the remote terminal, and the dedicated transformer data acquisition terminal itself can also activate the alarm.

[0064] It should be noted that an abnormal temperature change trend can refer to a temperature rise trend that is greater than the normal trend, or a temperature rise rate that is greater than the normal rate. Specifically, the temperature change trend can be displayed by a temperature change curve, and the curvature of the temperature change curve can be used to determine whether the temperature rise trend is greater than the normal trend.

[0065] Optionally, the aforementioned monitoring and early warning, as well as the judgment of abnormal temperature change trends and / or the probability of overheating being greater than the preset probability, should also take into account the different thresholds corresponding to different operating conditions. During the training of the preset neural network model, multiple sample data combinations and corresponding terminal temperature data can also be labeled with the corresponding operating conditions, so that the results obtained are more accurate.

[0066] Furthermore, to facilitate technical personnel in preparing different emergency plans for different warnings, this embodiment of the application can classify the warning situation. Optionally, the above-mentioned warning information includes multiple levels of warning information:

[0067] A Level 1 warning includes: the temperature trend is upward within a preset time period, and the rate of increase is within a preset range;

[0068] Level 2 warning includes: the current temperature is higher than the normal operating temperature but lower than the overheating temperature, and the probability of overheating occurring within a preset time period is greater than the preset probability;

[0069] Level 3 warning includes: the current temperature is higher than the over-temperature temperature.

[0070] It should be noted that the higher the level, the more serious the situation. A Level 1 warning can attract the attention of technical personnel, who will monitor the temperature rise in real time over a period of time and take immediate emergency measures once overheating occurs. The temperature change trend can be displayed through a temperature change curve. The rate of increase can represent the temperature rise per unit time, such as 0.3 degrees Celsius per minute, or it can be represented by the curvature of the temperature change curve; there are no restrictions here.

[0071] When a Level 2 warning occurs, staff need to further investigate the cause of the temperature rise and take appropriate measures to troubleshoot the problem. For example, they should consider whether there is a short circuit, terminal deformation, or foreign object intrusion, and address these issues accordingly.

[0072] Level 3 warning is the most severe, indicating that overheating has occurred and power must be cut off immediately. Then, the cause of the fault should be further determined and eliminated.

[0073] Furthermore, after outputting the temperature change trend of the high-power terminal block and the probability of overheating within a future preset time period, the cause of overheating is analyzed and obtained based on the temperature change trend of the high-power terminal block and the probability of overheating within the future preset time period, as well as the preset analysis model.

[0074] The preset analysis model can be trained based on the temperature change trend over a historical period and the corresponding over-temperature faults and causes.

[0075] Optionally, overtemperature causes can include any of the following: poor contact, overload, abnormal ambient temperature, etc. However, these are not limited to these; other causes include foreign object intrusion, terminal deformation, short circuit, component damage, etc. Recording and storing temperature change trends over a historical period, and recording the corresponding cause when an overtemperature fault occurs, serves as sample data for subsequent model training. Furthermore, when overtemperature occurs again, the corresponding cause is recorded as an update to the sample data. This allows for periodic model optimization, making the analysis results of the preset analysis model more accurate.

[0076] The sample data can also be labeled with the operating conditions at the time corresponding to the temperature change trend. The temperature change trend will be different for different operating conditions.

[0077] Optionally, the preset analysis model here can also be a convolutional neural network, a multilayer perceptron, etc., without specific limitations. The preset analysis model can output the probability corresponding to different causes of overtemperature, or directly output the final determined result based on the analysis probability, without specific limitations.

[0078] Furthermore, in this embodiment, sensor wear and tear in the working environment can be further considered. In power scenarios, high temperatures or other abnormal environments may sometimes cause sensor malfunction or inaccurate monitoring data. Therefore, sensor abnormalities can be detected in a timely manner based on the data submitted by the sensor.

[0079] Optionally, if it is detected that the data monitored by the target sensor in the above-mentioned multi-parameter fusion sensor or distributed optical fiber sensor deviates from the data monitored by other surrounding sensors by a value greater than a preset value, then the target sensor is determined to be a faulty sensor, and the data monitored by the faulty sensor is removed.

[0080] In the scenario described in this application, the distance between the multi-parameter fusion sensors and distributed fiber optic sensors deployed for high-power terminals is not very far. Therefore, the data difference between adjacent sensors is not very large, such as temperature and humidity data. If the data from one of the multiple sensors within a preset distance deviates from the data from other sensors by a preset value, then that sensor can be identified as a faulty sensor, and its collected data cannot be adopted to avoid inaccurate impact on the evaluation results.

[0081] Based on the above embodiments, after removing the data monitored by the faulty sensor, to avoid disrupting the continuity and completeness of the monitoring data, data collected by nearby sensors can be used to supplement it. Optionally, after determining that the target sensor is a faulty sensor and removing the data monitored by the faulty sensor, the method further includes:

[0082] Based on the location information of the multi-parameter fusion sensor and the distributed fiber optic sensor, the data of the N nearest sensors to the faulty sensor are obtained, and an interpolation algorithm is used to calculate the replacement data of the faulty sensor. Here, N is an integer greater than 0. Specifically, N is a preset parameter; for example, it can be set to obtain the data of the 3 nearest sensors to the faulty sensor and use an interpolation algorithm to calculate the replacement data of the faulty sensor. No limitation is imposed here.

[0083] When deploying the aforementioned multi-parameter fusion sensors and distributed fiber optic sensors, a coordinate system can be established and the position information of each sensor can be recorded. This facilitates the subsequent positioning of each sensor and also helps to fill in missing or faulty data.

[0084] Figure 3 This is a schematic diagram of a high-power terminal over-temperature detection device based on a dedicated transformer data acquisition terminal, provided in an embodiment of this application. The device is applied to the controller of the dedicated transformer data acquisition terminal. Multiple multi-parameter fusion sensors and distributed fiber optic sensors are arranged around the high-power terminal inside the dedicated transformer data acquisition terminal. Both the multi-parameter fusion sensors and the distributed fiber optic sensors are communicatively connected to the controller. Figure 3 As shown, the device includes:

[0085] The acquisition module 301 is used to acquire electrical parameters and environmental parameters through the multi-parameter fusion sensor and to acquire temperature distribution data through the distributed optical fiber sensor; wherein, the electrical parameters include: terminal temperature, current flowing through the terminal, voltage across the terminal, and terminal vibration parameters; the environmental parameters include: ambient humidity information and ambient temperature information;

[0086] The analysis module 302 is used to input the electrical parameters, the environmental parameters, and the temperature distribution data into a preset neural network model. The preset neural network model obtains the temperature change trend of the high-power terminal block and the probability of overheating within a preset time period based on different parameter combinations. The preset neural network model is trained based on multiple sample data combinations and corresponding terminal block temperature data. The multiple sample data combinations include different combinations of sample electrical parameters, sample environmental parameters, and sample temperature distribution data.

[0087] Optionally, the analysis module 302 is specifically used to obtain and evaluate the current health status of the high-power terminal block based on different parameter combinations through the preset neural network model; if the current health status indicates normal, the preset neural network model outputs the temperature change trend of the high-power terminal block and the probability of overheating within a future preset time period based on different parameter combinations and historical data stored in a preset time period.

[0088] Optionally, the analysis module 302 is further configured to send a warning message to a remote terminal and activate an alarm if the current health status indicates a health warning, and / or if the temperature change trend is abnormal or the probability of overheating is greater than a preset probability.

[0089] Optionally, the warning information includes multiple levels of warning information:

[0090] A Level 1 warning includes: the temperature trend is upward within a preset time period, and the rate of increase is within a preset range;

[0091] Level 2 warning includes: the current temperature is higher than the normal operating temperature but lower than the overheating temperature, and the probability of overheating occurring within a preset time period is greater than the preset probability;

[0092] Level 3 warning includes: the current temperature is higher than the over-temperature temperature.

[0093] Optionally, the analysis module 302 is further configured to analyze and obtain the cause of overheating based on the temperature change trend of the high-power terminal block and the probability of overheating within a future preset time period, as well as a preset analysis model. The preset analysis model is trained and obtained based on the temperature change trend of historical time periods and the corresponding overheating faults and causes. The causes of overheating include any of the following: poor contact, overload, and abnormal ambient temperature.

[0094] Optionally, the acquisition module 301 is further configured to determine that the target sensor is a faulty sensor and remove the data monitored by the faulty sensor if the deviation between the data monitored by the target sensor and the data monitored by other surrounding sensors in the multi-parameter fusion sensor and the distributed optical fiber sensor is greater than a preset value.

[0095] Optionally, the analysis module 302 is further configured to obtain the data of the N nearest sensors to the faulty sensor based on the location information of the multi-parameter fusion sensor and the distributed optical fiber sensor, and to calculate the alternative data of the faulty sensor using an interpolation algorithm, wherein N is an integer greater than 0.

[0096] Since the principle of the device in this application embodiment to solve the problem is similar to the method described above in this application embodiment, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0097] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0098] Figure 4 This is a schematic diagram of the structure of a dedicated transformer data acquisition terminal provided in an embodiment of this application, as shown below. Figure 4 As shown, the dedicated transformer data acquisition terminal includes: a processor 401, a memory 402, and optionally, a bus 403.

[0099] The memory 402 stores machine-readable instructions that can be executed by the processor 401. When the dedicated transformer data acquisition terminal is running, the processor 401 executes the machine-readable instructions to perform the above-mentioned high-power terminal over-temperature detection method based on the dedicated transformer data acquisition terminal.

[0100] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the above-described method for detecting over-temperature of high-power terminals based on a dedicated transformer acquisition terminal.

[0101] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0102] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the 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 a part of the technical solution, can be embodied in the form of a software product. This 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: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0103] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for detecting over-temperature of a high-power terminal based on a special variable acquisition terminal, characterized in that, The application relates to a controller applied to a special transformer collection terminal, wherein a plurality of multi-parameter fusion sensors and distributed optical fiber sensors are arranged on the periphery of a high-power terminal in the special transformer collection terminal, the multi-parameter fusion sensors and the distributed optical fiber sensors are in communication connection with the controller, and the method comprises the following steps: Electric appliance parameters and environmental parameters are collected by the multi-parameter fusion sensors, and temperature distribution data are collected by the distributed optical fiber sensors; wherein the electric appliance parameters include the temperature of a terminal, the current flowing through the terminal, the voltage between the terminal, and the vibration parameters of the terminal; and the environmental parameters include environmental humidity information and environmental temperature information; The electric appliance parameters, the environmental parameters and the temperature distribution data are input into a preset neural network model, the preset neural network model obtains the temperature change trend of the high-power terminal and the probability of over-temperature in a future preset time period according to different parameter combinations, wherein the preset neural network model is obtained by training according to a plurality of sample data combinations and corresponding terminal temperature data, and the plurality of sample data combinations include different combinations of sample electric appliance parameters, sample environmental parameters and sample temperature distribution data; The preset neural network model obtains the temperature change trend of the high-power terminal and the probability of over-temperature in a future preset time period according to different parameter combinations, which comprises the following steps: The current health state of the high-power terminal is evaluated according to different parameter combinations by the preset neural network model; If the current health state is normal, the preset neural network model outputs the temperature change trend of the high-power terminal and the probability of over-temperature in a future preset time period according to different parameter combinations and stored historical data of the preset time period.

2. The method of claim 1, wherein, The method further comprises the following steps: If the current health state indicates a health warning, and / or the temperature change trend is abnormal and the probability of over-temperature is greater than a preset probability, warning information is sent to a remote terminal and an alarm is started.

3. The method of claim 2, wherein, The warning information comprises a plurality of levels of warning information: The first-level warning comprises that the temperature change trend in a future preset time period is an upward trend, and the rising speed is within a preset speed range; The second-level warning comprises that the current temperature is greater than a normal operating temperature and less than an over-temperature temperature, and the probability of over-temperature in a future preset time period is greater than a preset probability; The third-level warning comprises that the current temperature is greater than the over-temperature temperature.

4. The method of claim 1, wherein, After the temperature change trend of the high-power terminal and the probability of over-temperature in a future preset time period are output, the following step is further included: According to the temperature change trend of the high-power terminal and the probability of over-temperature in a future preset time period, and a preset analysis model, the cause of over-temperature is analyzed and obtained, wherein the preset analysis model is obtained by training according to the temperature change trend of a historical time period and corresponding over-temperature faults and over-temperature causes, and the over-temperature causes include any one of the following: poor contact, overload and abnormal environmental temperature.

5. The method of claim 1, wherein, The method further comprises the following steps: If it is detected that the data monitored by the target sensor deviates from the data monitored by the surrounding sensors by more than a preset value, the target sensor is determined to be a faulty sensor, and the data monitored by the faulty sensor is excluded.

6. The method of claim 5, wherein, After determining that the target sensor is a faulty sensor and excluding the data monitored by the faulty sensor, the method further includes: According to the position information of the multi-parameter fusion sensor and the distributed optical fiber sensor, N sensor data closest to the faulty sensor are obtained, and an interpolation algorithm is used to calculate the replacement data of the faulty sensor, where N is an integer greater than 0.

7. A high-power terminal over-temperature detection device based on a special variable acquisition terminal, characterized in that, The controller is applied to a special transformer collection terminal, a plurality of multi-parameter fusion sensors and distributed optical fiber sensors are arranged outside the periphery of a high-power terminal in the special transformer collection terminal, the multi-parameter fusion sensors and the distributed optical fiber sensors are in communication connection with the controller, and the device includes: The acquisition module is configured to acquire electric appliance parameters and environmental parameters through the multi-parameter fusion sensors and temperature distribution data through the distributed optical fiber sensors; wherein the electric appliance parameters include the temperature of the terminal, the current flowing through the terminal, the voltage across the terminal, and the vibration parameter of the terminal; and the environmental parameters include environmental humidity information and environmental temperature information. The analysis module is configured to input the electric appliance parameters, the environmental parameters, and the temperature distribution data into a preset neural network model, and the preset neural network model is configured to obtain the temperature change trend of the high-power terminal and the probability of over-temperature in a future preset time period according to different parameter combinations, wherein the preset neural network model is obtained by training according to a plurality of sample data combinations and corresponding terminal temperature data, and the plurality of sample data combinations include different combinations of sample electric appliance parameters, sample environmental parameters, and sample temperature distribution data. The analysis module is specifically configured to evaluate the current health status of the high-power terminal according to different parameter combinations by using the preset neural network model; if the current health status indicates normal, the preset neural network model outputs the temperature change trend of the high-power terminal and the probability of over-temperature in a future preset time period according to different parameter combinations and stored historical data of the preset time period.

8. A special variable acquisition terminal, characterized by, The device includes: A processor and a memory, the memory stores machine readable instructions executable by the processor, when the special transformer collection terminal is running, the processor executes the machine readable instructions to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to perform the method of any one of claims 1 to 6.

Images