Transformer fault inspection system and method based on multiple sensors

Abstract

The invention relates to the technical field of electric power, in particular to a transformer fault inspection system and method based on multiple sensors, and the system comprises a first collection module, a temporary determination module, a second collection module, an overheating judgment module, a fault determination module, an adjustment module and an early warning module. Through real-time acquisition and comprehensive analysis of multi-dimensional data such as the flow velocity of transformer cooling oil, acetylene content, winding temperature, direct-current resistance and copper loss value, faults are rapidly positioned, detection parameters are dynamically adjusted, early warning is given out in time, the accuracy and efficiency of fault detection are improved, the operation and maintenance cost and the safety risk are reduced, and the fault detection efficiency is improved. The adaptability and stability of the system in a complex environment are enhanced, a powerful guarantee is provided for reliable operation of power equipment, and the problems of inaccurate fault diagnosis and response delay caused by a high-altitude extreme environment in the prior art are solved through multi-parameter monitoring, dynamic threshold adjustment and routing inspection path optimization.

Description

Technical Field

[0001] The present invention relates to the field of power technology, and in particular, to a transformer fault inspection system and method based on multi-sensors. Background Art

[0002] With the continuous growth of global energy demand and the rapid development of power systems, power transformers, as the core equipment for power transmission and distribution, their safe and stable operation is crucial for ensuring social production and life. However, in high-altitude areas with complex environments, transformers face many challenges. In high-altitude areas, the air is thin, the air pressure is low, the insulation performance decreases, and the transformer is prone to faults such as partial discharge. At the same time, in high-altitude areas, the temperature difference between day and night is large, the ultraviolet rays are strong, and the wind and sand are large. These harsh natural environmental factors will affect the insulation materials, sealing performance, etc. of the transformer, accelerate equipment aging, and increase the risk of faults. In addition, in high-altitude areas, the transportation is inconvenient, the manual inspection is difficult, inefficient, and there are certain safety risks. Therefore, it is particularly important to develop a system and method that can efficiently and accurately perform transformer fault inspection in extreme high-altitude environments.

[0003] The patent document with the publication number CN114264982A discloses a transformer inspection system, which includes: a plurality of state sensors and an inspection management platform; the inspection management platform is used to control the transformer inspection system to operate in the first inspection mode; wherein, in the first inspection mode, each state sensor respectively collects the operation state information of the target transformer at its corresponding sampling period and sends it to the inspection management platform; the inspection management platform judges whether the operation state information collected by each state sensor is abnormal. If the operation state information collected by a certain state sensor is abnormal, then control the transformer inspection system to operate in the second inspection mode; wherein, in the second inspection mode, the abnormal state sensor and the state sensors related to the abnormal state sensor synchronously collect the operation state information of the target transformer and send it to the inspection management platform, so that the inspection management platform can perform fault analysis on the target transformer.

[0004] It can be seen that the transformer inspection system has the following problems: in high-altitude and extreme environments, the data of a single sensor will be interfered by the environment, resulting in insufficient data specificity; the lack of multi-module collaborative analysis and low data fusion degree make it difficult to comprehensively reflect the operation state of the transformer; it is necessary to process data from different sources and in different formats, which increases the complexity of data processing and the computing burden; the communication signal in high-altitude areas is weak, and the data transmission between the sensor and the inspection management platform may be interfered, resulting in signal attenuation or interruption, leading to data transmission delay and affecting the real-time judgment of faults by the inspection management platform. Summary of the Invention

[0005] To this end, the present invention provides a transformer fault inspection system and method based on multi-sensors, which are used to overcome the problems of inaccurate fault diagnosis and response delay caused by high-altitude extreme environments in the prior art through multi-parameter monitoring, dynamically adjusting thresholds, and optimizing inspection paths.

[0006] To achieve the above object, on the one hand, the present invention provides a transformer fault inspection system based on multi-sensors, including: A first acquisition module, which is used to collect the temperature of the windings of each transformer to be measured set in the monitoring area in real time, and to collect the flow rate and acetylene content of the cooling oil in the cooling system of each transformer to be measured in the monitoring area in real time through an inspection device provided with multi-sensors; A temporary determination module, which is connected to the first acquisition module, and is used to determine a number of temporary transformers according to the flow rate, the temperature, and a preset synchronization threshold; A second acquisition module, which is connected to the temporary determination module, and is used to collect the DC resistance and copper loss values of the windings of each temporary transformer in real time along a temporary inspection route formed based on all the temporary transformers; An overheat determination module, which is respectively connected to the temporary determination module and the second acquisition module, and is used to determine a number of overheated transformers according to the DC resistance and the copper loss values; A fault determination module, which is respectively connected to the overheat determination module and the first acquisition module, and is used to determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and the acetylene content, and to determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and a preset radius; An adjustment module, which is connected to the fault determination module, and is used to adjust the preset synchronization threshold according to the number of the faulty transformers to form an adjusted synchronization threshold; An early warning module, which is respectively connected to the fault determination module and the adjustment module, and is used to issue an early warning according to the faulty transformers determined based on the adjusted synchronization threshold.

[0007] Further, the temporary determination module includes: A temperature fluctuation calculation unit, which is used to calculate the standard deviation of the temperature within a preset determination duration to form a temperature fluctuation value; A flow rate fluctuation calculation unit, which is used to calculate the standard deviation of the flow rate within the preset determination duration to form a flow rate fluctuation value; A temporary determination unit, which is respectively connected to the temperature fluctuation calculation unit and the flow rate fluctuation calculation unit, and is used to determine a number of temporary transformers according to the temperature fluctuation value and the flow rate fluctuation value.

[0008] Further, the temporary determination unit includes: A temperature fluctuation curve plotting subunit, configured to plot a change curve of the temperature fluctuation value within the preset determined duration to form a temperature fluctuation curve; A flow rate fluctuation curve plotting subunit, configured to plot a change curve of the flow rate fluctuation value within the preset determined duration to form a flow rate fluctuation curve; A synchronization degree calculation subunit, which is respectively connected to the temperature fluctuation curve plotting subunit and the flow rate fluctuation curve plotting subunit, and is configured to calculate the cosine similarity between the temperature fluctuation curve and the flow rate fluctuation curve to form a change synchronization degree; A temporary determination subunit, which is connected to the synchronization degree calculation subunit, and is configured to determine the transformer to be tested as the temporary transformer when the change synchronization degree is less than the preset synchronization degree threshold, so as to determine a plurality of the temporary transformers.

[0009] Further, the overheating determination module includes: A correlation coefficient calculation unit, configured to calculate the correlation coefficient between the DC resistance and the copper loss value within the preset determination duration to form a correlation coefficient; A determination unit, which is connected to the correlation coefficient calculation unit, and is configured to determine the temporary transformer as the overheating transformer according to the correlation coefficient and the preset correlation coefficient threshold to form a plurality of overheating transformers.

[0010] Further, the determination unit includes: A coefficient comparison subunit, configured to compare the correlation coefficient and the preset correlation coefficient threshold to form a coefficient comparison result; A determination subunit, which is connected to the coefficient comparison subunit, and is configured to determine the temporary transformer as the overheating transformer when the coefficient comparison result is that the correlation coefficient is greater than the preset correlation coefficient threshold to form a plurality of overheating transformers.

[0011] Further, the fault determination module includes: A first fault determination unit, configured to determine all the transformers within the circular area with a preset radius adjacent to the overheating transformer as fault transformers when the distance is less than the minimum value of the preset distance range, so as to determine a plurality of fault transformers; A second fault determination unit, configured to determine a plurality of fault transformers according to the acetylene content of each transformer to be tested within a preset determination range in the temporary inspection route between the adjacent overheating transformers when the distance is greater than the maximum value of the preset distance range.

[0012] Further, the second fault determination unit includes: An acetylene content fluctuation calculation subunit, configured to calculate the standard deviation of the acetylene content of the overheating transformer and each transformer to be tested respectively to form an acetylene content fluctuation value; A second fault determination subunit, connected to the acetylene content fluctuation calculation subunit, is configured to determine that both the overheated transformer and the transformer under test are faulty transformers when the acetylene content fluctuation value is less than a preset acetylene content fluctuation threshold; and determine that only the overheated transformer is a faulty transformer when the acetylene content fluctuation value is greater than or equal to the preset acetylene content fluctuation threshold.

[0013] Further, the adjustment module includes: A quantity fluctuation calculation unit, configured to calculate the standard deviation of the number of faulty transformers within a preset adjustment duration to form a quantity fluctuation value; An adjustment unit, connected to the quantity fluctuation calculation unit, is configured to adjust the preset synchronization threshold according to the quantity fluctuation value to form an adjusted synchronization threshold.

[0014] Further, the adjustment unit includes: A quantity fluctuation deviation calculation subunit, configured to calculate the relative deviation between the quantity fluctuation value and a preset quantity fluctuation threshold to form a quantity fluctuation deviation when the quantity fluctuation value is greater than the preset quantity fluctuation threshold; An adjustment subunit, connected to the quantity fluctuation deviation calculation subunit, is configured to increase the preset synchronization threshold according to the quantity fluctuation deviation and a preset adjustment coefficient to form an adjusted synchronization threshold when the quantity fluctuation deviation is greater than a preset quantity fluctuation deviation threshold.

[0015] On the other hand, the present invention also provides a multi-sensor-based transformer fault inspection method, including: Real-time collecting the temperature of the windings of each transformer under test arranged in the monitoring area, and real-time collecting the flow rate and acetylene content of the cooling oil in the cooling system of each transformer under test in the monitoring area through an inspection device provided with multi-sensors; Determining a number of temporary transformers according to the flow rate, the temperature, and a preset synchronization threshold; Real-time collecting the DC resistance and copper loss value of the windings of each temporary transformer along a temporary inspection route formed based on all the temporary transformers; Determining a number of overheated transformers according to the DC resistance and the copper loss value; Determining a number of faulty transformers according to the distance between any two adjacent overheated transformers and the acetylene content, and determining a number of faulty transformers according to the distance between any two adjacent overheated transformers and a preset radius; Adjusting the preset synchronization threshold according to the number of faulty transformers to form an adjusted synchronization threshold; Issuing a warning according to the faulty transformers determined based on the adjusted synchronization threshold.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows. By collecting and comprehensively analyzing multi-dimensional data such as the flow rate of the transformer cooling oil, the acetylene content, the temperature of the winding, the DC resistance, and the copper loss value in real time, faults can be quickly located, detection parameters can be dynamically adjusted, and early warnings can be issued in a timely manner. This improves the accuracy and efficiency of fault detection, reduces operation and maintenance costs and safety risks, enhances the adaptability and stability of the system in complex environments, and provides a strong guarantee for the reliable operation of power equipment. By monitoring multiple parameters, dynamically adjusting thresholds, and optimizing the inspection path, the problems of inaccurate fault diagnosis and response delay caused by extreme high-altitude environments in the prior art are overcome.

[0017] Furthermore, by calculating the temperature fluctuation value and the flow rate fluctuation value within a preset determination period and screening out temporary transformers based on this, transformers that may have faults can be quickly identified, providing a preliminary screening result for subsequent fault diagnosis, improving the detection efficiency and accuracy of the system, and reducing unnecessary detection workload.

[0018] Furthermore, by plotting the temperature fluctuation curve and the flow rate fluctuation curve within a preset determination period and calculating the cosine similarity between the two to form a change synchronization degree, the correlation between the temperature change and the flow rate change of the transformer can be effectively evaluated. When the change synchronization degree is lower than the preset synchronization degree threshold, the system marks the transformer to be tested as a temporary transformer, providing a basis for further detection, improving the accuracy of fault detection, reducing the false alarm rate, optimizing the monitoring resource allocation, improving the monitoring efficiency, and reducing the operation and maintenance costs. At the same time, the visualization curve provides intuitive data support for the operation and maintenance personnel, facilitating the quick understanding and analysis of the operation status of the transformer, enhancing the versatility and adaptability of the system, and providing a strong guarantee for the stable operation of the power system.

[0019] Furthermore, by calculating the correlation coefficient of the DC resistance and the copper loss value and making a determination in combination with a preset threshold, overheated transformers can be effectively identified, significantly improving the accuracy of fault diagnosis and reducing the false alarm rate. This not only optimizes the allocation of monitoring resources and improves the monitoring efficiency, but also realizes a quick response to the change of the transformer state by reasonably setting the preset determination period, and timely discovers potential faults.

[0020] Furthermore, by comparing the correlation coefficient with the preset correlation coefficient threshold, overheated transformers can be quickly and accurately identified, greatly improving the accuracy and efficiency of fault diagnosis, effectively reducing false alarms, avoiding misjudgment caused by single-parameter detection, quickly responding to abnormal changes in the transformer state, timely capturing overheating faults, and reducing the risk of fault expansion.

[0021] Furthermore, by setting a preset distance range and a preset radius, faulty transformers can be effectively identified and determined, significantly improving the accuracy and efficiency of fault diagnosis. When the distance between adjacent overheated transformers is less than the minimum value of the preset distance range, all transformers within the preset radius are determined as faulty transformers; when the distance between adjacent overheated transformers is greater than the maximum value of the preset distance range, based on the acetylene content of each transformer to be tested within the preset determination range in the temporary inspection route between the adjacent overheated transformers, the faulty transformers are further determined, thus comprehensively covering potential fault areas and avoiding missing fault points.

[0022] Furthermore, by calculating the standard deviation of the acetylene content of the overheated transformer and the transformer to be tested to form an acetylene content fluctuation value and comparing it with a preset acetylene content fluctuation threshold, faulty transformers and normal transformers can be effectively distinguished. When the fluctuation value is less than the preset threshold, it indicates that the acetylene content of the transformer to be tested is close to that of the overheated transformer, and the system determines both as faulty transformers; when the fluctuation value is greater than or equal to the preset threshold, it indicates that the acetylene content of the transformer to be tested is quite different from that of the overheated transformer, and only the overheated transformer is determined as a faulty transformer, improving the accuracy and reliability of fault diagnosis, reducing the false alarm rate, optimizing the allocation of monitoring resources at the same time, and improving the operation and maintenance efficiency, providing a strong guarantee for the stable operation of the power system.

[0023] Furthermore, by calculating the standard deviation of the number of faulty transformers within a preset adjustment duration to form a number fluctuation value and adjusting the preset synchronization threshold accordingly, the system can dynamically optimize the detection parameters according to the change in the number of faults, thereby improving the adaptability and reliability of the system. It not only enhances the stability of the system under different working conditions but also can respond in a timely manner to the change in the number of faults to ensure the accuracy of fault diagnosis.

[0024] Furthermore, by calculating the number fluctuation deviation and dynamically adjusting the preset synchronization threshold accordingly, the system can automatically optimize the detection parameters according to the change in the number of faults, improving the adaptability and reliability of the system, enabling it to better meet the fault detection requirements under different working conditions. At the same time, dynamically adjusting the threshold can reduce the false alarm rate, ensure the accuracy of fault diagnosis, optimize the allocation of monitoring resources, and improve the operation and maintenance efficiency, providing a more powerful guarantee for the stable operation of the power system.

[0025] Furthermore, by using multiple sensors to collect the key operating parameters of the transformer in real time and combining with preset thresholds and dynamic adjustment mechanisms, efficient monitoring and early warning of transformer faults are realized; the accuracy and reliability of fault diagnosis are improved, the false alarm rate is reduced, the allocation of monitoring resources is optimized, and the operation and maintenance costs are reduced; by multi-parameter monitoring, dynamically adjusting thresholds, and optimizing the inspection path, the problems of inaccurate fault diagnosis and response delay caused by extreme high-altitude environments in the existing technology are overcome. Description of the Drawings

[0026] Figure 1 This is a schematic diagram of the transformer fault inspection system based on multi - sensors in this embodiment; Figure 2 This is a decision logic diagram for the temporary determination unit in this embodiment to determine the temporary transformer; Figure 3 This is a decision logic diagram for the determination unit in this embodiment to determine the overheated transformer; Figure 4 This is a flowchart of the transformer fault inspection method based on multi - sensors in this embodiment. Detailed Embodiments

[0027] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0028] The preferred embodiments of the present invention will be described below with reference to the drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0029] On the one hand, please refer to Figure 1 as shown, which is a schematic diagram of the transformer fault inspection system based on multi - sensors in this embodiment; This embodiment provides a transformer fault inspection system based on multi - sensors, which is characterized by including: A first acquisition module, which is used to collect in real time the temperature of the windings of each transformer to be measured arranged in the monitoring area, and to collect in real time the flow rate and acetylene content of the cooling oil in the cooling system of each transformer to be measured in the monitoring area through an inspection device equipped with multi - sensors; A temporary determination module, which is connected to the first acquisition module and is used to determine a number of temporary transformers according to the flow rate, the temperature and a preset synchronization threshold; A second acquisition module, which is connected to the temporary determination module and is used to collect in real time the DC resistance and copper loss values of the windings of each temporary transformer along a temporary inspection route formed based on all the temporary transformers; An overheat determination module, which is respectively connected to the temporary determination module and the second acquisition module and is used to determine a number of overheated transformers according to the DC resistance and the copper loss values; A fault determination module, which is respectively connected to the overheat determination module and the first acquisition module and is used to determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and the acetylene content, and to determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and a preset radius; An adjustment module, which is connected to the fault determination module and is used to adjust the preset synchronization threshold according to the number of faulty transformers to form an adjusted synchronization threshold; An early warning module, which is respectively connected to the fault determination module and the adjustment module, and is used to give an early warning according to the faulty transformers determined based on the adjusted synchronization threshold.

[0030] In this embodiment, the inspection device equipped with multiple sensors refers to an inspection robot equipped with sensors such as ultrasonic sensors, acetylene sensors, and current sensors.

[0031] The monitoring area refers to an area located in a high-altitude region that covers all transformers to be monitored.

[0032] The flow rate refers to the flow velocity of the cooling oil in the transformer cooling system. The ultrasonic sensor can be used to measure the time difference between the forward and reverse propagation of ultrasonic waves in the oil flow, so as to calculate the actual flow velocity of the cooling oil.

[0033] The acetylene content refers to the concentration of acetylene gas dissolved in the transformer cooling oil. A professional acetylene sensor can be used to directly detect the acetylene content.

[0034] The temperature of the winding refers to the actual temperature of the transformer winding during operation. Fiber optic temperature sensors are embedded at key positions of the transformer winding, and the temperature distribution on the surface of the winding is obtained through the fiber optic temperature sensors.

[0035] The DC resistance refers to the resistance value of the transformer winding under DC conditions. The cold resistance of each transformer can be pre-stored, and the real-time DC resistance can be calculated according to the cold resistance, temperature coefficient, and real-time winding temperature.

[0036] The copper loss value refers to the heat loss generated in the transformer winding due to the passage of current. It can be calculated by measuring the current in the winding with a current sensor and the DC resistance calculated through the cold resistance and temperature coefficient using a formula.

[0037] The preset synchronization threshold is a key parameter for judging the synchronization of the temperature fluctuation curve and the flow rate fluctuation curve. When the change synchronization degree is lower than this threshold, it indicates that the transformer may be abnormal. It depends on the operating characteristics of the transformer, the statistical analysis of historical data, and the requirements for the sensitivity of fault detection. Usually, it is set between 0.5 and 0.8. In this embodiment, it is set to 0.7, which can effectively reduce false alarms while timely detecting abnormal situations where the temperature and flow rate change out of sync, improving the accuracy and reliability of fault detection.

[0038] The inspection route is optimized and generated by computer algorithms based on the location information of the transformers. The system will use the precise location information of the transformers and then calculate an optimal path that can cover all the transformers using the shortest path algorithm. This path will be optimized through multiple iterations to ensure that its total length is the shortest and it meets the actual inspection conditions.

[0039] The preset radius is a key parameter used to determine the range of potentially affected transformers within a circular area centered on the overheated transformer, usually set between 2 meters and 4 meters. In this embodiment, it is set to 3 meters, which can effectively cover the potential fault areas around the overheated transformer, ensuring the comprehensiveness and accuracy of fault diagnosis. At the same time, it avoids over-expanding the fault range and reduces the false alarm rate.

[0040] By real-time collecting the flow rate of the cooling oil, the acetylene content, and the temperature of the winding of the transformer, determining the temporary transformers according to the preset thresholds, and collecting the DC resistance and copper loss values along the temporary inspection route, the overheated transformer is further determined. Then, combining the distance and acetylene content of the overheated transformer to determine the faulty transformers, and dynamically adjusting the thresholds according to the number of faults, and finally issuing a fault warning.

[0041] Through the real-time collection and comprehensive analysis of multi-dimensional data such as the flow rate of the transformer cooling oil, the acetylene content, the temperature of the winding, the DC resistance, and the copper loss value, quickly locate the faults, dynamically adjust the detection parameters, and issue early warnings in a timely manner, improving the accuracy and efficiency of fault detection, reducing the operation and maintenance costs and safety risks, enhancing the adaptability and stability of the system in complex environments, and providing a strong guarantee for the reliable operation of power equipment. Overcome the problems of inaccurate fault diagnosis and response delay caused by high-altitude extreme environments in the existing technology through multi-parameter monitoring, dynamic threshold adjustment, and optimized inspection paths.

[0042] Specifically, the temporary determination module includes: A temperature fluctuation calculation unit for calculating the standard deviation of the temperature within a preset determination duration to form a temperature fluctuation value; A flow rate fluctuation calculation unit for calculating the standard deviation of the flow rate within the preset determination duration to form a flow rate fluctuation value; A temporary determination unit, which is respectively connected to the temperature fluctuation calculation unit and the flow rate fluctuation calculation unit, for determining a number of temporary transformers according to the temperature fluctuation value and the flow rate fluctuation value.

[0043] The preset determination duration is the time interval used to calculate the temperature fluctuation value and the flow rate fluctuation value, which depends on the operating characteristics of the transformer, the monitoring accuracy requirements, and the data acquisition frequency, usually set between 5 minutes and 1 hour. In this embodiment, it is set to 10 minutes, which can not only ensure the sufficiency of data acquisition but also quickly respond to the changes in the transformer state and detect potential faults in a timely manner.

[0044] By calculating the standard deviation of the temperature of the winding within a preset determination time period, a temperature fluctuation value is obtained; at the same time, the standard deviation of the cooling oil flow rate is calculated to obtain a flow rate fluctuation value; subsequently, abnormal transformers are screened out based on the temperature fluctuation value and the flow rate fluctuation value, and they are marked as temporary transformers.

[0045] By calculating the temperature fluctuation value and the flow rate fluctuation value within a preset determination time period and screening out temporary transformers based on this, it is possible to quickly identify transformers that may have faults, provide preliminary screening results for subsequent fault diagnosis, improve the detection efficiency and accuracy of the system, and reduce unnecessary detection workload.

[0046] Please continue to refer to Figure 2 as shown, which is the determination logic diagram for the temporary determination unit of this embodiment to determine temporary transformers; The temporary determination unit includes: A temperature fluctuation curve drawing subunit for drawing a change curve of the temperature fluctuation value within the preset determination time period to form a temperature fluctuation curve; A flow rate fluctuation curve drawing subunit for drawing a change curve of the flow rate fluctuation value within the preset determination time period to form a flow rate fluctuation curve; A synchronization degree calculation subunit, which is respectively connected to the temperature fluctuation curve drawing subunit and the flow rate fluctuation curve drawing subunit, for calculating the cosine similarity of the temperature fluctuation curve and the flow rate fluctuation curve to form a change synchronization degree; A temporary determination subunit, which is connected to the synchronization degree calculation subunit, for determining the transformer under test as the temporary transformer when the change synchronization degree is less than a preset synchronization degree threshold to determine a number of the temporary transformers.

[0047] The preset determination time period is the time interval used by the system when calculating the temperature fluctuation value and the flow rate fluctuation value and evaluating the change synchronization degree, which depends on the operating characteristics of the transformer, the monitoring accuracy requirements, and the data acquisition frequency, and is usually set between 10 minutes and 1 hour. In this embodiment, it is set to 30 minutes, which can not only ensure the sufficiency of data acquisition but also quickly respond to the change of the transformer state and timely detect potential faults.

[0048] The preset synchronization degree threshold is a key parameter for judging the change synchronization of the temperature fluctuation curve and the flow rate fluctuation curve. When the change synchronization degree is lower than this threshold, it indicates that the transformer may be abnormal, which depends on the operating characteristics of the transformer, the statistical analysis of historical data, and the requirements for the sensitivity of fault detection, and is usually set between 0.5 and 0.8. In this embodiment, it is set to 0.7, which can effectively reduce false alarms while timely detecting abnormal situations where the temperature and flow rate change out of sync, improving the accuracy and reliability of fault detection.

[0049] By separately plotting the temperature fluctuation curve and the flow rate fluctuation curve within a preset determined duration, the changing trends of temperature and flow rate are visually presented; the change synchronization degree is calculated based on the cosine similarity of these two curves; when the change synchronization degree is lower than the preset synchronization degree threshold, the transformer to be tested is marked as a temporary transformer, thereby screening out the transformers that may have problems.

[0050] By plotting the temperature fluctuation curve and the flow rate fluctuation curve within a preset determined duration, and calculating the cosine similarity between the two to form the change synchronization degree, the correlation between the temperature change and the flow rate change of the transformer can be effectively evaluated. When the change synchronization degree is lower than the preset synchronization degree threshold, the system marks the transformer to be tested as a temporary transformer, providing a basis for further detection, improving the accuracy of fault detection, reducing the false alarm rate, optimizing the monitoring resource allocation, improving the monitoring efficiency, and reducing the operation and maintenance cost. At the same time, the visualization curve provides intuitive data support for the operation and maintenance personnel, facilitating the quick understanding and analysis of the operation state of the transformer, enhancing the universality and adaptability of the system, and providing a strong guarantee for the stable operation of the power system.

[0051] Please continue to refer to Figure 3 as shown, which is the determination logic diagram for the overheated transformer determined by the determination module of this embodiment; Specifically, the overheat determination module includes: A correlation coefficient calculation unit for calculating the correlation coefficient between the DC resistance and the copper loss value within a preset determination duration to form a correlation coefficient; A determination unit, which is connected to the correlation coefficient calculation unit, for determining the temporary transformer as the overheated transformer according to the correlation coefficient and the preset correlation coefficient threshold to form a number of overheated transformers.

[0052] The preset determination duration refers to the time interval for analyzing the relationship between the DC resistance and the copper loss value, which depends on the stability of the transformer operation data, the monitoring accuracy requirements, and the data acquisition frequency, and is usually set between 10 minutes and 1 hour. In this embodiment, it is set to 20 minutes, which can ensure that enough data points are collected to improve the accuracy of calculating the correlation coefficient, and can complete the determination in a relatively short time, so as to quickly capture the abnormal changes in the transformer state, timely detect potential overheating faults, and effectively improve the fault diagnosis efficiency and reliability of the system.

[0053] The preset correlation coefficient threshold is a key parameter for judging the strength of the correlation between the DC resistance and the copper loss value. When the calculated correlation coefficient exceeds this threshold, it indicates a significant positive correlation between the two, which may indicate overheating problems in the transformer. Depending on the statistical characteristics of the transformer operation data, the monitoring accuracy requirements, and the demand for fault detection sensitivity, it is usually set between 0.5 and 0.9. In this embodiment, it is set to 0.7, which can effectively reduce false alarms while timely detecting the significant positive correlation between the DC resistance and the copper loss value, thereby accurately identifying overheated transformers and improving the accuracy and reliability of fault detection.

[0054] By calculating the correlation coefficient of the DC resistance and the copper loss value within the preset determination duration, and then, based on the calculated correlation coefficient and the preset correlation coefficient threshold, evaluating the temporary transformer to obtain several overheated transformers.

[0055] By calculating the correlation coefficient of the DC resistance and the copper loss value and making a determination in combination with the preset threshold, it is possible to effectively identify overheated transformers, significantly improve the accuracy of fault diagnosis, reduce the false alarm rate, not only optimize the allocation of monitoring resources and improve the monitoring efficiency, but also achieve a rapid response to changes in the transformer state by reasonably setting the preset determination duration, and timely detect potential faults.

[0056] Please continue to refer to Figure 3 as shown, which is the determination logic diagram for the determination unit of this embodiment to determine overheated transformers; The determination unit includes: A coefficient comparison sub-unit for comparing the correlation coefficient with the preset correlation coefficient threshold to form a coefficient comparison result; A determination sub-unit, which is connected to the coefficient comparison sub-unit, for determining that the temporary transformer is the overheated transformer and forming several overheated transformers when the coefficient comparison result is that the correlation coefficient is greater than the preset correlation coefficient threshold.

[0057] By comparing the correlation coefficient with the preset correlation coefficient threshold, a comparison result is obtained; when the correlation coefficient is greater than the preset threshold, it indicates a significant positive correlation between the DC resistance and the copper loss value. At this time, it is determined that a winding overheating event has occurred in the transformer, and it is marked as an overheated transformer.

[0058] By comparing the correlation coefficient with the preset correlation coefficient threshold, overheated transformers can be quickly and accurately identified, greatly improving the accuracy and efficiency of fault diagnosis, effectively reducing false alarms, avoiding misjudgment caused by single-parameter detection, and at the same time quickly responding to abnormal changes in the transformer state, timely capturing overheating faults, and reducing the risk of fault expansion.

[0059] Specifically, the fault determination module includes: A first fault determination unit, configured to determine all transformers within a circular area with a preset radius around the adjacent overheated transformer as faulty transformers when the distance is less than the minimum value of the preset distance range, so as to determine a number of faulty transformers; A second fault determination unit, configured to determine a number of faulty transformers according to the acetylene content of each transformer to be tested within a preset determination range in the temporary inspection route between the adjacent overheated transformers when the distance is greater than the maximum value of the preset distance range.

[0060] The preset distance range refers to a key parameter for judging the distance between adjacent overheated transformers, which depends on the layout of the transformers, the fault propagation characteristics, and the monitoring accuracy requirements, and is usually set between 1 meter and 5 meters. In this embodiment, it is set between 3 meters and 4 meters, which can effectively reduce false alarms while timely detecting potential fault areas between adjacent overheated transformers, ensuring the accuracy and reliability of fault diagnosis.

[0061] The preset determination range refers to the circular coverage area centered on the inspection device, which depends on the layout of the transformers, the fault propagation characteristics, and the monitoring accuracy requirements, and is usually set between 5 square meters and 15 square meters. In this embodiment, it is set to 10 square meters, which can effectively cover the potential fault areas around the overheated transformer, ensuring the comprehensiveness and accuracy of fault diagnosis, while avoiding over-expanding the fault range and reducing the false alarm rate.

[0062] By comparing the distance between any two adjacent overheated transformers with the preset distance range, a comparison result is obtained; when the comparison result shows that the distance between the adjacent overheated transformers is less than the minimum value of the preset distance range, the system will take the overheated transformer as the center and determine all transformers within the preset radius as faulty transformers; at the same time, when the distance between the adjacent overheated transformers is greater than the preset distance range, the system will further determine the faulty transformers according to the acetylene content of each transformer to be tested within the preset determination range in the temporary inspection route between the adjacent overheated transformers.

[0063] By setting the preset distance range and the preset radius, faulty transformers can be effectively identified and determined, significantly improving the accuracy and efficiency of fault diagnosis. When the distance between adjacent overheated transformers is less than the minimum value of the preset distance range, all transformers within the preset radius are determined as faulty transformers; when the distance between adjacent overheated transformers is greater than the maximum value of the preset distance range, the faulty transformers are further determined according to the acetylene content of each transformer to be tested within the preset determination range in the temporary inspection route between the adjacent overheated transformers, so as to comprehensively cover potential fault areas and avoid missing fault points.

[0064] Specifically, the second fault determination unit includes: An acetylene content fluctuation calculation subunit is used to calculate the standard deviations of the acetylene contents of the overheated transformer and each of the transformers to be measured respectively, and form an acetylene content fluctuation value. A second fault determination subunit, which is connected to the acetylene content fluctuation calculation subunit, is used to determine that both the overheated transformer and the transformers to be measured are faulty transformers when the acetylene content fluctuation value is less than a preset acetylene content fluctuation threshold; and determine that only the overheated transformer is a faulty transformer when the acetylene content fluctuation value is greater than or equal to the preset acetylene content fluctuation threshold.

[0065] The preset acetylene content fluctuation threshold is a key parameter for judging whether the acetylene content fluctuations of each transformer are abnormal, and depends on the normal fluctuation range of the acetylene content during the operation of the transformer, the statistical analysis of historical data, and the requirements for the sensitivity of fault detection. It is usually set between 0.1 μL / L and 1.0 μL / L. In this embodiment, it is set to 0.5 μL / L, which can effectively distinguish normal fluctuations and abnormal fluctuations, can avoid misjudgment caused by small fluctuations in acetylene content, and can timely detect significant changes in acetylene content caused by faults, improving the accuracy and reliability of fault diagnosis.

[0066] By calculating the standard deviations of the acetylene contents of the overheated transformer and the transformers to be measured, an acetylene content fluctuation value is formed; subsequently, by comparing the acetylene content fluctuation value with the preset acetylene content fluctuation threshold, if the acetylene content fluctuation value is less than the preset acetylene content fluctuation threshold, both the overheated transformer and the transformers to be measured are determined to be faulty transformers; if the acetylene content fluctuation value is greater than or equal to the preset acetylene content fluctuation threshold, only the overheated transformer is determined to be a faulty transformer.

[0067] By calculating the standard deviations of the acetylene contents of the overheated transformer and the transformers to be measured to form an acetylene content fluctuation value and comparing it with the preset acetylene content fluctuation threshold, faulty transformers and normal transformers can be effectively distinguished. When the fluctuation value is less than the preset threshold, it indicates that the acetylene content of the transformer to be measured is close to that of the overheated transformer, and the system determines both of them to be faulty transformers; when the fluctuation value is greater than or equal to the preset threshold, it indicates that the acetylene content of the transformer to be measured is quite different from that of the overheated transformer, and only the overheated transformer is determined to be a faulty transformer, improving the accuracy and reliability of fault diagnosis, reducing the false alarm rate, optimizing the allocation of monitoring resources at the same time, improving the operation and maintenance efficiency, and providing a strong guarantee for the stable operation of the power system.

[0068] Specifically, the adjustment module includes: A quantity fluctuation calculation unit is used to calculate the standard deviation of the number of faulty transformers within a preset adjustment duration, and form a quantity fluctuation value. An adjustment unit, which is connected to the quantity fluctuation calculation unit, is used to adjust the preset synchronization threshold according to the quantity fluctuation value to form an adjusted synchronization threshold.

[0069] The preset adjustment duration is the time interval for adjusting the number of faulty transformers required to adjust the preset synchronization threshold, which depends on the operating characteristics of the transformer, the fault occurrence frequency, and the monitoring accuracy requirements. It is usually set between 10 minutes and 1 hour. In this embodiment, it is set to 30 minutes, which can effectively balance the sufficiency of data collection and the system's response speed, ensure the accuracy of calculation, quickly respond to changes in the number of faults, timely adjust the preset synchronization threshold, and improve the adaptability and reliability of the system.

[0070] By calculating the standard deviation of the number of faulty transformers within the preset adjustment duration, the number fluctuation value is obtained; subsequently, the preset synchronization threshold is adjusted according to the number fluctuation value to obtain the adjusted synchronization threshold.

[0071] By calculating the standard deviation of the number of faulty transformers within the preset adjustment duration to form the number fluctuation value and adjusting the preset synchronization threshold accordingly, the system can dynamically optimize the detection parameters according to the change in the number of faults, thereby improving the adaptability and reliability of the system. It not only enhances the stability of the system under different working conditions but also can respond to changes in the number of faults in a timely manner to ensure the accuracy of fault diagnosis.

[0072] Specifically, the adjustment unit includes: The number fluctuation deviation calculation sub-unit is used to calculate the relative deviation between the number fluctuation value and the preset number fluctuation threshold when the number fluctuation value is greater than the preset number fluctuation threshold, and form the number fluctuation deviation; The adjustment sub-unit is connected to the number fluctuation deviation calculation sub-unit and is used to increase the preset synchronization threshold according to the number fluctuation deviation and the preset adjustment coefficient when the number fluctuation deviation is greater than the preset number fluctuation deviation threshold, and form the adjusted synchronization threshold.

[0073] The preset number fluctuation threshold is a key parameter for judging whether the number fluctuation of faulty transformers is abnormal, which depends on the statistical analysis of historical data of the number of faulty transformers, the monitoring accuracy requirements, and the demand for fault detection sensitivity. It is usually set between 0.5 and 2.0. In this embodiment, it is set to 1.0, which can effectively reduce false alarms while timely detecting significant fluctuations in the number of faults, and improve the adaptability and reliability of the system.

[0074] The preset number fluctuation deviation threshold is a key parameter for judging whether the number fluctuation deviation is abnormal, which depends on the statistical analysis of historical data of the number fluctuation of faults, the monitoring accuracy requirements, and the demand for fault detection sensitivity. It is usually set between 10% and 30%. In this embodiment, it is set to 20%, which can effectively distinguish normal fluctuations from abnormal fluctuations, avoid misjudgment caused by minor fluctuations, and timely detect deviations caused by significant changes in the number of faults, and improve the adaptability and reliability of the system.

[0075] The preset adjustment coefficient is a key parameter for adjusting the preset synchronization threshold, which depends on the system's adjustment strategy, monitoring accuracy requirements, and the need for fault detection sensitivity. It is usually set between 0.1 and 0.5. In this embodiment, it is set to 0.3, which can effectively reduce false alarms while timely adjusting the preset synchronization threshold, improving the adaptability and reliability of the system.

[0076] When the quantity fluctuation value exceeds the preset quantity fluctuation threshold, calculate the relative deviation between the quantity fluctuation value and the preset quantity fluctuation threshold to obtain the quantity fluctuation deviation. Subsequently, if the quantity fluctuation deviation exceeds the preset quantity fluctuation deviation threshold, the system will increase the preset synchronization threshold according to the quantity fluctuation deviation and the preset adjustment coefficient to form an adjusted synchronization threshold.

[0077] By calculating the quantity fluctuation deviation and dynamically adjusting the preset synchronization threshold accordingly, the system can automatically optimize the detection parameters according to the change in the number of faults, improving the adaptability and reliability of the system, enabling it to better meet the fault detection requirements under different working conditions. At the same time, dynamically adjusting the threshold can reduce the false alarm rate, ensure the accuracy of fault diagnosis, optimize the allocation of monitoring resources, improve the operation and maintenance efficiency, and provide more powerful guarantee for the stable operation of the power system.

[0078] On the other hand, please refer to Figure 4 as shown, which is the flowchart of the transformer fault inspection method based on multi-sensors in this embodiment; This embodiment also provides a transformer fault inspection method based on multi-sensors, including: Real-time collect the temperature of the windings of each transformer under test set in the monitoring area, and, through the inspection device equipped with multi-sensors, real-time collect the flow rate and acetylene content of the cooling oil in the cooling system of each transformer under test in the monitoring area; Determine a number of temporary transformers according to the flow rate, the temperature, and the preset synchronization threshold; Along the temporary inspection route formed based on all the temporary transformers, real-time collect the DC resistance and copper loss values of the windings of each temporary transformer; Determine a number of overheated transformers according to the DC resistance and the copper loss value; Determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and the acetylene content, and, determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and the preset radius; Adjust the preset synchronization threshold according to the number of the faulty transformers to form an adjusted synchronization threshold; Send out a warning according to the faulty transformers determined based on the adjusted synchronization threshold.

[0079] The temperature of the windings of each transformer to be measured in the monitoring area is collected in real time by optical fiber temperature sensors installed at key positions of the transformer windings, and the cooling oil flow rate and acetylene content of each transformer to be measured in the monitoring area are collected in real time by a multi-sensor inspection device; First, a number of temporary transformers are determined according to these parameters and a preset synchronization threshold; Then, the DC resistance and copper loss values of these temporary transformers are collected in real time along the temporary inspection route, and then a number of overheated transformers are determined; Subsequently, a number of faulty transformers are determined by combining the distance and acetylene content between adjacent overheated transformers and a preset radius; The preset synchronization threshold is dynamically adjusted according to the number of faulty transformers to form an adjusted synchronization threshold; Finally, a warning is issued for the faulty transformers determined based on the adjusted synchronization threshold.

[0080] By collecting key operating parameters of transformers in real time with multi-sensors and combining preset thresholds and dynamic adjustment mechanisms, efficient monitoring and early warning of transformer faults are achieved; The accuracy and reliability of fault diagnosis are improved, the false alarm rate is reduced, the allocation of monitoring resources is optimized, and the operation and maintenance costs are reduced; The problems of inaccurate fault diagnosis and response delay caused by high-altitude extreme environments in the prior art are overcome by multi-parameter monitoring, dynamic threshold adjustment and optimized inspection paths.

[0081] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A transformer fault inspection system based on multiple sensors, characterized in that: include: The first acquisition module is used to collect the temperature of the windings of each transformer to be tested in the monitoring area in real time, and to collect the flow rate and acetylene content of the cooling oil in the cooling system of each transformer to be tested in the monitoring area in real time through a patrol device provided with multiple sensors; a temporary determination module, connected to the first acquisition module, for determining a number of temporary transformers according to the flow rate, the temperature and a preset synchronization threshold; A second acquisition module, which is connected to the temporary determination module and is used to collect the DC resistance and copper loss value of each temporary transformer winding in real time along the temporary inspection route formed based on all the temporary transformers; an overheat determination module, which is connected to the temporary determination module and the second acquisition module respectively, and is used to determine a number of overheated transformers according to the DC resistance and the copper loss value; a fault determination module, which is connected to the overheat determination module and the first acquisition module respectively, and is used to determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and the acetylene content, and to determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and a preset radius; An adjustment module, connected to the fault determination module, for adjusting the preset synchronization threshold according to the number of the faulty transformers to form an adjusted synchronization threshold; An early warning module is connected to the fault determination module and the adjustment module respectively, and is used to issue an early warning according to the faulty transformer determined based on the adjustment synchronization threshold.

2. The transformer fault inspection system based on multiple sensors according to claim 1 is characterized in that: The temporary determination module comprises: A temperature fluctuation calculation unit, used to calculate the standard deviation of the temperature within a preset determined time period to form a temperature fluctuation value; A flow rate fluctuation calculation unit, used to calculate the standard deviation of the flow rate within the preset determined time period to form a flow rate fluctuation value; A temporary determination unit is connected to the temperature fluctuation calculation unit and the flow rate fluctuation calculation unit respectively, and is used to determine a number of temporary transformers according to the temperature fluctuation value and the flow rate fluctuation value.

3. The transformer fault inspection system based on multiple sensors according to claim 2 is characterized in that: The temporary determination unit includes: A temperature fluctuation curve drawing subunit is used to draw a change curve of the temperature fluctuation value within the preset determined time period to form a temperature fluctuation curve; A flow velocity fluctuation curve drawing subunit is used to draw a change curve of the flow velocity fluctuation value within the preset determined time length to form a flow velocity fluctuation curve; a synchronization degree calculation subunit, which is connected to the temperature fluctuation curve drawing subunit and the flow velocity fluctuation curve drawing subunit respectively, and is used to calculate the cosine similarity of the temperature fluctuation curve and the flow velocity fluctuation curve to form a change synchronization degree; A temporary determination subunit is connected to the synchronization calculation subunit and is used to determine that the transformer to be tested is the temporary transformer when the change synchronization is less than a preset synchronization threshold, so as to determine a number of the temporary transformers.

4. The transformer fault inspection system based on multiple sensors according to claim 3 is characterized in that: The overheat determination module comprises: A correlation coefficient calculation unit, used to calculate the correlation coefficient between the DC resistance and the copper loss value within a preset determination time to form a correlation coefficient; A determination unit is connected to the correlation coefficient calculation unit and is used to determine that the temporary transformer is the overheated transformer according to the correlation coefficient and a preset correlation coefficient threshold value, so as to form a plurality of overheated transformers.

5. The transformer fault inspection system based on multiple sensors according to claim 4 is characterized in that: The determination unit comprises: A coefficient comparison subunit, used to compare the correlation coefficient with the preset correlation coefficient threshold to form a coefficient comparison result; The determination subunit is connected to the coefficient comparison subunit, and is used to determine that the temporary transformer is the overheated transformer when the coefficient comparison result is that the correlation coefficient is greater than a preset correlation coefficient threshold, so as to form a plurality of overheated transformers.

6. The transformer fault inspection system based on multiple sensors according to claim 5 is characterized in that: The fault determination module comprises: a first fault determination unit, configured to determine, when the distance is less than a minimum value of the preset distance range, that the adjacent overheated transformer and all transformers within a circular area of ​​a preset radius are faulty transformers, so as to determine a number of faulty transformers; The second fault determination unit is used to determine a number of faulty transformers according to the acetylene content of each transformer to be tested within a preset determination range in the temporary inspection route between the adjacent overheated transformers when the distance is greater than the maximum value of the preset distance range.

7. The transformer fault inspection system based on multiple sensors according to claim 6 is characterized in that: The second fault determination unit includes: An acetylene content fluctuation calculation subunit, used to respectively calculate the standard deviation of the acetylene content of the overheated transformer and each of the transformers to be tested to form an acetylene content fluctuation value; A second fault determination subunit is connected to the acetylene content fluctuation calculation subunit, and is used to determine that the overheating transformer and the transformer to be tested are both faulty transformers when the acetylene content fluctuation value is less than a preset acetylene content fluctuation threshold; and to determine that only the overheating transformer is a faulty transformer when the acetylene content fluctuation value is greater than or equal to a preset acetylene content fluctuation threshold.

8. The transformer fault inspection system based on multiple sensors according to claim 7 is characterized in that: The adjustment module comprises: A quantity fluctuation calculation unit, used to calculate the standard deviation of the number of faulty transformers within a preset adjustment time to form a quantity fluctuation value; An adjustment unit is connected to the quantity fluctuation calculation unit and is used to adjust the preset synchronization threshold according to the quantity fluctuation value to form an adjusted synchronization threshold.

9. The transformer fault inspection system based on multiple sensors according to claim 8 is characterized in that: The adjustment unit comprises: A quantity fluctuation deviation calculation subunit, for calculating a relative deviation between the quantity fluctuation value and the preset quantity fluctuation threshold value when the quantity fluctuation value is greater than a preset quantity fluctuation threshold value, to form a quantity fluctuation deviation; an adjusting subunit, which is connected to the quantity fluctuation deviation calculating subunit, and is used to increase the preset synchronization threshold according to the quantity fluctuation deviation and a preset adjustment coefficient to form an adjusted synchronization threshold when the quantity fluctuation deviation is greater than a preset quantity fluctuation deviation threshold. The preset adjustment coefficient depends on the system's adjustment strategy, monitoring accuracy requirements, and requirements for fault detection sensitivity.

10. A transformer fault inspection method based on multiple sensors, based on the transformer fault inspection system based on multiple sensors according to any one of claims 1 to 9, characterized in that: include: Real-time collection of the temperature of the windings of each transformer to be tested set in the monitoring area, and real-time collection of the flow rate and acetylene content of the cooling oil in the cooling system of each transformer to be tested in the monitoring area through a patrol device equipped with multiple sensors; Determine a number of temporary transformers according to the flow rate, the temperature and a preset synchronization threshold; Collecting the DC resistance and copper loss value of each temporary transformer winding in real time along the temporary inspection route formed by all the temporary transformers; Determine a number of overheated transformers according to the DC resistance and the copper loss value; Determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and the acetylene content, and determine a number of faulty transformers according to the distance between any two adjacent overheated transformers and a preset radius; Adjusting the preset synchronization threshold according to the number of the faulty transformers to form an adjusted synchronization threshold; An early warning is issued according to the faulty transformer determined based on the adjustment synchronization threshold.

Images