Transformer system based on intelligent monitoring and self-adaptive heat dissipation and transformer heat dissipation method

Abstract

The invention relates to the technical field of transformer intelligent monitoring and heat dissipation control, in particular to a transformer system based on intelligent monitoring and self-adaptive heat dissipation and a transformer heat dissipation method, and the system comprises an intelligent monitoring module which is used for collecting physical quantity data in the operation process of a transformer in real time through a sensor; the data processing and analyzing unit is used for receiving the data transmitted by the intelligent monitoring module and establishing a transformer operation state model; the self-adaptive heat dissipation control module is used for receiving the operation state analysis result and dynamically adjusting operation parameters of the heat dissipation system based on a temperature threshold value and a load rate; and the fault early warning and diagnosis module is used for establishing an operation state evaluation model and a fault prediction model by adopting a machine learning algorithm, receiving an operation state analysis result and comparing the operation state analysis result with an early warning threshold value. Accurate monitoring, self-adaptive heat dissipation and fault early warning of the transformer are achieved, stable operation is guaranteed, and energy consumption is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring and heat dissipation control of transformers, and is a transformer system based on intelligent monitoring and adaptive heat dissipation and a transformer heat dissipation method. BACKGROUND

[0002] With the continuous development of modern power systems, the stability and reliability of transformers, as key equipment in power transmission and distribution, are crucial. In the power grid, transformers undertake important tasks such as voltage conversion and power distribution, and are widely used in power plants, substations, and various industrial and civilian power supply sites. However, they face significant challenges in heat dissipation during operation. When a transformer operates for a long time, heat is generated due to its own losses, causing the temperature to rise. Excessive temperature can accelerate the aging of internal insulation materials, reduce insulation performance, shorten service life, and even cause faults and affect power supply. Moreover, the load of the power system changes dynamically, and the demand for electricity varies at different times. Traditional transformers use fixed air cooling or oil cooling methods, and the heat dissipation power is constant. During low load, excessive heat dissipation leads to energy waste, and during high load, the temperature may be too high due to insufficient heat dissipation capacity.

[0003] The existing transformer lacks precision and comprehensiveness in monitoring key operating parameters, making it difficult to support efficient operation and maintenance. For parameters such as winding temperature, oil temperature, and internal partial discharge that can reflect the core state of the equipment, traditional monitoring methods can only obtain partial data, and cannot accurately capture the complex internal operating state of the transformer in real time, making it difficult for operation and maintenance personnel to timely grasp potential equipment hazards and providing comprehensive and reliable decision-making basis for subsequent maintenance.

[0004] In terms of fault early warning, the response capability of existing technologies is obviously insufficient. Traditional transformers mostly use simple fault early warning methods based on threshold judgment, which cannot effectively predict potential faults in advance. Only when the monitoring parameters exceed the set threshold will an alarm be issued. At this time, the fault may have occurred or is about to occur, making it difficult for operation and maintenance personnel to reserve sufficient time for fault diagnosis and processing, and easily leading to the expansion of faults and affecting the continuous and stable operation of the power system. SUMMARY

[0005] The present application provides a transformer system based on intelligent monitoring and adaptive heat dissipation and a transformer heat dissipation method, which overcomes the shortcomings of the prior art and effectively solves the problems of fixed heat dissipation mode of existing transformers, inaccurate and incomplete monitoring of key parameters, and poor fault early warning capability.

[0006] One of the technical solutions of the present application is achieved by the following measures: a transformer system based on intelligent monitoring and adaptive heat dissipation, comprising: The intelligent monitoring module is installed at a key position of the transformer, is used for collecting physical quantity data in a running process of the transformer in real time through a sensor, and transmits the collected data to the data processing and analysis unit. The data processing and analysis unit is used for receiving the data transmitted by the intelligent monitoring module, cleaning and fusion processing the data by using a data processing algorithm, establishing a transformer running state model, judging the running state by comparing real-time data with model parameters, and transmitting the analysis result to the adaptive heat dissipation control module and the fault early warning and diagnosis module. The adaptive heat dissipation control module is used for receiving the running state analysis result, dynamically adjusting heat dissipation system running parameters based on a temperature threshold and a load rate, controlling heat dissipation intensity by using multi-grade temperature threshold, and adjusting heat dissipation capacity according to the change of the load rate. The fault early warning and diagnosis module is used for establishing a running state evaluation model and a fault prediction model by using a machine learning algorithm, receiving the running state analysis result and comparing the result with a warning threshold, issuing a warning signal when the data deviates from a normal range and reaches the warning threshold, and analyzing and judging a fault type and a position and outputting troubleshooting suggestions.

[0007] The following is a further optimization or / and improvement of one of the above technical solutions: The installation position of the intelligent monitoring module can include a winding, a core and an oil tank wall of the transformer.

[0008] The sensors included in the intelligent monitoring module can include temperature sensors, current sensors, voltage sensors, gas sensors, vibration sensors and partial discharge sensors.

[0009] The intelligent monitoring module can further include a signal conditioning circuit for amplifying and filtering the collected raw data for preprocessing.

[0010] The fault types judged by the fault early warning and diagnosis module can include winding short circuit and core multi-point grounding.

[0011] The transformer running state model established by the data processing and analysis unit can be a multi-dimensional model including temperature, current, voltage, vibration frequency correlation parameters.

[0012] The second technical solution of the present application is realized by the following measures: a transformer heat dissipation method based on intelligent monitoring and adaptive heat dissipation, comprising the following steps: Step S1, data collection: collecting physical quantity data in a running process of the transformer in real time through a sensor installed at a key position of the transformer; Step S2, data processing and state analysis: cleaning and fusion processing the collected data, establishing a transformer running state model, and judging the running state by comparing real-time data with model parameters; Step S3, Adaptive heat dissipation control: Based on the operating status obtained in step S2, the operating parameters of the heat dissipation system are dynamically adjusted in combination with the temperature threshold and load rate. The heat dissipation intensity is controlled by multiple temperature threshold levels, and the heat dissipation capacity is adjusted according to the load rate. Step S4, Fault Warning and Diagnosis: A machine learning algorithm is used to establish an operating status assessment model and a fault prediction model. Based on the comparison between the operating status obtained in step S2 and the warning threshold, a warning signal is issued when the data deviates from the normal range and reaches the warning threshold. At the same time, the fault type and location are analyzed and the troubleshooting suggestions are output.

[0013] The following are further optimizations and / or improvements to the second technical solution of the above invention: The multiple temperature thresholds in step S3 above may include: the first temperature threshold corresponds to starting a low-speed cooling fan, the second temperature threshold corresponds to controlling the cooling fan to run at full speed, and the third temperature threshold corresponds to starting a liquid cooling auxiliary heat dissipation system.

[0014] The method for adjusting the heat dissipation capacity according to the load rate in step S3 above may include: reducing the speed of the cooling fan or reducing the flow rate of the cooling oil pump when the load rate is lower than the set value; increasing the number of cooling fans or increasing the power of the liquid cooling system when the load rate exceeds the set value.

[0015] The machine learning algorithm in step S4 above may include support vector machines, neural networks, or decision trees.

[0016] This invention, by incorporating an intelligent monitoring module, a data processing and analysis unit, an adaptive heat dissipation control module, and a fault early warning and diagnosis module, achieves comprehensive and accurate monitoring of transformer operating status, dynamic adaptation of heat dissipation strategies, and early warning of faults, resulting in significant overall technical effectiveness. Specifically, the intelligent monitoring module collects real-time physical data from key transformer components. Combined with data cleaning, fusion processing, and operating status model construction by the data processing and analysis unit, it enables maintenance personnel to clearly understand the transformer's true internal operating status, avoiding misjudgments caused by incomplete parameters and insufficient accuracy in traditional monitoring. The adaptive heat dissipation control module dynamically adjusts the heat dissipation system's operating parameters based on temperature and load, preventing energy waste from excessive heat dissipation under low loads and ensuring sufficient heat dissipation to maintain a suitable operating temperature under high loads, effectively slowing down the aging of internal insulation materials and extending the transformer's service life. The fault early warning and diagnosis module, using a model built with machine learning algorithms, can issue early warning signals when monitoring data deviates from the normal range but does not reach traditional thresholds, and identifies the fault type and location, allowing maintenance personnel sufficient time for troubleshooting and reducing the risk of fault escalation. Overall, this invention not only improves the stability and reliability of transformer operation and reduces energy consumption, but also provides a strong guarantee for the continuous and stable power supply of the power system, reduces power outages caused by transformer failures, and meets the needs of modern power systems for efficient operation and maintenance, energy-saving operation and safety assurance of transformers. Attached Figure Description

[0017] Appendix Figure 1 This is a schematic diagram of the structure of a transformer system based on intelligent monitoring and adaptive heat dissipation according to an embodiment of the present invention.

[0018] Appendix Figure 2 This is a schematic diagram of the sensor installation location for a transformer system based on intelligent monitoring and adaptive heat dissipation, according to an embodiment of the present invention.

[0019] The codes in the attached diagram are as follows: 1 for gas sensor, 2 for temperature sensor, 3 for vibration sensor, and 4 for partial discharge sensor. Detailed Implementation

[0020] The present invention is not limited to the following embodiments, and the specific implementation can be determined according to the technical solution of the present invention and the actual situation.

[0021] The present invention will be further described below with reference to embodiments: Example 1: As shown in the attached document Figure 1 , 2 As shown, this embodiment provides a transformer system based on intelligent monitoring and adaptive heat dissipation, including: The intelligent monitoring module, installed in key parts of the transformer, is used to collect physical quantity data of the transformer in real time through sensors and transmit the collected data to the data processing and analysis unit. By deploying sensors in the core operating area of ​​the transformer, physical quantities related to the equipment's operating status are directly captured, avoiding delays or distortions in data transmission and ensuring that raw data is delivered to the subsequent processing unit in a timely manner. This enables real-time acquisition of transformer operating data, providing accurate and timely basic data support for subsequent status analysis and control decisions. Various high-precision sensors are installed in key parts of the transformer (such as windings, core, and tank walls), including temperature sensors (such as fiber optic temperature sensors and thermocouple temperature sensors), current sensors (such as Rogowski coil current sensors and Hall current sensors), voltage sensors (such as capacitive voltage sensors and resistive voltage divider voltage sensors), gas sensors (for monitoring the composition and content of dissolved gases in transformer oil), and vibration sensors (such as accelerometers). The raw data collected by the sensors is amplified and filtered by the signal conditioning circuit, providing accurate raw information for subsequent analysis in real time. For example, fiber optic temperature sensors utilize the transmission characteristics of optical signals to accurately measure winding temperature, unaffected by electromagnetic interference, with a measurement accuracy of ±0.5℃. High-precision sensors are installed at key locations inside the transformer (such as windings, core, and tank walls), including temperature sensors (such as fiber optic temperature sensors and thermocouple temperature sensors), current sensors (such as Rogowski coil current sensors and Hall effect current sensors), voltage sensors (such as capacitive voltage sensors and resistive voltage divider voltage sensors), gas sensors (used to monitor the composition and content of dissolved gases in transformer oil), and vibration sensors (such as accelerometers). The sensors collect raw data, which is then amplified, filtered, and preprocessed through signal conditioning circuits before being transmitted to the data processing unit via high-speed data transmission lines.

[0022] The data processing and analysis unit receives data transmitted from the intelligent monitoring module, uses data processing algorithms to clean and fuse the data, establishes a transformer operating status model, judges the operating status by comparing real-time data with model parameters, and transmits the analysis results to the adaptive heat dissipation control module and the fault early warning and diagnosis module. First, data cleaning removes abnormal data caused by occasional sensor interference. Then, data fusion algorithms integrate data from multiple types of sensors, eliminating the limitations of single data sources. Combined with a preset normal operating status model, it accurately identifies whether there are any abnormalities in the current operation. This improves the accuracy and reliability of the data, ensuring that the judgment of the transformer's operating status is more in line with the actual situation, and providing a scientific basis for subsequent heat dissipation control and fault early warning. Data processing algorithms (including big data analysis technology and artificial intelligence algorithms) are used to deeply mine and analyze the collected data. First, data cleaning removes noise and abnormal data, and then data fusion algorithms comprehensively process multi-source data to improve data accuracy and reliability. A high-performance microprocessor or digital signal processor (DSP) is used as the data processing core. This unit receives preprocessed data from sensors, uses data fusion algorithms and machine learning algorithms to perform in-depth analysis of the data, establishes a multi-dimensional model of the transformer's operating status, compares the real-time monitoring data with the model parameters under normal operating conditions, and determines whether the transformer's current operating status is normal.

[0023] The adaptive heat dissipation control module receives operational status analysis results and dynamically adjusts the operating parameters of the heat dissipation system based on temperature thresholds and load rates. It controls the heat dissipation intensity through multiple temperature threshold levels and adjusts the heat dissipation capacity according to load rate changes. It receives temperature and load rate information from the data processing unit in real time. When the temperature or load rate reaches a set adjustment node, it automatically triggers the corresponding heat dissipation parameter adjustment to match the heat dissipation capacity with the actual heat dissipation needs of the equipment. This avoids energy waste or insufficient heat dissipation problems associated with fixed heat dissipation methods, maintains the transformer operating within a suitable temperature range, and slows down the aging of internal components. Based on the analysis results from the data processing and analysis unit, the adaptive heat dissipation control module dynamically adjusts the operating parameters of the heat dissipation system. This includes temperature threshold-based control and load rate-based control. Temperature threshold-based control involves setting different temperature thresholds. When the transformer temperature reaches a certain threshold, corresponding heat dissipation equipment is activated or the heat dissipation intensity is adjusted. For example, when the temperature reaches 60℃, a low-speed fan is activated; when it reaches 80℃, the fan runs at full speed; and when it reaches 95℃, liquid cooling auxiliary heat dissipation is activated. Load rate-based control dynamically adjusts the heat dissipation strategy according to the transformer load rate. When the load rate is low, the heat dissipation intensity is reduced; when the load rate is high, the heat dissipation capacity is increased. Precise control is achieved by establishing a model of the relationship between load rate and heat dissipation demand. For example, when the load rate exceeds 80%, the number of cooling fans is automatically increased or the power of the liquid cooling system is increased. Based on the analysis results from the data processing and analysis unit, the adaptive heat dissipation control module dynamically adjusts the operating parameters of the heat dissipation system. When it is determined that the transformer is under low load and at a low temperature, the cooling fan speed is reduced or the cooling oil pump flow rate is decreased. When an increase in load and a rise in temperature are detected, the cooling fan speed is automatically increased or the cooling oil pump flow rate is increased to ensure that the transformer is always within the optimal operating temperature range.

[0024] The fault early warning and diagnosis module uses machine learning algorithms to build operational status assessment and fault prediction models. It receives operational status analysis results and compares them with early warning thresholds. When data deviates from the normal range and reaches the early warning threshold, it issues an early warning signal. Simultaneously, it analyzes and determines the fault type and location, and outputs troubleshooting suggestions. By learning from a large amount of historical operational data and fault cases using machine learning algorithms, it forms a model capable of identifying potential anomalies. When real-time data matches abnormal characteristics, it quickly matches the corresponding fault type and possible location. This allows for the early detection of potential transformer faults, providing maintenance personnel with clear troubleshooting directions and reducing the risk of fault escalation. Machine learning algorithms (such as support vector machines, neural networks, and decision trees) are used to build transformer operational status assessment and fault prediction models. For example, a neural network-based fault prediction model, trained on a large amount of historical data, can accurately predict the probability of transformer winding short circuits, multi-point grounding of the core, and other faults, and preliminarily determine the fault location, issuing early warning signals in advance. The system uses machine learning algorithms to learn and train on historical monitoring data and fault cases to establish a fault prediction model. When the monitoring data deviates from the normal range and reaches the warning threshold set by the fault prediction model, the system automatically issues a warning signal. At the same time, the system uses fault diagnosis algorithms to preliminarily determine the fault type and location, providing detailed fault troubleshooting suggestions for maintenance personnel.

[0025] In this embodiment, the installation locations of the intelligent monitoring module include the transformer windings, core, and tank wall. The windings and core are the core heat-generating components of the transformer, and the tank wall temperature reflects the heat dissipation effect of the oil cooling system. Installing sensors in these locations allows for direct acquisition of operational data from key areas. This covers the core monitoring points of the transformer's operating status, avoiding misjudgments due to improper monitoring locations.

[0026] In this embodiment, the intelligent monitoring module includes sensors such as a temperature sensor, a current sensor, a voltage sensor, a gas sensor, a vibration sensor, and a partial discharge sensor. The temperature sensor monitors the heat generation of the equipment, the current and voltage sensors reflect load changes, the gas sensor detects abnormal gases in the oil to determine if there is an internal fault, and the vibration sensor identifies abnormal vibrations caused by loose or damaged components. In this way, transformer operating data can be collected from multiple dimensions to comprehensively reflect the operating status of the equipment and avoid the limitations of monitoring a single parameter.

[0027] In this embodiment, the intelligent monitoring module also includes a signal conditioning circuit for amplifying and filtering the collected raw data. The raw data collected by the sensor may contain weak signals or interference signals. The signal conditioning circuit improves data quality by amplifying weak signals and filtering interference signals. This ensures that the data transmitted to the data processing unit is clearer and more accurate, reduces the difficulty of subsequent data processing, and improves the overall monitoring accuracy.

[0028] In this embodiment, the fault warning and diagnosis module identifies fault types including winding short circuits and multi-point grounding of the core. Winding short circuits can cause abnormal local currents and a sudden rise in temperature, while multi-point grounding of the core can generate eddy currents that lead to overheating. These faults will exhibit specific characteristics in the monitoring data, and the module identifies these characteristics to match the corresponding fault types. In this way, common serious transformer fault types can be accurately located, providing support for maintenance personnel to quickly develop repair plans.

[0029] In this embodiment, the transformer operating state model established by the data processing and analysis unit is a multi-dimensional model, which includes parameters related to temperature, current, voltage, and vibration frequency. The transformer operating state is the result of the combined effect of multiple parameters, and the multi-dimensional model can reflect the correlation between various parameters, such as the correlation between load (current and voltage) changes and temperature and vibration, thereby making a more comprehensive judgment on the operating state. In this way, the one-sidedness of judging by a single parameter can be avoided, and the accuracy of identifying complex operating states of transformers can be improved.

[0030] During operation, the intelligent monitoring module collects physical quantity data from key parts of the transformer through various sensors. After preprocessing by the signal conditioning circuit, the data is transmitted to the data processing and analysis unit. The data processing unit cleans and merges the data, combines it with a multi-dimensional operating status model to determine the current operating status, and synchronizes the results to the adaptive heat dissipation control module and the fault early warning and diagnosis module. The adaptive heat dissipation control module dynamically adjusts heat dissipation parameters according to temperature and load rate, while the fault early warning module compares data with early warning thresholds in real time, issuing warnings and indicating fault information when an anomaly is detected. Overall, it realizes intelligent monitoring, dynamic heat dissipation, and early warning of the transformer, effectively improving operational stability and reducing energy consumption and fault risk. This invention can achieve comprehensive and accurate monitoring of the transformer's operating status, adaptively adjust the heat dissipation strategy according to real-time load and operating temperature, improve heat dissipation efficiency, reduce energy consumption, and enhance fault early warning capabilities, ensuring stable and reliable transformer operation.

[0031] Example 2: This example provides a transformer heat dissipation method based on intelligent monitoring and adaptive heat dissipation, including the following steps: Step S1, Data Acquisition: Sensors installed at key locations on the transformer are used to collect real-time physical data during transformer operation. Sensors are deployed in core areas such as the transformer windings and core to directly capture key physical quantities such as temperature, current, and vibration during operation, ensuring the real-time nature and relevance of data acquisition. This allows for the acquisition of raw data that directly reflects the transformer's operating status, providing a reliable basis for subsequent processing and control.

[0032] Step S2, Data Processing and Status Analysis: The collected data is cleaned and fused to establish a transformer operating status model. The operating status is determined by comparing real-time data with model parameters. First, interference and outliers are removed from the collected data. Then, data from different types of sensors are integrated to eliminate data silos. Combined with preset normal operating model parameters, the system identifies whether any anomalies exist in the current operation. This improves data validity, ensuring more accurate judgment of the transformer's operating status and laying the foundation for subsequent heat dissipation control and fault early warning.

[0033] Step S3, Adaptive Heat Dissipation Control: Based on the operating status obtained in Step S2, the operating parameters of the heat dissipation system are dynamically adjusted in conjunction with temperature thresholds and load rate. The heat dissipation intensity is controlled in stages using multiple temperature thresholds, and the heat dissipation capacity is adjusted according to changes in load rate. Based on the temperature and load rate information output in Step S2, when the temperature reaches different thresholds or the load rate changes, parameters such as the cooling fan speed and liquid cooling system power are adjusted accordingly to match the heat dissipation capacity with actual needs. This avoids energy waste or insufficient heat dissipation with fixed heat dissipation methods, maintaining a suitable operating temperature for the transformer.

[0034] Step S4, Fault Warning and Diagnosis: A machine learning algorithm is used to establish an operational status assessment model and a fault prediction model. Based on the comparison between the operational status obtained in Step S2 and the warning threshold, a warning signal is issued when the data deviates from the normal range and reaches the warning threshold. Simultaneously, the fault type and location are analyzed and determined, and troubleshooting suggestions are output. The machine learning algorithm learns from historical operational data and fault cases to form a fault identification model. When the operational status data output in Step S2 matches abnormal characteristics, the fault type and location are quickly matched, and a warning is issued. This allows for the early detection of potential faults, providing troubleshooting directions for maintenance personnel and reducing the impact of faults.

[0035] In this embodiment, the multiple temperature thresholds in step S3 include: a first temperature threshold corresponding to starting a low-speed cooling fan, a second temperature threshold corresponding to controlling the cooling fan to run at full speed, and a third temperature threshold corresponding to starting the liquid cooling auxiliary cooling system. Based on the heat dissipation requirements corresponding to different operating temperature ranges of the transformer, different temperature trigger nodes are set. Low-intensity heat dissipation is initiated in the low-temperature range, and high-intensity heat dissipation is initiated in the high-temperature range, avoiding waste of heat dissipation resources. This allows for graded adaptation of heat dissipation intensity, minimizing energy consumption while meeting heat dissipation requirements.

[0036] In this embodiment, the method for adjusting the heat dissipation capacity according to the load rate in step S3 includes: reducing the speed of the cooling fan or reducing the flow rate of the cooling oil pump when the load rate is lower than the set value; increasing the number of cooling fans or increasing the power of the liquid cooling system when the load rate exceeds the set value. The load rate directly reflects the power loss and heat generation of the transformer. When the load rate is low, less heat is generated, so the heat dissipation intensity can be reduced; when the load rate is high, more heat is generated, so the heat dissipation capacity needs to be increased. This allows the heat dissipation capacity to be precisely matched with the heat generation of the transformer, avoiding unnecessary energy consumption, while ensuring timely heat dissipation when heat generation increases.

[0037] In this embodiment, the machine learning algorithm in step S4 includes support vector machines, neural networks, or decision trees. Support vector machines can efficiently process high-dimensional data and accurately identify abnormal features in the data; neural networks can simulate the human learning process and improve the ability to identify complex fault features; and decision trees can clearly present the fault judgment logic, making it easy to quickly match fault types. In this way, the advantages of different algorithms can be utilized to improve the accuracy and efficiency of fault warning and diagnosis, and meet the fault identification needs in different scenarios.

[0038] During operation, step S1 is first executed to collect key physical quantity data of the transformer through sensors. Then, step S2 cleans and fuses the data and combines it with the operating status model to determine the current status of the equipment. Subsequently, step S3 dynamically adjusts the parameters of the heat dissipation system based on the temperature and load rate in the status data. At the same time, step S4 compares the status data with the early warning model, and issues an early warning and prompts fault information when an anomaly is detected. The entire method process is closely connected, realizing full-process intelligence from data acquisition to heat dissipation control and fault early warning, effectively ensuring the stable operation of the transformer and reducing energy consumption and fault risk.

[0039] The above technical features constitute the embodiments of the present invention, which have strong adaptability and implementation effect. Unnecessary technical features can be added or removed according to actual needs to meet the needs of different situations.

Claims

1. A transformer system based on intelligent monitoring and adaptive heat dissipation, characterized in that, include: The intelligent monitoring module is installed in key parts of the transformer and is used to collect physical data of the transformer in real time through sensors and transmit the collected data to the data processing and analysis unit. The data processing and analysis unit is used to receive data transmitted from the intelligent monitoring module, clean and fuse the data using data processing algorithms, establish a transformer operating status model, judge the operating status by comparing real-time data with model parameters, and transmit the analysis results to the adaptive heat dissipation control module and the fault early warning and diagnosis module. The adaptive heat dissipation control module is used to receive the operation status analysis results, dynamically adjust the operation parameters of the heat dissipation system based on the temperature threshold and load rate, control the heat dissipation intensity through multiple temperature threshold levels, and adjust the heat dissipation capacity according to the load rate changes. The fault early warning and diagnosis module is used to establish an operational status assessment model and a fault prediction model using machine learning algorithms. It receives operational status analysis results and compares them with early warning thresholds. When the data deviates from the normal range and reaches the early warning threshold, it issues an early warning signal. At the same time, it analyzes and judges the fault type and location and outputs troubleshooting suggestions.

2. The transformer system based on intelligent monitoring and adaptive heat dissipation according to claim 1, characterized in that, The installation locations of the intelligent monitoring module include the transformer windings, core, and tank walls.

3. The transformer system based on intelligent monitoring and adaptive heat dissipation according to claim 1, characterized in that, The intelligent monitoring module includes sensors such as temperature sensors, current sensors, voltage sensors, gas sensors, vibration sensors, and partial discharge sensors.

4. The transformer system based on intelligent monitoring and adaptive heat dissipation according to claim 1, 2, or 3, characterized in that, The intelligent monitoring module also includes a signal conditioning circuit, which amplifies and filters the collected raw data.

5. The transformer system based on intelligent monitoring and adaptive heat dissipation according to claim 1, 2, or 3, characterized in that, The fault warning and diagnosis module identifies fault types including winding short circuit and multi-point grounding of the iron core.

6. The transformer system based on intelligent monitoring and adaptive heat dissipation according to claim 1, 2, or 3, characterized in that, The transformer operating state model established by the data processing and analysis unit is a multi-dimensional model, which includes parameters related to temperature, current, voltage, and vibration frequency.

7. A transformer heat dissipation method based on intelligent monitoring and adaptive heat dissipation, characterized in that, Includes the following steps: Step S1, Data Acquisition: Real-time acquisition of physical quantity data during transformer operation is achieved by using sensors installed at key parts of the transformer. Step S2, Data Processing and Status Analysis: The collected data is cleaned and fused to establish a transformer operating status model. The operating status is determined by comparing real-time data with model parameters. Step S3, Adaptive heat dissipation control: Based on the operating status obtained in step S2, the operating parameters of the heat dissipation system are dynamically adjusted in combination with the temperature threshold and load rate. The heat dissipation intensity is controlled by multiple temperature threshold levels, and the heat dissipation capacity is adjusted according to the load rate. Step S4, Fault Warning and Diagnosis: A machine learning algorithm is used to establish an operating status assessment model and a fault prediction model. Based on the comparison between the operating status obtained in step S2 and the warning threshold, a warning signal is issued when the data deviates from the normal range and reaches the warning threshold. At the same time, the fault type and location are analyzed and the troubleshooting suggestions are output.

8. The transformer heat dissipation method based on intelligent monitoring and adaptive heat dissipation according to claim 7, characterized in that, The multiple temperature thresholds in step S3 include: the first temperature threshold corresponds to starting a low-speed cooling fan, the second temperature threshold corresponds to controlling the cooling fan to run at full speed, and the third temperature threshold corresponds to starting a liquid cooling auxiliary heat dissipation system.

9. The transformer heat dissipation method based on intelligent monitoring and adaptive heat dissipation according to claim 7 or 8, characterized in that, The method for adjusting the heat dissipation capacity according to the load rate in step S3 includes: reducing the speed of the cooling fan or reducing the flow rate of the cooling oil pump when the load rate is lower than the set value; increasing the number of cooling fans or increasing the power of the liquid cooling system when the load rate exceeds the set value.

10. The transformer heat dissipation method based on intelligent monitoring and adaptive heat dissipation according to claim 7 or 8, characterized in that, The machine learning algorithms in step S4 include support vector machines, neural networks, or decision trees.

Images