A substation transformer cooling control system and method

Abstract

This invention relates to the technical field of transformer cooling control, and discloses a substation transformer cooling control system and method, including an oil-immersed cooling tank, an oil flow pipe, and heat sinks. The transformer dissipates heat through oil immersion, with cooling oil flowing into the oil flow pipe to exchange heat with the air. After heat exchange, the cooling oil flows back into the transformer for oil immersion cooling. The transformer auxiliary cooling system includes a temperature detection unit and a particle size spray control unit. The temperature detection unit predicts changes in transformer temperature, and the particle size spray control unit receives the predicted temperature changes and adjusts the water mist particle size accordingly. If the temperature is abnormal, a cooling fan is activated. The speed of the cooling fan is determined by the level of temperature abnormality, thus achieving graded control of transformer cooling and intelligent control of controllable particle size.

Description

Technical Field

[0001] This invention relates to the technical field of transformer cooling control, and discloses a substation transformer cooling control system and method. Background Technology

[0002] Substation transformers generate significant heat during operation due to winding and core losses. Inadequate heat dissipation can lead to insulation aging, shortened lifespan, and even safety accidents. Traditional oil-immersed transformer cooling systems primarily rely on a combination of oil circulation and air cooling. Conventional oil pipes have smooth inner walls, resulting in predominantly laminar oil flow and insufficient heat exchange area. The simple layout of heat sinks and short air convection paths significantly reduce heat dissipation capacity at high temperatures. Traditional temperature detection often uses single-point sensors, failing to comprehensively perceive temperature gradients in transformer windings, oil, and cooling pipes. Spray cooling systems lack dynamic particle size adjustment mechanisms, resulting in fixed droplet sizes and potential for incomplete evaporation or overcooling under varying loads. When transformer overload causes a sudden temperature rise, existing systems struggle to respond quickly, relying on single-air cooling or fixed spray patterns with limited heat dissipation efficiency and posing a risk of temperature runaway. Summary of the Invention

[0003] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0004] To solve the above-mentioned technical problems, the main objective of this invention is to provide a substation transformer cooling control system, comprising:

[0005] The transformer cooling system includes an oil-immersed cooling box, oil flow pipes, and heat sinks;

[0006] The transformer cools itself by oil immersion. Cooling oil flows into the oil flow pipe and exchanges heat with the air. After the heat exchange is completed, the cooling oil flows back into the transformer for oil immersion cooling.

[0007] The transformer auxiliary heat dissipation includes a temperature detection unit and a particle size spray control unit. The temperature detection unit predicts the temperature change of the transformer, and the particle size spray control unit receives the predicted temperature change and adjusts the water mist particle size accordingly.

[0008] The transformer cooling cycle includes a cooling fan, a water collection channel, and convection plates. If the temperature is abnormal, the cooling fan is activated, and the speed of the cooling fan is determined by the level of temperature abnormality.

[0009] As a preferred embodiment of the substation transformer cooling control system of the present invention, wherein:

[0010] The transformer cooling body is used for heat dissipation of substation transformers. The oil flow pipe adopts an inner and outer double spiral structure. The inner spiral pipe wall is embedded with a silicon carbide nano-coating, and the outer spiral pipe is attached with a biomimetic shark skin corrugated surface.

[0011] The transformer dissipates heat through oil immersion. The cooling oil flows into the oil flow pipe through the inlet and is connected to the oil-immersed cooling tank at the bottom of the transformer. The outlet extends to the oil-immersed cooling tank at the top of the transformer. An eddy current generator is installed at the interface of the oil flow pipe to force the cooling oil to form turbulence.

[0012] As a preferred embodiment of the substation transformer cooling control system of the present invention, wherein:

[0013] The temperature detection unit includes a first distributed temperature sensor, a second distributed temperature sensor, and a third distributed temperature sensor.

[0014] The first distributed temperature sensor is located in the top winding area of ​​the transformer and is used to obtain the temperature of the top winding of the transformer.

[0015] The second distributed temperature sensor is installed on the inner wall of the bottom oil-immersed cooling box to obtain the temperature of the oil-immersed cooling box;

[0016] The third distributed temperature sensor is located at the outlet of the oil flow pipeline and is used to obtain the temperature at the outlet of the oil flow pipeline.

[0017] The temperature data acquired by the temperature detection unit is connected to the central controller via a CAN bus. The central controller collects the temperature and predicts temperature changes through machine learning, and adjusts the spray particle size based on the predicted temperature changes.

[0018] As a preferred embodiment of the substation transformer cooling control system of the present invention, wherein:

[0019] The particle size spray control unit applies vibration waves and reverse vibration waves to break the water flow into particle size droplets.

[0020] As a preferred embodiment of the substation transformer cooling control system of the present invention, wherein:

[0021] A paraffin or graphene composite phase change material box is placed on top of the transformer. When the temperature exceeds the maximum threshold, it automatically melts and absorbs heat, while triggering a micro air pump to force cold air into the phase change zone.

[0022] As a preferred embodiment of the substation transformer cooling control system of the present invention, wherein:

[0023] Methods for adjusting spray particle size by predicting temperature changes include:

[0024] Obtain the temperature of the transformer top winding, the temperature at the oil flow pipe outlet, and the temperature of the bottom oil-immersed cooling box;

[0025] Temperature data synchronization timestamps are used to weight and fuse the acquired temperature data by setting weights for the temperatures of the transformer top winding, oil flow pipe outlet, and bottom oil-immersed cooling box.

[0026] Input the processed transformer top winding temperature, oil flow pipe outlet temperature, and bottom oil immersion cooling box temperature data into the temperature detection unit;

[0027] The temperature detection unit predicts the transformer's temperature change rate based on the input temperature data;

[0028] The particle size control strategy is obtained by referring to the mapping table of particle size and temperature change rate, and the piezoelectric drive parameters are adjusted according to the particle size control strategy.

[0029] As a preferred embodiment of the substation transformer cooling control system of the present invention, wherein:

[0030] The substation transformer is set with a high temperature threshold and a safety threshold. If the temperature of the substation transformer exceeds the high temperature threshold, a transformer abnormality is triggered. If the temperature of the substation transformer does not reach the high temperature threshold but exceeds the safety threshold, a temperature alarm is triggered.

[0031] The output of the particle size spray control unit includes fine particle size water mist, mixed particle size water mist, and ultrafine particle size water mist;

[0032] The relationship between the temperature anomaly level and the spray particle size is as follows:

[0033] If the temperature does not exceed the safety threshold, the particle size spray control unit outputs fine particle size water mist.

[0034] If the temperature does not exceed the high temperature threshold but exceeds the safety threshold, the particle size spray control unit outputs a mixed particle size water mist.

[0035] If the temperature exceeds the high temperature threshold, the particle size spray control unit outputs ultrafine particle size water mist.

[0036] As a preferred embodiment of the substation transformer cooling control system of the present invention, wherein:

[0037] The convection plate is wound into a spiral tower-shaped structure, and the outer surface of the spiral tower-shaped structure is provided with a wave-shaped flow-guiding groove.

[0038] The outlet of the water collection channel extends to the root of the spiral convection vane. When the cooling fan starts, the axial airflow generated by the fan interacts with the spiral convection vane to form a centrifugal vortex, causing fine water droplets to spiral upward along the guide groove, and the droplets spread a liquid film on the surface of the copper and aluminum sheet.

[0039] The graded control of the cooling fan includes:

[0040] In case of a first-level temperature abnormality, the spray system is shut down, the cooling fan switches to pure air-cooling mode, and the airflow dissipates heat from the oil flow pipes and heat sinks of the transformer through the spiral convection vanes;

[0041] When a secondary temperature anomaly is detected, the spray coordination mode is activated. The cooling fan operates, driving fine-particle water mist into the spiral convection vanes, while simultaneously triggering the solenoid valve of the water collection channel to release recycled water.

[0042] As a preferred embodiment of the substation transformer cooling control system of the present invention, wherein:

[0043] The hot and humid air after spraying enters the cyclone condenser, where liquid water and steam are separated by centrifugal force. The liquid water is then returned to the storage tank after being filtered through a two-stage process of activated carbon and ceramic membrane.

[0044] Steam is condensed and recovered via a semiconductor cooling chip, and intelligent water replenishment is achieved in conjunction with a humidity sensor.

[0045] A method for controlling the cooling of a substation transformer, comprising:

[0046] The hot oil inside the transformer flows into the inner and outer double-helix structure oil flow pipe through the bottom oil-immersed cooling box. After exchanging heat with the outside air through the heat sink, the low-temperature oil flows back to the transformer from the outlet of the oil flow pipe, forming a closed oil circulation.

[0047] The system is equipped with a first distributed temperature sensor to collect the winding temperature in real time, a second distributed temperature sensor to monitor the oil temperature and oil heat dissipation efficiency, and a third distributed temperature sensor to provide feedback on the final cooling effect of the circulating oil. The temperature data is transmitted to the central controller via the CAN bus. Based on machine learning algorithms, the system predicts temperature change trends and adjusts the cooling strategy in advance.

[0048] The temperature change trend is received to control the particle size spray and cool the transformer. If an abnormal temperature occurs, the cooling fan is controlled in stages and the spray coordination mode is activated for heat dissipation.

[0049] The beneficial effects of this invention are:

[0050] This application adopts an oil flow pipe with an inner and outer double helix structure, which significantly improves the thermal conductivity. The outer helix tube is equipped with a biomimetic sharkskin corrugated surface, which effectively reduces fluid resistance. The vortex generator set at the oil pipe outlet forces the cooling oil to form turbulence, which greatly increases the convective heat transfer coefficient between the oil and the inner wall of the pipe.

[0051] This application uses a distributed temperature sensor network and machine learning algorithms to acquire and predict transformer temperature data. By using the predicted temperature data as feedback, coaxial dual-ring piezoelectric ceramic spray technology is used to interfere and control droplet size, thus solving the problems of response lag and coarse particle size control in traditional systems.

[0052] This invention constructs a transformer cooling system with high heat dissipation efficiency, precise control capability and strong reliability through an integrated design of multi-level coordinated oil immersion heat dissipation and auxiliary heat dissipation, which meets the intelligent operation and maintenance needs of substation equipment under high temperature and high load conditions. Attached Figure Description

[0053] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0054] Figure 1 This is a schematic diagram of the structure of a substation transformer cooling control system according to the present invention;

[0055] Figure 2 This is a flowchart illustrating the implementation of a substation transformer cooling control method according to the present invention;

[0056] Figure 3 This is a flowchart of a method for adjusting spray particle size based on temperature changes in a substation transformer cooling control method according to the present invention.

[0057] Figure 4 This is a schematic diagram of the outer heat sink of the oil flow pipe in a substation transformer cooling control system according to the present invention.

[0058] Figure 5 This is a schematic diagram of the inner and outer double helix structure in a substation transformer cooling control system according to the present invention.

[0059] Reference numerals: 1. Cooling oil; 2. Transformer winding; 3. Water tank; 4. Particle size spray control unit; 5. Cooling fan; 6. Inner and outer double spiral oil flow pipes; 7. Spray water guide pipe; 8. Water recovery pipe; 9. Eddy current generator; 10. First distributed temperature sensor; 11. Second distributed temperature sensor; 12. Third distributed temperature sensor; 13. Trench. Detailed Implementation

[0060] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0061] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0062] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0063] Example 1:

[0064] like Figure 1 As shown, a substation transformer cooling control system includes:

[0065] 1. Cooling oil; 2. Transformer winding; 3. Water storage tank; 4. Particle size spray control unit; 5. Cooling fan; 6. Inner and outer double spiral oil flow pipes; 7. Spray water guide pipes; 8. Water recovery pipes.

[0066] A substation transformer cooling control system is also equipped with an eddy current generator 9, a first distributed temperature sensor 10, a second distributed temperature sensor 11, a third distributed temperature sensor 12, and a trench 13.

[0067] Cooling oil 1 serves as the core heat-conducting medium for the transformer. It absorbs the heat generated by the transformer windings 2 during operation through oil immersion, forming a high-temperature oil. Passing through the inner and outer double-helix oil flow pipes 6, it undergoes forced heat exchange with the outside air, releasing heat before flowing back to the transformer oil-immersed cooling tank, thus achieving cyclic heat dissipation. Its fluidity and thermal conductivity directly affect the transformer's temperature field distribution. Combined with the eddy current generator 9 at the pipe interface to create turbulence, it can significantly improve heat exchange efficiency.

[0068] As the core component of power conversion, transformer winding 2 achieves voltage transformation through electromagnetic induction. During operation, Joule heat is generated due to copper and iron losses, which is the main heat source of the system. The external part is completely submerged in cooling oil 1, which absorbs the heat of the winding through oil convection and conduction, maintaining its temperature within a safe threshold and ensuring electromagnetic conversion efficiency and insulation reliability.

[0069] The water storage tank 3 stores the water required by the spray cooling system and provides a stable water supply to the particle size spray control unit 4; it has a built-in water quality filter to prevent impurities from clogging the spray pipes; it is equipped with a water level sensor and a pressure regulating valve to monitor the water volume in real time and maintain a stable water supply pressure to ensure the continuous operation of the spray system.

[0070] The particle size spray control unit 4 breaks the water flow into droplets of different sizes based on the temperature change predicted by the temperature detection unit. For example, in a specific implementation of this application, a preferred particle size droplet setting standard can be set as fine particle size of 50-100μm, mixed particle size of 10-100μm, and ultrafine particle size <30μm.

[0071] Furthermore, the conventional temperature control outputs fine-particle water mist to reduce the temperature of the transformer surface and surrounding air through evaporation and heat absorption; the emergency heat dissipation outputs ultra-fine water mist to maximize the utilization rate of latent heat of vaporization, and in conjunction with the cooling fan 5 to enhance gas-liquid heat exchange, quickly suppressing the sudden rise in oil temperature.

[0072] Cooling fan 5 adjusts its speed according to the level of temperature anomaly, driving airflow to enhance heat dissipation:

[0073] In case of Level 1 abnormal low-speed operation or shutdown, it relies on natural convection of the spiral convection vanes for energy-saving operation;

[0074] The second-level abnormal medium-speed operation, in conjunction with the spray system, promotes the diffusion of mist droplets, forming a composite heat dissipation of air cooling and mist cooling;

[0075] Level 3 abnormal operation at full speed, forced air convection, combined with ultra-fine water mist and phase change material box, to achieve emergency cooling under extreme conditions.

[0076] The spray water pipe 7 connects the water storage tank 3 and the particle size spray control unit 4 to deliver clean water to the spray device; the inner wall of the pipe is smoothed and a one-way valve is installed to prevent backflow of water and impurities; the pipe diameter and wall thickness are designed according to the maximum flow rate of the spray system to ensure stable water pressure and meet the water supply requirements of sprays with different particle sizes.

[0077] Inside the collection tower of the water recovery pipeline 8, a guide vane group can be installed to recover unevaporated droplets on the surface of the inner and outer double spiral oil flow pipeline 6. The droplets are then returned to the water storage tank 3 through the water collection channel, realizing the recycling of water resources. A filter screen is installed at the inlet of the water recovery pipeline 8 to intercept impurities in the air, and a solenoid valve is installed at the outlet to control the return rate. This, together with a water level sensor, maintains the water balance in the water storage tank 3, avoiding liquid accumulation on the ground and waste of resources.

[0078] The transformer cooling system includes an oil-immersed cooling box, oil flow pipes, and heat sinks;

[0079] The transformer cools down by oil immersion. Cooling oil 1 flows into the oil flow pipe and exchanges heat with the air. After the heat exchange is completed, the cooling oil 1 flows back into the transformer for oil immersion cooling.

[0080] The transformer cooling body is used for heat dissipation of the substation transformer, and the oil flow pipeline adopts an inner and outer double spiral oil flow pipeline 6 to form a circulation channel for cooling oil 1.

[0081] The transformer cools itself by oil immersion. The cooling oil 1 flows into the oil flow pipe through the inlet and is connected to the oil immersion cooling box at the bottom of the transformer. The outlet extends to the oil immersion cooling box at the top of the transformer. An eddy current generator 9 is installed at the outlet of the oil flow pipe to force the cooling oil 1 to form turbulence.

[0082] Specifically, the oil flow pipeline adopts a spiral structure, which increases the heat exchange area and oil flow path compared to straight pipes, such as... Figure 4 As shown, the heat sink can be made of corrugated aluminum alloy sheet, with vertical airflow arranged on the outer surface of the inner and outer double spiral oil flow pipes 6. Since the corrugated structure can increase the heat dissipation area and the aluminum alloy material can improve the thermal conductivity, the vertical airflow arrangement can form turbulence to enhance convective heat transfer and improve the heat dissipation efficiency of the oil flow pipes.

[0083] Furthermore, a method for implementing an inner and outer double helix structure includes:

[0084] The inner spiral pipe serves as the main cooling channel, transporting cooling oil that wraps around transformer winding 2 and the core. The outer spiral pipe surrounds the inner layer, maintaining a distance from the side wall of the oil tank to form an auxiliary cooling layer. The inner and outer oil flow directions are designed to flow in opposite directions, achieving full counter-current heat exchange and improving heat exchange efficiency.

[0085] like Figure 5 As shown, the inner spiral pipe is marked with a solid line and the outer spiral pipe is marked with a dashed line.

[0086] The channel seal adopts a whole plate rolling technology. The inner and outer spiral channels are sealed by integral molding and welding to avoid the risk of leakage caused by seams. The outer channel is fixed to the inner wall of the oil tank by a square steel support structure, which reduces welding points and enhances the overall rigidity.

[0087] A vortex generator 9 is installed at the interface of the oil flow pipeline. The vortex generator 9 causes local vortices in the oil flow, increasing fluid disturbance.

[0088] The dual-path oil pump drive system is equipped with multiple independent oil pumps. These pumps control the oil flow velocity in the inner and outer spiral channels, and the flow distribution is regulated by plate valves. The oil pump inlets are located in the oil storage area at the bottom of the transformer, and the outlets are split into two paths, injecting into the inner and outer spiral inlets respectively, forming a closed-loop circulation.

[0089] The direction of groove 13 is at a certain angle to the direction of oil flow, which reduces flow resistance.

[0090] Furthermore, the dual-helix synergistic heat dissipation mechanism:

[0091] The inner spiral layer tube wall is embedded with a silicon carbide nano-coating, which rapidly conducts heat to the tube wall and dissipates heat through radiation and convection.

[0092] In this embodiment, a preferred design of the outer spiral layer includes that the outer spiral layer can be configured as a biomimetic sharkskin corrugated surface to increase the heat dissipation area, and the interlayer gap can be filled with thermal grease to ensure the continuity of heat transfer between the inner and outer layers.

[0093] The transformer auxiliary heat dissipation includes a temperature detection unit and a particle size spray control unit 4. The temperature detection unit predicts the temperature change of the transformer, and the particle size spray control unit 4 receives the predicted temperature change and adjusts the water mist particle size accordingly.

[0094] The temperature detection unit includes a first distributed temperature sensor 10, a second distributed temperature sensor 11, and a third distributed temperature sensor 12.

[0095] The first distributed temperature sensor 10 is disposed in the top winding area of ​​the transformer to obtain the temperature of the top winding of the transformer;

[0096] The second distributed temperature sensor 11 is installed on the inner wall of the bottom oil-immersed cooling box to obtain the temperature of the oil-immersed cooling box;

[0097] The third distributed temperature sensor 12 is located at the outlet of the oil flow pipeline and is used to obtain the temperature at the outlet of the oil flow pipeline.

[0098] The temperature data acquired by the temperature detection unit is connected to the central controller via a CAN bus. The central controller collects the temperature and predicts temperature changes through machine learning, and adjusts the spray particle size based on the predicted temperature changes.

[0099] In this embodiment, a preferred example is that the particle size spray control unit 4 can break the water flow into controllable particle size droplets through the acoustic interference effect.

[0100] A specific implementation method for selecting and installing a temperature sensor includes:

[0101] The first distributed temperature sensor 10 can be a fiber optic grating temperature sensor, with multiple measuring points arranged at equal intervals along the top circumference of the transformer winding 2.

[0102] The second distributed temperature sensor 11 uses multiple corrosion-resistant temperature sensors, which are installed at the four corners and the center measuring point of the inner wall of the cooling box, and automatically switch when there is an abnormality.

[0103] The third distributed temperature sensor 12 is installed at the oil flow pipeline outlet.

[0104] A specific implementation method for data fusion and transmission includes:

[0105] The system integrates the raw temperature data from the first distributed temperature sensor 10, the second distributed temperature sensor 11, and the third distributed temperature sensor 12 in real time, and eliminates single-point noise through a weighted average algorithm. The weights are dynamically adjusted according to the sensor accuracy.

[0106] Extract features such as temperature change rate and gradient distribution.

[0107] The control strategy is triggered based on the fusion result. For example, the control strategy may include a daily temperature control mode or an emergency temperature control mode.

[0108] A specific implementation method for linking temperature prediction and particle size control includes:

[0109] The input features of the machine learning model include real-time temperature sequence, oil flow rate, ambient temperature and humidity, and load current.

[0110] Through convolution operations or temporal feature extraction processes using machine learning models, the future temperature change rate ΔT is output from the output terminal.

[0111] Set up training data to train the machine learning model. The machine learning model can be selected as an LSTM model, etc.

[0112] The prediction results are divided into multiple levels. For example, the prediction results can be divided into three levels: Level 1: ΔT < A℃ / min corresponds to steady-state mode, and the particle size is not adjusted; Level 2: A℃ / min ≤ ΔT < B℃ / min corresponds to early warning mode, which triggers fine particle size spraying; Level 3: ΔT ≥ B℃ / min corresponds to emergency mode, which adjusts ultra-fine particle size spraying and fan speed to full speed. Here, A and B are the temperature change rate thresholds, which can be set according to actual needs.

[0113] like Figure 3 As shown, the method for adjusting spray particle size by predicting temperature changes includes:

[0114] Obtain the temperature of the transformer top winding, the temperature at the oil flow pipe outlet, and the temperature of the bottom oil-immersed cooling box;

[0115] Temperature data synchronization timestamps are used to weight and fuse the acquired temperature data by setting weights for the temperatures of the transformer top winding, oil flow pipe outlet, and bottom oil-immersed cooling box.

[0116] Input the processed transformer top winding temperature, oil flow pipe outlet temperature, and bottom oil immersion cooling box temperature data into the temperature detection unit;

[0117] The temperature detection unit predicts the transformer's temperature change rate based on the input temperature data;

[0118] The particle size control strategy is obtained by referring to the mapping table of particle size and temperature change rate, and the piezoelectric drive parameters are adjusted according to the particle size control strategy.

[0119] A method for predicting temperature changes and adjusting spray particle size includes:

[0120] The temperature detection unit includes temperature data acquisition and processing, data fusion and anomaly filtering, temperature prediction and hierarchical control.

[0121] The top winding sensor is embedded in the top of transformer winding 2 to monitor the temperature of the area most prone to overheating in real time. The sensor is an anti-electromagnetic interference fiber optic grating sensor.

[0122] The bottom oil-immersion cooling tank sensor is installed on the inner wall of the cooling tank to monitor changes in oil temperature.

[0123] The oil flow pipeline outlet sensor captures the temperature of the oil flow after heat dissipation in real time through infrared non-contact temperature measurement.

[0124] The central controller assigns weights to winding temperature, oil temperature, and outlet temperature according to priority, and calculates the comprehensive temperature value.

[0125] The input features are real-time temperature sequence, oil flow rate, ambient temperature and humidity, and transformer load current.

[0126] Based on historical temperature sequences, oil flow rate, ambient temperature and humidity, and transformer load current, a time-series prediction model is trained. The model can be updated online to adapt to equipment aging.

[0127] Temperature anomalies are classified into four levels: normal, warning, moderate, and emergency.

[0128] In normal conditions, the spray is turned off and heat dissipation relies solely on air cooling; in the warning state, fine-particle water mist is activated to cover the surface of the heat sink and form a uniform water film; in the moderate abnormal state, it switches to mixed-particle water mist to enhance evaporation efficiency; in the emergency state, ultra-fine-particle water mist is triggered, and nano-sized droplets penetrate into the gaps to quickly absorb heat, and the fan runs at full speed.

[0129] Furthermore, the spray particle size can be adjusted by predicting temperature changes through the mapping between particle size and temperature prediction. Specifically, the mapping between particle size and temperature prediction can be obtained by referring to the theoretical mapping rules between the rated temperature of the transformer and the particle size and temperature in different environments.

[0130] The specific implementation method of the spray particle size dynamic control mechanism is as follows:

[0131] In this embodiment, a preferred embodiment of a particle size spray control unit 4 includes:

[0132] The particle size spray control unit 4 can be equipped with a piezoelectric ceramic nozzle to control the droplet size.

[0133] The piezoelectric ceramic driving principle is a double-ring vibration interference. The inner ring generates a basic sound wave through high-frequency vibration, which cuts the water flow into larger droplets. The outer ring vibrates in the opposite or same direction, and the droplets are further broken up through the superposition and interference of the sound waves.

[0134] The smooth transition design includes gradual adjustment and feedback calibration;

[0135] The gradual adjustment involves switching the piezoelectric drive parameters gradually as the temperature change rate crosses different levels, thus avoiding water flow impact or unstable atomization.

[0136] Feedback calibration involves real-time monitoring of droplet size and dynamic fine-tuning of frequency and phase to ensure that the actual droplet size matches the target.

[0137] This solution achieves dynamic optimization of transformer heat dissipation through a deep integration of high-precision temperature prediction and piezoelectric spray control, providing an efficient, reliable, and easy-to-maintain intelligent cooling system for transformers without relying on complex mathematical models.

[0138] The transformer cooling cycle includes a cooling fan 5, a water collection channel, and convection plates. If the temperature is abnormal, the cooling fan 5 is started, and the speed of the cooling fan 5 is determined by the temperature abnormality level.

[0139] When the cooling fan 5 starts, it causes fine water droplets to spiral down along the pre-guided grooves, and the droplets spread a liquid film on the surface of the copper and aluminum sheets.

[0140] The graded control of the cooling fan 5 includes:

[0141] In case of a first-level temperature abnormality, the spray system is shut down and the cooling fan 5 is switched to pure air-cooling mode. The airflow passes through the spiral convection plate to dissipate heat from the oil flow pipe and the heat sink of the transformer. The convection plate is wound into a spiral tower-shaped structure and installed between the oil flow pipe outlet end and the cooling fan 5. The outer surface is provided with a wave-shaped flow guide groove.

[0142] When a secondary temperature anomaly is detected, the spray coordination mode is activated, and the cooling fan 5 operates, driving fine-particle water mist into the spiral convection vanes. At the same time, the solenoid valve of the water collection channel is triggered to release recycled water.

[0143] The mode switching principle is that for first-level temperature anomalies, the latent heat of vaporization is utilized first; for second-level temperature anomalies, the insulation performance is avoided due to spraying at high temperatures.

[0144] Example 2:

[0145] like Figure 2 As shown, a method for controlling the cooling of a substation transformer includes:

[0146] The hot oil inside the transformer flows into the inner and outer double-helix structure oil flow pipe through the bottom oil-immersed cooling box. After exchanging heat with the outside air through the heat sink, the low-temperature oil flows back to the transformer from the outlet of the oil flow pipe, forming a closed oil circulation.

[0147] The first distributed temperature sensor 10 is set to collect the winding temperature in real time, the second distributed temperature sensor 11 monitors the oil temperature and oil heat dissipation efficiency, and the third distributed temperature sensor 12 provides feedback on the final cooling effect of the circulating oil.

[0148] Temperature data is transmitted to the central controller via the CAN bus, and the future temperature change trend is predicted based on machine learning algorithms to adjust the cooling strategy in advance.

[0149] A specific implementation method for using a machine learning algorithm to predict future changes includes:

[0150] The asynchronous sampling data from the first distributed temperature sensor 10, the second distributed temperature sensor 11, and the third distributed temperature sensor 12 are calibrated to a uniform time interval using timestamps. Short-term missing data is filled using a sliding window interpolation method, while sudden abnormal values ​​are detected and corrected.

[0151] A multi-dimensional feature vector containing real-time winding temperature, oil temperature, heat dissipation efficiency, cooling effect, ambient temperature, and load power is constructed to form a time-series dataset.

[0152] By taking the historical characteristics of the previous N time steps as input, the inertial pattern of temperature change is captured; the trend and periodicity characteristics of derived indicators such as the winding temperature rise rate per unit time, the heat dissipation efficiency fluctuation coefficient, and the correlation coefficient between cooling effect and oil temperature are calculated.

[0153] Machine learning prioritizes algorithms that can capture long-range dependencies, such as LSTM-like time-series neural networks, which include an input layer, a feature encoding layer, and a prediction output layer.

[0154] Specifically, the input layer receives a time-series dataset containing both original and derived features.

[0155] The feature encoding layer extracts short-term temperature fluctuations and long-term trends at different time scales through temporal convolution.

[0156] The prediction output layer outputs the predicted winding temperature and oil temperature values ​​for the next T time steps, supporting multi-step prediction.

[0157] Furthermore, the rate of change of winding temperature must not exceed the theoretical threshold of the thermal conductivity characteristics of the transformer material, serving as a filtering rule for anomaly prediction.

[0158] Training samples are generated using the sliding window method, and the input samples contain multidimensional feature vectors for K consecutive time steps.

[0159] Output short-term and medium-term predicted temperature values ​​for multiple future time steps.

[0160] Data sets can be divided according to season and load patterns. For example, samples from high-load periods and low-load periods can be trained separately to improve the model's adaptability to different operating scenarios.

[0161] Multi-objective optimization is adopted, which simultaneously improves the prediction accuracy of winding temperature and oil temperature, and the weights are dynamically adjusted according to the transformer safety level.

[0162] Adversarial example training is introduced, artificially injecting simulated cooling system failure data to enhance the model's robustness in predicting abnormal operating conditions.

[0163] Rolling prediction validation is employed, using data from the previous year for training and data from the following three months for daily validation. The latest week's data is updated to the training set every day to simulate an online learning scenario.

[0164] The controllable particle size regulation adjusts the receiving temperature change trend, controls the particle size spray, and cools the transformer. If an abnormal temperature occurs, a five-stage cooling fan control is adopted, and a spray coordination mode is activated for heat dissipation.

[0165] It is important to note that the constructions and arrangements of this application shown in several different exemplary embodiments are merely illustrative. Although only two embodiments are described in detail in this disclosure, those who consult this disclosure will readily understand that many modifications are possible without substantially departing from the novel teachings and advantages of the subject matter described in this application. For example, variations in the size, dimensions, structure, shape, and proportions of various elements, as well as parameter values ​​(e.g., temperature, pressure, etc.), mounting arrangements, use of materials, color, orientation, etc. For instance, an element shown as integrally formed may be composed of multiple parts or elements, the position of elements may be inverted or otherwise altered, and the nature or number or position of discrete elements may be changed or altered. Therefore, all such modifications are intended to be included within the scope of the invention. The order or sequence of any process or method steps may be changed or rearranged according to alternative embodiments. Any "device plus function" clause is intended to cover the structure performing the function described herein, and not only structurally equivalent but also equivalent in structure. Other substitutions, modifications, alterations, and omissions may be made in the design, operation, and arrangement of the exemplary embodiments without departing from the scope of the invention. Therefore, the present invention is not limited to the specific embodiments, but extends to various modifications that still fall within the scope of the appended invention.

[0166] Furthermore, in order to provide a concise description of exemplary embodiments, not all features of actual embodiments (i.e., those features that are not relevant to the best mode of carrying out the invention as currently considered, or those features that are not relevant to implementing the invention) may be omitted.

[0167] It should be understood that numerous specific implementation decisions can be made during the development of any practical implementation, such as in any engineering or design project. Such development efforts may be complex and time-consuming, but for those of ordinary skill in the art who benefit from this disclosure, the development effort will be a routine task in design, manufacturing, and production without requiring extensive experimentation.

[0168] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the present invention.

Claims

1. A substation transformer cooling control system, characterized in that, include: The transformer cooling system includes an oil-immersed cooling box, oil flow pipes, and heat sinks; The transformer cools itself by oil immersion. Cooling oil flows into the oil flow pipe and exchanges heat with the air. After the heat exchange is completed, the cooling oil flows back into the transformer for oil immersion cooling. The transformer auxiliary heat dissipation includes a temperature detection unit and a particle size spray control unit. The temperature detection unit collects the temperature of the transformer top winding, the temperature of the bottom oil-immersed cooling box, and the temperature at the oil flow pipe outlet, and transmits them to the central controller via the CAN bus. The central controller processes the temperature data and predicts temperature changes. The particle size spray control unit receives the predicted temperature changes output by the central controller and adjusts and controls the water mist particle size. The transformer cooling cycle includes a cooling fan, a water collection channel, and convection plates. The temperature anomaly level is determined based on the temperature data obtained by the temperature detection unit. If the temperature is abnormal, the cooling fan is started. The speed of the cooling fan is determined by the temperature anomaly level. The transformer cooling body is used for heat dissipation of substation transformers. The oil flow pipe adopts an inner and outer double spiral structure. The inner spiral pipe wall is embedded with a silicon carbide nano-coating, and the outer spiral pipe is attached with a biomimetic shark skin corrugated surface. The transformer cools itself by oil immersion. The cooling oil flows into the oil flow pipe through the inlet and is connected to the oil immersion cooling box at the bottom of the transformer. The outlet extends to the oil immersion cooling box at the top of the transformer. An eddy current generator is installed at the interface of the oil flow pipe to force the cooling oil to form turbulence. The particle size spray control unit receives predicted temperature changes from the central controller and adjusts the water mist particle size accordingly, including: Obtain the temperature of the transformer top winding, the temperature at the oil flow pipe outlet, and the temperature of the bottom oil-immersed cooling box; Temperature data synchronization timestamps are used to weight and fuse the acquired temperature data by setting weights for the temperatures of the transformer top winding, oil flow pipe outlet, and bottom oil-immersed cooling box. Input the processed transformer top winding temperature, oil flow pipe outlet temperature, and bottom oil immersion cooling box temperature data into the temperature detection unit; The temperature detection unit predicts the transformer's temperature change rate based on the input temperature data; The particle size control strategy is obtained by referring to the mapping table of particle size and temperature change rate, and the piezoelectric drive parameters are adjusted according to the particle size control strategy. The inner spiral pipe serves as the main cooling channel, used to transport cooling oil that wraps the transformer windings and core; the outer spiral pipe is arranged around the inner layer, maintaining a distance from the side wall of the oil tank to form an auxiliary cooling layer; the inner and outer oil flow directions are designed to flow in opposite directions; the output of the particle size spray control unit includes fine particle size water mist, mixed particle size water mist, and ultrafine particle size water mist.

2. The substation transformer cooling control system according to claim 1, characterized in that: The temperature detection unit includes a first distributed temperature sensor, a second distributed temperature sensor, and a third distributed temperature sensor. The first distributed temperature sensor is located in the top winding area of ​​the transformer and is used to obtain the temperature of the top winding of the transformer. The second distributed temperature sensor is installed on the inner wall of the bottom oil-immersed cooling box to obtain the temperature of the oil-immersed cooling box; The third distributed temperature sensor is located at the outlet of the oil flow pipeline and is used to obtain the temperature at the outlet of the oil flow pipeline. The temperature data acquired by the temperature detection unit is connected to the central controller via a CAN bus. The central controller processes the temperature data and predicts temperature changes, adjusting the spray particle size based on these predictions.

3. A substation transformer cooling control system according to claim 2, characterized in that: The particle size spray control unit applies vibration waves and reverse vibration waves to break the water flow into particle size droplets.

4. A substation transformer cooling control system according to claim 3, characterized in that: A phase change material box is placed on top of the transformer. When the temperature exceeds the maximum threshold, it automatically melts and absorbs heat, while triggering a micro air pump to force cold air into the phase change zone.

5. A substation transformer cooling control system according to claim 1, characterized in that: The substation transformer is set with a high temperature threshold and a safety threshold. If the temperature of the substation transformer exceeds the high temperature threshold, a transformer abnormality is triggered. If the temperature of the substation transformer does not reach the high temperature threshold but exceeds the safety threshold, a temperature alarm is triggered. The relationship between the temperature anomaly level and the spray particle size is as follows: If the temperature does not exceed the safety threshold, the particle size spray control unit outputs fine particle size water mist. If the temperature does not exceed the high temperature threshold but exceeds the safety threshold, the particle size spray control unit outputs a mixed particle size water mist. If the temperature exceeds the high temperature threshold, the particle size spray control unit outputs ultrafine particle size water mist.

6. A substation transformer cooling control system according to claim 5, characterized in that: The convection plate is wound into a spiral tower-shaped structure, and the outer surface of the spiral tower-shaped structure is provided with a wave-shaped flow-guiding groove. The outlet of the water collection channel extends to the root of the spiral convection vane. When the cooling fan starts, the axial airflow generated by the fan interacts with the spiral convection vane to form a centrifugal vortex, causing fine water droplets to spiral upward along the guide groove, and the droplets spread a liquid film on the surface of the copper and aluminum sheet. The graded control of the cooling fan includes: In case of a first-level temperature abnormality, the spray system is shut down, the cooling fan switches to pure air-cooling mode, and the airflow dissipates heat from the oil flow pipes and heat sinks of the transformer through the spiral convection vanes; When a secondary temperature anomaly is detected, the spray coordination mode is activated. The cooling fan operates, driving fine-particle water mist into the spiral convection vanes, while simultaneously triggering the solenoid valve of the water collection channel to release recycled water.

7. A substation transformer cooling control system according to claim 6, characterized in that: The hot and humid air after spraying enters the cyclone condenser, where liquid water and steam are separated by centrifugal force. The liquid water is then returned to the storage tank after being filtered through a two-stage process of activated carbon and ceramic membrane. Steam is condensed and recovered through a semiconductor cooling chip, and intelligent water replenishment is achieved in conjunction with a humidity sensor.

8. A method for cooling a substation transformer, implemented based on a substation transformer cooling control system according to any one of claims 1-7, characterized in that, The method includes the following specific steps: The hot oil inside the transformer flows into the inner and outer double-helix structure oil flow pipe through the bottom oil-immersed cooling box. After exchanging heat with the outside air through the heat sink, the low-temperature oil flows back to the transformer from the outlet of the oil flow pipe, forming a closed oil circulation. The system is equipped with a first distributed temperature sensor to collect the winding temperature in real time, a second distributed temperature sensor to monitor the oil temperature and oil heat dissipation efficiency, and a third distributed temperature sensor to provide feedback on the final cooling effect of the circulating oil. The temperature data is transmitted to the central controller via the CAN bus. Based on machine learning algorithms, the system predicts temperature change trends and adjusts the cooling strategy in advance. The temperature change trend is received to control the particle size spray and cool the transformer. If an abnormal temperature occurs, the cooling fan is controlled in stages and the spray coordination mode is activated for heat dissipation.

Images