Deep learning based motor cooling system adaptive optimization method

Abstract

This invention discloses an adaptive optimization method for motor cooling systems based on deep learning, belonging to the field of cooling system optimization technology. The method includes the following steps: installing temperature sensors at the coolant outlet and inlet of the motor cooling system to detect the outlet and inlet temperatures; calculating the heat exchange temperature difference of the motor cooling system based on the outlet and inlet temperatures and further calculating the heat exchange efficiency; analyzing the pump influence relationship between the pump power and heat exchange efficiency of the motor cooling system using historical operating data; analyzing the fan influence relationship between the fan power and heat exchange efficiency based on historical operating data; and optimizing the motor cooling system based on the pump influence relationship, temperature conversion relationship, and fan influence relationship. This invention addresses the problem that existing cooling system optimization technologies often fail to balance cooling efficiency and energy consumption, leading to excessive energy consumption in the cooling system.

Description

Technical Field

[0001] This invention relates to the field of cooling system optimization technology, specifically to an adaptive optimization method for motor cooling systems based on deep learning. Background Technology

[0002] Cooling system optimization technology refers to a series of engineering methods aimed at improving the overall performance of cooling systems. Its core lies in achieving the most efficient heat removal and management with the lowest energy consumption, cost, and space occupation, while ensuring the safe and reliable operation of the object being cooled (such as a motor) through active monitoring, dynamic adjustment, and control strategies.

[0003] For equipment like motors that easily generate high temperatures, traditional air cooling cannot meet their heat dissipation needs. Liquid cooling is usually required to provide better heat dissipation. However, existing cooling system optimization technologies typically only control the cooling system to dissipate heat from the motor, ensuring that the temperature of the cooling system is within a certain range, without optimizing the energy consumption of the cooling system. Different operating parameters in the cooling system may have the same heat dissipation effect. If only heat dissipation efficiency is considered, it will lead to high energy consumption of the cooling system. For example, in the patent application with publication number CN115547655A, a "method for optimizing the cooling system of the main transformer in a large thermal power plant" is disclosed. This solution does not consider the energy consumption of the cooling system, but only ensures that the cooling system reaches the required cooling efficiency. Existing cooling system optimization technologies also have insufficient balance between cooling efficiency and energy consumption, which leads to the problem of excessive energy consumption in the cooling system. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art. It involves installing temperature sensors at the coolant outlet and inlet of the motor cooling system to detect the outlet and inlet temperatures. Based on these temperatures, the heat exchange temperature difference across the motor's heat conductor is calculated, followed by the calculation of the heat exchange efficiency. Historical operating data is then used to analyze the influence of pump power and heat exchange efficiency on the pump. Similarly, historical operating data is used to analyze the influence of fan power and heat exchange efficiency on the fan. The required heat exchange efficiency for the motor components is then calculated, along with the required pump and fan power. Finally, the motor cooling system is optimized based on these required pump and fan power. This addresses the problem that existing cooling system optimization techniques often fail to balance cooling efficiency and energy consumption, leading to excessive energy consumption in the cooling system.

[0005] To achieve the above objectives, this application provides an adaptive optimization method for a motor cooling system based on deep learning, comprising the following steps: Temperature sensors are installed at the coolant outlet and coolant inlet of the motor cooling system to detect the outlet and inlet temperatures of the motor cooling system. The heat exchange temperature difference of the motor cooling system is calculated based on the outlet temperature and the inlet temperature, and the heat exchange efficiency is further calculated. Based on historical operating data of the motor cooling system, the influence relationship between the pump power and heat exchange efficiency of the motor cooling system is analyzed. Analysis of the fan influence relationship between fan power and heat exchange efficiency based on historical operating data; The motor cooling system is optimized based on the influence of water pumps, temperature conversion, and fans.

[0006] Furthermore, temperature sensors are installed at the coolant outlet and coolant inlet of the motor cooling system to detect the outlet and inlet temperatures of the motor cooling system, including the following sub-steps: Temperature sensors are installed at the coolant outlet and coolant inlet of the motor cooling system. The coolant outlet and coolant inlet are both connection ports between the cooler and the water distribution pipe in the motor cooling system. The coolant in the coolant outlet flows from the water distribution pipe to the cooler, and the coolant in the coolant inlet flows from the cooler to the water distribution pipe. The temperature of the coolant at the coolant outlet and coolant inlet is detected by temperature sensors and named outlet temperature and inlet temperature, respectively.

[0007] Furthermore, calculating the heat exchange temperature difference of the motor cooling system based on the outlet and inlet temperatures, and further calculating the heat exchange efficiency, includes the following sub-steps: The heat exchange temperature difference between the two sides of the heat conductor is calculated based on the outlet temperature and the inlet temperature. The heat exchange efficiency of the motor cooling system is calculated based on the heat exchange temperature difference.

[0008] Furthermore, calculating the heat exchange temperature difference across the heat conductor of the motor based on the outlet and inlet temperatures includes the following sub-steps: Obtain the outlet temperature and inlet temperature, denoted by the symbols TO and TI respectively, calculate TI-TO, and label the calculation result as ΔT; The specific heat capacity of the coolant is obtained, denoted by the symbol c, and the density of the coolant is obtained, denoted by the symbol ρ. Set a detection cycle and count the volume of coolant flowing through the coolant inlet within the detection cycle, represented by the symbol VL; The heat removed by the coolant during the testing period is called the cooling amount. The cooling amount is calculated using the formula Q1=ρ×VL×c×ΔT, where Q1 is the cooling amount. The contact area between the heat exchange chamber and the motor assembly in the motor cooling system is obtained and represented by the symbol S. The thermal conductivity and thickness of the heat conductor between the heat exchange chamber and the motor assembly are obtained and represented by the symbols λ and L, respectively. The detection period is marked as U. Q1 / U is calculated and Q1 is converted into heat flux and marked as Q2. The heat exchange temperature difference can be calculated using the formula Q2=ΔTC×λ×S / L, where ΔTC is the heat exchange temperature difference.

[0009] Furthermore, calculating the heat exchange efficiency of the motor cooling system based on the heat exchange temperature difference includes the following sub-steps: The temperature of the motor assembly before cooling is named the pre-cooling temperature and represented by the symbol TD. The convective heat transfer coefficient is obtained and represented by the symbol h. The temperature of the contact surface between the heat conductor and the coolant is calculated using the formula Q2=h×S×(TS-TI), where TS is the temperature of the contact surface between the heat conductor and the coolant. TS+ΔTC=TD is calculated. The temperature of the motor assembly after cooling is named the cooled temperature and represented by the symbol TL. The heat exchange efficiency is obtained by calculating (TD-TL) / TD.

[0010] Furthermore, analyzing the pump influence relationship between the pump power and heat exchange efficiency of the motor cooling system based on historical operating data includes the following sub-steps: Record historical operating data of the motor cooling system, including historical water pump power, fan power, outlet temperature, inlet temperature, temperature before cooling, temperature after cooling, heat exchange temperature difference, and heat exchange efficiency. Establish a plane rectangular coordinate system with pump power as the X-axis and heat exchange efficiency as the Y-axis, and name it the Pump Influence Analysis Diagram. Enter the heat exchange efficiency in the historical operating data into the Pump Influence Analysis Diagram according to the corresponding pump power. A function regression is performed on the pump influence analysis diagram, and the resulting curve is named the pump influence curve. The coordinate points in the pump influence analysis diagram are named the pump influence analysis points. The pump influence curve and the pump influence analysis points constitute the pump influence relationship.

[0011] Furthermore, analyzing the fan-related relationship between fan power and heat exchange efficiency based on historical operating data includes the following sub-steps: A plane rectangular coordinate system is established with heat exchange temperature difference as the X-axis and heat exchange efficiency as the Y-axis, named the Temperature Difference Influence Analysis Chart. The heat exchange efficiency in the historical operating data is entered into the Temperature Difference Influence Analysis Chart according to the corresponding heat exchange temperature difference. Perform function regression on the temperature difference influence analysis diagram, name the curve obtained from the regression as the temperature difference influence curve, and name the coordinate points in the temperature difference influence analysis diagram as temperature difference influence analysis points. Establish a Cartesian coordinate system with fan power as the X-axis and heat exchange temperature difference as the Y-axis, and name it Fan Heat Dissipation Analysis Chart. Enter the heat exchange temperature difference in the historical operating data into the Fan Heat Dissipation Analysis Chart according to the corresponding fan power. Perform function regression on the fan heat dissipation analysis diagram, name the curve obtained from the regression as the fan heat dissipation curve, and name the coordinate points in the fan heat dissipation analysis diagram as fan heat dissipation analysis points. The temperature difference influence curve, temperature difference influence analysis point, fan heat dissipation curve, and fan heat dissipation analysis point constitute the fan influence relationship.

[0012] Furthermore, optimizing the motor cooling system based on the influence relationships of the water pump and the fan includes the following sub-steps: Calculate the current required heat exchange efficiency for the motor assembly and the required power for the water pump and fan. The motor cooling system is optimized based on the required water pump power and fan power.

[0013] Furthermore, calculating the current required heat exchange efficiency of the motor assembly and the required water pump and fan power includes the following sub-steps: Calculate the current pre-cooling temperature of the motor assembly, named the real-time equipment temperature, denoted by the symbol T1. Obtain the optimal operating temperature of the motor assembly, denoted by the symbol T2. Calculate (T1-T2) / T1 to obtain the current required heat exchange efficiency of the motor assembly, named the real-time demand efficiency. Find the points in the pump influence curve and the temperature difference influence curve where the Y-axis equals the real-time demand efficiency, and name them the pump point to be analyzed and the temperature difference point to be analyzed, respectively. The pump point and temperature difference point to be analyzed are analyzed independently. When analyzing the pump point or temperature difference point, they are named real-time analysis points. If the real-time analysis point is the pump point to be analyzed, the pump power is named the main parameter, the pump influence curve is named the real-time main curve, the pump influence analysis point is named the main point, the heat exchange temperature difference is named the auxiliary parameter, the fan influence curve is named the real-time auxiliary curve, and the fan influence analysis point is named the auxiliary point. If the real-time analysis point is the fan point to be analyzed, the heat exchange temperature difference is named the main parameter, the fan influence curve is named the real-time main curve, the fan influence analysis point is named the main point, the pump power is named the auxiliary parameter, the pump influence curve is named the real-time auxiliary curve, and the pump influence analysis point is named the auxiliary point. Obtain the main point whose X-axis is equal to the real-time analysis point and name it as the effective point. Obtain the effective point that is below the real-time analysis point and is closest to it and name it as the effective lower point. Obtain the effective point that is above the real-time analysis point and is closest to it and name it as the effective upper point. At the same time, label the Y-axis values ​​of the effective upper point and the effective lower point as YU and YD respectively, label the real-time demand efficiency as PN, calculate YU / PN and YD / PN, and obtain the upper point ratio and the lower point ratio respectively. Obtain the auxiliary parameters corresponding to the valid upper and lower points in the historical running data, and name them the valid upper parameter and valid lower parameter respectively. Find the points in the real-time auxiliary curve whose X-axis is equal to the valid upper parameter and valid lower parameter, and name them the valid upper reference point and valid lower reference point respectively. Label the effective upper parameter and effective lower parameter as Y3 and Y4 respectively. Assume that the auxiliary parameter required at the real-time analysis point is RE. There is a relationship Y3 / RE=YU / PN. Solve RE and label it as E1. At the same time, there is a relationship Y4 / RE=YD / PN. Solve RE and label it as E2. Calculate (E1+E2) / 2. Name the calculation result as the required secondary parameter. At the same time, name the value of the X-axis corresponding to the real-time analysis point as the required primary parameter. If the heat exchange temperature difference is the main parameter, then find the point in the fan heat dissipation curve where the Y-axis is equal to the required main parameter, name it the fan requirement point, obtain the X-axis value corresponding to the fan requirement point, name it the fan requirement power, and name the required secondary parameter the water pump requirement power. If the heat exchange temperature difference is an auxiliary parameter, then find the point on the fan cooling curve where the Y-axis is equal to the required secondary parameter, name it the fan requirement point, obtain the corresponding X-axis value of the fan requirement point, name it the fan requirement power, and name the primary parameter the water pump requirement power.

[0014] Furthermore, optimizing the motor cooling system based on the required water pump power and fan power includes the following sub-steps: Using the water pump point to be analyzed as the real-time analysis point, analyze the fan power demand and water pump power demand, and label them as P1 and P2 respectively. Calculate P1+P2 to obtain the first total power. The fan power demand and water pump power demand are analyzed using the temperature difference point to be analyzed as the real-time analysis point, and marked as P3 and P4 respectively. P3+P4 is calculated to obtain the second total power. If the first total power is less than or equal to the second total power, then adjust the power of the water pump in the motor cooling system to P2 and the power of the fan to P1. If the first total power is greater than the second total power, then adjust the power of the water pump in the motor cooling system to P4 and the power of the fan to P3.

[0015] The beneficial effects of this invention are as follows: This invention installs temperature sensors at the coolant outlet and coolant inlet of the motor cooling system to detect the outlet and inlet temperatures of the motor cooling system. Then, it calculates the heat exchange temperature difference between the two sides of the motor's heat conductor based on the outlet and inlet temperatures, and then calculates the heat exchange efficiency of the motor cooling system based on the heat exchange temperature difference. The advantage is that in the process of calculating the heat exchange efficiency, the difference between the motor temperature and the coolant temperature is considered, rather than a certain temperature value. By considering the temperature difference, the influence of ambient temperature on heat dissipation can be eliminated, thus improving the accuracy and effectiveness of cooling system optimization. This invention analyzes the influence of pump power and heat exchange efficiency on the motor cooling system by combining historical operating data. Then, based on historical operating data, it analyzes the influence of fan power and heat exchange efficiency on the fan. Next, it calculates the current required heat exchange efficiency for the motor components and the required pump and fan power. Finally, it optimizes the motor cooling system based on the required pump and fan power. The advantage lies in the fact that pump power affects the coolant flow rate. While increasing the coolant flow rate reduces the contact time between the coolant and the heat exchange surface, it also increases turbulence and reduces the boundary layer thickness, thus enhancing heat transfer. Fan power affects the temperature difference between the coolant and the motor, i.e., the heat exchange temperature difference. The larger the heat exchange temperature difference, the greater the heat dissipation difference between the coolant and the motor. Heat is conducted from high-temperature to low-temperature areas, and the greater the temperature difference, the faster the heat conduction. Therefore, under the premise of meeting the current required heat exchange efficiency for the motor components, it calculates the required pump and fan power and finds the combination with the lowest energy consumption. This balances and optimizes the cooling system's heat dissipation efficiency and energy consumption, improving the accuracy, effectiveness, and rationality of the cooling system optimization. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the steps of the method of the present invention; Figure 2 This is a schematic diagram of the cold liquid outlet and cold liquid inlet of the present invention; Figure 3 This is a schematic diagram of the water pump influence analysis diagram of the present invention; Figure 4 This is a schematic diagram of the temperature difference effect analysis diagram of the present invention; Figure 5 This is a schematic diagram of the fan heat dissipation analysis diagram of the present invention; Figure 6 This is a schematic diagram of the real-time analysis point, effective upper point, and effective lower point of the present invention. Figure 7 This is a schematic diagram illustrating the effective upper reference point and the effective lower reference point of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1, please refer to Figure 1 As shown, this application provides an adaptive optimization method for a motor cooling system based on deep learning, including the following steps: Step S1 involves installing temperature sensors at the coolant outlet and coolant inlet of the motor cooling system to detect the outlet and inlet temperatures of the motor cooling system. Step S1 includes the following sub-steps: Please see Figure 2 As shown, in step S101, temperature sensors are installed at the coolant outlet and coolant inlet of the motor cooling system. The coolant outlet and coolant inlet are both connection ports between the cooler and the water distribution pipe in the motor cooling system. The coolant in the coolant outlet flows from the water distribution pipe to the cooler, and the coolant in the coolant inlet flows from the cooler to the water distribution pipe. Step S102: The temperature of the coolant at the coolant outlet and coolant inlet is detected by a temperature sensor and named the outlet temperature and inlet temperature, respectively. In practice, a liquid cooling system typically consists of components such as a heat exchange chamber, a heat dissipation chamber, and water distribution pipes. The heat exchange chamber contacts the motor assembly, transferring heat from the motor assembly to the coolant through heat conduction. The water distribution pipes transport the coolant, and the heat dissipation chambers cool the coolant using a fan. The positional relationships between the coolant outlet and inlet and the heat exchange chamber, heat dissipation chamber, and water distribution pipes are as follows: Figure 2 As shown, the outlet temperature and inlet temperature are detected by a temperature sensor.

[0019] Step S2 involves calculating the heat exchange temperature difference of the motor cooling system based on the outlet and inlet temperatures, and further calculating the heat exchange efficiency. Step S2 includes the following sub-steps: Step S201: Calculate the heat exchange temperature difference between the two sides of the motor heat conductor based on the outlet temperature and the inlet temperature. Step S201 includes the following sub-steps: Step S2011: Obtain the outlet temperature and inlet temperature, represented by the symbols TO and TI respectively, calculate TI-TO, and mark the calculation result as ΔT; Step S2012: Obtain the specific heat capacity of the coolant, represented by the symbol c, and obtain the density of the coolant, represented by the symbol ρ. Step S2013: Set the detection cycle and count the volume of coolant flowing through the coolant inlet within the detection cycle, represented by the symbol VL; Step S2014: The heat carried away by the coolant during the detection cycle is named the cooling amount. The cooling amount is calculated using the formula Q1=ρ×VL×c×ΔT, where Q1 is the cooling amount. Step S2015: Obtain the contact area between the heat exchange chamber and the motor assembly in the motor cooling system, represented by the symbol S; obtain the thermal conductivity and thickness of the heat conductor between the heat exchange chamber and the motor assembly, represented by the symbols λ and L respectively; mark the detection period as U; calculate Q1 / U and convert Q1 into heat flux, marked as Q2. Step S2016: Solve for the heat exchange temperature difference using the formula Q2=ΔTC×λ×S / L, where ΔTC is the heat exchange temperature difference. In the specific implementation, the outlet temperature TO was obtained as 65℃, and the inlet temperature TI was obtained as 55℃. The calculated ΔT = 10℃ was then obtained. In this embodiment, ethylene glycol aqueous solution was used as the coolant. The specific heat capacity c of the coolant was obtained as 3500 J / (kg×℃), and the density ρ was obtained as 1060 kg / m³. A detection period was set because the instantaneous volume of the coolant could not be extracted. When obtaining the volume of coolant flowing through based on the flow rate, a time frame must be set as a reference. Therefore, a detection period is required. The setting of the detection period is usually not specific and can be freely set by the experimenter. In this embodiment, the detection period was set to 5 seconds. The flow rate of the coolant flowing through the inlet can be extracted by the flow rate sensor and multiplied by the detection period. Finally, the volume VL of the coolant flowing through the inlet within the detection period was obtained as 0.0047 m³. The final calculation... The cooling amount Q1 is 174370J. Converting Q1 to heat flux, we get Q2 as 34874W. The contact area S is 0.5㎡, the thickness L is 0.002m, and the thermal conductivity λ is 4W / (m×K). Substituting these values ​​into the calculation, we get a heat exchange temperature difference of approximately 35K. The calculation result is rounded to one decimal place. Since the heat exchange temperature difference is a temperature difference, its unit can be directly converted from Kelvin to °C. That is, the heat exchange temperature difference is 35°C, which means that the temperature difference between the contact surface between the heat conductor and the motor assembly and the contact surface between the heat conductor and the coolant is 35°C. The motor temperature is actually monitored as the temperature of the contact surface between the heat conductor and the motor assembly.

[0020] Step S202: Calculate the heat exchange efficiency of the motor cooling system based on the heat exchange temperature difference; Step S202 includes the following sub-steps: Step S2021: The temperature of the motor assembly before cooling is named the pre-cooling temperature and represented by the symbol TD. The convective heat transfer coefficient is obtained and represented by the symbol h. The temperature of the contact surface between the heat conductor and the coolant is calculated by the formula Q2=h×S×(TS-TI), where TS is the temperature of the contact surface between the heat conductor and the coolant. TS+ΔTC=TD is calculated. Step S2022: The motor temperature after cooling is named the cooled temperature and represented by the symbol TL. The heat exchange efficiency is calculated by (TD-TL) / TD. In the specific implementation, h was obtained as 5130W / (m²·K), which was substituted into the calculation to obtain TS as 68.6℃. The calculation result was rounded to one decimal place and converted to ℃. Further calculation yielded TD as 103.6℃. The motor temperature after cooling of the motor assembly was named the cooling temperature TL, which could be directly obtained through the temperature sensor inside the motor assembly. TL was obtained as 68℃, and the heat exchange efficiency was calculated to be 0.3436. The calculation result was rounded to four decimal places.

[0021] Step S3 involves analyzing the pump's influence on the motor cooling system's power and heat exchange efficiency based on historical operating data. Step S3 includes the following sub-steps: Step S301: Record the historical operating data of the motor cooling system. The historical operating data includes the historical water pump power, fan power, outlet temperature, inlet temperature, temperature before cooling, temperature after cooling, heat exchange temperature difference, and heat exchange efficiency. Please see Figure 3 As shown, in step S302, a plane rectangular coordinate system is established with the water pump power as the X-axis and the heat exchange efficiency as the Y-axis, named the water pump influence analysis diagram. The heat exchange efficiency in the historical operating data is entered into the water pump influence analysis diagram according to the corresponding water pump power. Step S303: Perform function regression on the pump influence analysis diagram, name the curve obtained from the regression as the pump influence curve, and name the coordinate points in the pump influence analysis diagram as the pump influence analysis points. The pump influence curve and the pump influence analysis points are the pump influence relationship. In practice, the pump impact analysis diagram is constructed as follows: Figure 3 As shown, Figure 3 The curve in the figure is the water pump influence curve, and the dots are the water pump influence analysis points. The water pump power affects the coolant flow rate, and the coolant flow rate can affect the heat dissipation efficiency. The water pump influence analysis figure reveals the influence law of water pump power on heat dissipation efficiency.

[0022] Step S4 involves analyzing the fan influence relationship between fan power and heat exchange efficiency based on historical operating data. Step S4 includes the following sub-steps: Please see Figure 4As shown, in step S401, a plane rectangular coordinate system is established with the heat exchange temperature difference as the X-axis and the heat exchange efficiency as the Y-axis, named the temperature difference influence analysis diagram. The heat exchange efficiency in the historical operating data is entered into the temperature difference influence analysis diagram according to the corresponding heat exchange temperature difference. Step S402: Perform function regression on the temperature difference influence analysis diagram, name the curve obtained from the regression as the temperature difference influence curve, and name the coordinate points in the temperature difference influence analysis diagram as temperature difference influence analysis points. Please see Figure 5 As shown, in step S403, a plane rectangular coordinate system is established with fan power as the X-axis and heat exchange temperature difference as the Y-axis, named the fan heat dissipation analysis diagram. The heat exchange temperature difference in the historical operating data is entered into the fan heat dissipation analysis diagram according to the corresponding fan power. Step S404: Perform function regression on the fan heat dissipation analysis graph, name the curve obtained from the regression as the fan heat dissipation curve, and name the coordinate points in the fan heat dissipation analysis graph as fan heat dissipation analysis points. Step S405: The temperature difference influence curve, temperature difference influence analysis point, fan heat dissipation curve, and fan heat dissipation analysis point constitute the fan influence relationship. In practice, the temperature difference influence analysis diagram is constructed as follows: Figure 4 As shown, Figure 4 The curve in the figure is the temperature difference influence curve, and the dots are the analysis points of temperature difference influence. The fan heat dissipation analysis diagram is as follows. Figure 5 As shown, Figure 5 The curve in the figure is the fan cooling curve, and the dots are the fan cooling analysis points.

[0023] Step S5 involves optimizing the motor cooling system based on the influence relationships of the water pump, temperature conversion, and fan. Step S5 includes the following sub-steps: Step S501: Calculate the current required heat exchange efficiency of the motor assembly and the required water pump power and fan power; Step S501 includes the following sub-steps: Step S5011: Calculate the current pre-cooling temperature of the motor assembly, named the real-time equipment temperature, denoted by the symbol T1; obtain the optimal operating temperature of the motor assembly, denoted by the symbol T2; calculate (T1-T2) / T1 to obtain the current required heat exchange efficiency of the motor assembly, named the real-time demand efficiency. Please see Figure 6 As shown, in step S5012, find the points in the water pump influence curve and the temperature difference influence curve where the Y-axis is equal to the real-time demand efficiency, and name them as the water pump point to be analyzed and the temperature difference point to be analyzed, respectively. Step S5013: Analyze the pump point and temperature difference point to be analyzed independently. When analyzing the pump point or temperature difference point, name it the real-time analysis point. If the real-time analysis point is the pump point to be analyzed, name the pump power as the main parameter, the pump influence curve as the real-time main curve, the pump influence analysis point as the main point, the heat exchange temperature difference as the auxiliary parameter, the fan influence curve as the real-time auxiliary curve, and the fan influence analysis point as the auxiliary point. If the real-time analysis point is the fan point to be analyzed, name the heat exchange temperature difference as the main parameter, the fan influence curve as the real-time main curve, the fan influence analysis point as the main point, the pump power as the auxiliary parameter, the pump influence curve as the real-time auxiliary curve, and the pump influence analysis point as the auxiliary point. Step S5014: Obtain the main point whose X-axis is equal to the real-time analysis point and name it as a valid point; obtain the valid point below the real-time analysis point and closest to it and name it as a valid lower point; obtain the valid point above the real-time analysis point and closest to it and name it as a valid upper point; simultaneously, label the Y-axis values ​​of the valid upper point and valid lower point as YU and YD respectively, label the real-time demand efficiency as PN, calculate YU / PN and YD / PN, and obtain the upper point ratio and lower point ratio respectively; In specific implementation, according to the analysis process of steps S201 and S202, the current pre-cooling temperature of the motor assembly is calculated, and the temperature T1 of the implemented equipment is found to be 90℃. The optimal operating temperature T2 of the motor assembly is obtained as 65℃, meaning that the temperature of the motor assembly needs to be reduced to 65℃. The real-time required efficiency is calculated to be (90-65) / 90=5 / 18. The point where the Y-axis of the water pump influence curve and the temperature difference influence curve equals 5 / 18 is found, thus obtaining the water pump point and the temperature difference point to be analyzed. Since the analysis process of the water pump point and the temperature difference point to be analyzed is exactly the same in the subsequent analysis process, this embodiment only uses the water pump point to be analyzed as the real-time analysis point as an example for illustration. At this time, the water pump power is the main parameter, the water pump influence curve is the real-time main curve, the water pump influence analysis point is the main point, the heat exchange temperature difference is the auxiliary parameter, the fan influence curve is the real-time auxiliary curve, and the fan influence analysis point is the auxiliary point. The real-time analysis point, the effective upper point, and the effective lower point are extracted as follows: Figure 6 As shown, the X-axis of the effective upper and lower points is the same as the X-axis of the real-time analysis point. The YU and YD values ​​are 0.3 and 0.25, respectively. The real-time demand efficiency PN is 5 / 18. The calculated upper point ratio is 1.08 and the lower point ratio is 0.9. Please see Figure 7As shown, in step S5015, obtain the auxiliary parameters corresponding to the valid upper point and the valid lower point in the historical running data, and name them as valid upper parameter and valid lower parameter respectively. Find the points in the real-time auxiliary curve whose X-axis is equal to the valid upper parameter and the valid lower parameter, and name them as valid upper reference point and valid lower reference point respectively. Step S5016: Mark the effective upper parameter and effective lower parameter as Y3 and Y4 respectively. Assume that the auxiliary parameter required at the real-time analysis point is RE. There is a relationship Y3 / RE=YU / PN. Solve RE and mark it as E1. At the same time, there is a relationship Y4 / RE=YD / PN. Solve RE and mark it as E2. Calculate (E1+E2) / 2. Name the calculation result as the required secondary parameter. At the same time, name the value of the X-axis corresponding to the real-time analysis point as the required primary parameter. In practice, the auxiliary parameter is the heat exchange temperature difference. The effective upper and lower parameters are obtained as 35℃ and 30℃, respectively. The auxiliary curve is the temperature difference influence curve. Points on the X-axis of the temperature difference influence curve in the temperature difference influence analysis diagram, where 35℃ and 30℃ are found, are obtained to obtain the effective upper reference point and effective lower reference point, as shown below. Figure 7 As shown, Y3 and Y4 are 48℃ and 30℃ respectively. The relationships Y3 / RE=YU / PN and Y4 / RE=YD / PN exist because, in the pump influence analysis diagram, the effective upper point, real-time analysis point, and effective lower point have the same pump power, but their heat exchange efficiencies differ. This is due to the influence of the heat exchange temperature difference, which leads to the difference in heat exchange efficiency. The magnitude of the difference in heat exchange efficiency among the effective upper point, real-time analysis point, and effective lower point is equivalent to the difference between the effective upper reference point, effective lower reference point, and effective lower reference point in the temperature difference influence analysis diagram. The difference in heat transfer between the auxiliary parameters required at the real-time analysis point, i.e., the relationship between RE and Y3 and Y4, is approximately the same as the relationship between PN and YU and YD. Substituting these values ​​into the solution, we obtain E1 as 34.0 and E2 as 33.3. The calculation results are rounded to one decimal place. Further calculation yields a required secondary parameter of 33.7℃, meaning that the heat transfer temperature difference needs to be ensured to be 33.7℃. The calculation results are rounded to one decimal place, and the X-axis value corresponding to the real-time analysis point is obtained as 500W. This means that the required primary parameter is 500W, which indicates that the water pump power needs to be ensured to be 500W.

[0024] Step S5017: If the heat exchange temperature difference is the main parameter, find the point in the fan heat dissipation curve where the Y-axis is equal to the required main parameter, name it the fan requirement point, obtain the X-axis value corresponding to the fan requirement point, name it the fan requirement power, and name the required secondary parameter the water pump requirement power. Step S5018: If the heat exchange temperature difference is an auxiliary parameter, find the point in the fan heat dissipation curve where the Y-axis is equal to the required secondary parameter, name it the fan demand point, obtain the X-axis value corresponding to the fan demand point, name it the fan demand power, and name the main demand parameter the water pump demand power. In specific implementation, the heat exchange temperature difference listed in this embodiment is an auxiliary parameter. Therefore, the point on the fan cooling curve where the Y-axis equals the required secondary parameter is found, i.e., the point where the Y-axis equals 33.7℃, is obtained to determine the fan demand point. Then, the corresponding X-axis value is obtained to determine the required fan power. Figure 5 The fan power requirement is 1930W, meaning the fan power needs to be 1930W.

[0025] Step S502: Optimize the motor cooling system based on the required water pump power and fan power; Step S502 includes the following sub-steps: Step S5021: Using the water pump point to be analyzed as the real-time analysis point, analyze the fan power demand and water pump power demand, and mark them as P1 and P2 respectively. Calculate P1+P2 to obtain the first total power. Step S5022: Using the temperature difference point to be analyzed as the real-time analysis point, analyze the fan power demand and water pump power demand, and mark them as P3 and P4 respectively. Calculate P3+P4 to obtain the second total power. Step S5023: If the first total power is less than or equal to the second total power, adjust the power of the water pump in the motor cooling system to P2 and the power of the fan to P1; if the first total power is greater than the second total power, adjust the power of the water pump in the motor cooling system to P4 and the power of the fan to P3. In specific implementation, using the water pump point to be analyzed as the real-time analysis point, P1 is found to be 1930W and P2 to be 500W, and the first total power is calculated to be 2430W. Following the analysis process listed in this embodiment, similarly using the temperature difference point to be analyzed as the real-time analysis point, P3 is found to be 2550W and P4 to be 2100W, and the second total power is calculated to be 450W. By comparison, it is found that the first total power is less than the second total power. Therefore, the water pump power in the motor cooling system is adjusted to 500W and the fan power is adjusted to 1930W. At this time, the energy consumption of the motor cooling system can be reduced while meeting the heat dissipation requirements of the motor components.

[0026] Example 2: This application provides an electronic device, which may include a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The memory stores computer-readable instructions. The processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, steps such as those in the deep learning-based adaptive optimization method for motor cooling systems are performed to achieve the following functions: installing temperature sensors at the coolant outlet and coolant inlet of the motor cooling system to detect the outlet and inlet temperatures; calculating the heat exchange temperature difference of the motor cooling system based on the outlet and inlet temperatures and further calculating the heat exchange efficiency; analyzing the pump influence relationship between the pump power and heat exchange efficiency of the motor cooling system based on historical operating data; analyzing the fan influence relationship between fan power and heat exchange efficiency based on historical operating data; and optimizing the motor cooling system based on the pump influence relationship, temperature conversion relationship, and fan influence relationship.

[0027] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0028] Example 3: This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the deep learning-based adaptive optimization method for a motor cooling system provided by the above methods. This method includes: installing temperature sensors at the coolant outlet and coolant inlet of the motor cooling system to detect the outlet temperature and inlet temperature of the motor cooling system; calculating the heat exchange temperature difference of the motor cooling system based on the outlet temperature and inlet temperature and further calculating the heat exchange efficiency; analyzing the pump influence relationship between the pump power and heat exchange efficiency of the motor cooling system based on historical operating data of the motor cooling system; analyzing the fan influence relationship between the fan power and heat exchange efficiency based on historical operating data; and optimizing the motor cooling system based on the pump influence relationship, temperature conversion relationship, and fan influence relationship.

[0029] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the above-mentioned deep learning-based adaptive optimization method for motor cooling systems to achieve the following functions: installing temperature sensors at the coolant outlet and coolant inlet of the motor cooling system to detect the outlet and inlet temperatures of the motor cooling system; calculating the heat exchange temperature difference of the motor cooling system based on the outlet and inlet temperatures and further calculating the heat exchange efficiency; analyzing the pump influence relationship between the pump power and heat exchange efficiency of the motor cooling system based on historical operating data of the motor cooling system; analyzing the fan influence relationship between the fan power and heat exchange efficiency based on historical operating data; and optimizing the motor cooling system based on the pump influence relationship, temperature conversion relationship, and fan influence relationship.

[0030] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0031] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0032] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An adaptive optimization method for motor cooling systems based on deep learning, characterized in that, Includes the following steps: Temperature sensors are installed at the coolant outlet and coolant inlet of the motor cooling system to detect the outlet and inlet temperatures of the motor cooling system. The heat exchange temperature difference of the motor cooling system is calculated based on the outlet temperature and the inlet temperature, and the heat exchange efficiency is further calculated. Based on historical operating data of the motor cooling system, the influence relationship between the pump power and heat exchange efficiency of the motor cooling system is analyzed. Analysis of the fan influence relationship between fan power and heat exchange efficiency based on historical operating data; The motor cooling system is optimized based on the influence of water pumps, temperature conversion, and fans.

2. The adaptive optimization method for a motor cooling system based on deep learning according to claim 1, characterized in that, Temperature sensors are installed at the coolant outlet and coolant inlet of the motor cooling system. Detecting the outlet and inlet temperatures of the motor cooling system includes the following sub-steps: Temperature sensors are installed at the coolant outlet and coolant inlet of the motor cooling system. The coolant outlet and coolant inlet are both connection ports between the cooler and the water distribution pipe in the motor cooling system. The coolant in the coolant outlet flows from the water distribution pipe to the cooler, and the coolant in the coolant inlet flows from the cooler to the water distribution pipe. The temperature of the coolant at the coolant outlet and coolant inlet is detected by temperature sensors and named outlet temperature and inlet temperature, respectively.

3. The adaptive optimization method for a motor cooling system based on deep learning according to claim 2, characterized in that, Calculating the heat exchange temperature difference of the motor cooling system based on the outlet and inlet temperatures, and further calculating the heat exchange efficiency, includes the following sub-steps: The heat exchange temperature difference between the two sides of the heat conductor is calculated based on the outlet temperature and the inlet temperature. The heat exchange efficiency of the motor cooling system is calculated based on the heat exchange temperature difference.

4. The adaptive optimization method for a motor cooling system based on deep learning according to claim 3, characterized in that, Calculating the heat exchange temperature difference across the heat conductor based on the outlet and inlet temperatures includes the following sub-steps: Obtain the outlet temperature and inlet temperature, denoted by the symbols TO and TI respectively, calculate TI-TO, and label the calculation result as ΔT; The specific heat capacity of the coolant is obtained, denoted by the symbol c, and the density of the coolant is obtained, denoted by the symbol ρ. Set a detection cycle and count the volume of coolant flowing through the coolant inlet within the detection cycle, represented by the symbol VL; The heat removed by the coolant during the testing period is called the cooling amount. The cooling amount is calculated using the formula Q1=ρ×VL×c×ΔT, where Q1 is the cooling amount. The contact area between the heat exchange chamber and the motor assembly in the motor cooling system is obtained and represented by the symbol S. The thermal conductivity and thickness of the heat conductor between the heat exchange chamber and the motor assembly are obtained and represented by the symbols λ and L, respectively. The detection period is marked as U. Q1 / U is calculated and Q1 is converted into heat flux and marked as Q2. The heat exchange temperature difference can be calculated using the formula Q2=ΔTC×λ×S / L, where ΔTC is the heat exchange temperature difference.

5. The adaptive optimization method for a motor cooling system based on deep learning according to claim 4, characterized in that, Calculating the heat exchange efficiency of a motor cooling system based on the heat exchange temperature difference includes the following sub-steps: The temperature of the motor assembly before cooling is named the pre-cooling temperature and represented by the symbol TD. The convective heat transfer coefficient is obtained and represented by the symbol h. The temperature of the contact surface between the heat conductor and the coolant is calculated using the formula Q2=h×S×(TS-TI), where TS is the temperature of the contact surface between the heat conductor and the coolant. TS+ΔTC=TD is calculated. The temperature of the motor assembly after cooling is named the cooled temperature and represented by the symbol TL. The heat exchange efficiency is obtained by calculating (TD-TL) / TD.

6. The adaptive optimization method for a motor cooling system based on deep learning according to claim 5, characterized in that, Analyzing the pump influence relationship between pump power and heat exchange efficiency in the motor cooling system based on historical operating data includes the following sub-steps: Record historical operating data of the motor cooling system, including historical water pump power, fan power, outlet temperature, inlet temperature, temperature before cooling, temperature after cooling, heat exchange temperature difference, and heat exchange efficiency. Establish a plane rectangular coordinate system with pump power as the X-axis and heat exchange efficiency as the Y-axis, and name it the Pump Influence Analysis Diagram. Enter the heat exchange efficiency in the historical operating data into the Pump Influence Analysis Diagram according to the corresponding pump power. A function regression is performed on the pump influence analysis diagram, and the resulting curve is named the pump influence curve. The coordinate points in the pump influence analysis diagram are named the pump influence analysis points. The pump influence curve and the pump influence analysis points constitute the pump influence relationship.

7. The adaptive optimization method for a motor cooling system based on deep learning according to claim 6, characterized in that, Analyzing the fan-related relationship between fan power and heat exchange efficiency based on historical operating data includes the following sub-steps: A plane rectangular coordinate system is established with heat exchange temperature difference as the X-axis and heat exchange efficiency as the Y-axis, named the Temperature Difference Influence Analysis Chart. The heat exchange efficiency in the historical operating data is entered into the Temperature Difference Influence Analysis Chart according to the corresponding heat exchange temperature difference. Perform function regression on the temperature difference influence analysis diagram, name the curve obtained from the regression as the temperature difference influence curve, and name the coordinate points in the temperature difference influence analysis diagram as temperature difference influence analysis points. Establish a Cartesian coordinate system with fan power as the X-axis and heat exchange temperature difference as the Y-axis, and name it Fan Heat Dissipation Analysis Chart. Enter the heat exchange temperature difference in the historical operating data into the Fan Heat Dissipation Analysis Chart according to the corresponding fan power. Perform function regression on the fan heat dissipation analysis diagram, name the curve obtained from the regression as the fan heat dissipation curve, and name the coordinate points in the fan heat dissipation analysis diagram as fan heat dissipation analysis points. The temperature difference influence curve, temperature difference influence analysis point, fan heat dissipation curve, and fan heat dissipation analysis point constitute the fan influence relationship.

8. The adaptive optimization method for a motor cooling system based on deep learning according to claim 7, characterized in that, Optimizing the motor cooling system based on the influence of water pumps and fans includes the following sub-steps: Calculate the current required heat exchange efficiency for the motor assembly and the required power for the water pump and fan. The motor cooling system is optimized based on the required water pump power and fan power.

9. The adaptive optimization method for a motor cooling system based on deep learning according to claim 8, characterized in that, Calculating the required heat exchange efficiency for the motor assembly and the required pump and fan power includes the following sub-steps: Calculate the current pre-cooling temperature of the motor assembly, named the real-time equipment temperature, denoted by the symbol T1. Obtain the optimal operating temperature of the motor assembly, denoted by the symbol T2. Calculate (T1-T2) / T1 to obtain the current required heat exchange efficiency of the motor assembly, named the real-time demand efficiency. Find the points in the pump influence curve and the temperature difference influence curve where the Y-axis equals the real-time demand efficiency, and name them the pump point to be analyzed and the temperature difference point to be analyzed, respectively. The pump point and temperature difference point to be analyzed are analyzed independently. When analyzing the pump point or temperature difference point, they are named real-time analysis points. If the real-time analysis point is the pump point to be analyzed, the pump power is named the main parameter, the pump influence curve is named the real-time main curve, the pump influence analysis point is named the main point, the heat exchange temperature difference is named the auxiliary parameter, the fan influence curve is named the real-time auxiliary curve, and the fan influence analysis point is named the auxiliary point. If the real-time analysis point is the fan point to be analyzed, the heat exchange temperature difference is named the main parameter, the fan influence curve is named the real-time main curve, the fan influence analysis point is named the main point, the pump power is named the auxiliary parameter, the pump influence curve is named the real-time auxiliary curve, and the pump influence analysis point is named the auxiliary point. Obtain the main point whose X-axis is equal to the real-time analysis point and name it as the effective point. Obtain the effective point that is below the real-time analysis point and is closest to it and name it as the effective lower point. Obtain the effective point that is above the real-time analysis point and is closest to it and name it as the effective upper point. At the same time, label the Y-axis values ​​of the effective upper point and the effective lower point as YU and YD respectively, label the real-time demand efficiency as PN, calculate YU / PN and YD / PN, and obtain the upper point ratio and the lower point ratio respectively. Obtain the auxiliary parameters corresponding to the valid upper and lower points in the historical running data, and name them the valid upper parameter and valid lower parameter respectively. Find the points in the real-time auxiliary curve whose X-axis is equal to the valid upper parameter and valid lower parameter, and name them the valid upper reference point and valid lower reference point respectively. Label the effective upper parameter and effective lower parameter as Y3 and Y4 respectively. Assume that the auxiliary parameter required at the real-time analysis point is RE. There is a relationship Y3 / RE=YU / PN. Solve RE and label it as E1. At the same time, there is a relationship Y4 / RE=YD / PN. Solve RE and label it as E2. Calculate (E1+E2) / 2. Name the calculation result as the required secondary parameter. At the same time, name the value of the X-axis corresponding to the real-time analysis point as the required primary parameter. If the heat exchange temperature difference is the main parameter, then find the point in the fan heat dissipation curve where the Y-axis is equal to the required main parameter, name it the fan requirement point, obtain the X-axis value corresponding to the fan requirement point, name it the fan requirement power, and name the required secondary parameter the water pump requirement power. If the heat exchange temperature difference is an auxiliary parameter, then find the point on the fan cooling curve where the Y-axis is equal to the required secondary parameter, name it the fan requirement point, obtain the corresponding X-axis value of the fan requirement point, name it the fan requirement power, and name the primary parameter the water pump requirement power.

10. The adaptive optimization method for a motor cooling system based on deep learning according to claim 9, characterized in that, Optimizing the motor cooling system based on the required water pump power and fan power includes the following sub-steps: Using the water pump point to be analyzed as the real-time analysis point, analyze the fan power demand and water pump power demand, and label them as P1 and P2 respectively. Calculate P1+P2 to obtain the first total power. The fan power demand and water pump power demand are analyzed using the temperature difference point to be analyzed as the real-time analysis point, and marked as P3 and P4 respectively. P3+P4 is calculated to obtain the second total power. If the first total power is less than or equal to the second total power, then adjust the power of the water pump in the motor cooling system to P2 and the power of the fan to P1. If the first total power is greater than the second total power, then adjust the power of the water pump in the motor cooling system to P4 and the power of the fan to P3.

Images