Thermal management system energy grade and energy conversion difference measurement method based on analysis

Abstract

The invention provides a thermal management system energy grade and energy conversion difference measurement method based on # imgabs0 # analysis, and the method comprises the steps: obtaining key parameters of all parts of a system in real time, carrying out # imgabs1 # analysis, and obtaining an energy quality coefficient; performing grade difference measurement and heat flow distribution to obtain grade grading and flow direction configuration of each component; constructing a heat energy network model, and optimizing a network loop to form a high and low temperature multi-loop heat energy network; measuring component energy conversion efficiency difference to obtain a difference analysis result; analyzing the corresponding speed of energy conversion and performing control medium classification to obtain corresponding speed classification and medium distribution suggestions; and constructing a heat flow prediction model, designing an algorithm reward function, and obtaining an optimization control strategy based on response difference measurement. The heat flow can be reasonably distributed and utilized step by step according to the grade, the energy utilization efficiency of the total system is improved, the optimal energy utilization terminal combination scheme can be designed, energy loss is reduced, and the overall performance of the system is improved.

Description

Technical Field

[0001] The present invention relates to the field of thermal management technology, in particular to a method based on Analyze the energy taste and energy conversion difference measurement methods of thermal management systems. Background Art

[0002] With the continuous development of vehicle thermal management technology, the efficient use of energy has become a key issue. Modern thermal management systems are generally oriented towards multi-heat source power systems, and there is a strong demand for improving thermal efficiency. Traditional reliance on manual experience diversion and passive cooling makes it difficult to optimize the quality and energy flow. Therefore, the existing technologies have the following problems: 1) Most of them only focus on thermal balance or energy conservation, ignoring the complementarity of "energy quality" and different heat flows; 2) Traditional circuits are fixed, and the heat flow direction + utilization structure is rigid, making it difficult to adapt to complex working conditions / extreme situations; 3) There is a lack of hierarchical optimization ideas for subsystem response speed and matching cooling media; 4) Over-reliance on manual experience, insufficient data-driven, slow response to extreme and dynamic working conditions, and low accuracy. Summary of the Invention

[0003] In order to overcome the deficiencies in the prior art, the present invention aims to provide a The analyzed method for measuring the energy quality and energy conversion differences of the thermal management system can determine the appropriate quality of input heat flow based on the working requirements of each subsystem, achieve reasonable distribution of heat flow and utilize it step by step according to its quality, thereby improving the energy utilization efficiency of the overall system. It can also quantify the energy conversion efficiency differences of the cooling system, design the optimal energy utilization terminal combination plan, reduce energy loss, and improve the overall performance of the system.

[0004] To achieve the above object, the present invention provides the following solution: a method based on The energy taste and energy conversion difference measurement methods of the thermal management system analyzed include:

[0005] Real-time acquisition of key parameters of each component in the vehicle thermal management system, obtaining original parameter data, and performing maintenance on each component based on the original parameter data. Analyze and obtain the energy quality coefficient;

[0006] Based on the energy quality coefficient, the quality difference measurement and heat flow distribution are performed to obtain the quality classification and flow configuration of each component. Based on the quality classification and flow configuration, a thermal energy network model is constructed, and the network loop is optimized to form a high and low temperature multi-loop thermal energy network;

[0007] Based on the high and low temperature multi-circuit thermal energy network, the differences in energy conversion efficiency of components are measured to obtain difference analysis results. Based on the difference analysis results, the corresponding energy conversion speed is analyzed and the control medium classification is performed to obtain corresponding speed classification and medium distribution suggestions;

[0008] A heat flow prediction model based on machine learning is constructed. Combining the heat flow prediction model with energy velocity difference metric, an algorithm reward function is designed to obtain an optimization control strategy based on response difference metric.

[0009] Optionally, key parameters of each component in the vehicle thermal management system are acquired in real time to obtain original parameter data, and each component is Analyze and obtain the energy quality coefficient, including:

[0010] Real-time acquisition of temperature, flow, power, and heat flow of each component in the vehicle thermal management system to obtain raw parameter data; these components include the engine, generator, motor, thermal storage module, controller, coolant circuit, radiator, oil cooler, intercooler, and electronically controlled valve;

[0011] Based on the original parameter data, each component in the vehicle thermal management system is Analyze and use relevant thermodynamic formulas to calculate the input of each component separately and output , and then according to the input and the output , calculate the energy quality coefficient of each component.

[0012] Optionally, based on the energy quality coefficient, quality difference measurement and heat flow distribution are performed to obtain quality classification and flow configuration of each component. Based on the quality classification and flow configuration, a thermal energy network model is constructed, and the network loop is optimized to form a high and low temperature multi-loop thermal energy network, including:

[0013] According to the energy quality coefficient and temperature index, the energy quality of each component is distinguished, and the quality coefficient of each component is defined. Then, based on the quality coefficient, the adaptability temperature and thermal energy of each component are sorted out. , and classify the components into layers; wherein the energy quality includes high quality, medium quality and low quality;

[0014] According to the working requirements of each subsystem in the high and low temperature circulating cooling system, heat flow is distributed and utilized step by step according to the energy quality, and quality classification and flow direction configuration are obtained;

[0015] Based on the grade classification and flow configuration, a thermal energy network model is constructed. Using the thermal energy network model, high-grade components are connected in parallel to the high-temperature cycle, and low-grade components are connected to the low-temperature cycle to organize the heat energy flow of the components;

[0016] Based on the heat energy flow of the components and taking into account energy recovery and cabin heating, the various components are arranged at corresponding key nodes to capture and utilize waste heat, realize network loop optimization, and form a high and low temperature multi-loop thermal energy network.

[0017] Optionally, based on the high and low temperature multi-circuit thermal energy network, differences in component energy conversion efficiency are measured to obtain difference analysis results, including:

[0018] For the various operating modes of the vehicle thermal management system, evaluate and compare the energy conversion efficiency of the heat storage function and the heating function under the conditions of turning on and off in each operating mode;

[0019] The energy conversion efficiency is measured to obtain a difference in energy conversion efficiency. Based on the difference in energy conversion efficiency, the room for energy efficiency improvement under different operating modes is quantitatively analyzed to obtain a difference analysis result.

[0020] Optionally, based on the difference analysis results, the energy conversion corresponding speed is analyzed and the control medium classification is performed to obtain corresponding speed classification and medium allocation suggestions, including:

[0021] Based on the difference analysis results, using simulation tools to simulate the response of the vehicle thermal management system under different heat source fluctuation conditions, and analyzing the energy flow response speed of key subsystems in the vehicle thermal management system under transient extreme conditions to measure and differentiate the response speed differences;

[0022] The calculation expression of the response speed difference metric is:

[0023] ε=△P / △t

[0024] Where ε is the rate of change of power over a period of time, P is power, and t is time;

[0025] The calculation expression of the response speed difference is:

[0026] η sd =ε y / ε x

[0027] Among them, η sd is the response speed differentiation coefficient, ε x is the rate of change of heat release of the system independent variable over time, ε y is the rate of change of the system's heat absorption with time in response to changes in the independent variable;

[0028] Based on the response speed difference metric and the response speed differentiation, the response speed differences of the phase change material, coolant, and air to the transient heat flux mutation of the heat source are compared, and the mutation levels of different heat sources are distinguished to match the optimal cooling medium, thereby obtaining corresponding speed classification and medium allocation recommendations.

[0029] Optionally, a heat flow prediction model based on machine learning is constructed, and an algorithm reward function is designed by combining the heat flow prediction model with an energy velocity difference metric to obtain an optimization control strategy based on a response difference metric, including:

[0030] Using measured and simulated data sets, artificial neural network training is performed on the main components of the vehicle thermal management system to perform real-time heat flow distribution prediction and network modeling under multiple operating conditions, thereby obtaining a heat flow prediction model based on machine learning;

[0031] Using the heat flow prediction model, the heat dissipation of each component under different speed, torque and load conditions is predicted in real time to obtain energy flow distribution data for dynamic optimization of the high and low temperature multi-circuit thermal energy network;

[0032] Based on the response speed difference metric, the response speed differentiation and the dynamic optimization results of the high and low temperature multi-loop thermal energy network, an algorithm reward function is designed to formulate an optimization control strategy for the vehicle thermal management system execution unit.

[0033] Optionally, the process of constructing the heat flow prediction model includes:

[0034] Constructing first training data and second training data; the first training data includes ambient temperature, altitude, engine speed, engine torque, body heat dissipation, interstage intercooler heat dissipation, first-stage intercooler heat dissipation, second-stage intercooler heat dissipation, and oil cooler heat dissipation; the second training data includes generator speed, generator torque, left motor speed, left motor torque, right motor speed, right motor torque, generator heat dissipation, motor heat dissipation, and battery discharge status;

[0035] defining a first boundary condition based on the first training data, defining a second boundary condition based on the second training data, and training a machine learning model using the first training data and the second training data based on the first boundary condition and the second boundary condition to obtain a heat dissipation prediction model for each component of the power device;

[0036] According to the vehicle dynamics model, the engine torque speed, generator torque speed and motor torque speed are input into the heat dissipation prediction model to calculate the heat dissipation and effective power of each component in the current state to obtain energy flow distribution data.

[0037] Optionally, the calculation expression of the algorithm reward function is:

[0038] R total =R temp +R fluct +R energy +R stable

[0039] R temp =-w1·(T t -T target ) 2

[0040] R fluct =-w2·ΔT, ΔT=|T t -T t-1 ∣

[0041] R energy =-w3·(∑P pump +∑P fan )

[0042] R stable = +w4·I(|T t -T target ∣≤∈)

[0043] Among them, R temp is the temperature tracking target, T t is the actual temperature, T target Target temperature, R fluct For temperature fluctuation suppression, R energy To optimize the energy efficiency of water pumps and fans, P pump is the pump power, P fan is the fan power, R stable is the temperature stabilization time, w1, w2, w3, and w4 are all weights.

[0044] The present invention provides a The energy taste and energy conversion difference measurement method of the thermal management system analyzed discloses the following technical effects:

[0045] 1. Based on The energy quality coefficient analyzed is used to conduct a reasonable evaluation of comprehensive energy efficiency and establish a method to measure energy grade differences. This can accurately evaluate the availability of different energy forms in the system, achieve a reasonable distribution and step-by-step utilization of heat flow, and improve the energy utilization efficiency of the overall system.

[0046] 2. Through the energy conversion efficiency difference measurement method, the energy conversion efficiency difference of the cooling system is quantified, and the optimal energy utilization terminal combination solution is designed to reduce energy loss and improve the overall system performance.

[0047] 3. By analyzing the energy conversion response speed of the subsystem under instantaneous extreme conditions, a difference measurement method for the energy conversion response speed is established, an instantaneous extreme heat flux distribution network is constructed, and targeted control strategies are formulated to achieve instantaneous high-response heat flux regulation of the system and ensure the stable operation of the system under different heat source fluctuations.

[0048] 4. The construction of an instantaneous extreme heat flux distribution network based on machine learning can accurately predict the heat dissipation of each component under different working conditions, realize dynamic heat flux characteristic analysis and control strategy optimization, and improve the accuracy and real-time performance of energy flow distribution.

[0049] 5. Formulate control strategies based on energy response speed difference measurement, according to the vehicle's operating status and the heat dissipation requirements of heat-generating components, to ensure that the system can maintain good performance in various environments, while optimizing energy use and improving overall energy efficiency.

[0050] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 A schematic diagram of a method flow chart provided in an embodiment of the present invention;

[0053] Figure 2 A simplified diagram of a thermal energy network provided by an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of energy flow distribution provided by an embodiment of the present invention;

[0055] Figure 4 A schematic diagram of an engine cooling circuit provided by an embodiment of the present invention;

[0056] Figure 5 A schematic diagram of torque at different speeds under external characteristic working conditions provided by an embodiment of the present invention;

[0057] Figure 6 A schematic diagram of fuel consumption rates at different speeds under external characteristic working conditions provided by an embodiment of the present invention;

[0058] Figure 7 The embodiment of the present invention provides different speed mechanical Schematic diagram;

[0059] Figure 8 The chemical energy at different speeds under the external characteristic working conditions provided by the embodiment of the present invention Schematic diagram;

[0060] Figure 9 A schematic diagram of energy quality coefficients at different speeds under external characteristic working conditions provided by an embodiment of the present invention;

[0061] Figure 10 Each component under the external characteristic working condition provided by the embodiment of the present invention Distribution diagram;

[0062] Figure 11 Each component under the external characteristic working condition provided by the embodiment of the present invention Schematic diagram of the proportion;

[0063] Figure 12 A schematic diagram of a system thermal energy network provided by an embodiment of the present invention;

[0064] Figure 13 A schematic diagram of the response speed of different cooling media provided by an embodiment of the present invention;

[0065] Figure 14 A schematic diagram of different cooling medium temperatures provided by an embodiment of the present invention;

[0066] Figure 15 A schematic diagram of an instantaneous extreme heat flux distribution network provided by an embodiment of the present invention;

[0067] Figure 16 A schematic diagram of constructing an instantaneous extreme heat flux distribution network based on machine learning provided in an embodiment of the present invention;

[0068] Figure 17 Schematic diagram of an artificial neural network provided by an embodiment of the present invention; wherein (a) is a schematic diagram of the structure of different layers in the artificial neural network; (b) is a schematic diagram of the artificial neural network training process;

[0069] Figure 18 Schematic diagram of model training and verification results provided by an embodiment of the present invention;

[0070] Figure 19 A schematic diagram of the instantaneous extreme heat flux distribution network provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0072] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0073] like Figure 1 As shown, the present invention provides a The energy taste and energy conversion difference measurement methods of the thermal management system analyzed include:

[0074] 1. Real-time acquisition of key parameters of each component in the vehicle thermal management system, obtaining original parameter data, and performing thermal management on each component based on the original parameter data. Analyze and obtain the energy quality coefficient; including:

[0075] like Figure 2 As shown, the system captures the temperature, flow rate, power, and heat flow of each component in the vehicle thermal management system in real time, generating raw parameter data. These components include the engine, generator, motor, heat storage module, controller, coolant circuit, radiator, oil cooler, intercooler, and electronically controlled valves. These components are interconnected by a coolant circulation system, forming two heat exchange loops: high- and low-temperature circulation. Coolant circulates through the system, passing through each component, removing and dissipating heat. The system also includes electronically controlled valves to control the direction and distribution of the coolant flow.

[0076] like Figure 3 As shown, based on the original parameter data, each component in the vehicle thermal management system is Analyze and use relevant thermodynamic formulas to calculate the input of each component separately and output , and then according to the input and the output , calculate the energy quality coefficient of each component to evaluate the availability of different energy forms in the system.

[0077] Specifically:

[0078] The chemical energy of the fuel is converted into mechanical energy through combustion in the engine, driving the generator to generate electricity. The electricity generated by the generator is distributed to the left / right motors through the motor controller, which converts the electrical energy into mechanical energy to directly drive the wheels. Excess electricity can be stored in the power battery for use during high loads or when the engine is shut down. Thermal energy management is divided into two levels: high-temperature cycle and low-temperature cycle. The high-temperature cycle mainly processes high-quality thermal energy from the engine water jacket and intercooler, temporarily storing it in the heat storage module, and dissipating excess heat to the environment through the high-temperature radiator. The low-temperature cycle processes low-quality thermal energy from the motor controller, transmission system, etc., maintaining a stable temperature in the cooling system and reducing the consumption of high-quality electrical energy. In the power unit cooling system, the main heat sources include the engine, generator, motor, heat storage module and controller.

[0079] In the system After analysis, the energy quality coefficient of each part is calculated, and the formula is:

[0080]

[0081] Where: η ex is the energy quality coefficient, E out Output for components 、E in Entered for the component .

[0082] The following takes the engine and its accessories as an example. Analyze and calculate the energy quality coefficient. The engine generates a lot of heat during the fuel combustion process. Part of the heat is used to drive the vehicle, and the remaining heat is dissipated to the environment through the cooling system. The path is fuel chemical →Machinery (drive generator) + waste heat (exhaust, coolant).

[0083] like Figure 4 As shown, Figure 4 It is a schematic diagram of the engine cooling circuit. The object of study has a two-stage turbocharger (low-pressure stage LPT + high-pressure stage HPT) and a three-stage intercooler, which is used to reduce the air temperature after supercharging and improve combustion efficiency. Its input is diesel chemical energy, and its output is mechanical work, exhaust heat energy, cooling system heat energy, and unused waste heat.

[0084] Chemical energy :The chemical energy generated by fuel combustion can be partially converted into mechanical energy (engine work), and the remaining part is transferred to the cooling system in the form of heat energy. The calculation formula is:

[0085]

[0086] Where LHV is the lower heating value of the fuel, η comb For combustion efficiency, is the diesel mass flow rate.

[0087] The working part of the engine It can be calculated by the following formula:

[0088] E work =η engine ×E chem (2)

[0089] Among them, η engine It is the efficiency of the engine, which indicates the part of the fuel combustion energy used to do mechanical work.

[0090] Loss: Due to irreversible phenomena (such as incomplete combustion, friction loss, etc.) during the combustion process, a certain amount of Loss. Some of this lost energy cannot be converted into useful work and is ultimately lost to the environment.

[0091] According to the input and output Calculate the energy quality coefficient of the engine:

[0092]

[0093] like Figure 5 、 Figure 6 As shown, Figure 5 、 Figure 6 The torque at different speeds and the fuel consumption rate at different speeds under the external characteristic working conditions are shown in Figure 2. It can be seen that the torque reaches its maximum value at 3000r / min, and the fuel consumption rate is the lowest at this time. Calculation formula and mechanical The calculation formula is used to obtain the chemical energy corresponding to different speeds under external characteristic conditions. and machinery As shown in the figure, the calorific value of diesel is LHV==42.7MJ / kg.

[0094] like Figure 7 、 Figure 8 As shown, Figure 7 For machines with different speeds under external characteristic conditions 、 Figure 8 For machines with different speeds under external characteristic conditions And the chemical energy at different speeds under external characteristic conditions , it can be seen that as the speed increases, the mechanical energy of the engine and chemical energy It shows an upward trend. According to the energy quality coefficient calculation formula, we can get Figure 9 Energy quality coefficient at different speeds under the external characteristic conditions shown.

[0095] like Figure 9 As shown, Figure 9 The energy quality coefficient (EQC) at different speeds under external characteristic conditions is shown in the figure. As the speed increases from 2000 to 3800 r / min, the EQC first increases and then decreases. At low speeds (2000 r / min), the EQC is low, indicating low energy conversion efficiency or high energy losses. As the speed increases to the medium range (2500-3000 r / min), the EQC gradually increases, reaching a peak at 3000 r / min, indicating the highest energy conversion efficiency and lowest energy losses.

[0096] like Figure 10 As shown, Figure 10 For each component under external characteristic conditions Distribution, as the speed increases, the combustion chemical energy Rapid increase; mechanical energy , exhaust heat energy Values ​​such as [number of components] also increase with speed. This is primarily because, with other operating parameters remaining constant, as speed increases, the fuel injection rate per cycle increases, leading to a rise in in-cylinder gas temperature. This in turn increases heat transfer through the cylinder head, liner, and piston, leading to a corresponding rise in exhaust temperature. Therefore, the absolute value of each component of heat increases with speed. However, the proportion of each component of heat in the total combustion heat release varies at different speeds.

[0097] like Figure 11 As shown, Figure 11 For each component under external characteristic conditions The proportion of chemical energy when the power unit works under the external characteristics of the engine , mechanical energy , oil cooler heat energy , interstage intercooler heat energy , first-stage intercooler heat energy , Secondary intercooler heat energy , diesel engine body heat energy , exhaust heat energy , the changes in the proportion of residual losses. It can be seen that when the power unit works under the external characteristics of the engine, the mechanical energy The percentage is around 35% to 42%, and reaches a maximum of 42% when the speed n = 3000r / min. At this time, the effective output efficiency of the power unit is the highest. It accounts for 25% to 30% of the total heat, and reaches a maximum of 30.24% when the speed n = 3800r / min. The remaining losses account for about 8% to 11% of the total heat, and the trend of change with the speed is not large. The proportion is lower at high speed and even lower at low speed. The remaining losses include the heat energy of the oil pan. , the surface radiation heat energy of the body , engine friction loss, etc.

[0098] 2. Based on the energy quality coefficient, perform quality difference measurement and heat flow distribution to obtain the quality classification and flow configuration of each component. Based on the quality classification and flow configuration, construct a thermal energy network model and optimize the network loop to form a high and low temperature multi-loop thermal energy network; including:

[0099] 2.1 Heat flow is rationally distributed and utilized step by step according to its grade

[0100] According to the energy quality coefficient and temperature index, the energy quality of each component is distinguished, and the quality coefficient of each component is defined. Then, based on the quality coefficient, the adaptability temperature and thermal energy of each component are sorted out. , and classify the components into layers; wherein, the energy quality includes high quality, medium quality and low quality; according to the working requirements of each subsystem in the high and low temperature circulation cooling system, the heat flow is distributed and utilized step by step according to the energy quality, and the quality classification and flow direction configuration are obtained.

[0101] Specifically:

[0102] The high and low temperature circulating cooling system includes multiple different subsystems and devices, such as engine water jacket, radiator, generator water jacket, motor water jacket, oil cooler, intercooler, etc. The energy quality and energy conversion efficiency of each device directly affect the overall performance of the system.

[0103] Temperature is a key factor influencing energy quality. Energy availability (quality) is directly related to the temperature of the heat source; higher temperatures indicate higher energy quality. Measuring energy quality through the temperature dimension helps identify systems with high energy utilization potential and those with lower energy efficiency.

[0104] In high and low temperature circulation systems, temperature differences determine the energy quality of different devices. Engines operate at higher temperatures (above 500°C) and therefore have higher energy quality. Generators and motors operate at lower temperatures than engines, but their energy quality is still higher because electrical and mechanical energy can be efficiently converted into other forms of energy. Devices such as radiators and oil coolers are used to dissipate heat from the system to the environment. Their operating temperatures are usually lower (40-100°C) and their energy quality is relatively low. The temperature of the thermal storage module may vary greatly, depending on the process of storing and releasing heat, and the energy quality depends on its operating temperature range.

[0105] For cooling systems, different heat dissipation components have different temperature adaptability ranges due to differences in energy conversion forms and materials. The energy quality coefficient λ represents the "quality" of energy and is defined as:

[0106]

[0107] Where: T0 is the ambient temperature; T is the adaptation temperature of the component (converted to absolute temperature K).

[0108] For each component of the power unit, in the same time and space and at the same ambient temperature, the energy quality order in the cooling system remains unchanged. Analysis and data collection to obtain the thermal energy of each component And the applicable temperature range is shown in Table 1:

[0109] Table 1 Adaptable temperature and energy grade of each component in the cooling system

[0110] Table 1 shows the temperature and energy grade of each component in the cooling system. For the cooling system, the heat energy of the engine body, the first stage intercooler, and the interstage intercooler is As well as the high energy grade, the high-grade heat can be collected through the heat storage module and supplied to the high and low temperature cooling systems during low-temperature startup, and the crew cabin can be heated to realize waste heat utilization.

[0111] 2.2 Thermal Energy Network

[0112] Based on the quality classification and flow configuration, a thermal energy network model is constructed. Using the thermal energy network model, high-quality components are connected in parallel to the high-temperature cycle, and low-quality components are connected to the low-temperature cycle to organize the thermal energy flow of the components. Based on the thermal energy flow of the components and taking into account energy recovery and cabin heating, the various components are arranged at corresponding key nodes to capture and utilize waste heat, realize network loop optimization, and form a high-low temperature multi-loop thermal energy network.

[0113] Specifically:

[0114] like Figure 12 As shown, according to the energy quality, the system thermal network is established. The high-quality components are placed in parallel in the high-temperature cycle. The heat storage module is placed in front of the radiator inlet to store the waste heat. In the low-temperature cycle, the heat energy of each hot component is obtained according to the low-temperature cycle. As well as the adaptable temperature range, and taking into account heat storage and crew cabin heating.

[0115] Coolant flows from the expansion tank into the system and is driven by a water pump through two heat exchange circuits, low-temperature and high-temperature. It then passes through components such as the engine, intercooler, oil heat exchanger, and transmission oil cooler, removing heat and dissipating it to the outside world. Electronically controlled valves and check valves in the system control the direction and distribution of the coolant flow, ensuring optimal distribution under varying operating conditions. During the coolant's circulation, heat generated by the engine is rapidly dissipated through the high-temperature heat exchanger and intercooler, while the low-temperature circuit dissipates heat to the left and right motors, generator, and transmission oil. The entire cooling system utilizes a multi-circuit parallel design to effectively cool the engine and related components and utilize excess heat.

[0116] 3. Based on the high-low temperature multi-circuit thermal energy network, measure the differences in component energy conversion efficiency to obtain difference analysis results. Based on the difference analysis results, analyze the corresponding energy conversion speed and perform control medium classification to obtain corresponding speed classification and medium allocation suggestions;

[0117] 3.1 Energy conversion efficiency difference measurement

[0118] For the various operating modes of the vehicle thermal management system, the energy conversion efficiencies of the heat storage function and the heating function under the on and off conditions in each operating mode are evaluated and compared respectively; a difference measurement is performed based on the energy conversion efficiency to obtain the energy conversion efficiency difference; based on the energy conversion efficiency difference, the energy efficiency improvement space under different operating modes is quantitatively analyzed to obtain the difference analysis results.

[0119] Specifically:

[0120] The energy conversion efficiency assessment compares the energy distribution in different modes. By comparing and analyzing the energy loss performance of each mode stage or terminal, the energy conversion efficiency improvement of the thermal energy network is compared when the thermal storage module is activated and when cabin heating is activated. This helps identify the possible energy loss paths and efficiency improvement potential of each component.

[0121] The calculation steps are as follows:

[0122] 1) Determine the thermal energy of high and low temperature systems enter;

[0123] 2) Determine the subsystem Output;

[0124] 3) Calculate the difference in energy conversion efficiency between turning on the heat storage module and heating the cabin to calculate the energy quality coefficient:

[0125]

[0126] Energy conversion efficiency difference = η ex *100%

[0127] The energy conversion efficiency difference measurement method evaluates the differences between each conversion stage or terminal system by quantifying the energy loss ratio, so as to reduce energy loss and improve the overall energy utilization efficiency. efficiency.

[0128] By calculating the difference in energy conversion efficiency between when the heat storage module is enabled and when cabin heating is enabled under external characteristic conditions and when neither is enabled, the energy conversion efficiency difference table 2 is obtained as follows:

[0129] Table 2 Energy conversion efficiency difference metrics

[0130] model Whether to enable the heat storage module Whether to enable cabin heating Differences in energy conversion efficiency Hybrid Mode 1 no no - Hybrid Mode 2 yes no 3.1％ Hybrid Mode 3 yes yes 6.2％ Pure electric mode 1 no no - Pure Electric Mode 2 yes no 5.9％ Pure Electric Mode 3 yes yes 11.9％ Power generation mode no no - Stop heating mode yes yes 100％

[0131] Table 2 is a measure of the difference in energy conversion efficiency. In the multi-mode design of the thermal management system, different operating modes significantly affect the difference in energy conversion efficiency by enabling or disabling the heat storage module and crew cabin heating functions. Hybrid mode 1 does not enable the heat storage module and crew cabin heating. After hybrid mode 2 enables the heat storage module, the energy conversion efficiency increases by 3.1%; and hybrid mode 3 further improves the energy conversion efficiency to 6.2% when the heat storage module and crew cabin heating are enabled at the same time. In pure electric mode, pure electric mode 1 does not enable any additional functions, and the energy conversion efficiency does not change; after pure electric mode 2 enables the heat storage module, the energy conversion efficiency reaches 5.9%; and pure electric mode 3 significantly improves the energy conversion efficiency to 11.9% when the heat storage module and crew cabin heating are enabled at the same time. In power generation mode, the heat storage module and crew cabin heating are not enabled, and the energy conversion efficiency is not affected; while in shutdown heating mode, the heat storage module and crew cabin heating functions are enabled at the same time, which converts the heat energy that was originally unusable into energy. The difference in energy conversion efficiency reached 100%, achieving the utilization of waste heat. These results show that by rationally configuring the thermal storage module and the cabin heating function, the difference in energy conversion efficiency can be significantly optimized, improving the overall energy efficiency of the system.

[0132] 3.2 Difference measurement of energy conversion response speed

[0133] Analyze the energy conversion response speed of the subsystem under instantaneous extreme conditions, establish a difference measurement method for the energy conversion response speed, and compare the response characteristics of the subsystem under different heat source fluctuations by defining the response speed differentiation measurement coefficient. Then, different cooling media are allocated to lay the foundation for realizing the instantaneous high-response heat flow control of the system.

[0134] Specifically:

[0135] Analyze the energy conversion response speed of the subsystem under transient extreme conditions. Establish a differential measurement method for energy conversion response speeds, and use simulation to capture the subsystem's response characteristics under varying heat source fluctuations. Combined with simulation data, construct a transient extreme heat flux distribution network and develop targeted control strategies to achieve highly responsive transient heat flux control.

[0136] Based on the results of this differential analysis, simulation tools are used to simulate the vehicle thermal management system's response under varying heat source fluctuations. The energy flow response speeds of key subsystems within the vehicle thermal management system under transient extreme conditions are analyzed to measure and differentiate response speed differences. A key focus is on analyzing the speed response differences of subsystems when the heat source undergoes sudden changes. When the load suddenly increases or decreases during high and low temperature cycles, how can the internal heat flow of the system be rapidly regulated to maintain stability? The transient response characteristics of each subsystem in the simulation data are captured to evaluate its performance under heat source fluctuations.

[0137] The calculation expression of the response speed difference metric is:

[0138] ε=△P / △t

[0139] Where ε is the rate of change of power over a period of time, P is power, and t is time. ε measures the variability of the system's response speed, evaluating how long it takes for the computing system to reach the next stable state from one state when faced with transient conditions.

[0140] The calculation expression of the response speed difference is:

[0141] η sd =ε y / ε x

[0142] Among them, η sd is the response speed differentiation coefficient, ε x is the rate of change of heat release of the system independent variable (heat source) over time, ε y is the rate of change of the system's heat absorption with time in response to changes in the independent variable; this formula quantifies the difference in the system's response speed under different heat source fluctuations and measures the difference in energy conversion response speed.

[0143] Based on the response speed difference metric and the response speed differentiation, the response speed differences of phase change materials, coolants, and air to transient heat flux mutations in heat sources are compared, and the mutation levels of different heat sources are distinguished to match the most suitable cooling medium (determine the energy conversion medium required for each subsystem) and obtain corresponding speed classification and medium allocation recommendations.

[0144] like Figure 13 、 Figure 14 As shown in Table 3, there are significant differences in the response speeds of different cooling media. In the differential measurement of the response speeds of phase change materials, coolants, and air during a transient heat flux mutation, the response speed differential measurement coefficients for phase change materials are 1.6, coolants are 4.25, and air is 8.05. This indicates that during a transient heat flux mutation, phase change materials have the fastest response speed, followed by coolants, and air has the slowest response speed, as shown in Table 3.

[0145] Table 3 Response speed differentiation measurement

[0146]

[0147] Therefore, when facing a sudden change in heat flow from a heat source, it is necessary to match the corresponding cooling medium according to the transient heat flow mutation speed of the heat source. In a thermal energy network, the working characteristics of each subsystem are different, and the heat source mutation speed is also different. Different heat source mutation speed levels are divided according to their mutation speed and heat:

[0148] Minute-level components: large heat capacity, slow heat mutation rate, usually involving large mechanical components such as engines, radiators, and heat sinks / heat exchangers.

[0149] Second-level components: small heat capacity, fast heat mutation rate, involving mechanical components such as motors.

[0150] Millisecond-level components: The heat capacity is very small, the heat changes suddenly at a fast rate, and involve electronic components such as controllers.

[0151] Table 4 shows the mutation speed and distribution medium of different heat source components. The corresponding cooling medium is allocated according to the classification level. Among them, the millisecond-level components are allocated with the fastest response speed phase change material and coolant, the second-level and minute-level components are allocated with coolant for heat dissipation, and finally the slowest response speed air is allocated to the radiator to discharge the waste heat into the atmosphere.

[0152] Table 4 Different heat source components mutation speed and distribution medium

[0153]

[0154]

[0155] 4. Construct a heat flow prediction model based on machine learning, combine the heat flow prediction model with the energy velocity difference metric, design an algorithm reward function, and obtain an optimization control strategy based on the response difference metric. This includes:

[0156] 4.1 Construction of heat flow prediction model

[0157] Using measured and simulated data sets, artificial neural network training is performed on the main components of the vehicle thermal management system to perform real-time heat flow distribution prediction and network modeling under multiple working conditions, and a heat flow prediction model based on machine learning is obtained; using the heat flow prediction model, the heat dissipation of each component under different speeds, torques and load conditions is predicted in real time, and energy flow distribution data is obtained to dynamically optimize the high and low temperature multi-circuit thermal energy network.

[0158] Specifically:

[0159] 4.1.1 Transient extreme heat flux distribution network

[0160] like Figure 15 As shown, Figure 15It is a schematic diagram of the instantaneous extreme heat flow distribution network, which includes an energy flow model and a vehicle cooling system model. The energy flow simulation module is based on a machine learning model and has the ability to input and train experimental and simulation data. By inputting the real-time speed and torque of the power components, the real-time heat dissipation of the heat source components is output. In the cooling system simulation module, it has the ability to call the one-dimensional simulation model of the cooling system. By inputting the real-time heat dissipation of the heat source components and the status of components such as the valves of the water pump and fan, the temperature, flow rate and other parameters of each node of the cooling system are output. In the cooling system control module, it has the ability to call the one-dimensional control joint simulation model of the cooling system and provides several control algorithm templates. Subsequent models can select templates as needed to start building the control model. By inputting the control target and the water temperature of each node, the real-time status of components such as the water pump, fan and valve is output.

[0161] 4.1.2 Machine Learning-Based Instantaneous Extreme Heat Flow Distribution Network

[0162] like Figure 16 As shown, Figure 16 This is a schematic diagram of a machine learning-based energy flow model. The transient extreme heat flux distribution network model is based on a machine learning model. The training data for the transient extreme heat flux distribution network is input using heat dissipation data from various components under different operating conditions. This training data can come from vehicle tests, bench tests, or simulations. This ensures the accuracy and scalability of the database. Through machine learning model training, a heat dissipation prediction model for each power unit component is generated. Based on the engine torque speed, generator torque speed, and motor torque speed input from the vehicle dynamics model, the heat dissipation and effective power of each component in the current state are calculated, ultimately generating energy flow distribution data. The machine learning-based energy flow model has significant advantages. First, trained with extensive data from vehicle tests, bench tests, and simulations, the model accurately predicts the heat dissipation of each component under different operating conditions, thereby improving the accuracy of energy flow distribution. Second, the model can receive input parameters from the vehicle dynamics model in real time and rapidly calculate the heat dissipation and effective power of each component, supporting real-time energy management. Continuous updates to the training data enhance the adaptability and robustness of the transient extreme heat flux distribution network.

[0163] Among them, the training data includes constructing first training data and second training data; the first training data includes ambient temperature, altitude, engine speed, engine torque, body heat dissipation, interstage intercooler heat dissipation, first-stage intercooler heat dissipation, second-stage intercooler heat dissipation and oil cooler heat dissipation, etc., and the second training data includes generator speed, generator torque, left motor speed, left motor torque, right motor speed, right motor torque, generator heat dissipation, motor heat dissipation and battery discharge status, etc.

[0164] A first boundary condition is defined based on the first training data, a second boundary condition is defined based on the second training data, and a machine learning model is trained using the first training data and the second training data based on the first boundary condition and the second boundary condition to obtain a heat dissipation prediction model for each component of the power device.

[0165] like Figure 17 As shown, Figure 17 (a) shows the different layers of an artificial neural network. An ANN consists of an input layer, multiple hidden layers, and an output layer. Training is performed using a known set of input-output data and a suitable learning method by adjusting the weight coefficients between neurons. The training process continues until the network output matches the desired output. Changes to weights and biases should reduce the error between the network output and the desired output. Training terminates automatically when the error falls below a certain threshold or exceeds a maximum duration.

[0166] Figure 17 (b) is a flowchart of the artificial neural network training process. Before collecting training data, the input and output parameters are selected to form an input-output matrix. Because neural networks are trained under supervision, the input and output data are obtained from experiments or digital simulations. The collected data is divided into three data sets (training set, validation set, and test set). The input and output parameters are then normalized to increase the learning speed of the algorithm. The network structure is selected based on the application involved, and the network parameters (such as the training data requirements, the number of hidden layers, the number of hidden neurons, the learning rate, and the momentum coefficient) are optimized to achieve good accuracy. Finally, the trained algorithm is evaluated.

[0167] like Figure 18 As shown, Figure 18 The graph shows the training and validation results. The graph compares the heat dissipation between the validation and training set results and the simulation results. The X-axis represents the predicted value, the Y-axis represents the simulated value, and the diagonal line in the middle represents the fit evaluation line. The closer a point in the graph is to the fit evaluation line, the better the fit. RMSE measures the difference between the predicted and simulated values ​​by calculating the root mean square error, as shown in the following formula:

[0168]

[0169] In the formula, n is the total number of data. The closer the RMSE result is to zero, the more accurate the prediction.

[0170] R 2 It is used to determine the correlation between the predicted data and the actual data. 2 is equal to 1, then the predicted data and the actual data are completely correlated, R 2 The calculation formula is as follows:

[0171]

[0172] Where y' is the value of the original output data.

[0173] By calculation, in the training set, their RMSE is less than 12, and their R 2 The values ​​are very close to 1. This data shows that the ANN algorithm has achieved a high level of learning on the training set. In the validation set, their RMSE is less than 13, and their R 2 The values ​​are all within 0.03 of 1. The prediction results of the ANN algorithm on the validation set show that the algorithm has the ability to predict instantaneous extreme heat flux and has generalization ability.

[0174] like Figure 19 As shown, Figure 19 In order to realize the instantaneous extreme heat flux distribution network model, the machine learning model and the one-dimensional thermal energy network model are combined through Simulink to form an instantaneous extreme heat flux distribution network model to realize dynamic heat flux characteristic analysis and control strategy optimization.

[0175] 4.2 Control strategy formulation

[0176] Based on the response speed difference metric, the response speed differentiation and the dynamic optimization results of the high and low temperature multi-loop thermal energy network, an algorithm reward function is designed to formulate an optimization control strategy for the vehicle thermal management system execution unit.

[0177] Specifically:

[0178] A control strategy based on energy response speed difference measurement is designed. Based on the state parameters within the cooling system, the parameters of the cooling system components are controlled to achieve efficient heat flow regulation and optimal distribution of system thermal energy. Based on the prediction model, the system further uses a reward function based on energy response speed difference measurement to optimize control decisions. This process evaluates the differences in energy response speed between different control strategies and adjusts the weight coefficients accordingly. Here, the algorithm reward function is formulated as:

[0179] R total =R temp +R fluct +R energy +R stable

[0180] R temp =-w1·(T t -T target ) 2

[0181] R fluct =-w2·ΔT, ΔT=|T t -Tt-1 ∣

[0182] R energy =-w3·(∑P pump +∑P fan )

[0183] R stable = +w4·I(|T t -T target ∣≤∈)

[0184] in:

[0185] R temp To track the temperature, accurate tracking is encouraged; t is the actual temperature; T target Target temperature;

[0186] R fluct For temperature fluctuation suppression, suppress frequent fluctuations;

[0187] R energy Optimize the energy consumption efficiency of water pumps and fans to achieve optimal energy consumption of water pumps and fans; pump is the water pump power; P fan is the fan power;

[0188] R stable is the temperature stabilization time; |T t -T target ∣≤∈ is the temperature stability range. If the temperature enters the stable range, the reward will be gradually accumulated;

[0189] w1, w2, w3, and w4 are all weights.

[0190] By designing a reward function based on a measure of energy response speed differences, the intelligent agent can achieve a dynamic balance between precise temperature control, low energy consumption, and rapid stabilization, adapting to the complex thermal management requirements of extreme heat flow scenarios. This allows the system to more precisely adjust the openings of fans, pumps, and valves for more effective thermal management. This approach not only enables precise temperature control but also optimizes energy use, improving overall energy efficiency.

[0191] Therefore, the present invention provides a method for measuring the energy quality and energy conversion differences of a thermal management system based on #imgpt85# analysis. This method can determine the appropriate quality of input heat flow according to the working requirements of each subsystem, achieve reasonable distribution of heat flow and utilize it step by step according to its quality, thereby improving the energy utilization efficiency of the overall system. It can also quantify the energy conversion efficiency differences of the cooling system, design the optimal energy utilization terminal combination plan, reduce energy loss, and improve the overall performance of the system.

[0192] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0193] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A method based on The energy taste and energy conversion difference measurement method of the thermal management system analyzed is characterized by: include: Real-time acquisition of key parameters of each component in the vehicle thermal management system, obtaining original parameter data, and performing maintenance on each component based on the original parameter data. Analyze and obtain the energy quality coefficient; Based on the energy quality coefficient, the quality difference measurement and heat flow distribution are performed to obtain the quality classification and flow configuration of each component. Based on the quality classification and flow configuration, a thermal energy network model is constructed, and the network loop is optimized to form a high and low temperature multi-loop thermal energy network; Based on the high and low temperature multi-circuit thermal energy network, the differences in energy conversion efficiency of components are measured to obtain difference analysis results. Based on the difference analysis results, the corresponding energy conversion speed is analyzed and the control medium classification is performed to obtain corresponding speed classification and medium distribution suggestions; A heat flow prediction model based on machine learning is constructed. Combining the heat flow prediction model with energy velocity difference metric, an algorithm reward function is designed to obtain an optimization control strategy based on response difference metric.

2. A method according to claim 1 The energy taste and energy conversion difference measurement method of the thermal management system analyzed is characterized by: Real-time acquisition of key parameters of each component in the vehicle thermal management system, obtaining original parameter data, and performing maintenance on each component based on the original parameter data. Analyze and obtain the energy quality coefficient, including: Real-time acquisition of temperature, flow, power, and heat flow of each component in the vehicle thermal management system to obtain raw parameter data; these components include the engine, generator, motor, thermal storage module, controller, coolant circuit, radiator, oil cooler, intercooler, and electronically controlled valve; Based on the original parameter data, each component in the vehicle thermal management system is Analyze and use relevant thermodynamic formulas to calculate the input of each component separately and output , and then according to the input and the output , calculate the energy quality coefficient of each component.

3. A method according to claim 2 based on The energy taste and energy conversion difference measurement method of the thermal management system analyzed is characterized by: Based on the energy quality coefficient, the quality difference measurement and heat flow distribution are performed to obtain the quality classification and flow configuration of each component. Based on the quality classification and flow configuration, a thermal energy network model is constructed, and the network loop is optimized to form a high and low temperature multi-loop thermal energy network, including: According to the energy quality coefficient and temperature index, the energy quality of each component is distinguished, and the quality coefficient of each component is defined. Then, based on the quality coefficient, the adaptability temperature and thermal energy of each component are sorted out. , and classify the components into layers; wherein the energy quality includes high quality, medium quality and low quality; According to the working requirements of each subsystem in the high and low temperature circulating cooling system, heat flow is distributed and utilized step by step according to the energy quality, and quality classification and flow direction configuration are obtained; Based on the grade classification and flow configuration, a thermal energy network model is constructed. Using the thermal energy network model, high-grade components are connected in parallel to the high-temperature cycle, and low-grade components are connected to the low-temperature cycle to organize the heat energy flow of the components; Based on the heat energy flow of the components and taking into account energy recovery and cabin heating, the various components are arranged at corresponding key nodes to capture and utilize waste heat, realize network loop optimization, and form a high and low temperature multi-loop thermal energy network.

4. A method according to claim 3 based on The energy taste and energy conversion difference measurement method of the thermal management system analyzed is characterized by: Based on the high and low temperature multi-circuit thermal energy network, the differences in component energy conversion efficiency are measured to obtain difference analysis results, including: For the various operating modes of the vehicle thermal management system, evaluate and compare the energy conversion efficiency of the heat storage function and the heating function under the conditions of turning on and off in each operating mode; The energy conversion efficiency is measured to obtain a difference in energy conversion efficiency. Based on the difference in energy conversion efficiency, the room for energy efficiency improvement under different operating modes is quantitatively analyzed to obtain a difference analysis result.

5. A method according to claim 4 based on The energy taste and energy conversion difference measurement method of the thermal management system analyzed is characterized by: Based on the difference analysis results, the corresponding energy conversion speed is analyzed and the control medium classification is performed to obtain the corresponding speed classification and medium allocation suggestions, including: Based on the difference analysis results, using simulation tools to simulate the response of the vehicle thermal management system under different heat source fluctuation conditions, and analyzing the energy flow response speed of key subsystems in the vehicle thermal management system under transient extreme conditions to measure and differentiate the response speed differences; The calculation expression of the response speed difference metric is: ε=△P / △t Where σ is the rate of change of power over a period of time, P is power, and t is time; The calculation expression of the response speed difference is: or sd =e y / e x Among them, η sd is the response speed differentiation coefficient, ε x is the rate of change of heat release of the system independent variable over time, σ y is the rate of change of the system's heat absorption with time in response to changes in the independent variable; Based on the response speed difference metric and the response speed differentiation, the response speed differences of the phase change material, coolant, and air to the transient heat flux mutation of the heat source are compared, and the mutation levels of different heat sources are distinguished to match the optimal cooling medium, thereby obtaining corresponding speed classification and medium allocation recommendations.

6. A method according to claim 5 based on The energy taste and energy conversion difference measurement method of the thermal management system analyzed is characterized by: A machine learning-based heat flow prediction model is constructed. Combining the heat flow prediction model with the energy velocity difference metric, an algorithmic reward function is designed to obtain an optimized control strategy based on the response difference metric, including: Using measured and simulated data sets, artificial neural network training is performed on the main components of the vehicle thermal management system to perform real-time heat flow distribution prediction and network modeling under multiple operating conditions, thereby obtaining a heat flow prediction model based on machine learning; Using the heat flow prediction model, the heat dissipation of each component under different speed, torque and load conditions is predicted in real time to obtain energy flow distribution data for dynamic optimization of the high and low temperature multi-circuit thermal energy network; Based on the response speed difference metric, the response speed differentiation and the dynamic optimization results of the high and low temperature multi-loop thermal energy network, an algorithm reward function is designed to formulate an optimization control strategy for the vehicle thermal management system execution unit.

7. A method according to claim 6 based on The energy taste and energy conversion difference measurement method of the thermal management system analyzed is characterized by: The construction process of the heat flow prediction model includes: Constructing first training data and second training data; the first training data includes ambient temperature, altitude, engine speed, engine torque, body heat dissipation, interstage intercooler heat dissipation, first-stage intercooler heat dissipation, second-stage intercooler heat dissipation, and oil cooler heat dissipation; the second training data includes generator speed, generator torque, left motor speed, left motor torque, right motor speed, right motor torque, generator heat dissipation, motor heat dissipation, and battery discharge status; defining a first boundary condition based on the first training data, defining a second boundary condition based on the second training data, and training a machine learning model using the first training data and the second training data based on the first boundary condition and the second boundary condition to obtain a heat dissipation prediction model for each component of the power device; According to the vehicle dynamics model, the engine torque speed, generator torque speed and motor torque speed are input into the heat dissipation prediction model to calculate the heat dissipation and effective power of each component in the current state to obtain energy flow distribution data.

8. A method according to claim 7 based on The energy taste and energy conversion difference measurement method of the thermal management system analyzed is characterized by: The calculation expression of the algorithm reward function is: R total =R temp +R fluct +R energy +R stable R temp =-w1·(T t -T tar get ) 2 R fluct =-w2·ΔT,ΔT=∣T t -T t-1 ∣ R energy =-w3·(∑P pump +∑P fan ) R stable =+w4·I(∣T t -T target ∣≤∈) Among them, R temp is the temperature tracking target, T t is the actual temperature, T target Target temperature, R fluct For temperature fluctuation suppression, R energy To optimize the energy efficiency of water pumps and fans, P pump is the pump power, P fan is the fan power, R stable is the temperature stabilization time, w1, w2, w3, and w4 are all weights.

Images