Thermal management system for an electric vehicle and method of operation thereof

Abstract

A thermal management system for an electric vehicle and a method for operating the same are provided, which achieves an optimal balance between user comfort and driving range by applying supervised learning. An AI-based control approach considers user requirements regarding driving speed, interior temperature, and conditions of a selected driving route to generate a final control means output that operates the thermal management system with minimum energy consumption and maximum COP. A continuous and highly efficient thermal management system for an electric vehicle is provided, comprising a thermal system including a refrigerant loop and / or a coolant loop and a control means. The control means applies a data-driven supervised learning model in combination with a control optimization that provides optimal control set points, with standard sub-controls.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application is based on German patent application No. 102022115096.8, filed on June 15, 2022, the entire contents of which are incorporated herein by reference. [Technical field]

[0002] The present disclosure relates to a thermal management system for an electric vehicle and a method of operating the same. [Background technology]

[0003] In battery-powered electric vehicles, the demand for driving range and driver comfort is pushing for further efficiency of the thermal system of electric vehicles. This is increasing the complexity of the thermal management system of electric vehicles and its control. Therefore, it is desirable to apply advanced control techniques to increase the efficiency of the thermal management system of electric vehicles. Current state-of-the-art thermal systems have many actuators, which are controlled to achieve the target temperatures of the cabin, the battery, and the electric powertrain. Conventionally, in order to achieve the required heating performance with minimum energy loss, the system needs to be calibrated through a large number of tests under diverse conditions, which significantly increases the system calibration effort. The found calibration values ​​are stored in a look-up map and the control is configured. Despite all the calibration efforts, a completely optimal control is not always guaranteed throughout the entire driving range.

[0004] Reference 1 discloses a heat exchange system for cooling purposes in large-scale industrial applications. To increase the efficiency of the heat exchange system, a supervised learning model is applied to determine optimal operating parameters for a particular cooling application. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2011 / 119398 Summary of the Invention

[0006] An objective of the present disclosure is to provide a thermal management system for an electric vehicle and an operating method thereof that can apply supervised learning to optimize the balance between user comfort and driving range.

[0007] The above objectives are achieved by a thermal management system for an electric vehicle according to the present disclosure.

[0008] The AI-based control method according to the present disclosure generates a final output of the control means that operates the thermal management system with minimum energy consumption and maximum COP, taking into account the user's requirements for driving speed, vehicle interior temperature, and conditions of the selected driving route. A continuous and highly efficient thermal management system for an electric vehicle is provided, comprising a thermal system including a refrigerant loop and / or a coolant loop and a control means. The refrigerant system is also known as an air conditioning system or a heat pump system (hereinafter also described as an H / P system). The heat pump is a key thermal system for regulating, heating or cooling the cabin to a comfortable temperature range and / or for regulating, heating or cooling the high voltage battery to an optimal operating condition. The coolant system is necessary to regulate the electric powertrain and the battery to an optimal and robust temperature range. The control means applies a data-driven supervised learning model to standard lower level controls in combination with a control optimization that provides optimal control settings. The AI-based control means automatically ensures optimal efficiency of the refrigerant or coolant system under all conditions, increasing the range of the electric vehicle. AI-based control measures significantly reduce the calibration effort since the AI ​​model can be automatically trained offline, for example using neural networks. The thermal plant digital twin is trained using supervised learning methods. The data used in training comes from an accurate simulation environment that allows efficient data generation by fast and continuous operation of the simulated plant. Alternatively, the above data may be obtained directly from the target vehicle. Once the supervised learning model is trained, it can be used as a function call for the optimal control problem. Both the trained model and the optimization method can be executed in real time to ensure continuous optimality.

[0009] The present disclosure has the following advantages: - Guaranteed optimum system performance, i.e. efficiency. - Reduction in calibration effort by replacing current map-based calibration. -Easy per-module updates by retraining models with updated datasets.

[0010] For data-driven supervised learning models, preferably artificial neural networks are applied, and for control optimization, preferably swarm optimization or gradient dispersion methods are applied.

[0011] The present disclosure may be directed to a thermal management system comprising a thermal system including an H / P system that regulates, heats or cools the cabin to a comfortable temperature range taking into account the state of charge of the battery, ambient conditions, the state of the H / P system, and the state of the vehicle.

[0012] The condenser means includes an inner condenser arranged in the HVAC flow path and operated with inner condenser power, and / or an outer condenser arranged outside the HVAC flow path and in communication on the coolant side with a heat core arranged in the HVAC flow path and operated with outer condenser power.

[0013] The present disclosure can use a data-driven supervised learning model using an optimization algorithm to determine optimal input parameters to the control means.

[0014] This disclosure may define a preferred target power calculation means to be used as input to the data-driven supervised learning model.

[0015] The present disclosure may define the most appropriate optimal control settings that are output by the optimization algorithm / unit and input downstream.

[0016] The present disclosure can determine the most appropriate subordinate control outputs to be used to operate and control the thermal management system.

[0017] The present disclosure may be directed to a thermal management system comprising a thermal system, including an electric powertrain cooling system, that regulates and operates the electric powertrain and battery in an optimal and robust temperature range.

[0018] According to the present disclosure, the external condenser coolant loop may be connected with the powertrain / battery coolant loop.

[0019] The present disclosure may define optimal inputs, intermediate outputs, and optimal control settings for the lower level control units / algorithms when the H / P system is operated in a heating mode to warm the cabin air.

[0020] The present disclosure may define optimal inputs, intermediate outputs, and optimal control settings for the lower level control units / algorithms when the H / P system is operated in a dehumidification mode where it reheats and dehumidifies cooled cabin air.

[0021] The present disclosure may define optimal inputs, intermediate outputs, and optimal control settings for the underlying control units / algorithms when the H / P system is operated in a cooling mode to cool the cabin air. [Brief description of the drawings]

[0022] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure. Corresponding parts are indicated by corresponding reference numerals throughout the several views of the drawings. [Figure 1] FIG. 1 shows the H / P system, which heats and cools the cabin air as part of the thermal system that is managed and controlled by the thermal management system. [Diagram 2] Figure 2 shows the electric powertrain / battery cooling system that keeps the electric powertrain and battery within a desired temperature range. [Diagram 3] FIG. 3 shows a control means for controlling the thermal system shown in FIGS. [Figure 4] FIG. 4 shows a first embodiment of the present disclosure applied when cabin heating is required. [Diagram 5] FIG. 5 shows a second embodiment of the present disclosure applied when cabin dehumidification is required. [Figure 6]FIG. 6 shows a third embodiment of the present disclosure which is applied when cabin cooling is required. [Figure 7] FIG. 7 illustrates a fourth embodiment of the present disclosure which is a generalized H / P system control. [Figure 8] FIG. 8 illustrates a fifth embodiment of the present disclosure applied to keep an electric powertrain / battery coolant system within a proper temperature range under conditions imposed by the driver, ambient conditions, and vehicle component specifications. [Figure 9] FIG. 9 shows a sixth embodiment with a modified H / P system. [Figure 10] FIG. 10 shows a seventh embodiment that adds an interconnection between the H / P system and the electric powertrain / battery coolant system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] Exemplary embodiments will now be described in more detail with reference to the accompanying drawings. The following description is merely exemplary in nature and is not intended to limit the scope, application, or uses of the present disclosure.

[0024] FIG. 1 shows a heat pump or H / P system 100 for heating and cooling the cabin air, FIG. 2 shows an electric powertrain / battery cooling system 200 for keeping the electric powertrain and battery within a desired temperature range, and FIG. 3 shows a control means 300 for controlling the thermal management system.

[0025] The H / P system 100 includes a chiller 2, an inner condenser 102 (an example of a condenser means), an evaporator 104, a compressor 106, an outer heat exchanger 108 having a fan 110 connected to each other via a refrigerant loop 112, and a blower 114 for sending air as a cooling fluid toward the evaporator 104 and the inner condenser 102. The H / P system 100 further includes an accumulator 116 for storing liquid refrigerant and separating the liquid refrigerant from the gaseous refrigerant. The outlet of the compressor 106 is connected to the inlet of the inner condenser 102. The outlet of the inner condenser 102 is connected to the outer heat exchanger expansion valve 118, which is connected to the inlet of the outer heat exchanger 108. The opening degree of the outer heat exchanger expansion valve 118 is set to an EXV OHX (corresponding to the outer heat exchanger expansion valve opening). The outlet of the outer heat exchanger 108 is connected via a first check valve 120 to a point located between the evaporator expansion valve 122 and the chiller expansion valve 124. The opening of the evaporator expansion valve 122 is referred to as EXV EVA (corresponding to the evaporator expansion valve opening). The opening of the chiller expansion valve 124 is referred to as EXV CHI (corresponding to the chiller expansion valve opening degree). The chiller expansion valve 124 is connected to the refrigerant inlet of the chiller 2. The evaporator expansion valve 122 is connected to the inlet of the evaporator 104. The outlet of the evaporator 104 is connected to the inlet of the accumulator 116 via the pressure regulating valve 126. The refrigerant outlet of the chiller 2 is also connected to the inlet of the accumulator 116. The outlet of the outer heat exchanger 108 is similarly connected to the inlet of the accumulator 116 via the dehumidification control valve 130 (an example of a dehumidification valve means) and the second check valve 132. A point located between the outer heat exchanger expansion valve 118 and the outlet of the inner condenser 102 is connected to a point located between the first check valve 120 and the chiller expansion valve 124 or the evaporator expansion valve 122 via the heating control valve 134 (an example of a heating valve means). The inner condenser 102 and evaporator 104 are disposed in a heating, cooling and air conditioning or HVAC channel 136 that enters the vehicle interior.

[0026] The electric powertrain / battery cooling system 200 shown in FIG. 2 includes a coolant side of a chiller 2, a battery 202, a battery heater 203 (i.e., an electric battery heater), an electric powertrain 204, and a radiator 206, which are interconnected via a powertrain / battery coolant loop 208. The powertrain / battery coolant loop 208 connects a coolant outlet of the chiller 2 and a coolant inlet of the battery heater 203. The coolant outlet of the battery heater 203 is connected to a coolant inlet of the battery 202. The coolant outlet of the battery 202 is connected to a coolant inlet of the chiller 2 via a two-way valve 210 (an example of a valve means) and a first pump 212 (an example of a coolant pump means). The coolant outlet of the chiller 2 is also connected to a coolant inlet of the electric powertrain 204 and a second pump 216 (an example of a coolant pump means). A coolant outlet of the electric powertrain 204 is connected to a first pump 212 and a coolant inlet of the radiator 206 via a three-way valve 218 (an example of a valve means). As shown in Figures 1 and 2, the outer heat exchanger 108 is disposed opposite the radiator 206, which is equipped with an air fan 110 and active grill shutters 4.

[0027] The control means 300 comprises a data-driven supervised learning model unit 302, a control optimization unit 304, and a low-level control unit 306. The inputs 318 to the control means are applied to the data-driven supervised learning model unit 302. The data-driven supervised learning model unit 302 uses the data-driven supervised learning model to calculate a cost function in an optimization domain as an intermediate output 320 to the control optimization unit 304. The optimization unit 304 (i.e., a control optimization algorithm) calculates optimal control settings 322 for the low-level control unit 306. The low-level control unit 306 performs low-level control and calculates a final control means output 324 (i.e., low-level control output) for operating the thermal management system. The final control means output 324 corresponds to the low-level control output.

[0028] The inputs 318 to the control means 300 and the data-driven supervised learning model unit 302 are selected from a set of parameters defining the target air conditions in the cabin, the ambient conditions, the thermal system conditions, and the vehicle state. The intermediate outputs calculated by the data-driven supervised learning model unit 302 include the coefficient of performance COP of the thermal system and / or the power consumption parameters Pxx of the electrically driven components, such as pumps, valve actuators, fans, blowers, compressors, etc. The optimal control set points for the lower level controller 306 include operating parameters such as compressor speed, blower speed, valve actuation, etc., and / or temperature conditions such as cabin air temperature, battery temperature, coolant temperature, refrigerant temperature, etc.

[0029] An artificial neural network is preferably applied to the data-driven supervised learning model unit 302. For optimization in the control optimizer unit 304, a swarm optimization or gradient dispersion method is preferably applied.

[0030] 4 illustrates the first embodiment of the present disclosure when cabin heating is requested. Examples of suitable inputs to the control means 300 for cabin heating include the following inputs 318: Target T_air_ICDS_out = target air temperature at the inner condenser air outlet (corresponding to the inner condenser air outlet target temperature), N Blower = Blower rotation speed (target blower speed, corresponding to the target blower load / air volume), T_amb = ambient temperature, Target T_coolt_CHI_out = Target chiller cooling water outlet temperature (corresponding to the target chiller cooling water outlet temperature), T_coolt_CHI_in = Chiller inlet cooling water temperature (corresponding to chiller cooling water inlet temperature), Vdot_coolt_CHI_in = cooling water volume flow rate entering the chiller (corresponding to chiller cooling water inlet mass / volume flow rate), H_amb = ambient humidity, V_spd = vehicle speed, Recycle_ratio = ventilation rate in the cabin (corresponding to the indoor air recycling rate). Fanreq coolt = Fan speed requested by typical HVAC controls (corresponding to target fan load factor, fan load / speed).

[0031] Among the above inputs, Target T_air_ICDS_out, N Blower , and T_amb is the target inner condenser power P as an input to the data-driven supervised learning model unit 302. ICDS,req The inputs T_coolt_CHI_out, T_coolt_CHI_in, and Vdot_coolt_CHI_in are fed to an inner condenser power calculation means 326 which calculates the target chiller power P CHI,req The inner condenser power calculation means 326 and the chiller power calculation means 328 may be considered as part of the data-driven supervised learning model unit 302. coolt These inputs are directly input to the data-driven supervised learning model unit 302. The data-driven supervised learning model unit 302 calculates the calculated inner condenser power P ICDS (u), Calculated chiller power P CHI The control optimization unit 304 outputs the calculated COP value COP(u) and the calculated COP value COP(u) as intermediate output 320. In the control optimization unit 304, a cost function is defined as shown in the following formulas 1 to 3.

number

number

number

[0032] Here, w 1 , w 2 , w 3is the coefficient of performance COP, and the chiller power P CHI , inner condenser power P ICDS COP is the weight that adjusts the effect of useful heating Q H Or cooling Q C The COP for heating is the ratio of Q to the work (energy) Win input into the system. H / W in It is.

[0033] The appropriate optimal control setting value 322 output by the control optimization unit 304 is Optimum compressor speed N CMP,opt (corresponding to the rotation speed of the compressor 106), Optimum inner condenser subcooling temperature T SC,ICDS,opt (corresponding to the subcooling temperature of the inner condenser 102), and Optimal chiller superheat temperature T SH,CHI,opt (Corresponding to the overheat temperature of Chiller 2).

[0034] In addition, Optimal opening of inner condenser expansion valve 118 and chiller expansion valve 124 EXV xx,opt , and Optimal Fan Speed ​​N fan,opt , may also be selected as the optimal control setting 322.

[0035] These optimal control settings 322 are input to a common subordinate control 306 which generates a final control means output 324 .

[0036] 5 illustrates a second embodiment of the present disclosure when cabin dehumidification is required. The following inputs 318 are shown as examples of preferred inputs to the control means 300 for cabin dehumidification: Target T_air_ICDS_out = target air temperature at inner condenser air outlet, N Blower = Blower rotation speed, T_amb = ambient temperature, Target T_air_EVA_out = target air temperature at the evaporator air outlet (corresponding to the evaporator air outlet target temperature), H_amb = ambient humidity, V_spd = vehicle speed, Recycle_ratio = Cabin ventilation rate, and Fanreq coolt = Fan speed requested by typical HVAC controls.

[0037] Among the above inputs, Target T_air_ICDS_out, N Blower , and T_amb is the target inner condenser power P as an input to the data-driven supervised learning model unit 302. ICDS,req The target T_air_EVA_out, N Blower and T_amb is the target evaporator power P as an input to the data-driven supervised learning model unit 302. EVA,req The inner condenser power calculation means 326 and the evaporator power calculation means 330 may be considered as part of the data-driven supervised learning model unit 302. coolt These inputs are directly input to the data-driven supervised learning model unit 302. The data-driven supervised learning model unit 302 outputs as intermediate output 320 the calculated inner condenser power P ICDS (u), evaporator power calculation value P EVA The control optimization unit 304 outputs a calculated COP value COP(u) and a calculated COP value COP(u). In the control optimization unit 304, a cost function is defined as shown in the following formulas 4 to 6.

number

number

number

[0038] Here, w 1 , w 2 , w 3is the coefficient of performance COP, and the chiller power P CHI , inner condenser power P ICDS is the weight that adjusts the influence of

[0039] The appropriate optimal control setting value 322 output by the control optimization unit 304 is Optimum compressor speed N CMP,opt , Optimal evaporator superheating temperature T SH,EVA,opt (corresponding to the superheat temperature of the evaporator 104), Dehumidification control valve 134 status 2WV Dehum,opt , and Heating control valve 130 status 2WV Heat,opt Includes.

[0040] In addition, Optimum inner condenser subcooling temperature T SC,ICDS,opt , Optimal opening of inner condenser expansion valve 118 and evaporator expansion valve 122 EXV xx,opt , and Optimal Fan Speed ​​N fan,opt , may also be selected as the optimal control setting 322.

[0041] These optimal control settings 322 are input to a common subordinate control 306 which generates a final control means output 324 .

[0042] 6 illustrates a third embodiment of the present disclosure when cabin cooling is required. Preferred examples of inputs to the control means 300 for cabin dehumidification include the following inputs 318: Target T_air_EVA_out = Target air temperature at the evaporator air outlet, N Blower = Blower rotation speed, T_amb = ambient temperature, Target T_coolt_CHI_out = target cooling water temperature at chiller cooling water outlet, T_coolt_CHI_in = Chiller inlet cooling water temperature, Vdot_coolt_CHI_in = volume of cooling water entering the chiller, H_amb = ambient humidity, V_spd = vehicle speed, Recycle_ratio = Cabin ventilation rate, and Fanreq coolt = Fan speed requested by typical HVAC controls.

[0043] Target T_air_EVA_out, N Blower The above inputs, such as , and T_amb, are input to the data-driven supervised learning model unit 302 as the target evaporator power P EVA,reqを The inputs T_coolt_CHI_out, T_coolt_CHI_in, and Vdot_coolt_CHI_in are input to the evaporator power calculation means 330, which calculates the target chiller power P CHI,reqを The values ​​are fed to a chiller power calculation means 328 which calculates T_amb, H_amb, V_spd, Recycle_ratio, and Fanreq. coolt These inputs are directly input to the data-driven supervised learning model unit 302. The data-driven supervised learning model unit 302 outputs as intermediate output 320 the calculated evaporator power P EVA (u), Calculated chiller power P CHI The control optimization unit 304 outputs a calculated COP value COP(u) and a calculated COP value COP(u). In the control optimization unit 304, a cost function is defined as shown in the following formulas 7 to 9.

number

number

number

[0044] The appropriate optimal control setting value 322 output by the control optimization unit 304 is Optimum compressor speed N CMP,opt , Optimum outer heat exchanger subcooling temperature TSC,OHX,opt (corresponding to the subcooling temperature of the outer heat exchanger 108), and Optimal chiller superheat temperature T SH,CHI,opt It is.

[0045] In addition, Optimal opening of the outer heat exchanger expansion valve 118 and the chiller expansion valve 124 EXV xx,opt , and Optimal Fan Speed ​​N fan,opt , may also be selected as the optimal control setting 322.

[0046] These optimal control settings 322 are input to a common subordinate control 306 which generates a final control means output 324 .

[0047] 7 is a generalized H / P system control, which is essentially a combination of the first, second and third embodiments. Examples of suitable inputs to the control means 300 for cabin heating include the following inputs 318: Target T_air_ICDS_out = target air temperature at inner condenser air outlet, N Blower = Blower rotation speed (corresponding to the blower load / air volume), T_amb = ambient temperature, Target T_air_EVA_out = Target air temperature at the evaporator air outlet, Target T_coolt_CHI_out = target cooling water temperature at chiller cooling water outlet, T_coolt_CHI_in = Chiller inlet cooling water temperature, Vdot_coolt_CHI_in = volume of cooling water entering the chiller, H_amb = ambient humidity, V_spd = vehicle speed, Recycle_ratio = Cabin ventilation rate, and Fanreq coolt = Fan speed requested by typical HVAC controls.

[0048] The target inner condenser power P is calculated by the inner condenser power calculation means 326, the chiller power calculation means 328, and the evaporator power calculation means 330, which are not shown in FIG. ICDS,req , target chiller power P CHI,req , target evaporator power P EVA,req is calculated and input to the data-driven supervised learning model unit 302. Inputs such as T_amb, H_amb, and V_spd are directly input to the data-driven supervised learning model unit 302. In addition, Recycle_ratio and Fanreq coolt may be selected as an input 318 to the control means and input to the data-driven supervised learning model portion 302.

[0049] The data-driven supervised learning model unit 302 outputs as intermediate output 320 the calculated inner condenser power P ICDS (u), evaporator power calculation value P EVA (u), Calculated chiller power P CHI The control optimization unit 304 outputs a cost function as shown in the following equation.

number

number

number

[0050] In addition, Optimal opening degrees EXV of the outer heat exchanger expansion valve 118, the chiller expansion valve 124, and the evaporator expansion valve 122 xx,opt , and Optimum fan speed N Blower,opt , may also be selected as the optimal control setting 322.

[0051] These optimal control settings 322 are input to a common subordinate control 306 which generates a final control means output 324 .

[0052] 8 illustrates a fifth embodiment of the present disclosure applied to keep an electric powertrain / battery coolant system within a suitable temperature range under conditions imposed by the driver, ambient conditions, and vehicle component specifications. Examples of suitable inputs to the control means 300 for cabin dehumidification include the following inputs 318: Ambient temperature T_amb, Vehicle speed V_spd, Battery temperature T_battery, Electric powertrain temperature T_ePT, Target chiller power P CHI,req (i.e. chiller power required), Target power of electric powertrain P ePT,req (electric powertrain power requirement), and Target battery power P battery,req (i.e. battery power required).

[0053] The data-driven supervised learning model unit 302 calculates the power consumption P ePT The calculated value of (u), the output power P of the battery 202 battery The calculated value of (u) (i.e., the calculated power supply) and the power consumption P of the electric drive auxiliary parts aux Output the calculated value of (u). Here, P auxis the power consumption of all electrically driven components such as fans, blowers, water pumps, valve actuators, etc. In the control optimization unit 304, a cost function is defined as shown in the following formulas 13 to 15.

number

number

number

[0054] The appropriate optimal control setting value 322 output by the control optimization unit 304 is Optimal valve control setpoint MCVe ctrl (corresponding to optimal valve means control parameter), Optimal battery heater control PTC ctrl (for optimal electric heater control parameters), Optimal load eWP1 duty of the first water pump 212, the optimal load eWP2 duty of the second water pump 216, and Optimal fan control Fan ctrl.

[0055] In addition, Optimal electric powertrain oil load ePT oil pump, Optimal active grill shutter control AGS grill shutter, Optimal auxiliary control parameters Aux ctrl, and Optimal chiller power P CHI,opt , may also be selected as the optimal control setting 322.

[0056] The electric powertrain / battery cooling system shown in Figure 2 employs a two-way valve 210 and a three-way valve 218. Instead of the single valve described above, a multi-control valve arrangement may also be employed.

[0057] In any embodiment, the control optimizer 304 calculates optimal control settings that operate the thermal management system with minimum energy consumption and maximum COP, taking into account the user's requirements regarding driving speed, interior temperature, and conditions of the selected driving route.

[0058] 9 shows a sixth embodiment having a modified H / P system in which an outer condenser 138 (an example of a condenser means) is placed outside the HVAC channel 136 instead of the inner condenser 102, and a heat core 140 is placed inside the HVAC channel 136. The outer condenser 138 and the heat core 140 are interconnected via an outer condenser coolant loop 142 with a coolant pump 144. The heat core 140 in the HVAC channel 136 is a liquid / air heat exchanger for warming the indoor air with heat from the outer condenser 138.

[0059] When using the external condenser 138, the control parameters corresponding to the control parameters of the internal condenser 102 are as follows: P OCDS,req = target value of external condenser power, P OCDS (u) = calculated external condenser power, T_coolt_OCDS_out = target outer condenser cooling water outlet temperature, T SC,OCDS = outer condenser subcooling temperature (corresponding to the subcooling temperature of the outer condenser 138), The cooling water volumetric flow rate of the outer condenser cooling water loop 142 (i.e., the target cooling water volumetric flow rate through the outer condenser 138), and the cooling water pump load factor.

[0060] These parameters need to be input to the control means 300 and optimized. The Target T_air_OCDS_out, T_amb, and the cooling water flow rate through the external condenser 138 are used as inputs to the data-driven supervised learning model unit 302 to determine the target external condenser power P OCDS,req The power is fed to an outer condenser power calculation means which calculates:

[0061] 10 shows a seventh embodiment in which the heat core 140 is provided in addition to the inner condenser 102, rather than replacing it with the heat core 140. Furthermore, the outer condenser coolant loop 142 is connected to the powertrain / battery coolant loop 208. The heat core 140 heats the air in the vehicle cabin with heat from the outer condenser and heat from the electric powertrain 204 and / or the battery 202. However, in a bypass with a bypass valve 220, the powertrain / battery coolant loop 208 and the outer condenser coolant loop 142 may be separated.

[0062] The embodiment of Figures 9 and 10 is based on the H / P system 100 and the electric powertrain / battery cooling system 200. Basically, only the added and modified parts are shown in Figures 9 and 10. The parts not shown in Figures 9 and 10 are elements of the sixth and seventh embodiments.

[0063] The control means and methods described in this application may be fully implemented by a special purpose computer configured with a processor programmed to perform one or more specific functions embodied in a computer program.

Claims

1. 1. A thermal management system for an electric vehicle having a cabin, comprising: a thermal system (100, 200) having sensor means for detecting environmental parameters, driving parameters and conditions of the thermal system and the electric vehicle, and control means (300) configured to generate subordinate control outputs (324) for operating a thermal management system (100, 200) based on control means inputs (318) including user requests and parameters detected by said sensor means, The thermal system (100, 200) includes a cooling or heating component having an electrically driven component and an electrically driven auxiliary component, and a cooling or heating component not having an electrically driven component and an electrically driven auxiliary component, The control means (300) A data-driven supervised learning model unit (302); A control optimization unit (304), and A lower level control unit (306) is provided, The input (318) to the control means (300) is applied to the data-driven supervised learning model unit (302); the data-driven supervised learning model unit (302) is configured to calculate a cost function in an optimization domain of the control optimizer unit (304) and generate a calculated intermediate output (320); the control optimization unit (304) is configured to calculate optimal control settings (322) for the lower level control unit (306); the low-level controller (306) is configured to calculate the low-level control output (324) for operation of the thermal management system; The inputs (318) to the control means are selected from a set of parameters defining target cabin air conditions, ambient conditions, thermal system conditions, and vehicle conditions; The intermediate output (320) calculated by the data-driven supervised learning model unit (302) may be a coefficient of performance (COP) of the thermal system (100, 200) and / or a power consumption parameter (P xx ), A thermal management system, wherein the optimal control set points (322) for the subcontroller (306) include operating parameters and / or temperature conditions of the thermal system.

2. 2. The thermal management system of claim 1, The thermal system comprises an H / P system (100) having a chiller (2), condenser means (102, 138), an evaporator (104) arranged in an HVAC (136), a compressor (106), an external heat exchanger (108) with a fan (110), a blower (114) for air as a cooling fluid for the evaporator (104) and the internal condenser (102), heating valve means (134), and a dehumidification valve means (130), interconnected via a refrigerant loop (112); The intermediate output (320) calculated by the data-driven supervised learning model unit (302) is The coefficient of performance (COP) of the H / P system; It contains two parameters selected from the following list of parameters: Condenser power calculation value (P ICDS (u), P OCDS (u)), Chiller power calculation value (P CHI (u)), and Calculated evaporator power according to capacity (P EVA (u)), The optimal control set point (322) for the subordinate control unit (306) is the rotational speed (N CMP ) and one temperature parameter.

3. 3. The thermal management system of claim 2, The condenser means is disposed in the HVAC flow path (136) and has an inner condenser power (P ICDS ) and / or an outer condenser power (P OCDS ) and comprising an external condenser (138) connected on a coolant side to a heat core (140) for heating interior air arranged in the HVAC flow path (136).

4. 4. The thermal management system according to claim 2 or 3, The inputs to the control means (318) are the following parameters: Ambient temperature (T_amb), Ambient humidity (H_amb), Vehicle speed (V_spd), Indoor air recycling rate (Recycle_ratio), Target fan load factor (Fanreq coolt ), Target inner condenser air outlet temperature (T_air_ICDS_out), Target outer condenser cooling water outlet temperature (T_coolt_OCDS_out), Target evaporator air outlet temperature (T_air_EVA_out), Target fan speed (N Blower )、 Target chiller cooling water outlet temperature (T_coolt_CHI_out), Chiller cooling water inlet temperature (T_coolt_CHI_in), and Chiller cooling water inlet mass / volume flow rate (Vdot_coolt_CHI_in), A thermal management system selected from the group consisting of:

5. the target inner condenser air outlet temperature (T_air_ICDS_out), the ambient temperature (T_amb), and the target blower speed (N Blower ) based on the target inner condenser power (P ICDS,req The thermal management system of claim 4 , further comprising an inner condenser power calculation means (326) configured to calculate an inner condenser power (W) of the inner condenser.

6. the target evaporator air outlet temperature (T_air_EVA_out), the ambient temperature (T_amb), and the target blower speed (N Blower ) based on the target evaporator power (P EVA，req The thermal management system of claim 4 or 5, further comprising an evaporator power calculation means (330) configured to calculate the evaporator power (Vp) of the evaporator.

7. Based on the target outer condenser cooling water outlet temperature (T_coolt_OCDS_out), the ambient temperature (T_amb), and the cooling water flow rate through the outer condenser (138), OCDS，req The thermal management system of claim 4 , further comprising an outer condenser power calculation means configured to calculate an outer condenser power (E 1 ).

8. The target chiller power (P CHI，req The thermal management system of any one of claims 4 to 7, further comprising a chiller power calculation means (328) configured to calculate a chiller power (V) of the chiller.

9. 9. A thermal management system according to any one of claims 2 to 8, comprising: The optimal control set points (322) of the control optimizer (304) are determined based on the following group of operating parameters of the thermal management system: The rotation speed of the compressor (N CMP ), The superheat temperature of the evaporator (T SH,EVA ), The subcooling temperature of the inner condenser (T SC,ICDS ), Subcooling temperature of the outer condenser (T SC,OCDS ), The subcooling temperature of the outer heat exchanger (T SC,OHX ), The superheat temperature of the chiller (T SH,CHI ), Chiller expansion valve opening (EXV CHI ), and Target fan load factor (Fanreq coolt ), A thermal management system selected from the group consisting of:

10. 9. A thermal management system according to any one of claims 2 to 8, comprising: The low level control output (324) of the low level controller (306) controls the following groups of operating parameters of the thermal management system: The state of the heating valve means (2WV heat ), The state of the dehumidification valve means (2WV dehum ), Evaporator expansion valve opening (EXV EVA ), External heat exchanger expansion valve opening (EXV OHX )、 Chiller expansion valve opening (EXV CHI ), Target fan speed (N Blower )、 a target volumetric flow rate of cooling water through the external condenser (138); and Fan load / speed (Fanreq coolt ), A thermal management system selected from:

11. A thermal management system according to any one of claims 1 to 10, The thermal system comprises an electric powertrain / battery cooling water system (200) including an electric powertrain (204), a battery (202), valve means (210, 218), cooling water pump means (212, 216), an electric battery heater (203), a chiller (2), and a radiator (206) with a fan (110), interconnected via a powertrain / battery cooling water loop (208); The input to the control means (318) is Ambient temperature (T_amb), Vehicle speed (V_spd), Battery temperature (T_battery), Electric powertrain temperature (T_ePT), Target chiller power (P CHI,req ), Electric powertrain target power (P ePT,req ), and Target Battery Power (P battery,req ), The intermediate output (320) calculated by the data-driven supervised learning model unit (302) is Calculated power consumption of electric powertrain (P ePT (u)), Calculated battery output power (P battery (u)), and Calculated power consumption of electric drive auxiliary components (P aux (u) The optimal control settings (322) for the subordinate control unit (306) are Optimal valve means control parameters (MCVe ctrl), Optimal electric heater control parameters (PTC ctrl), Optimal auxiliary control parameters (Aux ctrl), and Optimal chiller power (P CHI,opt ).

12. 12. The thermal management system of claim 11, The powertrain / battery cooling water loop (208) is connected to the outer condenser cooling water loop (142); A thermal management system, wherein a cooling water inlet of the heat core (140) is connected to a cooling water outlet of the outer condenser (138).

13. A method of operating a thermal management system according to any one of claims 1 to 12, comprising the steps of: The data-driven supervised learning model (302) is used to calculate a cost function in an optimization domain to generate optimal control settings (322) for the sub-controls (306); a data-driven supervised learning model (302) generating intermediate outputs (320) based on inputs (318) that form inputs to the control optimizer (304), which generates optimal control set points (322) that are used to generate lower-level control outputs (324) as operating parameters of the thermal management system; The input (318) to the control means (300) is selected from a set of parameters defining target interior air conditions, ambient conditions, thermal system conditions, and vehicle conditions; the intermediate outputs (320) calculated by the data-driven supervised learning model (302) include a coefficient of performance (COP) of the thermal system (100, 200) and / or power consumption parameters of electrical components; The method of claim 1, wherein the optimal control set points (322) for the lower level controls (306) include operating parameters and / or temperature conditions of the thermal system.

14. 14. The method of claim 13, the thermal system is a H / P system (100); The intermediate outputs (320) calculated by the data-driven supervised learning model (302) include at least a calculated coefficient of performance (COP(u)) of the H / P system and two parameters selected from the following list of parameters: Calculated value of inner condenser power (P ICDS (u)), Calculated value of the external condenser power (P OCDS (u)), Chiller power calculation value (P CHI (u)), and Calculated evaporator power (P EVA (u)), The optimal control set point (322) for the lower level control is the compressor rotation speed (N CMP ) and one temperature parameter.

15. 15. The method of claim 14, The inputs to the supervised learning model (318) are the following parameters: Ambient temperature (T_amb), Ambient humidity (H_amb), Vehicle speed (V_spd), Indoor air recycling rate (Recycle_ratio), Target fan load factor (Fanreq coolt ), Target inner condenser air outlet temperature (T_air_ICDS_out), Target outer condenser cooling water outlet temperature (T_coolt_OCDS_out), Target evaporator air outlet temperature (T_air_EVA_out), Target fan speed (N Blower )、 Target chiller cooling water outlet temperature (T_coolt_CHI_out), Chiller cooling water inlet temperature (T_coolt_CHI_in), and Chiller cooling water inlet mass / volume flow rate (Vdot_coolt_CHI_in), A method selected from the above.

16. The optimal control set points (322) of the control optimizer (304) are determined based on the following group of operating parameters of the thermal management system: The rotation speed of the compressor (N CMP ), Evaporator superheat temperature (T SH,EVA ), Subcooling temperature of the inner condenser (T SC,ICDS ), Subcooling temperature of the outer heat exchanger (T SC,OHX ), Chiller overheat temperature (T SH,CHI ), Chiller expansion valve opening (EXV CHI ), and Target fan load factor (Fanreq coolt ), 16. The method according to claim 14 or 15, selected from:

17. A method of operating a thermal management system according to any one of claims 14 to 16, comprising the steps of: The lower level control outputs (324) of the lower level controls the following groups of operating parameters of the thermal management system: Heating valve means status (2W heat ), Dehumidification valve means status (2W heat ), Evaporator expansion valve opening (EXV EVA ), External heat exchanger expansion valve opening (EXV OHX )、 Chiller expansion valve opening (EXV CHI ), Target blower load / speed (N Blower ), and Fan load / speed (Fanreq coolt ), A method selected from the above.

18. 18. A method for operating a thermal management system according to any one of claims 14 to 17 in a heating mode, comprising the steps of: The input to the supervised learning model (318) is Target inner condenser air outlet temperature (T_air_ICDS_out), Target fan speed (N Blower )、 Target chiller cooling water outlet temperature (T_coolt_CHI_out), Chiller cooling water inlet temperature (T_coolt_CHI_in), Chiller cooling water inlet mass / volume flow rate (Vdot_coolt_CHI_in), Ambient temperature (T_amb), Ambient humidity (H_amb), Vehicle speed (V_spd), Indoor air recycling rate (Recycle_ratio), and Target fan load factor (Fanreq coolt ), The intermediate output (320) of the supervised learning model is Calculated value of inner condenser power (P ICDS (u)), Calculated chiller power ( PCHI (u)), and a calculated coefficient of performance (COP) for said H / P system; The optimal control setpoints (322) for the lower level controls are The rotation speed of the compressor (N CMP ), Evaporator superheat temperature (T SH,EVA ), and Subcooling temperature of the inner condenser (T SC,ICDS ).

19. 18. A method of operating a thermal management system according to any one of claims 14 to 17 in a dehumidifying mode, comprising the steps of: The input to the supervised learning model (318) is Target inner condenser air outlet temperature (T_air_ICDS_out), Target evaporator air outlet temperature (T_air_EVA_out), Target fan speed (N Blower )、 Ambient temperature (T_amb), Ambient humidity (H_amb), and Includes vehicle speed (V_spd), The intermediate output (320) of the supervised learning model is Calculated value of inner condenser power (P ICDS (u)), Calculated evaporator power (P EVA (u)), and a calculated coefficient of performance (COP) for said H / P system; The optimal control settings (322) for the lower level controls include at least The rotation speed of the compressor (N CMP ), Evaporator superheat temperature (T SH,EVA ), Heating valve means status (2WV dehum ), and Dehumidification valve means status (2W heat ).

20. 18. A method of operating a thermal management system according to any one of claims 14 to 17 in a cooling mode, comprising the steps of: The input to the supervised learning model (318) is Target evaporator air outlet temperature (T_air_EVA_out), Target fan speed (N Blower )、 Target chiller cooling water outlet temperature (T_coolt_CHI_out), Chiller cooling water inlet temperature (T_coolt_CHI_in), Chiller cooling water inlet mass / volume flow rate (Vdot_coolt_CHI_in), Ambient temperature (T_amb), Ambient humidity (H_amb), and Includes vehicle speed (V_spd), The intermediate output (320) of the supervised learning model is Calculated chiller power (P CHI (u)), Calculated evaporator power (P EVA (u)), and a calculated coefficient of performance (COP) for said H / P system; The optimal control setpoints (322) for the lower level controls are The rotation speed of the compressor (N CMP ), The superheat temperature of the outer heat exchanger (T SH,OHX ), and び, Chiller overheat temperature (T SH,CHI ).

21. 21. The method according to any one of claims 14 to 20, comprising: Target inner condenser power (P ICDS,req ) is the target inner condenser air outlet temperature (T_air_ICDS_out), ambient temperature (T_amb), and blower speed (N Blower ) based on the calculation method.

22. 22. The method according to any one of claims 14 to 21, comprising: Target outer condenser power (P OCDS,req ) is calculated based on a target outer condenser cooling water outlet temperature (T_coolt_OCDS_out), an ambient temperature (T_amb), and a cooling water flow rate through the outer condenser (138).

23. 23. The method of any one of claims 14 to 22, comprising: Target evaporator power (P EVA,req ) is the target evaporator air outlet temperature (T_air_EVA_out), the ambient temperature (T_amb), and the blower speed (N Blower ) based on the calculation method.

24. 24. The method according to any one of claims 14 to 23, comprising: Target chiller power (P CHI,req ) is calculated based on the target chiller cooling water outlet temperature (T_coolt_CHI_out), the chiller cooling water inlet temperature (T_coolt_CHI_in), and the chiller cooling water inlet mass / volume flow rate (Vdot_coolt_CHI_in).

25. 21. The method of claim 10, further comprising: performing thermal management in an electric powertrain cooling system mode, the method comprising: The thermal system includes an electric powertrain / battery cooling system (200); The input to the supervised learning model (318) is Ambient temperature (T_amb), Includes vehicle speed (V_spd), Battery temperature (T_battery), Electric powertrain temperature (T_ePT), Target chiller power (P CHI,req ), Electric powertrain target power (P ePT,req ), and Target Battery Power (P battery,req ), The intermediate output (320) computed by the data-driven supervised learning model may be: Calculated power consumption of electric powertrain (P ePT (u)), Calculated battery power consumption (P battery (u)), and Calculated power consumption of electric drive auxiliary components (P aux (u) The optimal control setpoints (322) for the lower level controls are Optimal valve means control parameters (MCVe ctrl), Optimal electric heater control parameters (PTC ctrl), Optimal auxiliary control parameters (Aux ctrl), and Optimal chiller power (P CHI ).

Images