Thermal management system of electric vehicle and operation method of thermal management system

Abstract

A thermal management system of an electric vehicle and a method of operating the same are provided that apply supervised learning to obtain an optimal balance between user comfort and a driving routine. The AI-based control method generates a final control component output that operates the thermal management system with minimum energy consumption and maximum COP in consideration of user conditions for travel speed, cabin temperature, and selected travel route. A continuously efficient electric vehicle thermal management system is provided having a thermal system including a refrigerant circuit and / or a coolant circuit, and a control member. The control component applies a data-driven supervised learning model in combination with a control optimization that provides an optimal control setpoint to standard underlying control.

Description

[0001] Cross-reference to related applications

[0002] This application is based on German patent application No. 102022115096.8 filed on June 15, 2022, and is incorporated herein by reference. Technical Field

[0003] The invention relates to a thermal management system of an electric vehicle and an operating method of the thermal management system. Background Art

[0004] In battery-powered electric vehicles, the requirements for driving range and driver comfort lead to more efficient thermal systems in electric vehicles. This increases the complexity of thermal management systems and their control in electric vehicles. Therefore, it is desirable to apply advanced control techniques to improve the efficiency of thermal management systems in electric vehicles. Thermal systems of the prior art include many actuators that are controlled to achieve target temperatures in the cabin, battery and electric powertrain. Traditionally, in order to achieve the required heating power with minimal energy losses, a large number of tests are performed under many different conditions to calibrate the system, which significantly increases the calibration effort. The calibration values ​​found are stored in a lookup map and the control is configured. Despite all the calibration work, completely optimal control cannot always be guaranteed over the entire operating domain.

[0005] A heat exchanger system for cooling purposes in large industrial applications is known from Patent Document 1. In order to improve the efficiency of the heat exchanger system, a supervised learning model is applied to determine optimal operating parameters for a specific cooling application.

[0006] Citation list

[0007] Patent Literature

[0008] Patent document 1: WO2011 / 119398A1. Summary of the invention

[0009] Therefore, an object of the present invention is to provide a thermal management system for an electric vehicle that applies supervised learning to achieve an optimal balance between user comfort and driving range, and a method of operating the thermal management system.

[0010] This object is achieved by a thermal management system for an electric vehicle according to the invention.

[0011] The AI-based control method according to the present invention considers the user's request for driving speed, cabin temperature and conditions of the selected driving route, and generates the final control component output for operating the thermal management system with minimum energy consumption and maximum COP. A continuously efficient thermal management system for electric vehicles is provided, which has a thermal system including a refrigerant circuit and / or a coolant circuit, and a control component. The refrigerant system is also called an air conditioning system or a heat pump system (H / P system). The heat pump is a key thermal system for adjusting, heating or cooling the cabin of the vehicle to a comfortable temperature range and / or adjusting, heating or cooling the high-voltage battery to optimal working conditions. The coolant system is required to adjust the electric powertrain and battery to the optimal and most stable temperature range. The control component combines the data-driven supervised learning model with the control optimization that provides the optimal control set point to the standard lower-level control. The AI-based control component ensures that the refrigerant or coolant system automatically achieves the optimal efficiency under all conditions, thereby increasing the mileage of the electric vehicle. The AI-based control component significantly reduces the calibration work because it allows offline automatic training of the AI ​​model, such as using a neural network. The digital twin of the thermal facility uses a supervised learning method for training. The data used in training can come from an accurate simulation environment that allows efficient data generation through rapid and continuous operation of the simulation facility. Data can also be retrieved directly from the target vehicle. When training a supervised learning model, it can be used as a function to predict the optimal control problem. Both the trained model and the optimization method can be run in real time, thus ensuring optimality continuously.

[0012] The invention has the following advantages:

[0013] Ensure optimal system performance, such as efficiency;

[0014] Reduced calibration effort as it replaces current mapping-based calibration;

[0015] Modularity enables easy updating by retraining the model with an updated dataset.

[0016] For data-driven supervised learning models, artificial neural networks are preferably used. For optimization in control optimization, swarm optimization or gradient descent methods are preferably used.

[0017] The present invention may relate to a thermal management system having a thermal system with an H / P system that conditions, heats or cools a vehicle's cabin to a comfortable temperature range taking into account the battery's state of charge, ambient conditions, H / P system conditions, and vehicle status.

[0018] The condenser component has an internal condenser arranged inside the HVAC channel and / or an external condenser arranged outside the HVAC channel, the internal condenser has internal condenser power, the external condenser has external condenser power, and the external condenser is connected to the heating core arranged in the HVAC channel on the coolant side.

[0019] The present invention may utilize an optimization algorithm to define the most appropriate input parameters for a control component with a data-driven supervised learning model.

[0020] The present invention may define a preferred target power calculation component to be used as input to a data-driven supervised learning model.

[0021] The present invention can define the most appropriate optimal control set point output by the optimization algorithm / unit and input it to the lower layer.

[0022] The present invention can define the most appropriate underlying control outputs to be used to operate and control a thermal management system.

[0023] The present invention may be directed to a thermal management system having a thermal system with an electric powertrain cooling system that regulates and operates the electric powertrain and battery within an optimal and most stable temperature range.

[0024] According to the invention, an external condenser coolant circuit may be connected to the powertrain / battery coolant circuit.

[0025] The present invention can define the most appropriate inputs, intermediate outputs and optimal control set points for the underlying control units / algorithms when the H / P system operates in a heating mode for heating the cabin air.

[0026] The present invention can define the most appropriate inputs, intermediate outputs and optimal control set points for the underlying control units / algorithms when the H / P system operates in a dehumidification mode that reheats and dehumidifies previously cooled cabin air.

[0027] The present invention can define the most appropriate inputs, intermediate outputs and optimal control set points for the underlying control units / algorithms when the H / P system operates in a cooling mode for cooling the cabin air. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present invention. Corresponding reference numerals indicate corresponding parts throughout the several views of the drawings.

[0029] Figure 1 An H / P system for heating and cooling cabin air is shown as part of a thermal system managed and controlled by a thermal management system.

[0030] Figure 2 An electric powertrain / battery coolant system for maintaining an electric powertrain and battery within a desired temperature range is shown.

[0031] Figure 3 Show control as Figure 1 and Figure 2 Control components of the thermal system shown.

[0032] Figure 4 A first embodiment of the present invention is described which is applied when heating of a vehicle interior is required.

[0033] Figure 5 A second embodiment of the present invention is described which is applied when dehumidification of a vehicle interior is required.

[0034] Figure 6 A third embodiment of the present invention is described which is applied when cooling of the vehicle interior is required.

[0035] Figure 7 A fourth embodiment of the present invention is described as a generalized H / P system control.

[0036] Figure 8 A fifth embodiment of the invention is shown which is applied to maintain an electric powertrain / battery coolant system within a suitable temperature range under conditions imposed by the driver, ambient conditions, and vehicle component specifications.

[0037] Fig. 9 A sixth embodiment is shown with an improved H / P system.

[0038] Fig.10 A seventh embodiment is shown having additional interconnections between the H / P system and the electric powertrain / battery coolant system. DETAILED DESCRIPTION

[0039] The embodiments are described more fully with reference to the accompanying drawings.The following description is merely exemplary in nature and is not intended to limit the present invention, application, or uses.

[0040] Figure 1 1 shows a heat pump or H / P system 100 for heating and cooling vehicle interior air. Figure 2 shows an electric powertrain / battery coolant system 200 for maintaining an electric powertrain and battery within a desired temperature range, and Figure 3 A control means 300 for controlling the thermal management system is shown.

[0041] The H / P system 100 includes a cooler 2, an internal condenser 102 (an example of a condenser component), an evaporator 104, a compressor 106, and an external heat exchanger 108 with a fan 110, which are interconnected via a refrigerant circuit 112, and an air blower 114 for allowing air to flow as a cooling fluid to the evaporator 104 and the internal condenser 102. In addition, a liquid accumulator 116 is configured to store liquid refrigerant and separate liquid and gaseous refrigerants. The outlet of the compressor 106 is connected to the inlet of the internal condenser 102. The outlet of the internal condenser 102 is connected to an external heat exchanger expansion valve 118, which in turn is connected to the inlet of the external heat exchanger 108. The opening ratio of the external heat exchanger expansion valve 118 is marked as EXV OHX (corresponding to the external heat exchanger expansion valve opening ratio). The outlet of the external heat exchanger 108 is connected to a point between the evaporator expansion valve 122 and the cooler expansion valve 124 via the first non-return valve 120. The opening ratio of the evaporator expansion valve 122 is denoted as EXV EVA (corresponding to the evaporator expansion valve opening ratio). The opening ratio of the cooler expansion valve 124 is denoted as EXV CHI (Corresponding to the cooler expansion valve opening ratio). The cooler expansion valve 124 is in turn connected to the refrigerant inlet of the cooler 2. The evaporator expansion valve 122 is in turn 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 cooler 2 is also connected to the inlet of the accumulator 116. The outlet of the external heat exchanger 108 is also connected to the inlet of the accumulator 116 via the dehumidification control valve 130 (an example of a dehumidification valve component) and the second non-return valve 132. The point between the external heat exchanger expansion valve 118 and the outlet of the internal condenser 102 is connected to the point between the first non-return valve 120 and the cooler expansion valve 124 or the evaporator expansion valve 122 via the heating control valve 134 (an example of a heating valve component). The interior condenser 102 and the evaporator 104 are disposed in a heating-cooling-air-conditioning or HVAC duct 136 into the vehicle cabin.

[0042] Figure 2The electric powertrain / battery coolant system 200 shown has the coolant side of the cooler 2, the battery 202, the battery heater 203 (e.g., an electric battery heater), the electric powertrain 204, and the radiator 206 interconnected via a powertrain / battery coolant loop 208. The powertrain / battery coolant loop 208 connects the coolant outlet of the cooler 2 to the coolant inlet of the battery heater 203. The coolant outlet of the battery heater 203 is connected to the coolant inlet of the battery 202. The coolant outlet of the battery 202 is connected to the coolant inlet of the cooler 2 via a two-way valve 210 (an example of a valve member) and a first pump 212 (an example of a coolant pump member). The coolant outlet of the cooler 2 is also connected to the coolant inlet of the electric powertrain 204 and a second pump 216 (an example of a coolant pump member). The coolant outlet of the electric powertrain 204 is connected to the first pump 212 and the coolant inlet of the radiator 206 via a three-way valve 218 (an example of a valve member). Figure 1 and Figure 2 As shown, the external heat exchanger 108 , the radiator 206 with the fan 110 , and the active grille shutters 4 are configured in a stacked manner.

[0043] The control component 300 is provided with a data-driven supervised learning model unit 302, a control optimization unit 304, and a lower-level control unit 306. A control component input 318 is 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 (e.g., a control optimization algorithm) calculates an optimal control set point 322 for the lower-level control unit 306. The lower-level control unit 306 performs the lower-level control to calculate a final control component output 324 (e.g., a lower-level control output) for operating the thermal management system. The final control component output 324 corresponds to the lower-level control output.

[0044] The input 318 to the control member 300 and the data-driven supervised learning model unit 302 is selected from a set of parameters defining the target air condition in the vehicle cabin, the environmental conditions, the thermal system conditions and the vehicle state. The calculated intermediate output of the data-driven supervised learning model unit 302 has the coefficient of performance COP of the thermal system and / or the power consumption parameter Pxx of the electrically driven components such as pumps, valve actuators, fans, blowers, compressors, etc. The optimal control set point for the lower control unit 306 has operating parameters such as compressor speed, blower speed regulating valve actuation state and / or temperature conditions such as vehicle cabin air temperature, battery temperature, coolant and refrigerant temperature, etc.

[0045] For the data-driven supervised learning model unit 302, an artificial neural network is preferably applied. For the optimization in the control optimization unit 304, a swarm optimization or a gradient descent method is preferably applied.

[0046] Figure 4 A first embodiment of the invention is shown when heating of the vehicle cabin is required. For this purpose, the following input 318 to the control member 300 proves to be suitable:

[0047] Target T_air_ICDS_out = target air temperature at the air outlet of the internal condenser (corresponds to the target internal condenser air outlet temperature);

[0048] N Blower = air blower speed (corresponding to target blower speed, blower load / airflow);

[0049] T_amb = ambient temperature;

[0050] Target T_coolt_CHI_out = target coolant temperature at the coolant outlet of the chiller (corresponding to the target coolant outlet temperature of the chiller);

[0051] T_coolt_CHI_in = coolant temperature at the cooler inlet (corresponds to the coolant inlet temperature of the cooler);

[0052] Vdot_coolt_CHI_in = coolant flow into the cooler (corresponding to the coolant inlet mass / volume flow);

[0053] H_amb = ambient humidity;

[0054] V_spd = vehicle speed;

[0055] Recycle_ratio = the air change rate in the vehicle cabin (corresponding to the vehicle cabin air circulation rate); and

[0056] Fanreq coolt = The fan speed typically required for HVAC control (corresponding to target fan duty cycle, fan duty cycle / speed).

[0057] The above input Target T_air_ICDS_out, N Blower and T_amb are supplied to the internal condenser power calculation component 326, which calculates the target internal condenser power P ICDS,reqAs input to the data driven supervised learning model unit 302. The inputs Target T_coolt_CHI_out, T_coolt_CHI_in and Vdot_coolt_CHI_in are supplied to the cooler power calculation component 328, which calculates the target cooler power P CHI,req As input to the data driven supervised learning model unit 302. The internal condenser power calculation component 326 and the chiller power calculation component 328 can be considered as part of the data driven supervised learning model unit 302. Input T_amb, H_amb, V_spd, Recycle_ratio and Fanreq coolt is directly input into the data-driven supervised learning model unit 302. The data-driven supervised learning model unit 302 outputs the calculated internal condenser power P ICDS (u), calculated cooler power P CHI (u) and the calculated COP (u) of the H / P system 100 are used as the intermediate output 320. For the control optimization unit 304, a cost function is defined as shown in Mathematical Formulas 1 to 3.

[0058] [Mathematical formula 1]

[0059]

[0060] [Mathematical formula 2]

[0061] u=[N CMP T SC,ICDS T SH,CHI ] T

[0062] [Mathematical formula 3]

[0063] v = [T_amb V_spd H_amb] T

[0064] Among them, w1, w2 and w3 are the coefficient of performance COP, cooler power P CHI And the internal condenser power P ICDS The weight of the influence of COP is the effective heating Q H or Cooling Q C The ratio between the work / energy Win put into the system. For heating, COP = Q H / W in .

[0065] The appropriate optimal control set point 322 output by the control optimization unit 304 is as follows:

[0066] Optimum compressor speed N CMP,opt(corresponding to the rotation speed of the compressor 106);

[0067] Optimum internal condenser subcooling temperature T SC,ICDS,opt (corresponding to the subcooling temperature of the internal condenser 102); and

[0068] Optimum cooler superheat temperature T SH,CHI,opt (corresponding to the superheat temperature of cooler 2).

[0069] in addition,

[0070] The optimal opening ratio EXV of the internal condenser expansion valve 118 and the cooler expansion valve 124 xx,opt ;as well as

[0071] Optimal air fan speed N fan,opt

[0072] can be selected as the optimal control set point 322.

[0073] These optimal control set points 322 are input to the common lower level control unit 306 which generates a final control component output 324 .

[0074] Figure 5 A second embodiment of the invention is shown when dehumidification of the vehicle cabin is required. For this purpose, the following input 318 to the control member 300 proves to be suitable:

[0075] Target T_air_ICDS_out = target air temperature at the air outlet of the internal condenser;

[0076] N Blower = air blower speed;

[0077] T_amb = ambient temperature;

[0078] Target T_air_EVA_out = target air temperature at the evaporator air outlet (corresponds to target evaporator air outlet temperature);

[0079] H_amb = ambient humidity;

[0080] V_spd = vehicle speed;

[0081] Recycle_ratio = the rate at which air changes within the vehicle cabin; and

[0082] Fanreq coolt = The fan speed normally required for HVAC control.

[0083] The above input Target T_air_ICDS_out, N Blowerand T_amb are supplied to the internal condenser power calculation component 326, which calculates the target internal condenser power P ICDS,req As the input to the data-driven supervised learning model unit 302. Input Target T_air_EVA_out, N Blower and T_amb is supplied to the evaporator power calculation component 330, which calculates the target evaporator power P EVA,req As input to the data driven supervised learning model unit 302. The internal condenser power calculation component 326 and the evaporator power calculation component 330 can be considered as part of the data driven supervised learning model unit 302. Input T_amb, H_amb, V_spd, Recycle_ratio and Fanreq coolt is directly input into the data-driven supervised learning model unit 302. The data-driven supervised learning model unit 302 outputs the calculated internal condenser power P ICDS (u), calculated evaporator power P EVA (u) and the calculated COP (u) of the H / P system 100 are used as the intermediate output 320. For the control optimization unit 304, a cost function is defined as shown in Mathematical Formulas 4 to 6.

[0084] [Formula 4]

[0085]

[0086] [Formula 5]

[0087] u=[N CMP T SH,EVA 2W Heat 2W Dehum T SH,ICDS EXV EVA EXV HEAT ] T

[0088] [Mathematical formula 6]

[0089] v = [T_amb V_spd H_amb] T

[0090] Among them, w1, w2 and w3 are the coefficient of performance COP, cooler power P CHI And the internal condenser power P ICDS The weight of the impact.

[0091] The appropriate optimal control set point 322 output by the control optimization unit 304 is as follows:

[0092] Optimum compressor speed N CMP,opt ;

[0093] Optimum evaporator superheat temperature T SH,EVA,opt (corresponding to the superheat temperature of the evaporator 104);

[0094] The state (i.e. condition) of the dehumidification control valve 134 is 2WV Dehum,opt ;as well as

[0095] The state (ie, condition) of the heating control valve 130 is 2WV Heat,opt .

[0096] in addition,

[0097] Optimum internal condenser subcooling temperature T SC,ICDS,opt ;

[0098] The optimal opening ratio EXV of the internal condenser expansion valve 118 and the evaporator expansion valve 122 xx,opt ;as well as

[0099] Optimal air fan speed N fan,opt

[0100] can be selected as the optimal control set point 322.

[0101] These optimal control set points 322 are input to the common lower level control unit 306 which generates a final control component output 324 .

[0102] Figure 6 A third embodiment of the invention is shown when cooling of the vehicle cabin is required. For this purpose, the following input 318 to the control member 300 proves to be suitable:

[0103] Target T_air_EVA_out = target air temperature at evaporator air outlet;

[0104] N Blower = air blower speed;

[0105] T_amb = ambient temperature;

[0106] Target T_coolt_CHI_out = target coolant temperature at the coolant outlet of the chiller;

[0107] T_coolt_CHI_in = coolant temperature at the cooler inlet;

[0108] Vdot_coolt_CHI_in = coolant flow into the cooler;

[0109] H_amb = ambient humidity;

[0110] V_spd = vehicle speed;

[0111] Recycle_ratio = the rate at which air changes within the vehicle cabin; and

[0112] Fanreq coolt = The fan speed normally required for HVAC control.

[0113] The above input Target T_air_EVA_out, N Blower and T_amb is supplied to the evaporator power calculation component 330, which calculates the target evaporator power P EVA,req As input to the data driven supervised learning model unit 302. The inputs Target Tcoolt_CHI_out, T_coolt_CHI_in and Vdot_coolt_CHI_in are supplied to the cooler power calculation component 328, which calculates the target cooler power P CHI,req As input to the data-driven supervised learning model unit 302. Input T_amb, H_amb, V_spd, Recycle_ratio and Fanreq coolt The data driven supervised learning model unit 302 outputs the calculated evaporator power P EVA (u), calculated cooler power P CHI (u) and the calculated COP (u) of the H / P system 100 are used as the intermediate output 320. For the control optimization unit 304, the cost function is defined as shown in Mathematical Formulas 7 to 9.

[0114] [Formula 7]

[0115]

[0116] [Mathematical formula 8]

[0117] u=[N CMP T SC,OHX T SH,CHI ] T

[0118] [Mathematical formula 9]

[0119] v = [T_amb V_spd H_amb] T

[0120] The appropriate optimal control set point 322 output by the control optimization unit 304 is as follows:

[0121] Optimum compressor speed NCMP,opt ;

[0122] Optimum external heat exchanger subcooling temperature T SC,OHX,opt (corresponding to the subcooling temperature of the external heat exchanger 108); and

[0123] Optimum cooler superheat temperature T SH,CHI,opt .

[0124] in addition,

[0125] The optimal opening ratio EXV of the external heat exchanger expansion valve 118 and the cooler expansion valve 124 xx,opt ;as well as

[0126] Optimal air fan speed N fan,opt

[0127] can be selected as the optimal control set point 322.

[0128] These optimal control set points 322 are input to the common lower level control unit 306 which generates a final control component output 324 .

[0129] Figure 7 is the generated H / P system control and is essentially a combination of the first, second and third embodiments. For this purpose, the following input 318 to the control member 300 proves to be suitable:

[0130] Target T_air_ICDS_out = target air temperature at the air outlet of the internal condenser;

[0131] N Blower = air blower speed (corresponding to blower load / airflow);

[0132] T_amb = ambient temperature;

[0133] Target T_air_EVA_out = target air temperature at evaporator air outlet;

[0134] Target T_coolt_CHI_out = target coolant temperature at the coolant outlet of the chiller;

[0135] T_coolt_CHI_in = coolant temperature at the cooler inlet;

[0136] Vdot_coolt_CHI_in = coolant flow into the cooler;

[0137] H_amb = ambient humidity;

[0138] V_spd = vehicle speed;

[0139] Recycle_ratio = the rate at which air changes within the vehicle cabin; and

[0140] Fanreq coolt = The fan speed normally required for HVAC control.

[0141] use Figure 7 The internal condenser power calculation component 326, the cooler power calculation component 328, and the evaporator power calculation component 330, which are not shown in the figure, calculate the target internal condenser power P ICDS,req , Target cooler power P CHI,req And the target evaporator power P EVA,req And they are input into the data driven supervised learning model unit 302. Input T_amb, H_amb and V_spd are directly input into the data driven supervised learning model unit 302. In addition, Recycle_ratio and Fanreq can also be selected coolt It is input to the data-driven supervised learning model unit 302 as control component input 318 .

[0142] The data-driven supervised learning model unit 302 outputs the calculated internal condenser power P ICDS (u), calculated evaporator power P EVA (u), calculated cooler power P CHI (u) and the calculated COP (u) of the H / P system 100 are used as the intermediate output 320. For the control optimization unit 304, a cost function is defined as shown in Mathematical Formulas 10 to 12.

[0143] [Formula 10]

[0144]

[0145] [Mathematical formula 11]

[0146] u=[N CMP T SH,EVA 2W Dehum 2W Heat T SC,ICDS T SH,CHI Fan] T

[0147] [Mathematical formula 12]

[0148] v = [T_amb V_spd H_amb] T

[0149] The appropriate optimal control set point 322 output by the control optimization unit 304 is as follows:

[0150] Optimum compressor speed N CMP,opt ;

[0151] Optimum evaporator superheat temperature T SH,EVA,opt ;

[0152] Optimum internal condenser subcooling temperature T SC,ICDS,opt ;

[0153] Optimum cooler superheat temperature T SH,CHI,opt ;

[0154] Optimal air fan speed N fan,opt ;

[0155] State 2WV of the dehumidification control valve 134 dehum,opt ;as well as

[0156] State 2WV of the heating control valve 130 heat,opt .

[0157] in addition,

[0158] The optimal opening ratio EXV of the external heat exchanger expansion valve 118, the cooler expansion valve 124 and the evaporator expansion valve 122 xx,opt ;as well as

[0159] Optimum air blower speed N Blower,opt

[0160] can be selected as the optimal control set point 322.

[0161] These optimal control set points 322 are input to the common lower level control unit 306 which generates a final control component output 324 .

[0162] Figure 8 A fifth embodiment of the invention is shown, which is applied to maintain the electric powertrain / battery coolant system within a suitable temperature range under conditions imposed by the driver, environmental conditions, vehicle component specifications. For this purpose, the following input 318 to the control member 300 proves to be suitable:

[0163] Ambient temperature Tamb;

[0164] Vehicle speed V_spd;

[0165] Battery temperature T_battery;

[0166] Electric powertrain temperature T_ePT;

[0167] Target cooler power P CHI,req (i.e. required cooler power);

[0168] Target power of electric powertrain P ePT,req (i.e. the power required from the electric powertrain); and

[0169] Target battery power P battery,req (i.e. the battery power required).

[0170] The data-driven supervised learning model unit 302 outputs the calculated power consumption P of the electric powertrain 204 ePT (u), the calculated power output P of the battery 202 battery (u) (i.e. the calculated power distribution) and the calculated power consumption P of the electric drive auxiliary components aux (u). Among them, P aux It is the power consumption of all electrically driven components such as fans, blowers, water pumps, valve actuators, etc. For the control optimization unit 304, the cost function is defined as shown in Mathematical Formulas 13 to 15.

[0171] [Mathematical formula 13]

[0172]

[0173] [Formula 14]

[0174]

[0175] [Mathematical formula 15]

[0176] v=[T_amb V_spd T_ePT T_battery] T

[0177] The appropriate optimal control set point 322 output by the control optimization unit 304 is as follows:

[0178] Optimal valve control set point MCVe ctrl (corresponding to optimal valve member control parameters);

[0179] Optimal battery heater control PTC ctrl (corresponding to the optimal electric heater control parameters);

[0180] Optimal first water pump 212 load eWP1 duty;

[0181] The optimal second water pump 216 load eWP2 duty; and

[0182] Optimal fan control Fan ctrl.

[0183] in addition,

[0184] Optimal electric powertrain oil load ePT oil pump;

[0185] Optimal active grille shutter control AGS grill shutter;

[0186] Optimal auxiliary component control parameter Aux ctrl; and

[0187] Optimum cooler power P CHI,opt

[0188] can be selected as the optimal control set point 322.

[0189] exist Figure 2 The electric powertrain / battery coolant system shown employs a two-way valve 210 and a three-way valve 218. A multiple control valve configuration may be employed in place of the single valve described above.

[0190] In any embodiment, the optimization control unit 304 takes into account the user's requirements for speed, cabin temperature, and conditions of the selected driving route to calculate the optimal control set points for the thermal management system to operate with minimum energy consumption and maximum COP.

[0191] Fig. 9 The sixth embodiment with an improved H / P system is shown, in which an external condenser 138 (an example of a condenser member) arranged outside the HVAC passage 136 and a heater core 140 arranged inside the HVAC passage 136 are applied instead of the internal condenser 102. The external condenser 138 and the heater core 140 are connected to each other via an external condenser coolant circuit 142 and a coolant pump 144. The heater core 140 in the HVAC passage 136 is a liquid / air heat exchanger that heats the cabin air using the heat from the external condenser 138.

[0192] When the external condenser 138 is used, the control parameters corresponding to the control parameters of the internal condenser 102 are as follows:

[0193] P OCDS,req = target external condenser power;

[0194] P OCDS (u) = calculated external condenser power output;

[0195] T_coolt_OCDS_out = target external condenser coolant outlet temperature;

[0196] T SC,OCDS = external condenser subcooling temperature (corresponding to the subcooling temperature of the external condenser 138);

[0197] The coolant volumetric flow rate in the external condenser coolant circuit 142 (ie, the target volumetric flow rate of coolant through the external condenser 138 ); and the coolant pump duty cycle.

[0198] These parameters must be input to the control component 300 and optimized. The inputs Target T_air_OCDS_out, T_amb and the coolant flow through the external condenser 138 are fed to the external condenser power calculation component which calculates the target external condenser power P OCDS,req As input to the data-driven supervised learning model unit 302.

[0199] Fig.10 A seventh embodiment is shown in which the heater core 140 is not substituted for the internal condenser 102 but is provided as an addition. In addition, the external condenser coolant circuit 142 is connected to the powertrain / battery coolant circuit 208. The heater core 140 heats the cabin air using heat from the external condenser and from the electric powertrain 204 and / or the battery 202. However, using a bypass path having a bypass valve 220, the powertrain / battery coolant circuit 208 and the external condenser coolant circuit 142 can be separated.

[0200] Fig. 9 and Fig.10 The embodiment of is based on the H / P system 100 and the electric powertrain / battery coolant system 200. Fig. 9 and Fig.10 In the drawings, basically only the additional and changed parts are shown. Fig. 9 and Fig.10 The parts not shown in FIG. 1 are elements of the sixth and seventh embodiments.

[0201] The control means and methods described in this application may be fully implemented by a special purpose computer created by configuring a processor that is programmed to perform one or more specific functions embodied in a computer program.

Claims

1. A thermal management system for an electric vehicle having a vehicle compartment, characterized in that: have: A thermal system (100, 200) and a control member (300), the thermal system having a sensor member for detecting environmental parameters, operating parameters and conditions of the thermal system and the electric vehicle, the control member being configured to generate a lower level control output (324) for operating the thermal management system (100, 200) based on a control member input (318), the control member input including a user request and parameters detected by the sensor member, The thermal system (100, 200) comprises cooling and heating components and electrically driven auxiliary components, the cooling and heating components having or not having electrically driven components, The control component (300) comprises: Data-driven supervised learning model unit (302); a control optimization unit (304); and The lower control unit (306), wherein the input (318) of the control component (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 for the control optimization unit (304) and generate a calculated intermediate output (320), The control optimization unit (304) is configured to calculate an optimal control set point (322) for the lower control unit (306), The lower-level control unit (306) is configured to calculate the lower-level control output (324) for operating the thermal management system, wherein the input (318) to the control means is selected from a set of parameters defining target air conditions in the vehicle cabin, environmental conditions, thermal system conditions and vehicle status, The calculated intermediate output (320) of the data-driven supervised learning model unit (302) includes a coefficient of performance (COP) of the thermal system (100, 200) and / or a power consumption parameter (P xx ), And, wherein the optimal control set point (322) for the lower control unit (306) has operating parameters and / or temperature conditions of the thermal system.

2. The thermal management system according to claim 1, characterized in that: in, The thermal system has an H / P system (100), which has: a cooler (2); a condenser component (102, 138); an evaporator (104) configured in an HVAC (136); a compressor (106); an external heat exchanger (108) having a fan (110); an air blower (114); a heating valve component (134); and a dehumidification valve component (130), wherein the cooler, the condenser component, the evaporator, the compressor and the external heat exchanger are interconnected via a refrigerant circuit (112), and the air blower is used to make air flow as a cooling fluid to the evaporator (104) and the internal condenser (102), The calculated intermediate output (320) of the data-driven supervised learning model unit (302) comprises a coefficient of performance (COP) of the H / P system and two parameters selected from the following group of parameters: Calculated condenser power (P ICDS (u), P OCDS (u)); Calculated cooler power (P CHI (u)); and Calculated evaporator performance power (P EVA (u)), And, wherein the optimal control set point (322) for the lower control unit (306) has a rotation speed (N CMP ) and a temperature parameter.

3. The thermal management system according to claim 2, characterized in that: in, The condenser component has an internal condenser (102) disposed inside the HVAC passage (136) and / or an external condenser (138) disposed outside the HVAC passage (136), wherein the internal condenser has an internal condenser power (P ICDS ), the external condenser (138) has an external condenser power (P OCDS ), and the external condenser is connected to a heater core (140) arranged in the HVAC passage (136) on the coolant side, and the heater core is used to heat the vehicle cabin air.

4. The thermal management system according to claim 2 or 3, It is characterized in that in, The input to the control means (318) is selected from the following set of parameters: Ambient temperature (T_amb); Ambient humidity (H_amb); Vehicle speed (V_spd); Cabin air circulation rate (Recycle_ratio); Target fan duty cycle (Fanreq coolt ); Target internal condenser air outlet temperature (T_air_ICDS_out); Target external condenser coolant outlet temperature (T_coolt_OCDS_out); Target evaporator air outlet temperature (T_air_EVA_out); Target blower speed (N Blower ); Target cooler coolant outlet temperature (T_coolt_CHI_out); Chiller coolant inlet temperature (T_coolt_CHI_in); and Chiller coolant inlet mass / volume flow rate (Vdot_coolt_CHI_in).

5. The thermal management system according to claim 4, characterized in that: The internal condenser power calculation component (326) is also provided, and the internal condenser power calculation component is configured to calculate the internal condenser power based on the target internal condenser air outlet temperature (T_air_ICDS_out), the ambient temperature (T_amb), and the target blower speed (N Blower ) to calculate the target internal condenser power (P ICDS,req ).

6. The thermal management system according to claim 4 or 5, characterized in that: The evaporator power calculation component (330) is further provided. The evaporator power calculation component is configured to calculate the target evaporator air outlet temperature (T_air_EVA_out), the ambient temperature (T_amb) and the target blower speed (N Blower ) to calculate the target evaporator power (P EVA,req ).

7. The thermal management system according to any one of claims 4 to 6, characterized in that: The invention also includes an external condenser power calculation component, which is configured to calculate a target external condenser power (P) based on the target external condenser coolant outlet temperature (T_coolt_OCDS_out), the ambient temperature (T_amb) and the coolant flow rate through the external condenser (138). OCDS,req ).

8. The thermal management system according to any one of claims 4 to 7, characterized in that: The device further comprises a cooler power calculation unit (328) configured to calculate a target cooler power (P) based on the target cooler coolant outlet temperature (T_coolt_CHI_out), the cooler coolant inlet temperature (T_coolt_CHI_in) and the cooler coolant mass / volume flow rate (Vdot_coolt_CHI_in). CHI,req ).

9. The thermal management system according to any one of claims 2 to 8, characterized in that: in, The optimal control set point (322) of the control optimization unit (304) is selected from the following set of operating parameters of the thermal management system: The speed of the compressor (N CMP ); The superheat temperature (T SH,EVA ); The subcooling temperature (T SC,ICDS ); The subcooling temperature (T SC,OCDS ); The subcooling temperature (T SC,OHX ); Cooler superheat temperature (T SH,CHI ); Cooler expansion valve opening ratio (EXV CHI );as well as Target fan duty cycle (Fanreq coolt ).

10. The thermal management system according to any one of claims 2 to 8, It is characterized in that The lower-level control output (324) of the lower-level control unit (306) is selected from the following set of operating parameters of the thermal management system: The conditions for heating the valve member (2WV heat ); The condition of the dehumidification valve component (2WV dehum ); Evaporator expansion valve opening ratio (EXV EVA ); External heat exchanger expansion valve opening ratio (EXV OHX ); Cooler expansion valve opening ratio (EXV CHI ); Target blower speed (N Blower ); a target volumetric flow rate of cooling liquid through the external condenser (138); and Fan duty cycle / speed (Fanreq coolt ).

11. The thermal management system according to any one of claims 1 to 10, It is characterized in that in, The thermal system comprises an electric powertrain / battery coolant system (200), the electric powertrain / battery coolant system comprising an electric powertrain (204), a battery (202), a valve component (210, 218), a coolant pump component (212, 216), an electric battery heater (203), a cooler (2), and a radiator (206) having a fan (110) which are interconnected via a powertrain / battery coolant circuit (208). Wherein, the input to the control component (318) includes: Ambient temperature (T_amb); Vehicle speed (V_spd); Battery temperature (T_battery); Electric powertrain temperature (T_ePT); Target cooler power (P CHI,req ); The target power of the electric powertrain (P ePT,req );as well as Target battery power (P battery,req ), Wherein, the calculated intermediate output (320) of the data-driven supervised learning model unit (302) includes: The calculated power consumption of the electric powertrain (P ePT (u)); The calculated power distribution of the battery (P battery (u)); and The power consumption (P aux (u)), And, wherein the optimal control set point (322) for the lower control unit (306) comprises: Optimal valve component control parameters (MCVe ctrl); Optimal electric heater control parameters (PTC ctrl); Optimal auxiliary component control parameters (Aux ctrl); and Optimum cooler power (P CHI,opt ).

12. The thermal management system according to claim 11, characterized in that: in, The powertrain / battery coolant circuit (208) is connected to the external condenser coolant circuit (142), and The coolant inlet of the heating core (140) is connected to the coolant outlet of the external condenser (138).

13. A method for operating a thermal management system, the thermal management system being the thermal management system according to any one of claims 1 to 12, characterized in that: in, A data-driven supervised learning model (302) is used to calculate a cost function in the optimization domain to provide an optimal control set point (322) for the lower-level control (306), wherein, based on the input (318), the data-driven supervised learning model (302) generates an intermediate output (320), which forms an input to the control optimization unit (304), and the control optimization unit (304) generates the optimal control set point (322), and the optimal control set point (322) is used to generate a lower-level control output (324) as an operating parameter of the thermal management system, wherein the input (318) to the control means (300) is selected from a set of parameters defining target air conditions in the vehicle cabin, environmental conditions, thermal system conditions and vehicle status, wherein the calculated intermediate output (320) of the data-driven supervised learning model (302) comprises a coefficient of performance (COP) of the thermal system (100, 200) and / or a power consumption parameter of the electrical component, And, wherein the optimal control set point (322) for the lower level control (306) has operating parameters and / or temperature conditions of the thermal system.

14. The method for operating a thermal management system according to claim 13, characterized in that: in, The thermal system is a H / P system (100), wherein the calculated intermediate output (320) of the data-driven supervised learning model (302) comprises at least the calculated coefficient of performance (COP(u)) of the H / P system and two parameters selected from the following group of parameters: Calculated internal condenser power (P ICDS (u)); Calculated external condenser power (P OCDS (u)); Calculated cooler power (P CHI (u)); and Calculated evaporator power (P EVA (u)), And, wherein the optimal control set point (322) for the lower level control has a compressor (N CMP ) speed and a temperature parameter.

15. The method for operating a thermal management system according to claim 14, It is characterized in that in, The input (318) to the supervised learning model is selected from the following set of parameters: Ambient temperature (T_amb); Ambient humidity (H_amb); Vehicle speed (V_spd); Cabin air circulation rate (Recycle_ratio); Target fan duty cycle (Fanreq coolt ); Target internal condenser air outlet temperature (T_air_ICDS_out); Target external condenser coolant outlet temperature (T_coolt_OCDS_out); Target evaporator air outlet temperature (T_air_EVA_out); Target blower speed (N Blower ); Target cooler coolant outlet temperature (T_coolt_CHI_out); Chiller coolant inlet temperature (T_coolt_CHI_in); and Chiller coolant inlet mass / volume flow rate (Vdot_coolt_CHI_in).

16. The method for operating a thermal management system according to claim 14 or 15, characterized in that: in, The optimal control set point (322) of the control optimization unit (304) is selected from the following set of operating parameters of the thermal management system: The speed of the compressor (N CMP ); Evaporator superheat temperature (T SH,EVA ); The subcooling temperature of the internal condenser (T SC,ICDS ); Subcooling temperature of external heat exchanger (T SC,OHX ); Cooler superheat temperature (T SH,CHI ); Cooler expansion valve opening ratio (EXV CHI );as well as Target fan duty cycle (Fanreq coolt ).

17. The method for operating a thermal management system according to any one of claims 14 to 16, It is characterized in that in, The lower level control output (324) of the lower level control is selected from the following set of operating parameters of the thermal management system: Conditions for heating valve components (2WV heat ); Dehumidification valve component conditions (2WV heat ); Evaporator expansion valve opening ratio (EXV EVA ); External heat exchanger expansion valve opening ratio (EXV OHX ); Cooler expansion valve opening ratio (EXV CHI ); Target blower load / speed (N Blower );as well as Fan duty cycle / speed (Fanreq coolt ).

18. The method for operating a thermal management system according to any one of claims 14 to 17, characterized in that: In heating mode, The input (318) to the supervised learning model has the following parameters: Target internal condenser air outlet temperature (T_air_ICDS_out); Target blower speed (N Blower ); Target cooler coolant outlet temperature (T_coolt_CHI_out); The coolant inlet temperature of the cooler (T_coolt_CHI_in); The cooler coolant inlet mass / volume flow rate (Vdot_coolt_CHI_in); Ambient temperature (T_amb); Ambient humidity (H_amb); Vehicle speed (V_spd); Cabin air circulation rate (Recycle_ratio); and Target fan duty cycle (Fanreq coolt ), Wherein, the intermediate output (320) of the supervised learning model includes: The calculated internal condenser power (P ICDS (u)); The calculated cooler power (P CHI (u)); and the calculated coefficient of performance (COP) of the H / P system, And, wherein the optimal control set point (322) for the lower level control has: The speed of the compressor (N CMP ); Evaporator superheat temperature (T SH,EVA );as well as The subcooling temperature of the internal condenser (T SC,ICDS ).

19. The method for operating a thermal management system according to any one of claims 14 to 17, characterized in that: In dehumidification mode, The input (318) to the supervised learning model has the following parameters: Target internal condenser air outlet temperature (T_air_ICDS_out); Target evaporator air outlet temperature (T_air_EVA_out); Target blower speed (N Blower ); Ambient temperature (T_amb); Ambient humidity (H_amb); and Vehicle speed (V_spd), The intermediate output (320) of the supervised learning model has: The calculated internal condenser power (P ICDS (u)); The calculated evaporator power (P EVA (u)); and the calculated coefficient of performance (COP) of the H / P system, And, wherein the optimal control set point (322) for the lower level control is at least: The speed of the compressor (N CMP ); Evaporator superheat temperature (T SH,EVA ); Conditions for heating valve components (2WV dehum );as well as Dehumidification valve component conditions (2WV heat ).

20. The method for operating a thermal management system according to any one of claims 14 to 17, characterized in that: In cooling mode, The input (318) to the supervised learning model is the following parameters: Target evaporator air outlet temperature (T_air_EVA_out); Target blower speed (N Blower ); Target cooler coolant outlet temperature (T_coolt_CHI_out); The coolant inlet temperature of the cooler (T_coolt_CHI_in); The cooler coolant inlet mass / volume flow rate (Vdot_coolt_CHI_in); Ambient temperature (T_amb); Ambient humidity (H_amb); and Vehicle speed (V_spd), The intermediate output (320) of the supervised learning model has: The calculated cooler power (P CHI (u)); The calculated evaporator power (P EVA (u)); and the calculated coefficient of performance (COP) of the H / P system, And, wherein the optimal control set point (322) for the lower level control has: The speed of the compressor (N CMP ); The superheat temperature of the external heat exchanger (T SH,OHX );as well as Cooler superheat temperature (T SH,CHI ).

21. The method for operating a thermal management system according to any one of claims 14 to 20, characterized in that: in, Target internal condenser power (P ICDS,req ) is based on the target internal condenser air outlet temperature (T_air_ICDS_out), ambient temperature (T_amb), and blower speed (N Blower ) calculated.

22. The method for operating a thermal management system according to any one of claims 14 to 21, characterized in that: in, Target external condenser power (P OCDS,req ) is calculated based on the target external condenser coolant outlet temperature (T_coolt_OCDS_out), the ambient temperature (T_amb), and the coolant flow through the external condenser (138).

23. The method for operating a thermal management system according to any one of claims 14 to 22, characterized in that: in, Target evaporator power (P EVA,req ) is based on the target evaporator air outlet temperature (T_air_EVA_out), ambient temperature (T_amb), and blower speed (N Blower ) is calculated.

24. The method for operating a thermal management system according to any one of claims 14 to 23, characterized in that: in, Target cooler power (P CHI,req ) is calculated based on the target cooler coolant outlet temperature (T_coolt_CHI_out), the cooler coolant inlet temperature (T_coolt_CHI_in) and the cooler coolant inlet mass / volume flow rate (Vdot_coolt_CHI_in).

25. The method for operating a thermal management system according to any one of claims 10 to 20, characterized in that: In the electric powertrain coolant system mode, Wherein, the thermal system comprises an electric powertrain / battery coolant system (200), The input (318) to the supervised learning model has the following parameters: Ambient temperature (T_amb); Vehicle speed (V_spd); Battery temperature (T_battery); Electric powertrain temperature (T_ePT); Target cooler power (P CHI,req ); The target power of the electric powertrain (P ePT,req );as well as Target battery power (P battery,req ), Wherein, the calculated intermediate output (320) of the data-driven supervised learning model has: The calculated power consumption of the electric powertrain (P ePT (u)); The calculated battery power distribution (P battery (u)); and Calculated power consumption of electric drive auxiliary components (P aux (u)), And, wherein the optimal control set point (322) for the lower level control has: Optimal valve component control parameters (MCVe ctrl); Optimal electric heater control parameters (PTC ctrl); Optimal auxiliary component control parameters (Aux ctrl); and Optimum cooler power (P CHI ).

Images