Optimal torque distribution method and system for dual-motor four-wheel drive automobile
By acquiring the loss model of the dual motor system and solving the optimal torque distribution coefficient, the problem of low torque distribution efficiency of the dual motor drive is solved, and the energy consumption of the dual motor and the improvement of vehicle economy under different operating conditions is achieved.
Patent Information
- Application Number
- CN202411502148.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-25
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art is difficult to perform reasonable driving torque distribution for dual motors, resulting in the inability to allocate to the motor in accordance with the method with the highest energy efficiency, affecting the economy of the vehicle.
By obtaining the loss model of the dual motor system corresponding to the base speed zone and the weak magnetic zone, the optimal torque distribution coefficient is solved and torque distribution is performed to achieve optimal energy consumption of the dual motor.
It realizes the minimization of dual-motor drive power consumption under different working conditions, improving the vehicle's economy and vehicle performance.
Smart Images

Figure CN119058430A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to an optimal torque distribution method and system for a dual-motor four-wheel drive vehicle, belonging to the technical field of new energy vehicles. Background Art
[0002] Pure electric vehicles have the advantages of energy saving, no pollution and low noise, and have become the best development direction for new energy vehicles. At present, most pure electric vehicles are driven by a single motor, with a simple structure and easy control, but their development has been limited by the bottleneck of cruising range; under the condition of limited improvement of battery energy density, in order to solve this problem, optimizing the vehicle drive configuration and reducing drive loss have become effective ways to alleviate this bottleneck. Therefore, starting from the characteristics of the motor itself, it is of great significance to optimize the drive efficiency of the dual / multi-power source drive motor and perform optimal torque distribution, which can further improve the vehicle's overall performance and achieve its efficient operation.
[0003] It is difficult to reasonably distribute the driving torque to the dual motors with the existing technology, resulting in the inability to distribute it to the motors in the most energy efficient way, affecting the economy of the vehicle. Summary of the invention
[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide an optimal torque distribution method and system for a dual-motor four-wheel drive vehicle, so as to solve the problem that it is difficult in the prior art to reasonably distribute the driving torque to the dual motors, resulting in the inability to distribute it to the motors in the most energy efficient way.
[0005] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions:
[0006] In a first aspect, the present invention provides an optimal torque distribution method for a dual-motor four-wheel drive vehicle, comprising:
[0007] Obtaining a first dual-motor system loss model corresponding to a base speed region under a given driving condition;
[0008] Obtaining a second dual-motor system loss model corresponding to a weak magnetic field region under a given driving condition;
[0009] With the goal of optimizing the energy consumption of dual motors, the first dual motor system loss model and the second dual motor system loss model are solved respectively to obtain the corresponding optimal torque distribution coefficient, and then torque distribution is performed.
[0010] Furthermore, the given driving condition is:
[0011]
[0012] in, is the angular velocity of the front wheel motor, is the angular velocity of the rear wheel motor; is the preset motor angular velocity;
[0013] The expression of the first dual-motor system loss model is:
[0014]
[0015] in,
[0016]
[0017] P cu _ t 1 ( β ) = R s [ β a 1 T d a 2 + a 3 ] 2 + R s [ ( 1 − β ) a 1 T d a 2 + a 3 ] 2
[0018] P inv _ t 1 ( β ) = 6 ( C 1 + C 3 ) [ ( β T d a 2 ) 2 + ( ( 1 − β ) T d a 2 ) 2 ] + 6 ( C 2 + C 4 ) T d a 2
[0019] P F e _ t 1 ( β ) = a 4 [ ( a 5 ( 1 − β ) T d a 2 + ψ f ) 2 + ( L m ( 1 − β ) T d a 2 ) 2 ] + a 4 [ ( a 5 β T d a 2 + ψ f ) 2 + ( L m β T d a 2 ) 2 ]
[0020]
[0021]
[0022]
[0023]
[0024]
[0025] Where: is the loss equation of the first dual-motor system; It is the copper loss of dual motors in base speed zone; is the loss of dual motor inverter in base speed area; is the iron loss of the dual motors in the base speed zone; is the vehicle speed; is the dual motor torque distribution coefficient; The driving torque distributed to the front wheel motor; The driving torque distributed to the rear wheel motor; Demand driving torque for the vehicle; is the armature resistance; is the iron loss equivalent resistance; is the flux generated by the permanent magnet of the motor; P is the number of motor pole pairs; is the motor inductance; r is the wheel radius; is the transmission ratio of the transmission system; , , , is the inverter loss constant.
[0026] Furthermore, the method for obtaining the optimal torque distribution coefficient corresponding to the base speed zone includes:
[0027] For the base speed zone To perform the derivation:
[0028] ∂ F ( β ) ∂ β | 0 ≤ β ≤ 1 = 2 ( T d a 2 ) 2 [ R s a 1 2 + a 4 ( a 5 2 + L m 2 ) + 6 ( C 1 + C 3 ) ] ( 2 β − 1 )
[0029] ∂ 2 F ( β ) ∂ β 2 | 0 ≤ β ≤ 1 = 4 ( T d a 2 ) 2 [ R s a 1 2 + a 4 ( a 5 2 + L m 2 ) + 6 ( C 1 + C 3 ) ] > 0
[0030] Among them, when hour, ,Right now exist 0.5 when the extreme value is obtained, combined with
[0031] It can be seen that:
[0032] exist The minimum value is obtained at 0.5;
[0033] It can be seen that for a dual-motor four-wheel drive vehicle in the base speed zone, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle.
[0034] Furthermore, the given driving condition is:
[0035]
[0036] The weak magnetic zone includes a weak magnetic zone I and a weak magnetic zone II; the second dual-motor system loss model includes a first sub-dual-motor system loss model and a second sub-dual-motor system loss model;
[0037] The first sub-dual motor system loss model corresponds to the weak magnetic field region I;
[0038] The second sub-dual motor system loss model corresponds to the weak magnetic region II.
[0039] Furthermore, the expression of the loss model of the first sub-dual motor system is:
[0040]
[0041] in,
[0042]
[0043]
[0044] P F e _ t 1 ( β ) ' = a 5 Pvf d r [ 2 g 2 + a 5 ( T d L m a 2 ) 2 ( 2 β 2 − 2 β + 1 ) ] + 2 Pvf d a 5 3 T d rL m a 2 [ β f 1 + ( 1 − β ) f 3 ]
[0045]
[0046]
[0047] f 2 = [ ( - ψ f L m + g 2 − ( β T d a 2 ) 2 ) 2 + ( β T d a 2 ) 2 ] 3 2
[0048]
[0049] f 4 = [ ( − ψ f L m + g 2 − ( ( 1 − β ) T d a 2 ) 2 ) 2 + ( ( 1 − β ) T d a 2 ) 2 ] 3 2
[0050] Where: is the loss model of the first sub-dual motor system; is the copper loss of the dual motor in the weak magnetic field zone I; is the dual-motor inverter loss in field weakening zone I; is the iron loss of the dual motor in the field weakening zone I; is the maximum voltage of the motor.
[0051] Furthermore, the expression of the loss model of the second sub-dual motor system is:
[0052]
[0053] in,
[0054]
[0055]
[0056]
[0057] P i nv _ t 1 ( β ) '' = 12 ( C 1 + C 3 ) ( − ψ f L m ) 2 + 6 ( C 1 + C 3 ) [ ( β T d a 2 ) 2 + ( ( 1 − β ) T d a 2 ) 2 ] +
[0058] Where: is the loss model of the second sub-dual motor system; It is the copper loss of dual motor in weak magnetic zone II; is the dual-motor inverter loss in field weakening zone II; It is the iron loss of dual motor in weak magnetic zone II.
[0059] Furthermore, the method for obtaining the optimal torque distribution coefficient corresponding to the magnetic weakening area includes:
[0060] Derivatives are performed for the first sub-dual motor system loss model and the second sub-dual motor system loss model;
[0061] Among them, the first sub-dual motor system loss model is derived to obtain:
[0062]
[0063] Among them, when hour, ,Right now exist 0.5 when the extreme value is obtained, combined with
[0064] It can be seen that:
[0065] exist The minimum value is obtained at 0.5;
[0066] It can be seen that for a dual-motor four-wheel drive vehicle in weak magnetic zone I, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle.
[0067] Furthermore, by deriving the loss model of the second sub-dual motor system, we can obtain:
[0068]
[0069] Among them, when hour, ,Right now exist 0.5 when the extreme value is obtained, combined with It can be seen that:
[0070] 'exist The minimum value is obtained at 0.5;
[0071] It can be seen that for a dual-motor four-wheel drive vehicle in the weak magnetic zone II, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle;
[0072] In summary, for a dual-motor four-wheel drive vehicle in a weak magnetic field condition, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle.
[0073] In a second aspect, the present invention provides an optimal torque distribution system for a dual-motor four-wheel drive vehicle, comprising:
[0074] A first acquisition module is used to acquire a first dual-motor system loss model corresponding to a base speed zone under a given driving condition;
[0075] A second acquisition module is used to acquire a second dual-motor system loss model corresponding to a weak magnetic field region under a given driving condition;
[0076] The torque distribution module is used to solve the first dual-motor system loss model and the second dual-motor system loss model with the goal of optimizing the dual-motor energy consumption, obtain the optimal torque distribution coefficient, and perform torque distribution.
[0077] In a third aspect, the present invention provides a vehicle, including the optimal torque distribution system for the dual-motor four-wheel drive vehicle described in the second aspect.
[0078] Compared with the prior art, the present invention has the following beneficial effects:
[0079] By calculating the optimal torque distribution coefficient in the base speed zone and the optimal torque distribution coefficient in the weak magnetic zone, the present invention can find that from the perspective of reducing the vehicle's driving power consumption, whether it is low-speed or medium-high-speed working conditions, the vehicle adopts a dual-motor average torque distribution strategy, and reasonable driving torque distribution for the dual motors can achieve optimal driving energy efficiency and improve economy. BRIEF DESCRIPTION OF THE DRAWINGS
[0080] Figure 1 1 is a schematic diagram of a working process of an optimal torque distribution method for a dual-motor four-wheel drive vehicle provided according to an embodiment of the present invention;
[0081] Figure 2 is a schematic diagram of a loss function for deep reinforcement learning algorithm training of a dual deep Q network provided in an embodiment of the present invention;
[0082] Figure 3 is a schematic diagram of torque distribution optimization results provided according to an embodiment of the present invention;
[0083] Figure 4 It is a schematic diagram of the dual motor configuration and driving power loss characteristic law provided according to an embodiment of the present invention. DETAILED DESCRIPTION
[0084] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.
[0085] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.
[0086] Embodiment 1:
[0087] According to the dual motor configuration and the driving power loss characteristic law, the total driving efficiency of the front and rear power systems is obtained, wherein the total driving efficiency of the front and rear power systems is expressed by the motor angular velocity, the transmission system loss equation, the dual motor system loss equation and the dual motor torque distribution coefficient under a given driving condition;
[0088] in, Figure 4 In and They are the power losses of the front and rear power systems respectively.
[0089] In one embodiment, the total driving efficiency of the front and rear power systems is as follows:
[0090]
[0091] In the formula, is the total driving efficiency of the power system; Output power to the power system; is the inverter system power consumption; is the power consumption of the motor system; is the power consumption of the transmission system; represents the front power system; subscript Rear powertrain.
[0092] In one embodiment, the single motor loss (motor + inverter) is a function of the motor speed and torque; the power consumption of the transmission system is mainly related to the vehicle speed. Under a given working condition (vehicle speed v and vehicle required driving torque Given), the total loss of the front and rear transmission systems can be regarded as a constant; therefore, under given driving conditions, the driving efficiency of the front and rear power systems can be defined as follows:
[0093] η = [ β K c T d ω f + ( 1 − β ) K c T d ω r ] β K c T d ω f + ( 1 − β ) K c T d ω r + F ( β ) + C ( v )
[0094] Where: is the angular velocity of the front wheel motor; is the angular velocity of the rear wheel motor; is the unit conversion factor; is the transmission system loss equation; is the dual motor torque distribution coefficient; is the loss equation of the dual motor system; Demand driving torque for the vehicle;
[0095] in:
[0096]
[0097] Where: The driving torque distributed to the front wheel motor, The driving torque distributed to the rear wheel motor;
[0098] Therefore, for a dual-motor four-wheel drive electric vehicle, under a given operating condition, , that is, establish a dual motor system loss model , and seek The minimum torque distribution coefficient is the key to achieving efficient driving of the whole vehicle. At this time, the total driving efficiency of the power system is:
[0099]
[0100] in, is the motor angular velocity; from the above formula, we can know that The smaller the The bigger;
[0101] In one embodiment, the dual-motor system loss model specifically includes an inverter loss model, a motor loss model, a dual-motor system loss model in a base speed region, and a dual-motor system loss model in a weak magnetic field region. The inverter loss model includes conduction loss and switching loss, which is equivalent to:
[0102]
[0103] In the formula, is the IGBT conduction loss; is the diode conduction loss; is the IGBT switching loss; is the phase current amplitude; , , , is the inverter loss constant; where IGBT is an insulated gate bipolar transistor.
[0104] In one embodiment, the motor loss model includes mechanical loss, motor copper loss and motor iron loss;
[0105] The mechanical loss is mainly affected by the motor speed and can be ignored under given working conditions. The influence of the change is not calculated for mechanical loss.
[0106] For the motor copper loss and motor iron loss, according to the dq equivalent circuit model, the expressions of motor copper loss and motor iron loss are obtained as follows:
[0107] P cu = R s [ ( i dc + i dt ) 2 + ( i qc + i qt ) 2 ]
[0108]
[0109] Where: is the motor copper loss, is the motor iron loss; is the armature resistance; is the iron loss equivalent resistance; and are the d-axis torque and iron loss equivalent current components respectively; and They are the q-axis torque and iron loss equivalent current components respectively.
[0110] like Figure 1 and Figure 3 As shown, an embodiment of the present invention provides an optimal torque distribution method for a dual-motor four-wheel drive vehicle, comprising:
[0111] Obtaining a first dual-motor system loss model corresponding to a base speed region under a given driving condition;
[0112] Obtaining a second dual-motor system loss model corresponding to a weak magnetic field region under a given driving condition;
[0113] With the goal of optimizing the energy consumption of dual motors, the first dual motor system loss model and the second dual motor system loss model are solved respectively to obtain the corresponding optimal torque distribution coefficient, and then torque distribution is performed.
[0114] In one embodiment, the given driving condition is:
[0115]
[0116] in, is the angular velocity of the front wheel motor, is the angular velocity of the rear wheel motor; is the preset motor angular velocity;
[0117] The expression of the first dual-motor system loss model is:
[0118]
[0119] in,
[0120]
[0121] P cu _ t 1 ( β ) = R s [ β a 1 T d a 2 + a 3 ] 2 + R s [ ( 1 − β ) a 1 T d a 2 + a 3 ] 2
[0122] P inv _ t 1 ( β ) = 6 ( C 1 + C 3 ) [ ( β T d a 2 ) 2 + ( ( 1 − β ) T d a 2 ) 2 ] + 6 ( C 2 + C 4 ) T d a 2
[0123] P F e _ t 1 ( β ) = a 4 [ ( a 5 ( 1 − β ) T d a 2 + ψ f ) 2 + ( L m ( 1 − β ) T d a 2 ) 2 ] + a 4 [ ( a 5 β T d a 2 + ψ f ) 2 + ( L m β T d a 2 ) 2 ]
[0124]
[0125]
[0126]
[0127]
[0128]
[0129] Where: is the loss equation of the first dual-motor system; It is the copper loss of dual motors in base speed zone; is the loss of dual motor inverter in base speed area; is the iron loss of the dual motors in the base speed zone; is the vehicle speed; is the dual motor torque distribution coefficient; The driving torque distributed to the front wheel motor; The driving torque distributed to the rear wheel motor; Demand driving torque for the vehicle; is the armature resistance; is the iron loss equivalent resistance; is the flux generated by the permanent magnet of the motor; P is the number of motor pole pairs; is the motor inductance; r is the wheel radius; is the transmission ratio of the transmission system; , , , is the inverter loss constant.
[0130] Specifically, for a surface permanent magnet motor, in the base speed region, the motor direct axis component current id=0. Combining its voltage balance, flux linkage and torque equations, under a given operating condition, the single motor copper loss equation is:
[0131] P cu = R s [ ( ( Pvf d L m rR c ) 2 + 1 ) T d P ψ f + Pvf d ψ f rR c ] 2
[0132] In the formula, is the flux generated by the permanent magnet of the motor; P is the number of motor pole pairs; is the motor inductance; r is the wheel radius; is the transmission ratio of the transmission system; v is the vehicle speed;
[0133] make ,
[0134] Get the dual motor copper loss equation for:
[0135] P cu_t1 ( β ) = R f _ s [ a f _ 1 β T d a f _ 2 + a f _ 3 ] 2 + R r _ s [ a r _ 1 ( 1 − β ) T d a r _ 2 + a r _ 3 ] 2
[0136] For dual motors, , ,in, is the pole pair number of the front dynamic system, is the number of pole pairs of the rear power system; , They are the flux linkages generated by the permanent magnets of the front and rear power system motors respectively; Mainly affected by the motor speed, which can be ignored under given working conditions the impact of change; Mainly affected by the motor temperature, for dual-motor driven trams with good cooling conditions, = , , are the armature resistances of the front and rear power systems respectively; the copper loss equation of the dual motors in the base speed zone is simplified to:
[0137] P cu _ t 1 ( β ) = R s [ β a 1 T d a 2 + a 3 ] 2 + R s [ ( 1 − β ) a 1 T d a 2 + a 3 ] 2
[0138] Similarly, the loss of the dual-motor inverter in the base speed zone can be obtained: and iron loss The equation is
[0139] P inv _ t 1 ( β ) = 6 ( C 1 + C 3 ) [ ( β T d a 2 ) 2 + ( ( 1 − β ) T d a 2 ) 2 ] + 6 ( C 2 + C 4 ) T d a 2
[0140] P F e _ t 1 ( β ) = a 4 [ ( a 5 ( 1 − β ) T d a 2 + ψ f ) 2 + ( L m ( 1 − β ) T d a 2 ) 2 ] + a 4 [ ( a 5 β T d a 2 + ψ f ) 2 + ( L m β T d a 2 ) 2 ] .
[0141] In one embodiment, a method for obtaining an optimal torque distribution coefficient corresponding to a base speed zone includes:
[0142] For the base speed zone To perform the derivation:
[0143] ∂ F ( β ) ∂ β | 0 ≤ β ≤ 1 = 2 ( T d a 2 ) 2 [ R s a 1 2 + a 4 ( a 5 2 + L m 2 ) + 6 ( C 1 + C 3 ) ] ( 2 β − 1 )
[0144] ∂ 2 F ( β ) ∂ β 2 | 0 ≤ β ≤ 1 = 4 ( T d a 2 ) 2 [ R s a 1 2 + a 4 ( a 5 2 + L m 2 ) + 6 ( C 1 + C 3 ) ] > 0
[0145] Among them, when hour, ,Right now exist 0.5 when the extreme value is obtained, combined with
[0146] It can be seen that:
[0147] exist The minimum value is obtained at 0.5;
[0148] It can be seen that for a dual-motor four-wheel drive vehicle in the base speed zone, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle.
[0149] In one embodiment, the given driving condition is:
[0150]
[0151] The weak magnetic zone includes a weak magnetic zone I and a weak magnetic zone II; the second dual-motor system loss model includes a first sub-dual-motor system loss model and a second sub-dual-motor system loss model;
[0152] The first sub-dual motor system loss model corresponds to the weak magnetic field region I;
[0153] The second sub-dual motor system loss model corresponds to the weak magnetic region II.
[0154] Specifically, the weakening magnetic zone I refers to the constant torque operation of the motor below the base speed (usually refers to the rated speed of the motor), and is controlled by the linear maximum torque current ratio MTPA (the ratio of the electromagnetic torque to the current required to produce it); the area between the maximum torque current ratio curve and the maximum torque voltage ratio curve is called the first weakening magnetic zone, and the weakening magnetic zone II refers to the motor running along the maximum torque voltage ratio MTPV curve above the base speed, which is called the second weakening magnetic zone.
[0155] The expression of the loss model of the first sub-dual motor system is:
[0156]
[0157] in,
[0158]
[0159]
[0160] P F e _ t 1 ( β ) ' = a 5 Pvf d r [ 2 g 2 + a 5 ( T d L m a 2 ) 2 ( 2 β 2 − 2 β + 1 ) ] + 2 Pvf d a 5 3 T d rL m a 2 [ β f 1 + ( 1 − β ) f 3 ]
[0161]
[0162]
[0163] f 2 = [ ( - ψ f L m + g 2 − ( β T d a 2 ) 2 ) 2 + ( β T d a 2 ) 2 ] 3 2
[0164]
[0165] f 4 = [ ( − ψ f L m + g 2 − ( ( 1 − β ) T d a 2 ) 2 ) 2 + ( ( 1 − β ) T d a 2 ) 2 ] 3 2
[0166] Where: is the loss model of the first sub-dual motor system; is the copper loss of the dual motor in the weak magnetic field zone I; is the dual-motor inverter loss in field weakening zone I; is the iron loss of the dual motor in the field weakening zone I; is the maximum voltage of the motor.
[0167] The expression of the loss model of the second sub-dual motor system is:
[0168]
[0169] in,
[0170]
[0171]
[0172]
[0173] P i nv _ t 1 ( β ) '' = 12 ( C 1 + C 3 ) ( − ψ f L m ) 2 + 6 ( C 1 + C 3 ) [ ( β T d a 2 ) 2 + ( ( 1 − β ) T d a 2 ) 2 ] +
[0174] Where: is the loss model of the second sub-dual motor system; It is the copper loss of dual motor in weak magnetic zone II; is the loss of the dual-motor inverter in the field weakening zone II; It is the iron loss of dual motor in weak magnetic zone II.
[0175] In one embodiment, a method for obtaining an optimal torque distribution coefficient corresponding to a magnetic weakening region includes:
[0176] Derivatives are performed for the first sub-dual motor system loss model and the second sub-dual motor system loss model;
[0177] Among them, the first sub-dual motor system loss model is derived to obtain:
[0178]
[0179] Among them, when hour, ,Right now exist 0.5 when the extreme value is obtained, combined with
[0180] It can be seen that:
[0181] exist The minimum value is obtained at 0.5;
[0182] It can be seen that for a dual-motor four-wheel drive vehicle in weak magnetic zone I, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle;
[0183] By deriving the loss model of the second sub-dual motor system, we can obtain:
[0184]
[0185] Among them, when hour, ,Right now exist 0.5 when the extreme value is obtained, combined with It can be seen that:
[0186] 'exist The minimum value is obtained at 0.5;
[0187] It can be seen that for a dual-motor four-wheel drive vehicle in the weak magnetic zone II, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle;
[0188] In summary, for a dual-motor four-wheel drive vehicle in a weak magnetic field condition, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle; from the perspective of reducing the vehicle's driving power consumption, whether it is a low-speed or medium- and high-speed condition, the vehicle adopts a dual-motor average torque distribution strategy to achieve optimal driving energy efficiency and improve economy.
[0189] In one embodiment, a method for obtaining an optimal torque distribution coefficient in a base speed region includes:
[0190] The torque demand, vehicle speed, acceleration and battery charge state are taken as state function variables, namely: ;
[0191] The motor torque and speed are used as action vectors, that is, ;
[0192] Will , and as reward signals respectively;
[0193] The dual deep Q network model is trained using state function variables, action vectors, and reward signals to obtain the optimal torque allocation model.
[0194] The state function variables acquired in real time are input into the optimal torque distribution model to obtain the optimal torque distribution coefficient. , completing the torque distribution.
[0195] Among them, the optimal torque distribution coefficient with optimal energy consumption of dual motors obtained by deep reinforcement learning algorithm based on dual deep Q network specifically includes:
[0196] The torque allocation strategy based on deep reinforcement learning of dual deep Q networks aims to find the optimal torque allocation coefficient to achieve the optimal state of vehicle energy efficiency. and target update network The two deep neural networks decouple the two value functions, resulting in two sets of weights. and ', the initialization weights are consistent, The network updates the weights at each step. Network every Step update weights once, when updating, from The network selects the action with the largest target, using The action indicator corresponding to the network updates the target value, because The network is relatively stable, turning the overestimation of each step into The overestimation of the step is improved to improve the convergence speed and optimization performance of the algorithm, solve the problem of overestimation, and further obtain the optimal torque distribution coefficient with optimal energy consumption of dual motors through the greedy algorithm; Figure 2 As shown in , the loss function value of the system drops rapidly and tends to be stable, indicating that the algorithm converges; Figure 3 As shown, =0.5, the minimum driving power consumption can be achieved and the energy consumption is optimal.
[0197] in, is the preset value; the two value functions are the state function and the action function; the state function is to select the vehicle speed, acceleration, power battery SOC and motor torque as the state function; the action function is to select the motor torque and motor speed as the action function.
[0198] By calculating the optimal torque distribution coefficient in the base speed zone and the optimal torque distribution coefficient in the weak magnetic field zone, the present invention can know that from the perspective of reducing vehicle driving power consumption, whether it is low-speed or medium-high-speed working conditions, the vehicle adopts a dual-motor average torque distribution strategy and performs reasonable driving torque distribution for the dual motors, which can achieve optimal driving energy efficiency and improve economy, that is, 0.5, and then the present invention further obtains the optimal torque distribution coefficient with optimal energy consumption of dual motors through a deep reinforcement learning algorithm based on a dual deep Q network, that is, 0.5, so as to verify the optimal torque distribution coefficient in the base speed area and the optimal torque distribution coefficient in the weak magnetic field area, to ensure that the optimal torque distribution coefficient with optimal energy consumption of dual motors obtained by the deep reinforcement learning algorithm based on the dual deep Q network is correct, and then the torque distribution work is performed to achieve minimum driving power consumption and optimal energy consumption.
[0199] The present invention establishes a dual-motor system loss model based on the impact of motor loss on the vehicle driving efficiency, and takes into account the impact of the non-working motor in the single-motor mode.
[0200] The present invention can take into account the adverse effects of motor loss on the driving efficiency of the whole vehicle for dual / multi-power source drive, establish a dual-motor torque distribution strategy based on the motor loss mechanism, and optimize energy consumption; the deep reinforcement learning algorithm based on the dual deep Q network seeks the optimal torque distribution coefficient and performs torque distribution, which is more capable of adapting to environmental changes, thereby reducing the impact of random changes in the environment on the economy of the whole vehicle, which is of great significance to the robustness problem of new energy commercial vehicles in random driving environments.
[0201] The present invention constructs a dual-motor system loss model based on the power consumption characteristics of dual-motor drive, obtains the torque distribution coefficient with the best energy efficiency for the dual-motor through a deep reinforcement learning algorithm based on a dual deep Q network, and performs torque distribution, so that the dual-motor system is more adaptable to environmental changes, reduces the impact of random environmental changes on the economy of the whole vehicle, and distributes energy to the motors in the most energy efficient manner, thereby achieving efficient operation of multi-motor drive and improving economy.
[0202] Embodiment 2:
[0203] The present invention also provides an optimal torque distribution system for a dual-motor four-wheel drive vehicle, comprising:
[0204] A first acquisition module is used to acquire a first dual-motor system loss model corresponding to a base speed zone under a given driving condition;
[0205] A second acquisition module is used to acquire a second dual-motor system loss model corresponding to a weak magnetic field region under a given driving condition;
[0206] The torque distribution module is used to solve the first dual-motor system loss model and the second dual-motor system loss model with the goal of optimizing the dual-motor energy consumption, obtain the optimal torque distribution coefficient, and perform torque distribution.
[0207] Embodiment three:
[0208] The present invention also provides a vehicle, including the optimal torque distribution system for the dual-motor four-wheel drive vehicle described in the second embodiment.
[0209] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0210] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0211] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0212] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0213] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for optimal torque distribution of a dual-motor four-wheel drive vehicle, characterized in that: include: Obtaining a first dual-motor system loss model corresponding to a base speed region under a given driving condition; Obtaining a second dual-motor system loss model corresponding to the field weakening region under a given driving condition; With the goal of optimizing the energy consumption of the dual motors, the first dual motor system loss model and the second dual motor system loss model are solved respectively to obtain the corresponding optimal torque distribution coefficient, and then torque distribution is performed.
2. The optimal torque distribution method for a dual-motor four-wheel drive vehicle according to claim 1, characterized in that: The given driving condition is: in, is the angular velocity of the front wheel motor, is the angular velocity of the rear wheel motor; is the preset motor angular velocity; The expression of the first dual-motor system loss model is: in, Where: is the loss equation of the first dual-motor system; is the copper loss of the dual motors in the base speed zone; is the loss of the dual-motor inverter in the base speed zone; is the iron loss of the dual motors in the base speed zone; is the vehicle speed; is the dual motor torque distribution coefficient; The driving torque distributed to the front wheel motor; The driving torque distributed to the rear wheel motor; Drive torque required by the vehicle; is the armature resistance; is the iron loss equivalent resistance; is the flux linkage generated by the permanent magnet of the motor; P is the number of motor pole pairs; is the motor inductance; r is the wheel radius; is the transmission system transmission ratio; 、 、 、 is the inverter loss constant.
3. The optimal torque distribution method for a dual-motor four-wheel drive vehicle according to claim 2, characterized in that: The method for obtaining the optimal torque distribution coefficient corresponding to the base speed zone includes: For the base speed zone Take the derivative: Among them, when hour, ,Right now exist 0.5 when the extreme value is achieved, combined with It can be seen that: exist The minimum value is achieved at 0.5; It can be seen from this that for a dual-motor four-wheel drive vehicle in the base speed zone, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle.
4. The optimal torque distribution method for a dual-motor four-wheel drive vehicle according to claim 2, characterized in that: The given driving condition is: The magnetic weakening region includes a magnetic weakening region I and a magnetic weakening region II; the second dual-motor system loss model includes a first sub-dual-motor system loss model and a second sub-dual-motor system loss model; The first sub-dual motor system loss model corresponds to the field weakening region I; The second sub-dual motor system loss model corresponds to the magnetic weakening region II.
5. The optimal torque distribution method for a dual-motor four-wheel drive vehicle according to claim 4, characterized in that: The expression of the loss model of the first sub-dual motor system is: in, Where: is the loss model of the first sub-dual motor system; is the copper loss of the dual motor in field weakening zone I; is the loss of the dual-motor inverter in field weakening region I; is the iron loss of the dual motor in field weakening region I; is the maximum voltage of the motor.
6. The optimal torque distribution method for a dual-motor four-wheel drive vehicle according to claim 5, characterized in that: The expression of the loss model of the second sub-dual motor system is: in, Where: is the loss model of the second sub-dual motor system; is the copper loss of the dual motor in field weakening zone II; is the loss of the dual-motor inverter in field weakening region II; It is the iron loss of the dual motor in the field weakening zone II.
7. The optimal torque distribution method for a dual-motor four-wheel drive vehicle according to claim 6, characterized in that: The method for obtaining the optimal torque distribution coefficient corresponding to the field weakening region includes: Derivatives are obtained for the first sub-dual motor system loss model and the second sub-dual motor system loss model; Among them, the derivation of the first sub-dual motor system loss model can be obtained: Among them, when hour, ,Right now exist 0.5 when the extreme value is achieved, combined with It can be seen that: exist The minimum value is achieved at 0.5; It can be seen from this that for a dual-motor four-wheel drive vehicle in the weak magnetic zone I, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle.
8. The optimal torque distribution method for a dual-motor four-wheel drive vehicle according to claim 7, characterized in that: By deriving the loss model of the second sub-dual motor system, we can obtain: Among them, when hour, ,Right now exist 0.5 when the extreme value is achieved, combined with It can be seen that: 'exist The minimum value is achieved at 0.5; It can be seen that for a dual-motor four-wheel drive vehicle in the weak magnetic zone II, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle; In summary, for a dual-motor four-wheel drive vehicle in the weak magnetic field region, the average torque distribution strategy can minimize the driving power consumption of the dual-motor four-wheel drive vehicle.
9. An optimal torque distribution system for a dual-motor four-wheel drive vehicle, characterized in that: include: A first acquisition module is used to obtain a first dual-motor system loss model corresponding to a base speed region under a given driving condition; A second acquisition module is used to obtain a second dual-motor system loss model corresponding to the magnetic weakening region under a given driving condition; The torque distribution module is used to solve the first dual-motor system loss model and the second dual-motor system loss model with the goal of optimizing the energy consumption of the dual motors, obtain the optimal torque distribution coefficient, and perform torque distribution.
10. A vehicle, characterized in that: Including the optimal torque distribution system for a dual-motor four-wheel drive vehicle as described in claim 9.
Citation Information
Cited By
Dual-motor coupling driving method, system and equipment for electric vehicle and medium
CN119611096A
A method, system, device and medium for dual-motor coupled drive of electric vehicles
CN119611096B
