Method and system for coordinated control of front and rear power chains of a hybrid electric drive vehicle

Abstract

The application relates to a kind of front and rear power chain coordination control method and system for hybrid electric drive vehicle, which comprises: inputting historical vehicle speed, accelerator pedal and brake pedal signal into pre-constructed fuzzy reasoning system to obtain predicted vehicle speed; through power flow coupling relationship, the dynamic prediction model of front and rear power chain for control is pre-established, which is used to predict the future running state of vehicle, and a multi-objective optimization function considering vehicle speed tracking, SOC keeping, fuel consumption reduction and power fluctuation reduction is set, and the multi-objective optimization function is solved by numerical solution method under system constraint condition, to realize the coordinated optimization control of power distribution between different power sources of front power and longitudinal control of rear power chain.The application can weaken the severe fluctuation of power demand of hybrid electric vehicle power source under strong transient working condition, ensure the stability of engine operation under strong transient working condition, and improve fuel economy; it can be applied in vehicle control field.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, in particular to a front-rear power chain coordination control method and system for a hybrid electric drive vehicle. BACKGROUND

[0002] In a hybrid electric drive tracked vehicle, a series hybrid system is concerned due to its simple structure, flexible layout and easy control. However, the difference in response speed between the engine and the motor also brings new coordination control problems, which are manifested as difficulty in engine speed regulation and even engine stall under strong transient conditions, thereby causing the front power chain to fail to meet the power demand of the rear power chain. SUMMARY

[0003] To solve the above problems, the present application provides a front-rear power chain coordination control method and system for a hybrid electric drive vehicle, which can reduce the dramatic fluctuations in power demand of the hybrid vehicle power source under strong transient conditions, ensure the stability of the engine under strong transient conditions, and improve fuel economy.

[0004] To achieve the above-mentioned purpose, the present application adopts the following technical scheme: a front-rear power chain coordination control method for a hybrid electric drive vehicle, comprising: inputting historical vehicle speed, accelerator pedal and brake pedal signals into a pre-constructed fuzzy reasoning system to obtain a predicted vehicle speed; taking the predicted vehicle speed as a target vehicle speed in an optimization target, pre-establishing a dynamic prediction model of the front-rear power chain for control through a power flow coupling relationship, which is used to predict the future operating state of the vehicle, and setting a multi-objective optimization function considering vehicle speed tracking, SOC maintenance, fuel consumption reduction, power fluctuation reduction and target vehicle speed, and solving the multi-objective optimization function under system constraints using a numerical solution method to realize coordinated optimization control of power distribution between different power sources in the front power and longitudinal control of the rear power chain.

[0005] Further, the construction method of the fuzzy reasoning system comprises:

[0006] Divide typical cycle conditions and real vehicle operating data into a training set and a test set; the real vehicle operating data includes historical vehicle speed, accelerator pedal and brake pedal signals;

[0007] Set a five-layer structure of the fuzzy reasoning system;

[0008] Train the fuzzy reasoning system using the training set and adjust the antecedent and consequent parameters of the fuzzy reasoning system.

[0009] Further, the five-layer structure of the fuzzy reasoning system comprises:

[0010] The membership function layer is used to convert the precise value of the input signal into fuzzy language, dividing the domain of the current vehicle speed and acceleration into three categories: low, medium, and high. A Gaussian membership function is used to characterize the tendency of the two sides of the intermediate transition state difference;

[0011] Fuzzy reasoning layer, each node in this layer corresponds to a fuzzy rule, a total of 9 rules, the output is the membership function value ω of each rule i , represents the credibility of each rule:

[0012] Normalization layer, normalizes the 9 memberships;

[0013] Fuzzy rule output layer, each node i in this layer is an adaptive node, output Among them, {p, r, q} are the adjustable parameters of the node, called the consequent parameters;

[0014] The total output layer accumulates the output of each node in the fourth layer to obtain the total output.

[0015] Furthermore, the method of using the training set to train the fuzzy inference system and using a hybrid algorithm of the BP algorithm and the least squares method to adjust the antecedent and consequent parameters of the fuzzy inference system includes:

[0016] In the hybrid algorithm, the forward stage is calculated up to the fourth layer, and then the least squares method is used to identify the consequent parameters;

[0017] In the reverse phase, the error signal is back-propagated and the BP algorithm is used to update the antecedent parameters. When the antecedent parameters are fixed, the consequent parameters identified by the least squares method are optimal.

[0018] Furthermore, the dynamic prediction model is:

[0019]

[0020] Where, Represents the differential of battery SOC, U oc Indicates the battery open circuit voltage, P d Indicates the required power, P e Indicates engine power, R b Represents the internal resistance of the battery, Indicates fuel consumption rate, Lookup-Table (P e ) means looking up the table based on engine power. represents the vehicle speed differential, δ represents the rotational mass conversion coefficient, m represents the vehicle mass, r represents the tire radius, T m represents the driving motor torque, i′ represents the transmission ratio, T brepresents a mechanical braking torque, g represents a gravitational acceleration, f represents a rolling resistance coefficient, a represents a slope, p represents an air density, C D represents an air resistance coefficient, A represents a windward area, and v represents a vehicle speed.

[0021] Further, the multi-objective optimization function is:

[0022]

[0023] wherein N p represents a prediction horizon, ω1-ω6 represent weight coefficients of a vehicle speed tracking term, an SOC maintaining term, a fuel consumption term, a driving motor driving force term, a mechanical braking force term, and an engine power variation term, respectively, v ref represents a target vehicle speed, SOC represents an SOC of a battery, SOC ref represents a target SOC, m f represents a fuel consumption, ΔF m represents a driving motor force variation, ΔF brk represents a mechanical braking force variation, ΔP e represents an engine power variation.

[0024] Further, the solution of the multi-objective optimization function includes:

[0025] a state variable initial value x0 is given by feedback at the beginning of a time window, a dynamic prediction model is used to predict a pre-set prediction horizon N p of a system dynamic;

[0026] a predicted vehicle speed of a vehicle speed prediction model is used as a vehicle speed target value, an SOC target value is set as a constant value, the vehicle speed target value and the SOC target value are used to form a reference signal sequence, a control variable sequence within a control horizon N m is solved, N m ≤N p , the control variable outside the control horizon remains unchanged, so that the multi-objective optimization function reaches a minimum;

[0027] only the first control variable of the control sequence is applied to the controlled object, and the remaining control variables are all discarded, and the optimization process is repeated at the next sampling time.

[0028] A kind of for hybrid electric drive vehicle front and rear power chain coordination control system, it includes: vehicle speed prediction module, historical vehicle speed, accelerator pedal and brake pedal signal input is constructed in fuzzy reasoning system in advance, and the predicted vehicle speed of getting is obtained in advance;Coordination control module, predicted vehicle speed is as target vehicle speed in optimization target, the dynamic prediction model of front and rear power chain for control is established in advance by power flow coupling relationship, for predicting the future operating state of vehicle, and set considering vehicle speed tracking, SOC keeps, fuel consumption reduces, power fluctuation reduces and the multi-objective optimization function of target vehicle speed, and the multi-objective optimization function is solved under system constraint condition using numerical solution method, realize the coordination optimization control of power distribution between different power sources of front power and longitudinal control of rear power chain.

[0029] A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions which, when executed by a computing device, cause the computing device to perform any of the above-described methods.

[0030] A computing device comprising: one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the above-described methods.

[0031] The present application has the following advantages due to the above technical solutions:

[0032] 1、The present application can solve the problem of engine flameout of hybrid electric drive vehicle due to too large transient loading rate under strong transient operating condition, suppress the transient variation of hybrid power system under strong transient operating condition, and improve the fuel economy of hybrid electric drive vehicle.

[0033] 2、The present application reduces the severe fluctuation of power demand of hybrid electric vehicle power source under strong transient operating condition through optimization algorithm, ensures the stability of engine operation under strong transient operating condition, and improves fuel economy. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 It is a whole flow chart of the method for coordinating control of front and rear power chain of hybrid electric drive vehicle in an embodiment of the present application;

[0035] Figure 2 It is a detailed flow chart of the method for coordinating control of front and rear power chain in an embodiment of the present application;

[0036] Figure 3 It is a structure diagram of fuzzy reasoning system in an embodiment of the present application;

[0037] Figure 4 It is a schematic diagram of the method for solving multi-objective optimization function in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the described embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0039] It should be noted that the terms used herein are only intended to describe specific embodiments, and are not intended to limit the exemplary embodiments according to the present application. As used herein, the singular form is intended to include the plural form, unless the context clearly indicates otherwise, and it should also be understood that when the terms "comprise" and / or "include" are used in the specification, there is a presence of a feature, step, operation, device, component and / or combination thereof.

[0040] The present application provides a method and system for coordinating control of front and rear power chains of a hybrid electric drive vehicle, which predicts future vehicle speed according to historical vehicle speed information and driver pedal signal information; and through model predictive control, realizes coordinated optimization control of power distribution between different power sources of front power and longitudinal control of rear power chain, taking into account power smoothing and economy. The present application fully considers the response difference between engine and motor of heavy vehicle, and through vehicle speed prediction and optimization control method of model predictive control, realizes coordinated control between rear power chain loading and front power chain power output, which can effectively suppress the severe transient state of engine, and at the same time improve fuel economy.

[0041] In an embodiment of the present application, a method for coordinating control of front and rear power chains of a hybrid electric drive vehicle is provided. In the embodiment, as shown in Figure 1 , Figure 2 The method comprises the following steps:

[0042] 1) input historical vehicle speed, accelerator pedal and brake pedal signals into a pre-constructed fuzzy reasoning system to obtain accurate future predicted vehicle speed;

[0043] 2) take the predicted vehicle speed as the target vehicle speed v ref , pre-establish a dynamic prediction model of front and rear power chains for control through power flow coupling relationship, which is used to predict future running state of the vehicle, and set a multi-objective optimization function considering vehicle speed tracking, SOC maintenance, fuel consumption reduction, power fluctuation reduction and target vehicle speed, and solve the multi-objective optimization function under system constraint conditions to realize coordinated optimization control of power distribution between different power sources of front power and longitudinal control of rear power chain.

[0044] In the above step 1), the method for constructing the fuzzy inference system comprises the following steps:

[0045] 1.1) Divide the typical cycle conditions and the real vehicle running data into a training set and a test set; the real vehicle running data includes historical vehicle speed, accelerator pedal and brake pedal signals;

[0046] 1.2) Set a five-layer structure of the fuzzy inference system;

[0047] 1.3) Train the fuzzy inference system by using the training set, and adjust the antecedent and consequent parameters of the fuzzy inference system.

[0048] In the above step 1.2), the five-layer structure of the fuzzy inference system, as shown in Figure 3 , comprises:

[0049] The first layer: membership function layer, which is used to convert the input signal accurate value into fuzzy language, and divides the universe of discourse of the current vehicle speed and acceleration into three categories of low, medium and high, and adopts a Gaussian membership function to depict the tendency of the state difference in the middle transition;

[0050] The Gaussian membership function g(x; c, σ) is:

[0051]

[0052] In the formula, c and σ are parameters to be adjusted, c represents the center of the membership function, and σ represents the width of the membership function, and these parameters for determining the shape of the membership function are called antecedent parameters. x' represents the membership function input, and x represents the state variable.

[0053] The second layer: fuzzy inference layer, each node of which corresponds to a fuzzy rule, and there are 9 rules in total, and the output is the membership function value ω i of each rule, representing the credibility of each rule:

[0054]

[0055] Wherein, represents the output value of node A j when the input is x1, represents the output value of node B j when the input is x2, j = 1, 2, 3; x1 and x2 represent the first and second inputs respectively.

[0056] The third layer: normalization layer, which normalizes the 9 memberships:

[0057]

[0058] Wherein, wherein, i represents the node number corresponding to the ith rule.

[0059] The fourth layer is a fuzzy rule output layer, each node i of the layer is an adaptive node, and the output of the node i is wherein, {p, r, q} are adjustable parameters of the node, referred to as consequent parameters.

[0060] The fifth layer is a total output layer, and the total output O is obtained by accumulating the outputs of each node of the fourth layer.

[0061]

[0062] In the above step 1.3), after the given antecedent parameters, the output of the fuzzy neural network can be represented as a linear combination of the consequent parameters, so that the antecedent and consequent parameters of the system can be adjusted by combining the hybrid algorithm of the BP algorithm and the least square method.

[0063] In the embodiment, the training set is used to train the fuzzy inference system, the hybrid algorithm of the BP algorithm and the least square method is used to adjust the antecedent and consequent parameters of the fuzzy inference system, and the following steps are included.

[0064] 1.3.1) In the hybrid algorithm, the fourth layer is calculated in the forward stage, and then the least square method is used to identify the consequent parameters.

[0065] 1.3.2) In the backward stage, the error signal is propagated backward, the BP algorithm is used to update the antecedent parameters, and when the antecedent parameters are fixed, the consequent parameters identified by the least square method are optimal. The use of the hybrid algorithm can reduce the search space scale of the BP algorithm, thereby improving the training speed of the fuzzy neural network.

[0066] In the actual application process, the input values of n sets of training data are used in the forward learning process to obtain the parameter values and output values, the calculated values and the training data expected error values are calculated according to the least square method, and the error values are transmitted back to correct the antecedent parameters according to the gradient descent method. In the process of changing these parameters, the membership function graph is constantly modified, so as to achieve the purpose of minimizing the output error in the set cycle.

[0067] In the above step 2), the dynamic prediction model is:

[0068]

[0069] In the formula, represents the differential of the battery SOC, U oc represents the open-circuit voltage of the battery, P d represents the required power, P e represents the engine power, R bR denotes the battery internal resistance, R denotes the fuel consumption rate, Lookup-Table (P e ) denotes the engine power according to the lookup table, v denotes the vehicle speed differential, δ denotes the rotational mass conversion coefficient, m denotes the vehicle mass, r denotes the tire radius, T m T denotes the driving motor torque, i' denotes the transmission ratio, T b T denotes the mechanical brake torque, g denotes the gravity acceleration, f denotes the rolling resistance coefficient, α denotes the slope, ρ denotes the air density, C D C denotes the air resistance coefficient, A denotes the windward area, and v denotes the vehicle speed.

[0070] The state variable x, the control input u, and the measurable disturbance md are respectively:

[0071]

[0072] In the above step 2), the requirements of vehicle speed tracking, SOC maintenance, fuel consumption reduction, and smooth change of component power are comprehensively considered, and a multi-objective optimization function J is established in a prediction time domain N p

[0073]

[0074] In the formula, N p denotes the prediction time domain, ω1-ω6 respectively denote the weight coefficients of the vehicle speed tracking term, the SOC maintenance term, the fuel consumption term, the driving motor driving force term, the mechanical brake force term, and the engine power change term, v ref denotes the target vehicle speed, SOC denotes the SOC of the battery, SOC ref denotes the target SOC, m f denotes the fuel consumption, ΔF m denotes the driving motor force change amount, ΔF brk denotes the mechanical brake force change amount, and ΔP e denotes the engine power change amount.

[0075] In the above step 2), as shown in the formula (2), the solution of the multi-objective optimization function includes the following steps: Figure 4

[0076] 2.1) At the beginning of the time window, the initial value x0 of the state variable is given by feedback of the controlled object (the vehicle model), and the system dynamics in the pre-set prediction time domain N p is predicted by using the dynamic prediction model;

[0077] ​​2.2) The predicted vehicle speed of the vehicle speed prediction model is taken as the vehicle speed target value, the SOC target value is set as a constant value due to the SOC keeping to be realized, the vehicle speed target value and the SOC target value are taken as a reference signal sequence, a control variable sequence in a control time domain N is solved by using a numerical solution algorithm, N m ≤ N m ≤ N p , the control variable outside the control time domain is kept unchanged, so that a multi-target optimization function J reaches a minimum value;

[0078] In the embodiment, the optimization solution process needs to meet the limit value constraint of each physical quantity in addition to meeting the nonlinear dynamic constraint shown by the prediction model:

[0079]

[0080] 2.3) Only the first control variable of the control sequence is applied to the controlled object (the whole vehicle model), and the rest of the control variables are all discarded, and the optimization process is repeated at the next sampling time.

[0081] In summary, the application solves the problem of how to realize the coordination between the power supply and the power demand between the front and rear power chains of the hybrid electric drive vehicle by using the power flow coupling relationship in the prior art, so that the hybrid electric drive vehicle can still work stably under strong transient working conditions (such as sudden acceleration working conditions), and the engine stall and the battery current over-limit conditions can be avoided, and the fuel economy can be improved.

[0082] The application uses the fuzzy inference system to accurately predict the vehicle speed, and the vehicle speed prediction accuracy needs to be guaranteed to be more than 85% during verification; and the dynamic prediction model used is calibrated according to the data of the actual system, and the accuracy is guaranteed to be more than 85%.

[0083] In an embodiment of the application, a front and rear power chain coordination control system for a hybrid electric drive vehicle is provided, which comprises:

[0084] A vehicle speed prediction module, which inputs historical vehicle speed, accelerator pedal and brake pedal signals into a pre-constructed fuzzy inference system to obtain a predicted vehicle speed;

[0085] A coordination control module, which takes the predicted vehicle speed as a target vehicle speed in an optimization target, pre-establishes a dynamic prediction model of the front and rear power chains facing control through a power flow coupling relationship, is used to predict the future running state of the vehicle, sets a multi-target optimization function considering vehicle speed tracking, SOC keeping, fuel consumption reduction, power fluctuation reduction and target vehicle speed, and solves the multi-target optimization function by using a numerical solution method under system constraint conditions, so as to realize the coordinated optimization control of the power distribution between different power sources in the front power and the longitudinal control of the rear power chain.

[0086] The system provided by the embodiment is used for executing the above method embodiments, and the specific process and detailed content are referred to the above embodiments, which will not be repeated here.

[0087] The computing device structure provided in the embodiment of the application can be a terminal, which can include a processor, a communications interface, a memory, a display screen and an input device. The processor, the communications interface and the memory complete mutual communication through a communication bus. The processor is used for providing computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program is executed by the processor to implement a method for coordinated control of front and rear power chains of a hybrid electric drive vehicle. The internal memory provides an environment for running of the operating system and the computer program in the non-volatile storage medium. The communications interface is used for wired or wireless communication with an external terminal. The wireless communication can be realized through WIFI, a management merchant network, near field communication (NFC) or other technologies. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device can be a touch layer overlaid on the display screen, or a key, a trackball or a touchpad arranged on a shell of the computing device, or an external keyboard, a touchpad or a mouse, etc. The processor can call logical instructions in the memory to execute the following method: historical vehicle speed, an accelerator pedal and a brake pedal signal are input into a pre-constructed fuzzy reasoning system to obtain a predicted vehicle speed; the predicted vehicle speed is used as a target vehicle speed in an optimization target, a dynamic prediction model of the front and rear power chains oriented to control is pre-established through a power flow coupling relationship, and is used for predicting a future running state of the vehicle, a multi-target optimization function considering vehicle speed tracking, SOC keeping, fuel consumption reduction, power fluctuation reduction and the target vehicle speed is set, and the multi-target optimization function is solved by using a numerical solution method under system constraint conditions, so that coordinated optimization control of power distribution among different power sources in the front power and longitudinal control of the rear power chain is realized.

[0088] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0089] Those skilled in the art can understand that the structure of the above-mentioned computing device is only part of the structure related to the scheme of the present application, and does not constitute a limitation on the computing device to which the scheme of the present application is applied. The specific computing device can include more or fewer components, or combine certain components, or have a different component arrangement.

[0090] In an embodiment of the present application, a computer program product is provided, which includes a computer program stored on a non-transitory computer readable storage medium, and the computer program includes program instructions, when the program instructions are executed by a computer, the computer can execute the method provided by the above-mentioned method embodiments, for example, including: inputting historical vehicle speed, accelerator pedal and brake pedal signals into a pre-constructed fuzzy reasoning system to obtain a predicted vehicle speed; taking the predicted vehicle speed as a target vehicle speed in an optimization target, pre-establishing a dynamic prediction model of a front and rear power chain oriented to control through a power flow coupling relationship, for predicting the future running state of the vehicle, and setting a multi-objective optimization function considering vehicle speed tracking, SOC maintenance, fuel consumption reduction, power fluctuation reduction and target vehicle speed, and solving the multi-objective optimization function under system constraint conditions to realize coordinated optimization control of power distribution between different power sources in the front power and longitudinal control of the rear power chain.

[0091] In one embodiment of the present application, a non-transitory computer readable storage medium is provided, which stores server instructions, the computer instructions causing a computer to execute the method provided by each of the above embodiments, for example, including: inputting historical vehicle speed, accelerator pedal and brake pedal signals into a pre-constructed fuzzy reasoning system to obtain a predicted vehicle speed; taking the predicted vehicle speed as a target vehicle speed in an optimization target, pre-establishing a dynamic prediction model of a front and rear power chain oriented to control through a power flow coupling relationship, for predicting a future operating state of the vehicle, and setting a multi-objective optimization function considering vehicle speed tracking, SOC maintenance, fuel consumption reduction, power fluctuation reduction and target vehicle speed, and solving the multi-objective optimization function under system constraint conditions to realize coordinated optimization control of power distribution between different power sources in the front power and longitudinal control of the rear power chain.

[0092] The computer readable storage medium provided by the above embodiments has similar implementation principles and technical effects to the method embodiments, and thus will not be described here.

[0093] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device that implements the flow Figure 1 The function of one flow or multiple flows and / or blocks Figure 1 The function of one block or multiple blocks.

[0094] These computer program instructions can also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer readable memory produce a product including instruction devices, which implement the flow Figure 1 The function of one flow or multiple flows and / or blocks Figure 1 The function of one block or multiple blocks.

[0095] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide a process for implementing the flow Figure 1 The function of one flow or multiple flows and / or blocks Figure 1 The function of one block or multiple blocks.

[0096] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features therein can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for coordinating control of front and rear power chains of a hybrid electric drive vehicle, characterized by, The method comprises the following steps: The historical vehicle speed, the accelerator pedal signal and the brake pedal signal are input into a pre-constructed fuzzy inference system to obtain a predicted vehicle speed; The predicted vehicle speed is taken as a target vehicle speed in an optimization target, a dynamic prediction model of a front and rear power chain oriented to control is pre-established through a power flow coupling relationship, used for predicting a future running state of the vehicle, a multi-objective optimization function considering vehicle speed tracking, SOC maintenance, fuel consumption reduction, power fluctuation reduction and the target vehicle speed is set, and the multi-objective optimization function is solved under system constraint conditions by using a numerical solution method, so as to realize coordinated optimization control of power distribution among different power sources in the front power and longitudinal control of the rear power chain. The dynamic prediction model is: Where, represents the differential of battery SOC, Indicates the battery open circuit voltage, Indicates the required power, Indicates engine power, Represents the internal resistance of the battery, Indicates fuel consumption rate, Indicates that according to the engine power table, represents the vehicle speed differential, represents the rotational mass conversion factor, Indicates the vehicle mass, Indicates the tire radius, Indicates the driving motor torque, Indicates the transmission ratio, Represents the mechanical braking torque, represents the acceleration due to gravity, represents the rolling resistance coefficient, Indicates the slope, represents the air density, represents the air resistance coefficient, represents the frontal area, Indicates vehicle speed.

2. The method for coordinated control of front and rear power chains of a hybrid electric drive vehicle as claimed in claim 1, wherein, The construction method of the fuzzy inference system comprises the following steps: Typical cycle conditions and real vehicle running data are divided into a training set and a test set; the real vehicle running data comprises historical vehicle speed, accelerator pedal signal and brake pedal signal; a five-layer structure of the fuzzy inference system is set; the training set is used to train the fuzzy inference system, and the antecedent and consequent parameters of the fuzzy inference system are adjusted.

3. The method for coordinated control of front and rear power chains of a hybrid electric drive vehicle as claimed in claim 2, wherein, The five-layer structure of the fuzzy inference system comprises: a membership function layer, which is used for converting input signal accurate values into fuzzy language, dividing the domain of current vehicle speed and acceleration into three categories of low, medium and high respectively, and using a Gaussian membership function to depict the tendency of both sides in the middle transition state; The fuzzy inference layer, each node of which corresponds to a fuzzy rule, has a total of 9 rules, and the output is the membership function value of each rule , representing the credibility of each rule: ; wherein, represents the output value of the node when the input is , represents the output value of the node when the input is ; , represent the first and second inputs, respectively; a normalization layer, which normalizes nine membership degrees; a fuzzy rule output layer, each node of which is an adaptive node, output ; wherein is an adjustable parameter of the node, referred to as a consequent parameter; denotes the normalized membership function value; a total output layer, which accumulates the output of each node of the fourth layer to obtain a total output.

4. The method for coordinated control of front and rear power chains of a hybrid electric drive vehicle as claimed in claim 2, wherein, The training set is used to train the fuzzy inference system, and the antecedent and consequent parameters of the fuzzy inference system are adjusted by using a hybrid algorithm of a BP algorithm and a least square method, comprising: in the hybrid algorithm, the fourth layer is calculated in the forward stage, and then the least square method is used to identify the consequent parameters; in the reverse stage, error signals are back propagated, the antecedent parameters are updated by using the BP algorithm, and when the antecedent parameters are fixed, the consequent parameters identified by using the least square method are optimal.

5. The method for coordinated control of front and rear power trains of a hybrid electric drive vehicle as claimed in claim 1, wherein, The multi-objective optimization function is: wherein, denotes a prediction time domain, denote a vehicle speed tracking term, an SOC maintaining term, a fuel consumption term, a driving motor driving force term, a mechanical brake force term, and an engine power variation term weight coefficient, respectively, denotes a target vehicle speed, denotes an SOC of a battery, denotes a target SOC, denotes a fuel consumption, denotes a driving motor force variation amount, denotes a mechanical brake force variation amount, denotes an engine power variation amount.

6. The method for coordinated control of front and rear power trains of a hybrid electric drive vehicle as claimed in claim 1 or claim 5 wherein, The solution of the multi-objective optimization function comprises: initializing the state variables at the beginning of the time window by feedback predicting the system dynamics for a predefined prediction horizon using a dynamic prediction model ; The predicted speed of the speed prediction model is used as the speed target value, and the SOC target value is set as a constant value. The speed target value and the SOC target value are combined into a reference signal sequence to solve the control time domain The sequence of control variables within , the control variables outside the control time domain remain unchanged, so that the multi-objective optimization function reaches the minimum; Only the first control variable of the control sequence acts on the controlled object, and the remaining control variables are all discarded, and the optimization process is repeated at the next sampling time.

7. A system for coordinating control of front and rear power chains of a hybrid electric drive vehicle for implementing the method for coordinating control of front and rear power chains of a hybrid electric drive vehicle according to any one of claims 1 to 6, characterized by The method comprises the following steps: A vehicle speed prediction module is configured to input historical vehicle speed, accelerator pedal signal and brake pedal signal into a pre-constructed fuzzy inference system to obtain a predicted vehicle speed; A coordinated control module is configured to take the predicted vehicle speed as a target vehicle speed in an optimization target, pre-establish a dynamic prediction model of a front and rear power chain oriented to control through a power flow coupling relationship, used for predicting a future running state of the vehicle, set a multi-objective optimization function considering vehicle speed tracking, SOC maintenance, fuel consumption reduction, power fluctuation reduction and the target vehicle speed, and solve the multi-objective optimization function under system constraint conditions by using a numerical solution method, so as to realize coordinated optimization control of power distribution among different power sources in the front power and longitudinal control of the rear power chain.

8. A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions that when executed by a computer cause the computer to perform a method of any of claims 1-7. The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods of claims 1-6.

9. A computing device, comprising: The method comprises the following steps: One or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods of claims 1-6.

Images