On-line optimization calibration method, system and equipment for vehicle power system control parameters

Abstract

The embodiment of the present invention provides a method, system and device for online optimization and calibration of vehicle power system control parameters. The method includes triggering a calibration request when the vehicle enters any one of a plurality of driving sections, and the vehicle end uploads the calibration request and the acquired vehicle status information to the cloud platform; the cloud platform updates the vehicle power system model according to the vehicle status information and the pre-stored fuel cell polarization curve data of different aging degrees, predicts the future driving conditions of the vehicle according to the collected road traffic information, obtains the predicted speed of the road ahead, and uses a parallel multi-objective particle swarm algorithm to optimize the control parameters of the vehicle energy management strategy online based on the predicted speed of the road ahead and the updated vehicle power system model, and sends the generated calibration instructions to the vehicle end; the vehicle end receives and executes the calibration instructions to complete the online calibration of the control parameters. The present invention improves the flexibility of the energy management strategy of fuel cell vehicles.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of automobile technology, and in particular to a method, system and device for online optimization and calibration of control parameters of a vehicle power system. Background Art

[0002] Fuel cell vehicles have the characteristics of zero pollution, low noise and high efficiency. However, the working characteristics of fuel cells are relatively weak, and they are usually combined with power batteries to form a hybrid power system to drive fuel cell vehicles on the road.

[0003] The vehicle power system includes the energy conversion and transmission process of the vehicle, among which the energy management strategy is used to optimize the utilization and distribution of vehicle energy. It involves controlling and scheduling the energy used by the vehicle (such as fuel, electricity, etc.) to improve vehicle performance, reduce energy consumption and emissions. For traditional fuel vehicles, the vehicle energy management strategy can include measures such as engine start-stop system, energy recovery braking system and optimized transmission system. For electric vehicles, the vehicle energy management strategy is more critical. It needs to comprehensively consider factors such as battery power management, motor power output, energy recovery and energy consumption of auxiliary equipment. By reasonably controlling the battery charging and discharging process, optimizing the motor power output and vehicle driving mode, the cruising range and performance of electric vehicles can be improved. In the vehicle energy management strategy, the controller is the core device responsible for controlling the operation of various components and systems of the vehicle. The effective control and optimization of the vehicle energy management strategy can be achieved by calibrating the controller parameters.

[0004] For fuel cell vehicles, the fuel cell cost accounts for a large proportion of the vehicle cost, so when calibrating the vehicle controller parameters, it is necessary to focus on the life of the fuel cell and reduce the operating cost of the fuel cell vehicle. Therefore, the energy management control of fuel cell vehicles has a significant impact on reducing the vehicle running cost.

[0005] Among them, the rule-based energy management strategy is widely used in real vehicle controllers. Usually, intelligent optimization algorithms are used to calibrate the parameters of the rule-based control strategy. In actual applications, the rule-based energy management control strategy of the vehicle power system undergoes a large number of calibration tests for different working conditions before leaving the factory. However, during the operation of the vehicle after leaving the factory, the degradation of the fuel cell and the changing traffic scenes have a huge impact on the energy distribution of the power system, resulting in the calibration results before leaving the factory may not be able to adapt to the dynamic changes of internal factors of the vehicle and external traffic factors, and the control parameters need to be recalibrated. In other words, the control strategy with fixed parameters for fuel cell vehicles is difficult to adapt to the changing driving scenes and has poor flexibility. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a method, system and device for online optimization and calibration of vehicle power system control parameters to at least solve the above-mentioned problems.

[0007] According to a first aspect of an embodiment of the present invention, a method for online optimization and calibration of vehicle power system control parameters is provided, comprising: S1, when a vehicle enters any one of a plurality of driving sections, a calibration request is triggered, the vehicle end of the vehicle obtains vehicle status information and uploads the calibration request and the vehicle status information to a cloud platform via a T-box transceiver, wherein the vehicle is a fuel cell vehicle, and the plurality of driving sections are obtained by path planning by the vehicle end; S2, the cloud platform receives the calibration request and the vehicle status information and performs a calibration based on the vehicle status information, pre-stored fuel cells of different aging degrees, The vehicle power system model is updated based on the battery polarization curve data to obtain an updated vehicle power system model; S3, the cloud platform predicts the future driving conditions of the vehicle according to the collected road traffic information to obtain the predicted speed of the road ahead; S4, the cloud platform uses a parallel multi-objective particle swarm algorithm based on the predicted speed of the road ahead and the updated vehicle power system model to perform online optimization on the control parameters of the vehicle energy management strategy, generate calibration instructions and send the calibration instructions to the vehicle end; S5, the vehicle end receives and executes the calibration instructions to complete the online calibration of the control parameters.

[0008] In one implementation, the path planning performed by the vehicle in step S1 includes determining the entire driving path of the vehicle according to the starting point and the end point of the vehicle; and dividing the entire driving path to obtain the multiple driving sections.

[0009] In another implementation, the vehicle status information includes the output voltage data of the fuel cell, the output current data of the fuel cell and the charge state of the power battery, and the road traffic information includes the driving speed, traffic congestion and traffic light status of all vehicles on the road ahead of the vehicle.

[0010] In another implementation, in step S2, the cloud platform receives the calibration request and the vehicle status information and updates the vehicle power system model according to the vehicle status information and pre-stored fuel cell polarization curve data of different aging degrees to obtain an updated vehicle power system model, specifically including: pre-processing the output voltage data of the fuel cell and the output current data of the fuel cell to divide the output voltage data and the output current data into multiple groups of data segments; using the output current data in each group of data segments as state variables, using the output voltage data in each group of data segments and the output voltage corresponding to the pre-stored fuel cell polarization curve data of different aging degrees as action variables, using the cumulative absolute error as the objective function, and selecting the fuel cell polarization curve with the smallest cumulative error to update the vehicle power system model to obtain an updated vehicle power system model.

[0011] In another implementation, in step S3, the cloud platform predicts the future driving condition of the vehicle based on the collected road traffic information to obtain the predicted speed of the road ahead, including: selecting the average speed of all vehicles on the road ahead of the vehicle within a specified time as the average speed of the road ahead of the vehicle; and smoothing the average speed of the road ahead of the vehicle through a low-pass filter to obtain the predicted speed of the road ahead.

[0012] In another implementation, in step S4, the cloud platform uses a parallel multi-objective particle swarm algorithm to perform online optimization on the control parameters of the vehicle energy management strategy based on the predicted road speed ahead and the updated vehicle power system model, generates a calibration instruction and sends the calibration instruction to the vehicle end, including: setting the population particle range and the number of particles in the parallel multi-objective particle swarm algorithm according to the number of calibration parameters and the optimization range data in the calibration request; improving the fitness function of the parallel multi-objective particle swarm algorithm according to the calibration request; taking the predicted road speed ahead as the test condition and the updated vehicle power system model as the optimization object, iteratively searching for particles based on the population particle range, the number of particles and the improved fitness function to obtain the global optimal particle; generating the calibration instruction according to the calibration parameter combination corresponding to the global optimal particle; and sending the calibration instruction to the vehicle end.

[0013] In another implementation, in step S5, the vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters, including: the vehicle end receives the calibration instruction through the T-box transceiver; the T-box transceiver sends the calibration instruction to the ECU controller; the ECU controller executes the calibration instruction to complete the online calibration of the control parameters.

[0014] According to a second aspect of an embodiment of the present invention, there is provided a vehicle power system control parameter online optimization calibration system, comprising a vehicle end and a cloud platform, wherein the vehicle end and the cloud platform are communicatively connected; wherein, when a vehicle enters any one of a plurality of driving sections, a calibration request is triggered, and the vehicle end of the vehicle obtains vehicle status information and uploads the calibration request and the vehicle status information to the cloud platform via a T-box transceiver, wherein the vehicle is a fuel cell vehicle, and the plurality of driving sections are obtained by path planning by the vehicle end; the cloud platform receives the calibration request and the vehicle status information and calculates the calibration request and the vehicle status information according to the vehicle status information; The vehicle power system model is updated based on the information and pre-stored fuel cell polarization curve data of different aging degrees to obtain an updated vehicle power system model; the cloud platform predicts the future driving conditions of the vehicle according to the collected road traffic information to obtain the predicted speed of the road ahead; based on the predicted speed of the road ahead and the updated vehicle power system model, the cloud platform uses a parallel multi-objective particle swarm algorithm to perform online optimization on the control parameters of the vehicle energy management strategy, generates a calibration instruction and sends the calibration instruction to the vehicle end; the vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters.

[0015] According to a third aspect of an embodiment of the present invention, there is provided a device, comprising a processor and a memory storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes the method according to the first aspect.

[0016] According to a fourth aspect of an embodiment of the present invention, there is provided a computer storage medium on which a computer program is stored. When the program is executed by a processor, the method of the first aspect is implemented.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] (1) The present invention takes into account the impact of fuel cell degradation on parameter calibration results. By acquiring vehicle status information, including the output voltage data of the fuel cell, the output current data of the fuel cell and the charge state of the power battery, the vehicle power system model is updated in real time on the cloud platform based on the vehicle status information and the pre-stored fuel cell polarization curve data of different aging degrees. The impact of fuel cell aging on vehicle energy distribution is fully considered, and the energy distribution of the power system can be more accurately controlled during vehicle driving.

[0019] (2) The present invention takes into account the impact of changes in external driving conditions on the energy consumption of fuel cell vehicles, predicts the future driving conditions of the vehicle based on the collected road traffic information, and obtains the predicted speed of the road ahead, that is, the future driving speed of the vehicle. It fully considers the impact of the dynamic changes in the traffic environment in the actual driving field on the energy consumption of fuel cell vehicles, so that the energy management strategy can better adapt to complex driving scenarios during vehicle driving, thereby improving the flexibility of the energy management strategy of fuel cell vehicles.

[0020] (3) The present invention realizes the online calibration of vehicle energy management control parameters with the help of cloud platform and vehicle-side communication, so that the energy management strategy of deterministic rules can adapt to the ever-changing power system and real driving scenarios, effectively improving the economy of fuel cell vehicles and slowing down the aging of fuel cells, thereby reducing the driving cost of fuel cell vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0022] Figure 1 A flowchart of the steps of the on-line optimization and calibration method of the vehicle power system control parameters according to an embodiment of the present invention;

[0023] Figure 2 For Figure 1 A schematic flow chart of an online optimization and calibration method for vehicle power system control parameters corresponding to an embodiment;

[0024] Figure 3 Schematic diagram of the power system structure of a fuel cell vehicle in an embodiment of the present invention;

[0025] Figure 4 It is a membership function diagram of the fuzzy energy management strategy in an embodiment of the present invention;

[0026] Figure 5 The road speed prediction diagram of the fuel cell vehicle in the whole journey by road section in the embodiment of the present invention;

[0027] Figure 6 This is a flow chart of a parallel particle swarm algorithm for online calibration in an embodiment of the present invention;

[0028] Figure 7 This is a particle distribution diagram in the elite pool obtained by online calibration in an embodiment of the present invention;

[0029] Figure 8A comparison diagram of fuel cell power output of a fuel cell vehicle after online optimization in an embodiment of the present invention;

[0030] Fig. 9 This is a comparison diagram of the SOC of the power battery of a fuel cell vehicle after online optimization in an embodiment of the present invention;

[0031] Fig.10 A comparison diagram of hydrogen consumption of a fuel cell vehicle after online optimization in an embodiment of the present invention;

[0032] Fig.11 A schematic diagram of an online optimization and calibration system for control parameters of a vehicle power system according to an embodiment of the present invention;

[0033] Fig.12 FIG. 4 is a schematic structural diagram of a device according to another embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to have a clearer understanding of the technical features, purposes and effects of the embodiments of the present application, the specific implementation methods of the embodiments of the present application are now described with reference to the accompanying drawings.

[0035] In this document, “exemplary” means “serving as an example, instance or illustration”, and any illustration or implementation described in this document as “exemplary” should not be construed as a more preferred or more advantageous technical solution.

[0036] In order to simplify the drawings, only the parts related to the present application are shown in each figure by way of example, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one or more of the parts with the same structure or function are shown by way of example, or only one or more of them are marked.

[0037] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in the field based on the embodiments in the embodiments of the present invention should fall within the scope of protection of the embodiments of the present invention.

[0038] The specific implementation of the embodiment of the present invention is further described below in conjunction with the accompanying drawings of the embodiment of the present invention.

[0039] See also Figure 1 A flowchart of the steps of the on-line optimization calibration method for vehicle power system control parameters according to an embodiment of the present invention, Figure 2 For Figure 1 The schematic flow chart of the vehicle power system control parameter online optimization calibration method corresponding to the embodiment, combined with Figure 1 , Figure 2 , this embodiment mainly includes the following steps:

[0040] S1. When a vehicle enters any one of a plurality of driving sections, a calibration request is triggered, and the vehicle end of the vehicle obtains vehicle status information and uploads the calibration request and the vehicle status information to a cloud platform through a T-box transceiver, wherein the vehicle is a fuel cell vehicle, and the plurality of driving sections are obtained by path planning by the vehicle end;

[0041] S2, the cloud platform receives the calibration request and the vehicle status information and updates the vehicle power system model according to the vehicle status information and pre-stored fuel cell polarization curve data of different aging degrees to obtain an updated vehicle power system model;

[0042] S3, the cloud platform predicts the future driving conditions of the vehicle according to the collected road traffic information to obtain the predicted speed of the road ahead;

[0043] S4, the cloud platform uses a parallel multi-objective particle swarm algorithm to perform online optimization on the control parameters of the vehicle energy management strategy based on the predicted speed of the road ahead and the updated vehicle power system model, generates a calibration instruction and sends the calibration instruction to the vehicle end;

[0044] S5. The vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters.

[0045] It should be understood that control parameters refer to parameters in the vehicle power system that are controlled by the electronic control unit (ECU), i.e., the vehicle controller, such as hydrogen flow control gain, maximum output power limit, etc. These parameters have an important impact on the performance and fuel economy of the vehicle, and therefore need to be finely adjusted and controlled to achieve the best performance.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] (1) The present invention takes into account the impact of fuel cell degradation on parameter calibration results. By acquiring vehicle status information, including the output voltage data of the fuel cell, the output current data of the fuel cell and the charge state of the power battery, the vehicle power system model is updated in real time on the cloud platform based on the vehicle status information and the pre-stored fuel cell polarization curve data of different aging degrees. The impact of fuel cell aging on vehicle energy distribution is fully considered, and the energy distribution of the power system can be more accurately controlled during vehicle driving.

[0048] (2) The present invention takes into account the impact of changes in external driving conditions on the energy consumption of fuel cell vehicles, predicts the future driving conditions of the vehicle based on the collected road traffic information, and obtains the predicted speed of the road ahead, that is, the future driving speed of the vehicle. It fully considers the impact of the dynamic changes in the traffic environment in the actual driving field on the energy consumption of fuel cell vehicles, so that the energy management strategy can better adapt to complex driving scenarios during vehicle driving, thereby improving the flexibility of the energy management strategy of fuel cell vehicles.

[0049] (3) The present invention realizes the online calibration of vehicle energy management control parameters with the help of cloud platform and vehicle-side communication, so that the energy management strategy of deterministic rules can adapt to the ever-changing power system and real driving scenarios, effectively improving the economy of fuel cell vehicles and slowing down the aging of fuel cells, thereby reducing the driving cost of fuel cell vehicles.

[0050] In the embodiment of the present invention, the energy management control parameters of the power system of the fuel cell vehicle are calibrated online. The power system of the fuel cell vehicle is composed of a fuel cell, a power battery, a motor, a power converter and a hydrogen cylinder. The schematic diagram of the power system structure is shown in FIG. Figure 3 As shown. The chemical energy of hydrogen is converted into electrical energy through the fuel cell, and together with the power battery, it provides driving energy for the motor. The power battery can drive the vehicle in pure electric mode alone, can smooth the power fluctuation of the fuel cell, and can recover braking energy. The fuel cell is turned on and operates in the high-efficiency range according to the SOC state of the power battery, providing driving power and charging the power battery. The vehicle parameters are shown in Table 1:

[0051] Table 1 Other power parameters of the system

[0052]

[0053] The fuel cell vehicle energy management strategy of the present invention adopts a fuzzy control strategy, which is based on the power battery SOC and the vehicle demand power P load As input, the fuel cell power requirement P fc As output, the range of input and output variables is:

[0054]

[0055] The fuzzy set of the input variable SOC of the energy management strategy is {S, M, B}; the input variable P of the energy management strategy is load The fuzzy set is {NB, NM, S, Z, PS, PB}; the input variable P of the energy management strategy fc The fuzzy set is {VS,S,M,B,VB}.

[0056] The membership function of the input and output of fuzzy control is as follows: Figure 4 As shown. The value range of the inflection point parameter of the membership function is set as follows:

[0057]

[0058] The control rules of fuzzy control are set and fuzzy reasoning is performed. The present invention sets the control rules of fuzzy control based on the debugging data of the fuel cell vehicle under the WLTC standard working condition, adopts the "IF-THEN" language driving expression, and a total of 18 fuzzy rules constitute the fuzzy rule table of fuzzy control, as shown in Table 2:

[0059] Table 2 Fuzzy rules table

[0060]

[0061] For a two-dimensional controller, the control rule is specifically expressed as:

[0062] R1: if SOC=S and P load =NB, then P fc =VS;

[0063] R2: if SOC=S and P load =NM, then P fc =S; .......

[0064] R18: if SOC=B and P load =PB, then P fc =B;

[0065] The total fuzzy relationship of the control rules of the entire control system is expressed as:

[0066] R=R1∪R2∪..∪R18.

[0067] The scheme of the present invention is specifically described by the following examples:

[0068] Replay Figure 1 and Figure 2 , this embodiment mainly includes the following steps:

[0069] S1. When a vehicle enters any one of a plurality of driving sections, a calibration request is triggered, and the vehicle end obtains vehicle status information and uploads the calibration request and the vehicle status information to a cloud platform through a T-box transceiver, wherein the vehicle is a fuel cell vehicle, and the plurality of driving sections are obtained by path planning by the vehicle end.

[0070] Optionally, the path planning performed by the vehicle side in step S1 includes determining the entire driving path of the vehicle according to the starting point and the end point of the vehicle; and dividing the entire driving path to obtain the multiple driving sections.

[0071] Optionally, the vehicle status information includes output voltage data of the fuel cell, output current data of the fuel cell and the charge state of the power battery.

[0072] For example, (1) the starting and ending positions of the vehicle trip are set, and the vehicle side uses the intelligent transportation system to complete the vehicle's entire route planning, divide the planned path into Z driving sections, and store the longitude and latitude information of each section. When the vehicle enters the planned section, a calibration request is triggered. The calibration request includes the optimization target and the control parameters to be calibrated.

[0073] (2) The vehicle side collects vehicle status information, which includes the output voltage data of the fuel cell, the output current data of the fuel cell and the state of charge (SOC) of the power battery.

[0074] (3) The vehicle uploads the calibration request and vehicle status information to the cloud platform through the T-box transceiver.

[0075] S2. The cloud platform receives the calibration request and the vehicle status information and updates the vehicle power system model according to the vehicle status information and pre-stored fuel cell polarization curve data of different aging degrees to obtain an updated vehicle power system model.

[0076] Optionally, in step S2, the cloud platform receives the calibration request and the vehicle status information and updates the vehicle power system model according to the vehicle status information and pre-stored fuel cell polarization curve data of different aging degrees to obtain an updated vehicle power system model, specifically including: pre-processing the output voltage data of the fuel cell and the output current data of the fuel cell to divide the output voltage data and the output current data into multiple groups of data segments; using the output current data in each group of data segments as state variables, using the output voltage data in each group of data segments and the output voltage corresponding to the pre-stored fuel cell polarization curve data of different aging degrees as action variables, using the cumulative absolute error as the objective function, and selecting the fuel cell polarization curve with the smallest cumulative error to update the vehicle power system model to obtain an updated vehicle power system model.

[0077] For example: (1) Vehicle status information is collected during vehicle driving. Due to interference in data collection and network communication, the collected raw data will include some bad data. The cloud platform removes or interpolates abnormal data fragments such as missing data or long-term parking, and performs noise reduction on the data;

[0078] (2) The voltage and current data of the fuel cell operation are divided into m data segments according to a certain time period. At the same time, considering the change of the working life of the fuel cell, the cloud platform pre-stores the polarization curve data of the fuel cell under different degradation conditions;

[0079] (3) Taking the fuel cell current I1 as the state variable, V2 is obtained by interpolating the fuel cell polarization curve pre-stored on the cloud platform. The absolute error between V1 and V2 is calculated for each data segment, with the goal of minimizing the cumulative error of m data segments, and finding J error The vehicle power system model is updated based on the polarization curve corresponding to the minimum value to obtain an updated vehicle power system model.

[0080]

[0081] As another example: (1) the cloud platform pre-processes the output voltage data and the output current data of the fuel cell in the vehicle status information uploaded by the vehicle end, wherein the output voltage data V real The output current data of the fuel cell is divided into L groups of data segments.

[0082] Due to interference between data collection and network communication, the vehicle status information uploaded by the vehicle side will include some bad data. The cloud platform can remove or interpolate the abnormal data fragments such as missing or long-term parking in the output voltage data and output current data of the fuel cell in the vehicle status information uploaded by the vehicle side, and perform pre-processing such as noise reduction, and then convert the output voltage data V real The output current data of the fuel cell is divided into L groups of data segments.

[0083] (2) The output current data of the fuel cell of each data segment is used as input, and the corresponding voltage output V is obtained by interpolating the polarization curves of fuel cells with different aging degrees pre-stored on the cloud platform. test , calculate the difference voltage V of the polarization curve of each group of fuel cells with different aging degrees test With V real The absolute error of L groups of fragments is calculated and sorted to obtain the result with the minimum cumulative error.

[0084] (3) The polarization curve with the smallest cumulative error is used to update the stack module of the fuel cell model. At the same time, the initial SOC of the power battery model is updated to the SOC of the current vehicle, so as to obtain a power system model that adapts to the actual state of the vehicle.

[0085] S3. The cloud platform predicts the future driving conditions of the vehicle based on the collected road traffic information to obtain a predicted speed on the road ahead.

[0086] Optionally, in step S3, the cloud platform predicts the future driving condition of the vehicle based on the collected road traffic information to obtain a predicted speed of the road ahead, including: selecting the average speed of all vehicles on the road ahead of the vehicle within a specified time as the average speed of the road ahead of the vehicle; and smoothing the average speed of the road ahead of the vehicle through a low-pass filter to obtain the predicted speed of the road ahead.

[0087] Optionally, the road traffic information includes the driving speeds of all vehicles on the road ahead of the vehicle, traffic congestion conditions and traffic light status.

[0088] For example: (1) The cloud platform collects road traffic information with the help of the intelligent transportation system. The road traffic information includes the driving speed of all vehicles on the road ahead of the vehicle, traffic congestion and traffic light status.

[0089] Road traffic information may also include information such as travel time and vehicle location;

[0090] (2) Select the average speed of all vehicles passing on the road ahead within a specified time as the average speed of the road section, and the expression for the average speed in the road section can be obtained:

[0091]

[0092] In the formula, v i is the speed of the i-th vehicle passing through the road section, and N is the total number of vehicles passing through the section during this time period.

[0093] Combining the above formula (2) with the speed information of the vehicle on the road, the predicted speed of the road ahead is obtained after calculation and smoothing, and the prediction of the vehicle's future driving condition is completed.

[0094] As another example: (1) Based on the location of the calibration request uploaded by the vehicle, the speeds of all vehicles passing through the road section ahead of the target vehicle within a specified time are collected, and the speeds of these vehicles are expressed as V = [v1, v2, ... v k ].

[0095] (2) Combine the speed obtained in the previous step with the above formula (2) to get the average speed v of these vehicles road , combined with a low-pass filter to v road After smoothing, the average speed of the road section is used as the predicted future driving speed of the vehicle, that is, the predicted speed of the road ahead. The final predicted speed of the road ahead is as follows: Figure 5 shown.

[0096] S4. The cloud platform uses a parallel multi-objective particle swarm algorithm to perform online optimization on the control parameters of the vehicle energy management strategy based on the predicted speed of the road ahead and the updated vehicle power system model, generates a calibration instruction and sends the calibration instruction to the vehicle end.

[0097] Optionally, in step S4, the cloud platform uses a parallel multi-objective particle swarm algorithm to perform online optimization on the control parameters of the vehicle energy management strategy based on the predicted speed of the road ahead and the updated vehicle power system model, generates a calibration instruction and sends the calibration instruction to the vehicle end, including: setting the population particle range and the number of particles in the parallel multi-objective particle swarm algorithm according to the number of calibration parameters and the optimization range data in the calibration request; improving the fitness function of the parallel multi-objective particle swarm algorithm according to the calibration request; taking the predicted speed of the road ahead as the test condition and the updated vehicle power system model as the optimization object, iteratively searching for particles based on the population particle range, the number of particles and the improved fitness function to obtain the global optimal particle; generating the calibration instruction according to the calibration parameter combination corresponding to the global optimal particle; and sending the calibration instruction to the vehicle end.

[0098] It should be understood that the calibration request uploaded by the vehicle to the cloud platform carries calibration parameters and optimized data ranges, where calibration parameters are used to adjust and calibrate control parameters. In other words, calibration parameters are parameters that need to be calibrated in the controller to ensure that the control parameters of the vehicle power system can achieve the best performance and fuel economy. Calibration parameters include low battery trigger threshold, high battery trigger threshold, etc.

[0099] It should also be understood that the optimized data range is to adopt the recommended range of calibration parameters provided by the vehicle manufacturer.

[0100] For example, with the goal of minimizing fuel cell hydrogen consumption, fuel cell degradation cost, and power battery equivalent hydrogen consumption, the cloud platform uses a parallel multi-objective particle swarm algorithm based on MPI to perform online calibration of fuel cell vehicle energy management control parameters. The algorithm flow chart is as follows: Figure 6 As shown, it specifically includes the following steps:

[0101] (1) The cloud platform adopts a parallel multi-objective particle swarm algorithm based on MPI;

[0102] (2) setting initial parameters of the parallel multi-objective particle swarm algorithm, wherein the initial parameters include the size of the group, the size of the sub-group, the size of the elite pool, the learning factor, and the inertia weight;

[0103] (3) The vehicle power system model updated in step S2 is used as the optimization object, and the predicted speed of the road ahead obtained in step S3 is selected as the test condition;

[0104] (4) Taking the minimization of fuel cell hydrogen consumption, fuel cell degradation cost and power battery equivalent hydrogen consumption as the target cost function, the control parameters of the energy management control strategy of the fuel cell vehicle are used as the decision variables of the parallel multi-objective particle swarm algorithm;

[0105] (5) Determine the optimization range of the calibration parameters, initialize all particles, and evenly distribute all particles to K sub-populations to form K child nodes; the sub-populations perform evolutionary calculations on the nodes, including particle velocity and position updates, cost function value estimation, and non-dominant particle updates;

[0106] (6) The master node compares the non-dominated solutions sent by each child node, selects the global optimal particle from the elite pool and sends it to the slave node;

[0107] (7) If the loop end condition is met, the algorithm selects the global optimal particle from the elite pool of the master node as the final parameter calibration result output.

[0108] (8) Finally, a calibration instruction is generated according to the calibration parameter combination corresponding to the global optimal particle, and the calibration instruction is sent to the vehicle end.

[0109] As another example, with the goal of minimizing fuel cell hydrogen consumption, fuel cell degradation cost, and power battery equivalent hydrogen consumption, the cloud platform uses a parallel multi-objective particle swarm algorithm based on MPI to perform online calibration of fuel cell vehicle energy management control parameters. The algorithm flow chart is as follows: Figure 6 As shown, it specifically includes the following steps:

[0110] 1) Setting the initial parameters of the parallel particle swarm algorithm, the initial parameters include the group size M, the sub-population size N, the elite pool size K, the number of iterations I, the inertia weight ω, and the learning factors c1 and c2.

[0111] 2) In order to achieve the flexibility of energy management of fuel cell hybrid vehicles and to improve the economy of the entire vehicle and slow down the aging of power source components, the present invention is based on the various losses of fuel cell hybrid vehicles, specifically including fuel cell hydrogen consumption, fuel cell life attenuation and power battery equivalent hydrogen consumption, and establishes a cost function model according to the various loss cost models.

[0112] (1) The instantaneous hydrogen consumption of a fuel cell is related to its output power, so the fuel cell hydrogen consumption cost can be specifically expressed as:

[0113] cost fc =φ fc ∫m fc

[0114]

[0115] Among them, Φ fc is the unit price of hydrogen, m fc is the instantaneous hydrogen consumption of the fuel cell, P fc is the output power of the fuel cell, η fc For the efficiency of the fuel cell, LHV H2 It is the lower heating value of hydrogen.

[0116] (2) The equivalent hydrogen consumption of the power battery is related to its output power, so the equivalent hydrogen consumption of the power battery can be specifically expressed as:

[0117] cost bat =φ fc ∫m bat

[0118]

[0119] Among them, m bat is the instantaneous equivalent hydrogen consumption of the dynamic battery, P bat is the power battery output power, η bat is the working efficiency of the power battery, η DC / DC is the power efficiency of the DC / DC converter, η fc_avg is the average efficiency of the fuel cell.

[0120] (3) The life decay of the fuel cell is related to the sudden change, startup and shutdown of the fuel cell output power, so the life decay cost of the fuel cell is specifically expressed as:

[0121]

[0122] D fc =k1t1+k2n1+k3t2+k4t3

[0123] Among them, P nfc is the price per kilowatt of the fuel cell stack, D fc is the fuel cell degradation percentage, t1 is the idling time, n1 is the number of starts and stops, t2 is the high-power operation time, t3 is the load mutation time, k1, k2, k3 and k4 are the weight factors corresponding to the four parts.

[0124] 3) The vehicle power system model updated in step S2 is used as the optimization object, and the predicted speed of the road ahead obtained in step S3 is selected as the test condition.

[0125] 4) The present invention sets the inflection point parameter of the membership function of the fuzzy control strategy as the decision variable, and expresses the parameter vector to be optimized as X=[x1,x2,x3,y1,y2,y3,y4,y5,y6,z1,z2,z3,z4,z5]. The range of parameter optimization is limited according to the value range of the inflection point parameter, and the upper limit of the value of the decision variable is [0.35,0.5,0.8,5,10,15,20,40,80,8,12,18,25,36]. The lower limit of the value of the decision variable is [0.2,0.35,0.5,-20,5,10,15,20,40,5,8,12,18,25].

[0126] 5) Initialize the 14 unknown variables according to the number of particles M in the population, and the master node evenly distributes the M particles to the N sub-populations. Each sub-population calculates the fitness value of the particle on the node, and obtains the local optimal particle P of each node by performing non-dominated sorting on the particles in the sub-population and all particles in the sub-population. i (i).

[0127] 6) Send the first S particles of the non-dominated sorting results of each sub-population to the elite pool of the master node. The distribution of particles in the elite pool of the master node is as follows: Figure 7 In order to select the global optimal value of the population particles, the master node adopts normalized calculation at different target scales. The specific calculation method is:

[0128]

[0129] Among them, J i (K) represents the i-th optimization objective, z l and z s Represents the maximum and minimum values ​​of all particles in this target.

[0130] Get the best particle in the elite pool, that is, the global best particle g best , the master node sends the global optimal particle to the child node, and each sub-population updates the position and speed of the particle according to the global optimal value of the population and the local optimal value of the sub-population. The specific update method is:

[0131] v i (i+1)=ωv i (i)+c1r1[P i (i)-x i (i)]+c2r2[g best -x i (i)]

[0132] x i (i+1)=x i (i)+v i(i+1)

[0133] 7) If the number of iterations reaches the set value, the optimal parameter combination corresponding to the global particles sorted in the master node elite pool, i.e., the calibration parameter combination, is output as the optimization result; otherwise, the next generation of calculations is performed.

[0134] Finally, a calibration instruction is generated according to the calibration parameter combination corresponding to the global optimal particle, and the calibration instruction is sent to the vehicle end.

[0135] S5. The vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters.

[0136] Optionally, in step S5, the vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters, including: the vehicle end receives the calibration instruction through the T-box transceiver; the T-box transceiver sends the calibration instruction to the ECU controller; the ECU controller executes the calibration instruction to complete the online calibration of the control parameters.

[0137] The results of the online calibration of the vehicle control parameters according to the embodiment of the present invention are analyzed below.

[0138] See also Figure 8 From the fuel cell output power comparison chart, we can see that the optimized energy management strategy can reduce the fluctuation range of the fuel cell output power, smooth the power output, and effectively slow down the aging process of the fuel cell.

[0139] See also Fig. 9 The comparison chart of power battery SOC shows that the control strategy before optimization did not take into account the change of power battery SOC. Through the multi-objective online calibration of the cloud platform, the power battery SOC was effectively maintained while optimizing the fuel cell power distribution. This shows that with the help of the intelligent transportation system and the cloud platform, the vehicle's road speed prediction and the reasonable distribution of internal power system energy are guaranteed to ensure the stable output of the vehicle's power source components and extend the working life of the fuel cell and power battery.

[0140] See also Fig.10 From the fuel cell hydrogen consumption graph, we can see that not considering the changes in the vehicle's external traffic conditions and the fixed control strategy increases hydrogen consumption. However, by using the cloud platform to achieve online calibration of vehicle control parameters, the hydrogen consumption can be reduced by 13.62%, thereby improving the vehicle's fuel economy.

[0141] In summary, the present invention considers the dynamic changes of external driving conditions during driving and the inability of internal fixed control strategies to adapt to complex driving scenarios, and proposes an online optimization and calibration method for vehicle power system control parameters, which is applied to the energy management control system of fuel cell vehicle power system, and improves the flexibility of fuel cell vehicle energy management strategy, extends the working life of fuel cells and power batteries, and improves the fuel economy of vehicles. The above simulation experiments have verified that the present invention has better optimization results for the application background, and effectively balances the multi-objective optimization problem of power system control.

[0142] See also Fig.11 This is a schematic diagram of a vehicle power system control parameter online optimization and calibration system 200 according to an embodiment of the present invention, which mainly includes:

[0143] The vehicle end 220 and the cloud platform 210 are connected in communication with each other;

[0144] When the vehicle enters any one of the multiple driving sections, a calibration request is triggered, and the vehicle end 220 obtains the vehicle status information and uploads the calibration request and the vehicle status information to the cloud platform 210 through the T-box transceiver, wherein the vehicle is a fuel cell vehicle, and the multiple driving sections are obtained by path planning by the vehicle end;

[0145] The cloud platform 210 receives the calibration request and the vehicle status information and updates the vehicle power system model according to the vehicle status information and pre-stored fuel cell polarization curve data of different aging degrees to obtain an updated vehicle power system model;

[0146] The cloud platform 210 predicts the future driving conditions of the vehicle based on the collected road traffic information and obtains the predicted speed of the road ahead;

[0147] The cloud platform 210 uses a parallel multi-objective particle swarm algorithm to optimize the control parameters of the vehicle energy management strategy online based on the predicted speed of the road ahead and the updated vehicle power system model, generates a calibration instruction, and sends the calibration instruction to the vehicle end 220;

[0148] The vehicle end 220 receives and executes the calibration instruction to complete the online calibration of the control parameters.

[0149] The vehicle power system control parameter online optimization and calibration system 200 of this embodiment is used to implement the corresponding methods in the aforementioned multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0150] In addition, the functional implementation of the vehicle end 220 and the cloud platform 210 in the system of this embodiment can refer to the description of the corresponding parts in the aforementioned method embodiment, and will not be repeated here.

[0151] According to a third aspect of an embodiment of the present invention, a device is provided. Fig.12 , the structural block diagram of the device 1200 that can be used as the server or client of the present application will now be described, which is an example of a hardware device that can be applied to various aspects of the present application. The device is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0152] The device 1200 may include: a processor (processor) 1202 , a communications interface (Communications Interface) 1204 , a memory (memory) 1206 , and a communication bus 1208 .

[0153] The processor 1202, the communication interface 1204, and the memory 1206 communicate with each other via a communication bus 1208. The communication interface 1204 is used to communicate with other devices or servers.

[0154] The processor 1202 is used to execute the program 1210, and specifically can execute the relevant steps in the above method embodiment.

[0155] Specifically, the program 1210 may include program codes, which include computer operation instructions.

[0156] The processor 1202 may be a processor CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0157] The memory 1206 is used to store the program 1210. The memory 1206 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0158] Program 1210 can be specifically used to enable processor 1202 to perform the following operations: S1. When a vehicle enters any one of a plurality of driving sections, a calibration request is triggered, and the vehicle end obtains vehicle status information and uploads the calibration request and the vehicle status information to a cloud platform via a T-box transceiver, wherein the vehicle is a fuel cell vehicle, and the plurality of driving sections are obtained by path planning by the vehicle end; S2. The cloud platform receives the calibration request and the vehicle status information and calculates the calibration request based on the vehicle status information and the pre-stored fuel cell polarization curves of different aging degrees. The vehicle power system model is updated based on the data to obtain an updated vehicle power system model; S3, the cloud platform predicts the future driving conditions of the vehicle according to the collected road traffic information to obtain the predicted speed of the road ahead; S4, the cloud platform uses a parallel multi-objective particle swarm algorithm based on the predicted speed of the road ahead and the updated vehicle power system model to perform online optimization on the control parameters of the vehicle energy management strategy, generate a calibration instruction and send the calibration instruction to the vehicle end; S5, the vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters.

[0159] In addition, the specific implementation of each step in program 1210 can refer to the corresponding description of the corresponding steps and units in the above method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above method embodiment, which will not be repeated here.

[0160] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present invention can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present invention.

[0161] The exemplary embodiments of the present invention further provide a computer storage medium storing a computer program, wherein the computer program implements the methods of the various embodiments of the present invention when executed by a processor.

[0162] The above-described method according to an embodiment of the present invention may be implemented in hardware, firmware, or as software or computer code that may be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code that is originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded over a network and will be stored in a local recording medium, so that the method described herein may be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, processor, or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown herein.

[0163] It should be understood that although this specification is described according to various embodiments, not every embodiment contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

[0164] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.

Claims

1. A method for online optimization and calibration of vehicle power system control parameters, characterized in that: The following steps are involved: S1. When a vehicle enters any one of a plurality of driving sections, a calibration request is triggered, and the vehicle end of the vehicle obtains vehicle status information and uploads the calibration request and the vehicle status information to the cloud platform through a T-box transceiver, wherein the vehicle is a fuel cell vehicle, the plurality of driving sections are obtained by path planning by the vehicle end, and the vehicle status information includes output voltage data of the fuel cell, output current data of the fuel cell and charge state of the power battery; S2, the cloud platform receives the calibration request and the vehicle status information and updates the vehicle power system model according to the vehicle status information and the pre-stored fuel cell polarization curve data of different aging degrees to obtain an updated vehicle power system model, including: pre-processing the output voltage data of the fuel cell and the output current data of the fuel cell to divide the output voltage data and the output current data into multiple groups of data segments; using the output current data in each group of data segments as state variables, using the output voltage data in each group of data segments and the output voltage corresponding to the pre-stored fuel cell polarization curve data of different aging degrees as action variables, using the cumulative absolute error as the objective function, selecting the fuel cell polarization curve with the smallest cumulative error to update the vehicle power system model, and obtaining an updated vehicle power system model; S3, the cloud platform predicts the future driving condition of the vehicle according to the collected road traffic information to obtain the predicted speed of the road ahead, wherein the road traffic information includes the driving speed of all vehicles on the road ahead of the vehicle, traffic congestion conditions and traffic light status; S4. The cloud platform uses a parallel multi-objective particle swarm algorithm to optimize the control parameters of the vehicle energy management strategy online based on the predicted speed of the road ahead and the updated vehicle power system model, generates a calibration instruction and sends the calibration instruction to the vehicle end, including: setting the population particle range and particle number in the parallel multi-objective particle swarm algorithm according to the number of calibration parameters and the optimization range data in the calibration request; improving the fitness function of the parallel multi-objective particle swarm algorithm according to the calibration request; taking the predicted speed of the road ahead as the test condition and the updated vehicle power system model as the optimization object, minimizing the fuel cell hydrogen consumption, fuel cell degradation cost and power battery equivalent hydrogen consumption as the target cost function, and taking the control parameters of the energy management control strategy of the fuel cell vehicle as the decision variables of the parallel multi-objective particle swarm algorithm; iteratively optimizing the particles based on the population particle range, particle number and improved fitness function to obtain the global optimal particle; generating the calibration instruction according to the calibration parameter combination corresponding to the global optimal particle; sending the calibration instruction to the vehicle end; The parallel multi-objective particle swarm algorithm adopted by the cloud platform is a parallel multi-objective particle swarm algorithm based on MPI; Among them, the instantaneous hydrogen consumption of the fuel cell is related to its output power, so the fuel cell hydrogen consumption cost is specifically expressed as: Among them, Φ fc is the unit price of hydrogen, m fc is the instantaneous hydrogen consumption of the fuel cell, P fc is the output power of the fuel cell, η fc For the efficiency of the fuel cell, LHV H2 is the lower heating value of hydrogen; The equivalent hydrogen consumption of the power battery is related to its output power, so the equivalent hydrogen consumption of the power battery can be specifically expressed as: cost bat =φ fc ∫m bat Among them, m bat is the instantaneous equivalent hydrogen consumption of the dynamic battery, P bat is the power battery output power, η bat is the power battery working efficiency, η DC / DC is the power efficiency of the DC / DC converter, η fc_avg is the average working efficiency of the fuel cell; The life decay of the fuel cell is related to the sudden change, startup and shutdown of the fuel cell output power, so the life decay cost of the fuel cell is specifically expressed as: <h2 style=";text-align:left;direction:ltr">D<h2 style=";text-align:left;direction:ltr"> fc <h2 style=";text-align:left;direction:ltr"> =k1t1+k2n1+k3t2+k4t3 Among them, P nfc is the price per kilowatt of the fuel cell stack, D fc is the fuel cell degradation percentage, t1 is the idle operation time, n1 is the number of starts and stops, t2 is the high-power operation time, t3 is the load mutation time, k1, k2, k3 and k4 are the weight factors corresponding to the four parts; The vehicle energy management strategy adopts a fuzzy control strategy, which is based on the power battery SOC and the vehicle demand power P load As input, the fuel cell power requirement P fc As output, the range of input and output variables is: The value range of the inflection point parameter of the membership function is set as follows: The inflection point parameter of the membership function of the fuzzy control strategy is set as the decision variable, and the parameter vector to be optimized is expressed as X=[x1,x2,x3,y1,y2,y3,y4,y5,y6,z1,z2,z3,z4,z5]. The range of parameter optimization is limited according to the value range of the inflection point parameter. The upper limit of the decision variable is [0.35,0.5,0.8,5,10,15,20,40,80,8,12,18,25,36], and the lower limit of the decision variable is [0.2,0.35,0.5,-20,5,10,15,20,40,5,8,12,18,25]; S5. The vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters.

2. The method according to claim 1, characterized in that The vehicle-side path planning in step S1 includes: Determine the entire travel path of the vehicle according to the starting point and the end point of the vehicle; The entire driving route is divided into the plurality of driving sections.

3. The method according to claim 1, characterized in that In step S3, the cloud platform predicts the future driving conditions of the vehicle based on the collected road traffic information to obtain the predicted speed of the road ahead, including: Selecting the average speed of all vehicles on the road ahead of the vehicle within a specified time as the average speed of the road ahead of the vehicle; The average speed of the road ahead of the vehicle is smoothed by a low-pass filter to obtain the predicted speed of the road ahead.

4. The method according to claim 1, characterized in that In step S5, the vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters, including: The vehicle end receives the calibration instruction through the T-box transceiver; The T-box transceiver sends the calibration instruction to the ECU controller; The ECU controller executes the calibration instruction to complete the online calibration of the control parameters.

5. A vehicle power system control parameter online optimization calibration system, characterized in that: include: A vehicle terminal and a cloud platform, wherein the vehicle terminal and the cloud platform are communicatively connected; When the vehicle enters any one of the multiple driving sections, a calibration request is triggered, and the vehicle end obtains vehicle status information and uploads the calibration request and the vehicle status information to the cloud platform through a T-box transceiver, wherein the vehicle is a fuel cell vehicle, the multiple driving sections are obtained by path planning by the vehicle end, and the vehicle status information includes output voltage data of the fuel cell, output current data of the fuel cell and charge state of the power battery; The cloud platform receives the calibration request and the vehicle status information and updates the vehicle power system model according to the vehicle status information and pre-stored fuel cell polarization curve data of different aging degrees to obtain an updated vehicle power system model, including: pre-processing the output voltage data of the fuel cell and the output current data of the fuel cell to divide the output voltage data and the output current data into multiple groups of data segments; using the output current data in each group of data segments as a state variable, using the output voltage data in each group of data segments and the output voltage corresponding to the pre-stored fuel cell polarization curve data of different aging degrees as an action variable, using the cumulative absolute error as an objective function, and selecting the fuel cell polarization curve with the smallest cumulative error to update the vehicle power system model to obtain an updated vehicle power system model; The cloud platform predicts the future driving conditions of the vehicle based on the collected road traffic information to obtain the predicted speed of the road ahead, wherein the road traffic information includes the driving speeds of all vehicles on the road ahead of the vehicle, traffic congestion conditions, and traffic light status; The cloud platform uses a parallel multi-objective particle swarm algorithm to perform online optimization on the control parameters of the vehicle energy management strategy based on the predicted speed of the road ahead and the updated vehicle power system model, generates a calibration instruction and sends the calibration instruction to the vehicle end, including: setting the population particle range and the number of particles in the parallel multi-objective particle swarm algorithm according to the number of calibration parameters and the optimization range data in the calibration request; improving the fitness function of the parallel multi-objective particle swarm algorithm according to the calibration request; taking the predicted speed of the road ahead as the test condition and the updated vehicle power system model as the optimization object, minimizing the fuel cell hydrogen consumption, fuel cell degradation cost and power battery equivalent hydrogen consumption as the target cost function, and taking the control parameters of the energy management control strategy of the fuel cell vehicle as the decision variables of the parallel multi-objective particle swarm algorithm; iteratively optimizing the particles based on the population particle range, the number of particles and the improved fitness function to obtain the global optimal particle; generating the calibration instruction according to the calibration parameter combination corresponding to the global optimal particle; sending the calibration instruction to the vehicle end; The parallel multi-objective particle swarm algorithm adopted by the cloud platform is a parallel multi-objective particle swarm algorithm based on MPI; Among them, the instantaneous hydrogen consumption of the fuel cell is related to its output power, so the fuel cell hydrogen consumption cost is specifically expressed as: cost fc =φ fc ∫m fc Among them, Φ fc is the unit price of hydrogen, m fc is the instantaneous hydrogen consumption of the fuel cell, P fc is the output power of the fuel cell, η fc For the efficiency of the fuel cell, LHV H2 is the lower heating value of hydrogen; The equivalent hydrogen consumption of the power battery is related to its output power, so the equivalent hydrogen consumption of the power battery can be specifically expressed as: cost bat =φ fc ∫m bat Among them, m bat is the instantaneous equivalent hydrogen consumption of the dynamic battery, P bat is the power battery output power, η bat is the power battery working efficiency, η DC / DC is the power efficiency of the DC / DC converter, η fc_avg is the average working efficiency of the fuel cell; The life decay of the fuel cell is related to the sudden change, startup and shutdown of the fuel cell output power, so the life decay cost of the fuel cell is specifically expressed as: <h2 style=";text-align:left;direction:ltr">D<h2 style=";text-align:left;direction:ltr"> fc <h2 style=";text-align:left;direction:ltr"> =k1t1+k2n1+k3t2+k4t3 Among them, P nfc is the price per kilowatt of the fuel cell stack, D fc is the fuel cell degradation percentage, t1 is the idle operation time, n1 is the number of starts and stops, t2 is the high-power operation time, t3 is the load mutation time, k1, k2, k3 and k4 are the weight factors corresponding to the four parts; The vehicle energy management strategy adopts a fuzzy control strategy, which is based on the power battery SOC and the vehicle demand power P load As input, the fuel cell power requirement P fc As output, the range of input and output variables is: The value range of the inflection point parameter of the membership function is set as follows: The inflection point parameter of the membership function of the fuzzy control strategy is set as the decision variable, and the parameter vector to be optimized is expressed as X=[x1,x2,x3,y1,y2,y3,y4,y5,y6,z1,z2,z3,z4,z5]. The range of parameter optimization is limited according to the value range of the inflection point parameter. The upper limit of the decision variable is [0.35,0.5,0.8,5,10,15,20,40,80,8,12,18,25,36], and the lower limit of the decision variable is [0.2,0.35,0.5,-20,5,10,15,20,40,5,8,12,18,25]; The vehicle end receives and executes the calibration instruction to complete the online calibration of the control parameters.

6. A device, characterized in that: include: processor; A memory for storing programs; The program includes instructions, which, when executed by the processor, cause the processor to perform the steps of the method according to any one of claims 1 to 4.

7. A computer storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images