Multi-power coordinated control method, system, device and medium for hydrogen fuel cell vehicle

Abstract

The present application relates to the technical field of hydrogen fuel cell vehicles, and discloses a method, system, device and medium for coordinated control of multiple power sources of hydrogen fuel cell vehicles, including: obtaining the working condition data of the hydrogen fuel cell vehicle, and determining the typical working condition mode corresponding to the working condition data; determining the initial power allocation value corresponding to each power source according to the typical working condition mode; generating the optimal first power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future; generating the optimal second power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future; selecting the optimal power target allocation scheme under the typical working condition mode according to the optimal first power allocation scheme and the optimal second power allocation scheme, and sending the optimal power target allocation scheme to the vehicle control system to realize coordinated control of multiple power sources. Its beneficial effect is to make rapid and accurate decisions under rapidly changing working conditions.

Description

Technical Field

[0001] The present application relates to the technical field of hydrogen fuel cell vehicles, and in particular to a multi-power coordinated control method, system, device and medium for hydrogen fuel cell vehicles. Background Art

[0002] Hydrogen fuel cell vehicles face complex and changeable working conditions in emergency scenarios, so they must adapt to different environments and needs in real time. The main challenge at present is how to accurately identify the working conditions and quickly match the optimal control strategy, which requires solving problems such as real-time data acquisition, accuracy of pattern recognition algorithms, and response speed. In addition, coordinated control of multiple power systems is a dynamic optimization process that must maximize energy utilization efficiency while ensuring vehicle power performance. This requires the control algorithm to comprehensively consider the characteristics of each power source and make quick and accurate decisions under rapidly changing working conditions. Summary of the invention

[0003] The present application provides a multi-power coordinated control method, system, equipment and medium for a hydrogen fuel cell vehicle, which solves the technical problem of how to accurately identify the operating conditions and quickly match the optimal control strategy, achieving the technical effect of making rapid and accurate decisions under rapidly changing operating conditions.

[0004] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0005] In a first aspect, an embodiment of the present application provides a multi-power coordinated control method for a hydrogen fuel cell vehicle, wherein the multi-power includes a fuel cell, a lithium battery, and a supercapacitor, and the method includes:

[0006] Acquire operating condition data of a hydrogen fuel cell vehicle, and determine a typical operating condition mode corresponding to the operating condition data;

[0007] According to the typical operating mode, determining the initial power allocation value corresponding to each power source;

[0008] Based on the initial power allocation value, the operating condition data and the acquired current load power, generating a first optimal power allocation scheme corresponding to the hydrogen fuel cell vehicle in a future period of time;

[0009] Obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor, and generating a second optimal power allocation plan corresponding to the hydrogen fuel cell vehicle in the future;

[0010] According to the first optimal power allocation scheme and the second optimal power allocation scheme, an optimal power target allocation scheme under the typical operating mode is selected, and the optimal power target allocation scheme is sent to the vehicle control system to achieve coordinated control of multiple power sources.

[0011] The embodiment provides a multi-power coordinated control method for a hydrogen fuel cell vehicle. By acquiring the operating data of the hydrogen fuel cell vehicle, the typical operating mode of the hydrogen fuel cell vehicle under different operating conditions can be accurately identified. This identification provides a basis for the subsequent coordinated optimization method, so that the hydrogen fuel cell vehicle can adapt to various driving conditions in real time. First, according to these typical operating modes, the initial power allocation value of each power source is determined. This is a pre-optimized allocation scheme generated based on the currently identified typical operating mode. Then, using the initial power allocation value as input data, the optimal power first allocation scheme for a period of time in the future is further calculated to achieve the best performance and efficiency. In order to maximize the vehicle power supply capacity and energy utilization efficiency of the hydrogen fuel cell vehicle, the output power of the fuel cell, the charge state of the lithium battery, and the voltage of the supercapacitor are obtained. These data are used to generate the optimal power second allocation scheme for a period of time in the future. Subsequently, the performance of different power configuration schemes is evaluated using simulation tools, and the best power allocation scheme is selected. According to real-time data and simulation results, the power configuration is dynamically adjusted to ensure optimal power output and energy recovery, thereby optimizing the overall performance and efficiency of the vehicle.

[0012] Optionally, determining the initial power allocation value corresponding to each power source according to the typical operating mode includes:

[0013] According to the typical working mode, the initial power allocation ratio corresponding to each power source is obtained by matching from a preset multi-power source control strategy library;

[0014] The initial power allocation value corresponding to each power supply is generated according to the rated power of each power supply and the initial power allocation ratio.

[0015] This embodiment can ensure that the power distribution of each power source meets the actual needs under different typical operating modes by matching the initial power distribution ratio obtained from the multi-power control strategy library, thereby improving the efficiency and performance of the overall hydrogen fuel cell vehicle. By using the specific initial power distribution ratio and the rated power of each power source, the power distribution value of each power source is effectively matched with its capacity, ensuring that the power distribution of different power sources under different typical operating modes is reasonable, optimizing the energy utilization efficiency, and enhancing the responsiveness of the hydrogen fuel cell vehicle.

[0016] Optionally, generating a first optimal power allocation scheme corresponding to the hydrogen fuel cell vehicle in a future period of time based on the initial power allocation value, the operating condition data and the acquired current load power includes:

[0017] Constructing a multi-power coordinated control model; wherein the multi-power coordinated control model includes the dynamic response of the fuel cell, the state of charge constraint of the lithium battery and the power limit of the supercapacitor;

[0018] According to the initial power allocation value, the operating condition data and the acquired current load power, with minimizing energy consumption and maximizing the service life of each power source as the objective function, a rolling horizon control algorithm is used to solve the multi-power source coordinated control model to generate the optimal power first allocation plan corresponding to the hydrogen fuel cell vehicle in the future period of time.

[0019] This embodiment uses a multi-power coordinated control model to comprehensively analyze the dynamic response, state of charge constraints and power limits of fuel cells, lithium batteries and supercapacitors, and optimizes the power distribution of each power source. This ensures that while meeting load requirements, energy consumption is minimized and the service life of the power source is extended. Through the rolling time domain control algorithm, the model continuously adjusts the power distribution scheme of the power source to achieve optimal performance and efficiency.

[0020] Optionally, the acquiring the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor to generate a second optimal power allocation scheme corresponding to the hydrogen fuel cell vehicle in a future period of time includes:

[0021] Obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor;

[0022] Using a long short-term memory network to extract features of the output power, the state of charge and the voltage to obtain a multi-dimensional feature vector;

[0023] The multidimensional feature vector is input into a preset deep neural network, with maximizing the vehicle power supply performance and vehicle energy utilization efficiency of the hydrogen fuel cell vehicle as the objective function, to generate the optimal second power allocation plan corresponding to the hydrogen fuel cell vehicle in the future period of time.

[0024] First, this embodiment can monitor the state of the power system in real time by obtaining the output power of the fuel cell, the charge state of the lithium battery, and the voltage of the supercapacitor. Secondly, by using the long short-term memory network (LSTM) for feature extraction, time series data can be processed and multi-dimensional feature vectors representing the vehicle state can be extracted. Finally, these feature vectors are input into the deep neural network (DNN) to maximize the power supply capacity and energy utilization efficiency of the hydrogen fuel cell vehicle, thereby generating an optimized power allocation plan. This method can significantly improve the performance and energy efficiency of the power system and ensure the optimal operating state of the hydrogen fuel cell vehicle in the future.

[0025] Optionally, selecting an optimal power target allocation scheme under the typical operating mode according to the first optimal power allocation scheme and the second optimal power allocation scheme includes:

[0026] According to the first optimal power allocation scheme, the whole vehicle power supply capacity performance and the whole vehicle energy utilization efficiency under the typical operating mode are simulated by using simulation software to obtain the first whole vehicle power supply capacity performance and the first whole vehicle energy utilization efficiency corresponding to the first optimal power allocation scheme;

[0027] According to the second optimal power allocation scheme, the whole vehicle power supply capacity performance and the whole vehicle energy utilization efficiency under the typical operating mode are simulated by using simulation software to obtain the second whole vehicle power supply capacity performance and the second whole vehicle energy utilization efficiency corresponding to the second optimal power allocation scheme;

[0028] Performing a weighted summation of the first vehicle power supply capacity performance and the first vehicle energy utilization efficiency to obtain a first vehicle performance score corresponding to the first allocation scheme; and performing a weighted summation of the second vehicle power supply capacity performance and the second vehicle energy utilization efficiency to obtain a second vehicle performance score corresponding to the second allocation scheme;

[0029] The first whole vehicle performance score is compared with the second whole vehicle performance score, and the optimal power target allocation scheme is determined according to the comparison result.

[0030] This embodiment simulates two different power allocation schemes (the first and the second) under typical operating modes, and can obtain specific performance data of the two schemes in terms of power supply capacity and energy utilization efficiency of hydrogen fuel cell vehicles. The performance of each scheme under actual operating conditions can be understood in detail. The hydrogen fuel cell vehicle performance score of each scheme is calculated by weighted summation, which will comprehensively consider the two important indicators of power supply capacity and energy utilization efficiency. This scoring mechanism can quantify the overall performance of each scheme, which is convenient for subsequent comparative analysis. Comparing the performance scores of the two schemes can objectively evaluate which scheme is better in terms of hydrogen fuel cell vehicle performance. This comparison not only improves the accuracy of selecting the optimal scheme, but also ensures that the final selected scheme can achieve the best power supply capacity and energy utilization efficiency in practical applications.

[0031] Optionally, comparing the first whole vehicle performance score with the second whole vehicle performance score, and determining the optimal power target allocation scheme according to the comparison result, includes:

[0032] If the first vehicle performance score is greater than the second vehicle performance score, determining the first optimal power allocation scheme corresponding to the first vehicle performance score as the optimal power target allocation scheme;

[0033] If the second vehicle performance score is greater than the first vehicle performance score, determining the second optimal power allocation scheme corresponding to the second vehicle performance score as the optimal power target allocation scheme;

[0034] If the first vehicle performance score is equal to the first vehicle performance score, the optimal power second allocation plan corresponding to the second vehicle performance score or the optimal power second allocation plan corresponding to the second vehicle performance score is determined as the optimal power target allocation plan.

[0035] This embodiment makes the decision-making process intelligent and transparent, making the selection of power distribution scheme more scientific, and ensuring that the final scheme can effectively improve the performance and energy efficiency of the whole vehicle.

[0036] Optionally, after sending the optimal power target allocation scheme to the vehicle control system, the method further includes:

[0037] Get the current working parameters of each power supply;

[0038] According to the optimal power target allocation scheme and the current operating parameters, a preset PID algorithm is used to determine the adjustment value corresponding to each power supply;

[0039] Each power supply is regulated according to the regulation value.

[0040] This embodiment can obtain the current working status of each power supply in real time, thereby providing accurate basic data for subsequent adjustments. Then, the preset PID algorithm is used to calculate the adjustment value according to the optimal power target allocation plan and the current working parameters, so that the output of each power supply can be accurately adjusted to meet the predetermined target allocation plan. Finally, the power supply is actually adjusted according to the calculated adjustment value to ensure that the optimal power distribution can be maintained during operation, thereby improving the performance and efficiency of the overall hydrogen fuel cell vehicle.

[0041] Optionally, the method further comprises:

[0042] Determine the deviation between the current operating parameters and the optimal power target allocation scheme using an adaptive weighted mean square error algorithm;

[0043] When the deviation is greater than the preset deviation threshold, each power supply continues to be adjusted according to the adjustment value until the deviation is less than the preset deviation threshold, and the adjustment is terminated.

[0044] This embodiment can accurately measure the deviation between the current operating parameters and the optimal power target allocation scheme by adopting an adaptive weighted mean square error algorithm. This method enhances the responsiveness to different deviation situations by adaptively adjusting the weights, thereby improving the accuracy of measurement and evaluation. Based on the measured deviation, the power supply adjustment process is automatically controlled. When the deviation is greater than the preset deviation threshold, the system will continue to adjust until the deviation drops below the deviation threshold. This mechanism ensures that the vehicle can automatically make the necessary adjustments to maintain the optimal state of power distribution. Through continuous adjustment and monitoring until the deviation is within the acceptable range, the reliability of the vehicle under different working conditions is improved.

[0045] Optionally, the method further comprises:

[0046] Generate key indicators of working status corresponding to each power supply according to the current working parameters;

[0047] When the key indicator of the working state exceeds the preset key indicator threshold, an alarm is issued for the staff to perform maintenance and obtain maintenance data;

[0048] The remaining life of each power supply is generated according to the current working parameters, the key indicators of the working status and the maintenance data, so that the staff can formulate a maintenance plan.

[0049] This embodiment provides real-time power supply performance data by generating key indicators of the working status of each power supply. These indicators can reflect the operating status of the power supply and help to timely understand the actual working status of the hydrogen fuel cell vehicle. When the key indicators of the working status exceed the preset key indicator threshold, an alarm is issued, allowing staff to quickly identify potential problems and perform repairs. This early warning mechanism helps to reduce downtime and prevent faults from worsening. By analyzing the current operating parameters, key indicators of the working status and maintenance data, the remaining life of each power supply is generated. This enables staff to formulate more accurate maintenance plans based on detailed data, thereby optimizing the allocation of maintenance resources and extending the service life of equipment.

[0050] In a second aspect, an embodiment of the present application provides a multi-power coordinated control system for a hydrogen fuel cell vehicle, wherein the multi-power source includes a fuel cell, a lithium battery, and a supercapacitor, and the system includes:

[0051] An operating mode determination module is used to obtain operating data of a hydrogen fuel cell vehicle and determine a typical operating mode corresponding to the operating data;

[0052] A power allocation value determination module, used to determine the initial power allocation value corresponding to each power source according to the typical operating mode;

[0053] A first allocation scheme determination module, configured to generate an optimal first power allocation scheme corresponding to the hydrogen fuel cell vehicle within a future period of time based on the initial power allocation value, the operating condition data and the acquired current load power;

[0054] A second allocation scheme determination module is used to obtain the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor, and generate an optimal second power allocation scheme corresponding to the hydrogen fuel cell vehicle in a future period of time;

[0055] The target allocation scheme determination module is used to select the optimal power target allocation scheme under the typical operating mode according to the optimal first power allocation scheme and the optimal second power allocation scheme, and send the optimal power target allocation scheme to the vehicle control system to achieve multi-power coordinated control.

[0056] In a third aspect, an embodiment of the present application provides a computer device, including:

[0057] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the multi-power coordinated control method for a hydrogen fuel cell vehicle described above by executing the computer instructions.

[0058] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the multi-power coordination control method for a hydrogen fuel cell vehicle described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 A flowchart of a multi-power coordinated control method for a hydrogen fuel cell vehicle provided in an embodiment of the present application;

[0061] Figure 2 A flowchart of step S103 provided in an embodiment of the present application;

[0062] Figure 3 A flowchart of step S105 provided in an embodiment of the present application;

[0063] Figure 4A flowchart of step S107 provided in an embodiment of the present application;

[0064] Figure 5 A flowchart of step S109 provided in an embodiment of the present application;

[0065] Figure 6 A flowchart of step S97 provided in an embodiment of the present application;

[0066] Figure 7 The flowchart after step S109 provided for the embodiment of the present application;

[0067] Figure 8 A flowchart after step S205 provided in an embodiment of the present application;

[0068] Fig. 9 Another flowchart after step S205 provided in an embodiment of the present application;

[0069] Fig.10 A block diagram of a multi-power coordinated control system for a hydrogen fuel cell vehicle provided in an embodiment of the present application;

[0070] Fig.11 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0072] According to an embodiment of the present application, an embodiment of a multi-power coordinated control method for a hydrogen fuel cell vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0073] In this embodiment, a multi-power coordinated control method for a hydrogen fuel cell vehicle is provided. Figure 1 A flowchart of a multi-power coordinated control method for a hydrogen fuel cell vehicle provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the multiple power sources include fuel cells, lithium batteries and supercapacitors, and the process includes the following steps:

[0074] Step S101, obtaining operating data of a hydrogen fuel cell vehicle, and determining a typical operating mode corresponding to the operating data.

[0075] Specifically, first, high-precision sensors collect the operating data of hydrogen fuel cell vehicles in real time, including but not limited to time, vehicle speed, rotation speed, acceleration, deceleration, parking time, number of parking times, mileage, temperature, voltage, current, etc. corresponding to each power supply. Feature parameters are extracted from these data, and 10 feature parameters are extracted for each operating mode to obtain a real-time operating characteristic vector. Among them, the real-time operating characteristic vector includes at least running time, mileage, maximum vehicle speed, average vehicle speed, maximum acceleration, maximum deceleration, average acceleration, average deceleration, parking time and number of parking times. Since the operating data is a parameter containing a section of the path, the data obtained in real time cannot truly reflect the driving conditions of the hydrogen fuel cell vehicle. Therefore, the acquired operating data is collected according to time blocks (for example, the time length is 300s), and the operating data obtained in each time block is identified.

[0076] Next, the extracted real-time operating condition feature vector is matched with the operating condition feature vector in the preset typical operating condition pattern library. The typical operating condition pattern library contains 100 typical operating condition patterns, each with 10 operating condition feature vectors. Use a similarity calculation algorithm (such as the cosine similarity algorithm) to match the real-time operating condition feature vector with the operating condition feature vector in the preset typical operating condition pattern library to calculate the similarity. Set a similarity threshold to determine the typical operating condition pattern. If the similarity between the real-time operating condition feature vector and a typical operating condition pattern exceeds this threshold, the current operating condition is considered to belong to the typical operating condition pattern.

[0077] If the similarity between the real-time operating condition feature vector and all typical operating condition patterns does not exceed the threshold, the real-time operating condition feature vector is added to the training sample set. When the number of training samples accumulates to a certain extent (such as 500), a clustering algorithm (such as K-means) is used to mine the operating condition pattern, and the optimal number of clusters k is determined by calculating the silhouette coefficient, that is, for each cluster, the silhouette coefficient is calculated, which measures the compactness of the samples within the cluster and the separation between different clusters. The value range of the silhouette coefficient is [-1,1], and the larger the value, the better the clustering effect. By comparing the silhouette coefficients corresponding to different k values, the k value that maximizes the silhouette coefficient is selected as the optimal number of clusters. According to the clustering results, the typical operating condition pattern library is updated, and the newly discovered typical operating condition pattern is added to the typical operating condition pattern library. For the newly added typical operating condition pattern, the corresponding feature parameters are extracted to construct a new operating condition feature vector. After the typical operating condition pattern library is updated, the similarity between the real-time operating condition feature vector and all typical operating condition patterns in the typical operating condition pattern library is recalculated.

[0078] It should be noted that before the new typical operating mode is officially added to the typical operating mode library and verified, the current operating condition data can be fed back to the staff, who will manually match a suitable typical operating mode based on these data. This ensures that the operating condition data can be properly processed and matched before the typical operating mode library is updated, ensuring real-time and accuracy.

[0079] Step S103: determining the initial power allocation value corresponding to each power source according to the typical operating mode.

[0080] Specifically, according to the typical working mode, the initial power allocation ratio corresponding to each power source is matched from the preset multi-power control strategy library; wherein the power source includes a fuel cell, a lithium battery, and a supercapacitor; according to the rated power and the initial power allocation ratio of each power source, the initial power allocation value corresponding to each power source is generated. For example, if the rated power of the fuel cell is 100kW, the rated power of the lithium battery is 50kW, the rated power of the supercapacitor is 20kW, and the initial power allocation ratio is 6:3:1, then their initial power allocation values ​​are 60kW, 30kW, and 10kW, respectively.

[0081] First, build a multi-power control strategy library and collect historical data under different typical operating modes, such as performance data of fuel cells, lithium batteries, supercapacitors, etc. Set the initial power allocation ratio for each typical operating mode. This ratio can be verified by simulation tools, and the verified initial power allocation ratio is stored in the multi-power control strategy library. Then, obtain the current typical operating mode in real time, find the corresponding initial power allocation ratio from the multi-power control strategy library, and calculate the corresponding initial power allocation value based on the rated power of each power supply.

[0082] Step S105, based on the initial power allocation value, the operating condition data and the acquired current load power, generate the optimal first power allocation plan corresponding to the hydrogen fuel cell vehicle in the future period of time.

[0083] Specifically, the current operating condition data is collected, including but not limited to time, vehicle speed, rotation speed, acceleration, deceleration, parking time, number of stops, mileage, temperature, voltage, current, etc. corresponding to each power source. The current load power is obtained, that is, the current total energy demand of the hydrogen fuel cell vehicle. Combined with the initial power allocation value, linear programming, dynamic programming, model predictive control (MPC), etc. are used to predict the optimal power first allocation plan for hydrogen fuel cell vehicles in the future, including the power output plan of fuel cells, lithium batteries and supercapacitors in the future. The objective function usually includes maximizing the service life of each power source and minimizing energy consumption. The constraints are the maximum power and minimum power output limits of each power source, the SOC limit of the lithium battery, the dynamic response of the fuel cell, the safe temperature range, etc.

[0084] Step S107, obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor, and generating a second optimal power allocation plan corresponding to the hydrogen fuel cell vehicle in the future.

[0085] Specifically, key parameters such as the output power of the fuel cell, the state of charge (SOC) of the lithium battery, and the voltage of the supercapacitor are obtained in real time. Define the objective function, which usually includes the performance indicators of the vehicle's power supply capability (such as maximum power output, response time, etc.) and the vehicle's energy utilization efficiency indicators (such as energy consumption rate, cruising range, etc.). Set the constraints of the optimization problem, including the maximum and minimum output power of the fuel cell, the SOC range of the lithium battery, and the charge and discharge limits of the supercapacitor. Establish a prediction model to predict the optimal second power allocation plan for hydrogen fuel cell vehicles in the future, including the power output plan of fuel cells, lithium batteries, and supercapacitors in the future. Appropriate optimization algorithms can be selected, such as model predictive control (MPC), genetic algorithms, particle swarm optimization, etc., to solve the optimal power allocation problem.

[0086] Step S109, selecting the optimal power target allocation scheme under the typical operating mode according to the optimal first power allocation scheme and the optimal second power allocation scheme, and sending the optimal power target allocation scheme to the vehicle control system to achieve multi-power coordinated control.

[0087] Specifically, simulation software (such as MATLAB / Simulink, CRUISE, etc.) is used to build a simulation model of the whole vehicle, including a fuel cell model, a lithium battery model, and a supercapacitor model. The optimal power first allocation scheme and the optimal power second allocation scheme are used as inputs, and these schemes include the power output of the fuel cell, lithium battery, and supercapacitor. Under the corresponding typical operating mode, the simulation model is run to simulate the operation of the hydrogen fuel cell vehicle under the optimal power first allocation scheme and the optimal power second allocation scheme. The power supply capacity performance of the whole vehicle under each scheme is evaluated, such as maximum power output, response time, acceleration performance, etc. The energy utilization efficiency of the whole vehicle is evaluated, such as energy consumption rate, cruising range, energy recovery efficiency, etc. The performance of different schemes under typical operating modes is compared, and the scheme with the best performance of the power supply capacity and energy utilization efficiency of the whole vehicle is determined as the optimal power target allocation scheme. The selected optimal power target allocation scheme is sent to the vehicle control system and implemented by the controller. The control system adjusts the output of each power supply in real time according to the sent optimal power target allocation scheme to achieve coordinated control of multiple power supplies.

[0088] The embodiment provides a multi-power coordinated control method for a hydrogen fuel cell vehicle. By acquiring the operating data of the hydrogen fuel cell vehicle, the typical operating mode of the hydrogen fuel cell vehicle under different operating conditions can be accurately identified. This identification provides a basis for the subsequent coordinated optimization method, so that the hydrogen fuel cell vehicle can adapt to various driving conditions in real time. First, according to these typical operating modes, the initial power allocation value of each power source is determined. This is a pre-optimized allocation scheme generated based on the currently identified typical operating mode. Then, using the initial power allocation value as input data, the optimal power first allocation scheme for a period of time in the future is further calculated to achieve the best performance and efficiency. In order to maximize the vehicle power supply capacity and energy utilization efficiency of the hydrogen fuel cell vehicle, the output power of the fuel cell, the charge state of the lithium battery, and the voltage of the supercapacitor are obtained. These data are used to generate the optimal power second allocation scheme for a period of time in the future. Subsequently, the performance of different power configuration schemes is evaluated using simulation tools, and the best power allocation scheme is selected. According to real-time data and simulation results, the power configuration is dynamically adjusted to ensure optimal power output and energy recovery, thereby optimizing the overall performance and efficiency of the vehicle.

[0089] Figure 2 The flowchart of step S103 provided in the embodiment of the present application may include the following steps:

[0090] Step S31 : According to a typical operating mode, an initial power allocation ratio corresponding to each power source is obtained by matching from a preset multi-power source control strategy library.

[0091] Specifically, a multi-power control strategy library is pre-established, which contains control strategies under different typical operating modes, that is, the initial power allocation ratio of each power source. These control strategies are based on historical data, expert knowledge and simulation tests. According to the typical operating mode, the control strategy that matches the current typical operating mode is retrieved from the multi-power control strategy library. The control strategy includes the initial power allocation ratio of fuel cells, lithium batteries and supercapacitors. For example, under the typical operating mode of emergency repair charging in intermediate emergency situations, the preset strategy obtained from the multi-power control strategy library is that the initial power allocation ratio of fuel cells, lithium batteries and supercapacitors is 6:3:1.

[0092] Step S33: generating an initial power allocation value corresponding to each power source according to the rated power of each power source and the initial power allocation ratio.

[0093] Specifically, first, you need to know the rated power of each power source. For example, assume that the rated power of the fuel cell is 100kW, the rated power of the lithium battery is 50kW, and the rated power of the supercapacitor is 20kW. Based on the obtained initial power allocation ratio of fuel cell: lithium battery: supercapacitor = 6:3:1, and the rated power of each power source, calculate the initial power allocation value of each power source.

[0094] The calculation method is as follows:

[0095] Fuel cell allocation value = fuel cell rated power × (fuel cell allocation ratio / total ratio) = 100kW × (6 / 10) = 60kW;

[0096] The allocation value of lithium battery = rated power of lithium battery × (lithium battery allocation ratio / total ratio) = 50kW × (3 / 10) = 15kW;

[0097] The allocation value of the supercapacitor = the rated power of the supercapacitor × (supercapacitor allocation ratio / total ratio) = 20kW × (1 / 10) = 2kW.

[0098] and Figure 1 Compared with the embodiment shown in the figure, this embodiment can ensure that the power distribution of each power source meets the actual needs under different typical working modes by matching the initial power distribution ratio obtained from the multi-power control strategy library, thereby improving the efficiency and performance of the overall hydrogen fuel cell vehicle. By using the specific initial power distribution ratio and the rated power of each power source, the power distribution value of each power source is effectively matched with its capacity, ensuring that the power distribution of different power sources under different typical working modes is reasonable, optimizing the utilization efficiency of energy, and enhancing the responsiveness of the hydrogen fuel cell vehicle.

[0099] Figure 3The flowchart of step S105 provided in the embodiment of the present application may include the following steps:

[0100] Step S51, constructing a multi-power coordinated control model; wherein the multi-power coordinated control model includes the dynamic response of the fuel cell, the state of charge constraint of the lithium battery and the power limitation of the supercapacitor.

[0101] Specifically, the dynamic response of a fuel cell can be described by a simplified electrochemical model that takes into account the voltage-current relationship, activation loss, ohmic loss, and concentration loss of the fuel cell. The formula of the dynamic response model can be expressed as: V fc =E oc -η act -η ohm -η conc , where V fc is the output voltage of the fuel cell, E oc is the open circuit voltage, η act is the activation overpotential loss, η ohm is the ohmic overpotential loss, η conc is the concentration overpotential loss.

[0102] The state of charge constraint of lithium batteries is usually based on the ampere-hour integration method, which estimates the SOC by integrating the charge and discharge current of the battery. , where SOC(t) is the current SOC, SOC(t0) is the initial SOC, Q nom is the rated capacitance of the lithium battery, I(t) is the current of the lithium battery at time t, and τ is the integral variable.

[0103] The power limit of supercapacitors needs to consider their maximum charge and discharge power and voltage limit. The power limit can be expressed as: P sc ≤P max , where P sc is the current power of the supercapacitor, P max is the maximum allowable power.

[0104] The multi-power supply coordination control model is obtained by integrating the limitations of all the above power supplies. This model can optimize the power allocation of each power supply according to real-time operating condition data to achieve the best performance and efficiency.

[0105] Step S53, based on the initial power allocation value, operating condition data and the current load power obtained, with minimizing energy consumption and maximizing the service life of each power source as the objective function, a rolling horizon control algorithm is used to solve the multi-power source coordinated control model to generate the optimal first power allocation plan corresponding to the hydrogen fuel cell vehicle in the future period of time.

[0106] Specifically, the objective function aims to minimize the energy consumption and the degradation cost of the power supply over its service life: J = E + λD, where E is the total energy consumption within the prediction time horizon, D is the degradation cost of each power supply, and λ is the weight factor to balance the two objectives.

[0107]

[0108]

[0109] Among them, η fc , η bat , η sc is the efficiency of fuel cells, lithium batteries, and supercapacitors; P fc , P bat , P sc is the initial power distribution value of fuel cell, lithium battery and supercapacitor; D fc (t), D bat (t), D sc (t) are the degradation amounts of the fuel cell, lithium battery, and supercapacitor at time t, respectively, and α, β, and γ are weight factors.

[0110] The degradation of a fuel cell can be estimated by monitoring its performance parameters such as voltage, current and power output over time. A simplified degradation model can be expressed by the following formula: fc =(P fc -P current ) / P fc ; Among them, P current is the current power output.

[0111] The degradation of lithium batteries is usually related to their state of charge (SOC) and the number of cycles. The degradation can be estimated by monitoring the change in battery capacity, internal resistance or open circuit voltage over time. The degradation model of lithium batteries can be expressed as: bat =(Q bat -Q current ) / Q bat ; Among them, Q current is the current capacity.

[0112] The degradation of a supercapacitor is usually related to the number of charge and discharge cycles and temperature. The degradation can be estimated by monitoring the change in its capacity, internal resistance or equivalent series resistance (ESR) over time. The degradation model of a supercapacitor can be expressed as: sc =(Csc-C current ) / C sc Among them, C current is the current capacity.

[0113] Power balance constraint: Ensure that the total power output meets the load demand.fc (t)+P bat (t)+P sc (t) = P load (t); P load is the current load power.

[0114] Power Limiting: Ensure that the output power of each power supply is within its maximum and minimum limits. min,i ≤P i (t)≤P max,i ,∀i∈{fc,bat,sc}.

[0115] SOC Limit: Ensure that the SOC of the lithium battery is between its maximum and minimum limits. min ≤SOC bat (t)≤SOC max .

[0116] An optimization problem is solved at each control step, for example by the MPC algorithm, taking into account the forecast for a period of time in the future starting from the current time point. The goal of the optimization problem is to minimize the objective function within the forecast range while satisfying all constraints and generating the optimal power first allocation plan for hydrogen fuel cell vehicles in the future.

[0117] and Figure 1 Compared with the embodiment shown in the figure, this embodiment comprehensively analyzes the dynamic response, state of charge constraints and power limits of fuel cells, lithium batteries and supercapacitors through a multi-power coordinated control model, and optimizes the power distribution of each power source. This ensures that while meeting the load requirements, energy consumption is minimized and the service life of the power source is extended. Through the rolling time domain control algorithm, the model continuously adjusts the power distribution scheme of the power source to achieve optimal performance and efficiency.

[0118] Figure 4 The flowchart of step S107 provided in the embodiment of the present application may include the following steps:

[0119] Step S71, obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor.

[0120] Step S73, using a long short-term memory network to extract features of the output power, state of charge and voltage to obtain a multi-dimensional feature vector.

[0121] Step S75, input the multidimensional feature vector into a preset deep neural network, with maximizing the vehicle power supply performance and vehicle energy utilization efficiency of the hydrogen fuel cell vehicle as the objective function, and generate the optimal second power allocation plan corresponding to the hydrogen fuel cell vehicle in the future period of time.

[0122] Specifically, the output power of the fuel cell, the state of charge (SOC) of the lithium battery, and the voltage of the supercapacitor are collected in real time through the on-board sensors. The data collection frequency is sampled once every 100 milliseconds. The collected data is input into a three-layer LSTM neural network for feature extraction. The number of hidden layer nodes of the LSTM network is 128, the learning rate is set to 0.01, and the Adam optimization algorithm is used for training. The function of the LSTM network is to process time series data and extract multidimensional feature vectors that can represent the working state of the power system. The multidimensional feature vector (dimension is 256) extracted by LSTM is input into the pre-trained five-layer deep neural network DNN model. The number of nodes in each layer of the DNN model is 512, 256, 128, 64, and 3, respectively, and the activation function uses ReLU.

[0123] The optimization goal of the DNN model is to maximize the power supply performance and energy efficiency of the hydrogen fuel cell vehicle. The DNN model outputs the optimal power allocation plan for fuel cells, lithium batteries and supercapacitors.

[0124] The performance of the vehicle's power supply capacity refers to the ability of the hydrogen fuel cell vehicle's power system to provide electrical energy under specific conditions. It can be comprehensively evaluated by the output power of the fuel cell, the SOC of the lithium battery, and the voltage of the supercapacitor. The vehicle's energy utilization efficiency refers to the efficiency of the vehicle's energy utilization during driving, usually measured by the distance traveled per unit of energy. It can be obtained by calculating the ratio of energy consumption and mileage during actual driving. The calculation formula for energy utilization efficiency can be expressed as: Energy utilization efficiency = mileage / consumed energy, where the consumed energy includes the hydrogen energy consumed by the fuel cell, the electrical energy consumed by the lithium battery, and the energy recovered by the supercapacitor during braking.

[0125] The objective function can be:

[0126]

[0127] Among them, a1, a2, a3 are weight coefficients, which are used to adjust the influence of each parameter on the objective function; δ is the weight coefficient of energy consumption, which is used to reflect the importance of energy utilization efficiency; E total is the total energy consumption of the vehicle within the prediction time range.

[0128] and Figure 1Compared with the embodiment shown in the figure, this embodiment firstly, by obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor, the state of the power system can be monitored in real time. Secondly, by using the long short-term memory network (LSTM) for feature extraction, the time series data can be processed and a multi-dimensional feature vector representing the vehicle state can be extracted. Finally, these feature vectors are input into the deep neural network (DNN) to maximize the power supply capacity and energy utilization efficiency of the hydrogen fuel cell vehicle, thereby generating an optimized power allocation plan. This method can significantly improve the performance and energy efficiency of the power system and ensure the optimal operating state of the hydrogen fuel cell vehicle in the future.

[0129] Figure 5 The flowchart of step S109 provided in the embodiment of the present application may include the following steps:

[0130] Step S91, according to the optimal power first allocation scheme, use simulation software to simulate the vehicle power supply capacity performance and vehicle energy utilization efficiency under a typical operating mode, and obtain the first vehicle power supply capacity performance and the first vehicle energy utilization efficiency corresponding to the optimal power first allocation scheme.

[0131] Step S93, according to the optimal second power allocation scheme, use simulation software to simulate the vehicle power supply capacity performance and vehicle energy utilization efficiency under a typical operating mode, and obtain the second vehicle power supply capacity performance and second vehicle energy utilization efficiency corresponding to the optimal second power allocation scheme.

[0132] Step S95, weightedly sum the first vehicle power supply capacity performance and the first vehicle energy utilization efficiency to obtain a first vehicle performance score corresponding to the first allocation scheme; and weightedly sum the second vehicle power supply capacity performance and the second vehicle energy utilization efficiency to obtain a second vehicle performance score corresponding to the second allocation scheme.

[0133] Step S97, comparing the first vehicle performance score with the second vehicle performance score, and determining an optimal power target allocation scheme according to the comparison result.

[0134] Specifically, using simulation software, input the power allocation value of each power supply in the optimal power first allocation scheme. Simulate the vehicle operation under typical working conditions and record the simulation results, including the power supply capacity performance of the whole vehicle and the energy utilization efficiency of the whole vehicle. Similarly, input the power allocation value of each power supply in the optimal power second allocation scheme into the simulation software. Simulate the vehicle operation under the same typical working conditions and record the simulation results. Assign weights to the power supply capacity and energy utilization efficiency of the whole vehicle, α and β respectively. Calculate the performance score of the optimal power first allocation scheme: S1=α·P1 power supply+β·E1 efficiency. Calculate the performance score of the optimal power second allocation scheme: S2=α·P2 power supply+β·E2 efficiency. Compare the two performance scores S1 and S2. If S1>S2, the optimal power first allocation scheme is optimal; otherwise, the optimal power second allocation scheme is optimal.

[0135] and Figure 1 Compared with the embodiment shown in the figure, this embodiment simulates two different power allocation schemes (the first and the second) under typical operating modes, and can obtain specific performance data of the two schemes in terms of power supply capacity and energy utilization efficiency of hydrogen fuel cell vehicles. The performance of each scheme under actual operating conditions can be understood in detail. The hydrogen fuel cell vehicle performance score of each scheme is calculated by weighted summation, which will comprehensively consider the two important indicators of power supply capacity and energy utilization efficiency. This scoring mechanism can quantify the overall performance of each scheme, which is convenient for subsequent comparative analysis. Comparing the performance scores of the two schemes can objectively evaluate which scheme is better in terms of hydrogen fuel cell vehicle performance. This comparison not only improves the accuracy of selecting the optimal scheme, but also ensures that the final selected scheme can achieve the best power supply capacity and energy utilization efficiency in practical applications.

[0136] Figure 6 The flowchart of step S97 provided in the embodiment of the present application may include the following steps:

[0137] Step S971: If the first vehicle performance score is greater than the second vehicle performance score, the first optimal power allocation scheme corresponding to the first vehicle performance score is determined as the optimal power target allocation scheme.

[0138] Step S973: If the second vehicle performance score is greater than the first vehicle performance score, the second optimal power allocation scheme corresponding to the second vehicle performance score is determined as the optimal power target allocation scheme.

[0139] Step S975: If the first vehicle performance score is equal to the first vehicle performance score, the optimal power second allocation scheme corresponding to the second vehicle performance score or the optimal power second allocation scheme corresponding to the second vehicle performance score is determined as the optimal power target allocation scheme.

[0140] Specifically, if the vehicle performance score (S1) corresponding to the optimal power first allocation scheme obtained by simulation software is greater than the vehicle performance score (S2) corresponding to the optimal power second allocation scheme, the optimal power first allocation scheme is selected as the optimal power target allocation scheme. This means that the optimal power first allocation scheme outperforms the optimal power second allocation scheme in terms of power supply capacity and energy utilization efficiency. If the second vehicle performance score (S2) is greater than the first vehicle performance score (S1), the optimal power second allocation scheme is selected as the optimal power target allocation scheme. This shows that in the simulation, the optimal power second allocation scheme performs better than the optimal power first allocation scheme. If the first vehicle performance score (S1) is equal to the second vehicle performance score (S2), the optimal power first allocation scheme or the optimal power second allocation scheme is selected as the optimal power target allocation scheme.

[0141] and Figure 5 Compared with the embodiment shown, this embodiment makes the decision-making process intelligent and transparent, making the selection of power distribution scheme more scientific, and ensuring that the final scheme can effectively improve the performance and energy efficiency of the whole vehicle.

[0142] Figure 7 The flowchart after step S109 provided in the embodiment of the present application may include the following steps:

[0143] Step S201, obtaining current operating parameters of each power source.

[0144] Step S203: According to the optimal power target allocation scheme and the current operating parameters, a preset PID algorithm is used to determine the adjustment value corresponding to each power supply.

[0145] Step S205, adjusting each power source according to the adjustment value.

[0146] Specifically, the on-board controller collects the real-time operating parameters of each power source through sensors and monitoring systems, including but not limited to output power, voltage, current, etc. For example, the output power of the fuel cell is 28kW, the voltage is 360V, and the current is 78A; the output power of the lithium battery is 22kW, the voltage is 320V, and the current is 69A; the output power of the supercapacitor is 9kW, the voltage is 200V, and the current is 45A. The on-board controller receives the optimal power target allocation plan, which may be provided in JSON format and contains the target output power and control parameters. Using the preset PID (proportional-integral-differential) algorithm, the adjustment value of each power source is calculated based on the target output power and current operating parameters. For example, if the target output power of the fuel cell is 30kW and the current output power is 28kW, the adjustment value is 2kW; if the target output power of the lithium battery is 20kW and the current output power is 22kW, the adjustment value is -2kW; if the target output power of the supercapacitor is 10kW and the current output power is 9kW, the adjustment value is 1kW. The on-board controller sends the adjustment value to the controllers of each power source through the CAN bus. The controllers of each power source adjust their output power according to the received regulation value to match the target output power. For example, the controller of the fuel cell may increase the output power from 28kW to 30kW; the controller of the lithium battery may reduce the output power from 22kW to 20kW; the controller of the supercapacitor may increase the output power from 9kW to 10kW.

[0147] and Figure 1 Compared with the embodiment shown in the figure, this embodiment can obtain the current working status of each power supply in real time, thereby providing accurate basic data for subsequent adjustments. Then, the preset PID algorithm is used to calculate the adjustment value according to the optimal power target allocation scheme and the current working parameters, so that the output of each power supply can be accurately adjusted to meet the predetermined target allocation scheme. Finally, the power supply is actually adjusted according to the calculated adjustment value to ensure that the optimal power distribution can be maintained during operation, thereby improving the performance and efficiency of the overall hydrogen fuel cell vehicle.

[0148] Figure 8 A flowchart after step S205 is provided for an embodiment of the present application, and the process may include the following steps:

[0149] Step S301: using an adaptive weighted mean square error algorithm to determine the deviation between the current operating parameters and the optimal power target allocation solution.

[0150] Step S303, when the deviation is greater than the preset deviation threshold, continue to adjust each power supply according to the adjustment value until the deviation is less than the preset deviation threshold, and then end the adjustment.

[0151] Specifically, the mean square error algorithm with adaptive weights is used to calculate the deviation between the current operating parameters and the optimal power target allocation scheme. The adaptability of the weights in the algorithm means that the weights can be dynamically adjusted according to the performance and importance of the power source. The weights are dynamically adjusted according to the importance of the power source and the current operating conditions. For example, if the stability of the fuel cell is critical to the performance of the vehicle, it can be given a higher weight. The square difference between the actual output power and the target output power is calculated, then the average is calculated, and finally multiplied by the corresponding weight. Based on the deviation and weight adjustment value, the on-board controller generates a control command and sends it to the controller of each power source through the CAN bus.

[0152] Deviation is the difference between the actual output power and the target output power. For example, if the target output power of the lithium battery is 20kW and the actual output power is 22kW, the deviation is 2kW. A deviation threshold, such as 1%, is preset to determine whether the output power of the power supply is close enough to the target value. If the deviation exceeds the preset deviation threshold, such as the difference between the actual output power of the lithium battery and the target value exceeds 5%, the adjustment control instruction is triggered. In this example, the lithium battery needs to reduce the output power of 2kW. After receiving the control instruction sent by the on-board controller through the CAN bus, the battery management system (BMS) of the lithium battery adjusts the output power of the lithium battery to the target value (for example, from 22kW to 20kW). The on-board controller monitors the output power of each power supply in real time at a fixed period (such as 20ms) and compares it with the target value. If the deviation value is less than the preset deviation threshold (such as 1%), it is judged that the control process is completed. If the deviation value is greater than the deviation threshold, it enters the next round of iterative adjustment until the output power deviation value of all power supplies is less than 1%.

[0153] and Figure 7 Compared with the embodiment shown, this embodiment can accurately measure the deviation between the current operating parameters and the optimal power target allocation scheme by adopting an adaptive weighted mean square error algorithm. This method enhances the responsiveness to different deviation situations by adaptively adjusting the weights, thereby improving the accuracy of measurement and evaluation. Based on the measured deviation, the power supply adjustment process is automatically controlled. When the deviation is greater than the preset deviation threshold, the system will continue to adjust until the deviation drops below the deviation threshold. This mechanism ensures that the vehicle can automatically make the necessary adjustments to maintain the optimal state of power distribution. Through continuous adjustment and monitoring until the deviation is within the acceptable range, the reliability of the vehicle under different working conditions is improved.

[0154] Fig. 9 Another flowchart after step S205 provided in an embodiment of the present application may include the following steps:

[0155] Step S401, generating key indicators of the working status corresponding to each power supply according to the current working parameters.

[0156] Step S403, when the key indicator of the working status exceeds the preset key indicator threshold, an alarm is issued for the staff to perform maintenance and obtain maintenance data.

[0157] Step S405, generating the remaining life of each power supply according to the current working parameters, key indicators of the working status and maintenance data, so that the staff can formulate a maintenance plan.

[0158] Specifically, the on-board controller collects the real-time working parameters of each power source through sensors and monitoring systems, including but not limited to output power, voltage, current, etc. For example, the output power of the fuel cell is 28kW, the voltage is 360V, and the current is 78A; the output power of the lithium battery is 22kW, the voltage is 320V, and the current is 69A; the output power of the supercapacitor is 9kW, the voltage is 200V, and the current is 45A. The collected data is transmitted to the on-board industrial computer through the CAN bus, and then uploaded to the cloud data center through the 4G network. The cloud data center uses big data platforms such as Hadoop to clean, integrate, and mine and analyze the data to extract key indicators such as voltage stability, current ripple coefficient, and temperature uniformity. The extracted key indicators are compared with the preset key indicator thresholds. For example, if the voltage stability of the lithium battery is less than 95%, the current ripple coefficient is higher than 5%, or the temperature uniformity is less than 90%, it is judged as a fault. Once a fault is detected, the early warning mechanism is automatically triggered, a fault diagnosis report is generated, and the maintenance personnel are notified by SMS and email. After the maintenance personnel perform maintenance, they will upload various maintenance parameters including modulation voltage, cooling and other data to the cloud data center. Combined with current operating parameters, key indicators of operating status and maintenance data, a machine learning algorithm is used to predict the remaining life of each power supply. Based on the remaining life prediction results, a maintenance plan is formulated, including necessary inspections, replacement of parts, cleaning, lubrication and calibration.

[0159] Machine learning algorithms are usually trained based on historical data. In the case of hydrogen fuel cell vehicles, the algorithm uses the collected historical operating data and maintenance records to train the model in order to predict the remaining life of each power source.

[0160] and Figure 7Compared with the embodiment shown in the figure, this embodiment provides real-time power supply performance data by generating key indicators of the working status of each power supply. These indicators can reflect the operating status of the power supply and help to timely understand the actual working status of the hydrogen fuel cell vehicle. When the key indicators of the working status exceed the preset key indicator threshold, an alarm is issued, allowing staff to quickly identify potential problems and perform repairs. This early warning mechanism helps to reduce downtime and prevent faults from worsening. By analyzing the current operating parameters, key indicators of the working status and maintenance data, the remaining life of each power supply is generated. This enables staff to formulate more accurate maintenance plans based on detailed data, thereby optimizing the allocation of maintenance resources and extending the service life of equipment.

[0161] Accordingly, please refer to Fig.10 This is a block diagram of a multi-power coordinated control system for a hydrogen fuel cell vehicle provided in an embodiment of the present application. The multi-power source includes a fuel cell, a lithium battery and a supercapacitor. The system includes:

[0162] The operating mode determination module S111 is used to obtain the operating data of the hydrogen fuel cell vehicle and determine the typical operating mode corresponding to the operating data;

[0163] The power allocation value determination module S333 is used to determine the initial power allocation value corresponding to each power source according to the typical working mode;

[0164] The first allocation scheme determination module S555 is used to generate the optimal first power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future period based on the initial power allocation value, the operating condition data and the acquired current load power;

[0165] The second allocation scheme determination module S777 is used to obtain the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor, and generate the optimal second power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future period;

[0166] The target allocation scheme determination module S999 is used to select the optimal power target allocation scheme under the typical operating mode according to the optimal power first allocation scheme and the optimal power second allocation scheme, and send the optimal power target allocation scheme to the vehicle control system to realize multi-power coordinated control.

[0167] In some embodiments, the power allocation value determination module S333 includes:

[0168] According to the typical working mode, the initial power allocation ratio corresponding to each power source is matched from the preset multi-power source control strategy library;

[0169] According to the rated power of each power supply and the initial power allocation ratio, an initial power allocation value corresponding to each power supply is generated.

[0170] In some embodiments, the first allocation scheme determination module S555 includes:

[0171] Construct a multi-power coordinated control model; the multi-power coordinated control model includes the dynamic response of the fuel cell, the state of charge constraint of the lithium battery and the power limit of the supercapacitor;

[0172] According to the initial power allocation value, operating condition data and the current load power obtained, with minimizing energy consumption and maximizing the service life of each power source as the objective function, the rolling horizon control algorithm is used to solve the multi-power source coordinated control model to generate the optimal power first allocation plan corresponding to the hydrogen fuel cell vehicle in the future.

[0173] In some embodiments, the second allocation scheme determination module S777 includes:

[0174] Obtain the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor;

[0175] The output power, state of charge and voltage are extracted using long short-term memory network to obtain multi-dimensional feature vectors.

[0176] The multi-dimensional feature vector is input into the preset deep neural network, with maximizing the vehicle power supply performance and vehicle energy utilization efficiency of the hydrogen fuel cell vehicle as the objective function, to generate the optimal second power allocation plan corresponding to the hydrogen fuel cell vehicle in the future.

[0177] In some embodiments, the target allocation scheme determination module S999 includes:

[0178] According to the optimal first power allocation scheme, the whole vehicle power supply capacity performance and the whole vehicle energy utilization efficiency under the typical working mode are simulated by using simulation software to obtain the first whole vehicle power supply capacity performance and the first whole vehicle energy utilization efficiency corresponding to the optimal first power allocation scheme;

[0179] According to the optimal second power allocation scheme, the power supply capacity performance and energy utilization efficiency of the whole vehicle under the typical working mode are simulated by using simulation software to obtain the power supply capacity performance and energy utilization efficiency of the second whole vehicle corresponding to the optimal second power allocation scheme;

[0180] The first vehicle power supply capacity performance and the first vehicle energy utilization efficiency are weighted and summed to obtain a first vehicle performance score corresponding to the first allocation scheme; and the second vehicle power supply capacity performance and the second vehicle energy utilization efficiency are weighted and summed to obtain a second vehicle performance score corresponding to the second allocation scheme;

[0181] The first vehicle performance score is compared with the second vehicle performance score, and an optimal power target allocation scheme is determined based on the comparison result.

[0182] In some embodiments, comparing the first vehicle performance score with the second vehicle performance score, and determining the optimal power target allocation scheme according to the comparison result, includes:

[0183] If the first vehicle performance score is greater than the second vehicle performance score, the optimal power first allocation scheme corresponding to the first vehicle performance score is determined as the optimal power target allocation scheme;

[0184] If the second vehicle performance score is greater than the first vehicle performance score, the second optimal power allocation scheme corresponding to the second vehicle performance score is determined as the optimal power target allocation scheme;

[0185] If the first vehicle performance score is equal to the first vehicle performance score, the optimal power second allocation plan corresponding to the second vehicle performance score or the optimal power second allocation plan corresponding to the second vehicle performance score is determined as the optimal power target allocation plan.

[0186] In some embodiments, after the target allocation scheme determination module S999, the system further includes:

[0187] Get the current working parameters of each power supply;

[0188] According to the optimal power target allocation plan and current working parameters, the preset PID algorithm is used to determine the corresponding adjustment value of each power supply;

[0189] Each power supply is regulated according to the regulation value.

[0190] In some embodiments, the system further comprises:

[0191] Adopting adaptive weighted mean square error algorithm to determine the deviation between current working parameters and optimal power target allocation scheme;

[0192] When the deviation is greater than the preset deviation threshold, each power supply continues to be adjusted according to the adjustment value until the deviation is less than the preset deviation threshold, and the adjustment is terminated.

[0193] In some embodiments, the system further comprises:

[0194] Generate key indicators of the working status of each power supply according to the current working parameters;

[0195] When the key indicators of the working status exceed the preset key indicator threshold, an alarm is issued for the staff to carry out maintenance and obtain maintenance data;

[0196] Based on the current working parameters, key indicators of working status and maintenance data, the remaining life of each power supply is generated for staff to formulate maintenance plans.

[0197] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0198] In this embodiment, a multi-power coordination control system of a hydrogen fuel cell vehicle is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0199] See also Fig.11 , Fig.11 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown in FIG. Fig.11 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.11 A processor 10 is taken as an example.

[0200] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0201] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0202] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0203] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0204] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0205] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0206] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

[0207] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0208] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0209] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0210] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0211] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0212] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0213] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0214] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0215] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0216] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A multi-power coordinated control method for a hydrogen fuel cell vehicle, characterized in that: The multiple power sources include a fuel cell, a lithium battery and a supercapacitor, and the method includes: Acquire operating condition data of a hydrogen fuel cell vehicle, and determine a typical operating condition mode corresponding to the operating condition data; According to the typical operating mode, determining the initial power allocation value corresponding to each power source; Based on the initial power allocation value, the operating condition data and the acquired current load power, generating a first optimal power allocation scheme corresponding to the hydrogen fuel cell vehicle in a future period of time; Wherein, the generating of the optimal first power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future period of time based on the initial power allocation value, the operating condition data and the acquired current load power includes: Constructing a multi-power coordinated control model; wherein the multi-power coordinated control model includes the dynamic response of the fuel cell, the state of charge constraint of the lithium battery and the power limit of the supercapacitor; According to the initial power allocation value, the operating condition data and the acquired current load power, the multi-power coordinated control model is solved by using a rolling horizon control algorithm with the objective function of minimizing energy consumption and maximizing the service life of each power source, so as to generate the optimal first power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future period; Obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor, and generating a second optimal power allocation plan corresponding to the hydrogen fuel cell vehicle in the future; The step of obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor to generate the optimal second power allocation plan corresponding to the hydrogen fuel cell vehicle in the future period includes: Obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor; Using a long short-term memory network to extract features of the output power, the state of charge and the voltage to obtain a multi-dimensional feature vector; Input the multidimensional feature vector into a preset deep neural network, and use maximization of the whole vehicle power supply performance and the whole vehicle energy utilization efficiency of the hydrogen fuel cell vehicle as the objective function to generate the second optimal power allocation plan corresponding to the hydrogen fuel cell vehicle in the future period of time; According to the first optimal power allocation scheme and the second optimal power allocation scheme, an optimal power target allocation scheme under the typical operating mode is selected, and the optimal power target allocation scheme is sent to the vehicle control system to realize multi-power coordinated control; The step of selecting the optimal power target allocation scheme under the typical operating mode according to the optimal first power allocation scheme and the optimal second power allocation scheme includes: According to the first optimal power allocation scheme, the whole vehicle power supply capacity performance and the whole vehicle energy utilization efficiency under the typical operating mode are simulated by using simulation software to obtain the first whole vehicle power supply capacity performance and the first whole vehicle energy utilization efficiency corresponding to the first optimal power allocation scheme; According to the second optimal power allocation scheme, the whole vehicle power supply capacity performance and the whole vehicle energy utilization efficiency under the typical working mode are simulated by using simulation software to obtain the second whole vehicle power supply capacity performance and the second whole vehicle energy utilization efficiency corresponding to the second optimal power allocation scheme; Performing a weighted summation of the first vehicle power supply capacity performance and the first vehicle energy utilization efficiency to obtain a first vehicle performance score corresponding to the first allocation scheme; and performing a weighted summation of the second vehicle power supply capacity performance and the second vehicle energy utilization efficiency to obtain a second vehicle performance score corresponding to the second allocation scheme; The first whole vehicle performance score is compared with the second whole vehicle performance score, and the optimal power target allocation scheme is determined according to the comparison result.

2. The method according to claim 1, characterized in that Determining the initial power allocation value corresponding to each power source according to the typical operating mode includes: According to the typical working mode, the initial power allocation ratio corresponding to each power source is obtained by matching from a preset multi-power source control strategy library; The initial power allocation value corresponding to each power supply is generated according to the rated power of each power supply and the initial power allocation ratio.

3. The method according to claim 1, characterized in that: The comparing the first vehicle performance score with the second vehicle performance score, and determining the optimal power target allocation scheme according to the comparison result, includes: If the first vehicle performance score is greater than the second vehicle performance score, determining the first optimal power allocation scheme corresponding to the first vehicle performance score as the optimal power target allocation scheme; If the second vehicle performance score is greater than the first vehicle performance score, determining the second optimal power allocation scheme corresponding to the second vehicle performance score as the optimal power target allocation scheme; If the first vehicle performance score is equal to the first vehicle performance score, the optimal power second allocation plan corresponding to the second vehicle performance score or the optimal power second allocation plan corresponding to the second vehicle performance score is determined as the optimal power target allocation plan.

4. The method according to claim 1, characterized in that: After sending the optimal power target allocation scheme to the vehicle control system, the method further includes: Get the current working parameters of each power supply; According to the optimal power target allocation scheme and the current operating parameters, a preset PID algorithm is used to determine the adjustment value corresponding to each power supply; Each power supply is regulated according to the regulation value.

5. The method according to claim 4, characterized in that The method further comprises: Determine the deviation between the current operating parameters and the optimal power target allocation scheme using an adaptive weighted mean square error algorithm; When the deviation is greater than the preset deviation threshold, each power supply continues to be adjusted according to the adjustment value until the deviation is less than the preset deviation threshold, and the adjustment is terminated.

6. The method according to claim 4, characterized in that The method further comprises: Generate key indicators of working status corresponding to each power supply according to the current working parameters; When the key indicator of the working state exceeds the preset key indicator threshold, an alarm is issued for the staff to perform maintenance and obtain maintenance data; The remaining life of each power supply is generated according to the current working parameters, the key indicators of the working status and the maintenance data, so that the staff can formulate a maintenance plan.

7. A multi-power coordination control system for a hydrogen fuel cell vehicle, characterized in that: The multiple power sources include fuel cells, lithium batteries and supercapacitors, and the system includes: An operating mode determination module is used to obtain operating data of a hydrogen fuel cell vehicle and determine a typical operating mode corresponding to the operating data; A power allocation value determination module, used to determine the initial power allocation value corresponding to each power source according to the typical operating mode; A first allocation scheme determination module, configured to generate an optimal first power allocation scheme corresponding to the hydrogen fuel cell vehicle within a future period of time based on the initial power allocation value, the operating condition data and the acquired current load power; Wherein, the generating of the optimal first power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future period of time based on the initial power allocation value, the operating condition data and the acquired current load power includes: Constructing a multi-power coordinated control model; wherein the multi-power coordinated control model includes the dynamic response of the fuel cell, the state of charge constraint of the lithium battery and the power limit of the supercapacitor; According to the initial power allocation value, the operating condition data and the acquired current load power, the multi-power coordinated control model is solved by using a rolling horizon control algorithm with the objective function of minimizing energy consumption and maximizing the service life of each power source, so as to generate the optimal first power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future period; A second allocation scheme determination module is used to obtain the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor, and generate an optimal second power allocation scheme corresponding to the hydrogen fuel cell vehicle in a future period of time; The step of obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor to generate the optimal second power allocation plan corresponding to the hydrogen fuel cell vehicle in the future period includes: Obtaining the output power of the fuel cell, the state of charge of the lithium battery and the voltage of the supercapacitor; Using a long short-term memory network to extract features of the output power, the state of charge and the voltage to obtain a multi-dimensional feature vector; The multi-dimensional feature vector is input into a preset deep neural network, and the objective function is to maximize the whole vehicle power supply performance and the whole vehicle energy utilization efficiency of the hydrogen fuel cell vehicle, and generate the second optimal power allocation scheme corresponding to the hydrogen fuel cell vehicle in the future period of time; a target allocation scheme determination module is used to select the optimal power target allocation scheme under the typical operating mode according to the first optimal power allocation scheme and the second optimal power allocation scheme, and send the optimal power target allocation scheme to the vehicle control system to realize multi-power coordinated control; The step of selecting the optimal power target allocation scheme under the typical operating mode according to the optimal first power allocation scheme and the optimal second power allocation scheme includes: According to the first optimal power allocation scheme, the whole vehicle power supply capacity performance and the whole vehicle energy utilization efficiency under the typical operating mode are simulated by using simulation software to obtain the first whole vehicle power supply capacity performance and the first whole vehicle energy utilization efficiency corresponding to the first optimal power allocation scheme; According to the second optimal power allocation scheme, the whole vehicle power supply capacity performance and the whole vehicle energy utilization efficiency under the typical working mode are simulated by using simulation software to obtain the second whole vehicle power supply capacity performance and the second whole vehicle energy utilization efficiency corresponding to the second optimal power allocation scheme; Performing a weighted summation of the first vehicle power supply capacity performance and the first vehicle energy utilization efficiency to obtain a first vehicle performance score corresponding to the first allocation scheme; and performing a weighted summation of the second vehicle power supply capacity performance and the second vehicle energy utilization efficiency to obtain a second vehicle performance score corresponding to the second allocation scheme; The first whole vehicle performance score is compared with the second whole vehicle performance score, and the optimal power target allocation scheme is determined according to the comparison result.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the multi-power coordinated control method for a hydrogen fuel cell vehicle according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the multi-power coordinated control method for a hydrogen fuel cell vehicle according to any one of claims 1 to 6.

Images