Multi-scale prediction energy management method and system for fuel cell hybrid electric vehicle in vehicle following scene

Abstract

A fuel cell hybrid electric vehicle multi-scale prediction energy management method in a vehicle following scene comprises the steps that management basis data are obtained, and the management basis data comprise preceding vehicle historical motion data, road condition data and current energy data; setting a first constraint condition including a car following safety index and a driving comfort index; inputting the management basis data into a pre-constructed comprehensive planning model to generate an energy management scheme, wherein the comprehensive planning model comprises a vehicle following sub-model, a power demand prediction sub-model, an energy change evaluation sub-model and a planning sub-model; and controlling an energy source of the fuel cell hybrid electric vehicle based on the energy management scheme. When the vehicle action scheme and the energy management scheme are generated, the vehicle following safety and the driving comfort are emphasized, when the energy management scheme is generated, the fuel economy and the energy durability are emphasized, and it is guaranteed that efficient energy management and comfortable driving experience of the fuel cell hybrid electric vehicle can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cell hybrid electric vehicles, and in particular to a multi-scale predictive energy management method and system for fuel cell hybrid electric vehicles in a vehicle-following scenario. Background Art

[0002] As the number of cars on the road continues to increase, the resulting energy crisis, traffic safety, and environmental pollution are becoming increasingly severe. Energy conservation, efficiency, environmental protection, safety, and comfort have become the key themes of today's automotive industry. Fuel cell hybrid vehicles (FCHEVs), equipped with fuel cells and lithium batteries, can alleviate the range issues of pure electric vehicles without the pollution problem, making them an effective means of addressing the energy crisis and environmental pollution. However, balancing vehicle safety, driving comfort, fuel economy, and energy durability remains a major challenge for optimizing the energy control of FCHEVs in following traffic scenarios.

[0003] Chinese patent document "CN113085860A" discloses an energy management method for a fuel cell hybrid vehicle in a following vehicle environment. The method first optimizes the following distance based on the driving status information of the leading vehicle and the controlled vehicle; secondly, based on the obtained optimal following distance, a nonlinear tracking controller is designed using the backstepping method to obtain the vehicle's required power; then, a model of the controlled vehicle's on-board power source is established, where the power source includes a fuel cell and a lithium battery, with the fuel cell as the main energy source and the lithium battery as the auxiliary energy source; finally, the equal consumption minimization method is used to achieve vehicle energy management and complete the following driving of the controlled vehicle.

[0004] Although the above-mentioned technology can optimize the energy management scheme of fuel cell hybrid vehicles to a certain extent, the state it considers is too idealized and is only applicable to fuel cell hybrid vehicles in good health. When the fuel cell and lithium battery of the fuel cell hybrid vehicle age and decay, it is difficult to achieve optimized energy management based on the above-mentioned technology. Summary of the Invention

[0005] In order to address the deficiencies in the prior art, the present invention provides a multi-scale predictive energy management method and system for fuel cell hybrid vehicles in a following vehicle scenario. When generating vehicle action plans and energy management plans, the method emphasizes following vehicle safety and driving comfort. When generating energy management plans, the method emphasizes fuel economy and energy durability, ensuring efficient energy management and a comfortable driving experience for fuel cell hybrid vehicles in following vehicle scenarios.

[0006] To achieve the above objectives, the present invention adopts a specific solution: a multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a vehicle-following scenario, comprising the following steps:

[0007] Obtain management basis data, which includes historical movement data of the preceding vehicle, road condition data, and current energy data;

[0008] Setting a first constraint condition including a following vehicle safety index and a driving comfort index;

[0009] Input the management basis data into the pre-built comprehensive planning model to generate an energy management plan. The comprehensive demand prediction model includes a vehicle following sub-model, a power demand prediction sub-model, an energy change assessment sub-model and a planning sub-model. The vehicle following sub-model is used to predict the movement trend of the preceding vehicle based on the preceding vehicle's historical movement data and road condition data. The power demand prediction sub-model is used to predict the vehicle driving power demand based on the road condition data. The energy change assessment sub-model is used to predict the energy change trend based on the current energy data. The planning sub-model is used to generate a vehicle action plan and an energy management plan through the DP method based on the first constraint, the preceding vehicle's movement trend, the vehicle driving power demand and the energy change trend.

[0010] The energy source of fuel cell hybrid electric vehicles is controlled based on the energy management scheme.

[0011] As a further optimization of the multi-scale predictive energy management method for a fuel cell hybrid vehicle in the above-mentioned following vehicle scenario: the following vehicle sub-model includes a vehicle dynamics unit and a leading vehicle prediction unit, wherein the vehicle dynamics unit is:

[0012]

[0013] Among them, d r is the following distance between the preceding vehicle and the vehicle itself, v d is the speed difference between the preceding vehicle and the vehicle itself, v e is the speed of the vehicle, a e is the acceleration of the vehicle, v p is the speed of the preceding vehicle, a p is the acceleration of the preceding vehicle, x p is the longitudinal position of the preceding vehicle, x e is the longitudinal position of the vehicle, T s is the simulation sampling time, t is the moment;

[0014] The preceding vehicle prediction unit is obtained based on LSTM (Long Short Term Memory) neural network training.

[0015] As a further optimization of the multi-scale predictive energy management method for fuel cell hybrid vehicles in the above-mentioned following vehicle scenario: the road condition data includes road slope and traffic flow density, and the leading vehicle prediction unit is used to periodically predict the leading vehicle movement trend based on the leading vehicle historical movement data and road condition data, with the period set to 10-20s.

[0016] As a further optimization of the multi-scale predictive energy management method for fuel cell hybrid vehicles in the above-mentioned vehicle-following scenario: the energy change evaluation sub-model includes a lithium battery SoC dynamic unit and an energy source aging unit, wherein the lithium battery SoC dynamic unit is used to evaluate the energy change state of the lithium battery in the fuel cell hybrid vehicle, and the energy source aging unit is used to evaluate the aging state of the fuel cell and lithium battery in the fuel cell hybrid vehicle.

[0017] As a further optimization of the multi-scale predictive energy management method for fuel cell hybrid electric vehicles in the above-mentioned vehicle following scenario: the lithium battery SoC dynamic unit is:

[0018]

[0019] Among them, SoC(t+1) is the SoC at the next moment, P bat is the lithium battery power, E b It is the nominal capacity of lithium battery.

[0020] In the energy source aging unit, the aging state of the fuel cell is evaluated by:

[0021]

[0022] Among them, D fc is the fuel cell aging degree, k r is the actual working condition correction coefficient, V1, V2, V3 and V4 are the voltage attenuation values ​​of the fuel cell start-stop cycle, low load operation mode, high load operation mode and load fluctuation mode, respectively. f1, f2 and f3 are the start-stop voltage attenuation coefficient, low power voltage attenuation coefficient and high power voltage attenuation coefficient under the set working condition, respectively. ΔP fc is the fuel cell power wave fluctuation, ΔV is the maximum allowable attenuation value of the fuel cell voltage;

[0023] In the energy source aging unit, the evaluation method of the aging state of the lithium battery is:

[0024]

[0025] Among them, D bat is the aging degree of lithium battery, N cycle The maximum number of charge and discharge cycles for lithium batteries.

[0026] As a further optimization of the multi-scale predictive energy management method for a fuel cell hybrid vehicle in the above-mentioned vehicle following scenario, the first constraint condition is:

[0027]

[0028] in, is the minimum acceleration of the vehicle, is the maximum acceleration of the vehicle, J DS ,J DC are the corresponding cost functions for following safety and driving comfort, and there are:

[0029]

[0030] As a further optimization of the multi-scale predictive energy management method for a fuel cell hybrid vehicle in the above-mentioned vehicle-following scenario, when the planning sub-model generates an energy management plan, a second constraint is generated with the goal of minimizing the equivalent fuel consumption of the entire vehicle and the energy degradation cost. The second constraint is:

[0031] minJ2=[J FE ,J PD ]

[0032]

[0033] Among them, P fc is the fuel cell power, is the minimum output power of the fuel cell, is the maximum output power of the fuel cell, is the minimum output power of lithium battery, is the maximum output power of lithium battery, J FE ,J PD are fuel economy cost and energy source degradation cost respectively, and there are:

[0034]

[0035] Among them, η fc is the fuel cell efficiency, is the lower calorific value of the fuel, λ bat is the lithium battery energy consumption equivalent factor, and Among them, η dis and η chg are the charge and discharge efficiency of lithium batteries respectively.

[0036] As a further optimization of the multi-scale predictive energy management method for a fuel cell hybrid vehicle in the above-mentioned vehicle-following scenario: when the planning sub-model generates an energy management plan, a sequential quadratic programming algorithm is used to solve the second constraint condition to obtain the optimal output power of the fuel cell and the optimal output power of the lithium battery, and the energy management plan is generated based on the optimal output power of the fuel cell and the optimal output power of the lithium battery, and then a control instruction that can act on the drive motor of the fuel cell hybrid vehicle is generated based on the DC / DC converter.

[0037] A multi-scale predictive energy management system for a fuel cell hybrid electric vehicle in a following vehicle scenario is used to implement the above-mentioned multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a following vehicle scenario. The system includes:

[0038] Data collection module, used to obtain management basis data;

[0039] The solution planning module is used to generate energy management solutions based on pre-built comprehensive planning models and management basis data;

[0040] The control output module is used to generate control instructions that can act on the drive motor of the fuel cell hybrid vehicle according to the energy management solution.

[0041] Beneficial effects: The present invention first comprehensively collects management basis data including the historical motion data of the preceding vehicle, road condition data and current energy data, and comprehensively covers all aspects of data that may be involved in the fuel cell hybrid vehicle in the following scenario, so as to accurately characterize the vehicle's motion behavior and energy flow characteristics under following; secondly, a multi-scale comprehensive planning model is established, which can comprehensively plan vehicle action plans and energy management plans based on multiple factors, especially considering the aging and attenuation of fuel cells and lithium batteries, to ensure that the planned vehicle action plans and energy management plans are highly feasible; when generating vehicle action plans and energy management plans, emphasis is placed on following safety and driving comfort, and when generating energy management plans, emphasis is placed on fuel economy and energy durability, to ensure that efficient energy management and comfortable driving experience of fuel cell hybrid vehicles in following scenarios can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of the method of the present invention;

[0043] Figure 2 This is the control principle diagram of a fuel cell hybrid vehicle;

[0044] Figure 3 It is the schematic diagram for generating vehicle action plan and energy management plan. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] like Figures 1 to 3 As shown, a multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a vehicle-following scenario includes S1 to S4.

[0047] S1. Obtain management basis data, which includes historical movement data of the preceding vehicle, road condition data, and current energy data.

[0048] S2. Set the first constraint condition including the following vehicle safety index and the driving comfort index. The first constraint condition is:

[0049]

[0050] in, is the minimum acceleration of the vehicle, is the maximum acceleration of the vehicle, J DS ,J DC are the corresponding cost functions for following safety and driving comfort, and there are:

[0051]

[0052] S3. Input the management basis data into the pre-built comprehensive planning model to generate an energy management plan. The comprehensive demand prediction model includes a vehicle following sub-model, a power demand prediction sub-model, an energy change evaluation sub-model and a planning sub-model. The vehicle following sub-model is used to predict the movement trend of the preceding vehicle based on the preceding vehicle's historical movement data and road condition data. The power demand prediction sub-model is used to predict the vehicle driving power demand based on the road condition data. The energy change evaluation sub-model is used to predict the energy change trend based on the current energy data. The planning sub-model is used to generate the vehicle action plan and the energy management plan based on the first constraint, the preceding vehicle's movement trend, the vehicle driving power demand and the energy change trend through the DP (Dynamic programming) method. The DP method is an existing technology in this field and will not be described in detail here. Among them, the first constraint is used to generate the vehicle action plan. When generating the energy management plan, the second constraint needs to be determined. See below for details.

[0053] More specifically, the following vehicle model includes a vehicle dynamics unit and a leading vehicle prediction unit, where the vehicle dynamics unit is:

[0054]

[0055] Among them, d r is the following distance between the preceding vehicle and the vehicle itself, v d is the speed difference between the preceding vehicle and the vehicle itself, v e is the speed of the vehicle, a e is the acceleration of the vehicle, v p is the speed of the preceding vehicle, a p is the acceleration of the preceding vehicle, x p is the longitudinal position of the preceding vehicle, x e is the longitudinal position of the vehicle, T s is the simulation sampling time, t is the moment;

[0056] The preceding vehicle prediction unit is based on a trained LSTM (Long Short Term Memory) neural network. LSTM neural networks are a mature technology and will not be described in detail here.

[0057] Furthermore, the road condition data includes road slope and traffic flow density. The leading vehicle prediction unit is used to periodically predict the leading vehicle movement trend based on the leading vehicle historical movement data and road condition data, with the period set to 10-20s.

[0058] The energy change assessment sub-model includes a lithium battery SoC dynamic unit and an energy source aging unit. The lithium battery SoC dynamic unit is used to evaluate the energy change state of the lithium battery in a fuel cell hybrid vehicle, and the energy source aging unit is used to evaluate the aging state of the fuel cell and lithium battery in a fuel cell hybrid vehicle.

[0059] The dynamic units of lithium battery SoC are:

[0060]

[0061] Among them, SoC(t+1) is the SoC at the next moment, P bat is the lithium battery power, E b It is the nominal capacity of lithium battery.

[0062] In the energy source aging unit, the evaluation method for the aging state of the fuel cell is:

[0063]

[0064] Among them, D fc is the fuel cell aging degree, k ris the actual working condition correction coefficient, V1, V2, V3 and V4 are the voltage attenuation values ​​of the fuel cell start-stop cycle, low load operation mode, high load operation mode and load fluctuation mode, respectively. f1, f2 and f3 are the start-stop voltage attenuation coefficient, low power voltage attenuation coefficient and high power voltage attenuation coefficient under the set working condition, respectively. ΔP fc is the fuel cell power wave fluctuation, ΔV is the maximum allowable attenuation value of the fuel cell voltage.

[0065] In the energy source aging unit, the evaluation method for the aging state of lithium batteries is:

[0066]

[0067] Among them, D bat is the aging degree of lithium battery, N cycle The maximum number of charge and discharge cycles for lithium batteries.

[0068] When the planning sub-model generates an energy management plan, it generates a second constraint condition with the goal of minimizing the equivalent fuel consumption of the entire vehicle and the energy degradation cost. The second constraint condition is:

[0069] minJ2=[J FE ,J PD ]

[0070]

[0071] Among them, P fc is the fuel cell power, is the minimum output power of the fuel cell, is the maximum output power of the fuel cell, is the minimum output power of lithium battery, is the maximum output power of lithium battery, J FE ,J PD are fuel economy cost and energy source degradation cost respectively, and there are:

[0072]

[0073] Among them, η fc is the fuel cell efficiency, is the lower calorific value of the fuel, λ bat is the lithium battery energy consumption equivalent factor, and Among them, η dis and η chg are the charge and discharge efficiency of lithium batteries respectively.

[0074] Considering the degradation degree of the fuel cell, the output voltage expression of the fuel cell is:

[0075]

[0076] Among them, V fc 、V oc , I fc 、R e , I L are the fuel cell output voltage, open circuit voltage, output current, internal resistance and limiting current respectively, R is, T is the operating temperature, β is, z is the number of electron transfers, and F is the Faraday constant.

[0077] The consumption state of fuel cell fuel is:

[0078]

[0079] in, is the fuel consumption mass, P fc is the fuel cell power, η fc is the fuel cell efficiency, In one embodiment of the present invention, the fuel is hydrogen.

[0080] S4. Controlling the energy source of the fuel cell hybrid electric vehicle based on the energy management plan. Specifically, when the planning sub-model generates the energy management plan, a sequential quadratic programming algorithm is used to solve the second constraint to obtain the optimal output power of the fuel cell and the optimal output power of the lithium battery. The energy management plan is generated based on the optimal output power of the fuel cell and the optimal output power of the lithium battery, and then a control command is generated based on the DC / DC converter that can act on the drive motor of the fuel cell hybrid electric vehicle.

[0081] In order to ensure the accuracy of the comprehensive planning model, the following performance indicators are set. The four indicators are root mean square error, mean absolute error, mean error and coefficient of determination:

[0082]

[0083] The present invention first comprehensively collects management basis data including the historical motion data of the preceding vehicle, road condition data and current energy data, comprehensively covering all aspects of data that may be involved in the fuel cell hybrid vehicle in the following vehicle scenario, so as to accurately characterize the vehicle's motion behavior and energy flow characteristics under following vehicle; secondly, a multi-scale comprehensive planning model is established, which can comprehensively plan vehicle action plans and energy management plans based on multiple factors, especially considering the aging and attenuation of fuel cells and lithium batteries, to ensure that the planned vehicle action plans and energy management plans are highly feasible; when generating vehicle action plans and energy management plans, emphasis is placed on following vehicle safety and driving comfort, and when generating energy management plans, emphasis is placed on fuel economy and energy durability, to ensure that efficient energy management and comfortable driving experience of fuel cell hybrid vehicles in following vehicle scenarios can be achieved.

[0084] The present invention also provides a multi-scale predictive energy management system for fuel cell hybrid vehicles in a following vehicle scenario, which is used to implement the above-mentioned multi-scale predictive energy management method for fuel cell hybrid vehicles in a following vehicle scenario. The system includes a data acquisition module, a solution planning module and a control output module.

[0085] The data acquisition module is used to obtain management basis data. The data acquisition module can use V2V, V2I related wireless communications and vehicle-mounted radar sensors to obtain the historical movement data of the preceding vehicle. This belongs to the existing technology in this field and will not be detailed here.

[0086] The solution planning module is used to generate energy management solutions based on pre-built comprehensive planning models and management basis data.

[0087] The control output module is used to generate control instructions that can act on the drive motor of the fuel cell hybrid vehicle according to the energy management solution.

[0088] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-scale predictive energy management method for fuel cell hybrid electric vehicles in a vehicle-following scenario, characterized in that: The steps include: Obtaining management basis data, which includes historical movement data of the preceding vehicle, road condition data, and current energy data; setting a first constraint condition including a following vehicle safety index and a driving comfort index; Input the management basis data into the pre-built comprehensive planning model to generate an energy management plan. The comprehensive demand prediction model includes a vehicle following sub-model, a power demand prediction sub-model, an energy change assessment sub-model and a planning sub-model. The vehicle following sub-model is used to predict the movement trend of the preceding vehicle based on the preceding vehicle's historical movement data and road condition data. The power demand prediction sub-model is used to predict the vehicle driving power demand based on the road condition data. The energy change assessment sub-model is used to predict the energy change trend based on the current energy data. The planning sub-model is used to generate a vehicle action plan and an energy management plan through the DP method based on the first constraint, the preceding vehicle's movement trend, the vehicle driving power demand and the energy change trend. The energy source of fuel cell hybrid electric vehicles is controlled based on the energy management scheme.

2. The multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a following vehicle scenario according to claim 1, characterized in that: The following vehicle sub-model includes a vehicle dynamics unit and a leading vehicle prediction unit, wherein the vehicle dynamics unit is: Among them, d r is the following distance between the preceding vehicle and the vehicle itself, v d is the speed difference between the preceding vehicle and the vehicle itself, v e is the speed of the vehicle, a e is the acceleration of the vehicle, v p is the speed of the preceding vehicle, a p is the acceleration of the preceding vehicle, x p is the longitudinal position of the preceding vehicle, x e is the longitudinal position of the vehicle, T s is the simulation sampling time, t is the moment; The preceding vehicle prediction unit is obtained based on LSTM (Long Short Term Memory) neural network training.

3. The multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a following vehicle scenario according to claim 2, characterized in that: The road condition data includes road slope and traffic flow density. The preceding vehicle prediction unit is used to periodically predict the preceding vehicle movement trend based on the preceding vehicle historical movement data and road condition data, with the period being set to 10-20s.

4. The multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a following vehicle scenario according to claim 1, characterized in that: The energy change assessment sub-model includes a lithium battery SoC dynamic unit and an energy source aging unit, wherein the lithium battery SoC dynamic unit is used to evaluate the energy change state of the lithium battery in the fuel cell hybrid vehicle, and the energy source aging unit is used to evaluate the aging state of the fuel cell and lithium battery in the fuel cell hybrid vehicle.

5. The multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a following vehicle scenario according to claim 4, characterized in that: The lithium battery SoC dynamic unit is: Among them, SoC(t+1) is the SoC at the next moment, P bat is the lithium battery power, E b It is the nominal capacity of lithium battery.

6. The multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a following vehicle scenario according to claim 4, characterized in that: In the energy source aging unit, the aging state of the fuel cell is evaluated by: Among them, D fc is the fuel cell aging degree, k r is the actual working condition correction coefficient, V1, V2, V3 and V4 are the voltage attenuation values ​​of the fuel cell start-stop cycle, low load operation mode, high load operation mode and load fluctuation mode, respectively. f1, f2 and f3 are the start-stop voltage attenuation coefficient, low power voltage attenuation coefficient and high power voltage attenuation coefficient under the set working condition, respectively. ΔP fc is the fuel cell power wave fluctuation, ΔV is the maximum allowable attenuation value of the fuel cell voltage; In the energy source aging unit, the evaluation method of the aging state of the lithium battery is: Among them, D bat is the aging degree of lithium battery, N cycle The maximum number of charge and discharge cycles for lithium batteries.

7. The multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a following vehicle scenario according to claim 1, characterized in that: The first constraint condition is: in, is the minimum acceleration of the vehicle, is the maximum acceleration of the vehicle, J DS ,J DC are the corresponding cost functions for following safety and driving comfort, and there are:

8. The multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a following vehicle scenario as claimed in claim 7, characterized in that: When the planning sub-model generates an energy management plan, the second constraint condition is generated with the goal of minimizing the equivalent fuel consumption of the entire vehicle and the energy degradation cost. The second constraint condition is: minJ2=[J FE ,J PD ] Among them, P fc is the fuel cell power, is the minimum output power of the fuel cell, is the maximum output power of the fuel cell, is the minimum output power of lithium battery, is the maximum output power of lithium battery, J FE ,J PD are fuel economy cost and energy source degradation cost respectively, and there are: Among them, η fc is the fuel cell efficiency, is the lower calorific value of the fuel, λ bat is the lithium battery energy consumption equivalent factor, and Among them, η dis and η chg are the charge and discharge efficiency of lithium batteries respectively.

9. The multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a vehicle-following scenario according to claim 8, characterized in that: When the planning sub-model generates an energy management plan, a sequential quadratic programming algorithm is used to solve the second constraint condition to obtain the optimal output power of the fuel cell and the optimal output power of the lithium battery, and the energy management plan is generated based on the optimal output power of the fuel cell and the optimal output power of the lithium battery, and then a control instruction that can act on the drive motor of the fuel cell hybrid vehicle is generated based on the DC / DC converter.

10. A multi-scale predictive energy management system for fuel cell hybrid electric vehicles in a following vehicle scenario, characterized in that: A system for implementing a multi-scale predictive energy management method for a fuel cell hybrid electric vehicle in a vehicle-following scenario as described in any one of claims 1 to 9, the system comprising: Data collection module, used to obtain management basis data; The solution planning module is used to generate energy management solutions based on pre-built comprehensive planning models and management basis data; The control output module is used to generate control instructions that can act on the drive motor of the fuel cell hybrid vehicle according to the energy management solution.

Images