Energy management method based on digital twinning, cloud server and storage medium

Abstract

The invention provides an energy management method based on digital twinning, a cloud server and a storage medium, and relates to the technical field of vehicle management.The method comprises the steps that a monitoring instruction is received, and according to positioning information and the driving direction, the monitoring instruction is sent to the cloud server; determining a driving path corresponding to the target twin model from the digital twin model of the target fuel cell vehicle as a current driving path; determining a predicted road section according to the positioning information, and determining a target driving scene of the target driver from a target twin model according to the identification information of the target driver and the predicted road section; and an energy distribution control instruction corresponding to the target driving scene is issued to a vehicle controller, so that the vehicle controller performs energy distribution on a power cell and a fuel cell on the target fuel cell vehicle based on an energy distribution strategy corresponding to the energy distribution control instruction. The energy requirement of the target driving scene is fully met, the endurance mileage of the target fuel cell vehicle is prolonged, and the service life of the fuel cell is prolonged.

Description

Technical Field

[0001] The present application relates to the field of vehicle management technology, and more specifically, to an energy management method, a cloud server, and a storage medium based on digital twins. Background Art

[0002] With the rapid development of the logistics industry and increasingly stringent environmental protection policies, hydrogen energy commercial vehicles have gradually become the focus of market attention due to their advantages such as zero emissions and high efficiency. As the core power source of hydrogen energy commercial vehicles, the performance of the energy management system of hydrogen energy batteries directly affects the endurance, safety and economy of the vehicle. Therefore, the hydrogen energy battery energy management technology of hydrogen energy commercial vehicles has become one of the key technologies to promote the green development of the commercial vehicle field.

[0003] At present, the battery management system collects battery voltage, current, temperature and other data in real time, uses algorithms to estimate the battery's charge state, health state, etc., and uses preset protection strategies to prevent battery overcharging, over-discharging, overheating and other phenomena. At the same time, it optimizes the energy distribution strategy to balance the battery's charging and discharging process to extend battery life and improve the overall performance of the vehicle.

[0004] However, the energy management strategies of existing battery management systems are not adaptable enough when dealing with complex operating conditions such as high power and frequent start-stop of commercial vehicles, and are unable to increase the battery life while ensuring vehicle power performance and extending the driving range. Summary of the invention

[0005] The purpose of this application is to provide an energy management method, cloud server and storage medium based on digital twins to address the deficiencies in the above-mentioned prior art. This application fully meets the energy requirements of the target driving scenarios, while increasing the life of the fuel cell and extending the range of the target fuel cell vehicle.

[0006] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows: In a first aspect, an embodiment of the present application provides an energy management method based on digital twins, which is applied to a cloud server, and the method includes: Receiving a monitoring instruction uploaded by a vehicle controller of a target fuel cell vehicle, the monitoring instruction including: positioning information, driving direction, and identification information of a target driver of the target fuel cell vehicle; According to the positioning information and the driving direction, a target twin model is matched from a plurality of sub-twin models in the digital twin model of the target fuel cell vehicle, and a driving path corresponding to the target twin model is determined to be a current driving path; wherein the plurality of sub-twin models are respectively used to characterize a plurality of driving paths of the plurality of target fuel cell vehicles; Determining a predicted road section on the current driving path according to the positioning information; According to the identification information of the target driver and the predicted road section, a target driving scenario of the target driver is determined from multiple driving scenarios of the target twin model; different driving scenarios correspond to different energy allocation strategies; An energy distribution control instruction corresponding to the target driving scenario is issued to the vehicle controller, and the energy distribution control instruction is used to enable the vehicle controller to distribute energy to the power battery and fuel cell on the target fuel cell vehicle based on the energy distribution strategy corresponding to the energy distribution control instruction.

[0007] Optionally, the method further comprises: before matching the target twin model from the multiple sub-twin models, acquiring multiple groups of historical driving data of the target fuel cell vehicle, each group of historical driving data comprising: road condition data and driving condition data during one driving process; According to the identification information of the target fuel cell vehicle and the multiple groups of historical driving data of the target fuel cell vehicle, digital twin modeling is performed respectively to obtain the multiple sub-twin models of the target fuel cell vehicle.

[0008] Optionally, the driving condition data includes: vehicle state data and driving condition data; The digital twin modeling is performed respectively according to the identification information of the target fuel cell vehicle and the multiple groups of historical driving data of the target fuel cell vehicle to obtain the multiple sub-twin models of the target fuel cell vehicle, including: Determine driving condition data according to the vehicle state data, the driving condition data and the road condition data, wherein the driving condition data includes: driving condition data of multiple specific sections on a driving path; Determine turning driving condition data according to the driving condition data and the road condition data, wherein the turning driving condition data includes: driving condition data of a plurality of turning nodes on the one driving path; Digital twin modeling is performed based on the driving condition data of the multiple specific road sections, the driving condition data of the multiple turning nodes, and the road condition data to obtain a sub-twin model of the target fuel cell vehicle.

[0009] Optionally, each set of historical driving data includes: energy consumption data and braking recovery energy data of multiple location points during the one driving process; the method further includes: before performing digital twin modeling, determining the energy consumption data and braking recovery energy data of the multiple specific road sections according to the energy consumption data and braking recovery energy data of the multiple location points; The digital twin modeling is performed according to the driving condition data of the multiple specific road sections, the driving condition data of the multiple turning nodes and the road condition data to obtain a sub-twin model of the target fuel cell vehicle, including: Digital twin modeling is performed based on the driving condition data, energy consumption data and brake recovery energy data of the multiple specific road sections, the driving condition data of the multiple turning nodes and the road condition data to obtain a sub-twin model of the target fuel cell vehicle.

[0010] Optionally, determining a target driving scenario of the target driver from multiple driving scenarios of the target twin model according to the identification information of the target driver and the predicted road section includes: Acquiring historical driving behavior data of the target driver according to the identification information of the target driver; According to the historical driving behavior data and the predicted road section, a target driving scenario of the target driver is determined from the multiple driving scenarios.

[0011] Optionally, determining a target driving scenario of the target driver from the multiple driving scenarios based on the historical driving behavior data and the predicted road section includes: If the predicted road section is an uphill road section, determining the target driving scene from a plurality of driving scenes of the uphill road section according to the uphill accelerator pedal pressing duration and the accelerator pedal opening in the historical driving behavior data; Alternatively, if the predicted road section is a downhill section, the target driving scene is determined from a plurality of driving scenes of the downhill section according to the braking duration and the brake pedal travel in the historical driving behavior data.

[0012] Optionally, determining the target driving scene from a plurality of driving scenes on the uphill road section according to the uphill accelerator pedal pressing duration and the accelerator pedal opening in the historical driving behavior data includes: If the uphill accelerator pedal pressing time is greater than a first preset time threshold and the accelerator pedal opening is greater than a first preset opening threshold, determining that the target driving scene is the first driving scene; The sending of the energy distribution control instruction corresponding to the target driving scenario to the vehicle controller includes: A first control instruction is issued to the vehicle controller, wherein the first control instruction is used to enable the vehicle controller to start the fuel cell in advance, so as to use the fuel cell and the power battery to jointly provide power energy.

[0013] Optionally, determining the target driving scene from a plurality of driving scenes on the uphill road section according to the uphill accelerator pedal pressing duration and the accelerator pedal opening in the historical driving behavior data includes: If the uphill accelerator pedaling duration is less than a second preset duration threshold and the accelerator pedal opening is greater than a first preset opening threshold, determining that the target driving scenario is the second driving scenario; The sending of the energy distribution control instruction corresponding to the target driving scenario to the vehicle controller includes: A second control instruction and uphill energy consumption data are sent to the vehicle controller, wherein the second control instruction is used to enable the vehicle controller not to turn on the fuel cell when the current state of charge parameters of the power battery can guarantee the uphill energy consumption data and only when the predicted state of charge parameters of the power battery after completing the climb are greater than the first preset state of charge threshold; and to turn on the fuel cell in advance when the current state of charge parameters cannot guarantee the energy consumption data and only when the predicted state of charge parameters of the power battery after completing the climb are less than the second preset state of charge threshold, so as to use the fuel cell and the power battery to jointly provide climbing power energy.

[0014] Optionally, determining the target driving scenario from a plurality of driving scenarios on the downhill section according to the braking duration and brake pedal travel in the historical driving behavior data includes: If the braking time is greater than a third preset time threshold and the brake pedal stroke is greater than a preset braking stroke threshold, determining that the target driving scenario is a third driving scenario; The sending of the energy distribution control instruction corresponding to the target driving scenario to the vehicle controller includes: A third control instruction is sent to the vehicle controller, and the third control instruction is used to enable the vehicle controller to start braking energy recovery on the downhill section to recover the braking energy to the power battery, and to turn off the fuel cell to only use the power battery to provide downhill power energy.

[0015] Optionally, determining the target driving scenario from a plurality of driving scenarios on the downhill section according to the braking duration and brake pedal travel in the historical driving behavior data includes: If the braking duration is less than a fourth preset duration threshold and the brake pedal stroke is greater than a preset braking stroke threshold, determining that the target driving scenario is a fourth driving scenario; The sending of the energy distribution control instruction corresponding to the target driving scenario to the vehicle controller includes: A fourth control instruction and downhill energy consumption data are issued to the vehicle controller, the fourth control instruction is used to enable the vehicle controller to start braking energy recovery on the downhill section to recover braking energy to the power battery, and use the fuel cell and the power battery to jointly provide downhill power energy; only use the power battery to provide energy, and when the current state of charge parameter of the power battery can guarantee the downhill energy consumption data, and the predicted state of charge parameter of the power battery after completing the downhill is greater than the third preset state of charge threshold, the fuel cell is not turned on; when the current state of charge parameter cannot guarantee the downhill energy consumption data, and the predicted state of charge parameter of the power battery after completing the downhill is less than the fourth preset state of charge threshold, the fuel cell is turned on in advance, so that the fuel cell and the power battery are used to jointly provide downhill power energy.

[0016] In a second aspect, another embodiment of the present application provides an energy management device based on digital twins, the device comprising: A receiving module, used to receive a monitoring instruction uploaded by a vehicle controller of a target fuel cell vehicle, wherein the monitoring instruction includes: positioning information, driving direction, and identification information of a target driver of the target fuel cell vehicle; A first determination module is used to match a target twin model from multiple sub-twin models in the digital twin model of the target fuel cell vehicle according to the positioning information and the driving direction, and determine that the driving path corresponding to the target twin model is the current driving path; wherein the multiple sub-twin models are respectively used to characterize multiple driving paths of the multiple target fuel cell vehicles; A second determination module, used to determine a predicted road section on the current driving path according to the positioning information; A third determination module is used to determine a target driving scenario of the target driver from multiple driving scenarios of the target twin model according to the identification information of the target driver and the predicted road section; different driving scenarios correspond to different energy allocation strategies; A distribution module is used to send an energy distribution control instruction corresponding to the target driving scenario to the vehicle controller, and the energy distribution control instruction is used to enable the vehicle controller to distribute energy to the power battery and fuel cell on the target fuel cell vehicle based on the energy distribution strategy corresponding to the energy distribution control instruction.

[0017] In the third aspect, another embodiment of the present application provides a cloud server, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it executes the steps of the digital twin-based energy management method as described in any one of the first aspects above.

[0018] In a fourth aspect, another embodiment of the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the energy management method based on digital twins as described in any one of the above-mentioned first aspects are executed.

[0019] In the fifth aspect, another embodiment of the present application provides an energy management system, which includes: the cloud server and vehicle controller described in the third aspect above, the cloud server and the vehicle controller are communicatively connected, and the cloud server is used to execute any step of the digital twin-based energy management method described in the first aspect.

[0020] The beneficial effects of this application are: The present application provides an energy management method based on digital twins, a cloud server, and a storage medium. By receiving a monitoring instruction uploaded by a vehicle controller of a target fuel cell vehicle, the target twin model is matched from multiple sub-twin models in the digital twin model of the target fuel cell vehicle according to the positioning information and the driving direction, and the driving path corresponding to the target twin model is determined to be the current driving path. According to the positioning information, the predicted section on the current driving path is determined. According to the identification information and the predicted section of the target driver, the target driving scene of the target driver is determined from multiple driving scenes of the target twin model, and the energy distribution control instruction corresponding to the target driving scene is issued to the vehicle controller. The energy distribution control instruction is used to enable the vehicle controller to distribute energy to the power battery and the fuel cell on the target fuel cell vehicle based on the energy distribution strategy corresponding to the energy distribution control instruction. The present application determines the target twin model from the digital twin model of the target fuel cell vehicle according to the positioning information and the driving direction, determines the target driving scene and the energy distribution control instruction according to the target twin model, provides a personalized energy distribution strategy in a targeted manner, and optimizes the energy distribution strategy of the target fuel cell vehicle. The corresponding energy distribution control instructions are determined through the energy distribution strategy, so that the vehicle controller distributes energy to the power battery and fuel cell on the target fuel cell vehicle according to the corresponding energy distribution control instructions, ensuring the maximum utilization of the target fuel cell energy, fully meeting the energy requirements of the target driving scenario, and extending the range of the target fuel cell vehicle while increasing the fuel cell life. BRIEF DESCRIPTION OF THE DRAWINGS In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic diagram of a process flow of an energy management method based on digital twins provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for generating a twin model in a first energy management method based on digital twins provided in an embodiment of the present application; Figure 3 A schematic diagram of a process for generating a twin model in a second energy management method based on digital twins provided in an embodiment of the present application; Figure 4 A schematic diagram of a process for generating a twin model in a third energy management method based on digital twins provided in an embodiment of the present application; Figure 5 A schematic diagram of a process for determining a target driving scenario in a digital twin-based energy management method provided in an embodiment of the present application; Figure 6 A schematic diagram of a process for determining energy distribution control instructions in a first energy management method based on digital twins provided in an embodiment of the present application; Figure 7 A schematic diagram of a flow chart for determining energy distribution control instructions in a second energy management method based on digital twins provided in an embodiment of the present application; Figure 8 A schematic diagram of a process for determining energy distribution control instructions in a third energy management method based on digital twins provided in an embodiment of the present application; Fig. 9 A schematic diagram of a process for determining energy distribution control instructions in a fourth energy management method based on digital twins provided in an embodiment of the present application; Fig.10 A schematic diagram of the structure of an energy management device based on digital twins provided in an embodiment of the present application; Fig.11 A schematic diagram of the structure of a cloud server provided in an embodiment of the present application; Fig.12 A schematic diagram of the structure of an energy management system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme 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. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0023] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0024] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0025] The energy management method based on digital twins provided in this application is applied to a cloud server. Among them, the digital twin is used to create a digital twin model of the target fuel cell vehicle through data technology. The cloud server includes: a user platform unit, a digital twin modeling unit, a model matching unit, and a scene definition unit. The vehicle number and the driver number can be set through the user platform unit, and the position of the vehicle in the current model and related parameters can be viewed. The digital twin modeling unit is modeled according to multiple groups of historical driving data of the target fuel cell vehicle, and iteratively updated in real time according to dynamic data to simulate and generate multiple sub-twin models. The model matching unit is used to match the target twin model from multiple sub-twin models in the digital twin model of the target fuel cell vehicle according to the positioning information and the driving direction, and the driving trajectory and working conditions can be predicted. If the vehicle positioning deviates from the planned path, it is re-matched in the digital twin model. If the road section does not exist in the digital twin model, the road section data is stored and modeled. The scene definition unit is used to determine the target driving scene of the target driver from multiple driving scenes of the target twin model according to the identification information of the target driver and the predicted road section.

[0026] In this application, the target fuel cell vehicle can be a hydrogen fuel cell vehicle, and the specific vehicle type can be a commercial hydrogen fuel cell vehicle. Since the driving path of a commercial hydrogen fuel cell vehicle is basically a fixed route within a fixed range, the energy distribution control instruction of the target fuel cell vehicle can be determined by an energy management method based on digital twins, thereby ensuring the power performance of the target fuel cell vehicle, while extending the cruising range of the target fuel cell vehicle and increasing the life of the fuel cell. The target fuel cell electric vehicle includes a driving information acquisition module and an energy management module. The driving information acquisition module includes: a positioning module, an image acquisition module, and a driving condition acquisition module. The positioning module is used to determine the positioning information of the target fuel cell. The image acquisition module is used to obtain road condition data, such as intersections, traffic signs, obstacles, congestion, road environment, etc. The driving condition acquisition module is used to obtain driving condition data and vehicle status data. The driving condition data can be the current speed of the vehicle and the throttle output, the throttle pressing time, the brake pedal travel and the braking time, the steering wheel angle, etc., and the vehicle status data can be the vehicle's yaw, pitch, roll, acceleration, deceleration, steering, etc. The energy management module includes: an energy consumption calculation module, an energy monitoring module and an energy distribution module. The energy consumption calculation module is used to calculate the energy consumption data of the target fuel cell and the braking recovery energy data. The energy monitoring module is used to determine the current state of charge parameters of the power battery of the target fuel cell vehicle, the working state of the power battery, the remaining fuel amount of the fuel cell and the working state of the fuel cell. The energy distribution module is used to distribute energy to the target fuel cell vehicle according to the energy distribution control.

[0027] The following is an example of the digital twin-based energy management method implemented in the cloud server with reference to the accompanying drawings. Figure 1 A schematic diagram of a process flow of an energy management method based on digital twins provided in an embodiment of the present application, the method comprising: Step 101: Receive a monitoring instruction uploaded by a vehicle controller of a target fuel cell vehicle.

[0028] The monitoring instructions include: the positioning information of the target fuel cell vehicle, the driving direction, and the identification information of the target driver.

[0029] Among them, the target fuel cell vehicle is provided with a positioning module and a plurality of different types of sensors. The positioning information of the target fuel cell vehicle can be determined by the positioning module provided on the target fuel cell vehicle. The driving direction of the target fuel cell vehicle can be determined according to the steering angle sensor to determine the steering wheel turning direction of the target fuel cell vehicle, thereby determining the driving direction of the target fuel cell according to the steering wheel turning direction. The identification information of the target driver is the information input into the vehicle controller by the driver before driving, such as work number, ID number and other information, which is not limited in the embodiments of the present application.

[0030] Optionally, the vehicle controller receiving the target fuel cell vehicle obtains the positioning information of the target fuel cell vehicle based on a positioning module provided on the target fuel cell vehicle; the vehicle controller receiving the target fuel cell vehicle obtains the data of the steering angle sensor based on multiple different types of sensors on the target fuel cell vehicle, thereby determining the steering wheel turning direction of the target fuel cell vehicle; the vehicle controller receiving the target fuel cell vehicle obtains the identification information of the target driver input by the driver on the target fuel cell vehicle before driving.

[0031] Step 102: According to the positioning information and the driving direction, the target twin model is matched from multiple sub-twin models in the digital twin model of the target fuel cell vehicle, and the driving path corresponding to the target twin model is determined to be the current driving path.

[0032] The digital twin model of the target fuel cell vehicle is constructed based on the historical driving data of the target fuel cell. The digital twin model includes multiple sub-twin models, which are used to represent multiple driving paths of multiple target fuel cell vehicles.

[0033] Optionally, since the driving path of commercial vehicles is relatively fixed, once the positioning information and driving direction of the target fuel cell vehicle are determined, the target twin model can be matched from multiple sub-twin models in the digital twin model of the target fuel cell vehicle, and the driving path corresponding to the target twin model can be determined as the current driving path.

[0034] Step 103: Determine the predicted road section on the current driving path according to the positioning information.

[0035] The predicted road section may be a flat road section, an uphill road section, a downhill road section, etc.

[0036] Optionally, according to the positioning information, since the target vehicle is traveling in the current driving path, there is no need to predict the sections traveled in the current driving path, so the sections not traveled in the positioning information are determined from the current driving path as the corresponding predicted sections.

[0037] Step 104: Determine the target driving scenario of the target driver from multiple driving scenarios of the target twin model based on the identification information of the target driver and the predicted road section.

[0038] Different driving scenarios correspond to different energy allocation strategies. The driving scenario can be determined based on the driver's driving habits and predicted road sections.

[0039] Optionally, the driving habits of the target driver are determined based on the identification information of the target driver, and the target driving scenario of the target driver is determined from multiple driving scenarios of the target twin model based on the driving habits of the target driver and the predicted road section.

[0040] Step 105: Send an energy distribution control instruction corresponding to the target driving scenario to the vehicle controller, where the energy distribution control instruction is used to enable the vehicle controller to distribute energy to the power battery and fuel cell on the target fuel cell vehicle based on the energy distribution strategy corresponding to the energy distribution control instruction.

[0041] Optionally, the vehicle controller receives energy distribution control instructions corresponding to the target driving scenario issued by the cloud server, and then controls the activation of energy recovery of the power battery on the target fuel cell vehicle and the start and stop of the fuel cell based on the energy distribution strategy corresponding to the energy distribution control instructions, thereby realizing energy distribution.

[0042] In an embodiment of the present application, a monitoring instruction uploaded by a vehicle controller of a target fuel cell vehicle is received, and the target twin model is matched from multiple sub-twin models in the digital twin model of the target fuel cell vehicle according to the positioning information and the driving direction, and the driving path corresponding to the target twin model is determined to be the current driving path, and the predicted section on the current driving path is determined according to the positioning information, and the target driving scene of the target driver is determined from multiple driving scenes of the target twin model according to the identification information and the predicted section of the target driver, and the energy distribution control instruction corresponding to the target driving scene is issued to the vehicle controller, and the energy distribution control instruction is used to enable the vehicle controller to distribute energy to the power battery and fuel cell on the target fuel cell vehicle based on the energy distribution strategy corresponding to the energy distribution control instruction. The present application determines the target twin model from the digital twin model of the target fuel cell vehicle according to the positioning information and the driving direction, and can provide a personalized energy distribution strategy and optimize the energy distribution strategy of the target fuel cell vehicle. By determining the corresponding energy distribution control instructions through the energy distribution strategy, the vehicle controller distributes energy to the power battery and fuel cell on the target fuel cell vehicle according to the corresponding energy distribution control instructions, which can ensure the maximum utilization of the target fuel cell energy, fully meet the energy requirements of the target driving scenario, and extend the range of the target fuel cell vehicle while increasing the life of the fuel cell.

[0043] Based on the above embodiments, the present application also provides a process for generating a twin model in a first energy management method based on digital twins. Figure 2 A schematic diagram of a process for generating a twin model in the first energy management method based on digital twins provided in an embodiment of the present application, such as Figure 2As shown, in the above step 102, before matching the target twin model from multiple sub-twin models, it also includes: Step 201: Acquire multiple groups of historical driving data of a target fuel cell vehicle.

[0044] Each set of historical driving data includes: road condition data and driving condition data during a driving process.

[0045] Among them, the target fuel cell vehicle is provided with an image acquisition module, and the image acquisition module can be an image sensor, and the image acquisition module is used to collect intersections, traffic signs, obstacles, congestion, road environment, etc. during driving as road conditions. The vehicle status data and driving behavior data of the target fuel cell vehicle are determined by multiple sensors of the target fuel cell vehicle. The vehicle status data is used to indicate the state of the vehicle during the driving process of the vehicle, such as: elevation, pitch or yaw, etc., which is not limited in the embodiments of the present application. The driving behavior data can be: current vehicle speed, throttle output, throttle depression time, brake pedal travel and braking time, steering wheel angle, etc., which is not limited in the embodiments of the present application.

[0046] Step 202: Perform digital twin modeling based on the identification information of the target fuel cell vehicle and multiple groups of historical driving data of the target fuel cell vehicle to obtain multiple sub-twin models of the target fuel cell vehicle.

[0047] Optionally, according to the identification information of the target fuel cell vehicle, multiple groups of historical driving data corresponding to the target fuel cell vehicle are determined, and digital twin modeling is performed on the target fuel cell vehicle to obtain multiple sub-twin models of the target fuel cell vehicle. Each twin model corresponds to a different driving path.

[0048] In an embodiment of the present application, multiple groups of historical driving data of the target fuel cell vehicle are obtained, and digital twin modeling is performed respectively according to the multiple groups of historical driving data of the target fuel cell vehicle to obtain multiple digital twin models of the target fuel cell vehicle. The present application can more accurately determine the target twin model, reduce the deviation of a single model, improve the prediction accuracy, thereby optimizing the energy allocation strategy of the fuel cell and the power battery, and improving the energy utilization efficiency.

[0049] Based on the above embodiment, the driving condition data includes: vehicle status data and driving condition data. To this end, the present application also provides a second process for generating a twin model in an energy management method based on digital twins, Figure 3 A schematic diagram of a process for generating a twin model in a second energy management method based on digital twins provided in an embodiment of the present application, such as Figure 3As shown, in the above step 202, digital twin modeling is performed respectively according to the identification information of the target fuel cell vehicle and multiple groups of historical driving data of the target fuel cell vehicle to obtain multiple sub-twin models of the target fuel cell vehicle, including: Step 301: Determine driving condition data according to vehicle state data, driving condition data and road condition data.

[0050] The driving road condition data includes: driving road condition data of multiple specific road sections on a driving route. The driving road condition data can be downhill road condition data, flat road condition data, uphill road condition data, etc.

[0051] Optionally, the current state of the target fuel cell vehicle is determined according to the pitch angle and / or roll angle in the vehicle state data, and the driving condition data is determined according to the current state of the target fuel cell vehicle, the driving condition data and the road condition data. The driving condition data also includes specific positioning information of the driving condition.

[0052] For example, when the pitch angle in the vehicle state data of the target fuel cell vehicle is greater than 15° and lasts for more than three minutes, the driving road condition data is determined to be uphill road condition data. When the pitch angle in the vehicle state data of the target fuel cell vehicle is less than -15° and lasts for more than three minutes, the driving road condition data is determined to be uphill road condition data.

[0053] Step 302: Determine steering operating condition data according to the driving operating condition data and the road operating condition data.

[0054] Among them, the turning driving condition data includes: driving condition data of multiple turning nodes on a driving path; the driving condition data can be: left turn condition data, right turn condition data, U-turn condition data, lane change condition data and other data, and the embodiments of the present application do not impose any restrictions on this.

[0055] Optionally, driving condition data of a plurality of turning nodes of a target fuel cell vehicle on a driving path are determined based on a steering wheel angle in the driving condition data and road condition data.

[0056] Step 303: Perform digital twin modeling based on the driving condition data of multiple specific road sections, the driving condition data of multiple turning nodes, and the road condition data to obtain a sub-twin model of the target fuel cell vehicle.

[0057] Among them, a sub-twin model is used to characterize a driving path, and a sub-twin model includes: driving condition data of multiple specific sections on a driving path, driving condition data of multiple turning nodes, and road condition data.

[0058] Optionally, digital twin modeling is performed based on the driving condition data of multiple specific road sections, the driving condition data of multiple turning nodes, and the road condition data to obtain a sub-twin model of the target fuel cell vehicle. A digital twin model of the target fuel cell vehicle is constructed based on the multiple sub-twin models.

[0059] Based on the embodiments of the present application, the driving condition data is determined according to the vehicle state data, the driving condition data and the road condition data, and the steering driving condition data is determined according to the driving condition data and the road condition data. According to the driving condition data of multiple specific sections, the driving condition data of multiple turning nodes and the road condition data, digital twin modeling is performed to obtain a sub-twin model of the target fuel cell vehicle. The digital twin model in the present application can more accurately predict the driving scenario of the vehicle, thereby identifying potential safety risks and improving the safety of the target fuel cell vehicle.

[0060] Based on the above embodiment, each set of historical driving data includes: energy consumption data of multiple locations during a driving process and braking energy recovery data. To this end, the present application also provides a third process for generating a twin model in an energy management method based on digital twins, Figure 4 A schematic diagram of a process for generating a twin model in a third energy management method based on digital twins provided in an embodiment of the present application, such as Figure 4 As shown, before obtaining a sub-twin model of the target fuel cell vehicle in step 303, the method further includes: Step 401: Determine energy consumption data and braking recovery energy data of multiple specific road sections based on energy consumption data and braking recovery energy data of multiple location points.

[0061] Optionally, the energy consumption data and the braking recovery energy data of the specific road section between the starting point and the ending point are determined based on the energy consumption data and the braking recovery energy data corresponding to the starting points and the ending points of multiple specific road sections.

[0062] For example, when the energy consumption data or braking recovery energy data of the starting point of the characteristic road section is a, and the energy consumption data or braking recovery energy data of the ending point is b, then the energy consumption data of the characteristic road section is ba.

[0063] In the above step 303, digital twin modeling is performed based on the driving condition data of multiple specific road sections, the driving condition data of multiple turning nodes, and the road condition data to obtain a sub-twin model of the target fuel cell vehicle, including: Step 402: Perform digital twin modeling based on the driving condition data, energy consumption data, and brake recovery energy data of multiple specific road sections, the driving condition data of multiple turning nodes, and the road condition data to obtain a sub-twin model of the target fuel cell vehicle.

[0064] Among them, the data twin model also includes energy consumption data of multiple characteristic road sections and brake recovery energy data.

[0065] Optionally, digital twin modeling is performed based on the driving condition data, energy consumption data, braking energy recovery data, driving condition data of multiple turning nodes, and road condition data of multiple specific sections to obtain a sub-twin model of the target fuel cell vehicle. Among them, the driving condition data, energy consumption data, braking energy recovery data, driving condition data of multiple turning nodes, and road condition data of multiple specific sections of the target fuel cell vehicle can be determined based on a sub-twin model of the target fuel cell vehicle.

[0066] In an embodiment of the present application, the energy consumption data and braking energy recovery data of multiple specific sections are determined based on the energy consumption data and braking energy recovery data of multiple location points, thereby constructing a sub-twin model of the target fuel cell vehicle. The present application can accurately predict the energy consumption data and braking energy data of the target fuel cell vehicle during driving through the sub-twin model, thereby improving the accuracy of the energy allocation strategy.

[0067] Based on the above embodiments, the present application also provides a process for determining a target driving scenario in an energy management method based on digital twins. Figure 5 A schematic diagram of a process for determining a target driving scenario in an energy management method based on digital twins provided in an embodiment of the present application, such as Figure 5 As shown, in the above step 104, according to the identification information of the target driver and the predicted road section, the target driving scene of the target driver is determined from multiple driving scenes of the target twin model, including: Step 501: Acquire historical driving behavior data of the target driver according to the identification information of the target driver.

[0068] The historical driving behavior data may include: the duration of the driver's accelerator pedaling, the accelerator pedal opening, the brake pedal travel, the duration of the brake pedaling, etc., which are not limited in the embodiments of the present application. The identification information of the target driver may include: the driver's name, the driver's work number, the driver's ID number, etc., which are not limited in the embodiments of the present application.

[0069] Optionally, the driving behavior data of the driver is determined by using a plurality of sensors disposed in the target fuel cell vehicle, and the historical driving behavior data of the target driver is acquired based on the identification information of the target driver.

[0070] Step 502: Determine a target driving scenario for a target driver from multiple driving scenarios based on historical driving behavior data and predicted road sections.

[0071] Optionally, based on the predicted road section, a driving scene corresponding to the predicted road section is determined from multiple driving scenes, and based on historical driving behavior data, a target driving scene for the target driver is determined from the driving scenes corresponding to the predicted road section.

[0072] In this application, the historical driving behavior data is first determined, and based on the historical driving behavior data and the predicted road section, the target driving scenario of the target driver is determined from multiple driving scenarios. This application can provide drivers with a more personalized driving experience, adapt to the driver's driving habits and preferences, and help predict potential driving risks, so that measures can be taken in advance to avoid accidents.

[0073] Based on the above embodiment, the present application also provides another process for determining a target driving scenario in an energy management method based on data twins. In the above step 502, the target driving scenario of the target driver is determined from multiple driving scenarios based on historical driving behavior data and predicted road sections, including: If the predicted road section is an uphill section, the target driving scene is determined from multiple driving scenes of the uphill section according to the uphill accelerator pedal pressing duration and the accelerator pedal opening in the historical driving behavior data.

[0074] Among them, the duration of accelerator pedal pressing and the accelerator pedal opening can indicate the driver's driving habits. When the driver's accelerator pedal pressing duration is long and the accelerator pedal opening is large, it means that the driver prioritizes driving dynamics. When the driver's accelerator pedal pressing duration is short and the accelerator pedal opening is small, it means that the driver prioritizes energy saving. This application only uses the above as an example for explanation. The specific driving habits are determined according to actual conditions, and the embodiments of this application do not limit this.

[0075] Optionally, if the predicted road section is an uphill road section, the driving habit of the driver is determined according to the uphill accelerator pedaling duration and the accelerator pedal opening in the historical driving behavior data. The target driving scene is determined from multiple driving scenes of the uphill road section according to the driving habit of the driver.

[0076] Alternatively, if the predicted road section is a downhill section, the target driving scene is determined from multiple driving scenes of the downhill section according to the braking duration and brake pedal travel in the historical driving behavior data.

[0077] Optionally, if the predicted road section is a downhill section, the driving habit of the driver is determined according to the braking duration and brake pedal travel in the historical driving behavior data. The target driving scene is determined from multiple driving scenes of the downhill section according to the driving habit of the driver.

[0078] In the embodiment of the present application, the target driving scene is determined from multiple driving scenes of different predicted sections according to the predicted section and the braking duration and brake pedal travel in the historical driving behavior data. The present application can more accurately predict the driver's behavior on a specific section, thereby improving the matching degree between the driver and the driving scene, maximizing the use of energy recovered during braking, and improving battery efficiency.

[0079] Based on the above embodiments, the present application also provides a process for determining energy distribution control instructions in a first energy management method based on digital twins. Figure 6 A schematic diagram of a process for determining energy distribution control instructions in a first energy management method based on digital twins provided in an embodiment of the present application, such as Figure 6 As shown, in the above, according to the uphill accelerator pedal pressing duration and accelerator pedal opening in the historical driving behavior data, the target driving scene is determined from multiple driving scenes on the uphill road section, including: Step 601: If the uphill accelerator pedal pressing duration is greater than a first preset duration threshold and the accelerator pedal opening is greater than a first preset opening threshold, then the target driving scene is determined to be the first driving scene.

[0080] Among them, the first preset duration threshold is T1, and the first preset duration threshold can be determined according to the parameters of the power battery and the fuel cell, or the first preset duration threshold can be determined according to the road conditions of the current uphill section, or other determination methods, which are not limited in the embodiments of the present application. The first preset opening threshold can be 30%. At this time, the degree to which the driver presses the accelerator pedal is 30% of the degree to which the accelerator pedal is fully pressed. The first driving scenario is: in the case of an uphill section, the uphill accelerator pedal duration is greater than the first preset duration threshold and the accelerator pedal opening is greater than the first preset opening threshold.

[0081] Optionally, if the uphill accelerator pedal pressing duration is greater than a first preset duration threshold and the accelerator pedal opening is greater than a first preset opening threshold, it means that the driver prioritizes driving dynamics on the uphill section, and the target driving scenario is determined to be the first driving scenario.

[0082] In the above step 105, the energy distribution control instruction corresponding to the target driving scenario is sent to the vehicle controller, including: Step 602: Send a first control instruction to the vehicle controller, where the first control instruction is used to enable the vehicle controller to start the fuel cell in advance, so as to use the fuel cell and the power battery to jointly provide power energy.

[0083] Among them, the first control instruction is an instruction of "about to climb a slope, start energy storage". The first control instruction not only includes the road condition of about to climb a slope, but also instructs to start energy storage.

[0084] Optionally, when the target driving scenario is the first driving scenario, it means that the driver prioritizes driving dynamics on the uphill section, and needs to store energy in advance on the uphill section, and start the fuel cell and power battery in advance to supply power at the same time. When the vehicle reaches a preset distance from the uphill section, the "about to climb, start energy storage" instruction is sent to the vehicle controller, so that the vehicle controller starts the fuel cell in advance, so that the fuel cell and power battery can jointly provide power energy, thereby ensuring the driving dynamics of the target fuel cell vehicle. The preset distance can be 300 meters.

[0085] In an embodiment of the present application, the corresponding driving scenario can be determined based on the predicted road section and throttle information, and the corresponding control instructions can be determined based on the driving scenario, so that the vehicle controller distributes energy according to the corresponding control instructions, thereby providing a smoother driving experience. At the same time, energy management can be effectively performed to improve driving safety.

[0086] Based on the above embodiments, the present application also provides a second process for determining energy distribution control instructions in an energy management method based on digital twins. Figure 7 A schematic diagram of a flow chart for determining energy distribution control instructions in a second energy management method based on digital twins provided in an embodiment of the present application, such as Figure 7 As shown, in the above, according to the uphill accelerator pedal pressing duration and accelerator pedal opening in the historical driving behavior data, the target driving scene is determined from multiple driving scenes on the uphill road section, including: Step 701: If the uphill accelerator pedal pressing duration is less than a second preset duration threshold and the accelerator pedal opening is greater than a first preset opening threshold, then determine that the target driving scene is the second driving scene.

[0087] Among them, the second preset duration threshold is T2, and the second preset duration threshold can be determined according to the parameters of the power battery and the fuel cell, or the second preset duration threshold can be determined according to the road conditions of the current uphill section, or other determination methods, which are not limited in the embodiments of the present application. The first preset opening threshold can be 30%. The second preset duration threshold T2 is less than the first preset duration threshold T1. The second driving scenario is: in the case of an uphill section, the uphill accelerator pedal duration is less than the second preset duration threshold and the accelerator pedal opening is greater than the first preset opening threshold.

[0088] Optionally, if the uphill accelerator pedal pressing duration is less than a second preset duration threshold and the accelerator pedal opening is greater than a first preset opening threshold, it means that the driver gives priority to energy saving on the uphill section, and the target driving scenario is determined to be the second driving scenario.

[0089] In the above step 105, the energy distribution control instruction corresponding to the target driving scenario is sent to the vehicle controller, including: Step 702, send a second control instruction and uphill energy consumption data to the vehicle controller, the second control instruction is used to enable the vehicle controller not to turn on the fuel cell when the current state of charge parameters of the power battery can guarantee the uphill energy consumption data, and the predicted state of charge parameters after the power battery completes the climb are greater than the first preset state of charge threshold; when the current state of charge parameters cannot guarantee the energy consumption data, and the predicted state of charge parameters after the power battery completes the climb are less than the second preset state of charge threshold, turn on the fuel cell in advance, so as to use the fuel cell and the power battery to jointly provide climbing power energy.

[0090] Among them, the uphill energy consumption data is Q1, and the uphill energy consumption data is the energy consumption data consumed by the vehicle traveling between the starting point and the end point of the uphill section. The current state of charge parameter is Q0, the first preset state of charge threshold can be 45%, and the second preset state of charge threshold can be 85%. The second control instruction is the "about to climb" instruction, and the second control instruction only includes the road conditions about to climb, and does not include the control of energy storage. Optionally, when the target driving scenario is the second driving scenario, it means that the driver gives priority to energy saving on uphill sections, and it is necessary to determine whether energy storage is needed based on the state of charge parameters of the power battery in the target fuel cell vehicle. When the vehicle controller is at a preset distance from the uphill section, an "about to climb" instruction is sent to the vehicle controller, so that the vehicle controller does not turn on the fuel cell when the current state of charge parameters of the power battery can guarantee the uphill energy consumption data, and only when the predicted state of charge parameters after the power battery completes the climb are greater than the first preset state of charge threshold. Among them, the preset distance can be 300 meters. Specifically, when the difference between the current state of charge parameter Q0 of the power battery and the uphill energy consumption data Q1 is greater than 45% of the first preset state of charge threshold, the fuel cell is not turned on.

[0091] Optionally, when the current state of charge parameter cannot guarantee the energy consumption data, and only the power battery is used to complete the climbing, when the difference between the current state of charge parameter Q0 of the power battery and the uphill energy consumption data Q1 is less than the first preset state of charge threshold value of 45%, then when the state of charge parameter of the power battery reaches 85%, the fuel cell is turned on in advance to use the fuel cell and the power battery to jointly provide the climbing power energy. When the state of charge parameter of the power battery reaches 95%, and the difference between the current state of charge parameter Q0 of the power battery and the uphill energy consumption data Q1 is greater than the first preset state of charge threshold value of 45%, the fuel cell is turned off.

[0092] In an embodiment of the present application, the corresponding driving scenario can be determined based on the predicted road section and throttle information, and the corresponding control instructions can be determined based on the driving scenario, so that the vehicle controller distributes energy according to the corresponding control instructions, helping the driver to make better choices under complex or uncertain driving conditions and improving the driver's driving experience.

[0093] Based on the above embodiments, the present application also provides a third process for determining energy distribution control instructions in an energy management method based on digital twins. Figure 8 A schematic diagram of a process for determining energy distribution control instructions in a third energy management method based on digital twins provided in an embodiment of the present application, such as Figure 8 As shown, in the above, according to the braking duration and brake pedal travel in the historical driving behavior data, the target driving scenario is determined from multiple driving scenarios on the downhill section, including: Step 801: If the braking time is greater than a third preset time threshold and the brake pedal travel is greater than a preset braking travel threshold, it is determined that the target driving scene is the third driving scene.

[0094] Among them, the third preset duration threshold is T3, and the third preset duration threshold can be determined according to the parameters of the power battery and the fuel cell, or the third preset duration threshold can be determined according to the road conditions of the current uphill section, or other determination methods, which are not limited in the embodiments of the present application. The preset braking stroke threshold can be 20%. The third driving scenario is: in the case of a downhill section, the braking time is greater than the third preset duration threshold and the brake pedal stroke is greater than the preset braking stroke threshold.

[0095] Optionally, if the braking time is greater than a third preset time threshold and the brake pedal stroke is greater than a preset braking stroke threshold, it means that the driver prioritizes braking on an uphill section, and the target driving scene is determined to be the third driving scene.

[0096] In the above step 105, the energy distribution control instruction corresponding to the target driving scenario is sent to the vehicle controller, including: Step 802: Send a third control instruction to the vehicle controller, which is used to enable the vehicle controller to start braking energy recovery on a downhill section to recover braking energy to the power battery, and turn off the fuel cell to only use the power battery to provide downhill power energy.

[0097] Among them, the third control instruction is the instruction of "about to go downhill, please turn on braking energy recovery". The third control instruction not only includes the road conditions of about to go downhill, but also instructs to turn on automatic energy recovery.

[0098] Optionally, when the target driving scenario is the third driving scenario, it means that the driver has priority to brake on the downhill section, and sends a "downhill approaching, please turn on brake energy recovery" command to the vehicle controller when the driver is at a preset distance from the downhill section, so that the vehicle controller turns on automatic energy recovery in advance on the downhill section to recover the brake energy to the power battery, and turns off the fuel cell to only use the power battery to provide downhill power energy. The preset distance can be 300 meters.

[0099] In an embodiment of the present application, the corresponding driving scenario can be determined based on the predicted road section and throttle information, and the corresponding control instructions can be determined based on the driving scenario, so that the vehicle controller distributes energy according to the corresponding control instructions, ensuring that the target fuel cell vehicle can prepare and distribute the necessary energy in advance, thereby improving the driving safety of the driver.

[0100] Based on the above embodiments, the present application also provides a fourth process for determining energy distribution control instructions in an energy management method based on digital twins. Fig. 9 A schematic diagram of a flow chart for determining energy distribution control instructions in a fourth energy management method based on digital twins provided in an embodiment of the present application, such as Fig. 9 As shown, in the above, according to the braking duration and brake pedal travel in the historical driving behavior data, the target driving scenario is determined from multiple driving scenarios on the downhill section, including: Step 901: If the braking duration is less than a fourth preset duration threshold and the brake pedal travel is greater than a preset braking travel threshold, it is determined that the target driving scenario is the fourth driving scenario.

[0101] Among them, the fourth preset duration threshold is T4, and the fourth preset duration threshold can be determined according to the parameters of the power battery and the fuel cell, or the fourth preset duration threshold can be determined according to the road conditions of the current uphill section, or other determination methods, which are not limited in the embodiments of the present application. The fourth preset duration threshold T4 is less than the third preset duration threshold T3. The fourth driving scenario is: in the case of a downhill section, the braking time is less than the fourth preset duration threshold and the brake pedal stroke is greater than the preset braking stroke threshold.

[0102] Optionally, if the braking time is less than a fourth preset time threshold and the brake pedal stroke is greater than a preset braking stroke threshold, it means that the driver is driving normally on a downhill section, and the target driving scene is determined to be the fourth driving scene.

[0103] In the above step 105, the energy distribution control instruction corresponding to the target driving scenario is sent to the vehicle controller, including: Step 902, send a fourth control instruction and downhill energy consumption data to the vehicle controller, the fourth control instruction is used to enable the vehicle controller to start braking energy recovery on a downhill section to recover braking energy to the power battery, and use the fuel cell and the power battery to jointly provide downhill power energy; only use the power battery to provide energy, and when the current state of charge parameter of the power battery can guarantee the downhill energy consumption data, and the predicted state of charge parameter after the downhill is completed by the power battery alone is greater than the third preset state of charge threshold, the fuel cell is not turned on; when the current state of charge parameter cannot guarantee the downhill energy consumption data, and the predicted state of charge parameter after the downhill is completed by the power battery alone is less than the fourth preset state of charge threshold, the fuel cell is turned on in advance, so that the fuel cell and the power battery are used to jointly provide downhill power energy.

[0104] Among them, the fourth control instruction is a "downhill" instruction, that is, the fourth control instruction does not indicate whether to recover kinetic energy of the power battery, but only includes predicted road information. The downhill energy consumption data is Q2. The third preset state of charge threshold can be 90%, and the fourth preset state of charge threshold can be 80%.

[0105] Optionally, when the target driving scenario is the fourth driving scenario, it means that the driver and the personnel are driving on a downhill section, and when they are at a preset distance from the downhill section, "about to go downhill" and downhill energy consumption data Q2 are sent to the vehicle controller, so that the vehicle controller starts braking energy recovery on the downhill section to recover the braking energy to the power battery, and uses the fuel cell and the power battery to jointly provide downhill power energy.

[0106] Optionally, when the target driving scenario is the fourth driving scenario, it means that the driver and personnel are driving on a downhill section, and only the power battery provides power energy for the target fuel cell vehicle. When the vehicle is at a preset distance from the downhill section, "about to go downhill" and downhill energy consumption data Q2 are sent to the vehicle controller. When the current state of charge parameter Q0 of the power battery can guarantee the downhill energy consumption data Q2, and the predicted state of charge parameter after the downhill is completed by the power battery alone is greater than 90% of the third preset state of charge threshold, the fuel cell is not turned on; when the current state of charge parameter Q0 cannot guarantee the downhill energy consumption data Q2, and the predicted state of charge parameter after the downhill is completed by only the power battery is less than 80% of the fourth preset state of charge threshold, the fuel cell is turned on in advance, so that the fuel cell and the power battery are used to jointly provide downhill power energy.

[0107] In an embodiment of the present application, a corresponding driving scenario can be determined based on the predicted road section and throttle information, and a corresponding control instruction can be determined based on the driving scenario, so that the vehicle controller distributes energy according to the corresponding control instruction, which can effectively manage the energy of the target fuel cell vehicle, increase the cruising range of the target fuel cell vehicle, and reduce the fuel consumption of the fuel cell or the power consumption of the power battery, thereby reducing the operating cost of the target fuel cell vehicle.

[0108] Based on the same inventive concept, the embodiments of the present application also provide an energy management device based on digital twins corresponding to the energy management method based on digital twins. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the above-mentioned energy management method based on digital twins in the embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0109] Fig.10 A schematic diagram of the structure of an energy management device based on digital twins provided in an embodiment of the present application is shown in FIG. Fig.10 As shown, the device comprises: The receiving module 1001 is used to receive the monitoring instruction uploaded by the vehicle controller of the target fuel cell vehicle, and the monitoring instruction includes: the positioning information, the driving direction, and the identification information of the target driver of the target fuel cell vehicle; The first determination module 1002 is used to match the target twin model from multiple sub-twin models in the digital twin model of the target fuel cell vehicle according to the positioning information and the driving direction, and determine that the driving path corresponding to the target twin model is the current driving path; wherein the multiple sub-twin models are respectively used to represent multiple driving paths of multiple target fuel cell vehicles; The second determination module 1003 is used to determine the predicted road section on the current driving path according to the positioning information; The third determination module 1004 is used to determine the target driving scenario of the target driver from multiple driving scenarios of the target twin model according to the identification information of the target driver and the predicted road section; different driving scenarios correspond to different energy allocation strategies; The allocation module 1005 is used to send energy allocation control instructions corresponding to the target driving scenario to the vehicle controller, and the energy allocation control instructions are used to enable the vehicle controller to allocate energy to the power battery and fuel cell on the target fuel cell vehicle based on the energy allocation strategy corresponding to the energy allocation control instructions.

[0110] Optionally, the first determination module 1002 is further used to: obtain multiple groups of historical driving data of the target fuel cell vehicle, each group of historical driving data includes: road condition data and driving condition data during a driving process; According to the identification information of the target fuel cell vehicle and multiple groups of historical driving data of the target fuel cell vehicle, digital twin modeling is performed respectively to obtain multiple sub-twin models of the target fuel cell vehicle.

[0111] Optionally, the driving condition data includes: vehicle state data and driving condition data; the first determination module 1002 is specifically used to: determine the driving road condition data according to the vehicle state data, the driving condition data and the road condition data, and the driving road condition data includes: driving road condition data of multiple specific sections on a driving path; Optionally, the first determination module 1002 is specifically used to perform digital twin modeling based on driving condition data of multiple specific road sections, driving condition data of multiple turning nodes, and road condition data to obtain a sub-twin model of the target fuel cell vehicle.

[0112] Optionally, each set of historical driving data includes: energy consumption data and braking recovery energy data of multiple position points during a driving process; the first determination module 1002 is further used to: determine the energy consumption data and braking recovery energy data of multiple specific road sections according to the energy consumption data and braking recovery energy data of the multiple position points; Optionally, the first determination module 1002 is specifically used to perform digital twin modeling based on driving condition data, energy consumption data and braking energy recovery data of multiple specific road sections, driving condition data and road condition data of multiple turning nodes, to obtain a sub-twin model of the target fuel cell vehicle.

[0113] Optionally, the third determination module 1004 is specifically configured to: obtain historical driving behavior data of the target driver according to the identification information of the target driver; Based on historical driving behavior data and predicted road sections, the target driving scenario of the target driver is determined from multiple driving scenarios.

[0114] Optionally, the third determination module 1004 is specifically configured to: if the predicted road section is an uphill road section, determine the target driving scene from a plurality of driving scenes of the uphill road section according to the uphill accelerator pedal pressing duration and the accelerator pedal opening in the historical driving behavior data; Alternatively, if the predicted road section is a downhill section, the target driving scene is determined from multiple driving scenes of the downhill section according to the braking duration and brake pedal travel in the historical driving behavior data.

[0115] Optionally, the third determination module 1004 is specifically configured to: determine that the target driving scene is the first driving scene if the uphill accelerator pedal pressing time is greater than a first preset time threshold and the accelerator pedal opening is greater than a first preset opening threshold; Optionally, the allocation module 1005 is specifically used to: send a first control instruction to the vehicle controller, the first control instruction is used to enable the vehicle controller to start the fuel cell in advance, so as to use the fuel cell and the power battery to jointly provide power energy.

[0116] Optionally, the third determination module 1004 is specifically configured to: determine that the target driving scene is the second driving scene if the uphill accelerator pedal pressing duration is less than a second preset duration threshold and the accelerator pedal opening is greater than a first preset opening threshold; Optionally, the allocation module 1005 is specifically used to: send a second control instruction and uphill energy consumption data to the vehicle controller, the second control instruction is used to enable the vehicle controller not to turn on the fuel cell when the current state of charge parameters of the power battery can guarantee the uphill energy consumption data, and only the predicted state of charge parameters after the power battery completes the climb are greater than the first preset state of charge threshold; when the current state of charge parameters cannot guarantee the energy consumption data, and only the predicted state of charge parameters after the power battery completes the climb are less than the second preset state of charge threshold, turn on the fuel cell in advance, so as to use the fuel cell and the power battery to jointly provide climbing power energy.

[0117] Optionally, the third determination module 1004 is specifically configured to: determine that the target driving scenario is a third driving scenario if the braking duration is greater than a third preset duration threshold and the brake pedal travel is greater than a preset braking travel threshold; Optionally, the allocation module 1005 is specifically used to: send a third control instruction to the vehicle controller, the third control instruction is used to enable the vehicle controller to start braking energy recovery on a downhill section to recover the braking energy to the power battery, and turn off the fuel cell to only use the power battery to provide downhill power energy.

[0118] Optionally, the third determination module 1004 is specifically configured to: determine that the target driving scenario is a fourth driving scenario if the braking duration is less than a fourth preset duration threshold and the brake pedal travel is greater than a preset braking travel threshold; Optionally, the allocation module 1005 is specifically used to: send a fourth control instruction and downhill energy consumption data to the vehicle controller, the fourth control instruction is used to enable the vehicle controller to start braking energy recovery on a downhill section to recover braking energy to the power battery, and use the fuel cell and the power battery to jointly provide downhill power energy; only use the power battery to provide energy, and when the current state of charge parameters of the power battery can guarantee the downhill energy consumption data, and the predicted state of charge parameters after the power battery completes the downhill only are greater than the third preset state of charge threshold, the fuel cell is not turned on; when the current state of charge parameters cannot guarantee the downhill energy consumption data, and the predicted state of charge parameters after the power battery completes the downhill only are less than the fourth preset state of charge threshold, the fuel cell is turned on in advance, so that the fuel cell and the power battery are used to jointly provide downhill power energy.

[0119] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0120] The present application also provides a cloud server. Fig.11 A schematic diagram of the structure of a cloud server provided in an embodiment of the present application is shown in FIG. Fig.11 As shown, the cloud server 1100 includes: a processor 1101, a memory 1102, and optionally, a bus 1103. The memory 1102 stores machine-readable instructions executable by the processor 1101. When the cloud server 1100 is running, the processor 1101 communicates with the memory 1102 through the bus 1103. When the machine-readable instructions are executed by the processor 1101, the steps of the energy management method based on digital twins are performed.

[0121] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned energy management method based on digital twins are executed.

[0122] The present application also provides an energy management system. Fig.12 A schematic diagram of the structure of an energy management system provided in an embodiment of the present application is shown in FIG. Fig.12 As shown, the energy management system includes: a cloud server 1100 and a vehicle controller 1201, and the cloud server 1100 and the vehicle controller 1201 are communicatively connected. The cloud server 1100 is used to execute the steps of the energy management method based on digital twins.

[0123] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0124] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or part of the technical solution that contributes to the prior art or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk and other media that can store program code.

[0125] The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. An energy management method based on digital twins, characterized in that: Applied to a cloud server, the method comprises: Receiving a monitoring instruction uploaded by a vehicle controller of a target fuel cell vehicle, the monitoring instruction including: positioning information, driving direction, and identification information of a target driver of the target fuel cell vehicle; According to the positioning information and the driving direction, a target twin model is matched from a plurality of sub-twin models in the digital twin model of the target fuel cell vehicle, and a driving path corresponding to the target twin model is determined to be a current driving path; wherein the plurality of sub-twin models are respectively used to characterize a plurality of driving paths of the plurality of target fuel cell vehicles; Determining a predicted road section on the current driving path according to the positioning information; According to the identification information of the target driver and the predicted road section, a target driving scenario of the target driver is determined from multiple driving scenarios of the target twin model; different driving scenarios correspond to different energy allocation strategies; An energy distribution control instruction corresponding to the target driving scenario is issued to the vehicle controller, and the energy distribution control instruction is used to enable the vehicle controller to distribute energy to the power battery and fuel cell on the target fuel cell vehicle based on the energy distribution strategy corresponding to the energy distribution control instruction.

2. The energy management method based on digital twin according to claim 1 is characterized in that: The method further comprises: Before matching the target twin model from the multiple sub-twin models, multiple groups of historical driving data of the target fuel cell vehicle are obtained, each group of historical driving data includes: road condition data and driving condition data during one driving process; According to the identification information of the target fuel cell vehicle and the multiple groups of historical driving data of the target fuel cell vehicle, digital twin modeling is performed respectively to obtain the multiple sub-twin models of the target fuel cell vehicle.

3. The energy management method based on digital twin according to claim 2 is characterized in that: The driving condition data includes: vehicle status data and driving condition data; The digital twin modeling is performed respectively according to the identification information of the target fuel cell vehicle and the multiple groups of historical driving data of the target fuel cell vehicle to obtain the multiple sub-twin models of the target fuel cell vehicle, including: Determine driving condition data according to the vehicle state data, the driving condition data and the road condition data, wherein the driving condition data includes: driving condition data of multiple specific sections on a driving path; Determine turning driving condition data according to the driving condition data and the road condition data, wherein the turning driving condition data includes: driving condition data of a plurality of turning nodes on the one driving path; Digital twin modeling is performed based on the driving condition data of the multiple specific road sections, the driving condition data of the multiple turning nodes, and the road condition data to obtain a sub-twin model of the target fuel cell vehicle.

4. The energy management method based on digital twin according to claim 3 is characterized in that: Each set of historical driving data includes: energy consumption data and braking recovery energy data of multiple position points during the driving process; the method also includes: Before performing digital twin modeling, determining the energy consumption data and the braking recovery energy data of the multiple specific road sections according to the energy consumption data and the braking recovery energy data of the multiple location points; The digital twin modeling is performed according to the driving condition data of the multiple specific road sections, the driving condition data of the multiple turning nodes and the road condition data to obtain a sub-twin model of the target fuel cell vehicle, including: Digital twin modeling is performed based on the driving condition data, energy consumption data and brake recovery energy data of the multiple specific road sections, the driving condition data of the multiple turning nodes and the road condition data to obtain a sub-twin model of the target fuel cell vehicle.

5. The energy management method based on digital twin according to claim 1 is characterized in that: The determining, according to the identification information of the target driver and the predicted road section, a target driving scenario of the target driver from multiple driving scenarios of the target twin model includes: Acquiring historical driving behavior data of the target driver according to the identification information of the target driver; According to the historical driving behavior data and the predicted road section, a target driving scenario of the target driver is determined from the multiple driving scenarios.

6. The energy management method based on digital twin according to claim 5 is characterized in that: The determining, based on the historical driving behavior data and the predicted road section, a target driving scenario of the target driver from the multiple driving scenarios includes: If the predicted road section is an uphill road section, determining the target driving scene from a plurality of driving scenes of the uphill road section according to the uphill accelerator pedal pressing duration and the accelerator pedal opening in the historical driving behavior data; Alternatively, if the predicted road section is a downhill section, the target driving scene is determined from a plurality of driving scenes of the downhill section according to the braking duration and the brake pedal travel in the historical driving behavior data.

7. The energy management method based on digital twin according to claim 6 is characterized in that: The determining the target driving scene from a plurality of driving scenes on the uphill road section according to the uphill accelerator pedal pressing duration and the accelerator pedal opening in the historical driving behavior data includes: If the uphill accelerator pedal pressing time is greater than a first preset time threshold and the accelerator pedal opening is greater than a first preset opening threshold, determining that the target driving scene is the first driving scene; The sending of the energy distribution control instruction corresponding to the target driving scenario to the vehicle controller includes: A first control instruction is issued to the vehicle controller, wherein the first control instruction is used to enable the vehicle controller to start the fuel cell in advance, so as to use the fuel cell and the power battery to jointly provide power energy.

8. The energy management method based on digital twin according to claim 6 is characterized in that: The determining the target driving scene from a plurality of driving scenes on the uphill road section according to the uphill accelerator pedal pressing duration and the accelerator pedal opening in the historical driving behavior data includes: If the uphill accelerator pedaling duration is less than a second preset duration threshold and the accelerator pedal opening is greater than a first preset opening threshold, determining that the target driving scenario is the second driving scenario; The sending of the energy distribution control instruction corresponding to the target driving scenario to the vehicle controller includes: A second control instruction and uphill energy consumption data are sent to the vehicle controller, wherein the second control instruction is used to enable the vehicle controller not to turn on the fuel cell when the current state of charge parameters of the power battery can guarantee the uphill energy consumption data and only when the predicted state of charge parameters of the power battery after completing the climb are greater than the first preset state of charge threshold; and to turn on the fuel cell in advance when the current state of charge parameters cannot guarantee the energy consumption data and only when the predicted state of charge parameters of the power battery after completing the climb are less than the second preset state of charge threshold, so as to use the fuel cell and the power battery to jointly provide climbing power energy.

9. The energy management method based on digital twin according to claim 6, characterized in that: The step of determining the target driving scenario from a plurality of driving scenarios on the downhill section according to the braking duration and the brake pedal travel in the historical driving behavior data includes: If the braking time is greater than a third preset time threshold and the brake pedal stroke is greater than a preset braking stroke threshold, determining that the target driving scenario is a third driving scenario; The sending of the energy distribution control instruction corresponding to the target driving scenario to the vehicle controller includes: A third control instruction is sent to the vehicle controller, and the third control instruction is used to enable the vehicle controller to start braking energy recovery on the downhill section to recover the braking energy to the power battery, and to turn off the fuel cell to only use the power battery to provide downhill power energy.

10. A cloud server, characterized in that: include: A memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the energy management method based on digital twins as described in any one of claims 1 to 9 are performed.

11. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the energy management method based on digital twins as described in any one of claims 1 to 9 are executed.

Images