Method for determining energy management strategy of vehicle and related device

Abstract

The embodiment of the invention provides a method for determining an energy management strategy of a vehicle and a related device, and relates to the technical field of vehicle energy management. And the energy management strategy is determined according to the target whole vehicle demand power corresponding to the mode that the energy consumption is minimum based on the prediction information, so that the energy consumption of the vehicle can be minimum, and the energy consumption of the vehicle can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle energy management, and more particularly, to a method for determining an energy management strategy of a vehicle and a related device. BACKGROUND

[0002] At present, with the development of new energy vehicles, the classification of power modes of plug-in hybrid electric vehicles (PHEV) is more and more diverse, including pure electric priority mode, forced pure electric mode, fuel priority mode and power preservation mode, etc.

[0003] However, the pure electric priority mode, the forced pure electric mode, the fuel priority mode and the power preservation mode, etc. are generally to set the priority of engine driving or driving motor providing power. For example, the pure electric priority mode indicates that the driving motor is preferred to provide power, the forced pure electric mode indicates that only the driving motor provides power, the fuel priority mode indicates that the engine is preferred to provide power, and the power preservation mode indicates that the battery needs to maintain the power above a certain threshold, that is, when the battery power is below the threshold, the engine is preferred to provide power.

[0004] However, the current power mode can only set the priority of engine driving or driving motor providing power, and the energy consumption of the vehicle still needs to be reduced. SUMMARY

[0005] The embodiments of the present application provide a method for determining an energy management strategy of a vehicle and a related device, which can reduce the energy consumption of the vehicle.

[0006] In a first aspect, an embodiment of the present application provides a method for determining an energy management strategy for a vehicle, wherein the vehicle includes an engine for providing power, a drive motor for providing power, and a battery for providing energy to the drive motor. The method includes: obtaining prediction information corresponding to multiple future moments of the vehicle in a future time period, the prediction information includes power information, and the power information includes vehicle speed and acceleration; for any future moment, based on the prediction information corresponding to the future moment, determining multiple vehicle power requirements corresponding to the future moment, the vehicle power requirements include power requirements for meeting the power information, and the power requirements include a first power requirement when the engine provides power and a second power requirement when the drive motor provides power. The second required power; for any future moment, based on the multiple vehicle required powers corresponding to the future moment, determine the multiple energy consumptions corresponding to the future moment, and the multiple energy consumptions correspond one to one to the multiple vehicle required powers; for any future moment, determine the minimum energy consumption among the multiple energy consumptions corresponding to the future moment, and based on the vehicle required power corresponding to the minimum energy consumption, determine it as the target vehicle required power corresponding to the future moment; based on the target vehicle required powers corresponding to each of the multiple future moments, determine the energy management strategy of the vehicle in the future time period, and the energy management strategy is used to represent the total energy that the engine and battery need to provide at each future moment and the distribution method of the total energy.

[0007] In this embodiment, by obtaining prediction information corresponding to multiple future moments of the vehicle in the future time period, the prediction information includes power information, and the power information includes vehicle speed and acceleration; for any future moment, based on the prediction information corresponding to the future moment, multiple vehicle power requirements corresponding to the future moment are determined, and the vehicle power requirements include the power required to meet the power information, and the power required power includes a first power requirement when the engine provides power and a second power requirement when the drive motor provides power; for any future moment, based on the multiple vehicle power requirements corresponding to the future moment, multiple energy consumptions corresponding to the future moment are determined, and the multiple energy consumptions are correlated with the multiple vehicle power requirements. Find the one-to-one correspondence between power; for any future moment, determine the minimum energy consumption among the multiple energy consumptions corresponding to the future moment, and determine the target vehicle demand power corresponding to the future moment based on the vehicle demand power corresponding to the minimum energy consumption; based on the target vehicle demand power corresponding to each of the multiple future moments, determine the energy management strategy of the vehicle in the future time period. The energy management strategy is used to represent the total energy that the engine and battery need to provide at each future moment and the distribution method of the total energy. Since the energy management strategy is determined by selecting the target vehicle demand power corresponding to the minimum energy consumption, the energy consumption of the vehicle can be minimized, thereby reducing the energy consumption of the vehicle.

[0008] In a possible implementation, the first demand power includes a power demand power of the engine, and the second demand power includes a power demand power of the driving motor and a demand power of thermal management of the battery.

[0009] In the embodiment, when the power demand power of the driving motor is not zero, it indicates that the driving motor is providing power, and at this time, the thermal management of the battery is needed, that is, when the demand power considering the power provided by the driving motor is considered, the power needed by the thermal management is also considered, so that the accuracy of the determined vehicle demand power can be improved, and the accuracy of the energy management can be improved.

[0010] In a possible implementation, the prediction information further includes a first initial temperature of the battery, and the demand power of the thermal management of the battery is determined based on the first initial temperature and a first target temperature of the battery corresponding to the future moment, and the thermal management is used to adjust the temperature of the battery from the first initial temperature to a floating range of the first target temperature.

[0011] In the embodiment, the demand power of the thermal management of the battery corresponding to the future moment is determined based on the first initial temperature and the first target temperature of the battery corresponding to the future moment, and the thermal management is used to adjust the temperature of the battery from the first initial temperature to a floating range of the first target temperature, so that the demand power of the thermal management can be more accurately determined, and the accuracy of the energy management can be improved.

[0012] In a possible implementation, the prediction information further includes road condition information, and the multiple vehicle demand powers corresponding to the future moment are determined based on the prediction information corresponding to the future moment, including: determining the power demand power in the multiple vehicle demand powers corresponding to the future moment based on the power information corresponding to the future moment and the road condition represented by the road condition information.

[0013] In the embodiment, the power demand power in the multiple vehicle demand powers corresponding to the future moment is determined based on the power information corresponding to the future moment and the road condition represented by the road condition information, so that the accuracy of the determined power demand power can be improved, and the accuracy of the energy management can be improved.

[0014] In a possible implementation, the prediction information further includes a battery state of charge of the battery, and the multiple vehicle demand powers corresponding to the future moment are determined based on the prediction information corresponding to the future moment, including: determining the power demand power in the multiple vehicle demand powers corresponding to the future moment based on the battery state of charge of the battery corresponding to the future moment and the power information, so that the battery state of charge of the battery is not lower than a state of charge threshold.

[0015] In the embodiment, the power demand power in the plurality of vehicle demand powers corresponding to the future moment is determined based on the battery state of charge and the power information of the battery corresponding to the future moment, so that the battery state of charge of the battery is not lower than the state of charge threshold, that is, the power demand power is determined considering the battery state of charge, and thus the accuracy of determining the power demand power can be improved, and the accuracy of energy management can be improved.

[0016] In a possible implementation, the vehicle further includes an electric appliance, the prediction information further includes working information of the electric appliance, and the vehicle demand power further includes electric appliance demand power for meeting the working information. The plurality of vehicle demand powers corresponding to the future moment are determined based on the prediction information corresponding to the future moment, including: the electric appliance demand power in the plurality of vehicle demand powers corresponding to the future moment is determined based on the working information of the electric appliance corresponding to the future moment.

[0017] In the embodiment, the electric appliance demand power in the plurality of vehicle demand powers corresponding to the future moment is determined based on the working information of the electric appliance corresponding to the future moment, and thus the vehicle demand power is determined based on the electric appliance demand power and the power demand power. Since the electric appliance demand power of the electric appliance is considered, the accuracy of the obtained vehicle demand power can be improved, and the accuracy of energy distribution can be improved.

[0018] In a possible implementation, the electric appliance includes a compressor for controlling the temperature of a cabin space of the vehicle, and the working information of the compressor includes a floating range in which the temperature of the cabin space is adjusted from a second initial temperature to a second target temperature. The electric appliance demand power in the plurality of vehicle demand powers corresponding to the future moment is determined based on the working information of the electric appliance corresponding to the future moment, including: the electric appliance demand power in the plurality of vehicle demand powers corresponding to the future moment is determined based on the working information of the compressor corresponding to the future moment, and the electric appliance demand power includes the demand power of the compressor, and the demand power of the compressor represents the power required in the floating range in which the temperature of the cabin space is adjusted from the second initial temperature to the second target temperature.

[0019] In the embodiment, the electric appliance demand power in the plurality of vehicle demand powers corresponding to the future moment is determined based on the working information of the compressor corresponding to the future moment, and the electric appliance demand power includes the demand power of the compressor, and the demand power of the compressor represents the power required in the floating range in which the temperature of the cabin space is adjusted from the second initial temperature to the second target temperature, so that the demand power of the compressor can be more accurately determined, and the accuracy of energy management can be improved.

[0020] In a second aspect, the application provides a device for determining an energy management strategy of a vehicle, including functional modules for implementing the above method.

[0021] In a third aspect, an electronic device is provided, including a processor and a memory, wherein: the memory is configured to store a computer program; and the processor is configured to execute the program stored in the memory to implement the method described above.

[0022] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. When the computer program is executed by a processor, the method described above is implemented. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 A flowchart of a method for determining an energy management strategy of a vehicle is provided for an embodiment of the present application; Figure 2 A schematic diagram of obtaining a demand power is provided for an embodiment of the present application; Figure 3 A flowchart of a method for determining an energy management strategy of a vehicle is provided for another embodiment of the present application; Figure 4 A structural schematic diagram of a device for determining an energy management strategy of a vehicle is provided for an embodiment of the present application; Figure 5 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the technical problems, technical solutions and beneficial effects of the present application clearer, the present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0025] With the development of new energy vehicles, the classification of power modes of plug-in hybrid electric vehicles (PHEV) is becoming more and more diverse, including pure electric priority mode, forced pure electric mode, fuel priority mode and power preservation mode, etc.

[0026] However, the pure electric priority mode, the forced pure electric mode, the fuel priority mode and the power preservation mode, etc. are generally set to prioritize the engine drive or the drive motor to provide power. For example, the pure electric priority mode indicates that the drive motor is preferred to provide power, the forced pure electric mode indicates that only the drive motor provides power, the fuel priority mode indicates that the engine is preferred to provide power, and the power preservation mode indicates that the battery needs to maintain the power above a certain threshold, that is, when the battery power is below the threshold, the engine is preferred to provide power.

[0027] However, through the long-term research of the inventor, it is found that in some scenarios, the energy consumption is lower when only the engine provides power, in some other scenarios, the energy consumption is lower when only the driving motor provides power, and in some other scenarios, the energy consumption is lower when the engine and the driving motor provide power at the same time. Moreover, when the engine and the driving motor provide power, the sizes of the power provided by the engine and the driving motor respectively also lead to different energy consumption results.

[0028] However, the current power mode can only set the priority of the engine driving or the driving motor providing power, and the energy consumption of the vehicle still needs to be reduced.

[0029] Therefore, embodiments of the present application provide a method for determining an energy management strategy of a vehicle and related apparatuses, which can reduce the energy consumption of the vehicle.

[0030] Please refer to Figure 1 , Figure 1 A flowchart of a method for determining an energy management strategy of a vehicle is provided in an embodiment of the present application. The vehicle can include an engine for providing power, a driving motor for providing power, and a battery for providing energy for the driving motor. Optionally, the engine can also have the ability to provide energy for the battery, or can not have the ability to provide energy for the battery.

[0031] As shown in the method shown in Figure 1 The method can be executed by an electronic device, which can be a vehicle terminal or a server. The method can manage the energy consumption of the vehicle, as shown in the method shown in Figure 1 The method can include the following steps. S110, obtaining predicted information corresponding to each of a plurality of future time points in a future time period of the vehicle, the predicted information including power information, the power information including vehicle speed and acceleration.

[0032] In this embodiment, the predicted information can be used to represent the state or working condition of the vehicle at the future time point. In this embodiment, the predicted information includes power information, and the power information includes vehicle speed and acceleration. Therefore, obtaining the power information at the future time point can be understood as predicting that the vehicle can travel at the power information at the future time point, that is, predicting that the vehicle can travel at the vehicle speed and the acceleration at the future time point.

[0033] It should be noted that the prediction information of the embodiment can be obtained by inputting the current information of the vehicle into the model to obtain the prediction information of the vehicle at multiple future time points, or by obtaining the historical driving information and the historical state information of the vehicle, mining and analyzing the historical driving information and the historical state information, determining the higher frequency trip segments (for example, the trip segments with a frequency higher than a frequency threshold) of the vehicle, and then obtaining the prediction information corresponding to multiple future time points when the vehicle is driving on the target trip segment (also referred to as the target trip segment) when the vehicle enters the higher frequency trip segment. The prediction information can be the characteristics (for example, driving characteristics or working condition characteristics) mined from the historical information (historical driving information and historical state information) of the vehicle when the vehicle is driving on the target trip segment.

[0034] For example, the mining of the historical driving information (referred to as driving information) and the historical state information (referred to as state information) is described below. It should be understood that mining the historical driving information (referred to as driving information) and the historical state information (referred to as state information) can reduce the computing resources required to obtain the prediction information.

[0035] Specifically, the driving information of the driver, such as the trip route, the trip start time, the trip end time, the driving duration, the geographic position, the driving mode, the average speed, the temperature in the vehicle, etc., can be obtained through the data reported by the telematics box (T-BOX) at the vehicle end, and the travel habits of the driver can be analyzed. In terms of driving habits, the speed, acceleration, braking force and frequency of the driver are continuously monitored through the signals at the vehicle end. Then, intelligent mining and analysis are performed based on the k-means clustering algorithm in machine learning, and the output is the trip characteristics of the driver, such as high-frequency trip characteristics, trip road condition prediction, optimal cooling mileage, optimal heating mileage, and trip energy consumption expectation, etc. In terms of trip road conditions, real-time road condition information is obtained through navigation information and various sensors equipped in the vehicle, such as radar, camera, etc. For example, the average speed of the navigation segment, the congestion degree, the road speed limit, the start / stop state of the traffic light at the intersection, the road speed limit, the uphill, the downhill and the flat road, etc. High-frequency trip characteristics can represent trips (also referred to as segments) with a high driving frequency, trip road condition prediction represents the road conditions of the trip segment with a high driving frequency, for example, congestion or smoothness, for example, uphill or downhill, etc. The optimal cooling mileage can be the mileage of the vehicle performing the cooling function, for example, the mileage of the vehicle performing the cooling function of the battery or the mileage of the vehicle performing the cooling function of the cabin space. The optimal heating mileage can be the mileage of the vehicle performing the heating function, for example, the mileage of the vehicle performing the heating function of the battery or the mileage of the vehicle performing the heating function of the cabin space. The trip energy consumption expectation can be the energy consumption of the high-frequency trip.

[0036] In addition, data reported by the vehicle-side T-BOX can be used to obtain vehicle status information, such as minimum and maximum battery temperatures, average battery temperature, battery charge status, current, voltage, compressor speed, circulation mode, and coolant temperature. This allows analysis of various vehicle operating conditions, including power output ratios under different road conditions, energy consumption, and battery charge and discharge status. Compressor speed can refer to the speed of the compressor used to cool or heat the vehicle's cabin, and the circulation mode can be internal or external. Intelligent mining and analysis using the k-means clustering algorithm in machine learning is then performed, resulting in the output of vehicle operating characteristics, such as cooling battery efficiency, cooling requests during driving, heating requests during driving, heating requests during charging, initial battery temperature, and initial cabin temperature.

[0037] S120. For any future moment, based on the prediction information corresponding to the future moment, determine multiple vehicle power requirements corresponding to the future moment, where the vehicle power requirements include the power requirements for satisfying the power information, and the power requirements include a first power requirement when the engine provides power and a second power requirement when the drive motor provides power.

[0038] Among them, the vehicle power requirement may refer to the power required when the vehicle is running. In this embodiment, the vehicle power requirement includes the power requirement power used to meet the power information, that is, how much power is needed to meet the power information. In this embodiment, the power requirement power includes a first power requirement when the engine provides power and a second power requirement when the drive motor provides power. The first power requirement may be zero or a number greater than zero. The power requirement power may be the sum of the first power requirement and the second power requirement. In this embodiment, the required power may also be referred to as power demand.

[0039] Optionally, the first power requirement includes the power requirement of the engine, and the second power requirement includes the power requirement of the drive motor. When the power requirement of the engine is zero, the engine does not provide power, and when the power requirement of the engine is greater than zero, the engine provides power. When the power requirement of the drive motor is zero, the drive motor may not provide power. When the power requirement of the drive motor is less than zero, the engine may provide energy to the battery, or the drive motor may convert mechanical energy into electrical energy due to deceleration. When the power requirement of the drive motor is greater than zero, the drive motor may provide power.

[0040] In a possible implementation, the second demand power further includes a demand power for thermal management of the battery. Generally, if the power demand power for driving the motor is not zero, the demand power for thermal management of the battery can also be greater than zero. Alternatively, the second demand power can be the sum of the demand power for thermal management and the power demand power for driving the motor.

[0041] In the embodiment, when the power demand power for driving the motor is not zero, it indicates that the motor is powered, and at this time, the battery needs to provide energy for driving the motor, and at this time, the battery generates heat, and the battery needs to be thermally managed, so that the temperature of the battery is maintained within a certain range, and the working safety of the battery is ensured.

[0042] In another possible implementation, the demand power for thermal management of the battery can also be not considered, which can improve the efficiency of energy management.

[0043] In a possible implementation, the prediction information further includes a first initial temperature of the battery, and the demand power for thermal management of the battery is determined in the following manner: based on the first initial temperature and the first target temperature of the battery corresponding to the future time, the demand power for thermal management of the battery corresponding to the future time is determined, and the thermal management is used to adjust the temperature of the battery from the first initial temperature to the floating range of the first target temperature.

[0044] Alternatively, the floating range can be set as needed. For example, the floating range can be related to the ambient temperature, or related to the travel mileage involved in the future time period, which can be determined by predicting the distance between the destination and the starting point. Alternatively, the higher the ambient temperature, the larger the floating range, and the shorter the travel mileage, the larger the floating range. The first target temperature can be a preset temperature. The first initial temperature can be related to the ambient temperature, or related to the heat generated by discharging or charging the battery. In addition, the demand power can also be determined by considering the thermal management efficiency of the battery, which can represent the relationship between the ability of temperature control of the battery and the energy consumption. Alternatively, the first initial temperature can include the temperature of the battery when the battery is not thermally managed. When the first initial temperature is within the floating range of the first target temperature, the demand power for thermal management is low, and when the first initial temperature is outside the floating range of the first target temperature, the demand power for thermal management is high, and the greater the difference between the first initial temperature and the floating range of the first target temperature, the higher the demand power for thermal management. It should be immediately noted that the first initial temperature and the first target temperature are relative, the first initial temperature is before adjustment, and the first target temperature is after adjustment.

[0045] In another possible implementation, the demand power for thermal management can be a preset value, which can improve the efficiency of energy management.

[0046] S130, for any future time, based on the plurality of whole vehicle demand powers corresponding to the future time, determine the plurality of energy consumptions corresponding to the future time, the plurality of energy consumptions correspond one-to-one to the plurality of whole vehicle demand powers.

[0047] In this embodiment, after determining the plurality of whole vehicle demand powers corresponding to the future time, for each whole vehicle demand power in the plurality of whole vehicle demand powers, the corresponding energy consumption can be determined. The energy consumption can be the product of the whole vehicle demand power and the time, for example, the product of the time period between the whole vehicle demand power and the future time. Alternatively, according to the whole vehicle power calculation formula , the work done by the battery consumption power represents the work W (i.e. energy consumption) done by the whole vehicle. In this embodiment, since the driving motor and / or the engine may be selected to provide power, but different results of providing power may result in different energy consumptions, therefore this step needs to determine the plurality of energy consumptions corresponding to the future time based on the plurality of whole vehicle demand powers corresponding to the future time.

[0048] S140, for any future time, determine the minimum energy consumption in the plurality of energy consumptions corresponding to the future time, and based on the whole vehicle demand power corresponding to the minimum energy consumption, determine the target whole vehicle demand power corresponding to the future time.

[0049] In this embodiment, the minimum energy consumption in the plurality of energy consumptions corresponding to the future time is determined, and based on the whole vehicle demand power corresponding to the minimum energy consumption, the target whole vehicle demand power corresponding to the future time is determined, so that the energy consumed by the target whole vehicle demand power is the least, that is, the energy consumption is the lowest.

[0050] S150, based on the target whole vehicle demand powers corresponding to the plurality of future times respectively, determine the energy management strategy of the vehicle in the future time period, the energy management strategy is used to represent the total energy required to be provided by the engine and the battery at each future time and the allocation manner of the total energy.

[0051] In this embodiment, the total energy provided by the engine and the battery at the future time point can be determined based on the target vehicle demand power determined at the future time point, for example, can be the product of the target vehicle demand power and the time period between the future time point and the next future time point, as the total energy provided by the engine and the battery at the future time point. In this embodiment, the total energy can be constrained by the total energy provided by the engine and the battery at the future time point, that is, the sum of the energy generated by the engine and the battery at the future time point does not exceed the total energy required to be provided at the future time point. The total energy distribution manner refers to how to distribute the energy, for example, the proportion of the distributed energy, etc. In this embodiment, the total energy distribution manner can include energy distribution of the engine and the drive motor to provide power demand power according to the first demand power and the second demand power. Optionally, the distribution result can also include energy distribution to the electrical appliances to meet the electrical appliance demand power.

[0052] Optionally, the plurality of vehicle demand powers corresponding to the same future time point are different, for example, the plurality of power demand powers are different, that is, the first demand power and / or the second demand power are different.

[0053] In a possible implementation, the prediction information further includes a battery state of charge of the battery, and the plurality of vehicle demand powers corresponding to the future time point are determined based on the prediction information corresponding to the future time point, including: The power demand power in the plurality of vehicle demand powers corresponding to the future time point is determined based on the battery state of charge of the battery and the power information corresponding to the future time point, so that the battery state of charge of the battery is not lower than a state of charge threshold.

[0054] The battery state of charge (SOC) is a parameter in battery management, which is used to quantify the remaining power of the battery. The state of charge threshold can be pre-set, for example, can be a default threshold, or can be a threshold set in the power saving mode, which is not limited herein. In this embodiment, if the battery state of charge of the battery reaches the state of charge threshold, the power demand power of the drive motor can be zero, and if the battery state of charge of the battery is lower than the state of charge threshold, the power demand power of the drive motor can be less than zero, that is, the engine can charge the battery. It should be noted that the battery state of charge of the battery is not lower than the state of charge threshold can be the final target that the battery state of charge is not lower than the state of charge threshold, but there can be a case that the battery state of charge is lower than the state of charge threshold in the intermediate process, for example, the battery state of charge reaches the state of charge threshold but encounters an uphill that requires the drive motor to provide power, at this time, the battery state of charge can be lower than the state of charge threshold, but the battery state of charge will not be lower than the state of charge threshold subsequently.

[0055] In another possible implementation, the battery state of charge of the battery can also be not considered, so as to improve the efficiency of energy management and reduce the computing resource required by energy management.

[0056] In a possible implementation, the vehicle further includes electrical appliances, the prediction information further includes working information of the electrical appliances, and the vehicle demand power further includes electrical appliance demand power for meeting the working information. The multiple vehicle demand powers corresponding to the future time points are determined based on the prediction information corresponding to the future time points, including: The electrical appliance demand power in the multiple vehicle demand powers corresponding to the future time points is determined based on the working information of the electrical appliances corresponding to the future time points.

[0057] In this embodiment, the electrical appliances of the vehicle can include but are not limited to a compressor or other electrical appliances for controlling the temperature of a cabin space of the vehicle. The other electrical appliances can include but are not limited to a light module, a signal interaction module, an audio module and other electrical appliances requiring power supply. Taking the electrical appliance as the compressor for example, the working information of the compressor can include a floating range for adjusting the temperature of the cabin space from a second initial temperature to a second target temperature, the working information of the light module can include the brightness of the light, the working information of the audio module can include the size of the volume, and the like. In this embodiment, the vehicle demand power can be the sum of the power demand power and the electrical appliance demand power.

[0058] In another possible implementation, the electrical appliance demand power can also be not considered, so as to improve the accuracy of energy management.

[0059] In a possible implementation, the electrical appliances include a compressor for controlling the temperature of a cabin space of the vehicle, and the working information of the compressor includes a floating range for adjusting the temperature of the cabin space from a second initial temperature to a second target temperature. The electrical appliance demand power in the multiple vehicle demand powers corresponding to the future time points is determined based on the working information of the electrical appliances corresponding to the future time points, including: The electrical appliance demand power in the multiple vehicle demand powers corresponding to the future time points is determined based on the working information of the compressor corresponding to the future time points. The electrical appliance demand power includes the demand power of the compressor, and the demand power of the compressor indicates the power required in the floating range for adjusting the temperature of the cabin space from the second initial temperature to the second target temperature.

[0060] Optionally, the floating range can be set as needed, for example, it can be related to the travel mileage involved in the future time period, which can be determined by predicting the distance between the destination and the departure location. Optionally, the shorter the travel mileage, the larger the floating range. The second target temperature can be a preset temperature, for example, a target temperature frequently set by the user in the air conditioning mode, or an automatically regulated temperature, which is not limited herein. The second initial temperature can be related to the ambient temperature. In addition, the temperature control efficiency of the battery, which can represent the relationship between the ability of temperature control of the cabin space and energy consumption, can also be considered to determine the demand power. When the second initial temperature is within the floating range of the second target temperature, the demand power of the compressor is low, and when the second initial temperature is outside the floating range of the second target temperature, the demand power of the compressor is high, and the greater the difference between the second initial temperature and the second target temperature, the higher the demand power of the compressor. It should be immediately noted that the second initial temperature and the second target temperature are relative, the second initial temperature is before adjustment, and the second target temperature is after adjustment.

[0061] Generally speaking, the power demand power and the demand power of the compressor account for a large part of the whole vehicle demand power, so after the power demand power and the demand power of the compressor are determined, the sum of the power demand power and the demand power of the compressor can be calculated, and then the sum of the power is multiplied by a coefficient greater than 1, and the approximate whole vehicle demand power can be obtained.

[0062] For ease of understanding, the determination of the demand power of the present application is described below in combination with the framework of the scheme.

[0063] Please refer to Figure 2 , Figure 2 A schematic diagram of obtaining a demand power is provided for the embodiments. As Figure 2 shown, the power demand power can be determined in combination with the vehicle speed, acceleration and thermal management parameters, and then the engine power, drive motor power demand and other electric appliance power demand can be determined in combination with the battery SOC, road conditions and temperature parameters and the like through a model algorithm.

[0064] The way of determining the power demand power in combination with the vehicle speed, acceleration and thermal management parameters, and the way of determining the engine power, drive motor power demand and other electric appliance power demand in combination with the battery SOC, road conditions and temperature parameters and the like can be referred to the above description of the embodiments, which will not be repeated here.

[0065] In another possible implementation, the demand power of the compressor can also be a preset value, which can improve the efficiency of energy management.

[0066] The prediction information further includes road condition information, and the plurality of vehicle demand powers corresponding to the future moment are determined based on the prediction information corresponding to the future moment, including: The power demand power of the plurality of vehicle demand powers corresponding to the future moment is determined based on the road condition represented by the power information corresponding to the future moment and the road condition information.

[0067] In this embodiment, the road condition information can be determined based on the road traffic information in the navigation route information. The road condition information can include at least one of first road condition information or second road condition information.

[0068] If the road condition is an uphill, the power demand power of the engine and the power demand power of the drive motor are both greater than zero, that is, the engine and the drive motor both provide power, which can ensure that the vehicle has enough power to climb uphill. If the road condition is a flat ground, at least one of the power demand power of the engine or the power demand power of the drive motor is greater than zero, that is, the engine and / or the drive motor provides power. If the road condition is a downhill, the power demand power of the drive motor is not greater than zero, that is, the drive motor does not provide power, but the drive motor can convert mechanical energy into electrical energy, so the power demand power of the drive motor is less than zero.

[0069] In this embodiment, by determining the power demand power of the plurality of vehicle demand powers corresponding to the future moment based on the road condition represented by the power information corresponding to the future moment and the first road condition information, if the road condition is an uphill, the power demand power of the engine and the power demand power of the drive motor are both greater than zero; if the road condition is a flat ground, at least one of the power demand power of the engine or the power demand power of the drive motor is greater than zero; if the road condition is a downhill, the power demand power of the drive motor is not greater than zero, in this way, the power of the vehicle can be guaranteed while reducing energy consumption.

[0070] In this embodiment, by determining the power demand power of the plurality of vehicle demand powers corresponding to the future moment based on the road condition represented by the power information corresponding to the future moment and the first road condition information, if the road condition is an uphill, the power demand power of the engine and the power demand power of the drive motor are both greater than zero; if the road condition is a flat ground, at least one of the power demand power of the engine or the power demand power of the drive motor is greater than zero; if the road condition is a downhill, the power demand power of the drive motor is not greater than zero, in this way, the power of the vehicle can be guaranteed while reducing energy consumption.

[0071] If the road condition is an uphill, the power demand power of the engine and the power demand power of the drive motor are both greater than zero, that is, the engine and the drive motor both provide power, which can ensure that the vehicle has enough power to climb uphill. If the road condition is a flat ground, at least one of the power demand power of the engine or the power demand power of the drive motor is greater than zero, that is, the engine and / or the drive motor provides power. If the road condition is a downhill, the power demand power of the drive motor is not greater than zero, that is, the drive motor does not provide power, but the drive motor can convert mechanical energy into electrical energy, so the power demand power of the drive motor is less than zero.

[0072] In this embodiment, the power information corresponding to the future moment can be adjusted based on the second road condition information, and then the power demand power in the multiple vehicle demand powers corresponding to the future moment is determined based on the adjusted power information. Optionally, if the congestion degree represented by the second road condition information is more congested than the congestion degree in the historical driving information, the power information corresponding to the future moment can be reduced, and if the congestion degree represented by the second road condition information is more smooth than the congestion degree in the historical driving information, the power information corresponding to the future moment can be increased.

[0073] In this embodiment, the power demand power in the multiple vehicle demand powers corresponding to the future moment is determined based on the power information corresponding to the future moment and the road condition represented by the second road condition information, which can improve the accuracy of the determined power demand power and improve the accuracy of energy management.

[0074] In another possible implementation, the road condition information can also not be considered, which can improve the efficiency of energy management and reduce the computing resources required for energy management.

[0075] In general, the present embodiment can include the following steps: Step 1: Obtain the driving information of the driver through the data reported by the vehicle end T-BOX, such as the trip route, the trip start time, the trip end time, the driving time, the geographic position, the driving mode, the average speed, the temperature in the vehicle, etc., and analyze the travel habits of the driver. In terms of driving habits, the speed, acceleration, braking force and frequency of the driver are continuously monitored through the vehicle end signal.

[0076] In this step, the driving information of the driver is obtained, and the travel habits of the driver are analyzed. If the driver is used to aggressive acceleration, the data of the power output of the engine and the motor in the vehicle starting and acceleration stage needs to be obtained. If the driver is used to smooth and moderate driving, the motor output and battery thermal management data need to be obtained.

[0077] Step 2: Intelligent mining analysis is performed based on the k-means clustering algorithm in machine learning, and the output is the trip characteristics of the driver, such as high-frequency trip characteristics, trip road condition prediction, optimal cooling mileage, optimal heating mileage, and trip energy consumption expectation, etc. In terms of trip road condition, real-time road condition information is obtained through navigation information and various sensors equipped in the vehicle, such as radar, camera, etc. For example, the average vehicle speed of the navigation section, the congestion degree, the road speed limit, the start / stop state of the intersection signal light, and the road speed limit, etc.

[0078] In this step, intelligent mining analysis is performed based on the k-means clustering algorithm in machine learning, and the output is the driving characteristics of the driver. Each object is assigned to the cluster corresponding to the nearest center point according to the value of each object and the K center points. According to the samples in the cluster grouping, the center point of each cluster is calculated, and the iteration is performed until the driving habits, travel habits, and other characteristics of the driver are converged.

[0079] Step 3: Obtain the state information of the vehicle, such as the minimum temperature of the battery, the maximum temperature of the battery, the average temperature of the battery, the charging status of the battery, the current, the voltage, the compressor speed, the circulation mode, the cooling liquid temperature, etc., through the data reported by the vehicle end T-BOX, and analyze the different working conditions of the vehicle. For example, the power output ratio under different road conditions, energy consumption, battery charging and discharging status, etc.

[0080] In this step, vehicle end data collection is performed in a periodic collection and trigger collection manner. If there is missing or error in collection, it will have a great impact on the data of the vehicle use part. Through the high compression time series database and edge computing engine components of the vehicle end bus data collection, prediction and planning decision can be completed without networking.

[0081] Step 4: Intelligent mining analysis is performed based on the k-means clustering algorithm in machine learning, and the output is the working condition characteristics of the vehicle, such as cooling battery efficiency, cooling request during driving, heating request during driving, heating request during charging, and initial temperature, etc.

[0082] In this step, given the vehicle condition dataset X, such as the slope, vehicle speed, engine and motor output when the vehicle is climbing uphill. The dataset has n samples, which are divided into K driver label clusters. Select the initial center point for the K cluster grouping, and calculate the distance d(K1, X1) between the n objects {X1, X2, X3, …, Xn} and the K center points.

[0083] Step 5: Obtain the road traffic information of the vehicle on the future predicted route (also known as the target section) by means of vehicle navigation route information, such as the average vehicle speed of the specified section, the road surface layer height, the start / stop state of the intersection signal light, and the road speed limit, etc. From this, the whole vehicle power demand on the driving route can be predicted. Real-time optimization algorithm is introduced to dynamically adjust the energy distribution strategy according to the current driving conditions and vehicle state. For example, in congested urban roads, the vehicle frequently starts and stops, relying more on pure electric driving, reducing the inefficient operation of the engine at low speed, and reducing fuel consumption and emissions. On the highway, the vehicle travels at a relatively stable and high speed, and according to the battery power and power demand, the engine is started in time to make it operate in the high efficiency interval to ensure the sustained power output and fuel economy of the vehicle.

[0084] In this step, the road traffic information of the car on the route is obtained through navigation route, real-time traffic, travel prediction, etc. Machine learning algorithms and models are used to identify traffic congestion, accidents, construction, etc. and compare them with historical data to update the navigation route and actual arrival time estimate in real time. By integrating road information and driving style, the vehicle energy consumption management strategy is optimized.

[0085] Step 6: Based on the above-obtained driving habits, trip characteristics, vehicle state, working condition characteristics, and road signal prediction of the vehicle's power demand in various scenarios, the vehicle's power is calculated according to the formula , the work done by the battery consumption power represents the work done by the vehicle W. The vehicle power demand is selected as the state variable, and the vehicle energy management is selected as the control variable. The process of solving the power P of the kth second is discretized until the prediction time domain k+p, and the vehicle power sequence [P(k+1), P(k+2), …, P(k+p)] in the prediction region is obtained. Where k, k+1, …, (k+p) can be corresponding to multiple future times. The multiple future times of this embodiment can be every second before reaching the destination.

[0086] In this step, the vehicle's power calculation formula , W represents the work done, t represents the time, , represents the work done by the battery, the work done by the engine. The work done by the engine and the battery under different working conditions is taken as the work done by the vehicle, and the model predictive control algorithm is adopted according to the vehicle's power calculation formula, the vehicle's power demand P is predicted, and the vehicle's energy output is intelligently adjusted to optimize the energy consumption economy of the hybrid vehicle. The vehicle power demand optimization control problem based on model predictive control can be converted into a constrained optimization control problem in a finite time domain, and the best control input that minimizes the specified objective function is obtained under the condition of meeting the specific constraints.

[0087] Step 7: According to the principle of model predictive control, the vehicle's power at P(k+1) seconds is sent to the vehicle's energy management controller. Then the backpropagation algorithm (BP) is used to solve the energy consumption curve, the discrete vehicle output power is determined, and an optimal vehicle output power curve is selected according to the energy consumption optimization in the prediction time domain. Roll optimization, repeat the above process (step 6 process).

[0088] In this step, the working process of the hybrid vehicle presents complex nonlinear characteristics, in order to accurately predict the output of the controlled object, a nonlinear model is used as the prediction model, thereby forming a nonlinear model predictive control problem. The output of the nonlinear prediction model is the total vehicle energy consumption, and the instantaneous energy consumption rate of the vehicle is obtained by using a nonlinear fitting model related to the vehicle output power. After discretization, it can be expressed as: wherein, represents the sum of the total vehicle energy consumption, (k+1) represents the sum of the total vehicle energy consumption in the k+1 second, (k) represents the sum of the total vehicle energy consumption in the k second, represents the vehicle output power. represents the instantaneous energy consumption rate under the vehicle output power, represents the duration of the instantaneous energy consumption rate under the vehicle output power, which can be 1 second, for example. can represent a dynamic correction factor.

[0089] Then, the state variables, control variables and output variables of the system are discretized according to the solving step, so as to convert the nonlinear model predictive control (NMPC) optimization problem into a discrete form: wherein, represents the vehicle output power, L(x) represents the objective function, represents the control variable. represents the k to k+i second, i represents the first future time, and H-1 represents the last future time.

[0090] Step 8: According to the optimal vehicle driving power output mode obtained in the previous steps, output vehicle driving mode switching control instructions, refrigeration mode temperature threshold, heating mode temperature threshold, etc. The refrigeration mode temperature threshold and the heating mode temperature threshold can refer to the description of the first target temperature and the second target temperature, and adjust the vehicle energy management strategy in real time through the vehicle energy management state module and the fusion judgment control module. Different road conditions have different requirements for driving force and thermal management, and the vehicle should adjust the energy distribution strategy according to these differences to achieve energy-saving, efficient and comfortable driving experience.

[0091] In this step, in order to obtain the optimal energy management input parameters of the hybrid electric vehicle, the NMPC problem is converted into a nonlinear programming (NLP) problem in a finite time domain. Based on the sequential quadratic programming (SQP) algorithm of the Newton-Lagrange method, the NLP problem is converted into a series of quadratic programming sub-problems to obtain the optimal solution. Using Taylor expansion, the nonlinear constraint optimization problem can be converted into a quadratic programming problem, and by solving the quadratic programming problem in each iteration step, the iteration point is constantly updated until the optimal solution is obtained: wherein, represents an approximate matrix of the Lagrange function matrix, represents the Lagrange function, represents the objective function, represents the equality constraints of the system, represents the inequality constraints of the system. Wherein, J represents the quadratic programming algorithm, which is the minimum value of the local quadratic approximation model of the original optimization problem at point d: is a search direction vector. It is a direction that we want to find near the point , along which moving can improve the value of the objective function. : is an nxn symmetric matrix (usually required to be positive definite or semi-positive definite). It represents the second-order information of the objective function f0(x) at point , which can be, for example, the Hessian matrix or its approximate matrix, such as the quasi-Hessian matrix obtained by the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm, the Davidon-Fletcher-Powell algorithm (DFP) and other methods. captures the curvature of the function.

[0092] : is the gradient vector (first derivative) of the objective function f0(x) at point . It represents the direction and rate of change of the function at the fastest (rising). : represents the transpose of a vector or matrix. Here it ensures that d is correctly multiplied by and By solving the minimization problem min with respect to d, the solution we get is called the search direction.

[0093] The Lagrangian function depends on the original variables (x) and Lagrange multipliers (μ, λ). The ith equality constraint function belonging to E. Requires The ith inequality constraint function belonging to I. Requires ≤ 0 or ≥ 0.

[0094] Where ∑{i∈E}: sum over all equality constraints. ∑{i∈I}: sum over all inequality constraints.

[0095] The equality constraints can be, for example, conditions that constrain equality, such as the energy provided and the energy consumed (for example, by the engine, the drive motor and the electrical appliances), and the inequality constraints can be, for example, conditions that constrain inequality, such as the temperature of the battery not exceeding the upper and lower limits of the floating range of the first target temperature, and the temperature of the cabin space not exceeding the upper and lower limits of the floating range of the second target temperature.

[0096] Exemplarily, the control result of the embodiment can be represented as follows: In the embodiment, first, the driver habit information is acquired through big data analysis; second, based on the road condition information of the vehicle navigation, a nonlinear prediction model is established, and the driving state variables of the vehicle in the future time domain are predicted by using the model; then, the target function in the prediction time domain is solved by using the sequence quadratic programming (SQP) algorithm, so as to obtain the optimal vehicle output power sequence corresponding to the vehicle at the lowest energy consumption; finally, the control variables of the optimal sequence are applied to the vehicle energy management system, so as to realize feedback rolling optimization.

[0097] In the embodiment, based on the navigation road condition information of the vehicle and the driver habit, a nonlinear model prediction control strategy method is proposed, the driving state of the vehicle in the future time domain is predicted by using the model, and the energy distribution of the hybrid electric vehicle is adjusted according to the prediction information. The energy management control strategy can not only overcome the disadvantages of the instantaneous optimization control strategy that cannot achieve global optimization, but also solve the problems of unknown future driving information and large calculation amount. Based on the navigation route and the driver habit, the algorithm model adjusts the energy distribution strategy of the vehicle in real time according to the different requirements of driving force and thermal management for different road conditions, so as to achieve energy-saving, efficient and comfortable driving experience.

[0098] Please refer to Figure 3 , Figure 3 A flowchart of a method for determining an energy management strategy of a vehicle is provided for another embodiment of the present application. As shown in Figure 3 the method can include: S301, start.

[0099] S302, initialize model predictive control parameters.

[0100] In the embodiment, the prediction time domain length (how many steps in the future to predict), the control time domain length (how many steps to optimize the control quantity), the vehicle state constraint (such as temperature range), the weight matrix initialization (the weight of the state variable and the control variable in the objective function), etc. can be set.

[0101] S303, define the objective function and the constraint condition.

[0102] S304, input the navigation route information.

[0103] In the embodiment, the navigation route information is used to determine the prediction information in the future time period. Specifically, the road section passing through the future time period can be determined according to the navigation route information, and then the prediction information can be determined according to the travel characteristics and state characteristics of the road section.

[0104] S305, predict the whole vehicle power demand based on the driver characteristics.

[0105] In the embodiment, the S305 can refer to the related description of 120.

[0106] S306, define the SQP parameters.

[0107] In the embodiment, the SQP parameters can include the upper limit of the iteration number, the convergence threshold tol (such as the gradient norm < 1e-4), the Hessian matrix initialization method (such as the unit matrix or the BFGS update).

[0108] S307, convert the NLP into an SQP problem and solve the search direction d.

[0109] In the embodiment, at the current point x k Second-order approximation is made for the nonlinear problem: Then, the constraint linearization is converted into a quadratic programming (QP) sub-problem. Then, the QP solver (such as the interior point method) is called to calculate the optimal direction d.

[0110] S308, whether the search direction d satisfies the condition.

[0111] In the embodiment, the conditions for judging whether the optimal solution is reached can be: condition 1: the step is small enough; condition 2: the first-order optimality is met; condition 3: the objective function descent tends to zero.

[0112] S309, solve the control sequence according to the optimal solution d.

[0113] In the embodiment, the solver outputs the optimal control sequence S310, take the first element as the current time control variable.

[0114] In this embodiment, only the following is performed (current time control variable), the next time re-rolling optimization, overcome the model error.

[0115] S311, end.

[0116] S312, selected parameters to obtain the descent direction d.

[0117] S313, update the parameter correction matrix.

[0118] In this embodiment, the Hessian matrix can be updated.

[0119] S314, k=k+1.

[0120] In this embodiment, k=k+1 update iteration counter, with the new x k+1 re-solve the QP sub-problem.

[0121] S315, whether to reach the maximum number of iterations.

[0122] In this embodiment, the maximum number of iterations may, for example, be the total number of multiple future time.

[0123] In general, in this embodiment, the control variable or reach the maximum number of iterations end.

[0124] This embodiment can be understood as a solution to obtain the minimum energy consumption, so as to determine the energy management strategy after determining the minimum energy consumption.

[0125] Please refer to Figure 4 , Figure 4 A structure diagram of a device for determining an energy management strategy of a vehicle is provided in an embodiment of the present application. The vehicle includes an engine for providing power, a drive motor for providing power, and a battery for providing energy for the drive motor. As Figure 4 The device shown in the figure can be applied to a server. The device can include an acquisition module 410, a whole vehicle demand power determination module 420, an energy consumption determination module 430, and an energy management strategy determination module 440, wherein: The acquisition module 410 is configured to acquire predicted information corresponding to each of a plurality of future time points in a future time period of the vehicle, the predicted information comprising power information, the power information comprising vehicle speed and acceleration; the vehicle demand power determination module 420 is configured to determine, for any future time point, a plurality of vehicle demand powers corresponding to the future time point based on the predicted information corresponding to the future time point, the vehicle demand powers comprising power demand powers for meeting the power information, the power demand powers comprising a first demand power when the engine provides power and a second demand power when the drive motor provides power; the energy consumption determination module 430 is configured to determine, for any future time point, a plurality of energy consumptions corresponding to the future time point based on the plurality of vehicle demand powers corresponding to the future time point, the plurality of energy consumptions corresponding to the plurality of vehicle demand powers in one-to-one manner; the energy management strategy determination module 440 is configured to determine, for any future time point, a minimum energy consumption in the plurality of energy consumptions corresponding to the future time point, and determine a target vehicle demand power corresponding to the future time point based on a vehicle demand power corresponding to the minimum energy consumption; and determine an energy management strategy for the vehicle in the future time period based on the target vehicle demand powers corresponding to the plurality of future time points, the energy management strategy being used to represent total energy required to be provided by the engine and the battery at each future time point and a distribution manner of the total energy.

[0126] In a possible implementation, the first demand power comprises power demand power of the engine, and the second demand power comprises power demand power of the drive motor and demand power of thermal management of the battery.

[0127] In a possible implementation, the predicted information further comprises a first initial temperature of the battery, and the vehicle demand power determination module 420 is further configured to determine, based on the first initial temperature and a first target temperature of the battery corresponding to the future time point, demand power of thermal management of the battery corresponding to the future time point, the thermal management being used to adjust the temperature of the battery from the first initial temperature to a floating range of the first target temperature.

[0128] In a possible implementation, the predicted information further comprises road condition information, and when the vehicle demand power determination module 420 determines, based on the predicted information corresponding to the future time point, the plurality of vehicle demand powers corresponding to the future time point, the vehicle demand power determination module 420 is configured to determine, based on the power information and the road condition represented by the road condition information corresponding to the future time point, the power demand powers in the plurality of vehicle demand powers corresponding to the future time point.

[0129] In a possible implementation, the predicted information further comprises a battery state of charge of the battery, and when the vehicle demand power determination module 420 determines, based on the predicted information corresponding to the future time point, the plurality of vehicle demand powers corresponding to the future time point, the vehicle demand power determination module 420 is configured to determine, based on the battery state of charge of the battery and the power information corresponding to the future time point, the power demand powers in the plurality of vehicle demand powers corresponding to the future time point, so that the battery state of charge of the battery is not lower than a state of charge threshold.

[0130] In a possible implementation, the vehicle further includes an electric appliance, the prediction information further includes working information of the electric appliance, and the vehicle demand power further includes electric appliance demand power for satisfying the working information. When the vehicle demand power determination module 420 determines the plurality of vehicle demand powers corresponding to the future time based on the prediction information corresponding to the future time, the vehicle demand power determination module 420 is configured to determine, based on the working information of the electric appliance corresponding to the future time, the electric appliance demand power in the plurality of vehicle demand powers corresponding to the future time.

[0131] In a possible implementation, the electric appliance includes a compressor configured to control a temperature of a cabin space of the vehicle, and the working information of the compressor includes a floating range in which the temperature of the cabin space is adjusted from a second initial temperature to a second target temperature. When the vehicle demand power determination module 420 determines the electric appliance demand power in the plurality of vehicle demand powers corresponding to the future time based on the working information of the electric appliance corresponding to the future time, the vehicle demand power determination module 420 is configured to determine, based on the working information of the compressor corresponding to the future time, the electric appliance demand power in the plurality of vehicle demand powers corresponding to the future time, and the electric appliance demand power includes demand power of the compressor, and the demand power of the compressor indicates power required for adjusting the temperature of the cabin space from the second initial temperature to the second target temperature within the floating range.

[0132] It should be noted that the specific working process of the apparatus and the unit described above can be clearly understood by those skilled in the art, and for the convenience and brevity of description, the corresponding process in the foregoing method embodiments can be referred to, and will not be described herein. In the several embodiments provided in the present application, the coupling between the modules can be electrical. In addition, each functional module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically independently, or two or more modules can be integrated in one module. The above integrated module can be realized in the form of hardware or in the form of a software functional module.

[0133] The present application also provides an electronic device 50, please refer to Figure 5 , including a processor 510 and a memory 520, wherein the memory 510 is used to store computer programs; the processor 520 is used to execute the programs stored in the memory 510, and realize the determination method of the energy management strategy of the vehicle introduced in any embodiment of the present application. The electronic device 50 can be, for example, a vehicle, a vehicle-mounted terminal or a server.

[0134] The present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the determination method of the energy management strategy of the vehicle introduced in any embodiment of the present application.

[0135] In the present application, multiple refers to two or more than two.

[0136] In the present application, unless otherwise explicitly defined, the terms "mounting", "connected", "connection" should be understood broadly, for example, can be fixed connection, can also be detachable connection, or integrally connected; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be the internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0137] The terms "first", "second", "third", "fourth" and the like (if any) in the present application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. "Multiple" means no less than two.

[0138] The term "and / or" in the present application is only a description of the association between the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects. "Multiple" means no less than two.

[0139] If not specifically stated, all steps of the present application can be performed in sequence or randomly. For example, the method comprises steps A and B, which means that the method can comprise sequentially performed steps A and B, or sequentially performed steps B and A. For example, it is mentioned that the method can further comprise step C, which means that step C can be added to the method in any order, for example, the method can comprise steps A, B and C, or steps A, C and B, or steps C, A and B, etc.

[0140] The above is only a preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a vehicle energy management strategy, characterized in that: The vehicle includes an engine for providing power, a drive motor for providing power, and a battery for providing energy to the drive motor, and the method includes: Obtaining prediction information corresponding to a plurality of future moments in a future time period for the vehicle, the prediction information including power information, and the power information including vehicle speed and acceleration; For any future moment, determining, based on the prediction information corresponding to the future moment, a plurality of vehicle power requirements corresponding to the future moment, the vehicle power requirements including a power requirement for satisfying the power information, the power requirement including a first power requirement when the engine provides power and a second power requirement when the drive motor provides power; For any future moment, based on a plurality of vehicle power requirements corresponding to the future moment, determining a plurality of energy consumption amounts corresponding to the future moment, wherein the plurality of energy consumption amounts correspond one-to-one to the plurality of vehicle power requirements; For any future moment, determining a minimum energy consumption among multiple energy consumptions corresponding to the future moment, and determining the target vehicle power requirement corresponding to the future moment based on the vehicle power requirement corresponding to the minimum energy consumption; Based on the target vehicle demand power corresponding to each of the multiple future moments, the energy management strategy of the vehicle in the future time period is determined. The energy management strategy is used to represent the total energy that the engine and the battery need to provide at each future moment and the distribution method of the total energy.

2. The method according to claim 1, characterized in that The first required power includes the power required by the engine, and the second required power includes the power required by the drive motor and the power required for thermal management of the battery.

3. The method according to claim 2, characterized in that The prediction information also includes a first initial temperature of the battery. The required power for thermal management of the battery is determined by: Based on a first initial temperature and a first target temperature of the battery corresponding to the future time, a required power of thermal management of the battery corresponding to the future time is determined, wherein the thermal management is used to adjust the temperature of the battery from the first initial temperature to within a floating range of the first target temperature.

4. The method according to claim 1, wherein The prediction information further includes road condition information. The determining of a plurality of vehicle power requirements corresponding to the future time based on the prediction information corresponding to the future time includes: Based on the power information corresponding to the future time and the road condition represented by the road condition information, a power requirement power among a plurality of vehicle requirement powers corresponding to the future time is determined.

5. The method according to claim 1, wherein The prediction information further includes the battery state of charge of the battery. The determining, based on the prediction information corresponding to the future time, a plurality of vehicle power requirements corresponding to the future time includes: Based on the battery state of charge and power information of the battery corresponding to the future time, a power demand power among a plurality of vehicle demand powers corresponding to the future time is determined so that the battery state of charge of the battery is not lower than a state of charge threshold.

6. The method according to claim 1, characterized in that The vehicle further includes an electrical appliance, the prediction information further includes operating information of the electrical appliance, the vehicle power requirement further includes the electrical appliance power requirement for satisfying the operating information, and determining a plurality of vehicle power requirements corresponding to the future moments based on the prediction information corresponding to the future moments includes: Based on the working information of the electrical appliance corresponding to the future time, the electrical appliance required power among the multiple vehicle required power requirements corresponding to the future time is determined.

7. The method according to claim 6, characterized in that The electrical appliance includes a compressor for controlling the temperature of a cabin space of the vehicle, operating information of the compressor includes adjusting the cabin space temperature from a second initial temperature to a floating range of a second target temperature, and determining, based on the operating information of the electrical appliance corresponding to the future time, an electrical appliance power requirement among a plurality of vehicle power requirements corresponding to the future time, including: Based on the operating information of the compressor corresponding to the future time, the electrical appliance power requirements among a plurality of vehicle power requirements corresponding to the future time are determined, the electrical appliance power requirements including the compressor power requirement, and the compressor power requirement represents the power required to adjust the temperature of the cabin space from the second initial temperature to within a floating range of the second target temperature.

8. A device for determining an energy management strategy, characterized in that: The method comprises a functional module for implementing the method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: comprising a processor and a memory, wherein: Memory for storing computer programs; A processor, configured to execute a program stored in a memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images