Energy management control method and device of vehicle, electronic equipment and storage medium

Abstract

The application discloses an energy management control method and device of a vehicle, electronic equipment and a storage medium. The method comprises the following steps: acquiring an operating state parameter of the vehicle and an ambient temperature parameter of the vehicle; determining an ambient temperature domain to which the ambient temperature parameter belongs; determining a target control constraint condition matched with the ambient temperature domain; performing multi-target collaborative decision based on an energy distribution decision model, the operating state parameter and the target control constraint condition, and generating an energy management control parameter; and controlling the vehicle to operate based on the energy management control parameter. The application solves the technical problem of low efficiency of energy management control of the vehicle in the related art.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more specifically, to a vehicle energy management and control method, device, electronic device, and storage medium. Background Technology

[0002] Hybrid vehicles rely on the coordinated operation of the engine and battery to achieve energy conservation, power enhancement, and improved performance. Energy management strategies can impact overall vehicle fuel economy, power stability, and battery life. Currently, most mainstream energy management strategies are calibrated under normal temperature conditions, relying on fixed threshold rules or single algorithms, adapting to a typical temperature range of 0℃ to 35℃. However, they exhibit significant drawbacks in extreme wide temperature ranges: at low temperatures, battery internal resistance increases dramatically, easily leading to insufficient battery output, high engine load, and a surge in fuel consumption, and also increasing the risk of lithium plating damage to battery life; at high temperatures, the risk of battery thermal runaway is high, and current strategies struggle to dynamically constrain peak power, easily leading to overheating and power imbalance. Current energy management and thermal management systems are independent, employing a decoupled control mode, making it difficult to achieve coordinated thermoelectric regulation across a wide temperature range. Battery parameter drift and engine operating condition deviations caused by temperature changes are difficult to correct in real time, and the lack of an adaptive temperature gradient zoning mechanism means that even small fluctuations can cause strategy failure. This results in poor adaptability to operating conditions, low control robustness, high energy consumption in extreme temperature ranges, and poor equipment reliability, making it difficult to meet the operating needs of hybrid vehicles in multiple regions and climates, and resulting in low efficiency in energy management and control of vehicles.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for energy management control of a vehicle, in order to at least solve the technical problem of low efficiency in energy management control of vehicles in related technologies.

[0005] According to one aspect of the present invention, a vehicle energy management control method is provided, comprising: acquiring vehicle operating state parameters and ambient temperature parameters of the vehicle; determining the ambient temperature domain to which the ambient temperature parameters belong; determining target control constraints that match the ambient temperature domain; performing multi-objective collaborative decision-making based on an energy allocation decision model, operating state parameters and target control constraints to generate energy management control parameters; and controlling vehicle operation based on the energy management control parameters.

[0006] In this embodiment of the invention, determining the target control constraint condition that matches the ambient temperature domain includes: obtaining a multi-temperature domain constraint condition mapping set; and selecting the target control constraint condition from the multi-temperature domain constraint condition mapping set based on the ambient temperature domain.

[0007] In this embodiment of the invention, obtaining a multi-temperature domain constraint condition mapping set includes: determining the control constraints of the test vehicle in different temperature domains through environmental chamber testing in advance; and constructing a multi-temperature domain constraint condition mapping set based on the mapping relationship between different temperature domains and the corresponding control constraints.

[0008] In this embodiment of the invention, based on the energy allocation decision model, operating state parameters, and target control constraints, multi-objective collaborative decision-making is performed to generate energy management control parameters, including: identifying the operating condition feature vector corresponding to the operating state parameters; inputting the target control constraints, operating state parameters, and operating condition feature vector into the energy allocation decision model; and using the energy allocation decision model to perform multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate energy management control parameters.

[0009] In this embodiment of the invention, target control constraints, operating state parameters, and operating condition feature vectors are input into an energy allocation decision model. The energy allocation decision model then performs multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate energy management control parameters. This includes: constructing target terms based on the operating state parameters and operating condition feature vectors, wherein the target terms include at least two of the following: fuel consumption, power battery charge / discharge cycle loss, temperature range safety constraint, and power smoothness; the temperature range safety constraint is used to characterize the degree to which the power battery temperature deviates from a preset safe temperature range; constructing a multi-objective decision evaluation function based on the target terms; and using the energy allocation decision model and the multi-objective decision evaluation function, performing multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate energy management control parameters.

[0010] In this embodiment of the invention, a multi-objective decision evaluation function is constructed based on the objective items, including: obtaining the weight coefficients corresponding to each item in the objective items; and fusing the objective items based on the weight coefficients corresponding to each item to obtain the multi-objective decision evaluation function.

[0011] In this embodiment of the invention, the method further includes: collecting energy consumption data after the vehicle executes energy management control parameters; constructing a closed-loop training dataset based on the operating status parameters and energy consumption data; and updating the model parameters of the energy allocation decision model based on the closed-loop training dataset.

[0012] According to another aspect of the present invention, a vehicle energy management control device is also provided, comprising: an acquisition module for acquiring vehicle operating state parameters and ambient temperature parameters; a first determination module for determining the ambient temperature range to which the ambient temperature parameters belong; a second determination module for determining target control constraints that match the ambient temperature range; a decision module for performing multi-objective collaborative decision-making based on an energy allocation decision model, operating state parameters, and target control constraints to generate energy management control parameters; and a control module for controlling vehicle operation based on the energy management control parameters.

[0013] In this embodiment of the invention, the second determining module is further configured to obtain a multi-temperature domain constraint condition mapping set; and select target control constraints from the multi-temperature domain constraint condition mapping set based on the ambient temperature domain.

[0014] In this embodiment of the invention, the second determining module is further configured to pre-determine the control constraints of the test vehicle in different temperature domains through environmental chamber testing; and to construct a multi-temperature domain constraint mapping set based on the mapping relationship between different temperature domains and the corresponding control constraints.

[0015] In this embodiment of the invention, the decision module is further configured to identify the operating condition feature vector corresponding to the operating state parameters; input the target control constraints, operating state parameters and operating condition feature vector into the energy allocation decision model; and use the energy allocation decision model to perform multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate energy management control parameters.

[0016] In this embodiment of the invention, the decision module is further configured to construct target items based on operating state parameters and operating condition feature vectors, wherein the target items include at least two of the following: fuel consumption item, power battery charge-discharge cycle loss item, temperature range safety constraint item, and power smoothness item, wherein the temperature range safety constraint item is used to characterize the degree to which the power battery temperature deviates from the preset safe temperature range; based on the target items, a multi-objective decision evaluation function is constructed; and using the energy allocation decision model and the multi-objective decision evaluation function, multi-objective collaborative decision-making is performed under the premise of satisfying the target control constraints to generate energy management control parameters.

[0017] In this embodiment of the invention, the decision module is further configured to obtain the weight coefficients corresponding to each item in the target item; and to fuse the target items based on the weight coefficients corresponding to each item to obtain a multi-objective decision evaluation function.

[0018] In this embodiment of the invention, the decision module is further configured to collect energy consumption data after the vehicle executes energy management control parameters; construct a closed-loop training dataset based on the operating status parameters and energy consumption data; and update the model parameters of the energy allocation decision model based on the closed-loop training dataset.

[0019] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0020] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0021] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0022] According to another aspect of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0023] According to another aspect of the present invention, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of the present invention.

[0024] In this embodiment of the invention, the vehicle's operating status parameters and the ambient temperature parameters are acquired; the ambient temperature domain to which the ambient temperature parameters belong is determined; target control constraints matching the ambient temperature domain are determined; multi-objective collaborative decision-making is performed based on the energy allocation decision model, operating status parameters, and target control constraints to generate energy management control parameters; and vehicle operation is controlled based on the energy management control parameters. This application acquires operating status parameters and ambient temperature parameters in real time and accurately divides the ambient temperature domain based on the ambient temperature parameters. By establishing a clear ambient temperature domain division mechanism, it helps to achieve accurate zonal control under wide temperature range conditions. The ambient temperature domain-based determination mechanism improves the pertinence and adaptability of the control strategy. Matching the corresponding target control constraints based on the determined ambient temperature domain provides clear boundary constraints for the energy allocation decision model, avoiding computational redundancy caused by blindly searching for optimal solutions and reducing decision complexity. Introducing an energy allocation decision model combined with operating status for multi-objective collaborative decision-making can quickly search for a comprehensive optimal solution that balances fuel economy, power performance, and battery health while meeting safety and lifespan constraints. Controlling vehicle operation based on the generated energy management control parameters ensures the real-time and accurate execution of control commands. Compared to related technologies that rely on fixed rules or decoupled control and lack dynamic adaptation to temperature changes, leading to frequent adjustments or strategy failures under extreme conditions, this application improves the control response speed and overall energy efficiency in complex and variable environments through the synergy of temperature-domain adaptive constraints and multi-objective energy allocation decision models. This achieves efficient and robust energy management, thereby solving the technical problem of low efficiency in energy management control of vehicles in related technologies. Attached Figure Description

[0025] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0026] Figure 1 This is a flowchart of a vehicle energy management control method according to an embodiment of the present invention;

[0027] Figure 2 This is a schematic diagram of an optional vehicle energy management control process according to an embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of another optional vehicle energy management control process according to an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of another optional vehicle energy management control process according to an embodiment of the present invention;

[0030] Figure 5 This is a schematic diagram of another optional vehicle energy management control process according to an embodiment of the present invention;

[0031] Figure 6 This is a schematic diagram of a vehicle energy management control device according to an embodiment of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] According to one aspect of the present invention, a vehicle energy management control method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] Figure 1 This is a flowchart of a vehicle energy management control method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0036] Step S102: Obtain the vehicle's operating status parameters and the ambient temperature parameters of the vehicle.

[0037] The aforementioned operating status parameters refer to the dynamic data set collected and transmitted by the vehicle controller, battery management system, engine controller, and motor controller during real-time operation of a hybrid vehicle. Specifically, these parameters may include the state of charge of the power battery, real-time temperature of the power battery cells, real-time operating temperature of the drive motor, engine speed, motor output power, real-time torque demand of the vehicle, vehicle speed, engagement or disengagement of the electronically controlled clutch, transient impact of clutch engagement, and rate of change of battery temperature. These operating status parameters constitute a real-time data stream reflecting the vehicle's current operating characteristics and energy supply-demand balance, serving as the foundational input data for energy management strategy decisions.

[0038] The aforementioned ambient temperature parameters can refer to real-time temperature data of the external environment in which the vehicle is located, as well as the battery cell temperature and drive motor temperature directly acquired by sensors. Ambient temperature parameters include the external ambient temperature used to determine macro-climate conditions, and also, importantly, the internal battery temperature indicators that directly affect the battery's internal resistance, charge / discharge rate, thermal runaway risk, and microscopic changes in engine thermal efficiency. By monitoring this temperature data in real time, the thermodynamic environment of the vehicle can be accurately perceived, providing an accurate temperature reference for subsequent temperature range division and thermoelectric synergistic control.

[0039] In one optional embodiment, the vehicle controller can coordinate sensors and controllers of various subsystems to collect vehicle operating status parameters in real time. These parameters may include the state of charge of the power battery, real-time battery cell temperature, real-time operating temperature of the drive motor, engine speed, motor output power, real-time torque demand of the vehicle, vehicle speed, engagement or disengagement of the electronically controlled clutch, and the rate of change of battery temperature. The ambient temperature parameters, primarily referring to external ambient temperature data, are also collected for macro-climate sensing. The collected data can be transmitted to the vehicle controller via the vehicle communication network, where it undergoes filtering, noise reduction, and standardization to form a real-time data stream. The operating status parameters reflect the instantaneous operating conditions and energy state of the vehicle's internal powertrain, while the ambient temperature parameters reflect the external thermodynamic environment. Together, they constitute the basic input data for subsequent temperature range determination and energy allocation decisions, ensuring that the system can accurately grasp the vehicle's current physical operating environment and internal state.

[0040] By acquiring multi-dimensional operating status parameters and external environmental parameters in real time, the system can accurately perceive the vehicle's actual operating characteristics across the entire temperature range. This provides accurate data support for subsequent multi-level wide-temperature-range stratification and zoning, ensuring the accuracy of temperature range division and providing a real-time feedback benchmark for thermoelectric synergistic coupling correction. This high-fidelity data input eliminates control errors caused by information lag or deviation, enabling the energy allocation decision model to respond quickly under extreme high and low temperature conditions, achieving a shift from passive adaptation to active prediction, thereby ensuring the accuracy and robustness of subsequent multi-objective collaborative decision-making.

[0041] Step S104: Determine the ambient temperature range to which the ambient temperature parameter belongs.

[0042] The aforementioned ambient temperature range refers to multiple differentiated control intervals within the full temperature range (-40℃ to 60℃) of vehicle operation, divided according to ambient temperature parameters and battery operating temperature parameters. These intervals can be categorized as extremely low temperature (-40℃ to -10℃), low temperature (-10℃ to 0℃), normal temperature (0℃ to 35℃), and high temperature (35℃ to 60℃). Each temperature range corresponds to different physical challenges, such as the risk of lithium plating in the extremely low temperature range and the risk of thermal runaway in the high temperature range. The purpose of dividing the temperature range is to provide customized basic control logic and constraint boundaries for different extreme operating conditions, breaking the limitations of a single normal temperature calibration.

[0043] In one optional embodiment, the vehicle controller receives ambient temperature parameters and focuses on extracting the temperature of the power battery cells as a criterion, using the external ambient temperature for auxiliary verification. Next, the acquired ambient temperature parameters are compared with a preset multi-level temperature range division standard. This standard divides the entire temperature range into multiple intervals: extremely low temperature zone (-40℃ to -10℃), low temperature zone (-10℃ to 0℃), normal temperature zone (0℃ to 35℃), and high temperature zone (35℃ to 60℃). The controller determines in real time which interval the power battery cell temperature falls into. It identifies the corresponding ambient temperature range, locks the zone identifier, and outputs the corresponding zone control reference signal. This process involves discrete logical judgment, aiming to map the continuously changing temperature environment into discrete temperature range categories with specific control strategy significance, providing a clear index for subsequent retrieval of matching constraints.

[0044] By establishing a clear environmental temperature domain division mechanism, the above settings enable accurate hierarchical and zoned control under wide temperature range conditions. This approach breaks the limitations of energy management strategies relying on fixed thresholds or single-condition calibration, allowing for rapid matching of differentiated basic control logic to the varying physical characteristics of batteries under different temperature domains, such as differences in internal resistance and thermal runaway risk. It effectively solves the problem of energy distribution imbalance under extreme high and low temperature conditions, ensuring priority for battery safety preheating at extremely low temperatures, strict power limitation to prevent thermal runaway at high temperatures, and pursuit of economic optimization at normal temperatures. This temperature domain-based determination mechanism enhances the targeting and adaptability of the control strategy, strengthens the system's robustness under complex climatic conditions, and provides a clear and stable control boundary for subsequent thermoelectric synergistic correction and multi-objective improvement, avoiding strategy conflicts or control failures caused by temperature domain ambiguity.

[0045] Step S106: Determine the target control constraints that match the ambient temperature range.

[0046] The aforementioned target control constraints refer to a set of rules and threshold parameters retrieved from a pre-defined constraint set based on the current ambient temperature domain, used to limit and guide energy distribution behavior. These conditions include battery charge / discharge rate limits under different temperature domains, engine start / stop thresholds, thermoelectric synergy weighting coefficients, motor peak power limits, clutch engagement smoothness constraints, and dynamic penalty factors, etc. The target control constraints ensure that the energy distribution decision model, while meeting the vehicle's power and economy objectives, strictly adheres to the physical limitations of battery safety, thermal management, and mechanical component lifespan, preventing equipment damage under extreme operating conditions.

[0047] In one optional embodiment, a set of corresponding control constraint parameters can be retrieved and extracted from a pre-set multi-temperature domain constraint condition mapping set based on the identified ambient temperature domain. This set of control constraint parameters was calibrated in advance through high and low temperature environment chamber tests and records the control boundaries corresponding to the extremely low temperature zone, low temperature zone, normal temperature zone, and high temperature zone. For example, if the zone is determined to be extremely low temperature zone, constraints such as battery discharge rate limit, increased weight of engine waste heat utilization, and prohibition of motor independent drive are retrieved; if the zone is high temperature zone, constraints such as strict limit of battery peak power, activation of forced cooling linkage, and reduction of battery continuous workload are retrieved. These retrieved parameters, including battery charge and discharge power limits, engine start threshold, thermoelectric synergy weight coefficient, and motor thermal constraint threshold, are combined to form the target control constraints for the current moment. These conditions are then used as hard constraints or soft penalty factors and input into the energy allocation decision model to limit and improve the subsequent energy allocation action space, ensuring that the generated control commands meet the physical safety and performance requirements under the current temperature domain.

[0048] By dynamically matching the target control constraints corresponding to the ambient temperature range, the energy management strategy is adaptively adjusted, effectively solving the problem of fixed threshold strategies failing in extreme temperature ranges. This setup ensures priority suppression of battery lithium plating risk at extremely low temperatures by limiting the discharge rate and utilizing engine waste heat to guarantee battery safety; and strictly avoids thermal runaway risk at high temperatures by limiting peak power and protecting battery life through coordinated heat dissipation. By transforming complex physical constraints into mathematical boundaries that the algorithm can handle, the energy allocation decision model can be improved while meeting safety requirements, enhancing its adaptability to operating conditions. This mapping mechanism simplifies the complexity of the control logic, improves system response speed, and avoids control oscillations or equipment damage caused by constraint mismatches, thereby ensuring vehicle power and economy, and enhancing operational stability and reliability across the entire temperature range.

[0049] Step S108: Based on the energy allocation decision model, operating status parameters, and target control constraints, perform multi-objective collaborative decision-making to generate energy management control parameters.

[0050] The aforementioned energy allocation decision model can refer to a reinforcement learning model based on an improved dual-delay deep deterministic policy gradient algorithm. This energy allocation decision model aims to improve multiple objectives, including lower vehicle fuel consumption, smaller battery temperature fluctuations, lower battery cycle life loss, and better vehicle power response. Based on operating state parameters and target control constraints, it suppresses estimation bias through a dual-evaluation network, avoids training oscillations through a policy delay update mechanism, and suppresses power jumps through action smoothing constraints. This results in the output of optimal energy allocation commands in a continuous action space, achieving multi-objective collaborative improvement.

[0051] The aforementioned multi-objective collaborative decision-making refers to the calculation process by which the energy allocation decision-making model simultaneously weighs and improves multiple mutually constraining or collaborative objectives such as fuel economy, thermal safety, battery life, and power smoothness during operation. This process searches for a globally optimal or near-optimal energy allocation strategy while meeting the current temperature range target control constraints, thereby achieving a better balance of overall vehicle performance under extreme wide temperature ranges.

[0052] The aforementioned energy management control parameters refer to the set of real-time control commands output by the energy allocation decision model after multi-objective collaborative decision-making, used to directly control the execution of vehicle powertrain components. Specifically, energy management control parameters can include continuous quantity action vectors such as the engine's real-time output power, the drive motor's real-time assist or regenerative power, and the power battery's real-time charging and discharging power. They can also include battery power limit adjustment coefficients dynamically corrected based on a thermoelectric coupling compensation model, engine energy allocation ratio correction values, and clutch engagement rate control signals, etc. These parameters can drive the vehicle controller to execute specific energy allocation actions.

[0053] In one optional embodiment, a condition-aware fusion module can be used to transform real-time collected operating state parameters into condition feature vectors, which, along with target control constraints, serve as input data. This data is then fed into an energy allocation decision model equipped with an improved dual-delay deep deterministic policy gradient algorithm. Internally, the energy allocation decision model uses a dual-evaluation network to assess the value of potential actions in the current state, employs a temperature-range constraint penalty factor to penalize violations in extreme temperature ranges, and combines this with clutch smoothness constraints corresponding to the parallel hybrid power configuration to suppress power jumps. Subsequently, the energy allocation decision model searches for optimal solutions that satisfy the target control constraints using a rolling improvement algorithm, with multiple objectives including fuel consumption, battery life loss, temperature range safety, and power smoothness. Finally, the energy allocation decision model outputs continuous energy management control parameters, including real-time engine output power, motor assist or regenerative power, and battery charging and discharging power. This process achieves an automated closed loop from state awareness to policy generation, ensuring that control commands conform to physical safety boundaries while also considering multiple performance indicators.

[0054] By introducing an energy allocation decision model for multi-objective collaborative decision-making, the limitations of rule-based control strategies in simultaneously addressing multiple objectives under complex operating conditions are overcome. This setup leverages the adaptive capabilities of deep reinforcement learning to dynamically balance fuel economy and power performance while ensuring safe battery preheating at extremely low temperatures and preventing thermal runaway at high temperatures, thus improving overall energy efficiency across a wide temperature range. This intelligent collaborative decision-making mechanism enhances the system's robustness, enabling real-time responses to temperature drift and changes in operating conditions. It avoids equipment damage or performance imbalances caused by single-objective improvements, achieving efficient, safe, and stable vehicle operation under extreme climatic conditions.

[0055] Step S110: Control vehicle operation based on energy management control parameters.

[0056] In one optional embodiment, the vehicle controller receives generated energy management control parameters, including instructions such as real-time engine output power, real-time motor assist or regenerative braking power, and real-time battery charge / discharge power. The vehicle controller distributes these instructions to the corresponding actuator controllers via the vehicle communication network. Specifically, it can send torque or power requests to the engine controller to adjust the engine output to a specified power; send torque or power instructions to the motor controller to control the motor for assist or energy recovery; and send charge / discharge power limits or current instructions to the battery management system to adjust the battery's energy throughput. Each subsystem controller accurately adjusts the engine throttle opening, motor inverter output frequency, and current magnitude based on the received instructions, thereby achieving energy distribution across the entire vehicle powertrain at the physical level. This process ensures that theoretically optimal energy strategies are accurately translated into actual vehicle operating states, achieving synergy between engine and motor power.

[0057] By implementing the above settings and accurately executing energy management control parameters, the theoretical improvement strategy is seamlessly integrated with the physical execution level, ensuring the real-time performance and accuracy of energy allocation commands. This configuration enables the vehicle to operate strictly according to the results of multi-objective collaborative decision-making, ensuring safe battery preheating and primary engine drive at extremely low temperatures, effectively suppressing battery heat accumulation at high temperatures, and maximizing fuel economy at normal temperatures.

[0058] In this embodiment of the invention, the vehicle's operating status parameters and the ambient temperature parameters are acquired; the ambient temperature domain to which the ambient temperature parameters belong is determined; target control constraints matching the ambient temperature domain are determined; multi-objective collaborative decision-making is performed based on the energy allocation decision model, operating status parameters, and target control constraints to generate energy management control parameters; and vehicle operation is controlled based on the energy management control parameters. This application acquires operating status parameters and ambient temperature parameters in real time and accurately divides the ambient temperature domain based on the ambient temperature parameters. By establishing a clear ambient temperature domain division mechanism, it helps to achieve accurate zonal control under wide temperature range conditions. The ambient temperature domain-based determination mechanism improves the pertinence and adaptability of the control strategy. Matching the corresponding target control constraints based on the determined ambient temperature domain provides clear boundary constraints for the energy allocation decision model, avoiding computational redundancy caused by blindly searching for optimal solutions and reducing decision complexity. Introducing an energy allocation decision model combined with operating status for multi-objective collaborative decision-making can quickly search for a comprehensive optimal solution that balances fuel economy, power performance, and battery health while meeting safety and lifespan constraints. Controlling vehicle operation based on the generated energy management control parameters ensures the real-time and accurate execution of control commands. Compared to related technologies that rely on fixed rules or decoupled control and lack dynamic adaptation to temperature changes, leading to frequent adjustments or strategy failures under extreme conditions, this application improves the control response speed and overall energy efficiency in complex and variable environments through the synergy of temperature-domain adaptive constraints and multi-objective energy allocation decision models. This achieves efficient and robust energy management, thereby solving the technical problem of low efficiency in energy management control of vehicles in related technologies.

[0059] In this embodiment of the invention, determining the target control constraint condition that matches the ambient temperature domain includes: obtaining a multi-temperature domain constraint condition mapping set; and selecting the target control constraint condition from the multi-temperature domain constraint condition mapping set based on the ambient temperature domain.

[0060] The aforementioned multi-temperature domain constraint mapping set can refer to a data set or database that is pre-established through prior environmental chamber experiments and parameter calibration, linking different temperature domains with their corresponding differentiated control constraints. This multi-temperature domain constraint mapping set records key control boundary values ​​such as battery charge / discharge power limits, internal resistance temperature mapping coefficients, heat loss rates, engine thermal efficiency correction parameters, and thermoelectric synergistic weighting coefficients across various temperature ranges from extremely low to high temperatures. By querying this multi-temperature domain constraint mapping set, matching target control constraints can be quickly and accurately selected based on the real-time determined ambient temperature domain, achieving temperature-domain adaptive regulation.

[0061] In one optional embodiment, data can be retrieved from a pre-set multi-temperature domain constraint condition mapping set. This mapping set, calibrated through prior high and low temperature environment chamber tests, stores control constraint parameter sets corresponding to multiple zones, including extremely low temperature, low temperature, normal temperature, and high temperature zones. Once the current ambient temperature domain is determined based on the ambient temperature parameters (e.g., extremely low temperature zone), a data entry matching the extremely low temperature zone identifier is searched within the mapping set. Subsequently, all target control constraints under this entry are extracted. These constraints include specific numerical or logical rules such as battery discharge rate limits, engine waste heat utilization weights, prohibition of independent motor drive, and clutch engagement state lockout. Finally, the extracted conditions are combined as the current target control constraints and output to the energy allocation decision model. This serves as the boundary limit and penalty basis for subsequent multi-objective collaborative decision-making, ensuring that the generated energy management strategy strictly complies with the physical safety and performance requirements of the current temperature domain.

[0062] By establishing a multi-temperature-domain constraint mapping set and dynamically selecting target control constraints, the modularity and adaptive adjustment of the energy management strategy are achieved. This setup avoids control failures caused by using incorrect constraints in extreme temperature domains. For example, it avoids forcibly limiting high-current battery discharge to prevent lithium plating at extremely low temperatures, or strictly constraining peak power to prevent thermal runaway at high temperatures. This allows the system to quickly load corresponding control logic to address the unique physical challenges of different temperature ranges, improving operating condition adaptability. This mapping mechanism simplifies real-time computational complexity, improves system response speed, and ensures that the energy allocation decision model can operate safely and stably within the boundaries of the complex and ever-changing full-range temperature conditions, thereby enhancing the robustness and reliability of the vehicle control.

[0063] In this embodiment of the invention, obtaining a multi-temperature domain constraint condition mapping set includes: determining the control constraints of the test vehicle in different temperature domains through environmental chamber testing in advance; and constructing a multi-temperature domain constraint condition mapping set based on the mapping relationship between different temperature domains and the corresponding control constraints.

[0064] The aforementioned environmental chamber test refers to the process of conducting actual measurements on a hybrid vehicle in a controlled high and low temperature environment chamber, simulating real vehicles at various extreme temperatures, such as -40℃, -20℃, 0℃, 25℃, 45℃, and 60℃, and under different states of charge and driving conditions, to obtain key performance data. This environmental chamber test is used to accurately calibrate the internal resistance changes, charge / discharge rate limits, and heat loss rates of the power battery at different temperatures, as well as the fuel consumption rate and thermal efficiency curves of the engine at different temperatures. This serves as the basic data source for constructing a wide-temperature-range parameter mapping database and a multi-temperature-range constraint condition mapping set, ensuring the accuracy and reliability of the model parameters.

[0065] The aforementioned different temperature domains refer to the classification of temperature ranges involved in environmental chamber testing and actual operation, specifically covering multiple levels including ultra-low temperature domain, low temperature domain, normal temperature domain, and high temperature domain. Different temperature domains represent the differences in the physical state of the battery and power system under different thermodynamic conditions: in the ultra-low temperature domain, the battery's internal resistance increases dramatically and lithium plating is easily achieved; in the low temperature domain, battery performance is limited; in the normal temperature domain, the system is in a highly efficient and stable state; and in the high temperature domain, the battery faces the risk of thermal runaway and the engine's thermal efficiency decreases. Distinguishing between different temperature domains allows for the development of targeted energy management strategies and thermal management coordination rules to address the unique failure modes and control challenges of each domain, achieving safe and efficient operation across the entire temperature range.

[0066] In one optional embodiment, during the R&D phase, the test vehicle is placed in a high- and low-temperature environmental chamber to simulate typical operating conditions in various temperature domains, including extremely low temperatures, low temperatures, normal temperatures, and high temperatures. Within each temperature domain, by changing the battery's state of charge and driving conditions, the internal resistance change of the power battery, the charge / discharge rate limit, the heat loss rate, and the engine's thermal efficiency curve and idling loss parameters are measured. Based on these measured data, the battery's safety boundary and the engine's optimal operating range are analyzed for each temperature domain, determining key control constraints such as the maximum allowable charge / discharge power, engine start-up threshold, and thermoelectric synergy weighting coefficient for that temperature domain. Next, a logical association is established between temperature domain identifiers and corresponding control constraint sets. Data such as low-rate discharge and waste heat priority strategies corresponding to the extremely low temperature zone, and power limits and forced cooling strategies corresponding to the high temperature zone, are structured and stored as a multi-temperature domain constraint mapping set. This multi-temperature domain constraint mapping set serves as a basic database, supporting rapid retrieval and retrieval during system operation.

[0067] By constructing a multi-temperature-domain constraint mapping set based on real-world test data, the scientific validity and engineering feasibility of the control strategy are ensured. This setup avoids control biases caused by theoretical estimations or empirical values, enabling the control constraints in each temperature domain to accurately reflect the true performance limits of the battery and engine under extreme physical conditions. Data-driven and accurate calibration of control parameters is achieved, providing a reliable basis for subsequent real-time energy management. This pre-calibration mechanism improves system development efficiency, allowing the energy allocation decision model to be directly improved using high-precision constraint boundaries, enhancing the vehicle's operational safety, fuel economy, and battery life across the entire temperature range, and strengthening the replicability and versatility of the technology.

[0068] In this embodiment of the invention, based on the energy allocation decision model, operating state parameters, and target control constraints, multi-objective collaborative decision-making is performed to generate energy management control parameters, including: identifying the operating condition feature vector corresponding to the operating state parameters; inputting the target control constraints, operating state parameters, and operating condition feature vector into the energy allocation decision model; and using the energy allocation decision model to perform multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate energy management control parameters.

[0069] The aforementioned operating condition feature vector refers to a multi-dimensional data set representing the current vehicle driving state and driving intentions, formed by fusing real-time collected vehicle operating parameters and historical driving behavior data through algorithm processing. This operating condition feature vector can specifically include indicators such as ambient temperature, battery cell temperature, battery state of charge, vehicle speed, vehicle torque demand, engine speed, motor power, clutch engagement status, and battery temperature change rate. It also incorporates recognition results of driving styles (e.g., smooth, aggressive, conservative) and driving scenarios (e.g., urban congestion, highway cruising, incline driving), providing comprehensive and accurate operating condition inputs for the energy distribution decision model to support the generation of adaptive control strategies.

[0070] In one optional embodiment, the operating condition perception fusion module preprocesses real-time collected operating state parameters, including ambient temperature, battery cell temperature, state of charge, vehicle speed, required torque, engine speed, and clutch status, and combines them with historical data for fusion analysis to identify the current driving style and driving scenario, constructing a high-dimensional real-time operating condition feature vector. Subsequently, the target control constraints, operating state parameters, and the generated operating condition feature vector are fed as input data into an energy allocation decision model equipped with an improved dual-delay deep deterministic strategy gradient algorithm. Internally, the energy allocation decision model uses state-space mapping and a dual-evaluation network to assess the value of different energy allocation actions, such as engine power, motor power, and battery power. Simultaneously, a temperature-domain constraint penalty factor is introduced to severely penalize actions that violate extremely low or high temperature safety boundaries. Under the premise of satisfying the target control constraints, through multi-objective rolling improvement, fuel economy, battery life, temperature-domain safety, and smoothness are balanced to search for a superior action strategy, outputting energy management control parameters containing specific power commands for each power source.

[0071] By constructing a feature vector of operating conditions and inputting it into the energy allocation decision model, an efficient transformation from raw data to intelligent decision-making is achieved. This setup enables accurate identification of complex and ever-changing driving intentions and driving environments, providing context-awareness for energy allocation. Combined with target control constraints, it can find a globally optimal solution within strict safety boundaries, avoiding the lag or mismatch of rule-based control strategies during sudden changes in operating conditions. The introduction of temperature-domain penalties and multi-objective collaboration ensures that battery safety and system stability are prioritized under extreme high and low temperatures, while pursuing energy efficiency at normal temperatures. This improves the overall performance, fuel economy, and driving comfort of the vehicle, and enhances the robustness and adaptability of the control strategy.

[0072] In this embodiment of the invention, target control constraints, operating state parameters, and operating condition feature vectors are input into an energy allocation decision model. The energy allocation decision model then performs multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate energy management control parameters. This includes: constructing target terms based on the operating state parameters and operating condition feature vectors, wherein the target terms include at least two of the following: fuel consumption, power battery charge / discharge cycle loss, temperature range safety constraint, and power smoothness; the temperature range safety constraint is used to characterize the degree to which the power battery temperature deviates from a preset safe temperature range; constructing a multi-objective decision evaluation function based on the target terms; and using the energy allocation decision model and the multi-objective decision evaluation function, performing multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate energy management control parameters.

[0073] The aforementioned fuel consumption item refers to an index used in a multi-objective decision evaluation function to quantify and evaluate the real-time fuel consumption of a hybrid vehicle's engine under a specific energy distribution strategy. This fuel consumption item is characterized by fuel consumption per unit time or unit mileage, reflecting the degree of impact of the current control strategy on the vehicle's fuel economy. The improvement process aims to minimize this fuel consumption item by prioritizing the use of high-efficiency engine operating conditions or rationally allocating electric motor auxiliary power, thereby reducing overall vehicle energy consumption.

[0074] The aforementioned charge-discharge cycle loss term for power batteries refers to an indicator used to quantify and evaluate the degree of lifespan loss caused by electrochemical aging mechanisms under specific charge-discharge rates, temperature ranges, and state-of-charge fluctuations. This term establishes a mathematical model related to the degradation of battery health by calculating the state-of-charge fluctuations caused by short-term charge-discharge cycles, the magnitude of charge-discharge current, and the stress effects at extreme temperatures. In energy management, introducing this charge-discharge cycle loss term aims to avoid high-rate charge-discharge cycles at extreme high or low temperatures, thereby suppressing accelerated aging phenomena such as lithium plating and thermal runaway, and extending battery lifespan.

[0075] The aforementioned temperature range safety constraint can refer to a punitive indicator used to characterize the degree to which the power battery temperature deviates from the preset safe temperature range and its potential risks. When the battery temperature is in the extremely low or high temperature range, this temperature range safety constraint dynamically calculates a penalty coefficient based on the temperature deviation value, applying negative rewards or penalties to energy allocation actions that may lead to lithium plating, thermal runaway, or severe performance degradation. This temperature range safety constraint forces the energy allocation decision model to prioritize thermal safety in extreme temperature ranges, ensuring that the battery operates within a safe temperature range by increasing the utilization of engine waste heat or limiting battery power output.

[0076] The aforementioned power smoothness parameter refers to an indicator used to quantitatively evaluate the power shock, jerking, and speed fluctuations generated during power switching, clutch engagement, or disengagement transients in parallel hybrid configurations. This power smoothness parameter calculates the clutch coupling shock by monitoring the rate of change of the motor's torque output, the clutch engagement rate, drive shaft speed fluctuations, and transient torque differences. In the improvement process, minimizing this power smoothness parameter aims to eliminate power interruptions and vibrations during gear shifts or mode changes, improve overall vehicle driving comfort and the reliability of mechanical components, and suppress control oscillations caused by unstable power coupling in extreme high and low temperature environments.

[0077] The aforementioned multi-objective decision evaluation function can refer to a comprehensive evaluation index that integrates multiple independent objectives, such as fuel consumption, power battery charge-discharge cycle loss, temperature range safety constraints, and power smoothness, through mathematical formulas and weighting coefficients. This multi-objective decision evaluation function can be constructed as a weighted summation, used in reinforcement learning algorithms to measure the merits of a state-action pair, i.e., calculating the cumulative reward value for a single step. Through the multi-objective decision evaluation function, the energy allocation decision model can compare the comprehensive effects of different control strategies in a unified scalar space, thereby guiding the algorithm to iteratively improve towards a globally optimal direction that balances economy, lifespan, safety, and comfort.

[0078] In one optional embodiment, the objective terms in the multi-objective improvement can be quantified based on real-time operating state parameters and operating condition feature vectors. Specifically, a fuel consumption term is calculated to evaluate fuel economy under the current strategy; a power battery charge-discharge cycle loss term is calculated to characterize the degree of battery life degradation through battery state-of-charge fluctuations; a temperature range safety constraint term is calculated, using a piecewise penalty formula to measure the degree to which the battery temperature deviates from a preset safe range, such as below -10℃ or above 35℃, and to penalize unsafe operations under extreme temperature ranges; and a power smoothness term is calculated to evaluate the impact of clutch engagement transients for parallel hybrid power configurations. Subsequently, the corresponding weight coefficients for each term are obtained, and the above objective terms are weighted and fused to construct a multi-objective decision evaluation function. Next, the energy allocation decision model uses this multi-objective decision evaluation function to perform multi-objective collaborative decision-making within a reinforcement learning framework. By maximizing the cumulative reward value, under the premise of satisfying the target control constraints, a better energy allocation action is dynamically searched to generate energy management control parameters that take into account energy consumption, lifespan, safety, and smoothness.

[0079] By constructing a multi-objective decision evaluation function that incorporates fuel economy, battery life, safety, and ride comfort, the performance of the hybrid power system is comprehensively and synergistically improved. This approach breaks away from the limitation of solely pursuing fuel economy, incorporating battery life and temperature range safety into the decision-making process. Under extreme high and low temperature conditions, the effective penalty of the temperature range safety constraint ensures that the battery does not experience lithium plating or thermal runaway, thus improving system safety. For the power smoothness aspect of the parallel hybrid configuration, shift jerks are effectively suppressed, enhancing the driving experience. This multi-objective collaborative decision-making mechanism enables dynamic balancing of various performance indicators based on real-time operating conditions, ensuring efficient vehicle operation, extending the lifespan of critical components, and enhancing the robustness and overall effectiveness of the control strategy.

[0080] In this embodiment of the invention, a multi-objective decision evaluation function is constructed based on the objective items, including: obtaining the weight coefficients corresponding to each item in the objective items; and fusing the objective items based on the weight coefficients corresponding to each item to obtain the multi-objective decision evaluation function.

[0081] The aforementioned weighting coefficients can refer to numerical parameters used to adjust the relative importance of various sub-indicators in a multi-objective decision-making evaluation function, such as fuel consumption, lifespan loss, temperature range safety, and powertrain smoothness. These weighting coefficients can be dynamically adjusted or adaptively selected based on the current ambient temperature range, driving conditions, and vehicle calibration requirements. For example, in extremely low temperature ranges, the weights of temperature range safety constraints and powertrain smoothness can be increased to prioritize battery safety and driving smoothness at the expense of some fuel economy; in the normal temperature high-efficiency range, the weight of fuel consumption may be increased to pursue energy conservation. Flexible setting of weighting coefficients helps to achieve multi-objective synergistic improvement.

[0082] In one optional embodiment, the weight coefficients corresponding to each objective item in the multi-objective decision evaluation function can be obtained from a pre-set calibration database or a real-time online learning module. These weight coefficients include fuel economy weight, battery state-of-charge loss weight, temperature range safety penalty weight, and power smoothness weight. The weight coefficients can be dynamically calibrated or adaptively adjusted according to the current ambient temperature range, battery state of charge, and driving style. For example, in extremely low temperature regions, the temperature range safety penalty weight and battery life weight can be increased, while the fuel economy weight can be reduced accordingly to prioritize battery safety; in normal temperature regions, the fuel economy weight can be appropriately increased. After obtaining the weight coefficients, the constructed fuel consumption item, power battery charge-discharge cycle loss item, temperature range safety constraint item, and power smoothness item can be multiplied by their corresponding weight coefficients and mathematically superimposed using a linear weighting or nonlinear fusion algorithm. Finally, these weighted indicators are integrated to construct the multi-objective decision evaluation function. This multi-objective decision evaluation function serves as the reward signal basis for the reinforcement learning algorithm in the energy allocation decision model, used to quantitatively evaluate the comprehensive advantages and disadvantages of different energy allocation strategies, and guide the energy allocation decision model to improve its strategies.

[0083] By dynamically acquiring and fusing various weight coefficients through the above settings, the multi-objective decision evaluation function is adaptively adjusted, enabling the energy management strategy to flexibly adapt to the priority requirements under different operating conditions. This setting avoids performance deviations caused by fixed weights, ensuring that battery safety and lifespan are automatically prioritized during extreme high and low temperatures, while pursuing optimal energy efficiency under normal operating conditions. The dynamic weight fusion mechanism enhances the flexibility and robustness of the control strategy, allowing the vehicle to maintain superior overall performance under different climatic conditions and driving scenarios. This accurate weight control helps balance conflicting objectives, achieving a better solution for multi-objective collaborative improvement, and enhancing the overall efficiency and reliability of the hybrid system under wide temperature range conditions.

[0084] In this embodiment of the invention, the method further includes: collecting energy consumption data after the vehicle executes energy management control parameters; constructing a closed-loop training dataset based on the operating status parameters and energy consumption data; and updating the model parameters of the energy allocation decision model based on the closed-loop training dataset.

[0085] The aforementioned energy consumption data refers to the set of measured data reflecting the vehicle's overall energy consumption during actual operation after the vehicle executes energy management control parameters. This energy consumption data may specifically include real-time engine fuel consumption, actual motor output power, actual battery charging and discharging power, actual vehicle mileage, and calculated comprehensive fuel consumption. This energy consumption data is used to verify the effectiveness of the current control strategy and is compared with model predictions, providing objective and accurate feedback for subsequent strategy adjustments, model parameter updates, and cloud-based big data iterations.

[0086] The aforementioned closed-loop training dataset can refer to a data set constructed from real-time vehicle operating status parameters, actual energy management control parameters, and corresponding actual energy consumption and safety feedback data. This closed-loop training dataset forms closed-loop sample pairs of states, actions, and results, which are used for offline or online retraining and parameter updates of the energy allocation decision model. By continuously inputting new closed-loop training data into the energy allocation decision model, deviations of the current control strategy under specific operating conditions can be identified, and network weights and hyperparameters can be automatically adjusted, thereby achieving self-learning and adaptive evolution of the energy management strategy and continuously improving control accuracy and robustness throughout its entire lifecycle.

[0087] In one optional embodiment, after the vehicle executes energy management control parameters, real-time feedback data can be collected, including actual fuel consumption, battery temperature changes, power response data, and energy consumption data. Subsequently, the real-time collected operating state parameters are combined with the aforementioned feedback energy consumption data to construct a closed-loop training dataset containing information on state, action, reward, and next state. This closed-loop training dataset records the actual decision-making effect and feedback results of the energy allocation decision model under the current operating conditions. Next, the constructed closed-loop training dataset is input into the energy allocation decision model, and the model parameters are iteratively updated using a temporal differential update mechanism of reinforcement learning or an offline training algorithm. This process enables continuous correction of model parameters based on real operating data, allowing the energy allocation decision model to gradually approach a better energy allocation strategy and complete adaptive evolution.

[0088] By constructing a closed-loop training dataset and updating model parameters, the energy management decision model is endowed with the ability to learn autonomously and continuously improve. This setup allows the energy allocation decision model to continuously accumulate experience from actual operation, correcting control errors caused by changes in operating conditions or parameter drift, and improving the accuracy and robustness of the strategy. The closed-loop iteration mechanism ensures that the energy allocation decision model can adapt to different vehicle models, regions, and driving habits, enhancing the versatility and scenario adaptability of the technology. Under long-term operation, the energy allocation decision model can continuously improve fuel economy and battery life, avoiding performance degradation caused by strategy rigidity, realizing intelligent evolution of the energy management strategy throughout its entire lifecycle, and improving the overall energy efficiency and control accuracy of the vehicle in complex and changing environments.

[0089] The technical solution proposed in this application is described below with reference to an optional embodiment. This application proposes a hybrid vehicle energy management method for a wide temperature range. It aims to solve the technical problems of current hybrid energy management strategies, such as narrow temperature range adaptability, decoupling of thermoelectric control, low energy distribution accuracy under extreme temperature conditions, and poor overall vehicle performance. The provided hybrid adaptive energy management system and method for a wide temperature range achieves adaptive energy regulation across the entire temperature range from -40℃ to 60℃. Through temperature range stratification and zoning, thermoelectric synergistic coupling, dynamic parameter correction, and multi-objective rolling improvement, it enhances the vehicle's fuel economy, power stability, and battery life under extreme conditions, exhibiting strong adaptability and control robustness.

[0090] The method described in this application is for hybrid vehicles with a parallel hybrid configuration, and can be extended to other hybrid configurations. The powertrain mainly consists of components such as an engine, motor, battery, transmission, and clutch, as well as controllers corresponding to each powertrain component. The controllers in the hybrid vehicle include a vehicle controller, motor controller, battery management system, engine controller, transmission controller, clutch, and DC-DC converter. These controllers communicate with each other via a controller area network (CAN). Specifically, the vehicle controller coordinates and controls the other subsystems; the motor controller controls the motor; the battery management system controls the battery; the engine controller controls the engine; the transmission controller controls the transmission; and the DC-DC converter converts high-voltage energy into low-voltage energy.

[0091] The adaptive energy management method for hybrid power systems with a wide temperature range provided in this application includes the following steps: building a coupled model of a wide temperature range hybrid power system and completing multi-dimensional parameter calibration, specifically including: based on the hybrid vehicle architecture, constructing an engine fuel consumption model, a power battery temperature-resistance coupling model, a motor efficiency model, and a vehicle power loss model; through high and low temperature environmental chamber tests, calibrating the charging and discharging power limits, internal resistance temperature mapping coefficient, and heat loss rate of the power battery under different battery states of charge and different operating conditions within the temperature range of -40℃ to 60℃, as well as the engine's temperature range thermal efficiency correction parameters and idling loss parameters, and establishing a wide temperature range parameter mapping database, i.e., a multi-temperature range constraint condition mapping set. A multi-level wide-temperature-range hierarchical zoning mechanism is constructed to divide the adaptive control intervals. Based on calibration data, the entire temperature range is divided into multiple control intervals, including the ultra-low temperature zone (-40℃ to -10℃), the low temperature zone (-10℃ to 0℃), the normal temperature zone (0℃ to 35℃), and the high temperature zone (35℃ to 60℃). Differentiated battery power constraint thresholds, engine start thresholds, and thermoelectric synergy weighting coefficients are set for each interval to achieve zoning adaptation of the basic control logic for different temperature ranges.

[0092] Real-time acquisition of vehicle operating status parameters and environmental parameters enables integrated perception of operating conditions. This includes real-time acquisition of ambient temperature, power battery cell temperature, battery state of charge, engine speed, motor output power, vehicle torque requirements, and vehicle speed data. By fusing historical operating data with real-time operating conditions, the system identifies the current driving style and operating conditions, constructing a real-time operating condition feature vector. Temperature-domain adaptive thermoelectric synergistic coupling correction dynamically improves control parameters. Based on the current real-time temperature, the system determines the corresponding temperature domain and retrieves the basic control parameters for that domain. Combining the real-time temperature change rate of the power battery and the operating status of the thermal management system, the system dynamically corrects the battery charging and discharging power limits and the engine energy distribution ratio. A thermoelectric coupling compensation model is established, incorporating battery heat loss and engine waste heat utilization into the parameter correction factors to solve the thermoelectric control decoupling problem over a wide temperature range. A wide-temperature-range, multi-objective rolling improvement model is constructed to output a superior energy allocation strategy. The model aims to minimize vehicle fuel consumption, reduce battery temperature fluctuations, minimize battery life loss, and optimize vehicle power response. Combining current temperature constraints, operating conditions, and battery status, an improved deep reinforcement learning algorithm is employed for rolling improvement. This dynamically allocates engine output power, motor assist power, and battery charging / discharging energy, outputting real-time optimal energy management commands. Real-time closed-loop control and iterative strategy updates are implemented. The model executes vehicle energy allocation based on the optimal energy management commands, monitors vehicle operating status and temperature parameter changes in real time, and adjusts the model's weight coefficients based on operational feedback data. Simultaneously, the wide-temperature-range parameter mapping database is iteratively updated via cloud-based big data to achieve adaptive evolution of the strategy.

[0093] Furthermore, the differentiated control logic of multi-level wide-temperature-range stratification and zoning is as follows: In the extremely low temperature zone, battery safety is prioritized, the battery discharge rate threshold is reduced, the weight of engine waste heat utilization is increased, and a battery low-temperature preheating collaborative strategy is activated. The battery temperature is assisted by engine waste heat to reduce the battery's low-temperature high-loss working state, and the engine is given priority to undertake the main power output of the vehicle; In the low temperature zone, the battery power constraint is moderately relaxed, and a collaborative mode of low-rate battery charging and discharging and intermittent engine assistance is adopted to balance preheating energy consumption and fuel energy consumption and avoid battery lithium plating loss; In the normal temperature zone, a conventional and more economical energy consumption strategy is adopted, with a focus on better fuel economy to maximize battery energy utilization; In the high temperature zone, the peak charging and discharging power of the battery is strictly constrained, the continuous workload of the battery is reduced, and a battery forced cooling linkage strategy is activated. The engine's stable output power is given priority to suppress battery heat accumulation and avoid the risk of thermal runaway.

[0094] Furthermore, the construction method of the thermoelectric coupling compensation model is as follows: collect the real-time heat loss value of the battery, the waste heat recovery efficiency of the engine, and the power consumption of the thermal management system, construct a three-dimensional coupling matrix of temperature, energy consumption and power, and superimpose the compensation coefficients calculated by the matrix into the basic energy distribution parameters to realize the real-time dynamic correction of the energy strategy by temperature changes and eliminate the control error caused by temperature range parameter drift.

[0095] Furthermore, the improved deep reinforcement learning algorithm adds a temperature range constraint penalty factor to penalize the battery's over-rate operation and the engine's inefficient operation under extreme temperature ranges, thereby improving the algorithm's accuracy under wide temperature range conditions and avoiding the battery life loss problem caused by superior single energy consumption.

[0096] This application also provides a wide-temperature-range hybrid adaptive energy management system for implementing the aforementioned energy management method, comprising: a parameter calibration and storage module for calibrating hybrid system parameters under full-temperature-range operating conditions, constructing and storing a wide-temperature-range parameter mapping database, and supporting real-time parameter retrieval and iterative updates; a temperature-range partitioning module for real-time identification of ambient temperature and battery operating temperature, determining the current multi-level temperature-range control interval, and outputting a partitioned control reference signal; a condition perception fusion module for real-time acquisition of vehicle operating conditions, battery status, and environmental parameters, fusing and processing to obtain real-time operating condition feature vectors and driving style features; a thermoelectric synergistic correction module with a built-in thermoelectric coupling compensation model for dynamically correcting energy control parameters based on real-time temperature and thermal management status to achieve thermoelectric synergistic control; a multi-objective improvement decision module equipped with an improved deep reinforcement learning algorithm for performing multi-objective rolling improvement based on temperature-range constraints and operating condition requirements, and outputting a better energy allocation command; and a closed-loop control and iteration module for executing energy management commands, collecting real-time operation feedback data, and completing parameter closed-loop correction and strategy iterative updates.

[0097] This application details the improved algorithm, specifically the dual-delay deep deterministic policy gradient algorithm, an improved deep reinforcement learning algorithm for continuous action spaces. It features a dual-evaluation network, effectively suppressing overestimation bias and improving accuracy under extreme constraints. Employing a policy delay update mechanism and a target policy smoothing strategy, it addresses training oscillations and control command jumps under dynamic and complex conditions, exhibiting stronger robustness and dynamic adaptability. This application further improves the algorithm for wide-temperature-range hybrid systems by adding a temperature-range constraint penalty factor and a dedicated improvement weight for parallel hybrid configurations. This accurately adapts to multi-dimensional hard boundary conditions such as battery power constraints, motor thermal constraints, and clutch smoothness constraints under extreme high and low temperatures, achieving a multi-objective collaborative optimization solution for vehicle energy consumption, battery life, and power smoothness, thus adapting to engineering control scenarios involving continuous dynamic power allocation in hybrid vehicles. For parallel hybrid vehicles, the improvements include: resolving inaccurate estimations under extreme high and low temperatures; addressing shifting and clutch transient training oscillations; and resolving power jumps and vehicle jerking.

[0098] Constructing a wide-temperature-range multi-objective cumulative reward function That is, a multi-objective decision evaluation function, which constructs a comprehensive reward function that takes into account fuel consumption, battery life, temperature safety, and smoothness:

[0099] ;

[0100] in, These are multi-objective weighting coefficients, corresponding to the weighting percentages of fuel economy, battery state of charge fluctuation loss, temperature range safety penalty, and power smoothness, respectively, and are adaptively selected based on the calibration conditions of the hybrid vehicle. This refers to real-time engine fuel consumption, i.e., the fuel consumption item. This refers to the loss due to fluctuations in the state of charge of the battery during short-term charge and discharge cycles, i.e., the loss due to the charge and discharge cycles of the power battery. This refers to the clutch coupling shock in a parallel hybrid powertrain configuration, i.e., the powertrain smoothness factor. This is a wide-temperature-range penalty term, i.e., a temperature-range safety constraint term.

[0101] The wide temperature range penalty term can be expressed as follows:

[0102] ;

[0103] in, It is a temperature penalty coefficient for the extremely low temperature range, suitable for extremely low temperature conditions from -40℃ to -10℃. This is a temperature penalty coefficient for high-temperature operating conditions, suitable for operating conditions ranging from 35℃ to 60℃. The critical temperature threshold for the low-temperature zone can be fixed at -10℃; The critical temperature threshold for the high-temperature zone can be fixed at 35℃. This segmented penalty mechanism enables the algorithm to actively constrain the battery rate and protect thermal safety in extreme temperature ranges, solving the problem of traditional energy management lacking hard temperature constraints.

[0104] The proposed wide-temperature-range hybrid adaptive energy management method includes the following steps: First, a wide-temperature-range hybrid system coupling model is built. Through high and low temperature environmental chamber tests, the charging and discharging power limits of the power battery under different operating conditions, internal resistance temperature mapping coefficient, heat loss rate, and engine temperature-range thermal efficiency correction parameters are calibrated within the temperature range of -40℃ to 60℃, and a wide-temperature-range parameter mapping database is established. Based on this database, the entire temperature range is divided into multi-level adaptive control intervals: extremely low temperature zone, low temperature zone, normal temperature zone, and high temperature zone. Differentiated battery power constraint thresholds, engine start thresholds, and thermoelectric synergy weighting coefficients are set for each interval. Second, ambient temperature, power battery cell temperature, battery state of charge, engine speed, motor output power, vehicle torque demand, and vehicle speed operating parameters are collected in real time and fused to obtain real-time... The system incorporates operating condition feature vectors and driving style characteristics. Based on real-time temperature, it determines the corresponding temperature control range, retrieves the basic control parameters for that range, and dynamically corrects the energy control parameters using a pre-set thermoelectric coupling compensation model, combining the real-time temperature change rate of the power battery and the operating status of the thermal management system to achieve coordinated thermoelectric coupling control. With multiple objectives including lower vehicle fuel consumption, smaller battery temperature fluctuations, lower battery life loss, and better vehicle power response, it employs an improved deep reinforcement learning algorithm for rolling improvement, dynamically allocating engine output power, motor assist power, and battery charging and discharging energy, and outputting optimal energy management commands. Executing these optimal energy management commands, it collects real-time vehicle operation feedback data, performs closed-loop correction of the improved model weight coefficients, and iteratively updates the wide-temperature-range parameter mapping database to achieve adaptive strategy improvement.

[0105] The temperature division criteria for the multi-level adaptive control range are as follows: extremely low temperature zone (-40℃ to -10℃), low temperature zone (-10℃ to 0℃), normal temperature zone (0℃ to 35℃), and high temperature zone (35℃ to 60℃). The differentiated control logic for each zone includes: In the extremely low temperature zone, the battery discharge rate threshold is reduced, the weight of engine waste heat utilization is increased, and a battery low-temperature preheating collaborative strategy is activated, with the engine undertaking the main power output of the vehicle; in the low temperature zone, a collaborative mode of low-rate battery charging and discharging + intermittent engine assistance is adopted to balance preheating energy consumption and fuel energy consumption; in the normal temperature zone, fuel economy is prioritized to maximize battery energy utilization; in the high temperature zone, the peak charging and discharging power of the battery is strictly constrained, the continuous workload of the battery is reduced, and a forced cooling linkage strategy for the battery is activated to suppress battery heat accumulation. The thermoelectric coupling compensation model is constructed by collecting real-time battery heat loss values, engine waste heat recovery efficiency, and thermal management system power consumption, constructing a three-dimensional coupling matrix of temperature, energy consumption, and power, calculating parameter compensation coefficients through the coupling matrix, and superimposing them on the basic energy allocation parameters to achieve real-time dynamic correction of the energy strategy under temperature range changes. An improved deep reinforcement learning algorithm is introduced, which adds a temperature range constraint penalty factor to penalize the battery operating at excessive rates and the engine operating inefficiently under extreme temperature ranges, thereby improving the accuracy of energy distribution improvement under wide temperature range conditions.

[0106] The above method is applicable to parallel hybrid vehicles, which are powertrain architectures where the drive motor is positioned between the engine and the transmission, and equipped with an electronically controlled disengagement clutch. This allows for multiple operating modes, including engine-only drive, motor-only drive, combined engine and motor drive, and regenerative braking. The parameter calibration process also includes calibration of parameters specific to the parallel hybrid configuration: for the clutch engagement / disengagement transients and shift power interruption conditions in the parallel hybrid configuration, the peak allowable output torque of the motor, the clutch coupling impact compensation coefficient, and the shift power dynamic constraint threshold are calibrated across the entire temperature range from -40℃ to 60℃. Combined with the characteristics of the motor directly coupling to the drive shaft, the full-temperature range motor efficiency decay curve is calibrated, and a temperature, torque, and efficiency mapping sub-database specific to the parallel hybrid configuration is constructed. The system employs differentiated control logic across multiple temperature zones, incorporating exclusive constraint strategies for parallel hybrid powertrain configurations. In the extremely low temperature zone (-40℃ to -10℃), the electronically controlled clutch engagement state is locked, prohibiting independent motor drive. The engine serves as the primary power output, with the motor providing low-rate assistance to suppress engine idling fluctuations. Simultaneously, waste heat from the engine is utilized to preheat the battery and motor controller. In the low temperature zone (-10℃ to 0℃), the duration of a single motor assist is limited, employing an intermittent assist mode to reduce the frequency of clutch engagement and disengagement, thus suppressing lithium deposition from frequent low-temperature charging and discharging of the battery. In the high temperature zone (35℃ to 60℃), continuous torque output from the motor is limited to prevent high-temperature demagnetization, reduce continuous high-current discharge from the battery, prioritize steady-state engine drive, and minimize heat accumulation in the integrated electrical system. The system also incorporates a new state recognition dimension specific to parallel hybrid powertrain configurations. Real-time data collection of clutch engagement status, motor input / output torque difference, shift signals, and drive shaft speed fluctuations identifies unique shift transients and clutch coupling conditions specific to parallel hybrid powertrain configurations, correcting the real-time operating condition feature vector. The thermoelectric coupling compensation model is adapted to highly integrated thermal coupling characteristics, incorporating motor operating temperature and motor controller heat loss into a three-dimensional coupling matrix of temperature, energy consumption, and power. It synchronously matches the clutch engagement rate, achieving coordinated correction and control of thermal state, energy distribution, and power coupling in the parallel hybrid configuration. An improved deep reinforcement learning algorithm adds auxiliary improvement weights for the parallel hybrid configuration, with clutch coupling smoothness, motor thermal stability, and optimized shifting energy consumption as auxiliary improvement targets. Under extreme temperature ranges, it prioritizes ensuring the coupling stability of the powertrain, then balances overall vehicle fuel economy with battery life loss.

[0107] This application offers the following beneficial technical effects: It establishes a multi-level, wide-temperature-range, hierarchical, and zoned control mechanism, overcoming the limitations of room-temperature calibration and achieving full coverage of extreme temperature ranges from -40℃ to 60℃. Differentiated control logic is designed for different temperature ranges, completely resolving the technical pain points of poor adaptability to extreme high and low temperature conditions and energy distribution imbalance in current strategies, thus improving operational stability under all climate conditions. An energy distribution decision model is constructed, breaking the traditional industry model of decoupled control between energy management and thermal management. Temperature drift, heat loss, and waste heat utilization are incorporated into the energy improvement system, enabling real-time parameter correction under temperature range changes, effectively eliminating control errors caused by temperature parameter drift, and improving control accuracy. An improved reinforcement learning algorithm with temperature-range constraint penalty factors is adopted to construct a multi-objective collaborative improvement system for energy consumption, temperature, lifespan, and power. This abandons a single, economically optimal control logic, effectively suppressing battery lithium plating and thermal runaway problems under extreme temperature ranges while ensuring vehicle power performance and fuel economy, thereby extending the lifespan of the power battery. It possesses independent iterative improvement capabilities, continuously refining wide-temperature-range control parameters through real-time operating condition feedback and cloud data iteration. Adapting to different vehicle models and usage scenarios, it exhibits exceptional robustness and versatility. Compared to traditional fixed-threshold strategies, it reduces overall vehicle fuel consumption under extreme temperature conditions. The overall solution features a closed-loop logic and high technical barriers, distinguishing it from current superficial improvement solutions that focus solely on thermal management or single-condition energy improvements. It achieves improvements across the entire chain, from model building and temperature-range zoning to coupled control, intelligent improvement, and closed-loop iteration.

[0108] Figure 2 This is a schematic diagram of an optional vehicle energy management control process according to an embodiment of the present invention, such as... Figure 2 As shown:

[0109] First, obtain the vehicle's operating status parameters and the ambient temperature parameters of the vehicle's location.

[0110] Next, determine the ambient temperature domain to which the ambient temperature parameter belongs; obtain the multi-temperature domain constraint mapping set; and select the target control constraint from the multi-temperature domain constraint mapping set based on the ambient temperature domain.

[0111] Next, based on the energy allocation decision model, operating status parameters, and target control constraints, multi-objective collaborative decision-making is carried out to generate energy management control parameters.

[0112] Finally, the vehicle operation is controlled based on energy management control parameters.

[0113] Figure 3 This is a schematic diagram of another optional vehicle energy management control process according to an embodiment of the present invention, such as... Figure 3 As shown:

[0114] First, obtain the vehicle's operating status parameters and the ambient temperature parameters of the vehicle's location.

[0115] Next, determine the ambient temperature domain to which the ambient temperature parameter belongs; obtain the multi-temperature domain constraint mapping set; and select the target control constraint from the multi-temperature domain constraint mapping set based on the ambient temperature domain.

[0116] Next, the operating condition feature vectors corresponding to the operating state parameters are identified; the target control constraints, operating state parameters, and operating condition feature vectors are input into the energy allocation decision model, and the energy allocation decision model is used to make multi-objective collaborative decisions under the premise of satisfying the target control constraints to generate energy management control parameters.

[0117] Finally, the vehicle operation is controlled based on energy management control parameters.

[0118] Figure 4 This is a schematic diagram of another optional vehicle energy management control process according to an embodiment of the present invention, such as... Figure 4 As shown:

[0119] First, obtain the vehicle's operating status parameters and the ambient temperature parameters of the vehicle's location.

[0120] Next, determine the ambient temperature domain to which the ambient temperature parameter belongs; obtain the multi-temperature domain constraint mapping set; and select the target control constraint from the multi-temperature domain constraint mapping set based on the ambient temperature domain.

[0121] Next, the operating condition feature vectors corresponding to the operating state parameters are identified; based on the operating state parameters and the operating condition feature vectors, target terms are constructed, wherein the target terms include at least two of the following: fuel consumption, power battery charge-discharge cycle loss, temperature range safety constraint, and power smoothness. The temperature range safety constraint is used to characterize the degree to which the power battery temperature deviates from the preset safe temperature range; based on the target terms, a multi-objective decision evaluation function is constructed; using the energy allocation decision model and the multi-objective decision evaluation function, multi-objective collaborative decision-making is performed under the premise of satisfying the target control constraints to generate energy management control parameters.

[0122] Finally, the vehicle operation is controlled based on energy management control parameters.

[0123] Figure 5 This is a schematic diagram of another optional vehicle energy management control process according to an embodiment of the present invention, such as... Figure 5 As shown:

[0124] First, obtain the vehicle's operating status parameters and the ambient temperature parameters of the vehicle's location.

[0125] Next, determine the ambient temperature domain to which the ambient temperature parameter belongs; obtain the multi-temperature domain constraint mapping set; and select the target control constraint from the multi-temperature domain constraint mapping set based on the ambient temperature domain.

[0126] Next, the operating condition feature vectors corresponding to the operating state parameters are identified; based on the operating state parameters and the operating condition feature vectors, target terms are constructed, wherein the target terms include at least two of the following: fuel consumption, power battery charge-discharge cycle loss, temperature range safety constraint, and power smoothness. The temperature range safety constraint is used to characterize the degree to which the power battery temperature deviates from the preset safe temperature range; based on the target terms, a multi-objective decision evaluation function is constructed; using the energy allocation decision model and the multi-objective decision evaluation function, multi-objective collaborative decision-making is performed under the premise of satisfying the target control constraints to generate energy management control parameters.

[0127] Finally, based on the energy management control parameters, the vehicle operation is controlled; energy consumption data after the vehicle executes the energy management control parameters is collected; a closed-loop training dataset is constructed based on the operating status parameters and energy consumption data; and the model parameters of the energy allocation decision model are updated based on the closed-loop training dataset.

[0128] According to another aspect of the present invention, a vehicle energy management control device is also provided. This device can execute the vehicle energy management control method of the above embodiments. The specific implementation method and preferred application scenarios are the same as those of the above embodiments, and will not be repeated here.

[0129] Figure 6 This is a schematic diagram of a vehicle energy management control device according to an embodiment of this application, as shown below. Figure 6 As shown, the device includes the following: an acquisition module 602, a first determination module 604, a second determination module 606, a decision module 608, and a control module 610.

[0130] The system includes: an acquisition module 602 for acquiring vehicle operating status parameters and ambient temperature parameters; a first determination module 604 for determining the ambient temperature range to which the ambient temperature parameters belong; a second determination module 606 for determining target control constraints that match the ambient temperature range; a decision module 608 for performing multi-objective collaborative decision-making based on the energy allocation decision model, operating status parameters, and target control constraints to generate energy management control parameters; and a control module 610 for controlling vehicle operation based on the energy management control parameters.

[0131] In this embodiment of the invention, the second determining module is further configured to obtain a multi-temperature domain constraint condition mapping set; and select target control constraints from the multi-temperature domain constraint condition mapping set based on the ambient temperature domain.

[0132] In this embodiment of the invention, the second determining module is further configured to pre-determine the control constraints of the test vehicle in different temperature domains through environmental chamber testing; and to construct a multi-temperature domain constraint mapping set based on the mapping relationship between different temperature domains and the corresponding control constraints.

[0133] In this embodiment of the invention, the decision module is further configured to identify the operating condition feature vector corresponding to the operating state parameters; input the target control constraints, operating state parameters and operating condition feature vector into the energy allocation decision model; and use the energy allocation decision model to perform multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate energy management control parameters.

[0134] In this embodiment of the invention, the decision module is further configured to construct target items based on operating state parameters and operating condition feature vectors, wherein the target items include at least two of the following: fuel consumption item, power battery charge-discharge cycle loss item, temperature range safety constraint item, and power smoothness item, wherein the temperature range safety constraint item is used to characterize the degree to which the power battery temperature deviates from the preset safe temperature range; based on the target items, a multi-objective decision evaluation function is constructed; and using the energy allocation decision model and the multi-objective decision evaluation function, multi-objective collaborative decision-making is performed under the premise of satisfying the target control constraints to generate energy management control parameters.

[0135] In this embodiment of the invention, the decision module is further configured to obtain the weight coefficients corresponding to each item in the target item; and to fuse the target items based on the weight coefficients corresponding to each item to obtain a multi-objective decision evaluation function.

[0136] In this embodiment of the invention, the decision module is further configured to collect energy consumption data after the vehicle executes energy management control parameters; construct a closed-loop training dataset based on the operating status parameters and energy consumption data; and update the model parameters of the energy allocation decision model based on the closed-loop training dataset.

[0137] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0138] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0139] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0140] According to another aspect of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0141] According to another aspect of the present invention, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of the present invention.

[0142] Embodiments of this application also provide an electronic device, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention during runtime.

[0143] The aforementioned memory can refer to devices inside a computer used to store data and programs, including RAM, hard disks, etc. RAM can be used to temporarily store running programs and data, while hard disks can be used to store programs and data long-term. Memory enables the computer to read and write data and execute programs. The aforementioned processor is responsible for executing instructions in computer programs and performing data processing. It can also be responsible for controlling and executing various operations, including arithmetic operations, logical operations, and data transmission.

[0144] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0145] The aforementioned computer storage media can refer to the media used in computer memory to store certain discontinuous physical quantities. Computer storage media mainly include semiconductors, magnetic cores, magnetic drums, magnetic tapes, laser discs, etc. Computer-readable storage media include stored programs, which can be a set of instructions that a computer can recognize and execute, running on an electronic computer to meet certain information needs.

[0146] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0147] The aforementioned computer program products can refer to software programs that have been written, tested, and released, and can run on computers or other devices. Computer program products can include application programs, operating systems, utility software, etc., used to achieve specific functions or solve specific problems.

[0148] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of the present invention.

[0149] The aforementioned non-volatile computer-readable storage medium can refer to a medium for storing data. Non-volatile computer-readable storage media can retain data without loss when power is off and can be used to store long-term data, such as operating systems, applications, and user files. Non-volatile storage media can include hard disk drives, solid-state drives, optical disks, and flash memory storage devices, etc.

[0150] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of the present invention.

[0151] The aforementioned computer program can refer to a set of instructions used to tell the computer to perform specific tasks or operations. Computer programs can be written by programmers using specific programming languages ​​and can include algorithms, data structures, logic, and control flow. Computer programs can be used for a variety of purposes, including application software, operating systems, etc.

[0152] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection can be through some interfaces; the indirect coupling or communication connection between units or modules can be electrical or other forms.

[0154] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0155] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0156] If the integrated unit is implemented as 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, in essence, or the part that contributes to the current technology, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0157] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for energy management and control of a vehicle, characterized in that, include: Obtain the vehicle's operating status parameters and the ambient temperature parameters of the vehicle's location; Determine the ambient temperature range to which the ambient temperature parameter belongs; Determine the target control constraints that match the ambient temperature range; Based on the energy allocation decision model, the operating state parameters, and the target control constraints, multi-objective collaborative decision-making is performed to generate energy management control parameters. The vehicle operation is controlled based on the energy management control parameters.

2. The energy management and control method for a vehicle according to claim 1, characterized in that, Determine the target control constraints that match the ambient temperature range, including: Obtain the multi-temperature domain constraint mapping set; Based on the ambient temperature domain, the target control constraint is selected from the multi-temperature domain constraint mapping set.

3. The energy management and control method for a vehicle according to claim 2, characterized in that, Obtain the multi-temperature domain constraint mapping set, including: The control constraints of the test vehicle under different temperature ranges were determined in advance through environmental chamber testing; Based on the mapping relationship between the different temperature domains and the corresponding control constraints, the multi-temperature domain constraint mapping set is constructed.

4. The energy management and control method for a vehicle according to claim 1, characterized in that, Based on the energy allocation decision model, the operating state parameters, and the target control constraints, multi-objective collaborative decision-making is performed to generate energy management control parameters, including: Identify the operating condition feature vector corresponding to the operating status parameters; The target control constraints, the operating state parameters, and the operating condition feature vector are input into the energy allocation decision model. The energy allocation decision model is then used to perform multi-objective collaborative decision-making under the premise of satisfying the target control constraints, thereby generating the energy management control parameters.

5. The vehicle energy management and control method according to claim 4, characterized in that, The target control constraints, the operating state parameters, and the operating condition feature vector are input into the energy allocation decision model. The energy allocation decision model then performs multi-objective collaborative decision-making under the premise of satisfying the target control constraints to generate the energy management control parameters, including: Based on the operating state parameters and the operating condition feature vector, a target item is constructed, wherein the target item includes at least two of the following: fuel consumption item, power battery charge and discharge cycle loss item, temperature range safety constraint item, and power smoothness item, wherein the temperature range safety constraint item is used to characterize the degree to which the power battery temperature deviates from the preset safe temperature range; Based on the aforementioned objective terms, a multi-objective decision evaluation function is constructed; Using the energy allocation decision model and the multi-objective decision evaluation function, multi-objective collaborative decision-making is performed under the premise of satisfying the target control constraints to generate the energy management control parameters.

6. The energy management and control method for a vehicle according to claim 5, characterized in that, Based on the aforementioned objective, a multi-objective decision evaluation function is constructed, including: Obtain the weight coefficients corresponding to each item in the target item; Based on the weight coefficients corresponding to each item, the objective items are fused to obtain the multi-objective decision evaluation function.

7. The energy management and control method for a vehicle according to any one of claims 1 to 6, characterized in that, The method further includes: Collect energy consumption data of the vehicle after executing the energy management control parameters; Based on the operating status parameters and the energy consumption data, a closed-loop training dataset is constructed; Based on the closed-loop training dataset, the energy allocation decision model is updated.

8. A vehicle energy management control device, characterized in that, include: The acquisition module is used to acquire the vehicle's operating status parameters and the ambient temperature parameters. The first determining module is used to determine the ambient temperature range to which the ambient temperature parameter belongs; The second determining module is used to determine the target control constraints that match the ambient temperature range; The decision module is used to make multi-objective collaborative decisions based on the energy allocation decision model, the operating state parameters, and the target control constraints, and to generate energy management control parameters. The control module is used to control the operation of the vehicle based on the energy management control parameters.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the energy management control method for a vehicle according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the energy management control method for a vehicle according to any one of claims 1 to 7.

Images