Adaptive rule energy management method and device for hybrid delivery vehicles

Abstract

The application relates to an adaptive rule energy management method and device of a hybrid logistics vehicle, wherein the method comprises the following steps: constructing a hybrid logistics vehicle model of a target hybrid logistics vehicle; determining a working mode rule and a plurality of adjustable threshold parameters of the target hybrid logistics vehicle based on the hybrid logistics vehicle model; in an outer layer control process, iteratively optimizing global benchmark rule threshold parameters in a whole driving cycle through a finite difference random approximation extreme value search algorithm, and dynamically adapting to periodic working condition changes of a route; and in an inner layer control process, separately fine-tuning parameters for each type of working condition through a pre-trained working condition clustering model, and accurately responding to real-time dynamic differences. Therefore, the problems in the prior art, such as the difficulty of fixed parameter rules in adapting to the periodic changes of the driving characteristics of a plug-in hybrid logistics vehicle, and the incapability of single route global parameter optimization in accurately responding to dynamic road conditions and environmental condition changes, are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to an adaptive rule-based energy management method and device for hybrid logistics vehicles. Background Technology

[0002] Plug-in Hybrid Electric Logistics Vehicles (PHELVs) are commercial transport vehicles that combine fuel and electric drive. Their energy management strategies directly determine the coordination between the engine and electric motor, the charging and discharging patterns of the power battery, and the vehicle's energy consumption and emissions performance under different operating conditions. Logistics transportation is characterized by large variations in load, complex road conditions, and frequent start-stop cycles. Without efficient energy management, uneven utilization of fuel and electricity may occur, leading to over-discharge of the power battery or high-load engine operation, thereby increasing operating costs, shortening battery life, and reducing overall vehicle efficiency. Therefore, research on energy management strategies optimized for logistics operating conditions is of great significance for improving economic efficiency, extending vehicle life, and achieving energy conservation and emission reduction.

[0003] In the existing technology system, rule-based methods have good robustness and real-time performance due to their simple structure and ease of implementation, and are widely used in industry. However, their core relies on fixed logical thresholds and empirical rules, and they lack the ability to adaptively adjust to complex working conditions and individual differences. Fixed parameters are difficult to continuously approach the global optimal solution in dynamically changing scenarios, resulting in limited energy utilization efficiency.

[0004] On the other hand, while optimization-based and learning-based methods demonstrate advantages in theoretical performance such as adaptability and global optimality, they are constrained by their own characteristics: optimization methods often require complex computation processes and have weak real-time response capabilities; learning methods are highly dependent on data quality and training scenarios, and their robustness under unknown operating conditions is difficult to guarantee. Furthermore, they have poor compatibility with existing rule-based engineering systems in the industry, resulting in low development and integration efficiency, making it difficult to directly apply them to the engineering practice of mass-produced vehicles.

[0005] Existing energy management strategies using fixed parameter rules have limitations. Specifically, the driving characteristics of plug-in hybrid logistics vehicles vary periodically due to factors such as traffic, time, and environment, and their logistics routes are fixed, making it difficult for fixed parameter rules to adapt to such changes. At the same time, in areas with specific geographical characteristics, there are dynamic changes in road conditions and environmental conditions, and global parameter optimization for a single route cannot accurately address these dynamic differences, resulting in poor energy management performance.

[0006] In summary, the fixed parameter rules in existing energy management strategies are difficult to adapt to the periodic changes in the driving characteristics of plug-in hybrid logistics vehicles, and the global parameter optimization of a single route cannot accurately cope with dynamic changes in road conditions and environmental conditions, which urgently need to be addressed. Summary of the Invention

[0007] This application provides an adaptive rule-based energy management method and apparatus for hybrid logistics vehicles to solve the problems that the fixed parameter rules in existing energy management strategies are difficult to adapt to the periodic changes in the driving characteristics of plug-in hybrid logistics vehicles, and that the global parameter optimization of a single route cannot accurately cope with changes in dynamic road conditions and environmental conditions.

[0008] The first aspect of this application provides an adaptive rule-based energy management method for a hybrid logistics vehicle, comprising the following steps: constructing a longitudinal dynamics model of a target hybrid logistics vehicle, and determining the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle, so as to construct a hybrid logistics vehicle model based on the longitudinal dynamics model, the power battery model type, the fuel consumption model, and the energy consumption assessment model objective function; based on the hybrid logistics vehicle model, determining the operating mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle, and iteratively optimizing the multiple adjustable threshold parameters throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm; collecting current operating condition data of the target hybrid logistics vehicle, and performing cluster analysis on the current operating condition data to calculate incremental parameters of different categories of operating condition data in the current operating condition data, and generating current rule parameters based on the operating mode rules, and by fusing the incremental parameters and the optimized multiple adjustable threshold parameters, so as to control the target hybrid logistics vehicle to perform adaptive energy management operations through the current rule parameters.

[0009] Optionally, in one embodiment of this application, the step of constructing a longitudinal dynamics model of the target hybrid logistics vehicle and determining the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle includes: calculating the wheel torque of the target hybrid logistics vehicle and constructing a longitudinal dynamics model of the target hybrid logistics vehicle based on the wheel torque; determining the open-circuit voltage, internal resistance, and battery capacity of the power battery of the target hybrid logistics vehicle, and calculating the load power and motor power of the power battery based on the open-circuit voltage; calculating the corresponding state of charge based on the load power, the motor power, the open-circuit voltage, the internal resistance, and the battery capacity, so as to construct the power battery model through the state of charge; calculating the engine power of the target hybrid logistics vehicle and calculating the corresponding compressed natural gas consumption rate based on the engine power, so as to construct the fuel consumption model through the compressed natural gas consumption rate; and calculating the equivalent energy consumption cost per 100 kilometers of the target hybrid logistics vehicle based on the power battery model type and the fuel consumption model, so as to determine the energy consumption assessment model objective function based on the equivalent energy consumption cost per 100 kilometers.

[0010] Optionally, in one embodiment of this application, determining the operating mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle based on the hybrid logistics vehicle model includes: determining whether the remaining battery power of the target hybrid logistics vehicle is greater than a preset critical remaining battery power based on the hybrid logistics vehicle model; if the remaining battery power is greater than the critical remaining battery power, the operating mode rule of the target hybrid logistics vehicle is the electric vehicle-battery consumption mode rule, and under the electric vehicle-battery consumption mode rule, a comparison analysis operation is performed on the required torque and current speed of the target hybrid logistics vehicle to obtain the corresponding comparison analysis result, and the target hybrid logistics vehicle is operated according to the comparison analysis result; if the remaining battery power is less than the critical remaining battery power, the operating mode rule of the target hybrid logistics vehicle is the battery maintenance mode rule, and the target hybrid logistics vehicle is operated using a preset electric auxiliary control strategy.

[0011] Optionally, in one embodiment of this application, the step of performing a comparative analysis operation on the required torque and current speed of the target hybrid logistics vehicle under the electric vehicle-electricity consumption mode rule to obtain the corresponding comparative analysis result, and operating the target hybrid logistics vehicle according to the comparative analysis result, includes: determining the minimum speed threshold, cutoff torque, optimal engine torque, and maximum motor torque corresponding to the target hybrid logistics vehicle; comparing the current speed of the target hybrid logistics vehicle with the minimum speed threshold, and comparing the required torque of the target hybrid logistics vehicle with the cutoff torque, the optimal engine torque, and the maximum motor torque; when the required torque is less than the cutoff torque, or the current speed is less than the minimum speed threshold, controlling the target hybrid... The hybrid logistics vehicle operates in pure electric mode. When the required torque is greater than the preset maximum motor torque and the current vehicle speed is less than the minimum speed threshold, the target hybrid logistics vehicle is controlled to operate in hybrid drive mode. When the required torque is greater than the cutoff torque but less than the engine's optimal torque, the engine of the target hybrid logistics vehicle is controlled to maintain operation at the optimal torque point, and the battery is charged through the motor. When the required torque is greater than the cutoff torque and the required torque is between the engine's optimal torque and the motor's maximum torque, the target hybrid logistics vehicle is driven solely by the engine. When the required torque is greater than the cutoff torque and greater than the motor's maximum torque, the target hybrid logistics vehicle is controlled to operate in hybrid drive mode.

[0012] Optionally, in one embodiment of this application, the step of iteratively optimizing the plurality of adjustable threshold parameters over the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm includes: determining the minimum equivalent energy consumption cost per 100 kilometers for the target hybrid logistics vehicle, and constructing a corresponding outer-layer optimization objective function based on the minimum equivalent energy consumption cost per 100 kilometers; and using the finite difference stochastic approximation algorithm to perform extreme value search on the outer-layer optimization objective function to optimize the plurality of adjustable threshold parameters.

[0013] A second aspect of this application provides an adaptive rule-based energy management device for a hybrid logistics vehicle, comprising: a modeling module for constructing a longitudinal dynamics model of a target hybrid logistics vehicle and determining the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle, so as to construct a hybrid logistics vehicle model based on the longitudinal dynamics model, the power battery model type, the fuel consumption model, and the energy consumption assessment model objective function; an outer optimization module for determining the operating mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle based on the hybrid logistics vehicle model, and iteratively optimizing the multiple adjustable threshold parameters throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm; and an inner control module for collecting current operating condition data of the target hybrid logistics vehicle, performing cluster analysis on the current operating condition data to calculate incremental parameters of different categories of operating condition data in the current operating condition data, and generating current rule parameters based on the operating mode rules and by fusing the incremental parameters and the optimized multiple adjustable threshold parameters, so as to control the target hybrid logistics vehicle to perform adaptive energy management operations through the current rule parameters.

[0014] Optionally, in one embodiment of this application, the modeling module includes: a first calculation unit, used to calculate the wheel torque of the target hybrid logistics vehicle and construct a longitudinal dynamics model of the target hybrid logistics vehicle based on the wheel torque; a second calculation unit, used to determine the open-circuit voltage, internal resistance, and battery capacity of the power battery of the target hybrid logistics vehicle, and calculate the load power and motor power of the power battery based on the open-circuit voltage; a third calculation unit, used to calculate the corresponding state of charge according to the load power, the motor power, the open-circuit voltage, the internal resistance, and the battery capacity, so as to construct the power battery model through the state of charge; a construction unit, used to calculate the engine power of the target hybrid logistics vehicle and calculate the corresponding compressed natural gas consumption rate according to the engine power, so as to construct the fuel consumption model through the compressed natural gas consumption rate; and a fourth calculation unit, used to calculate the equivalent energy consumption cost per 100 kilometers of the target hybrid logistics vehicle based on the power battery model type and the fuel consumption model, so as to determine the objective function of the energy consumption evaluation model based on the equivalent energy consumption cost per 100 kilometers.

[0015] Optionally, in one embodiment of this application, the outer optimization module includes: a judgment unit, configured to determine, based on the hybrid logistics vehicle model, whether the remaining battery power of the target hybrid logistics vehicle is greater than a preset critical remaining battery power; a comparison and analysis unit, configured to, if the remaining battery power is greater than the critical remaining battery power, set the operating mode rule of the target hybrid logistics vehicle to the electric vehicle-battery consumption mode rule, and under the electric vehicle-battery consumption mode rule, perform a comparison and analysis operation on the required torque and current speed of the target hybrid logistics vehicle to obtain the corresponding comparison and analysis results, and run the target hybrid logistics vehicle according to the comparison and analysis results; and a running unit, configured to, if the remaining battery power is less than the critical remaining battery power, set the operating mode rule of the target hybrid logistics vehicle to the battery maintenance mode rule, and run the target hybrid logistics vehicle using a preset electric auxiliary control strategy.

[0016] Optionally, in one embodiment of this application, the comparison and analysis unit includes: a determining subunit, configured to determine the minimum speed threshold, cutoff torque, optimal engine torque, and maximum motor torque corresponding to the target hybrid logistics vehicle; a comparing subunit, configured to compare the current vehicle speed of the target hybrid logistics vehicle with the minimum speed threshold, and compare the required torque of the target hybrid logistics vehicle with the cutoff torque, the optimal engine torque, and the maximum motor torque; a first control subunit, configured to control the target hybrid logistics vehicle to operate in pure electric mode when the required torque is less than the cutoff torque, or the current vehicle speed is less than the minimum speed threshold; and a second control subunit, configured to control the target hybrid logistics vehicle to operate in pure electric mode when the required torque is greater than a preset maximum motor torque, and the current vehicle speed is less than the minimum speed threshold. When the forward speed is less than the minimum speed threshold, the target hybrid logistics vehicle is controlled to operate in a hybrid drive mode; the third control subunit is used to control the engine of the target hybrid logistics vehicle to maintain operation at the optimal torque point and charge the battery through the motor when the required torque is greater than the cutoff torque but less than the engine's optimal torque; the drive subunit is used to drive the target hybrid logistics vehicle solely through the engine when the required torque is greater than the cutoff torque and the required torque is between the engine's optimal torque and the motor's maximum torque; the fourth control subunit is used to control the target hybrid logistics vehicle to operate in a hybrid drive mode when the required torque is greater than the cutoff torque and the required torque is greater than the motor's maximum torque.

[0017] Optionally, in one embodiment of this application, the outer optimization module further includes: a function construction unit, used to determine the minimum equivalent energy consumption cost per 100 kilometers for the target hybrid logistics vehicle, and to construct a corresponding outer optimization objective function based on the minimum equivalent energy consumption cost per 100 kilometers; and an extreme value search unit, used to perform extreme value search on the outer optimization objective function using the finite difference stochastic approximation algorithm to optimize the plurality of adjustable threshold parameters.

[0018] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the adaptive rule-based energy management method for hybrid logistics vehicles as described in the above embodiments.

[0019] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described adaptive rule-based energy management method for hybrid logistics vehicles.

[0020] A fifth aspect of this application provides a computer program product, including a computer program that is executed to implement the above-described adaptive rule-based energy management method for hybrid logistics vehicles.

[0021] Therefore, the embodiments of this application have the following beneficial effects: The embodiments of this application construct a longitudinal dynamics model of the target hybrid logistics vehicle and determine the target hybrid logistics vehicle's power battery model type, fuel consumption model, and energy consumption assessment model objective function. Based on the longitudinal dynamics model, power battery model type, fuel consumption model, and energy consumption assessment model objective function, a hybrid logistics vehicle model is constructed. Based on the hybrid logistics vehicle model, the operating mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle are determined. These adjustable threshold parameters are iteratively optimized throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm. Current operating condition data of the target hybrid logistics vehicle is collected, and cluster analysis is performed on the current operating condition data to calculate incremental parameters for different categories of operating condition data. Based on the operating mode rules, and by fusing the incremental parameters and the optimized multiple adjustable threshold parameters, current rule parameters are generated to control the target hybrid logistics vehicle to perform adaptive energy management operations. This application adopts an adaptive adjustable rule parameter design, ensuring the real-time performance and robustness of the strategy through a rule-based method, while also possessing the adaptability and optimality of an optimization-based method. This solves the problems in existing energy management strategies and methods, such as the inability of fixed parameter rules to adapt to the periodic changes in the driving characteristics of plug-in hybrid logistics vehicles, and the inability of single-route global parameter optimization to accurately cope with dynamic changes in road conditions and environmental conditions.

[0022] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0023] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of an adaptive rule-based energy management method for a hybrid logistics vehicle according to an embodiment of this application; Figure 2 A schematic diagram of the structure of a plug-in hybrid logistics vehicle provided in one embodiment of this application; Figure 3 A schematic diagram of a vehicle mode switching strategy related to an adaptive rule strategy for clustering-assisted mechanism search provided in one embodiment of this application; Figure 4 A schematic diagram of hardware-in-the-loop experimental conditions is provided as an embodiment of this application; Figure 5 A schematic diagram of a hardware-in-the-loop experimental platform is provided for one embodiment of this application; Figure 6A schematic diagram of vehicle SOC trajectory evolution in a hardware-in-the-loop experiment is provided as an embodiment of this application; Figure 7 A schematic diagram of control threshold parameters and equivalent cost in a hardware-in-the-loop experiment is provided as an embodiment of this application; Figure 8 A schematic diagram illustrating the incremental parameter changes of two rule threshold parameters under three operating conditions in a hardware-in-the-loop experiment, provided as an embodiment of this application; Figure 9 A schematic diagram comparing the results of hardware-in-the-loop experiments with and without inner-layer extremum search, provided as an embodiment of this application; Figure 10 This is an example diagram of an adaptive rule-based energy management device for a hybrid logistics vehicle according to an embodiment of this application; Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0024] Among them, 10-adaptive rule energy management device for hybrid logistics vehicles; 100-modeling module, 200-outer layer optimization module, 300-inner layer control module; 1101-memory, 1102-processor, 1103-communication interface. Detailed Implementation

[0025] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0026] The adaptive rule-based energy management method and apparatus for hybrid logistics vehicles according to embodiments of this application are described below with reference to the accompanying drawings. Addressing the problems mentioned in the background art, this application provides an adaptive rule-based energy management method for hybrid logistics vehicles. In this method, a longitudinal dynamics model of the target hybrid logistics vehicle is constructed, and the target hybrid logistics vehicle's power battery model type, fuel consumption model, and energy consumption assessment model objective function are determined. Based on the longitudinal dynamics model, power battery model type, fuel consumption model, and energy consumption assessment model objective function, a hybrid logistics vehicle model is constructed. Based on the hybrid logistics vehicle model, the operating mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle are determined. Through a preset finite difference stochastic approximation algorithm, the multiple adjustable threshold parameters are iteratively optimized throughout the entire driving cycle of the target hybrid logistics vehicle. Current operating condition data of the target hybrid logistics vehicle is collected, and cluster analysis is performed on the current operating condition data to calculate incremental parameters for different categories of operating condition data. Based on the operating mode rules, and by fusing the incremental parameters and the optimized multiple adjustable threshold parameters, current rule parameters are generated to control the target hybrid logistics vehicle to perform adaptive energy management operations. This application employs an adaptive and adjustable rule parameter design, ensuring the real-time performance and robustness of the strategy through a rule-based approach, while also possessing the adaptability and optimality of optimization-based methods. This addresses the problems of existing energy management strategies where fixed-parameter rules are ill-suited to the periodic changes in the driving characteristics of plug-in hybrid logistics vehicles, and where single-route global parameter optimization cannot accurately respond to dynamic road conditions and environmental changes.

[0027] Specifically, Figure 1 A flowchart illustrating an adaptive rule-based energy management method for a hybrid logistics vehicle provided in this application embodiment.

[0028] like Figure 1 As shown, the adaptive rule-based energy management method for this hybrid logistics vehicle includes the following steps: In step S101, a longitudinal dynamics model of the target hybrid logistics vehicle is constructed, and the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle are determined, so as to construct a hybrid logistics vehicle model based on the longitudinal dynamics model, power battery model type, fuel consumption model, and energy consumption assessment model objective function.

[0029] This application embodiment first establishes a longitudinal dynamics model reflecting the longitudinal force and motion relationship of the target hybrid logistics vehicle based on its driving characteristics; secondly, it determines the appropriate power battery model type by combining the state of charge of the logistics vehicle's power battery, and constructs a fuel consumption model based on the engine's working principle and fuel consumption characteristics, and clarifies the objective function of the energy consumption evaluation model used to assess the vehicle's energy utilization efficiency; finally, it integrates the longitudinal dynamics model, power battery model, fuel consumption model, and energy consumption evaluation model objective function to form a complete hybrid logistics vehicle model.

[0030] Therefore, the embodiments of this application construct a hybrid logistics vehicle model step by step to comprehensively characterize the power and energy consumption characteristics of the logistics vehicle, thereby improving the operational economy and energy utilization rate of the logistics vehicle.

[0031] Optionally, in one embodiment of this application, a longitudinal dynamics model of the target hybrid logistics vehicle is constructed, and the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle are determined. This includes: calculating the wheel torque of the target hybrid logistics vehicle and constructing a longitudinal dynamics model of the target hybrid logistics vehicle based on the wheel torque; determining the open-circuit voltage, internal resistance, and battery capacity of the power battery of the target hybrid logistics vehicle, and calculating the load power and motor power of the power battery based on the open-circuit voltage; calculating the corresponding state of charge based on the load power, motor power, open-circuit voltage, internal resistance, and battery capacity to construct a power battery model through the state of charge; calculating the engine power of the target hybrid logistics vehicle and calculating the corresponding compressed natural gas consumption rate based on the engine power to construct a fuel consumption model through the compressed natural gas consumption rate; and calculating the equivalent energy consumption cost per 100 kilometers of the target hybrid logistics vehicle based on the power battery model type and the fuel consumption model to determine the energy consumption assessment model objective function based on the equivalent energy consumption cost per 100 kilometers.

[0032] Specifically, the process of constructing a plug-in hybrid logistics vehicle model in this application embodiment is as follows: (1) Longitudinal dynamic model: PHELVs (Plug-in Hybrid Electric Logistics Vehicles) employ a coaxial parallel hybrid powertrain structure, consisting of an engine, electric motor, clutch, AMT (Automated Mechanical Transmission), and final drive. Their structure is as follows: Figure 2 As shown.

[0033] The formula for calculating the wheel torque of this plug-in hybrid logistics vehicle is as follows:

[0034] in, Represents wheel torque; For transmission efficiency; and These represent the gear ratios of the AMT transmission and the final drive, respectively. and These represent engine torque and electric motor torque, respectively. Braking torque acting on the wheels; Road slope; Refers to vehicle speed; To accelerate the vehicle.

[0035] It should be noted that the specific parameters of the above longitudinal dynamics model are shown in Table 1, and the main parameters of the PHELVs specification are shown in Table 2. Table 1

[0036] Table 2

[0037] (2) Types of power battery models: This application embodiment can use a lithium-ion battery to model an internal resistance battery model that does not consider the effects of temperature changes and battery aging. Its state of charge (SOC) is shown in the following formula:

[0038]

[0039]

[0040] in, , and These represent open-circuit voltage, internal resistance, and battery capacity, respectively. and These represent the load power and the motor power, respectively.

[0041] (3) Fuel consumption model: The CNG consumption rate (mL / s) of a compressed natural gas (CNG) engine is shown in the following formula:

[0042] in, To pass The calculated engine power; The compressed natural gas consumption rate corresponding to the current engine torque and speed can be obtained through calibration tests. This indicates the density of compressed natural gas.

[0043] (4) Objective function of energy consumption assessment model: The equivalent energy cost per 100 kilometers (yuan / 100 km) is shown in the following formula:

[0044] in, (Yuan / )and (Yuan / kW·h) represents the market price of compressed natural gas and electricity, respectively; ( )and (kW·h) represent gas consumption and electricity consumption, respectively; (km) represents the total distance traveled in a single cycle; and These represent the number of sampling points and the sampling time, respectively.

[0045] Therefore, the embodiments of this application can construct a hybrid logistics vehicle model based on the longitudinal dynamics model, the power battery model type, the fuel consumption model, and the energy consumption assessment model objective function, thereby providing reliable technical support for the subsequent implementation of adaptive rule-based energy management of hybrid logistics vehicles.

[0046] In step S102, based on the hybrid logistics vehicle model, the working mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle are determined, and multiple adjustable threshold parameters are iteratively optimized throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm.

[0047] In step S103, the current operating condition data of the target hybrid logistics vehicle is collected, and cluster analysis is performed on the current operating condition data to calculate the incremental parameters of different categories of operating condition data in the current operating condition data. Based on the working mode rules, and by fusing the incremental parameters and multiple optimized adjustable threshold parameters, the current rule parameters are generated to control the target hybrid logistics vehicle to perform adaptive energy management operations.

[0048] Furthermore, embodiments of this application also require determining the operating mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle based on the aforementioned hybrid logistics vehicle model.

[0049] Secondly, the specific implementation of adaptive energy management operations using the CAESRB (Cluster-Assisted Extremum Seeking adaptive Rule-Based) strategy in the embodiments of this application is as follows: 1. The outer controller learns periodic operating conditions through the extreme value search algorithm of Finite Difference Stochastic Approximation (FDSA), and iterates throughout the entire driving cycle to optimize the global baseline rule threshold parameters, thereby adapting to the operating condition changes of the fixed route.

[0050] 2. The inner controller uses a pre-trained working condition clustering model to fine-tune the baseline threshold parameters for each type of working condition using an extreme value search algorithm, in order to cope with real-time dynamic differences under the same working conditions.

[0051] Therefore, the embodiments of this application provide a reference parameter that adapts to periodic changes through an outer controller, and the inner controller dynamically corrects the parameter based on the clustering results, so that the parameter can meet the requirements of both long-term and short-term fluctuations. In addition, the embodiments of this application also need to introduce a perturbation coefficient to avoid local parameter adjustments from interfering with the global trend, and introduce a momentum term to reduce the number of iterations and accelerate convergence.

[0052] It is understood that the embodiments of this application aim to achieve near-optimal performance with low computational cost and high reliability, and ensure mass production feasibility, through an adaptive rule energy management strategy based on clustering-assisted extreme value search method. The CAESRB strategy adopts an adaptive adjustable rule parameter design, which ensures the real-time performance and robustness of the strategy through a rule-based method, while also possessing the adaptability and optimality of an optimization-based method.

[0053] Optionally, in one embodiment of this application, based on a hybrid vehicle model, the operating mode rules and multiple adjustable threshold parameters of the target hybrid vehicle are determined, including: based on the hybrid vehicle model, determining whether the remaining battery power of the target hybrid vehicle is greater than a preset critical remaining battery power; if the remaining battery power is greater than the critical remaining battery power, the operating mode rule of the target hybrid vehicle is the electric vehicle-battery consumption mode rule, and under the electric vehicle-battery consumption mode rule, a comparison analysis is performed on the required torque and current speed of the target hybrid vehicle to obtain the corresponding comparison analysis results, and the target hybrid vehicle is operated according to the comparison analysis results; if the remaining battery power is less than the critical remaining battery power, the operating mode rule of the target hybrid vehicle is the battery maintenance mode rule, and the target hybrid vehicle is operated using a preset electric auxiliary control strategy.

[0054] In actual implementation, the embodiments of this application can perform adaptive rule parameter design, wherein the adaptive rule parameters mainly include working mode rules and adjustable key threshold parameters, as described below: (1) Working mode rules: The working mode in this application embodiment adopts a three-stage rule of "EV (Electric Vehicle), CD (Charge Depleting) combined with CS (Charge Sustaining)": like Figure 3 As shown, when SOC > SOC L When the critical remaining power is reached, this embodiment of the application will adopt the electric vehicle-power consumption mode rule mode. In this mode, this embodiment of the application can compare the required torque of the hybrid logistics vehicle with the current vehicle speed to determine the corresponding control strategy and operate the hybrid logistics vehicle.

[0055] When SOC <SOC L In this embodiment, the system will switch to CS (Charge Sustaining) mode and employ an Electric Assist Control Strategy (EACS). At this time, the engine serves as the primary power source, while the electric motor (EM) assists the engine's operation while maintaining the battery's charging state. Considering that engine efficiency increases with load rate, its operation is limited to the lower limit T of the high-efficiency operating range. emin Up to the upper limit T emax Within the range, and through the additional charging torque T chg Charge the battery.

[0056] (2) Adjustable key threshold parameters: In the embodiments of this application, as shown in Table 3, the aforementioned adjustable key threshold parameters include vehicle speed thresholds. Engine cutoff torque coefficient : Table 3

[0057] Furthermore, this embodiment of the application also requires dynamic optimization of the adjustable key threshold parameters through extreme value search, the calculation expression of which is as follows:

[0058] Optionally, in one embodiment of this application, under the electric vehicle-electric power consumption mode rule, a comparative analysis operation is performed on the required torque and current speed of the target hybrid logistics vehicle to obtain the corresponding comparative analysis results, and the target hybrid logistics vehicle is operated according to the comparative analysis results, including: determining the minimum speed threshold, cutoff torque, optimal engine torque, and maximum motor torque corresponding to the target hybrid logistics vehicle; comparing the current speed of the target hybrid logistics vehicle with the minimum speed threshold, and comparing the required torque of the target hybrid logistics vehicle with the cutoff torque, optimal engine torque, and maximum motor torque; when the required torque is less than the cutoff torque, or the current speed is less than the minimum speed threshold, controlling the target hybrid... The hybrid logistics vehicle operates in pure electric mode. When the required torque is greater than the preset maximum motor torque and the current vehicle speed is less than the minimum speed threshold, the target hybrid logistics vehicle is controlled to operate in hybrid drive mode. When the required torque is greater than the cutoff torque but less than the engine's optimal torque, the engine of the target hybrid logistics vehicle is controlled to operate at the optimal torque point, and the battery is charged through the motor. When the required torque is greater than the cutoff torque and the required torque is between the engine's optimal torque and the motor's maximum torque, the target hybrid logistics vehicle is driven solely by the engine. When the required torque is greater than the cutoff torque and greater than the motor's maximum torque, the target hybrid logistics vehicle is controlled to operate in hybrid drive mode.

[0059] It should be noted that, as Figure 3 As shown, in the electric vehicle-electric consumption mode rule mode, if the vehicle speed is lower than the minimum speed threshold V L Or the required torque T r Less than the cutoff torque T eoff The vehicle will operate in pure electric mode; when the vehicle speed is below V... L And the required torque T r Exceeding the motor's maximum torque T mmax In this case, the embodiments of this application can automatically switch to hybrid driving mode.

[0060] When the required torque T r Greater than the cutoff torque T eoff At this point, it is necessary to further determine its relationship with the engine's optimal torque T. eopt Maximum torque T emax The relationship between the required torque T: r Less than the engine's optimal torque T eopt The engine will maintain operation at its optimal torque point while simultaneously charging the battery via the electric motor; if a torque T is required... r In T eopt With T emax Between (i.e., greater than T) eopt And less than T emaxIf the required torque T is T, then the vehicle is driven solely by the engine; r More than T emax Therefore, the hybrid driving mode can be enabled in the embodiments of this application.

[0061] Therefore, the embodiments of this application effectively ensure the reliability of the controller design by designing adaptive rule parameters.

[0062] Optionally, in one embodiment of this application, multiple adjustable threshold parameters are iteratively optimized throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm. This includes: determining the minimum equivalent energy consumption cost per 100 kilometers for the target hybrid logistics vehicle, and constructing a corresponding outer-layer optimization objective function based on the minimum equivalent energy consumption cost per 100 kilometers; and using the finite difference stochastic approximation algorithm to perform extreme value search on the outer-layer optimization objective function to optimize multiple adjustable threshold parameters.

[0063] Those skilled in the art should understand that in the prior art, rule-based methods rely on fixed parameters, and optimization learning-based methods have a single-layer structure. However, the embodiments of this application can achieve adaptive rule-based energy management for hybrid logistics vehicles through a two-layer optimization architecture that optimizes outer global baseline parameters and combines inner clustering to assist in incremental parameter fine-tuning. This architecture adapts to both the periodic changes of fixed routes and the dynamic differences of single road segments, taking into account real-time performance, robustness, and adaptability. The specific details are as follows: 1. Outer layer control: Extreme value search based on improved SPSA (Simultaneous Perturbation Stochastic Approximation).

[0064] (1) Optimization objective: Minimize the equivalent energy consumption cost per 100 kilometers, with the control variable being the baseline parameter; (2) Gradient estimation: The gradient is calculated by simultaneously perturbing the stochastic approximation, and momentum terms and noise are introduced to avoid local optima.

[0065] in, This represents two rule base parameters to be optimized; sequence Indicates the magnitude of the disturbance; It is a scaling factor that takes into account the different dimensions of each threshold. = [ , ] is the unit vector that determines the direction of the perturbation in SPSA.

[0066] (3) Parameter update:

[0067] in, Indicates the momentum coefficient; Indicates noise.

[0068] 2. Inner control: Cluster-aided extreme value search (1) Working condition clustering: Based on historical data (vehicle speed, altitude, temperature, air pressure), the driving conditions are divided into three categories (I, II, III), and the classification is carried out in real time through a pre-trained clustering model; (2) Incremental parameter optimization: Calculate incremental parameters for each type of working condition. ; (3) Gradient estimation:

[0069] in, As a reduction factor, the actual rule parameter input is:

[0070] It is understood that, in the embodiments of this application, the outer layer of the overall process iteratively optimizes the baseline parameters throughout the entire cycle using the FDSA (Finite Difference Stochastic Approximation) algorithm. The inner layer collects operating condition data in real time, classifies it using a clustering model, and calculates incremental parameters for each type of operating condition using extreme value search. ; Integration and It outputs real-time rule parameters to control power distribution, thereby achieving adaptive energy management under dynamic operating conditions on a fixed route through two-layer optimization, significantly improving energy efficiency.

[0071] Therefore, unlike existing rule-based fixed logic thresholds, the outer layer of this application uses a finite difference stochastic approximation extreme value search algorithm to iteratively optimize the global baseline rule threshold parameters throughout the entire driving cycle, dynamically adapting to the periodic changes in driving conditions and overcoming the limitations of fixed parameters. In addition, unlike the uniform processing of driving conditions in existing technologies, the inner layer of this application uses a pre-trained driving condition clustering model (which divides driving conditions into three categories based on data such as vehicle speed and altitude) to fine-tune parameters for each category of driving conditions using extreme value search, accurately responding to real-time dynamic differences.

[0072] The following specific embodiment illustrates the execution process and results of the adaptive rule-based energy management method for hybrid logistics vehicles of this application.

[0073] To verify the effectiveness and real-time performance of the embodiments of this application, a HIL simulation platform was built for experimental evaluation. For example... Figure 4As shown, the Speedgoat real-time control platform is equipped with a Celeron 2.0 GHz quad-core CPU, 4.0 GB of RAM, and a 32.0 GB solid-state drive. The host configuration includes 8.0 GB of RAM and a 1.8 GHz Core i5 processor. Figure 5 As shown.

[0074] The hardware configuration of the experimental platform in a specific embodiment of this application is shown in Table 1, the main parameters of the experimental vehicle are shown in Table 2, and the range setting of the adjustable threshold in the control strategy is shown in Table 3.

[0075] During the experiment, the control algorithm and model were compiled via the Simulink platform and then downloaded to the Speedgoat controller for real-time simulation. The simulation results were recorded by the host computer.

[0076] Understandably, a driving cycle is defined as a standardized test period used to evaluate a vehicle's fuel efficiency or dynamic performance. Based on data collected from relevant national highway logistics vehicle routes, a typical driving cycle condition is constructed, such as... Figure 4 As shown. The data for this driving cycle comes from three days of data selected from 135 sets of experimental curves, and its characteristic parameters cover vehicle speed, altitude, temperature, and air pressure.

[0077] 1. CAESRB test under cyclic operating conditions: First, in a specific embodiment of this application, the experiment adopts the following... Figure 4 The actual driving conditions shown were implemented, and each time a disturbance was applied, one set was randomly selected from 135 recorded conditions; the hardware-in-the-loop experimental results of the SOC trajectory are as follows. Figure 6 As shown, the Figure 6 The initial trajectory, intermediate trajectory, experimentally preset termination point trajectory, and optimal DP baseline trajectory are presented. Under 91 sets of online varying operating conditions, the SOC trajectory gradually approaches the solution obtained by dynamic programming from a suboptimal state based on rule control. This result demonstrates that the adaptability of this application to driving conditions is improved, achieving more efficient power distribution and significantly reducing fuel consumption.

[0078] As the disturbance progresses Figure 7 The adjustment curves of two rule threshold parameters (benchmark parameters) and the changes in the equivalent cost per 100 kilometers of driving route are shown: from 159.1 yuan to 148.2 yuan, a decrease of about 6.9%.

[0079] To address the complex operating conditions of fixed logistics vehicle routes, the Futian National Highway route is divided into three categories of independently optimized RB threshold parameters. The incremental parameter changes of the two regular threshold parameters under the three operating conditions are shown below. Figure 8 As shown.

[0080] 2. Comparison experiment with and without inner-layer extremum search: To verify the effectiveness of inner clustering-assisted extreme value search, based on the RB baseline parameters of the aforementioned termination point, the effects of having an inner ES and not having an inner ES were compared (where the incremental parameters are the optimized solution and zero, respectively). The relevant results are as follows: Figure 9 As shown in the figure. Experiments show that the inner ES layer can adapt to the complex operating conditions of the Foton National Highway, which can reduce the equivalent fuel cost by 2.3 yuan.

[0081] The final results comparison section demonstrates the differences between Rule Based (RB), Single Layer ES Adaptive Rule (SESRB), Cluster-Assisted ES Adaptive Rule (CAESRB), and Global Optimal Dynamic Programming (DP). The comparison parameters include initial SOC, final SOC, equivalent energy cost per 100 kilometers, and the percentage cost reduction compared to the rule-based strategy. The comparison data is shown in Table 4. Table 4

[0082] As can be seen from the above experiments, the embodiments of this application can effectively adapt to changes in operating conditions during vehicle energy management, and achieve adaptive adjustment of control parameters under the premise of low computational load and high reliability, so that the vehicle energy management system can adapt to various driving conditions and effectively reduce energy consumption during vehicle operation.

[0083] The adaptive rule-based energy management method for hybrid logistics vehicles proposed in this application involves constructing a longitudinal dynamics model of the target hybrid logistics vehicle and determining the target hybrid logistics vehicle's power battery model type, fuel consumption model, and energy consumption assessment model objective function. Based on these parameters, a hybrid logistics vehicle model is constructed. Based on the hybrid logistics vehicle model, the operating mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle are determined. These adjustable threshold parameters are iteratively optimized throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm. Current operating condition data of the target hybrid logistics vehicle is collected, and cluster analysis is performed on this data to calculate incremental parameters for different categories of operating condition data. Based on the operating mode rules and by fusing the incremental parameters and the optimized adjustable threshold parameters, current rule parameters are generated to control the target hybrid logistics vehicle for adaptive energy management operations. This application employs an adaptive adjustable rule parameter design, ensuring the real-time performance and robustness of the strategy through a rule-based approach, while also possessing the adaptability and optimality of an optimization-based approach.

[0084] Secondly, with reference to the accompanying drawings, an adaptive rule-based energy management device for a hybrid logistics vehicle according to an embodiment of this application is described.

[0085] Figure 10 This is a block diagram of an adaptive rule-based energy management device for a hybrid logistics vehicle according to an embodiment of this application.

[0086] like Figure 10 As shown, the adaptive rule energy management device 10 of the hybrid logistics vehicle includes: a modeling module 100, an outer optimization module 200, and an inner control module 300.

[0087] The modeling module 100 is used to construct the longitudinal dynamics model of the target hybrid logistics vehicle and determine the power battery model type, fuel consumption model and energy consumption assessment model objective function of the target hybrid logistics vehicle, so as to construct the hybrid logistics vehicle model based on the longitudinal dynamics model, power battery model type, fuel consumption model and energy consumption assessment model objective function.

[0088] The outer optimization module 200 is used to determine the working mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle based on the hybrid logistics vehicle model, and to iteratively optimize the multiple adjustable threshold parameters throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm.

[0089] The inner control module 300 is used to collect the current operating condition data of the target hybrid logistics vehicle, and perform cluster analysis on the current operating condition data to calculate the incremental parameters of different categories of operating condition data in the current operating condition data. Based on the working mode rules, and by integrating the incremental parameters and multiple optimized adjustable threshold parameters, the current rule parameters are generated to control the target hybrid logistics vehicle to perform adaptive energy management operations.

[0090] Optionally, in one embodiment of this application, the modeling module 100 includes: a first computing unit, a second computing unit, a third computing unit, a construction unit, and a fourth computing unit.

[0091] The first calculation unit is used to calculate the wheel torque of the target hybrid logistics vehicle and, based on the wheel torque, construct a longitudinal dynamic model of the target hybrid logistics vehicle.

[0092] The second calculation unit is used to determine the open-circuit voltage, internal resistance, and battery capacity of the power battery of the target hybrid logistics vehicle, and to calculate the load power of the power battery and the power of the motor based on the open-circuit voltage.

[0093] The third calculation unit is used to calculate the corresponding state of charge based on the load power, motor power, open circuit voltage, internal resistance and battery capacity, so as to build a power battery model through the state of charge.

[0094] The building unit is used to calculate the engine power of the target hybrid logistics vehicle and calculate the corresponding compressed natural gas consumption rate based on the engine power, so as to build a fuel consumption model through the compressed natural gas consumption rate.

[0095] The fourth calculation unit is used to calculate the equivalent energy consumption cost per 100 kilometers of the target hybrid logistics vehicle based on the power battery model type and fuel consumption model, so as to determine the objective function of the energy consumption assessment model based on the equivalent energy consumption cost per 100 kilometers.

[0096] Optionally, in one embodiment of this application, the outer optimization module 200 includes: a judgment unit, a comparison and analysis unit, and a running unit.

[0097] The judgment unit is used to determine, based on the hybrid logistics vehicle model, whether the remaining power of the target hybrid logistics vehicle is greater than the preset critical remaining power.

[0098] The comparison and analysis unit is used to determine the operating mode rule of the target hybrid logistics vehicle as the electric vehicle-electric power consumption mode rule if the remaining power is greater than the critical remaining power. Under the electric vehicle-electric power consumption mode rule, the unit performs a comparison and analysis operation on the required torque and current speed of the target hybrid logistics vehicle to obtain the corresponding comparison and analysis results, and then operates the target hybrid logistics vehicle based on the comparison and analysis results.

[0099] The operating unit is used to set the target hybrid logistics vehicle's operating mode rule to the power maintenance mode rule if the remaining power is less than the critical remaining power, and to operate the target hybrid logistics vehicle using a preset electric auxiliary control strategy.

[0100] Optionally, in one embodiment of this application, the comparison and analysis unit includes: a determination subunit, a comparison subunit, a first control subunit, a second control subunit, a third control subunit, a drive subunit, and a fourth control subunit.

[0101] The determination subunit is used to determine the minimum speed threshold, cutoff torque, optimal engine torque, and maximum motor torque corresponding to the target hybrid logistics vehicle.

[0102] The comparison sub-unit is used to compare the current speed and minimum speed threshold of the target hybrid logistics vehicle, and to compare the required torque of the target hybrid logistics vehicle with the cutoff torque, the optimal torque of the engine, and the maximum torque of the motor.

[0103] The first control subunit is used to control the target hybrid logistics vehicle to operate in pure electric mode when the required torque is less than the cutoff torque or the current vehicle speed is less than the minimum speed threshold.

[0104] The second control subunit is used to control the target hybrid logistics vehicle to operate in hybrid drive mode when the required torque is greater than the preset maximum motor torque and the current vehicle speed is less than the minimum speed threshold.

[0105] The third control subunit is used to control the engine of the target hybrid logistics vehicle to maintain operation at the optimal torque point when the required torque is greater than the cutoff torque but less than the engine's optimal torque, and to charge the battery through the motor. The drive subunit is used to drive the target hybrid logistics vehicle solely by the engine when the required torque is greater than the cutoff torque and the required torque is between the engine's optimal torque and the motor's maximum torque.

[0106] The fourth control subunit is used to control the target hybrid logistics vehicle to operate in hybrid drive mode when the required torque is greater than the cutoff torque and the required torque is greater than the maximum torque of the motor.

[0107] Optionally, in one embodiment of this application, the outer optimization module 200 further includes a function construction unit and an extreme value search unit.

[0108] The function construction unit is used to determine the minimum equivalent energy consumption cost per 100 kilometers for the target hybrid logistics vehicle, and to construct the corresponding outer optimization objective function based on the minimum equivalent energy consumption cost per 100 kilometers.

[0109] The extremum search unit is used to perform extremum search on the outer-layer optimization objective function using a finite difference stochastic approximation algorithm, in order to optimize multiple adjustable threshold parameters.

[0110] It should be noted that the explanation of the aforementioned embodiment of the adaptive rule energy management method for hybrid logistics vehicles also applies to the adaptive rule energy management device for hybrid logistics vehicles in this embodiment, and will not be repeated here.

[0111] The adaptive rule-based energy management device for hybrid logistics vehicles proposed in this application includes a modeling module 100, used to construct a longitudinal dynamics model of the target hybrid logistics vehicle and determine the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle, so as to construct a hybrid logistics vehicle model based on the longitudinal dynamics model, power battery model type, fuel consumption model, and energy consumption assessment model objective function; an outer optimization module 200, used to determine the working mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle based on the hybrid logistics vehicle model, and iteratively optimize the multiple adjustable threshold parameters throughout the entire driving cycle of the target hybrid logistics vehicle through a preset finite difference stochastic approximation algorithm; and an inner control module 300, used to collect the current working condition data of the target hybrid logistics vehicle, and perform cluster analysis on the current working condition data to calculate the incremental parameters of different categories of working condition data in the current working condition data, and generate current rule parameters based on the working mode rules and by fusing the incremental parameters and the optimized multiple adjustable threshold parameters, so as to control the target hybrid logistics vehicle to perform adaptive energy management operations through the current rule parameters. This application adopts an adaptive adjustable rule parameter design, which ensures the real-time performance and robustness of the strategy through a rule-based approach, while also possessing the adaptability and optimality of an optimization-based approach.

[0112] Figure 11 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 1101, the processor 1102, and the computer program stored on the memory 1101 and executable on the processor 1102.

[0113] When the processor 1102 executes the program, it implements the adaptive rule-based energy management method for hybrid logistics vehicles provided in the above embodiments.

[0114] Furthermore, electronic devices also include: Communication interface 1103 is used for communication between memory 1101 and processor 1102.

[0115] The memory 1101 is used to store computer programs that can run on the processor 1102.

[0116] The memory 1101 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage.

[0117] If the memory 1101, processor 1102, and communication interface 1103 are implemented independently, then the communication interface 1103, memory 1101, and processor 1102 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 11 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0118] Optionally, in a specific implementation, if the memory 1101, processor 1102, and communication interface 1103 are integrated on a single chip, then the memory 1101, processor 1102, and communication interface 1103 can communicate with each other through an internal interface.

[0119] The processor 1102 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0120] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described adaptive rule-based energy management method for hybrid logistics vehicles.

[0121] This application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-described adaptive rule-based energy management method for hybrid logistics vehicles.

[0122] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0123] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0124] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0125] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0126] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0127] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0128] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0129] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. An adaptive rule-based energy management method for hybrid logistics vehicles, characterized in that, Includes the following steps: A longitudinal dynamics model of the target hybrid logistics vehicle is constructed, and the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle are determined, so as to construct a hybrid logistics vehicle model based on the longitudinal dynamics model, the power battery model type, the fuel consumption model, and the energy consumption assessment model objective function; Based on the hybrid logistics vehicle model, the working mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle are determined, and the multiple adjustable threshold parameters are iteratively optimized throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm. The current operating condition data of the target hybrid logistics vehicle is collected, and cluster analysis is performed on the current operating condition data to calculate the incremental parameters of different categories of operating condition data in the current operating condition data. Based on the working mode rules, and by integrating the incremental parameters and multiple optimized adjustable threshold parameters, current rule parameters are generated to control the target hybrid logistics vehicle to perform adaptive energy management operations through the current rule parameters. The method involves iteratively optimizing the multiple adjustable threshold parameters throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm, including: Determine the minimum equivalent energy consumption cost per 100 kilometers for the target hybrid logistics vehicle, and construct the corresponding outer-layer optimization objective function based on the minimum equivalent energy consumption cost per 100 kilometers. The finite difference stochastic approximation algorithm is used to perform an extremum search on the outer optimization objective function in order to optimize the multiple adjustable threshold parameters.

2. The method according to claim 1, characterized in that, The construction of the longitudinal dynamics model of the target hybrid logistics vehicle, and the determination of the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle, include: Calculate the wheel torque of the target hybrid logistics vehicle, and construct a longitudinal dynamics model of the target hybrid logistics vehicle based on the wheel torque; Determine the open-circuit voltage, internal resistance, and battery capacity of the power battery of the target hybrid logistics vehicle, and calculate the load power and motor power of the power battery based on the open-circuit voltage; The corresponding state of charge is calculated based on the load power, the motor power, the open circuit voltage, the internal resistance, and the battery capacity, so as to construct the power battery model based on the state of charge; Calculate the engine power of the target hybrid logistics vehicle, and calculate the corresponding compressed natural gas consumption rate based on the engine power, so as to construct the fuel consumption model through the compressed natural gas consumption rate; Based on the power battery model type and the fuel consumption model, the equivalent energy consumption cost per 100 kilometers of the target hybrid logistics vehicle is calculated, so as to determine the objective function of the energy consumption assessment model according to the equivalent energy consumption cost per 100 kilometers.

3. The method according to claim 1, characterized in that, Based on the hybrid logistics vehicle model, the operating mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle are determined, including: Based on the hybrid logistics vehicle model, determine whether the remaining battery power of the target hybrid logistics vehicle is greater than a preset critical remaining battery power. If the remaining power is greater than the critical remaining power, the operating mode rule of the target hybrid logistics vehicle is the electric vehicle-power consumption mode rule. Under the electric vehicle-power consumption mode rule, the required torque and current speed of the target hybrid logistics vehicle are compared and analyzed to obtain the corresponding comparison and analysis results. The target hybrid logistics vehicle is then operated according to the comparison and analysis results. If the remaining power is less than the critical remaining power, the target hybrid logistics vehicle will operate under the power maintenance mode rule and will use a preset electric auxiliary control strategy.

4. The method according to claim 3, characterized in that, The step of comparing and analyzing the required torque and current speed of the target hybrid logistics vehicle under the electric vehicle-electricity consumption mode rule to obtain the corresponding comparison and analysis results, and then operating the target hybrid logistics vehicle according to the comparison and analysis results, includes: Determine the minimum speed threshold, cutoff torque, optimal engine torque, and maximum motor torque corresponding to the target hybrid logistics vehicle; The current speed of the target hybrid logistics vehicle is compared with the minimum speed threshold, and the required torque of the target hybrid logistics vehicle is compared with the cutoff torque, the optimal engine torque, and the maximum motor torque. When the required torque is less than the cutoff torque, or the current vehicle speed is less than the minimum speed threshold, the target hybrid logistics vehicle is controlled to operate in pure electric mode. When the required torque is greater than the preset maximum motor torque and the current vehicle speed is less than the minimum speed threshold, the target hybrid logistics vehicle is controlled to operate in hybrid drive mode. When the required torque is greater than the cutoff torque, but the required torque is less than the engine's optimal torque, the engine of the target hybrid logistics vehicle is controlled to maintain operation at the optimal torque point, and the battery is charged through the motor. When the required torque is greater than the cutoff torque, and the required torque is between the engine's optimal torque and the motor's maximum torque, the target hybrid logistics vehicle is driven solely by the engine. When the required torque is greater than the cutoff torque and the required torque is greater than the maximum torque of the motor, the target hybrid logistics vehicle is controlled to operate in hybrid drive mode.

5. An adaptive rule-based energy management device for a hybrid logistics vehicle, characterized in that, include: The modeling module is used to construct a longitudinal dynamics model of the target hybrid logistics vehicle and determine the power battery model type, fuel consumption model, and energy consumption assessment model objective function of the target hybrid logistics vehicle, so as to construct a hybrid logistics vehicle model based on the longitudinal dynamics model, the power battery model type, the fuel consumption model, and the energy consumption assessment model objective function; The outer optimization module is used to determine the working mode rules and multiple adjustable threshold parameters of the target hybrid logistics vehicle based on the hybrid logistics vehicle model, and to iteratively optimize the multiple adjustable threshold parameters throughout the entire driving cycle of the target hybrid logistics vehicle using a preset finite difference stochastic approximation algorithm. The inner control module is used to collect the current operating condition data of the target hybrid logistics vehicle, and perform cluster analysis on the current operating condition data to calculate the incremental parameters of different categories of operating condition data in the current operating condition data. Based on the working mode rules, and by integrating the incremental parameters and multiple optimized adjustable threshold parameters, the current rule parameters are generated to control the target hybrid logistics vehicle to perform adaptive energy management operations. The outer optimization module further includes: a function construction unit, used to determine the minimum equivalent energy consumption cost per 100 kilometers for the target hybrid logistics vehicle, and to construct a corresponding outer optimization objective function based on the minimum equivalent energy consumption cost per 100 kilometers; and an extreme value search unit, used to perform extreme value search on the outer optimization objective function using the finite difference random approximation algorithm to optimize the multiple adjustable threshold parameters.

6. The apparatus according to claim 5, characterized in that, The modeling module includes: The first calculation unit is used to calculate the wheel torque of the target hybrid logistics vehicle and, based on the wheel torque, construct a longitudinal dynamics model of the target hybrid logistics vehicle. The second calculation unit is used to determine the open-circuit voltage, internal resistance, and battery capacity of the power battery of the target hybrid logistics vehicle, and to calculate the load power and motor power of the power battery based on the open-circuit voltage. The third calculation unit is used to calculate the corresponding state of charge based on the load power, the motor power, the open circuit voltage, the internal resistance and the battery capacity, so as to construct the power battery model through the state of charge; A construction unit is used to calculate the engine power of the target hybrid logistics vehicle and calculate the corresponding compressed natural gas consumption rate based on the engine power, so as to construct the fuel consumption model through the compressed natural gas consumption rate; The fourth calculation unit is used to calculate the equivalent energy consumption cost per 100 kilometers of the target hybrid logistics vehicle based on the power battery model type and the fuel consumption model, so as to determine the objective function of the energy consumption assessment model according to the equivalent energy consumption cost per 100 kilometers.

7. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the adaptive rule-based energy management method for a hybrid logistics vehicle as described in any one of claims 1-4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the adaptive rule-based energy management method for hybrid logistics vehicles as described in any one of claims 1-4.

9. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the adaptive rule-based energy management method for hybrid logistics vehicles as described in any one of claims 1-4.

Images