Hybrid off-road vehicle energy management method and device
The hybrid off-road vehicle energy management method uses neural networks to predict off-road conditions and adjust APU output power, addressing the shortfall of traditional strategies by enhancing maneuverability and power performance in challenging terrains.
Patent Information
- Application Number
- CN202411285478.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-12-06
AI Technical Summary
Traditional energy management strategies for hybrid off-road vehicles prioritize fuel economy, failing to meet the actual power demands in harsh off-road conditions, leading to poor maneuverability.
A hybrid off-road vehicle energy management method that predicts future vehicle speed and road slope data using neural networks, determines a maneuverability coefficient, and adjusts the APU output power through a dynamic objective function to balance power and economic optimization, ensuring higher actual output power than required under challenging conditions.
Enhances vehicle maneuverability by aligning APU output power with power demands in complex and changeable off-road environments, improving power performance and responsiveness.
Smart Images

Figure CN119078788A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of vehicle energy management strategies, and in particular to a hybrid off-road vehicle energy management method and device. Background Art
[0002] At present, the energy management strategy of hybrid off-road vehicles is an important research direction of new energy vehicles. As a multi-energy coordinated and integrated mobile platform, hybrid off-road vehicles equipped with hub motors have complex and changeable driving conditions. The power demand of the whole vehicle is often presented in a step-like manner, and there is an electromechanical coupling characteristic between the power and drive units.
[0003] In the prior art, traditional energy management strategies usually take optimizing the fuel economy of the entire vehicle as the main goal.
[0004] When faced with harsh off-road conditions such as no roads, bad roads, and bumpy sections, the energy management strategy with economy as the sole optimization goal is difficult to meet the actual power requirements of off-road vehicles, resulting in poor maneuverability. Summary of the invention
[0005] In view of this, it is necessary to provide a hybrid off-road vehicle energy management method and device to solve the problem that the energy management strategy with economy as the single optimization goal in the prior art is difficult to meet the actual power demand of the off-road vehicle, resulting in poor maneuverability.
[0006] In order to solve the above problems, the present application provides a hybrid off-road vehicle energy management method, comprising: Acquire historical vehicle speed and road slope data, and predict future vehicle speed and road slope data based on the historical vehicle speed and road slope data; Determining the vehicle required power and a maneuvering coefficient for characterizing the effect of off-road degree on power based on the future vehicle speed and road gradient data; Determine an objective function with the APU actual output power as an independent variable based on the maneuverability coefficient and the vehicle required power, wherein the objective function includes a dynamic objective function; The objective function is solved to obtain the actual output power of the APU.
[0007] In some possible implementations, predicting future vehicle speed and road slope data based on the historical vehicle speed and road slope data includes: Determining a cluster identification result based on the historical vehicle speed and road slope data and an off-road condition identification model based on a neural network; Determine a fully trained operating condition data prediction model corresponding to the cluster identification result, wherein the operating condition data prediction model is a neural network model; The historical vehicle speed and road slope data are input into a well-trained working condition data prediction model corresponding to the cluster identification result to obtain future vehicle speed and road slope data.
[0008] In some possible implementations, the operating condition data prediction model is a bidirectional Bi-LSTM neural network model.
[0009] In some possible implementations, based on the historical vehicle speed and road slope data and the off-road condition identification model based on a neural network, a cluster identification result is determined, including: Based on the historical vehicle speed and road slope data, determining characteristic parameters of the vehicle speed and road slope data; Performing fuzzy processing on the vehicle speed and road slope data at the current moment in the historical vehicle speed and road slope data to obtain the off-road identification factor at the current moment; The characteristic parameters and the off-road identification factor at the current moment are input into a well-trained off-road operating condition identification model to obtain a cluster identification result.
[0010] In some possible implementations, the off-road operating condition identification model is a BP neural network model.
[0011] In some possible implementations, the calculation formula for the vehicle required power is:
[0012] In the formula, represents the vehicle's required power, Indicates the future vehicle speed data, represents the weight of the vehicle, represents the vehicle rolling resistance coefficient, represents the future slope data, is the air resistance coefficient, represents the frontal area of the vehicle, Indicates the vehicle mass, represents the vehicle's acceleration, Indicates the efficiency of the vehicle's powertrain.
[0013] In some possible implementations, determining a maneuverability coefficient for characterizing the effect of off-road degree on power based on the future vehicle speed and road slope data includes: Performing fuzzy processing on the future vehicle speed and road slope data to obtain an off-road identification factor at a future moment; Determining a maneuverability coefficient based on the off-road identification factor at the future time; The calculation formula of the maneuver coefficient is:
[0014]
[0015] In the formula, express The mobility coefficient at the time, express The off-road identification factor at all times, represents the minimum threshold of off-road identification factor, Indicates the maximum threshold of the off-road identification factor.
[0016] In some possible implementations, the dynamic objective function for:
[0017]
[0018]
[0019]
[0020]
[0021] In the formula, Indicates the current moment, Indicates the size of the prediction time domain, express Momentary mobility coefficient, express The actual output power of the APU at the moment, express The APU requires power at all times. express The vehicle's power demand at any given moment, express Battery output power at all times, express The battery SOC adjustment factor at each moment, is the natural logarithm, and represents the adjustment parameter, represents the optimal target value of battery SOC, express Battery charge status at all times, express The battery charge / discharge efficiency at all times, express Battery charge / discharge power threshold at all times, express Battery voltage at the moment, express The battery charge / discharge current threshold at all times, express Time charge / discharge rate, Indicates the battery capacity.
[0022] In some possible implementations, the objective function also includes an economic objective function. for:
[0023]
[0024]
[0025] =
[0026] In the formula, Indicates the current moment, Indicates the size of the prediction time domain, express Diesel engine fuel consumption at each moment, express The actual output power of the APU at the moment, express Fuel consumption rate at each moment, Indicates the time difference, Indicates the working efficiency of the generator, express Equivalent fuel consumption of battery at all times, express The battery equivalent fuel consumption factor at the moment, express Engine efficiency at all times, express The battery's charge / discharge efficiency at all times, express Battery output power at all times, Indicates the lower calorific value of diesel.
[0027] The present application also provides a hybrid off-road vehicle energy management device, comprising: A data acquisition unit, used to acquire historical vehicle speed and road slope data; A working condition prediction unit, used for predicting future vehicle speed and road slope data based on the historical vehicle speed and road slope data; a function construction unit, for determining a vehicle required power and a maneuverability coefficient for characterizing the effect of off-road degree on power based on the future vehicle speed and road slope data, and determining an objective function with an actual APU output power as an independent variable based on the maneuverability coefficient and the vehicle required power, wherein the objective function includes a dynamic objective function; The function solving unit is used to solve the objective function to obtain the actual output power of the APU.
[0028] The beneficial effect of the present application is that the hybrid off-road vehicle energy management method provided by the present application adjusts the relationship between the actual output power of the APU and the required power of the APU through the maneuverability coefficient, so that under conditions where the off-road degree is high, the driving environment is poor, the road conditions are complex and changeable, and the power performance requirements are high, the actual output power of the APU can be slightly higher than the required power of the APU, so as to better cope with the step-like vehicle power demand caused by the high off-road degree, and effectively improve the maneuverability of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 A schematic flow chart of an embodiment of a hybrid off-road vehicle energy management method provided in the present application; Figure 2 For this application Figure 1 A schematic flow chart of an embodiment of step S102; Figure 3 For this application Figure 2 A schematic flow chart of an embodiment of step S201; Figure 4 Schematic diagram of fuzzy regular surface provided for this application; Figure 5 A schematic diagram of the battery SOC adjustment factor versus SOC curve provided in this application; Figure 6 A schematic structural diagram of an embodiment of a hybrid off-road vehicle energy management device provided in this application. DETAILED DESCRIPTION
[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.
[0031] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowcharts, or may remove one or more operations from the flowcharts, under the guidance of the content of this application. Some of the block diagrams shown in the accompanying drawings are functional entities, and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.
[0032] The descriptions of "first", "second", etc. involved in the embodiments of the present application are only used to describe the implicit purpose, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist, for example: A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone.
[0033] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0034] The present application provides a hybrid off-road vehicle energy management method, which is described below.
[0035] Figure 1 A schematic flow chart of an embodiment of the hybrid off-road vehicle energy management method provided in this application is as follows: Figure 1 As shown, the energy management method of the hybrid off-road vehicle includes: S101, obtaining historical vehicle speed and road slope data; S102, predicting future vehicle speed and road slope data based on historical vehicle speed and road slope data; S103, determining the vehicle required power and a maneuverability coefficient for characterizing the effect of off-road degree on power based on the future vehicle speed and road slope data; S104, determining an objective function with the actual output power of the APU as an independent variable based on the maneuverability coefficient and the vehicle required power, wherein the objective function includes a dynamic objective function; It will be appreciated that APU refers to engine generator unit.
[0036] S105: Solve the objective function to obtain the actual output power of the APU.
[0037] Compared with the prior art, the present application adjusts the relationship between the actual APU output power and the APU required power through the maneuverability coefficient, so that the actual APU output power can be slightly higher than the APU required power under conditions where the off-road degree is high, the driving environment is poor, the road conditions are complex and changeable, and the power performance requirements are high. This can better cope with the step-like vehicle power demand caused by the high off-road degree, and effectively improve the vehicle's maneuverability.
[0038] In order to better predict future vehicle speed and road slope data, in some embodiments, such as Figure 2 As shown, step S102 includes: S201, determining a cluster identification result based on historical vehicle speed and road slope data and an off-road condition identification model based on a neural network; S202, determining a fully trained operating condition data prediction model corresponding to the cluster identification result, where the operating condition data prediction model is a neural network model; It should be noted that the operating condition data prediction model is a bidirectional Bi-LSTM neural network model. The training set input of the bidirectional Bi-LSTM neural network consists of operating condition segments in the off-road operating condition library. In the actual prediction process, it has high versatility, but excessive versatility will affect the prediction accuracy of the prediction model. Taking the above problems into consideration, this application optimizes the training set composition of the training prediction model (designs appropriate operating condition segment weights) based on the above cluster identification results, and designs a multi-layer Bi-LSTM neural network operating condition data prediction model. On the basis of ensuring a certain degree of operating condition versatility, it improves the prediction accuracy of the prediction model and the calculation speed of the model, providing a more effective parameter basis for the subsequent energy management strategy design.
[0039] Taking the off-road working condition library including 4 clusters of off-road working conditions as an example, the working condition segment weights of the working condition data prediction model training set corresponding to different clusters are shown in Table 1: Table 1: Weights of operating conditions in the model training set corresponding to each cluster
[0040] In Table 1, the prediction model of cluster 1, the total working condition time length is set to , the calculation formula for the splicing length of the training set working condition data is:
[0041]
[0042] In the formula, Represents cluster class In the working condition data prediction model The length of time occupied by the cluster operating condition segment, Represents cluster class In the working condition data prediction model The proportion of cluster operating conditions.
[0043] S203 , inputting historical vehicle speed and road slope data into a well-trained working condition data prediction model corresponding to the cluster identification result to obtain future vehicle speed and road slope data.
[0044] In order to obtain better cluster identification results, in some embodiments, such as Figure 3 As shown, step S201 includes: S301, determining characteristic parameters of vehicle speed and road slope data based on historical vehicle speed and road slope data; It should be noted that the historical vehicle speed and road slope data (driving condition data) are sampled and updated and iterated through a sliding window. The historical vehicle speed and road slope data specifically refer to the vehicle speed and road slope data within the window size time from the current moment. Following the time series changes, the data samples are updated and the samples with changes at the front end of the time series are deleted. The sliding window of the fixed window needs to set two parameters, the window size and the update time. The window size is the sample size of the condition data in the window, and the update time is the cycle of the condition data update. By collecting data within a fixed time period, the update efficiency and adaptability of the off-road condition identification model can be improved.
[0045] It should also be noted that the 17 characteristic parameters with higher independence are shown in Table 2: Table 2: Characteristic parameters
[0046] S302, performing fuzzy processing on the current vehicle speed and road slope data in the historical vehicle speed and road slope data to obtain the off-road identification factor at the current moment; It should be noted that the off-road identification factor can characterize the transient characteristic parameters of the vehicle. Since it is not affected by historical information, its transient response speed is fast, which can improve the identification accuracy and response speed of the off-road condition identification model when the working conditions change. At the same time, by limiting the distribution range threshold, it can improve the stability of the condition identification under fixed conditions.
[0047] It should also be noted that, in this embodiment, the fuzzy processing steps are specifically as follows: 1) Input and output fuzzification: The speed and road slope As the input of the fuzzy control system, the off-road identification factor As the output of the fuzzy system, the membership function of the input and output (combination of triangle and trapezoid) is determined; the fuzzy subsets of vehicle speed, road slope and off-road identification factor are shown in the following formula:
[0048]
[0049]
[0050] In the formula, , , and Representing low, medium, high and very high, respectively. , , and They represent urban-like, light off-road, regular off-road and extreme off-road respectively, and characterize the transient off-road degree of the vehicle.
[0051] The basic domain of vehicle speed and road gradient is set according to the upper and lower thresholds of the operating condition fragments in the off-road operating condition library.
[0052] In this embodiment, the off-road operating condition library includes four operating conditions: urban operating condition OR1, extreme off-road operating condition OR2, conventional off-road operating condition OR3 and mild off-road OR4; among them, the urban operating condition OR1 is characterized by uniform distribution of vehicle speed intervals, small changes in acceleration and deceleration, similar vehicle speed-related characteristics to existing typical cycle operating conditions, small road slope and gentle change rate, indicating that the vehicle is on a paved road or an unpaved road with a good road environment; the operating condition fragments of the extreme off-road operating condition OR2 cluster have an average vehicle speed of 10, a maximum vehicle speed of 24, an average slope of 10%, a maximum slope of 60%, and large slope operating condition fragments account for 10%. It is relatively high, and the slope changes frequently, indicating that the vehicle is in a complex off-road condition with poor road conditions and poor passability; the vehicle speed distribution of the working condition fragments of the conventional off-road condition OR3 cluster is relatively high in the range of 30-50, and the vehicle speed of the working condition within the cluster is distributed in the range of 60-80, with an average slope of 6%, a gentle slope change, and a maximum slope of no more than 15%. The proportion of gentle slope conditions is relatively large, indicating moderate off-road conditions; the average speed of the working condition fragments of the mild off-road condition OR4 cluster is distributed in the range of 40±5, and the acceleration and deceleration of this type of working condition fragments are significantly higher than those of the other clusters, indicating the vehicle's rapid maneuvering conditions on unpaved roads.
[0053] Based on the above off-road condition library, set the vehicle speed The basic domain of is [0,120], the road slope The basic domain of is [-20,60], The basic domain of is [-1,1].
[0054] 2) Formulate fuzzy rule table and fuzzy rule surface: The fuzzy rule table is shown in Table 3: Table 3: Fuzzy rules table
[0055] Fuzzy regular surfaces such as Figure 4 shown.
[0056] The above four off-road conditions data are input into the constructed fuzzy controller, and the output off-road identification factor The interval distribution of is shown in Table 4: Table 4: Off-road identification factors corresponding to each cluster of off-road conditions parameter
[0057] When the road slope When the variable language after fuzzification is H or EH, After defuzzification, the road is roughly in the range of [-0.2, 1], which indicates a strong off-road road surface. When the variable language after fuzzification is L or M, After defuzzification, it is roughly in the interval [-1, 0.2], which is characterized as a road with a low degree of off-road.
[0058] S303: Input the characteristic parameters and the off-road identification factor at the current moment into a well-trained off-road operating condition identification model to obtain a cluster identification result.
[0059] It should be noted that, in this embodiment, the off-road condition identification model is a BP neural network model.
[0060] Since the vehicle's required power will vary greatly with the changes in vehicle speed and road slope, the vehicle speed and road slope are important factors affecting the calculation of the vehicle's required power. In some embodiments, in order to better reflect the actual required power under off-road conditions, the calculation formula for the vehicle's required power is:
[0061] In the formula, represents the vehicle's required power, Indicates the future vehicle speed data, represents the weight of the vehicle, represents the vehicle rolling resistance coefficient, represents the future slope data, is the air resistance coefficient, represents the frontal area of the vehicle, Indicates the vehicle mass, represents the vehicle's acceleration, Indicates the efficiency of the vehicle's powertrain.
[0062] When designing the objective function, due to the particularity of off-road vehicles, the energy management strategy goal needs to balance the relationship between power and economic optimization; under conditions where the driving environment is poor, the road conditions are complex and changeable, and the power performance requirements are high, the objective function focuses on the power goal, while the economic goal is at a lower priority, that is, the objective function is designed to relatively reduce fuel consumption while providing better power performance; when the vehicle is driving on a paved road with a low degree of off-road, that is, under conditions where there is no off-road demand, the economic indicator has a higher priority, which is characterized by maximizing the vehicle's mileage under limited fuel reserves.
[0063] In order to improve the maneuverability of the vehicle, this application designs a maneuverability coefficient based on the off-road identification factor to characterize the impact of off-road degree on power. , maneuverability coefficient The calculation formula is:
[0064]
[0065] In the formula, express The mobility coefficient at the time, express The off-road identification factor of the moment is The vehicle speed and road slope data at the moment are obtained by fuzzy processing. express The normalized value, represents the minimum threshold of off-road identification factor, Indicates the maximum threshold of the off-road identification factor.
[0066] At the same time, in order to ensure that the power battery operates in the high-efficiency range as much as possible and avoid excessive and frequent charging and discharging of the battery, a battery SOC adjustment factor is designed to characterize the impact of battery SOC on power. , battery SOC adjustment factor The calculation formula is:
[0067] In the formula, express The battery SOC adjustment factor at each moment, is the natural logarithm, and Represents the adjustment parameter, which is used to characterize the convergence speed of the function. represents the optimal target value of battery SOC, express Battery charge state at all times, battery SOC adjustment factor The SOC curve is as follows: Figure 5 As shown, Figure 5 In the figure, the horizontal axis is SOC and the vertical axis is the battery SOC adjustment factor. .
[0068] Based on the above maneuverability coefficient and battery SOC adjustment factor , determine the dynamic objective function for:
[0069]
[0070]
[0071]
[0072] In the formula, Indicates the current moment, Indicates the size of the prediction time domain, express Momentary mobility coefficient, express The actual output power of the APU at the moment, express The APU requires power at all times. express The vehicle's power demand at any given moment, express Battery output power at all times, express The battery SOC adjustment factor at each moment, express Battery charge status at all times, express The battery charge / discharge efficiency at all times, express Battery charge / discharge power threshold at all times, express Battery voltage at the moment, express The battery charge / discharge current threshold at all times, express The charge / discharge rate at each moment can be obtained in real time by using the table lookup interpolation method. Indicates battery capacity, battery Charge / discharge power at all times The numerical value and Battery SOC adjustment factor at all times , Battery capacity , Battery charge and discharge rate , Battery Charge State and battery voltage related.
[0073] To optimize the dynamic objective function value, under the influence of the maneuverability coefficient, under the OR2, OR3 and OR4 conditions, The actual APU output power exceeds the APU demand power at the current moment, the power output is at a relatively high level, the vehicle's power responsiveness is better, and the excess power is used to charge the power battery. Under the OR1 condition, the gap between the APU demand power and the APU actual output power is smaller, the power performance indicators can also be met, and the vehicle's fuel economy is better. At the same time, the rapid update of the maneuverability coefficient based on the transient identification result of the off-road identification factor enables it to respond quickly to changes in the operating condition cluster, thereby improving its adaptability to the operating conditions.
[0074] In order to keep the power battery SOC in the high efficiency range, the SOC adjustment factor is designed Dynamically adjust the APU demand power by adjusting the power battery output power to achieve SOC maintenance and APU power output adjustment: In a specific embodiment, , when SOC is in the [0%, 50%] interval, the distance of SOC close to 0% is The slope is negatively correlated, that is, the power battery discharge power In a dynamic decreasing trend, the closer the SOC is to 0%, the greater the decrease. The expected power of the APU at this moment Increase, due to the dynamic objective function The rapid convergence of the current moment increases the actual output value of the APU, which charges the power battery while meeting the power demand of the vehicle. When the SOC is near the optimal target value, The value fluctuates around 1, which can achieve dynamic maintenance of SOC; when SOC is in the range of [50%, 100%], the distance between SOC and 0% is The slope is positively correlated, that is, the power battery discharge power The power is in a dynamic increasing trend and the battery is in a high-rate discharge state. The vehicle gives priority to using the power battery as the power source, while fully ensuring the vehicle's demand power responsiveness, avoiding overcharging of the power battery due to excessive power generation of the APU system.
[0075] When the vehicle is traveling on a paved road with a low degree of off-road driving (i.e., the OR1 working condition constructed in this paper, where there is no off-road demand), the priority of the economic index is higher. Therefore, in some embodiments, the economic objective function is designed. for:
[0076]
[0077]
[0078] =
[0079]
[0080] In the formula, Indicates the current moment, Indicates the size of the prediction time domain, express Diesel engine fuel consumption at each moment, express The actual output power of the APU at the moment, express The fuel consumption rate at each moment can be obtained by interpolation. Indicates the time difference, Indicates the working efficiency of the generator, express Equivalent fuel consumption of battery at all times, express The battery equivalent fuel consumption factor at the moment, express Engine efficiency at all times, express The battery's charge / discharge efficiency at all times, express Battery output power at all times, Indicates the low calorific value of diesel. express Generator torque at time, express Generator speed at the moment.
[0081] Based on the above framework, the final objective function includes the dynamic objective function and the economic objective function. The designed objective function is:
[0082] In the formula, is the economic objective function, is the dynamic objective function.
[0083] When solving the objective function, the dynamic programming (DP) algorithm is introduced to solve the multi-objective optimization problem. The comprehensive objective function should be It converges quickly to the minimum, and then finds the optimal control sequence (generator torque and speed) in the solution domain. By controlling the power flow distribution of the on-board energy, the operating efficiency of the whole vehicle is optimized and the comprehensive objective function is Converges to a minimum.
[0084] In order to better implement a hybrid off-road vehicle energy management method in an embodiment of the present application, based on a hybrid off-road vehicle energy management method, correspondingly, as Figure 6 As shown, the embodiment of the present application also provides a hybrid off-road vehicle energy management device 600, including: A data acquisition unit 601 is used to acquire historical vehicle speed and road slope data; The operating condition prediction unit 602 is used to predict future vehicle speed and road slope data based on historical vehicle speed and road slope data; A function construction unit 603 is used to determine the vehicle required power and a maneuverability coefficient used to characterize the influence of off-road degree on power based on the future vehicle speed and road slope data, and determine an objective function with the actual output power of the APU as an independent variable based on the maneuverability coefficient and the vehicle required power, wherein the objective function includes a dynamic objective function; The function solving unit 604 is used to solve the target function to obtain the actual output power of the APU.
[0085] The hybrid off-road vehicle energy management device 600 provided in the above embodiment can implement the technical solution described in the above hybrid off-road vehicle energy management method embodiment. The specific implementation principles of the above units can refer to the corresponding contents in the above hybrid off-road vehicle energy management method embodiment, which will not be repeated here.
[0086] The above is a detailed introduction to a hybrid off-road vehicle energy management method provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
[0087] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.
Claims
1. A hybrid off-road vehicle energy management method, characterized in that: include: Acquire historical vehicle speed and road slope data, and predict future vehicle speed and road slope data based on the historical vehicle speed and road slope data; Determining the vehicle required power and a maneuvering coefficient for characterizing the effect of off-road degree on power based on the future vehicle speed and road gradient data; Determine an objective function with the APU actual output power as an independent variable based on the maneuverability coefficient and the vehicle required power, wherein the objective function includes a dynamic objective function; The objective function is solved to obtain the actual output power of the APU.
2. The hybrid off-road vehicle energy management method according to claim 1, characterized in that: Based on the historical vehicle speed and road slope data, predicting future vehicle speed and road slope data includes: Determining a cluster identification result based on the historical vehicle speed and road slope data and an off-road condition identification model based on a neural network; Determine a fully trained operating condition data prediction model corresponding to the cluster identification result, wherein the operating condition data prediction model is a neural network model; The historical vehicle speed and road slope data are input into a well-trained working condition data prediction model corresponding to the cluster identification result to obtain future vehicle speed and road slope data.
3. The hybrid off-road vehicle energy management method according to claim 2, characterized in that: The operating condition data prediction model is a bidirectional Bi-LSTM neural network model.
4. The hybrid off-road vehicle energy management method according to claim 2, characterized in that: Based on the historical vehicle speed and road slope data and the off-road condition identification model based on a neural network, a cluster identification result is determined, including: Based on the historical vehicle speed and road slope data, determining characteristic parameters of the vehicle speed and road slope data; Performing fuzzy processing on the vehicle speed and road slope data at the current moment in the historical vehicle speed and road slope data to obtain the off-road identification factor at the current moment; The characteristic parameters and the off-road identification factor at the current moment are input into a well-trained off-road operating condition identification model to obtain a cluster identification result.
5. The hybrid off-road vehicle energy management method according to claim 4, characterized in that: The off-road operating condition identification model is a BP neural network model.
6. The hybrid off-road vehicle energy management method according to claim 1, characterized in that: The calculation formula of the vehicle demand power is: In the formula, represents the vehicle's required power, Indicates the future vehicle speed data, represents the weight of the vehicle, represents the vehicle rolling resistance coefficient, represents the future slope data, is the air resistance coefficient, represents the frontal area of the vehicle, Indicates the vehicle mass, represents the vehicle's acceleration, Indicates the efficiency of the vehicle's powertrain.
7. The hybrid off-road vehicle energy management method according to claim 1, characterized in that: Based on the future vehicle speed and road slope data, a maneuvering coefficient for characterizing the effect of off-road degree on power is determined, including: Performing fuzzy processing on the future vehicle speed and road slope data to obtain an off-road identification factor at a future moment; Determining a maneuverability coefficient based on the off-road identification factor at the future time; The calculation formula of the maneuver coefficient is: In the formula, express The mobility coefficient at the time, express The off-road identification factor at all times, represents the minimum threshold of off-road identification factor, Indicates the maximum threshold of the off-road identification factor.
8. The hybrid off-road vehicle energy management method according to claim 7, characterized in that: The dynamic objective function for: In the formula, Indicates the current moment, Indicates the prediction time domain size, express Momentary mobility coefficient, express The actual output power of the APU at the moment, express The APU requires power at all times. express The vehicle's power demand at any given moment, express Battery output power at all times, express The battery SOC adjustment factor at each moment, is the natural logarithm, and represents the adjustment parameter, Indicates the optimal target value of battery SOC, express Battery charge status at all times, express The battery charge / discharge efficiency at all times, express Battery charge / discharge power threshold at all times, express Battery voltage at the moment, express The battery charge / discharge current threshold at all times, express Time charge / discharge rate, Indicates the battery capacity.
9. The hybrid off-road vehicle energy management method according to claim 1, characterized in that: The objective function also includes an economic objective function, wherein the economic objective function for: = In the formula, Indicates the current moment, Indicates the size of the prediction time domain, express Diesel engine fuel consumption at each moment, express The actual output power of the APU at the moment, express Fuel consumption rate at each moment, Indicates the time difference, Indicates the working efficiency of the generator, express The equivalent fuel consumption of the battery at each moment, express The battery equivalent fuel consumption factor at the moment, express Engine efficiency at all times, express The charging / discharging efficiency of the battery at all times, express Battery output power at all times, Indicates the lower calorific value of diesel.
10. A hybrid off-road vehicle energy management device, characterized in that: include: A data acquisition unit, used to acquire historical vehicle speed and road slope data; A working condition prediction unit, used for predicting future vehicle speed and road slope data based on the historical vehicle speed and road slope data; a function construction unit, for determining a vehicle required power and a maneuverability coefficient for characterizing the effect of off-road degree on power based on the future vehicle speed and road slope data, and determining an objective function with an actual APU output power as an independent variable based on the maneuverability coefficient and the vehicle required power, wherein the objective function includes a dynamic objective function; The function solving unit is used to solve the objective function to obtain the actual output power of the APU.
Citation Information
Cited By
Hybrid power automobile train energy management method based on self-adaptive weight dynamic programming
CN121947451A
