Energy management method, device and electronic equipment for hybrid off-road vehicle

Abstract

The application relates to an energy management method, device and electronic equipment of a hybrid off-road vehicle, which comprises the following steps: acquiring a target characteristic parameter of the off-road vehicle in real time, calculating a principal component score of the off-road vehicle according to the target characteristic parameter; performing cluster analysis on the principal component score of the off-road vehicle, and determining a driving condition type of the off-road vehicle according to the cluster analysis result; determining a demand power analysis model according to the driving condition type of the off-road vehicle, inputting the principal component score of the off-road vehicle into the demand power analysis model to obtain the demand power of the off-road vehicle; and calculating the output power of the off-road vehicle according to the target characteristic parameter, the demand power of the off-road vehicle and a preset constraint condition. The application improves the accuracy of the driving condition type determination through the principal component score, improves the real-time performance and accuracy of the demand power through the demand power analysis model, and finally determines the output power through the constraint condition, so that the balance between the power and economy of the off-road vehicle is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle energy management, and in particular to an energy management method, device and electronic equipment for a hybrid off-road vehicle. BACKGROUND

[0002] With the rapid development of vehicle power system technology, the proportion of electrification in automobile power is increasing, and hybrid power technology has become one of the effective technologies for reducing fuel consumption. Due to the low market share, special use scenarios and many other reasons, the working condition construction system for off-road vehicles has not yet matured, and key research is still missing. The current research on working condition recognition is mostly based on known information for performance optimization, which limits the control strategy.

[0003] In the prior art, the energy management of hybrid vehicles is mostly a rule-based energy management method, which is mainly formulated according to the control curve MAP of the main components of the vehicle such as the engine and the motor, and the engineering practice experience. The vehicle driving condition is identified, and the energy management strategy corresponding to the vehicle driving condition is adopted to control the output torque of the vehicle engine and motor in real time.

[0004] However, the driving conditions of hybrid off-road vehicles are complex and changeable, and the driving state of hybrid off-road vehicles changes frequently. The existing energy management method for hybrid vehicles cannot meet the accuracy and real-time requirements of hybrid off-road vehicle working condition recognition. At present, the mainstream research direction of hybrid vehicle energy management strategy is mostly based on urban vehicle working conditions with the optimization target of vehicle fuel consumption, and only the economic strategy analysis and design are completed, which cannot meet the balance between power and economy of hybrid off-road vehicles. SUMMARY

[0005] Therefore, it is necessary to provide an energy management method, device and electronic equipment for a hybrid off-road vehicle to solve the problem that the existing energy management method for hybrid vehicles cannot maintain the balance between power and economy of hybrid off-road vehicles, and cannot meet the accuracy and real-time requirements of hybrid off-road vehicle working condition recognition.

[0006] To achieve the above technical purpose, the present application adopts the following technical scheme:

[0007] In a first aspect, the present application provides an energy management method for a hybrid off-road vehicle, comprising:

[0008] real-time acquisition of target feature parameters of the off-road vehicle, calculation of principal component scores of the off-road vehicle according to the target feature parameters;

[0009] clustering analysis of the principal component scores of the off-road vehicle, determination of the driving condition type of the off-road vehicle according to the clustering analysis result;

[0010] determine the demand power of the off-road vehicle according to the principal component scores of the off-road vehicle and the demand power analysis model corresponding to the driving condition type of the off-road vehicle.

[0011] determine the output power of the off-road vehicle according to the target characteristic parameter, the demand power of the off-road vehicle and the preset constraint condition.

[0012] In some possible implementation manners, the target characteristic parameter of the off-road vehicle is acquired in real time, and the principal component scores of the off-road vehicle are calculated according to the target characteristic parameter, including:

[0013] The target characteristic parameter of the off-road vehicle is collected in real time at a preset sampling period, and the principal component scores of the off-road vehicle are obtained by dimension reduction processing of the target characteristic parameter of the off-road vehicle based on a preset analysis method.

[0014] In some possible implementation manners, the principal component scores of the off-road vehicle are subjected to cluster analysis, and the driving condition type of the off-road vehicle is determined according to a result of the cluster analysis, including:

[0015] A plurality of cluster centers are set according to historical driving data of the off-road vehicle.

[0016] A condition similarity between the principal component scores and all the cluster centers is calculated.

[0017] A cluster center corresponding to a maximum value of the condition similarity is set as the driving condition type of the off-road vehicle.

[0018] In some possible implementation manners, the demand power analysis model includes a steady-state condition analysis model and a transient condition analysis model; the demand power analysis model is determined according to the driving condition type of the off-road vehicle, and the demand power of the off-road vehicle is obtained by inputting the principal component scores of the off-road vehicle into the demand power analysis model, including:

[0019] The steady-state condition analysis model and the transient condition analysis model are set according to historical driving data of the off-road vehicle.

[0020] The principal component scores are input into the corresponding demand power analysis model according to the driving condition type of the off-road vehicle and at a preset time window to obtain a demand power time sequence of the off-road vehicle.

[0021] In some possible implementation manners, the principal component scores are input into the corresponding demand power analysis model according to the driving condition type of the off-road vehicle and at a preset time window to obtain a demand power time sequence of the off-road vehicle, including:

[0022] The principal component scores are subjected to Markov time sequence prediction based on the steady-state condition analysis model to determine a steady-state demand power time sequence of the off-road vehicle.

[0023] Based on the transient operating condition analysis model, the NAR neural network time series prediction is performed on the principal component scores to determine the time series of the transient demand power of the off-road vehicle.

[0024] In some possible implementation manners, the target characteristic parameter comprises a change rate of an accelerator pedal opening degree; the output power of the off-road vehicle is calculated according to the target characteristic parameter, the demand power of the off-road vehicle and a preset constraint condition, comprising:

[0025] The demand power of the off-road vehicle and the change rate of the accelerator pedal opening degree are subjected to fuzzy processing to determine an optimization factor;

[0026] The power demand power and the economic demand power are determined according to the optimization factor, the target characteristic parameter and the demand power of the off-road vehicle;

[0027] The comprehensive demand power is determined according to a preset weight factor, the power demand power and the economic demand power;

[0028] The output power of the off-road vehicle is obtained by subjecting the comprehensive demand power to the preset constraint condition.

[0029] In some possible implementation manners, the demand power of the off-road vehicle and the change rate of the accelerator pedal opening degree are subjected to fuzzy processing to determine an optimization factor, comprising:

[0030] The average demand power in the prediction time window is calculated according to the prediction time window and the demand power of the off-road vehicle;

[0031] The average demand power and the change rate of the accelerator pedal opening degree are input into a preset fuzzy controller, and the optimization factor is output.

[0032] In a second aspect, the present application further provides an energy management device of a hybrid off-road vehicle, comprising:

[0033] A principal component score module is configured to acquire a target characteristic parameter of the off-road vehicle in real time, and calculate a principal component score of the off-road vehicle according to the target characteristic parameter;

[0034] An operating condition recognition module is configured to perform cluster analysis on the principal component score of the off-road vehicle, and determine a driving operating condition type of the off-road vehicle according to a result of the cluster analysis;

[0035] A demand power analysis module is configured to determine a demand power analysis model according to the driving operating condition type of the off-road vehicle, and input the principal component score of the off-road vehicle into the demand power analysis model to obtain a demand power of the off-road vehicle;

[0036] An output power calculation module is configured to calculate an output power of the off-road vehicle according to the target characteristic parameter, the demand power of the off-road vehicle and a preset constraint condition.

[0037] In a third aspect, the present application further provides an electronic device comprising a memory and a processor, wherein

[0038] a memory for storing a program;

[0039] a processor coupled to the memory, configured to execute the program stored in the memory, so as to implement the steps in the energy management method of the hybrid off-road vehicle in any of the above implementation manners.

[0040] In a fourth aspect, the present application further provides a computer readable storage medium for storing computer readable programs or instructions, which can implement the steps in the energy management method of the hybrid off-road vehicle in any of the above implementation manners when executed by a processor.

[0041] The beneficial effects of the above embodiments are that the present application relates to an energy management method, device and electronic device of a hybrid off-road vehicle, which comprises the following steps: obtaining a target characteristic parameter of the off-road vehicle in real time, calculating a principal component score of the off-road vehicle according to the target characteristic parameter; performing cluster analysis on the principal component score of the off-road vehicle, and determining a driving condition type of the off-road vehicle according to the result of the cluster analysis; determining a demand power analysis model according to the driving condition type of the off-road vehicle, inputting the principal component score of the off-road vehicle into the demand power analysis model to obtain a demand power of the off-road vehicle; and calculating an output power of the off-road vehicle according to the target characteristic parameter, the demand power of the off-road vehicle and a preset constraint condition. The present application improves an energy management method, device and electronic device of a hybrid off-road vehicle, which first calculates a principal component score, determines a driving condition type of the off-road vehicle through the principal component score, improves the accuracy of driving condition type identification, then accurately determines the demand power of the off-road vehicle through a demand power analysis model, quickly calculates the demand power of the off-road vehicle, improves the real-time performance of the calculation, and finally determines the output power of the off-road vehicle in combination with the constraint condition, so as to balance the power and economy of the off-road vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A flowchart of an embodiment of the energy management method of the hybrid off-road vehicle provided by the present application;

[0043] Figure 2 A relationship diagram of an embodiment of the working condition identification period and the update period provided by the present application;

[0044] Figure 3 A flowchart of an embodiment of step S102 in the method; Figure 1

[0045] Fig. 4(a), (b), (c) and (d) are vehicle speed diagrams of an embodiment of the cluster center type provided by the present application; ​

[0046] Figure 5 For Figure 1 The relationship diagram of an embodiment of step S104;

[0047] Figure 6 The structure diagram of an embodiment of the energy management device of the hybrid off-road vehicle provided by the present application;

[0048] Figure 7 The structure diagram of the electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0049] The preferred embodiments of the present application will be described in detail below with reference to the drawings, which constitute a part of this application, and are used to explain the principles of the embodiments of the present application, but are not used to limit the scope of the present application.

[0050] In the description of the present application, the meaning of "a plurality of" is two or more than two, unless otherwise explicitly and specifically limited.

[0051] In the present application, the reference to "embodiments" means that the specific features, structures or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase at various places in the specification does not necessarily mean that it refers to the same embodiment, nor is it independent or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present application can be combined with other embodiments.

[0052] The present application provides an energy management method, device and electronic equipment for a hybrid off-road vehicle, which are described below respectively.

[0053] Please refer to Figure 1 , Figure 1 The flowchart of an embodiment of the energy management method of the hybrid off-road vehicle provided by the present application, one specific embodiment of the present application discloses an energy management method for a hybrid off-road vehicle, which comprises:

[0054] S101, acquiring the target characteristic parameters of the off-road vehicle in real time, and calculating the principal component score of the off-road vehicle according to the target characteristic parameters;

[0055] S102, performing cluster analysis on the principal component score of the off-road vehicle, and determining the driving condition type of the off-road vehicle according to the result of the cluster analysis;

[0056] S103, determining the demand power analysis model according to the driving condition type of the off-road vehicle, and inputting the principal component score of the off-road vehicle into the demand power analysis model to obtain the demand power of the off-road vehicle;

[0057] S104, calculate the output power of the off-road vehicle according to the target characteristic parameter, the demand power of the off-road vehicle and the preset constraint condition.

[0058] In the above embodiment, the target characteristic parameters of the off-road vehicle driving can be collected by various sensors and detection devices or equipment arranged on the off-road vehicle. It can be understood that the collected characteristic parameters are generally characteristic parameters in a period of time (a working condition section). The characteristic parameters not only need to reflect the speed of vehicle operation, but also need to represent the fluctuation of vehicle speed and the comprehensive proportion of driving state. Therefore, the construction of the characteristic parameter set is mainly based on three dimensions: speed, acceleration and driving state proportion.

[0059] In this embodiment, 14 characteristic parameters are collected, and the 14 characteristic parameters are reduced to 3 principal components K1, K2 and K3 by principal component analysis (PCA), to obtain the principal component scores of the working condition section. K1 is positively correlated with parameters such as average speed, maximum speed, maximum acceleration and deceleration, but has little correlation with average acceleration and its standard deviation, and can be used to quantify the driving scene of moderate and high speed with moderate driving intention; K2 is positively correlated with parameters such as average acceleration, acceleration standard deviation and acceleration and deceleration section proportion, and can be used to quantify the driving scene of low speed with strong driving intention; and K3 highlights the driving scene of low speed with moderate driving intention.

[0060] In this embodiment, the clustering analysis is a driving condition type clustering analysis based on K-Means algorithm. The principal component scores of each working condition section are clustered by K-Means algorithm, and the driving condition type of the hybrid off-road vehicle is extracted therefrom. The Euclidean distance is used to calculate the closeness of the real-time working condition and each cluster condition, which is used in subsequent working condition type identification.

[0061] The demand power analysis model in this embodiment is a Markov-NAR demand power composite prediction model. For steady-state conditions, the Markov prediction model has lower prediction error due to the dependence on the state transition probability matrix. For transient conditions, due to the frequent jump of longitudinal vehicle speed information caused by vehicle sudden acceleration / deceleration, the solidification of the state transition probability matrix makes the accuracy of the Markov prediction model significantly decrease. Therefore, in the whole prediction time domain, the prediction effect of the multi-step NAR model is better than that of the Markov prediction model.

[0062] Combining the characteristics of the two time series prediction methods, the demand power composite prediction model based on working condition identification first identifies the current working condition type through a sliding window online, and then combines the vehicle driving working condition type with the characteristics of different prediction methods: for the transient working condition with high nonlinearity, a multi-step NAR neural network model good at nonlinear fitting is used for power prediction; for the steady-state working condition with relatively stable time series changes, a Markov time series prediction model is used to accurately grasp the state transition process of the vehicle, and the related prediction parameters are dynamically changed to improve the time series prediction effect.

[0063] The power performance function J1 and the economic performance function J2 are determined by the target characteristic parameters and the demand power of the off-road vehicle respectively, and then the comprehensive output power is determined by combining the power performance function J1 and the economic performance function J2. Finally, the final output power of the off-road vehicle is determined by combining the preset constraint condition with the comprehensive output power.

[0064] Compared with the prior art, the energy management method of the hybrid off-road vehicle provided by the embodiment comprises: acquiring target characteristic parameters of the off-road vehicle in real time, calculating principal component scores of the off-road vehicle according to the target characteristic parameters; performing cluster analysis on the principal component scores of the off-road vehicle, and determining a driving working condition type of the off-road vehicle according to the results of the cluster analysis; determining a demand power analysis model according to the driving working condition type of the off-road vehicle, inputting the principal component scores of the off-road vehicle into the demand power analysis model to obtain the demand power of the off-road vehicle; and calculating the output power of the off-road vehicle according to the target characteristic parameters, the demand power of the off-road vehicle and a preset constraint condition. The improved energy management method, device and electronic equipment of the hybrid off-road vehicle first calculate the principal component scores, determine the driving working condition type of the off-road vehicle through the principal component scores, improve the accuracy of driving working condition type identification, then accurately determine the demand power of the off-road vehicle through the demand power analysis model, quickly calculate the demand power of the off-road vehicle, improve the real-time performance of the calculation, and finally determine the output power of the off-road vehicle in combination with the constraint condition to balance the power and economy of the off-road vehicle.

[0065] Please refer to Figure 2 , Figure 2 The relationship diagram between the working condition identification period and the updating period of an embodiment provided by the present application is shown in the figure. In some embodiments of the present application, the target characteristic parameters of the off-road vehicle are acquired in real time, and the principal component scores of the off-road vehicle are calculated according to the target characteristic parameters, which comprises:

[0066] The target characteristic parameters of the off-road vehicle are collected in real time at a preset sampling period, and the target characteristic parameters of the off-road vehicle are dimensionally reduced to obtain the principal component scores of the off-road vehicle based on a preset analysis method.

[0067] In the above embodiment, during real-time driving of the vehicle, assuming that the current time is t, then ΔT is used as a sampling time window for feature parameter extraction, and Δσ is used as a working condition recognition update period. The sliding window recognition method has a backward traceability, that is, when the working condition type is updated at the next time, part of the historical vehicle state information in the working condition recognition period ΔT is still retained, which avoids sample fragmentation and frequent jumping of the recognition result, and thus the vehicle control effect is improved. Meanwhile, appropriate selection of Δσ and ΔT values helps to accurately track the driving state of the off-road vehicle while reducing the calculation amount and improving the online working condition recognition efficiency. As a preferred embodiment, the value of Δσ is 5s, and the value of ΔT is 50s.

[0068] During real-time driving of the vehicle, the feature parameter set is calculated in real time with a period of ΔT; then, according to the principal component space analysis theory, the target working condition section is mapped into the principal component space, and the score values of the principal components K1, K2 and K3 are calculated.

[0069] Referring to Figure 3 , Figure 3 for Figure 1 the flowchart of an embodiment of step S102, in some embodiments of the present application, the principal component scores of the off-road vehicle are subjected to cluster analysis, and the driving working condition type of the off-road vehicle is determined according to the cluster analysis result, which comprises the following steps:

[0070] S301, setting a plurality of cluster centers according to the historical driving data of the off-road vehicle;

[0071] S302, calculating the working condition similarity between the principal component scores and all cluster centers;

[0072] S303, setting the cluster center corresponding to the maximum working condition similarity as the driving working condition type of the off-road vehicle.

[0073] In the above embodiment, referring to Figs. 4(a), (b), (c) and (d), Figs. 4(a), (b), (c) and (d) are vehicle speed schematic diagrams of an embodiment of the cluster center type provided by the present application, the kinematic segment extraction is performed on the typical working conditions by using the travel analysis method, the kinematic segments of the above typical working conditions are extracted by using the script program written by the Matlab software, and after the extraction, a total of 205 segments are accumulated, which are recorded as a typical working condition segment set, the component analysis is performed on the 205 typical working condition segment set, and four typical cluster centers C1, C2, C3 and C4 are determined.

[0074] The calculation formula of the working condition similarity variable ξ(C i ,X Δt ) is as follows:

[0075]

[0076] ξ(X ΔT )=max{ξ(C1,X ΔT ),ξ(C2,X ΔT ),…,ξ(C4,X ΔT )};

[0077] Wherein, m is the number of principal components, X Δt is the target working condition section principal component score set, the online working condition type recognition result is recorded as ξ(X ΔT ), and k represents the time.

[0078] In some embodiments of the application, the demand power analysis model includes a steady state working condition analysis model and a transient working condition analysis model; the demand power analysis model is determined according to the driving condition type of the off-road vehicle, and the principal component score of the off-road vehicle is input into the demand power analysis model to obtain the demand power of the off-road vehicle, including:

[0079] The steady state working condition analysis model and the transient working condition analysis model are set according to the historical driving data of the off-road vehicle;

[0080] The principal component score is input into the corresponding demand power analysis model according to the driving condition type of the off-road vehicle to obtain the demand power time sequence of the off-road vehicle.

[0081] In the above embodiments, the steady state working condition analysis model is a Markov prediction model, and the transient working condition analysis model is a multi-step NAR neural network model. The Markov prediction model and the multi-step NAR neural network model are determined according to the historical driving data of the hybrid off-road vehicle to analyze different types of working conditions.

[0082] The principal component score is input into the corresponding demand power analysis model to obtain the demand power time sequence of the off-road vehicle, wherein the steady state is divided into low and medium speed steady state and medium and high speed steady state of C1 and C4, and the transient state is divided into low and medium speed transient state and medium and high speed transient state of C2 and C3.

[0083] In some embodiments of the application, the principal component score is input into the corresponding demand power analysis model according to the driving condition type of the off-road vehicle to obtain the demand power time sequence of the off-road vehicle, including:

[0084] Based on the steady state working condition analysis model, the Markov time sequence prediction is performed on the principal component score to determine the steady state demand power time sequence of the off-road vehicle;

[0085] Based on the transient working condition analysis model, the NAR neural network time sequence prediction is performed on the principal component score to determine the transient demand power time sequence of the off-road vehicle.

[0086] In the above embodiment, the principal component scores of the steady state working condition are input into the steady state working condition analysis model, and the steady state demand power time sequence of the off-road vehicle is determined through Markov time sequence prediction.

[0087] The principal component scores of the transient working condition are input into the transient working condition analysis model, and the transient demand power time sequence of the off-road vehicle is determined through NAR neural network time sequence prediction.

[0088] It should be noted that Markov time sequence prediction and NAR neural network time sequence prediction are prior art, and the present application does not need to be described in more detail.

[0089] Please refer to Figure 5 , Figure 5 For Figure 1 The relationship diagram of an embodiment of step S104, in some embodiments of the present application, the target characteristic parameter includes the rate of change of the accelerator pedal opening degree; the output power of the off-road vehicle is calculated according to the target characteristic parameter, the demand power of the off-road vehicle and the preset constraint condition, including:

[0090] S501, the demand power of the off-road vehicle and the rate of change of the accelerator pedal opening degree are fuzzy processed to determine an optimization factor;

[0091] S502, the power demand power and the economic demand power are determined according to the optimization factor, the target characteristic parameter and the demand power of the off-road vehicle;

[0092] S503, the comprehensive demand power is determined according to the preset weight factor, the power demand power and the economic demand power;

[0093] S504, the output power of the off-road vehicle is obtained by constraining the comprehensive demand power through the preset constraint condition.

[0094] In the above embodiment, the power source of the hybrid off-road vehicle is the APU system (auxiliary power system) and the diesel engine, and the efficient operation of the APU system is conducive to the rapid replenishment of electric energy, that is, to ensure that the SOC is maintained in the efficient discharge interval, so as to better exert the power potential of the hybrid off-road vehicle and achieve good power response effect. Taking the off-road vehicle sudden acceleration working condition as an example, when the vehicle has a high power request, the power battery should be preferentially discharged in the early stage of driving, and the APU power generation system operation efficiency should be improved as soon as possible in the later stage, so as to efficiently realize power supply while maintaining the SOC in the efficient working interval, and the optimization factor is designed to determine the demand power.

[0095] For the distributed drive hybrid off-road vehicle, the electric energy from the APU power generation system or power battery is transmitted to the wheel hub motor to provide the power source for the whole vehicle. Considering that the power battery has strong charging and discharging capacity in the high-efficiency SOC working interval, and the output response speed is significantly better than that of the APU power generation system, combined with the special demand of the research object for power performance, the power performance function J1 is designed to determine the power demand, and the calculation formula is as follows:

[0096]

[0097]

[0098]

[0099] Wherein, P APU (k) is the output power of the APU power generation system at the kth moment, P req (k) is the demand power of the off-road vehicle at the kth moment, P bat (k) is the output power of the power battery at the kth moment, λ(k) is the charging / discharging rate, ξ(k) is the charging / discharging factor, U(k) is the terminal voltage of the power battery at the kth moment, SOC(k) is the remaining power of the power battery at the kth moment, E bat is the power battery capacity, SOC low and SOC hiigh are the minimum threshold and maximum threshold of the remaining power of the power battery respectively.

[0100] When the hybrid off-road vehicle runs in the working condition with slow change of power demand (such as cruising working condition, suburban working condition), the fuel economy of the whole vehicle should be focused on. Among them, the fuel consumption is the most representative evaluation index of fuel economy, the economic performance function J2 is designed to determine the economic demand power, and the calculation formula is as follows:

[0101]

[0102]

[0103]

[0104] Wherein, f eng (k) is the fuel consumption of the diesel engine, f bat (k) is the equivalent fuel consumption of the power battery, P eng (k) is the output power of the diesel engine at the kth moment, be(k) is the fuel consumption rate of the diesel engine at the kth moment, which is a function of torque and speed, i.e. be(k) = [ eng (), T m ()], which can be obtained by interpolation method; is the equivalent fuel consumption conversion coefficient; ηAPU η is the working efficiency of the APU power generation system when charging the power battery bat H is the working efficiency of the power battery μ I is the low heat value of diesel fuel, and I(k) is the charging and discharging current of the power battery at the kth moment.

[0105] In order to improve the working condition adaptability of the hybrid off-road vehicle, the real-time working condition type of the vehicle is combined with the whole vehicle energy management and APU power generation decision, adaptive factors λ1 and λ2 are introduced to comprehensively adjust the priority relationship between power performance and fuel economy, and the expressions of λ1 and λ2 are as follows:

[0106]

[0107]

[0108] wherein d(C(k),C i ) represents the Euclidean distance between the principal component score of the kth moment working condition recognition window and the principal component score of the i-type cluster center.

[0109] It should be noted that the adaptive factors λ1 and λ2 can be regarded as the optimization weight coefficients of power response and fuel economy respectively, and the online working condition recognition model based on the sliding window divides the working condition into four types C1 to C4. C1 and C4 belong to transient working condition types, accompanied by sudden acceleration / deceleration or emergency overtaking and obstacle climbing intention, the working condition time sequence changes greatly, at this time, the off-road vehicle power demand should be given priority to, and the proportion of J1 in J * should be increased; and C2 and C3 belong to steady working condition types, the vehicle is in cruise or coasting state, the working condition time sequence changes relatively smoothly, therefore, the proportion of J2 should be increased, and the optimal economic performance of the vehicle is pursued, and the predictive control performance function J * Determine the comprehensive demand power:

[0110]

[0111] According to the MPC theory, the optimization solution of the objective function should be limited by certain constraint conditions, otherwise it may lead to the deterioration of the performance of the control system. The setting of the constraint condition is usually derived from the objective limitation factors of the control system, and the present application adds the following constraint conditions from the safety problem of the whole vehicle in the cooperation of multiple energy sources:

[0112] 1) Power battery safety constraint:

[0113]

[0114] wherein P bat_max max and P bat_min min represent the maximum / minimum discharging power of the power battery; U(k) max max and U(k)min Indicates the maximum / minimum terminal voltage; I const (k), I peak (k) represents the continuous charge / discharge and peak charge / discharge current of the power battery, and their values ​​should be less than their respective real-time allowable limits I allow_const (k), I allow_peak (k).

[0115] 2) Safety constraints of the APU power generation system and drive motor:

[0116]

[0117] Among them, P eng_max 、P eng_min is the maximum / minimum output power of the diesel engine; temp eng_max 、temp eng_min - Upper / lower limit of diesel engine operating temperature; P motor Temp is the safe power of the generator. To avoid irreversible high-temperature demagnetization failure of the drive motor / generator due to excessive operating temperature, its value should always be greater than the peak power of the drive motor / generator. motor_max 、temp motor_min The upper / lower limit of the operating temperature of the drive motor / generator.

[0118] For multi-objective optimization problems, dynamic programming algorithms can be used to solve them. The idea is to regard all the calculation and solution processes as several related sub-processes, and to find the optimal control sequence of each sub-process in turn to obtain the optimal solution for a single prediction time domain. * , considering the constraints, the inverse solution process can be expressed as:

[0119] J * (k+p)=min{λ1J1(k+p)+λ2J2(k+p)}

[0120] J * (k+p-1)=min{λ1J1(k+p-1)+λ2J2(k+p-1)+J * (k+p)}

[0121]

[0122] J * (k) = min{λ1J1(k) + λ2J2(k) + J * (k+1)};

[0123] The optimal solution of the multi-objective optimization equation under safety constraints in the prediction time domain is expressed as:

[0124]

[0125] u * The result of (t) is the output power of the off-road vehicle.

[0126] In some embodiments of the present application, the optimization factor is determined by fuzzy processing of the required power of the off-road vehicle and the rate of change of the accelerator pedal opening, comprising:

[0127] calculating the average required power within the prediction time window according to the prediction time window and the required power of the off-road vehicle;

[0128] inputting the average required power and the rate of change of the accelerator pedal opening into a preset fuzzy controller to output the optimization factor.

[0129] In the above embodiments, the average required power is predicted according to the required power and the rate of change of the accelerator pedal opening Δα Acc The responsive optimization factor κ(k) is designed according to the required power analysis model, and the prediction value of t-1 to t-p for t can be obtained. The accuracy of power prediction at t-p to t-1 increases step by step, so the prediction value of the required power at t needs to be self-corrected according to the time window rolling, which is calculated as follows:

[0130]

[0131] wherein, is the corrected prediction average of the required power; and p is the prediction time domain length.

[0132] The fuzzy universe of the preset fuzzy controller is set to [0, 160] and [0, 300], respectively, and the fuzzy language variable is taken as {S, M, B, VB}. The average required power and the rate of change of the accelerator pedal opening are input into the preset fuzzy controller, and the optimization factor κ(k) can be output.

[0133] The significance of κ(k) is that it can dynamically coordinate the power output proportion of different energy sources of the vehicle according to the driving intention of the driver and the change of the required power. Acc It can represent the intensity of the driving intention of the driver, and when Δα Acc When the fuzzy variable language is VB or B, κ(k) is basically in the interval [1, 1.3] after defuzzification, so P APU (k) in the subtracted term in J1 is small, and the output proportion of the power battery rises; similarly, It represents the power prediction average extracted from the working condition information, and when When the fuzzy variable language is VB or B, κ(k) is basically in the interval [0.6, 1] after defuzzification, so P APU(k) increase, thereby increasing the proportion of APU power generation system output power, ensuring the vehicle energy storage and power output efficiency, thereby realizing the vehicle power response performance optimization.

[0134] In order to better implement the energy management method of the hybrid off-road vehicle in the embodiment of the present application, on the basis of the energy management method of the hybrid off-road vehicle, please refer to Figure 6 , Figure 6 The structure diagram of an embodiment of the energy management device of the hybrid off-road vehicle provided by the present application, the embodiment of the present application provides an energy management device 600 of a hybrid off-road vehicle, comprising:

[0135] The principal component score module 610 is configured to acquire the target feature parameter of the off-road vehicle in real time, and calculate the principal component score of the off-road vehicle according to the target feature parameter;

[0136] The working condition recognition module 620 is configured to perform cluster analysis on the principal component score of the off-road vehicle, and determine the driving working condition type of the off-road vehicle according to the result of the cluster analysis;

[0137] The demand power analysis module 630 is configured to determine a demand power analysis model according to the driving working condition type of the off-road vehicle, and input the principal component score of the off-road vehicle into the demand power analysis model to obtain the demand power of the off-road vehicle;

[0138] The output power calculation module 640 is configured to calculate the output power of the off-road vehicle according to the target feature parameter, the demand power of the off-road vehicle and a preset constraint condition.

[0139] It should be noted that the device 600 provided in the above embodiment can realize the technical solutions described in the above method embodiments, and the principles of the specific implementation of the above modules or units can be referred to the corresponding content in the above method embodiments, which will not be described here.

[0140] Please refer to Figure 7 , Figure 7 The structure diagram of an electronic device provided by the embodiment of the present application. Based on the above-mentioned energy management method of the hybrid off-road vehicle, the present application further correspondingly provides an energy management device of a hybrid off-road vehicle. The energy management device of the hybrid off-road vehicle can be a mobile terminal, a desktop computer, a notebook computer, a palm computer and a server, etc. The energy management device of the hybrid off-road vehicle includes a processor 710, a memory 720 and a display 730. Figure 7 Only part of the components of the electronic device are shown, but it should be understood that all the shown components are not required, and more or less components can be alternatively implemented.

[0141] The memory 720 can be an internal storage unit of the energy management device of the hybrid off-road vehicle in some embodiments, such as a hard disk or a memory of the energy management device of the hybrid off-road vehicle. The memory 720 can also be an external storage device of the energy management device of the hybrid off-road vehicle in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the energy management device of the hybrid off-road vehicle. Further, the memory 720 can include both the internal storage unit and the external storage device of the energy management device of the hybrid off-road vehicle. The memory 720 is configured to store application software and various data installed on the energy management device of the hybrid off-road vehicle, such as program codes installed on the energy management device of the hybrid off-road vehicle. The memory 720 can also be configured to temporarily store data that has been output or is to be output. In an embodiment, the memory 720 stores the energy management program 740 of the hybrid off-road vehicle, which can be executed by the processor 710 to implement the energy management method of the hybrid off-road vehicle according to the embodiments of the present application.

[0142] The processor 710 can be a central processing unit (CPU), a microprocessor or other data processing chip in some embodiments, configured to run program codes or process data stored in the memory 720, such as to execute the energy management method of the hybrid off-road vehicle.

[0143] The display 730 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. in some embodiments. The display 730 is configured to display information of the energy management device of the hybrid off-road vehicle and to display a visualized user interface. The components 710-730 of the energy management device of the hybrid off-road vehicle communicate with each other through a system bus.

[0144] In an embodiment, the processor 710 implements the steps in the energy management method of the hybrid off-road vehicle as described above when executing the energy management program 740 of the hybrid off-road vehicle stored in the memory 720.

[0145] The embodiment also provides a computer readable storage medium having the energy management program of the hybrid off-road vehicle stored thereon, which, when executed by a processor, implements the following steps:

[0146] Real-time target characteristic parameters of the off-road vehicle are acquired, and principal component scores of the off-road vehicle are calculated according to the target characteristic parameters;

[0147] The principal component scores of the off-road vehicle are subjected to cluster analysis, and a driving condition type of the off-road vehicle is determined according to a result of the cluster analysis;

[0148] A demand power analysis model is determined according to the driving condition type of the off-road vehicle, and demand power of the off-road vehicle is obtained by inputting the principal component scores of the off-road vehicle into the demand power analysis model;

[0149] Output power of the off-road vehicle is calculated according to the target characteristic parameters, the demand power of the off-road vehicle, and a preset constraint condition.

[0150] In summary, the energy management method, device and electronic equipment for the hybrid off-road vehicle provided in the embodiment include the following steps: real-time target characteristic parameters of the off-road vehicle are acquired, and principal component scores of the off-road vehicle are calculated according to the target characteristic parameters; the principal component scores of the off-road vehicle are subjected to cluster analysis, and a driving condition type of the off-road vehicle is determined according to a result of the cluster analysis; a demand power analysis model is determined according to the driving condition type of the off-road vehicle, and demand power of the off-road vehicle is obtained by inputting the principal component scores of the off-road vehicle into the demand power analysis model; and output power of the off-road vehicle is calculated according to the target characteristic parameters, the demand power of the off-road vehicle, and a preset constraint condition. The energy management method, device and electronic equipment for the hybrid off-road vehicle provided in the embodiment improve the accuracy of driving condition type identification by calculating principal component scores, determining the driving condition type of the off-road vehicle through the principal component scores, accurately determining demand power of the off-road vehicle through the demand power analysis model, quickly calculating the demand power of the off-road vehicle, improving the real-time performance of calculation, and finally determining output power of the off-road vehicle in combination with the constraint condition to achieve a balance between power and economy of the off-road vehicle.

[0151] The above description is merely preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions easily thought of by those skilled in the art within the technical scope disclosed by the present application should be encompassed within the protection scope of the present application.

Claims

1. A method for energy management of a hybrid off-road vehicle, characterized in that: include: acquiring target characteristic parameters of the off-road vehicle in real time, and calculating a principal component score of the off-road vehicle based on the target characteristic parameters; Performing a cluster analysis on the principal component scores of the off-road vehicle, and determining the driving condition type of the off-road vehicle according to the results of the cluster analysis; Determining a power demand analysis model according to the driving condition type of the off-road vehicle, and inputting the principal component score of the off-road vehicle into the power demand analysis model to obtain the power demand of the off-road vehicle; Calculating the output power of the off-road vehicle according to the target characteristic parameters, the required power of the off-road vehicle and preset constraints; The target characteristic parameter includes a rate of change of an accelerator pedal opening; and calculating the output power of the off-road vehicle according to the target characteristic parameter, the required power of the off-road vehicle, and preset constraints includes: Performing fuzzy processing on the required power of the off-road vehicle and the rate of change of the accelerator pedal opening to determine an optimization factor; Determining the power demand power and the economic demand power according to the optimization factor, the target characteristic parameter and the demand power of the off-road vehicle; Determine the comprehensive required power according to the preset weight factor, the power required power and the economic required power; The output power of the off-road vehicle is obtained by constraining the comprehensive required power through the preset constraint condition; The power demand is calculated by a power performance function, which is as follows: Where, For the k The output power at the moment, For off-road vehicles k The power demand at any time, For power battery k The output power at the moment, is the charge / discharge rate, is the charge and discharge factor, For power battery k The terminal voltage at the moment, For power battery k The remaining power at the moment, is the power battery capacity, are the minimum and maximum thresholds of the remaining power of the power battery, is the optimization factor, is the predicted time domain length.

2. The energy management method of a hybrid off-road vehicle according to claim 1, characterized in that: The step of acquiring target characteristic parameters of the off-road vehicle in real time and calculating a principal component score of the off-road vehicle according to the target characteristic parameters includes: The target characteristic parameters of the off-road vehicle are collected in real time at a preset sampling period, and based on a preset analysis method, the target characteristic parameters of the off-road vehicle are subjected to dimensionality reduction processing to obtain a principal component score of the off-road vehicle.

3. The energy management method of a hybrid off-road vehicle according to claim 1, characterized in that: The performing cluster analysis on the principal component scores of the off-road vehicle and determining the driving condition type of the off-road vehicle according to the results of the cluster analysis includes: Set several cluster centers based on the historical driving data of off-road vehicles; Calculating the operating condition similarity between the principal component score and all the cluster centers; The cluster center corresponding to the maximum operating condition similarity value is set as the driving condition type of the off-road vehicle.

4. The energy management method of a hybrid off-road vehicle according to claim 3, characterized in that: The power demand analysis model includes a steady-state operating condition analysis model and a transient operating condition analysis model; determining the power demand analysis model according to the driving condition type of the off-road vehicle, and inputting the principal component score of the off-road vehicle into the power demand analysis model to obtain the power demand of the off-road vehicle, including: Setting the steady-state operating condition analysis model and the transient operating condition analysis model according to historical driving data of the off-road vehicle; According to the driving condition type of the off-road vehicle, the principal component scores are input into the corresponding demand power analysis model in a preset time window to obtain the demand power time series of the off-road vehicle.

5. The energy management method of a hybrid off-road vehicle according to claim 4, characterized in that: The step of inputting the principal component scores into the corresponding power demand analysis model according to the driving condition type of the off-road vehicle in a preset time window to obtain the power demand time series of the off-road vehicle includes: Based on the steady-state operating condition analysis model, performing Markov time series prediction on the principal component scores to determine the steady-state required power time series of the off-road vehicle; Based on the transient operating condition analysis model, the principal component scores are subjected to NAR neural network time series prediction to determine the transient demand power time series of the off-road vehicle.

6. The energy management method of a hybrid off-road vehicle according to claim 1, characterized in that: The step of performing fuzzy processing on the required power of the off-road vehicle and the rate of change of the accelerator pedal opening to determine the optimization factor includes: Calculating an average required power within the forecast time window according to the forecast time window and the required power of the off-road vehicle; The average required power and the rate of change of the accelerator pedal opening are input into a preset fuzzy controller, and an optimization factor is output.

7. An energy management device for a hybrid off-road vehicle, characterized in that: include: A principal component scoring module is used to obtain target characteristic parameters of the off-road vehicle in real time and calculate the principal component score of the off-road vehicle based on the target characteristic parameters; a working condition identification module, configured to perform cluster analysis on the principal component scores of the off-road vehicle and determine the driving condition type of the off-road vehicle based on the results of the cluster analysis; a power demand analysis module, configured to determine a power demand analysis model according to the driving condition type of the off-road vehicle, and input the principal component score of the off-road vehicle into the power demand analysis model to obtain the power demand of the off-road vehicle; an output power calculation module, configured to calculate the output power of the off-road vehicle based on the target characteristic parameters, the required power of the off-road vehicle, and preset constraints; The target characteristic parameter includes a rate of change of an accelerator pedal opening; and calculating the output power of the off-road vehicle according to the target characteristic parameter, the required power of the off-road vehicle, and preset constraints includes: Performing fuzzy processing on the required power of the off-road vehicle and the rate of change of the accelerator pedal opening to determine an optimization factor; Determining the power demand power and the economic demand power according to the optimization factor, the target characteristic parameter and the demand power of the off-road vehicle; Determine the comprehensive required power according to the preset weight factor, the power required power and the economic required power; The output power of the off-road vehicle is obtained by constraining the comprehensive required power through the preset constraint condition; The power demand is calculated by a power performance function, which is as follows: Where, For the k The output power at the moment, For off-road vehicles k The power demand at any time, For power battery k The output power at the moment, is the charge / discharge rate, is the charge and discharge factor, For power battery k The terminal voltage at the moment, For power battery k The remaining power at the moment, is the power battery capacity, are the minimum and maximum thresholds of the remaining power of the power battery, is the optimization factor, is the predicted time domain length.

8. An electronic device, characterized in that: comprising a memory and a processor, wherein, The memory is used to store programs; The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps of the energy management method for a hybrid off-road vehicle according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the energy management method for a hybrid off-road vehicle as described in any one of claims 1 to 6.

Images