An optimal intelligent energy management method under multiple working conditions alternation

Abstract

The application discloses a kind of optimal intelligent energy management methods under the alternation of multiple conditions, it is related to the field of automobile energy management, solve the technical problem that existing energy management strategy because real driving environment and condition thereby affect power output.Step one: obtaining automobile standard power domain, current traffic condition information and current automobile power domain, establish automobile power domain database according to the automobile standard power domain, current traffic condition information and current automobile power domain;Step two: according to the automobile power domain database, construct classification set model;Step three: real-time detection monitoring is carried out to the subsystem in the classification set model and the data in the subsystem are acquired.The application realizes the reasonable use of hybrid vehicle energy, improves the power performance and economy of vehicle, and at the same time, the data contained in power domain database is numerous, there are more working conditions for comparative analysis, and the application scenarios and field range are wide.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automobile energy management, more particularly, it relates to an optimal intelligent energy management method under multiple working conditions alternately. BACKGROUND

[0002] The function of the power domain controller is mainly to control the powertrain of the vehicle, optimize the power performance of the vehicle, and ensure the power safety of the vehicle. Other functions of the power domain controller include but are not limited to engine management, gearbox management, battery management, power distribution management, emission management, speed limit management, fuel saving and power saving management, etc. For a hybrid electric vehicle, a suitable energy management strategy is selected to match the power system, and the energy management strategy is used to effectively coordinate each energy source, so that the power system can work in the high efficiency zone as much as possible, improve the efficiency of the power system and the utilization rate of each energy source, thereby prolonging the service life of the battery.

[0003] However, due to the characteristics of the current battery itself, the performance will be attenuated at high or low temperature, and the energy consumption of comfort and entertainment accessories is large, and the battery temperature is too high or too low, which will affect the power output, thereby affecting the power performance and economy of the vehicle, and bringing more inconvenience to the user. Secondly, the current energy management strategy has certain limitations, because there are many uncertainties in the real driving environment, and in the actual driving process, there are many transient and steady state multiple working conditions alternately, which greatly affect the energy management strategy, so it is necessary to consider multiple basic working conditions to set the energy management strategy. SUMMARY

[0004] The technical problem to be solved by the present application is to solve the technical problem that the existing energy management strategy affects the power output due to the real driving environment and working conditions.

[0005] The optimal intelligent energy management method under multiple working conditions alternately provided by the present application comprises,

[0006] Step 1: Obtain the standard power domain of the vehicle, the current traffic condition information and the current power domain of the vehicle, and establish a vehicle power domain database according to the standard power domain of the vehicle, the current traffic condition information and the current power domain of the vehicle;

[0007] Step 2: Construct a classification set model according to the vehicle power domain database;

[0008] Step 3: Real-time detect and monitor the subsystems in the classification set model and obtain the data in the subsystems;

[0009] Step 4: Optimize the data in the subsystems to output an energy control decision signal.

[0010] As a further improvement, the method for establishing the automobile power domain database is as follows: obtaining a standard state value and a standard parameter in the standard automobile power domain, obtaining a current state value and a current parameter in the current automobile power domain, obtaining a state difference value by subtracting the current state value from the standard state value, and taking the standard state value as an optimal state value when the state difference value is greater than a preset state difference threshold; otherwise, taking the current state value as the optimal state value;

[0011] obtaining a parameter difference value by subtracting the current parameter from the standard parameter, and taking the standard parameter as an optimal parameter when the parameter difference value is greater than a preset parameter difference threshold; otherwise, taking the current parameter as the optimal parameter;

[0012] establishing the automobile power domain database according to the optimal parameter, the optimal state value, and current traffic condition information.

[0013] Further, the method for constructing the classification collection model is as follows:

[0014] First step: extracting keywords of data in the automobile power domain database and indexing the keywords;

[0015] Second step: classifying the keywords and generating a plurality of collections;

[0016] Third step: setting a classifier, inputting the collections into the classifier for training to obtain a subsystem corresponding to the collections, and constructing the classification collection model according to the subsystem.

[0017] Further, the keywords include engine working conditions, road conditions, and automobile driving mileage.

[0018] Further, the method for optimizing data in the subsystem is as follows:

[0019] integrating data in a preset automobile standard database into a standard case, integrating data in the subsystem into an existing case, calculating a case similarity between the existing case and the standard case, taking data in the subsystem corresponding to the existing case as an energy control decision signal when the case similarity is less than a preset standard similarity, and taking data in the automobile standard database corresponding to the standard case as the energy control decision signal when the case similarity is greater than or equal to the standard similarity.

[0020] Further, the data in the automobile standard database and the data in the subsystem are both integrated into a form of a table or an image.

[0021] Further, an expression for calculating the case similarity between the existing case and the standard case is as follows:

[0022]

[0023] Wherein, n is the number of case attributes, w j is the weight of the i-th attribute, p is direct matching, q is indirect matching, C i is the existing case, C r is the standard case, S(C i , C r ) is the case similarity.

[0024] Further, the method for real-time detection and monitoring of the subsystem in the classification set model is:

[0025] The standard parameters in the preset automobile standard database are acquired, the standard parameters are subtracted from the parameters in the subsystem to obtain a data difference value, when the data difference value is greater than or equal to a preset data alarm difference value, fault alarm is performed; when the data difference value is less than the preset data alarm difference value, fault alarm is not performed.

[0026] Further, after outputting the energy control decision signal, the energy control decision signal is recorded into the automobile standard database.

[0027] Further, a decision priority is set, and the data in the subsystem is optimized according to the decision priority and an energy control decision signal is outputted.

[0028] Beneficial effects

[0029] The present application has the advantages that:

[0030] The present application establishes an automobile power domain database according to the acquired automobile standard power domain, current traffic condition information and current automobile power domain, constructs a classification set model according to the automobile power domain database, performs real-time detection and monitoring of the subsystem in the classification set model and acquires the data in the subsystem, optimizes the data in the subsystem to output an energy control decision signal, realizes reasonable utilization of the energy of the hybrid automobile, improves the power performance and economy of the vehicle, and at the same time, the data contained in the power domain database is numerous, the working conditions that can be compared and analyzed are more, the applicable scenarios and field range are wide. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 is the flow chart of the energy management method of the present application;

[0032] Figure 2 is the flow chart of the energy management strategy based on fuzzy rules in the energy management method of the present application;

[0033] Figure 3Torque graph of the energy management strategy based on the Pontryagin minimum value in the energy management method of the application. DETAILED DESCRIPTION

[0034] The application will be further described below in connection with the embodiments, but does not constitute any limitation to the application, and any limited number of modifications made by anyone within the scope of the claims of the application is still within the scope of the claims of the application.

[0035] Reference Figures 1-3 , the optimal intelligent energy management method under multiple working conditions of the application, the method comprises,

[0036] Step one: obtaining the automobile standard power domain, the current traffic condition information and the current automobile power domain, and establishing the automobile power domain database according to the automobile standard power domain, the current traffic condition information and the current automobile power domain.

[0037] The method for establishing the automobile power domain database is to obtain the standard state value and the standard parameter in the automobile standard power domain, obtain the current state value and the current parameter of the current automobile power domain, and obtain the state difference value by subtracting the standard state value from the current state value, when the state difference value is greater than the preset state difference threshold value, the standard state value is taken as the optimal state value, otherwise, the current state value is taken as the optimal state value.

[0038] The parameter difference value is obtained by subtracting the standard parameter from the current standard parameter, when the parameter difference value is greater than the preset parameter difference threshold value, the standard parameter is taken as the optimal parameter, otherwise, the current parameter is taken as the optimal parameter.

[0039] The current automobile power domain database is established according to the optimal parameter, the optimal state value and the current traffic condition information.

[0040] The application also provides a method for establishing a vehicle longitudinal dynamics model in the automobile power domain:

[0041] In the time domain model, the state quantity is x = [s v] T , wherein s is the driving displacement of the vehicle with time, v is the driving speed of the vehicle, and the vehicle longitudinal dynamics state expression is:

[0042]

[0043] , wherein u = F t , F t is the vehicle driving force of the current automobile power domain, is the vehicle longitudinal dynamics state quantity.

[0044] The general automobile driving equation is F t＝ F f+ F w+ Fi+ F j ;

[0045] Wherein F f is the current automobile power domain rolling resistance, F w is the current automobile power domain air resistance, F i is the current automobile power domain slope resistance, F j is the current automobile power domain acceleration resistance.

[0046] Get the expression of the automobile power balance value:

[0047] According to the automobile power balance value, the vehicle driving force, the rolling resistance, the air resistance, the slope resistance and the acceleration resistance, a vehicle longitudinal dynamics model is created.

[0048] Step two: according to the automobile power domain database, a classification set model is constructed. The method for constructing the classification set model is:

[0049] First step: extract the keywords of the data in the automobile power domain database and index the keywords;

[0050] Second step: classify the keywords and generate multiple sets;

[0051] Third step: set a classifier, input the set into the classifier for training to obtain the subsystem corresponding to the set, and construct the classification set model according to the subsystem.

[0052] The keywords include engine working condition, road condition and automobile mileage.

[0053] Step three: real-time detection monitoring is performed on the subsystems in the classification set model, and data in the subsystems are obtained.

[0054] According to the working condition, the road condition and the automobile mileage and other keywords, a general classification is performed, for example, an engine temperature is too high classification. If the current detection is consistent with this classification, it is preferred to enter this set for searching and analysis, that is, the clustering set is divided.

[0055] The method for real-time detection monitoring of the subsystems in the classification set model is:

[0056] Obtain the standard parameters in the preset automobile standard database, and obtain the data difference value by subtracting the parameters in the subsystem from the standard data. When the data difference value is greater than or equal to the preset data alarm difference value, a fault alarm is performed; when the data difference value is less than the preset data alarm difference value, no fault alarm is performed.

[0057] Step 4: Optimize the data in the subsystem to output the energy control decision signal. After outputting the energy control decision signal, record it in the vehicle standard database.

[0058] The method for optimizing the data in the subsystem is as follows:

[0059] The case-based reasoning method integrates data from a pre-set automotive standard database into standard cases and data from subsystems into existing cases. It calculates the case similarity between existing cases and standard cases. When the case similarity is less than the pre-set standard similarity, the data from the subsystem corresponding to the existing case is used as the energy control decision signal. When the case similarity is greater than or equal to the standard similarity, the data from the automotive standard database corresponding to the standard case is used as the energy control decision signal.

[0060] The data in the automotive standard database and the data in the subsystems are integrated into tables or images.

[0061] The expression for calculating the case similarity between existing cases and standard cases is:

[0062]

[0063] Where n is the number of case attributes, w j Let be the weight of the i-th attribute. p represents direct matching, q represents indirect matching, and C represents direct matching. i As an existing case, C r For the standard case, the case set is: C = {C1, C2, LC} i The attribute set of the i-th case is...

[0064] The system sets decision priorities and optimizes data in subsystems based on these priorities, outputting energy control decision signals. For example, regarding the problem of weak acceleration in a car, based on the preset decision priorities, the system first considers the internal combustion engine, a key component, acquiring relevant data for analysis, optimization, and management decisions. This includes improving combustion efficiency by adjusting the fuel ratio and adjusting the power of the fuel pump or intake and exhaust valves. Next, the system optimizes the transmission system by adjusting the transmission ratio to reduce energy loss during transmission. Finally, it analyzes phenomena such as abnormal tire pressure, ultimately completing the system's sequential optimization of a specific problem.

[0065] This invention provides three standard examples of energy control decisions:

[0066] like Figure 2 As shown, the first standard case is a control strategy based on fuzzy rules:

[0067] The control of the hybrid system can be completed without the precise mathematical standard model, which is more suitable for the multivariable, nonlinear and time-varying hybrid system, and has strong stability and robustness.

[0068] For the reasonable distribution of the power of the vehicle with multiple power sources, when the SOC (state of charge) of the power battery is in the middle and high state stage, the ECU controls the vehicle to preferentially use the energy of the power battery to run under the condition that other requirements are met; when the SOC of the power battery is in the low state, the economy of the vehicle is preferred, and the fuel cell outputs most of the power to meet the energy requirement of normal driving. The SOC of the power battery is maintained in a reasonable charge state interval through energy management, and the whole process mainly uses the SOC of the power battery and the working condition power as the main input parameters to perform fuzzy logic control of small variables.

[0069] As shown in Figure 3 , the second standard case is an energy management strategy based on Pontryagin minimum value:

[0070] The Pontryagin minimum value (PMP) principle is in the form of a set of optimal necessary conditions, which redefines the global optimal control problem according to the local conditions of satisfying the system state, the variation of the coordination state and the instantaneous minimization.

[0071] Suppose that the state equation of the control system is:

[0072] Where x (t) is the state quantity, u (t) is the control quantity, is the state value of the control system.

[0073] The goal of the optimization problem is to minimize the total cost consumed at the end of the system operation, which can be represented by an augmented cost function, specifically as shown in the formula:

[0074] Where J (tf) is the total cost of the system, tf represents the time when the system ends, L(x (t) , u (t) ) is the instantaneous cost function, and Φ(x (tf) ) is the system end state condition.

[0075] The motor-assisted energy control strategy uses the engine as the main power source, and the motor and the battery assist to provide peak power. This control strategy is easy to optimize the engine operating conditions. Compared with the engine, the motor has fast response and sensitive control, and different control methods can be easily realized. This control strategy is used in most parallel hybrid systems. First, the power demand of the system is obtained according to the driver's instructions (accelerator pedal and brake pedal); the controller controls the energy flow in the hybrid system according to the power demand; then the operating state of the engine and the motor is divided by the SOC according to the vehicle speed, load and battery SOC.

[0076] As shown in Figure 3 When the SOC is greater than the lower limit value cs lo soc, the engine efficiency is too low in the case of low vehicle speed, engine speed lower than the starting speed, or system demand torque too low, at which time the engine is turned off and the motor provides all the drive torque (shown in the shaded area in Figure 3 When the system demand torque is greater than the maximum torque that the engine can provide, the engine and the motor jointly provide torque (shown in the area above the engine maximum torque curve in Figure 3 ).

[0077] The third standard case is a real-time energy management strategy based on minimum equivalent fuel consumption:

[0078] In order to minimize the battery energy output, when the vehicle driving force F t is negative, the energy consumption is constant; when the vehicle driving force F t is positive, the battery outputs energy, and the energy consumption function is P(t), and the energy consumption E t in a predicted time T can be described as:

[0079]

[0080] The basic principle is to save a certain amount of fuel by using electric energy; the implementation method is to convert the electric energy consumed or recovered by the motor into fuel consumption through a conversion factor (equivalent factor), and the objective function is converted into total fuel consumption, and the output torque of the motor is determined by solving the minimum objective function.

[0081] The essence of the adaptive equivalent fuel consumption algorithm is to automatically adjust the equivalent factor to minimize the equivalent fuel consumption using some algorithms. At present, most of them use PI controllers to adaptively adjust the equivalent factor.

[0082] PID control is a linear control, which is based on the set value r (t) and the actual output value y (t) to form a control error e(t):

[0083] e(t) = r(t) - y(t)

[0084] Continuous case

[0085]

[0086] Discrete case

[0087]

[0088] Δu(k) = k p (e(k) - e(k-1)) + k i e(k) + k d e(k) - 2e(k-1) + e(k-2) ;

[0089] According to the research, the equivalent factor can be described as:

[0090]

[0091] Where S (u+1) is the equivalent factor of the next iteration period, S (u) is the equivalent factor of the current iteration period, k p is the proportional factor of the target SOC and the SOC deviation at time t, k i is the integral factor of the target SOC and the SOC deviation at time t. The equivalent factor S (u) of the previous iteration interval [u, u+1] is much lower than the theoretical optimal equivalent factor S optimal(u) that maintains the SOC balance in the interval, so the cost of the hybrid system consuming electric energy is relatively small, and the power battery still has a trend of reducing the SOC; if S (u) is not increased, the battery will still reduce the SOC in the next iteration interval [u+1, u+2], and continue to make the SOC deviate from the SOC, at which time S (u) needs to be increased to make it close to S optimal(u) , which will make the battery have a trend of increasing the SOC. Overall, the SOC data parameters and related power output conditions are monitored in real time, the equivalent factor is introduced, and the adaptive equivalent fuel consumption minimum algorithm is used to maintain the SOC stable as the optimization goal for comprehensive control.

[0092] The above only describes the preferred embodiments of the present application, and it should be noted that for those skilled in the art, without departing from the structure of the present application, a number of modifications and improvements can be made, which will not affect the effect of the present application and the practicality of the patent.

Claims

1. A method for optimal intelligent energy management under multiple operating conditions alternately, characterized in that, The method comprises, Step one: obtaining the automobile standard power domain, current traffic condition information and current automobile power domain, and establishing an automobile power domain database according to the automobile standard power domain, current traffic condition information and current automobile power domain; Step two: constructing a classification set model according to the automobile power domain database; Step three: performing real-time detection monitoring on the subsystems in the classification set model and obtaining data in the subsystems; Step four: optimizing the data in the subsystems to output an energy control decision signal; The method for establishing the automobile power domain database is as follows: obtaining standard state values and standard parameters in the automobile standard power domain, obtaining current state values and current parameters in the current automobile power domain, obtaining state difference values by subtracting the current state values from the standard state values, taking the standard state values as optimal state values when the state difference values are greater than a preset state difference threshold, otherwise, taking the current state values as the optimal state values; obtaining parameter difference values by subtracting the current standard parameters from the standard parameters, taking the standard parameters as optimal parameters when the parameter difference values are greater than a preset parameter difference threshold, otherwise, taking the current parameters as the optimal parameters; establishing an automobile power domain database according to the optimal parameters, optimal state values and current traffic condition information; integrating data in a preset automobile standard database into standard cases, integrating data in the subsystems into existing cases, calculating case similarity between the existing cases and the standard cases, taking data in the subsystems corresponding to the existing cases as the energy control decision signal when the case similarity is less than a preset standard similarity, and taking data in the automobile standard database corresponding to the standard cases as the energy control decision signal when the case similarity is greater than or equal to the standard similarity; The expression for calculating the case similarity between the existing cases and the standard cases is as follows: ； wherein, n is the number of case attributes, w j is the weight of the ith attribute, p is the direct match, q is the indirect match, C i is the existing case, C r is the standard case, S(C i ，C r ) is the case similarity.

2. The optimal intelligent energy management method under multiple working conditions alternation according to claim 1, characterized in that, The method for constructing the classification set model is as follows, First step: extracting keywords of data in the automobile power domain database and indexing the keywords; Second step: classifying the keywords and generating a plurality of sets; Third step: setting a classifier, inputting the sets into the classifier for training to obtain subsystems corresponding to the sets, and constructing the classification set model according to the subsystems.

3. The optimal intelligent energy management method under multiple working conditions alternation according to claim 2, characterized in that, The keywords include engine working conditions, road conditions and automobile driving mileage.

4. The optimal intelligent energy management method under multiple working conditions according to claim 1, characterized in that, The data in the automobile standard database and the data in the subsystems are both integrated into the form of tables or images.

5. The optimal intelligent energy management method under multiple working conditions according to claim 1, characterized in that, The method for performing real-time detection monitoring on the subsystems in the classification set model is as follows: obtaining standard parameters in a preset automobile standard database, obtaining data difference values by subtracting parameters in the subsystems from the standard parameters, performing fault alarm when the data difference values are greater than or equal to a preset data alarm difference value, and not performing fault alarm when the data difference values are less than the preset data alarm difference value.

6. The optimal intelligent energy management method under multiple working conditions according to claim 5, characterized in that, After the energy control decision signal is output, the energy control decision signal is recorded into the automobile standard database.

7. The optimal intelligent energy management method under multiple working conditions according to claim 1, characterized in that, Setting a decision priority, optimizing data in the subsystem according to the decision priority and outputting an energy control decision signal.

Images