CN113552803B - Energy management method based on working condition identification - Google Patents

Energy management method based on working condition identification Download PDF

Info

Publication number
CN113552803B
CN113552803B CN202110846298.8A CN202110846298A CN113552803B CN 113552803 B CN113552803 B CN 113552803B CN 202110846298 A CN202110846298 A CN 202110846298A CN 113552803 B CN113552803 B CN 113552803B
Authority
CN
China
Prior art keywords
soc
working conditions
equivalent fuel
characteristic parameters
energy management
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110846298.8A
Other languages
Chinese (zh)
Other versions
CN113552803A (en
Inventor
郑伟光
李燕青
许恩永
覃记荣
唐荣江
何水龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guilin University of Electronic Technology
Dongfeng Liuzhou Motor Co Ltd
Original Assignee
Guilin University of Electronic Technology
Dongfeng Liuzhou Motor Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guilin University of Electronic Technology, Dongfeng Liuzhou Motor Co Ltd filed Critical Guilin University of Electronic Technology
Priority to CN202110846298.8A priority Critical patent/CN113552803B/en
Publication of CN113552803A publication Critical patent/CN113552803A/en
Application granted granted Critical
Publication of CN113552803B publication Critical patent/CN113552803B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

The invention discloses an energy management method based on working condition identification, which comprises the steps of classifying four typical working conditions by using a K-means clustering algorithm, and calculating clustering centers of the four typical working conditions; establishing an equivalent fuel consumption minimum control strategy according to automobile parameters; combining a multi-island genetic algorithm and a sequence quadratic programming algorithm, and constructing a combined optimization model by using a Task component in Isight software; carrying out integrated optimization on variables of the equivalent fuel consumption minimum control strategy and the clustering centers of the four typical working conditions by using a combined optimization model to obtain a final clustering center and corresponding optimal equivalent fuel coefficients under the four typical working conditions; extracting a section of random driving condition characteristic parameters, classifying the working conditions, and optimally distributing power according to the type of the current typical working condition and the optimal equivalent fuel coefficient; the invention can realize the identification of the characteristic parameters of the working conditions and simultaneously solves the defect of a single local or global optimization algorithm.

Description

Energy management method based on working condition identification
Technical Field
The invention relates to the technical field of energy management of hybrid electric vehicles, in particular to an energy management method based on working condition identification.
Background
The rule-based energy management strategy is relatively low in fuel economy of the whole vehicle compared with the instantaneous optimization, the global optimization and the adaptive energy management strategy based on the working condition identification. Due to the fact that the instantaneous optimization is carried out on one driving working condition, the instantaneous optimization is poor in adaptability to other working conditions, and meanwhile the potential of the instantaneous optimization on improving fuel economy is insufficient; the global optimization algorithm is complex, the calculated amount is large, the future road condition needs to be known, and the practicability is poor; the self-adaptive energy management strategy based on the working condition identification can well improve the fuel economy of the whole vehicle, the commonly adopted working condition identification algorithms are a neural network, a support vector machine and the like, and the working condition identification algorithms are difficult to be directly applied to the energy management strategy of the actual vehicle due to the poor computing capability of the actual vehicle controller. In addition, the hybrid system is optimally designed through manual parameter adjustment or optimization algorithm compiling, so that the workload is large and tedious, and the accuracy is difficult to ensure.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and title of the application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the energy management method based on the working condition identification can improve the problems of low fuel economy of the whole vehicle, avoidance of the problem that a single algorithm falls into a local optimal solution, and effective improvement of the problems of large workload and high fault tolerance rate of compiling optimization algorithms and optimization variable codes.
In order to solve the technical problems, the invention provides the following technical scheme: the method comprises the steps of classifying the working conditions of four typical working conditions by using a K-means clustering algorithm, and calculating the clustering centers of the four typical working conditions; establishing an equivalent fuel consumption minimum control strategy according to automobile parameters; combining a multi-island genetic algorithm and a sequence quadratic programming algorithm, and constructing a combined optimization model by using a Task component in Isight software; performing integrated optimization on the variables of the minimum control strategy of equivalent fuel consumption and the clustering centers of the four typical working conditions by using the combined optimization model to obtain a final clustering center and corresponding optimal equivalent fuel coefficients under the four typical working conditions; and extracting a random section of characteristic parameters of the running condition, classifying the working condition, and optimally distributing power according to the type of the current typical working condition and the optimal equivalent fuel coefficient.
As a preferable scheme of the energy management method based on the working condition identification, the method comprises the following steps: the four typical operating conditions include crowded operating conditions, urban operating conditions, suburban operating conditions and highway operating conditions.
As a preferable scheme of the energy management method based on the working condition identification, the method comprises the following steps: the working condition classification comprises the steps of extracting characteristic parameters of random working conditions in an identification period before the current moment for the random working conditions; and taking the extracted characteristic parameters as an array, calculating Euclidean distances between the array and each cluster center, wherein the cluster center closest to the array is the cluster to which the array belongs, and the working condition to which the current moment belongs is the working condition type represented by the cluster.
As a preferable scheme of the energy management method based on the working condition identification, the method comprises the following steps: selecting characteristic parameters of the running conditions; and selecting the driving condition characteristic parameters by analyzing the correlation among the characteristic parameters and the oil consumption of the traditional automobile and the oil consumption of the hybrid electric automobile respectively and the sensitivity of the characteristic parameters changing along with the working condition.
As a preferable scheme of the energy management method based on the working condition identification, the method comprises the following steps: the sensitivity degree of the characteristic parameter changing along with the working condition comprises that the sensitivity degree of the characteristic parameter changing along with the working condition is determined by R1 and R2, wherein R1 reflects the amplitude of the characteristic parameter changing along with the working condition, and R2 reflects the speed of the characteristic parameter changing along with the working condition;
Figure GDA0003575035730000021
Figure GDA0003575035730000022
wherein x istIs the value of the t-th sample in the database with the sample capacity of n; f. of0.98And f0.02Is the variable value when the function value of the cumulative distribution of a certain variable is respectively 0.98 and 0.02.
As a preferable scheme of the energy management method based on the working condition identification, the method comprises the following steps: the establishment of the minimum control strategy of the equivalent fuel consumption comprises the establishment of a penalty function fsocGA _ NLPQL, wave for controlling battery SOCThe dynamic range is as follows:
Figure GDA0003575035730000023
establishing an objective function optimized by an equivalent fuel minimum energy management strategy
Figure GDA0003575035730000024
Constraint conditions are as follows:
Figure GDA0003575035730000025
SOCL≤SOC(t)≤SOCH
defining a fitness function Fit based on the objective functionecms(x)：
Figure GDA0003575035730000031
Wherein k isa、kb、kc、kdAnd keFor the fitting coefficient to be optimized,
Figure GDA0003575035730000032
for combined optimized motor equivalent fuel consumption, [ P ]b(t)]In order for the current motor to consume power,
Figure GDA0003575035730000033
for actual fuel consumption, SOC, of the engineL、SOCHRespectively the upper and lower limits of the battery SOC maintaining range, SOC (t) is the battery electric quantity value at the time t, CmaxIs JminGA_NLPQLMaximum estimated value of, DevsocAs an intermediate variable, Devsoc＝Soc-0.5(SOCL+SOCH) And Soc is the battery charge value.
As a preferable scheme of the energy management method based on the working condition identification, the method comprises the following steps: and optimizing the clustering centers of the four typical working conditions by combining a multi-island genetic algorithm and a sequence quadratic programming algorithm, and then carrying out K-means clustering analysis on the typical working condition data to obtain the final clustering center.
As a preferable scheme of the energy management method based on the working condition identification, the method comprises the following steps: the optimal allocation of power comprises initializing the fitting coefficient k to be optimizeda、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdisThen, calculating an optimal distribution mode of the required power under the current fitting coefficient to be optimized; for the random working condition, calculating the oil consumption Qfuel _ ecms of the whole vehicle at the moment, namely the actual oil consumption of the engine
Figure GDA0003575035730000034
Equivalent oil consumption of electric quantity consumed by motor
Figure GDA0003575035730000035
Sum of (2)
Figure GDA0003575035730000036
And judging a fitness function Fitecms(x)If it is minimum, if Fitecms(x)If minimum, the procedure is terminated, otherwise Fit is selected to be enabledecms(x)Copying chromosomes close to 0, generating new populations through crossing and variation, and obtaining a new fitting coefficient k after codinga、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdisRepeating the procedure until obtaining a fitting coefficient k corresponding to the minimum oil consumptiona、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdis。
As a preferable scheme of the energy management method based on the working condition identification, the method comprises the following steps: the automobile parameters comprise the total mass of the whole automobile, the service mass of the whole automobile, the windward area, the wind resistance coefficient, the rolling radius of the dynamic tire, the main reduction ratio, the wheel base, the peak power of the engine, the peak torque of the engine, the maximum rotating speed of the engine, the peak power of the motor, the peak torque of the motor, the maximum rotating speed of the motor, the voltage of a battery and the maximum current of the battery.
The invention has the beneficial effects that: the invention can realize the identification of the characteristic parameters of the working conditions, better combine different working conditions with the control strategy and realize the optimal economy of the whole vehicle under the constraint of the SOC of the battery; in addition, the method adopts the combined optimization algorithm, does not need to compile the optimization algorithm manually, not only avoids the complexity and the error of manually compiling the optimization algorithm, but also gives full play to the advantages of different optimization algorithms, overcomes the defect of a single local or global optimization algorithm, greatly shortens the optimization period of vehicle and control strategy parameters, improves the working efficiency, and has important scientific significance and practical value for the development of the automobile technology.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
FIG. 1 is a schematic flow chart illustrating a method for energy management based on condition identification according to a first embodiment of the present invention;
FIG. 2 is a schematic flow chart of a combined optimization model for an energy management method based on condition identification to optimize charge and discharge coefficients according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram of a random operating condition of a second embodiment of the energy management method based on operating condition identification according to the present invention;
FIG. 4 is a schematic diagram illustrating a condition recognition based energy management method according to a second embodiment of the present invention;
FIG. 5 is a comparative diagram illustrating SOC variation of a second embodiment of the energy management method based on condition identification according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 to 2, a first embodiment of the present invention provides an energy management method based on operating condition identification, including:
s1: classifying the working conditions of the four typical working conditions by using a K-means clustering algorithm, and calculating the clustering centers of the four typical working conditions;
it should be noted that the four typical operating conditions include NYCC (congestion operating condition), UDDS (urban operating condition), CYC _ WVUSUB (suburban operating condition), and HWFET (highway operating condition).
Starting from a certain moment in the driving process of the vehicle, reaching the next moment after t seconds, taking the motion process between the two moments as a data unit, and calling the kinematic segment as a working condition segment; the classification of the working conditions is to summarize the past t in real timepThe change rule of vehicle speed in second (identification period) to predict the future tqThe driving trend of the second (prediction period) changes, the recognition period is 450s, the prediction period is 3s, and when the recognition period is 450s, the driving condition of one section 1800s can be divided into 4 condition sections.
The effect of the operating mode characteristic parameter of traveling is used for carrying out the operating mode discernment, and operating mode characteristic parameter has about 60 a variety at present, and this embodiment divides operating mode data into the operating mode section according to 450 s' interval, extracts 8 kinds of operating mode characteristic parameters that are commonly used from the operating mode section of dividing: average velocity VmeanMaximum vehicle speed VmaxAverage acceleration ameanIdle time ratio ridelCruise time ratio rdriveMaximum acceleration amaxMinimum acceleration aminAnd a running distance s.
(1) Selecting characteristic parameters of the running condition:
and selecting the characteristic parameters of the running condition by analyzing the correlation between the characteristic parameters and the oil consumption of the traditional automobile and the oil consumption of the hybrid electric automobile respectively and the sensitivity of the characteristic parameters changing along with the working condition.
Specifically, the method comprises the following steps: analyzing the capability of each driving condition characteristic parameter for representing the driving condition through the correlation among the driving condition characteristic parameters, wherein the characteristic parameters with the correlation coefficient of more than 0.7 can be mutually replaced;
analyzing the correlation between the characteristic parameters of the driving conditions and the oil consumption of the traditional automobile and the oil consumption of the hybrid power automobile, judging the influence of the characteristic parameters of the driving conditions on the fuel economy, and determining that the characteristic parameters are related to the fuel economy of the automobile when the correlation coefficient is more than 0.3;
calculating the coefficient of variation degree and coefficient of variation rate of each characteristic parameter; the two coefficients are above 0.3 and are considered to meet the requirements;
the sensitivity degree of the characteristic parameter changing along with the working condition is determined by R1 and R2, wherein R1 reflects the amplitude (changing degree coefficient) of the characteristic parameter changing along with the working condition, and R2 reflects the speed (changing rate coefficient) of the characteristic parameter changing along with the working condition;
Figure GDA0003575035730000061
Figure GDA0003575035730000062
wherein x istIs the value of the t-th sample in the database with the sample capacity of n; f. of0.98And f0.02Is the variable value when the function value of the cumulative distribution of a certain variable is respectively 0.98 and 0.02.
Wherein, it should be noted that f is selected0.98And f0.02In order to eliminate the influence of some odd points in the sample on the test result and improve the accuracy of the test, the cumulative distribution function is the integral of the probability density function and is used for completely describingThe probability distribution of a real random variable is described, and the cumulative distribution function is:
F(x)＝P(X≤x)#(3)
where X is a random variable and P (X < ═ X) is the probability that the random variable X is less than or equal to a certain number X.
Through the third step of finally selecting the average speed VmeanAnd cruise time ratio rdriveAs representative characteristic parameters.
(2) The specific steps of classifying the working conditions by using the K-means clustering algorithm are as follows:
extracting characteristic parameters of random working conditions in an identification period before the current moment for the random working conditions;
and secondly, taking the extracted characteristic parameters as an array, calculating Euclidean distances between the array and each cluster center, wherein the cluster center closest to the array is the cluster to which the array belongs, and the working condition to which the current moment belongs is the working condition type represented by the cluster.
(3) Calculating the clustering centers of four typical working conditions:
k mean value clustering is also called fast clustering, and K classes and initial clustering centers are selected firstly; then calculating the minimum distance between each sample and the clustering center, and distributing each sample to the clustering center closest to the sample; then continuously calculating the clustering center and adjusting the category of each sample to ensure that the cluster has higher similarity and the similarity between clusters is lower; the specific process is as follows:
selecting k samples as initial clustering centers according to a certain principle aiming at n samples (z1, z2, …, zk);
secondly, allocating any sample xi to the nearest cluster center by applying Euclidean distance;
euclidean distance is the square root of the sum of the squares of the differences between all n variable values of two samples, i.e.
Figure GDA0003575035730000071
Wherein x isiIs the variable value of the ith variable of sample x; y isiIs of the sample yThe value of the variable of the ith variable.
S2: establishing an equivalent fuel consumption minimum control strategy according to automobile parameters;
(1) objective function for optimizing equivalent fuel consumption minimum control strategy
It should be noted that the minimum control strategy for equivalent fuel consumption is one of the instant optimization energy management strategies, that is, the actual fuel consumption of the engine is made at each time t
Figure GDA0003575035730000072
Equivalent oil consumption of electric quantity consumed by motor
Figure GDA0003575035730000073
Sum of (2)
Figure GDA0003575035730000074
At the minimum, the temperature of the mixture is controlled,
Figure GDA0003575035730000075
the formula is as follows:
Figure GDA0003575035730000076
wherein the content of the first and second substances,
Figure GDA0003575035730000077
is the total equivalent fuel consumption rate;
Figure GDA0003575035730000078
is the actual fuel consumption rate of the engine;
Figure GDA0003575035730000079
the equivalent fuel consumption rate of the motor;
Figure GDA0003575035730000081
can be obtained by interpolation of the steady-state model of the engine,
Figure GDA0003575035730000082
the calculation formula is as follows:
Figure GDA0003575035730000083
wherein k is 0.5{1+ sign [ p ]m(t)]}，pm(t) is the power of the motor at the current moment; rlhvIs a gasoline quality thermal value constant; lambda [ alpha ]equThe expression is equivalent fuel coefficient:
Figure GDA0003575035730000084
wherein λ ischar、λdisEquivalent fuel coefficient, η, of the motor during charging and discharging of the battery, respectivelychar、ηdisAverage efficiency, η, of the motor during charging and discharging of the battery, respectively, under the current driving environmente、ηmThe average efficiency of the engine and the electric machine, respectively, in the current driving environment.
Because the SOC balance of the battery cannot be effectively maintained by a pure equivalent fuel consumption minimum control strategy, a penalty function f is requiredsocThe SOC penalty function adopted in the embodiment is an S-shaped function formed by fitting a curve for 3 times and a curve for 4 times, the curve shape can be adjusted by modifying fitting coefficients a, b and c, and the penalty function fsocThe expression is as follows:
Devsoc＝Soc-0.5(SOCL+SOCH)
fsoc＝a+b(Devsoc)3+c(Devsoc)4
therein, SOCL、SOCHUpper and lower limits of battery SOC maintaining range, DevsocAs an intermediate variable, Devsoc＝Soc-0.5(SOCL+SOCH) Soc is the battery charge value, so the equivalent fuel factor lambdaequRewritable as follows:
λ′equ＝fsoc*λequ
the minimum control strategy for equivalent fuel consumption established by the embodiment is to make the actual fuel consumption of the engine for each moment t
Figure GDA0003575035730000085
Equivalent oil consumption of electric quantity consumed by motor
Figure GDA0003575035730000086
Sum of (2)
Figure GDA0003575035730000087
Minimal solution, due to the charge-discharge coefficient as a variable in genetic optimization, requires equivalent fuel consumption
Figure GDA0003575035730000088
Performing corresponding adjustment to obtain the equivalent oil consumption
Figure GDA0003575035730000089
The expression is as follows:
Figure GDA00035750357300000810
Figure GDA0003575035730000091
wherein λ ischar_GA_NLPQL、λdis_GA_NLPQLThe equivalent fuel coefficients of the motor when the battery is charged and discharged respectively,
Figure GDA00035750357300000910
the maximum value and the minimum value of the motor efficiency when the battery is charged and discharged in the current driving environment are respectively,
Figure GDA00035750357300000911
respectively, the maximum and minimum values of the engine and motor efficiencies in the current driving environment.
Will penalty function fsocTreated as one with DevsocConstructing new penalty function for quartic function of independent variable
Figure GDA0003575035730000092
Comprises the following steps:
Figure GDA0003575035730000093
wherein k isa、kb、kc、kdAnd keFor the fitting coefficient to be optimized, thus the equivalent fuel coefficient
Figure GDA0003575035730000094
Rewritable as follows:
Figure GDA0003575035730000095
therefore, the objective function and the constraint condition of the equivalent fuel consumption minimum control strategy are respectively as follows:
Figure GDA0003575035730000096
SOCL≤SOC(t)≤SOCH
defining a fitness function Fit based on an objective functionecms(x)：
Figure GDA0003575035730000097
Wherein k isa、kb、kc、kdAnd keFor the fitting coefficient to be optimized,
Figure GDA0003575035730000098
for combined optimized motor equivalent fuel consumption, [ P ]b(t)]In order for the current motor to consume power,
Figure GDA0003575035730000099
for the actual fuel consumption of the engine, SOC (t) is the battery charge value at time t, CmaxIs JminGA_NLPQLIs calculated.
S3: combining a multi-island genetic algorithm and a sequence quadratic programming algorithm, and constructing a combined optimization model by using a Task component in Isight software;
a Task component in Isight software is utilized, two optimization modules are selected, a global optimization MIGA (multiple island genetic algorithm) is selected at first, a local optimization algorithm NLPQL (sequential quadratic programming algorithm) is selected to construct a combined optimization model, and a k-means clustering center and a parameter variable in a minimum fuel strategy are integrated and optimized.
S4: carrying out integrated optimization on variables of the equivalent fuel consumption minimum control strategy and the clustering centers of the four typical working conditions by using a combined optimization model to obtain a final clustering center and corresponding optimal equivalent fuel coefficients under the four typical working conditions;
optimizing the clustering center in the step S1 by using a combined optimization model, and then carrying out K-means clustering analysis on the typical working condition data to obtain a final clustering center; the typical operating condition data is divided into 4 clusters, which can be expressed as: congestion working conditions, urban working conditions, suburban working conditions and highway working conditions.
Different penalty functions will influence the charge-discharge coefficient lambdachar、λdisThereby affecting the effect of the capacity management strategy; penalty function fsocThe expression is constructed according to the characteristics of the expression and by depending on experience, and has strong subjectivity; however, for random working conditions, a theoretical optimal penalty function exists, so that the penalty function f needs to be determined accurately and reasonablysoc(ii) a While equivalent fuel coefficient lambdachar、λdisIs obtained by a fixed step length exhaustive method, and if the selected step length is unreasonable, the actual optimal lambda can be missedchar、λdisThe possibility of (a); therefore, the embodiment combines the optimization models to make the penalty function fsocAnd λchar、λdisCarrying out optimization solution so as to realize the construction of optimal punishmentPenalty function fsocAnd avoid lambdachar、λdisMissing the optimal solution.
The specific solving process is as follows:
initializing the fitting coefficient k to be optimizeda、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdisThen, calculating an optimal distribution mode of the required power under the current fitting coefficient to be optimized;
for the random working condition, calculating the oil consumption Qfuel _ ecms of the whole vehicle at the moment, and calculating the oil consumption Qfuel _ ecms of the whole vehicle at the moment, namely the actual oil consumption of the engine
Figure GDA0003575035730000101
Equivalent oil consumption of electric quantity consumed by motor
Figure GDA0003575035730000102
Sum of (2)
Figure GDA0003575035730000103
And judging the fitness function Fitecms(x)If it is minimum, if Fitecms(x)If minimum, the procedure is terminated, otherwise Fit is selected to be enabledecms(x)Copying chromosomes close to 0, generating new populations through crossing and variation, and obtaining a new fitting coefficient k after codinga、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdisRepeating the procedure until obtaining the fitting coefficient k corresponding to the minimum oil consumptiona、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdis。
Preferably, in the embodiment, aiming at the main defects of the K-means clustering algorithm, the optimal initial clustering center is searched by using the global searchability of the combined optimization model, and then the optimized K-means clustering algorithm is operated, so that the stability of the algorithm is improved, and a better clustering effect is obtained.
Further, a random section of characteristic parameters of the running condition are extracted, the working condition is identified, and the optimal power distribution is carried out according to the type of the current typical working condition and the optimal equivalent fuel coefficient, so that the aim of improving the fuel economy of the hybrid electric vehicle is fulfilled.
Example 2
In order to verify and explain the technical effects adopted in the method, the embodiment selects a traditional energy management strategy (without adopting working condition identification) and the method, and respectively simulates the oil consumption and the battery power of the vehicle so as to verify the real effects of the method.
And (3) testing environment: integration of the isight model: integrating a whole vehicle model, a control strategy model and an optimization algorithm, adding control strategy parameters to be optimized, operating the established hybrid whole vehicle model and the control strategy, carrying out simulation calculation, and calculating the oil consumption and the power consumption of the whole vehicle;
the vehicle needs to simulate a random working condition given randomly, and oil consumption and battery power are obtained through simulation by adopting a traditional energy management strategy (working condition identification is not adopted).
The method adopts a random working condition, integrates an automobile model and a whole automobile control strategy model into an idle simulation platform, utilizes a combined optimization model, can quickly find an optimal solution, and finally compares the hundred kilometer oil consumption of two different strategies and the balance of battery electric quantity, wherein the results are respectively shown in table 1 and fig. 5.
Table 1: and (5) oil consumption simulation results.
Variables of Traditional energy management strategy Method for producing a composite material
Oil consumption (1/100km) 11.19 9.91
Distance traveled (m) 20175 20511
As can be seen from table 1 and fig. 5, compared with the conventional energy management strategy, the method can better maintain the electric quantity of the battery, greatly shorten the parameter optimization period of the control strategy, and improve the working efficiency;
referring to fig. 4, for a given random working condition (fig. 3), the method can accurately classify the working condition; the cushion is used for reducing the oil consumption of the whole vehicle.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.

Claims (6)

1. An energy management method based on working condition identification is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
classifying the working conditions of the four typical working conditions by using a K-means clustering algorithm, and calculating the clustering centers of the four typical working conditions;
establishing an equivalent fuel consumption minimum control strategy according to automobile parameters;
combining a multi-island genetic algorithm and a sequence quadratic programming algorithm, and constructing a combined optimization model by using a Task component in Isight software;
performing integrated optimization on the variables of the minimum control strategy of equivalent fuel consumption and the clustering centers of the four typical working conditions by using the combined optimization model to obtain a final clustering center and corresponding optimal equivalent fuel coefficients under the four typical working conditions;
extracting a random section of characteristic parameters of the running condition, classifying the working condition, and optimally distributing power according to the type of the current typical working condition and the optimal equivalent fuel coefficient;
wherein, the establishing of the equivalent fuel consumption minimum control strategy comprises,
establishing a penalty function fsocGA _ NLPQL, control fluctuation range of battery SOC:
fsocGANLPQL＝ka+kb(Devsoc)+kc(Devsoc)2+kd(Devsoc)3+ke(Devsoc)4
establishing an objective function J optimized by an equivalent fuel minimum energy management strategyminGANLPQLAnd constraint conditions:
Figure FDA0003575035720000011
SOCL≤SOC(t)≤SOCH
defining a fitness function Fit based on the objective functionecms(x)：
Figure FDA0003575035720000012
Wherein k isa、kb、kc、kdAnd keFor the fitting coefficient to be optimized,
Figure FDA0003575035720000013
for combined optimized motor equivalent fuel consumption, [ P ]b(t)]In order for the current motor to consume power,
Figure FDA0003575035720000014
for actual fuel consumption, SOC, of the engineL、SOCHRespectively the upper and lower limits of the battery SOC maintaining range, SOC (t) is the battery electric quantity value at the time t, CmaxIs JminGA_NLPQLMaximum estimated value of, DevsocAs an intermediate variable, Devsoc＝Soc-0.5(SOCL+SOCH) Soc is the battery charge value;
the combined optimization model comprises a plurality of combined optimization models,
optimizing the clustering centers of the four typical working conditions by using a combined multi-island genetic algorithm and a sequence quadratic programming algorithm, and then carrying out K-means clustering analysis on the typical working condition data to obtain the final clustering center;
the optimal allocation of the power comprises that,
initializing the fitting coefficient k to be optimizeda、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdisThen, calculating an optimal distribution mode of the required power under the current fitting coefficient to be optimized;
for the random working condition, calculating the oil consumption Qfuel _ ecms of the whole vehicle at the moment, namely the actual oil consumption of the engine
Figure FDA0003575035720000021
Equivalent oil consumption of electric quantity consumed by motor
Figure FDA0003575035720000022
Sum of (2)
Figure FDA0003575035720000023
And judging the fitness function Fitecms(x)If it is minimum, if Fitecms(x)If minimum, the procedure is terminated, otherwise Fit is selected to be enabledecms(x)Copying chromosomes close to 0, generating new populations through crossing and variation, and obtaining a new fitting coefficient k after codinga、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdisRepeating the procedure until obtaining a fitting coefficient k corresponding to the minimum oil consumptiona、kb、kc、kd、keAnd equivalent fuel coefficient lambdachar、λdis。
2. The method for energy management based on condition identification according to claim 1, characterized in that: the four typical operating conditions include crowded operating conditions, urban operating conditions, suburban operating conditions and highway operating conditions.
3. The method for energy management based on condition identification according to claim 1, characterized in that: the classification of the operating conditions includes that,
extracting characteristic parameters of the random working conditions in the identification period before the current moment for the random working conditions;
and taking the extracted characteristic parameters as an array, calculating Euclidean distances between the array and each cluster center, wherein the cluster center closest to the array is the cluster to which the array belongs, and the working condition to which the current moment belongs is the working condition type represented by the cluster.
4. The energy management method based on condition identification according to claim 1 or 3, characterized in that: selecting characteristic parameters of the running conditions;
and selecting the driving condition characteristic parameters by analyzing the correlation among the characteristic parameters and the oil consumption of the traditional automobile and the oil consumption of the hybrid electric automobile respectively and the sensitivity of the characteristic parameters changing along with the working condition.
5. The method for energy management based on condition identification according to claim 4, wherein: the sensitivity of the characteristic parameter to changes in the operating conditions includes,
the sensitivity of the characteristic parameters changing along with the working conditions is determined by R1 and R2, wherein R1 reflects the amplitude of the characteristic parameters changing along with the working conditions, and R2 reflects the speed of the characteristic parameters changing along with the working conditions;
Figure FDA0003575035720000024
Figure FDA0003575035720000031
wherein x istIs the value of the t-th sample in the database with the sample capacity of n; f. of0.98And f0.02Is the variable value when the function value of the cumulative distribution of a certain variable is respectively 0.98 and 0.02.
6. The method for energy management based on condition identification according to claim 1, characterized in that: the automobile parameters comprise the total mass of the whole automobile, the service mass of the whole automobile, the windward area, the wind resistance coefficient, the rolling radius of the dynamic tire, the main reduction ratio, the wheel base, the peak power of the engine, the peak torque of the engine, the maximum rotating speed of the engine, the peak power of the motor, the peak torque of the motor, the maximum rotating speed of the motor, the voltage of a battery and the maximum current of the battery.
CN202110846298.8A 2021-07-26 2021-07-26 Energy management method based on working condition identification Active CN113552803B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110846298.8A CN113552803B (en) 2021-07-26 2021-07-26 Energy management method based on working condition identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110846298.8A CN113552803B (en) 2021-07-26 2021-07-26 Energy management method based on working condition identification

Publications (2)

Publication Number Publication Date
CN113552803A CN113552803A (en) 2021-10-26
CN113552803B true CN113552803B (en) 2022-05-10

Family

ID=78104453

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110846298.8A Active CN113552803B (en) 2021-07-26 2021-07-26 Energy management method based on working condition identification

Country Status (1)

Country Link
CN (1) CN113552803B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113968233B (en) * 2021-10-29 2023-07-21 北京峰智睿联科技有限公司 Intelligent management method for on-line self-learning of whole vehicle energy and processing method for vehicle data

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111775925A (en) * 2020-06-09 2020-10-16 同济大学 Working mode decision method and device for power split hybrid electric vehicle

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107516107A (en) * 2017-08-01 2017-12-26 北京理工大学 A kind of driving cycle classification Forecasting Methodology of motor vehicle driven by mixed power
CN108490368A (en) * 2018-07-02 2018-09-04 桂林电子科技大学 A kind of charging and discharging lithium battery test device and method
GB2581137B (en) * 2019-01-30 2021-03-10 Lightfi Ltd Automation system
CN110727257A (en) * 2019-08-27 2020-01-24 华润置地控股有限公司 Equipment operation diagnosis method and device based on K-means clustering algorithm
CN110696816B (en) * 2019-10-22 2021-01-12 河南科技大学 Dynamic coordination hybrid electric vehicle energy management method based on working condition classification
CN110929920A (en) * 2019-11-05 2020-03-27 中车戚墅堰机车有限公司 Hybrid power train energy management method based on working condition identification
CN110962837B (en) * 2019-11-18 2021-02-09 浙江工业大学 Plug-in hybrid electric vehicle energy management method considering driving style
CN111429040B (en) * 2020-04-27 2022-06-21 西安建筑科技大学 Optimized deployment method for metering equipment of building energy consumption detection system
CN111907342B (en) * 2020-07-31 2022-03-25 江苏理工学院 Working condition identification control method of pure electric vehicle
CN112668848B (en) * 2020-12-18 2024-02-09 北京交通大学 Energy management method for modern tramcar hybrid energy storage system based on working condition analysis
CN113139251B (en) * 2021-04-23 2023-03-14 桂林电子科技大学 Variable working condition rolling bearing fault diagnosis method for optimizing theme correlation analysis

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111775925A (en) * 2020-06-09 2020-10-16 同济大学 Working mode decision method and device for power split hybrid electric vehicle

Also Published As

Publication number Publication date
CN113552803A (en) 2021-10-26

Similar Documents

Publication Publication Date Title
CN106004865B (en) Mileage ADAPTIVE MIXED power vehicle energy management method based on operating mode&#39;s switch
CN107688343B (en) Energy control method of hybrid power vehicle
CN105868942B (en) The orderly charging schedule method of electric car
CN112287463B (en) Fuel cell automobile energy management method based on deep reinforcement learning algorithm
CN108791270B (en) Power component working point regulation and control method of hybrid power vehicle based on working condition prediction
CN111619545B (en) Hybrid electric vehicle energy management method based on traffic information
CN113034210B (en) Vehicle running cost evaluation method based on data driving scene
CN108819934B (en) Power distribution control method of hybrid vehicle
CN112791997B (en) Method for cascade utilization and screening of retired battery
CN110929920A (en) Hybrid power train energy management method based on working condition identification
CN110751314A (en) Electric vehicle load prediction method considering user charging behavior characteristic data driving
CN113479186B (en) Energy management strategy optimization method for hybrid electric vehicle
CN112785845B (en) Vehicle speed prediction method based on K-means clustering and RBF neural network
CN113552803B (en) Energy management method based on working condition identification
CN113297795A (en) Method for constructing running condition of pure electric vehicle
Lin et al. Multi-objective optimized driving strategy of dual-motor EVs using NSGA-II as a case study and comparison of various intelligent algorithms
CN113222385A (en) Method for constructing and evaluating driving condition of electric automobile
Montazeri-Gh et al. Driving condition recognition for genetic-fuzzy HEV control
CN113715629B (en) Residual driving range prediction method based on improved symbolic regression and XGBoost algorithm
CN116702996A (en) Electric bus energy prediction method based on typical working condition recognition
CN117465301A (en) Fuel cell automobile real-time energy management method based on data driving
CN112035536A (en) Electric automobile energy consumption prediction method considering dynamic road network traffic flow
CN116080475A (en) Battery charging optimization management method for electric automobile
CN114139794A (en) Regional public parking lot charging demand prediction method based on parking big data
CN114179777A (en) Variable equivalent factor hybrid electric vehicle energy management method based on working condition identification

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant