CN118070031A - Method and system for extracting equivalent oil consumption correlation characteristics of hybrid electric vehicle - Google Patents
Method and system for extracting equivalent oil consumption correlation characteristics of hybrid electric vehicle Download PDFInfo
- Publication number
- CN118070031A CN118070031A CN202410189116.8A CN202410189116A CN118070031A CN 118070031 A CN118070031 A CN 118070031A CN 202410189116 A CN202410189116 A CN 202410189116A CN 118070031 A CN118070031 A CN 118070031A
- Authority
- CN
- China
- Prior art keywords
- feature
- feature subset
- subset
- subsets
- elements
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 50
- 239000000446 fuel Substances 0.000 claims description 22
- 230000001133 acceleration Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 abstract description 12
- 238000012216 screening Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 description 8
- 238000005457 optimization Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention relates to the technical field of hybrid vehicles, in particular to a method and a system for extracting equivalent oil consumption correlation characteristics of a hybrid vehicle, wherein the method comprises the following steps: acquiring original data of parameter variables of a hybrid electric vehicle; constructing a feature subset taking parameter variables as elements, and initializing the element quantity of the feature subset; based on the element quantity of the feature subsets, arranging and combining parameter variables to obtain a feature set containing a plurality of feature subsets; traversing the feature subsets in the feature set, calculating an evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the minimum evaluation coefficient to be a local optimal feature subset of the feature set; updating the element number of the feature subset, repeating the steps until the element number of the feature subset is equal to the parameter variable number, and enabling the local optimal feature subset with the minimum evaluation coefficient to be the global optimal feature subset. The invention ensures the consistency of the final screening result and the final performance, and expands the reliability and robustness of the algorithm.
Description
Technical Field
The invention relates to the technical field of hybrid vehicles, in particular to a method and a system for extracting equivalent oil consumption correlation characteristics of a hybrid vehicle.
Background
With the development of world economy, the total amount of fossil energy consumption worldwide is gradually increased, and the energy crisis is increasingly exacerbated. In order to reduce the dependence of the automobile industry on petroleum resources and simultaneously alleviate the environmental problem of PM2.5 rise in the atmosphere caused by automobile exhaust emission, the development of various new energy automobiles is supported for a long time in China. Hybrid vehicles are an important transitional vehicle model for the automotive industry to develop into pure electric vehicles via traditional internal combustion engine vehicles. However, the energy system is much more complex than that of the traditional fuel vehicle, and the energy distribution and management of the hybrid power vehicle are more difficult. In order to optimize the dynamic performance and economy of the hybrid electric vehicle, many enterprises currently research the hybrid electric vehicle optimization algorithm. Machine learning is an emerging optimization algorithm, and is increasingly gaining attention.
The feature extraction technology is a basic problem of the machine learning technology, and as one of the filtering method feature extraction technologies, the minimum redundancy maximum correlation analysis method (Minimum Redundancy Maximum Relevance, mRMR) was originally proposed by Peng Hanchuan teacher and the like, and has wide application in the fields of image recognition, machine learning and the like. Considering the single variable filter values considers the correlation between a single input variable and an output variable, and does not consider the correlation between the input variables, the feature subsets selected tend not to be independent of each other. The mRMR algorithm calculates redundancy with existing feature subset elements as new input variables are added to the feature subset and penalizes higher redundancy. mRMR may use various correlation analysis methods such as mutual information, correlation coefficients, etc. The purpose of feature selection is to find a feature subset S with m features such that the feature subset has the greatest correlation with the output variable, a method called Max-release.
However, the conventional mRMR belongs to a typical incremental greedy strategy, and when a feature is selected, the feature cannot be removed in a subsequent step, and the influence of a feature subset which does not contain the variable on the data fitting result is not considered by the strategy, so that the diversity of the feature subset is limited. The mRMR algorithm starts from the correlation operation between each feature variable and the output variable, screens and constructs a feature subset by calculating the correlation and redundancy of each feature, but the method does not consider the influence of the combination of a plurality of features on the correlation of the output variable, namely, the correlation between a single feature and the output variable is weak, but when the data fitting performance of the combination of a plurality of variables is strong, the mRMR algorithm cannot recognize the possibility.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for extracting equivalent oil consumption correlation characteristics of a hybrid electric vehicle.
The invention adopts the following technical scheme: a method for extracting equivalent oil consumption correlation characteristics of a hybrid electric vehicle comprises the following steps:
Acquiring original data of parameter variables of a hybrid electric vehicle, and inputting the original data of the parameter variables as data;
constructing a feature subset taking the parameter variable as an element, and initializing the element number of the feature subset;
Based on the element quantity of the feature subsets, arranging and combining the parameter variables to obtain a feature set containing a plurality of feature subsets;
Traversing the feature subsets in the feature set, calculating an evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the minimum evaluation coefficient to be a local optimal feature subset of the feature set;
And updating the element number of the feature subset, repeating the steps three to four until the element number of the feature subset is equal to the parameter variable number, and enabling the local optimal feature subset with the minimum evaluation coefficient to be a global optimal feature subset, namely enabling the parameter variable forming the global optimal feature subset to be the feature with the highest correlation of the equivalent fuel consumption of the hybrid electric vehicle.
According to the method for extracting the equivalent oil consumption correlation characteristic of the hybrid electric vehicle, disclosed by the embodiment of the invention, the characteristic subset formed by traversing all possible input parameter variable combinations is improved in the recognition capability of fitting effects of the characteristic subset comprising a plurality of parameter variables; the method has better global searching capability, and can screen out a better feature subset, thereby realizing better data fitting effect; considering the influence of the combination of a plurality of parameter variables on the correlation of the output variables, the consistency of the final screening result and the final performance is ensured from the integral performance of the feature subset, and the reliability and the robustness of the algorithm are expanded.
Further, the parameter variables include: battery capacity, battery SOC, engine power, engine start-stop rules, average vehicle speed, maximum acceleration, acceleration time, deceleration time, constant speed time, road grade, road flatness.
Further, the step of constructing a feature subset with the parameter variable as an element, and initializing the element number of the feature subset specifically includes:
Constructing a feature subset, and taking the parameter variable as an element of the feature subset;
Initializing the element number of the feature subset, enabling the element number of the feature subset to be 1, and enabling the element number of the feature subset to be increased by 1 every time of subsequent updating until updating is stopped.
Further, the step of obtaining a feature set including a plurality of feature subsets by permutation and combination of the parameter variables based on the element numbers of the feature subsets specifically includes:
setting the element number of the feature subset as m, and setting the parameter variable number as n;
The parameter variables are arranged and combined to obtain a plurality of feature subsets, each feature subset comprises m parameter variables, the feature subsets form a feature set, and the feature set J m is marked as:
Jm＝(jm1,jm2,jm3,…,jmk)
wherein, m is more than or equal to 1 and less than or equal to m, K is the number of feature subsets when the number of elements is m, J m is the feature set when the number of elements is m, and J mk is the kth feature subset when the number of elements is m.
Further, traversing the feature subsets in the feature set, and calculating an evaluation coefficient corresponding to each feature subset, where the feature subset with the smallest evaluation coefficient is a locally optimal feature subset of the feature set, where the step specifically includes:
traversing the feature subset within the feature set;
Calculating the mean square error and redundancy of each feature subset, which are respectively marked as MSE mk and R mk; wherein MSE mk is the mean square error of the kth feature subset when the number of elements is m, and R mk is the redundancy of the kth feature subset when the number of elements is m;
wherein, the redundancy R mk of the feature subset is:
wherein I is large mutual information among elements of the feature subset, and f x、fy is any two elements of the feature subset respectively; let x=y when m=1;
Calculating the correlation D m of the feature set:
Dm＝min(MSEmk)
wherein D m is the correlation of the feature set when the number of elements is m;
The evaluation coefficients M mk of the feature subset are:
Mmk＝Dm+Rmk
wherein M mk is an evaluation coefficient of the kth feature subset when the element number is M;
the feature subset with the smallest evaluation coefficient is a locally optimal feature subset of the feature set.
The invention also provides a system for extracting the equivalent oil consumption correlation characteristics of the hybrid electric vehicle, which comprises the following steps:
the acquisition module is used for acquiring the original data of the parameter variables of the hybrid electric vehicle and inputting the original data of the parameter variables as data;
an initialization module, configured to construct a feature subset with the parameter variable as an element, and initialize the element number of the feature subset;
the combination module is used for carrying out permutation and combination on the parameter variables based on the element quantity of the feature subsets to obtain a feature set containing a plurality of feature subsets;
The computing module is used for traversing the feature subsets in the feature set, computing the evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the smallest evaluation coefficient to be the local optimal feature subset of the feature set;
The extraction module is used for updating the element number of the feature subset, repeatedly executing permutation and combination of the parameter variables based on the element number of the feature subset, and obtaining a feature set containing a plurality of feature subsets; traversing the feature subsets in the feature set, calculating an evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the minimum evaluation coefficient to be a local optimal feature subset of the feature set; and enabling the local optimal feature subset with the smallest evaluation coefficient to be a global optimal feature subset until the element number of the feature subset is equal to the parameter variable number, namely enabling the parameter variable forming the global optimal feature subset to be the feature with highest correlation of equivalent fuel consumption of the hybrid electric vehicle.
According to the feature extraction system for the equivalent oil consumption of the hybrid electric vehicle, disclosed by the embodiment of the invention, the recognition capability of fitting effects of the feature subset containing a plurality of parameter variables is improved by traversing the feature subset formed by all possible input parameter variable combinations; the method has better global searching capability, and can screen out a better feature subset, thereby realizing better data fitting effect; considering the influence of the combination of a plurality of parameter variables on the correlation of the output variables, the consistency of the final screening result and the final performance is ensured from the integral performance of the feature subset, and the reliability and the robustness of the algorithm are expanded.
Further, the parameter variables include: battery capacity, battery SOC, engine power, engine start-stop rules, average vehicle speed, maximum acceleration, acceleration time, deceleration time, constant speed time, road grade, road flatness.
Further, the initialization module is specifically configured to:
Constructing a feature subset, and taking the parameter variable as an element of the feature subset;
Initializing the element number of the feature subset, enabling the element number of the feature subset to be 1, and enabling the element number of the feature subset to be increased by 1 every time of subsequent updating until updating is stopped.
Further, the combination module is specifically configured to:
setting the element number of the feature subset as m, and setting the parameter variable number as n;
The parameter variables are arranged and combined to obtain a plurality of feature subsets, each feature subset comprises m parameter variables, the feature subsets form a feature set, and the feature set J m is marked as:
Jm＝(jm1,jm2,jm3,…,jmk)
wherein, m is more than or equal to 1 and less than or equal to n, K is the number of feature subsets when the number of elements is m, J m is the feature set when the number of elements is m, and J mk is the kth feature subset when the number of elements is m.
Further, the computing module is specifically configured to:
traversing the feature subset within the feature set;
Calculating the mean square error and redundancy of each feature subset, which are respectively marked as MSE mk and R mk; wherein MSE mk is the mean square error of the kth feature subset when the number of elements is m, and R mk is the redundancy of the kth feature subset when the number of elements is m;
wherein, the redundancy R mk of the feature subset is:
wherein I is large mutual information among elements of the feature subset, and f x、fy is any two elements of the feature subset respectively; let x=y when m=1;
Calculating the correlation D m of the feature set:
Dm＝min(MSEmk)
wherein D m is the correlation of the feature set when the number of elements is m;
The evaluation coefficients M mk of the feature subset are:
Mmk＝Dm+Rmk
wherein M mk is an evaluation coefficient of the kth feature subset when the element number is M;
the feature subset with the smallest evaluation coefficient is a locally optimal feature subset of the feature set.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for extracting equivalent fuel consumption correlation features of a hybrid vehicle according to the present invention;
fig. 2 is a structural block diagram of the equivalent fuel consumption correlation feature extraction system of the hybrid electric vehicle.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended to illustrate embodiments of the invention and should not be construed as limiting the invention.
Example 1
Referring to fig. 1, in a first embodiment of the present invention, a method for extracting equivalent fuel consumption correlation features of a hybrid vehicle includes:
S1: acquiring original data of parameter variables of a hybrid electric vehicle, and inputting the original data of the parameter variables as data; further, the parameter variables include: battery capacity, battery SOC, engine power, engine start-stop rules, average vehicle speed, maximum acceleration, acceleration time, deceleration time, constant speed time, road grade, road flatness.
S2: constructing a feature subset taking the parameter variable as an element, and initializing the element number of the feature subset; further, the method specifically comprises the following steps:
Constructing a feature subset, and taking the parameter variable as an element of the feature subset;
Initializing the element number of the feature subset, enabling the element number of the feature subset to be 1, and enabling the element number of the feature subset to be increased by 1 every time of subsequent updating until updating is stopped.
S3: based on the element quantity of the feature subsets, arranging and combining the parameter variables to obtain a feature set containing a plurality of feature subsets; further, the method specifically comprises the following steps:
setting the element number of the feature subset as m, and setting the parameter variable number as n;
The parameter variables are arranged and combined to obtain a plurality of feature subsets, each feature subset comprises m parameter variables, the feature subsets form a feature set, and the feature set J m is marked as:
Jm＝(jm1,jm2,jm3,…,jmk)
wherein, m is more than or equal to 1 and less than or equal to n, K is the number of feature subsets when the number of elements is m, J m is the feature set when the number of elements is m, and J mk is the kth feature subset when the number of elements is m.
S4: traversing the feature subsets in the feature set, calculating an evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the minimum evaluation coefficient to be a local optimal feature subset of the feature set; further, the method specifically comprises the following steps:
traversing the feature subset within the feature set;
Calculating the mean square error and redundancy of each feature subset, which are respectively marked as MSE mk and R mk; wherein MSE mk is the mean square error of the kth feature subset when the number of elements is m, and R mk is the redundancy of the kth feature subset when the number of elements is m;
wherein, the redundancy R mk of the feature subset is:
wherein I is large mutual information among elements of the feature subset, and f x、fy is any two elements of the feature subset, namely any two parameter variables; let x=y when m=1;
Calculating the correlation D m of the feature set:
Dm＝min(MSEmk)
wherein D m is the correlation of the feature set when the number of elements is m;
The evaluation coefficients M mk of the feature subset are:
Mmk＝Dm+Rmk
wherein M mk is an evaluation coefficient of the kth feature subset when the element number is M;
the feature subset with the smallest evaluation coefficient is a locally optimal feature subset of the feature set.
In the process of correlation calculation, feature subsets are respectively constructed for the potential m parameter variables, in the process, the feature subsets screened in the previous step are not necessarily contained in the feature subsets screened in the current step, and the data fitting results of the feature subsets formed by all combined variables can be explored.
S5: and updating the element number of the feature subset, repeating the steps S3 to S4 until the element number of the feature subset is equal to the parameter variable number, and enabling the local optimal feature subset with the smallest evaluation coefficient to be a global optimal feature subset, namely enabling the parameter variable forming the global optimal feature subset to be the feature with highest correlation of the equivalent fuel consumption of the hybrid electric vehicle.
The invention considers the influence of the combination of a plurality of parameter variables on the correlation of the output variables, m represents the number of the parameter variables in each feature subset, and the number of the parameter variables m in the feature subset is increased by (m+1) along with the increase of the operation cycle until (m+1) =n stops operation and outputs the globally optimal feature subset, namely the maximum value of the number of the parameter variables in the feature subset is (n-1).
According to the method for extracting the equivalent oil consumption correlation characteristic of the hybrid electric vehicle, disclosed by the embodiment of the invention, the characteristic subset formed by traversing all possible input parameter variable combinations is improved in the recognition capability of fitting effects of the characteristic subset comprising a plurality of parameter variables; the method has better global searching capability, and can screen out a better feature subset, thereby realizing better data fitting effect; considering the influence of the combination of a plurality of parameter variables on the correlation of the output variables, the consistency of the final screening result and the final performance is ensured from the integral performance of the feature subset, and the reliability and the robustness of the algorithm are expanded.
Example two
Referring to fig. 2, the invention further provides a system for extracting equivalent oil consumption correlation characteristics of a hybrid electric vehicle, which comprises:
the acquisition module is used for acquiring the original data of the parameter variables of the hybrid electric vehicle and inputting the original data of the parameter variables as data;
an initialization module, configured to construct a feature subset with the parameter variable as an element, and initialize the element number of the feature subset;
the combination module is used for carrying out permutation and combination on the parameter variables based on the element quantity of the feature subsets to obtain a feature set containing a plurality of feature subsets;
The computing module is used for traversing the feature subsets in the feature set, computing the evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the smallest evaluation coefficient to be the local optimal feature subset of the feature set;
The extraction module is used for updating the element number of the feature subset, repeatedly executing permutation and combination of the parameter variables based on the element number of the feature subset, and obtaining a feature set containing a plurality of feature subsets; traversing the feature subsets in the feature set, calculating an evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the minimum evaluation coefficient to be a local optimal feature subset of the feature set; and enabling the local optimal feature subset with the smallest evaluation coefficient to be a global optimal feature subset until the element number of the feature subset is equal to the parameter variable number, namely enabling the parameter variable forming the global optimal feature subset to be the feature with highest correlation of equivalent fuel consumption of the hybrid electric vehicle.
Further, the parameter variables include: battery capacity, battery SOC, engine power, engine start-stop rules, average vehicle speed, maximum acceleration, acceleration time, deceleration time, constant speed time, road grade, road flatness.
Further, the initialization module is specifically configured to:
Constructing a feature subset, and taking the parameter variable as an element of the feature subset;
Initializing the element number of the feature subset, enabling the element number of the feature subset to be 1, and enabling the element number of the feature subset to be increased by 1 every time of subsequent updating until updating is stopped.
Further, the combination module is specifically configured to:
setting the element number of the feature subset as m, and setting the parameter variable number as n;
The parameter variables are arranged and combined to obtain a plurality of feature subsets, each feature subset comprises m parameter variables, the feature subsets form a feature set, and the feature set J m is marked as:
Jm＝(jm1,jm2,jm3,…,jmk)
wherein, m is more than or equal to 1 and less than or equal to n, K is the number of feature subsets when the number of elements is m, J m is the feature set when the number of elements is m, and J mk is the kth feature subset when the number of elements is m.
Further, the computing module is specifically configured to:
traversing the feature subset within the feature set;
Calculating the mean square error and redundancy of each feature subset, which are respectively marked as MSE mk and R mk; wherein MSE mk is the mean square error of the kth feature subset when the number of elements is m, and R mk is the redundancy of the kth feature subset when the number of elements is m;
wherein, the redundancy R mk of the feature subset is:
wherein I is large mutual information among elements of the feature subset, and f x、fy is any two elements of the feature subset respectively; let x=y when m=1;
Calculating the correlation D m of the feature set:
Dm＝min(MSEmk)
wherein D m is the correlation of the feature set when the number of elements is m;
The evaluation coefficients M mk of the feature subset are:
Mmk＝Dm+Rmk
wherein M mk is an evaluation coefficient of the kth feature subset when the element number is M;
the feature subset with the smallest evaluation coefficient is a locally optimal feature subset of the feature set.
As an optimization, the global optimal feature subset shows: the correlation between the feature subset formed by m parameter variables and the equivalent fuel consumption of the hybrid power is highest, and the correlation between various feature subsets and the equivalent fuel consumption is determined in the previous step and is represented by an evaluation coefficient.
As optimization, compared with the MSE mk value of the traditional algorithm and the MSE mk value calculated by the method is superior to the calculation result of the traditional algorithm, the smaller MSE mk value means that the feature subset can achieve better data fitting accuracy.
According to the feature extraction system for the equivalent oil consumption of the hybrid electric vehicle, disclosed by the embodiment of the invention, the recognition capability of fitting effects of the feature subset containing a plurality of parameter variables is improved by traversing the feature subset formed by all possible input parameter variable combinations; the method has better global searching capability, and can screen out a better feature subset, thereby realizing better data fitting effect; considering the influence of the combination of a plurality of parameter variables on the correlation of the output variables, the consistency of the final screening result and the final performance is ensured from the integral performance of the feature subset, and the reliability and the robustness of the algorithm are expanded.
Example III
In a third embodiment of the present invention, based on the same inventive concept, the present invention provides a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements the steps of the method for extracting equivalent fuel consumption correlation characteristics of a hybrid vehicle according to the above embodiment.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain or store the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
The memory may include, among other things, mass storage for data or instructions. By way of example, and not limitation, the memory may comprise a hard disk drive (HARD DISK DRIVE, abbreviated HDD), a floppy disk drive, a Solid state drive (Solid STATE DRIVE, abbreviated SSD), flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (Universal Serial Bus, abbreviated USB) drive, or a combination of two or more of these. The memory may include removable or non-removable (or fixed) media, where appropriate. The memory may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory is a Non-Volatile (Non-Volatile) memory. In particular embodiments, the Memory includes Read-Only Memory (ROM) and random access Memory (Random Access Memory RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, abbreviated PROM), an erasable PROM (Erasable Programmable Read-Only Memory, abbreviated EPROM), an electrically erasable PROM (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, abbreviated EEPROM), an electrically rewritable ROM (ELECTRICALLY ALTERABLE READ-Only Memory, abbreviated EAROM), or a FLASH Memory (FLASH), or a combination of two or more of these. The RAM may be a Static Random-Access Memory (SRAM) or a dynamic Random-Access Memory (Dynamic Random Access Memory DRAM), where the DRAM may be a fast page mode dynamic Random-Access Memory (Fast Page Mode Dynamic Random Access Memory, FPMDRAM), an extended data output dynamic Random-Access Memory (Extended Date Out Dynamic Random Access Memory, EDODRAM), a synchronous dynamic Random-Access Memory (Synchronous Dynamic Random-Access Memory, SDRAM), or the like, as appropriate.
Example IV
According to a fourth embodiment of the present invention, based on the same inventive concept, a terminal provided by the present invention includes: a processor, a memory; the processor and the memory are communicated with each other; the memory is used for storing instructions; the processor is configured to execute the instruction in the memory, and execute the method for extracting the equivalent fuel consumption correlation feature of the hybrid electric vehicle according to the above embodiment.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above additional technical features can be freely combined and superimposed by a person skilled in the art without conflict.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. The method for extracting the equivalent oil consumption correlation characteristics of the hybrid electric vehicle is characterized by comprising the following steps of:
Acquiring original data of parameter variables of a hybrid electric vehicle, and inputting the original data of the parameter variables as data;
constructing a feature subset taking the parameter variable as an element, and initializing the element number of the feature subset;
Based on the element quantity of the feature subsets, arranging and combining the parameter variables to obtain a feature set containing a plurality of feature subsets;
Traversing the feature subsets in the feature set, calculating an evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the minimum evaluation coefficient to be a local optimal feature subset of the feature set;
And updating the element number of the feature subset, repeating the steps three to four until the element number of the feature subset is equal to the parameter variable number, and enabling the local optimal feature subset with the minimum evaluation coefficient to be a global optimal feature subset, namely enabling the parameter variable forming the global optimal feature subset to be the feature with the highest correlation of the equivalent fuel consumption of the hybrid electric vehicle.
2. The method for extracting equivalent fuel consumption correlation characteristics of a hybrid vehicle according to claim 1, wherein the parameter variables include: battery capacity, battery SOC, engine power, engine start-stop rules, average vehicle speed, maximum acceleration, acceleration time, deceleration time, constant speed time, road grade, road flatness.
3. The method for extracting equivalent fuel consumption related features of a hybrid vehicle according to claim 1, wherein the step of constructing a feature subset having the parameter variable as an element and initializing the number of elements of the feature subset specifically comprises:
Constructing a feature subset, and taking the parameter variable as an element of the feature subset;
Initializing the element number of the feature subset, enabling the element number of the feature subset to be 1, and enabling the element number of the feature subset to be increased by 1 every time of subsequent updating until updating is stopped.
4. The method for extracting equivalent fuel consumption related features of a hybrid vehicle according to claim 1, wherein the step of permutation and combination of the parameter variables based on the number of elements of the feature subsets to obtain a feature set including a plurality of the feature subsets specifically includes:
setting the element number of the feature subset as m, and setting the parameter variable number as n;
The parameter variables are arranged and combined to obtain a plurality of feature subsets, each feature subset comprises m parameter variables, the feature subsets form a feature set, and the feature set J m is marked as:
Jm＝(jm1,jm2,jm3,…,jmk)
wherein, m is more than or equal to 1 and less than or equal to n, K is the number of feature subsets when the number of elements is m, J m is the feature set when the number of elements is m, and J mk is the kth feature subset when the number of elements is m.
5. The method for extracting equivalent fuel consumption related features of a hybrid vehicle according to claim 4, wherein the step of traversing the feature subsets in the feature set, calculating an evaluation coefficient corresponding to each feature subset, and making the feature subset with the smallest evaluation coefficient be a locally optimal feature subset of the feature set specifically comprises:
traversing the feature subset within the feature set;
Calculating the mean square error and redundancy of each feature subset, which are respectively marked as MSE mk and R mk; wherein MSE mk is the mean square error of the kth feature subset when the number of elements is m, and R mk is the redundancy of the kth feature subset when the number of elements is m;
wherein, the redundancy R mk of the feature subset is:
wherein I is large mutual information among elements of the feature subset, and f x、fy is any two elements of the feature subset respectively; let x=y when m=1;
Calculating the correlation D m of the feature set:
Dm＝min(MSEmk)
wherein D m is the correlation of the feature set when the number of elements is m;
The evaluation coefficients M mk of the feature subset are:
Mmk＝Dm+Rmk
wherein M mk is an evaluation coefficient of the kth feature subset when the element number is M;
the feature subset with the smallest evaluation coefficient is a locally optimal feature subset of the feature set.
6. The utility model provides a hybrid vehicle equivalent oil consumption relativity feature extraction system which characterized in that, the system includes:
the acquisition module is used for acquiring the original data of the parameter variables of the hybrid electric vehicle and inputting the original data of the parameter variables as data;
an initialization module, configured to construct a feature subset with the parameter variable as an element, and initialize the element number of the feature subset;
the combination module is used for carrying out permutation and combination on the parameter variables based on the element quantity of the feature subsets to obtain a feature set containing a plurality of feature subsets;
The computing module is used for traversing the feature subsets in the feature set, computing the evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the smallest evaluation coefficient to be the local optimal feature subset of the feature set;
The computing module is used for updating the element quantity of the feature subset, repeatedly executing the arrangement and combination of the parameter variables based on the element quantity of the feature subset, and obtaining a feature set containing a plurality of feature subsets; traversing the feature subsets in the feature set, calculating an evaluation coefficient corresponding to each feature subset, and enabling the feature subset with the minimum evaluation coefficient to be a local optimal feature subset of the feature set; and enabling the local optimal feature subset with the smallest evaluation coefficient to be a global optimal feature subset until the element number of the feature subset is equal to the parameter variable number, namely enabling the parameter variable forming the global optimal feature subset to be the feature with highest correlation of equivalent fuel consumption of the hybrid electric vehicle.
7. The hybrid vehicle equivalent fuel consumption correlation feature extraction system of claim 6, wherein the parameter variables include: battery capacity, battery SOC, engine power, engine start-stop rules, average vehicle speed, maximum acceleration, acceleration time, deceleration time, constant speed time, road grade, road flatness.
8. The hybrid vehicle equivalent fuel consumption correlation feature extraction system of claim 6, wherein the initialization module is specifically configured to:
Constructing a feature subset, and taking the parameter variable as an element of the feature subset;
Initializing the element number of the feature subset, enabling the element number of the feature subset to be 1, and enabling the element number of the feature subset to be increased by 1 every time of subsequent updating until updating is stopped.
9. The hybrid vehicle equivalent fuel consumption correlation feature extraction system of claim 6, wherein the combining module is specifically configured to:
setting the element number of the feature subset as m, and setting the parameter variable number as n;
The parameter variables are arranged and combined to obtain a plurality of feature subsets, each feature subset comprises m parameter variables, the feature subsets form a feature set, and the feature set J m is marked as:
Jm＝(jm1,jm2,jm3,…,jmk)
wherein, m is more than or equal to 1 and less than or equal to n, K is the number of feature subsets when the number of elements is m, J m is the feature set when the number of elements is m, and J mk is the kth feature subset when the number of elements is m.
10. The hybrid vehicle equivalent fuel consumption correlation feature extraction system of claim 9, wherein the computing module is specifically configured to:
traversing the feature subset within the feature set;
Calculating the mean square error and redundancy of each feature subset, which are respectively marked as MSE mk and R mk; wherein MSE mk is the mean square error of the kth feature subset when the number of elements is m, and R mk is the redundancy of the kth feature subset when the number of elements is m;
wherein, the redundancy R mk of the feature subset is:
wherein I is large mutual information among elements of the feature subset, and f x、fy is any two elements of the feature subset respectively; let x=y when m=1;
Calculating the correlation D m of the feature set:
Dm＝min(MSEmk)
wherein D m is the correlation of the feature set when the number of elements is m;
The evaluation coefficients M mk of the feature subset are:
Mmk＝Dm+Rmk
Wherein M mk is an evaluation coefficient of the kth feature subset when the element number is M; the feature subset with the smallest evaluation coefficient is a locally optimal feature subset of the feature set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410189116.8A CN118070031A (en) | 2024-02-20 | 2024-02-20 | Method and system for extracting equivalent oil consumption correlation characteristics of hybrid electric vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410189116.8A CN118070031A (en) | 2024-02-20 | 2024-02-20 | Method and system for extracting equivalent oil consumption correlation characteristics of hybrid electric vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118070031A true CN118070031A (en) | 2024-05-24 |
Family
ID=91109257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410189116.8A Pending CN118070031A (en) | 2024-02-20 | 2024-02-20 | Method and system for extracting equivalent oil consumption correlation characteristics of hybrid electric vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118070031A (en) |
-
2024
- 2024-02-20 CN CN202410189116.8A patent/CN118070031A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190378039A1 (en) | Normalized performance comparison techniques | |
| CN101847117B (en) | Unit testing method and device | |
| CN105844061B (en) | method and device for generating gear shifting map | |
| Moawad et al. | Novel large scale simulation process to support DOT’s CAFE modeling system | |
| CN111881578B (en) | Graph database based mechanical product digital twin model layered modeling method | |
| CN112298155B (en) | Method for predicting energy consumption of hybrid power truck based on variable time domain model | |
| CN117269754B (en) | IPSM rotor demagnetizing and eccentric fault diagnosis method based on convolutional neural network operation | |
| CN112819141A (en) | Information processing system based on deep neural network | |
| CN114692956A (en) | Charging facility load prediction method and system based on multilayer optimization kernel limit learning machine | |
| CN117400785A (en) | Prediction method and device for pure electric endurance mileage, electronic equipment and vehicle | |
| CN118070031A (en) | Method and system for extracting equivalent oil consumption correlation characteristics of hybrid electric vehicle | |
| CN113074045B (en) | Engine misfire diagnosis method, engine misfire diagnosis device, engine misfire diagnosis equipment and storage medium | |
| CN101882078B (en) | Inter-module real-time synchronization method based on internal memory data framework | |
| CN109376473B (en) | Vehicle controller, vehicle and method and device for calculating driving mileage of vehicle | |
| CN115828438B (en) | Method, medium and equipment for predicting ultimate performance of automobile | |
| CN114580086B (en) | Vehicle component modeling method based on supervised machine learning | |
| CN113733919B (en) | Method for calculating remaining endurance mileage of fuel cell vehicle | |
| CN114840926B (en) | Method for generating three-dimensional finite element grid with complex tire patterns | |
| Zhang et al. | Research on Electronic Circuit Fault Diagnosis Method Based on SWT and DCNN-ELM | |
| CN112712007A (en) | Algorithm for identifying automobile exhaust remote sensing data based on DCNN-inclusion network | |
| CN111898743A (en) | CNN acceleration method and accelerator | |
| Bruck et al. | An Iterative Histogram-Based Optimization of Calibration Tables in a Powertrain Controller | |
| CN118014098B (en) | Machine learning training data scheduling method and equipment | |
| CN115434817B (en) | Engine torque control method and device, electronic equipment and storage medium | |
| CN115964661B (en) | Rotary machine fault diagnosis method and system based on domain-by-domain network |
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 |