CN112810499A - Secondary processing algorithm and system for remaining mileage of new energy automobile - Google Patents
Secondary processing algorithm and system for remaining mileage of new energy automobile Download PDFInfo
- Publication number
- CN112810499A CN112810499A CN202110171165.5A CN202110171165A CN112810499A CN 112810499 A CN112810499 A CN 112810499A CN 202110171165 A CN202110171165 A CN 202110171165A CN 112810499 A CN112810499 A CN 112810499A
- Authority
- CN
- China
- Prior art keywords
- data
- new energy
- battery
- energy automobile
- firefly
- 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.)
- Withdrawn
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
- B60L58/12—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries responding to state of charge [SoC]
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2240/00—Control parameters of input or output; Target parameters
- B60L2240/40—Drive Train control parameters
- B60L2240/54—Drive Train control parameters related to batteries
-
- 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
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to the technical field of data processing, and discloses a secondary processing algorithm for the remaining mileage of a new energy automobile, which comprises the following steps: acquiring battery information data of a new energy automobile in a running process, and performing data preprocessing on the battery information data to obtain preprocessed battery information data; according to the preprocessed battery information data, estimating the battery state of the new energy automobile by using a battery state of charge estimation method based on battery characteristics; predicting the driving range of the new energy automobile by using a driving range estimation model of the new energy automobile; and (4) carrying out site selection on the new energy automobile charging station by using an improved firefly algorithm. The invention also provides a secondary processing system for the remaining mileage of the new energy automobile. The invention realizes the processing of the automobile data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a secondary processing algorithm and a secondary processing system for the remaining mileage of a new energy automobile.
Background
With the development of the storage battery technology and the reduction of the manufacturing cost of the new energy automobile, the new energy automobile industry develops rapidly, and how to predict the remaining mileage of the new energy automobile according to the battery state of the new energy automobile after the new energy automobile runs for a period of time becomes a hot topic of current research.
The battery charge state and the vehicle driving range are two important parameters in a battery management system, and have important significance for guiding the driving of a new energy automobile. However, due to the fact that driving conditions are complex and changeable, the charge state data of the new energy automobile battery and the unit mileage energy consumption are greatly different, and therefore the accuracy of the charge state estimation and the accuracy of the driving mileage prediction of the new energy automobile power battery are seriously affected.
In view of this, how to more accurately estimate the state of charge of the battery and predict the driving range of the new energy vehicle based on the state of charge of the battery is a problem to be solved by those skilled in the art.
Disclosure of Invention
The invention provides a secondary processing algorithm for the remaining mileage of a new energy automobile, which is characterized in that the battery state of the new energy automobile is estimated by using a battery charge state estimation method based on battery characteristics, and the driving range of the new energy automobile is predicted according to a driving range estimation model of the new energy automobile; and meanwhile, according to the battery state of the new energy automobile, the site selection of the new energy automobile charging station is carried out by utilizing an improved firefly algorithm.
In order to achieve the above object, the present invention provides a secondary processing algorithm for remaining mileage of a new energy vehicle, including:
acquiring battery information data of a new energy automobile in a running process, and performing data preprocessing on the battery information data to obtain preprocessed battery information data;
according to the preprocessed battery information data, estimating the battery state of the new energy automobile by using a battery state of charge estimation method based on battery characteristics;
predicting the driving range of the new energy automobile by using a driving range estimation model of the new energy automobile;
and (4) carrying out site selection on the new energy automobile charging station by using an improved firefly algorithm.
Optionally, the performing data preprocessing on the battery information data includes:
the battery information data is a binary file, each time node in the binary file corresponds to a battery information data packet, and in a specific embodiment of the invention, the battery information data packet comprises total voltage, total current, battery temperature and battery state of charge data of a new energy automobile battery;
the preprocessing process of the battery information data comprises the following steps:
1) starting to search downwards from the first piece of battery charge state data in the battery information data until a data item with the battery charge state of 100% and a positive current value is found, and marking the data item as an initial position in the battery discharging process;
2) searching downwards from the initial position of battery discharge until finding a data item with a negative current value, and marking the data item as the position of battery discharge end if the current values of the last three data items of the data item are all negative;
3) setting a time interval range [8,35] needing interpolation processing, discretizing the time range, segmenting according to the time interval of battery information data, marking data points needing interpolation, and if the occurrence time interval is more than 35s, determining that the battery in the time period is in a standing state; interpolating missing values in the battery information data by using a linear nearest interpolation method;
4) the battery information data in the initial position to the end position in the battery discharge process is subjected to deletion processing of an abnormal value including abnormal battery information data in which the total voltage is 0, the total current is not 0, and the like when the battery state of charge is not displayed as 0.
Optionally, the estimating the battery state of the new energy vehicle by using the battery state of charge estimation method based on the battery characteristics includes:
1) dividing the battery information data into N data subsets Sk(x1，x2…), for each data item x in the data subsetiFind k points in its vicinity, and center the k points as data item xiIs nearest neighbor calculation point x'i(ii) a The data item xiThe data contained in the data list is the total voltage, the total current, the battery temperature and the battery charge state data of the battery at the corresponding moment;
2) calculating a data item xiAnd nearest neighbor calculation point x'iDistance L betweeni：
Li＝||xi-x′i||
Computing a subset of data SkData center GkAnd SkDistance D between data items inki：
Dki＝||Gk-xki||
Wherein:
xkirepresenting a subset S of datakThe ith data item in (1);
3) for each data subset SkCalculating the de-sampling radius Rk：
vki＝1/Dki
Wherein:
vkirepresenting a radius update weight;
Mkirepresenting a data item xkiDistance to its nearest neighbor;
updating each data subset SkExtracted in its data center GkNearby RkAll data within the range, while data outside the range is no longer placed in the training data set;
4) for each data subset SkEstablishing SVM models, wherein each data subset is concentrated in data distribution, and each SVM model only needs good local fitting capacity, so that a Gaussian kernel function is selected as a kernel function of the model; meanwhile, because data among data subsets are obviously different, in order to ensure that each SVM model has good estimation performance on corresponding partial data, parameter setting and training are required to be performed on each SVM model one by one. Selecting model parameters by using grid search and cross validation, and selecting the optimal parameters for modeling and storing;
5) and integrating each SVM model by adopting a dynamic weight method:
wt＝1/||Gt-x||α
wherein:
h (x) is the integrated output of the N SVM models;
wtis at the tThe weight of the SVM model;
ht(x) Is the output of the tth SVM model;
x is input battery information data;
Gtfor the t-th data subset StThe data center of (1);
α is an output weight coefficient, which is set to 0.4;
wherein SVM sub-models closer to the battery information data center will get higher weights.
Optionally, the process of predicting the driving range of the new energy vehicle by using the driving range estimation model of the new energy vehicle is as follows:
1) taking the temperature of the battery pack and the charge state data of the battery as input, selecting 1000 battery information data at the past moment for modeling, and constructing an SVR model;
2) estimating delta C of one kilometer in the future by utilizing an SVR model, wherein C represents the charge state data of the battery, and delta C represents the variation of the charge state data of the battery;
3) on the basis, subtracting the delta C from the residual battery charge state data C of the new energy battery to obtain residual battery charge state data C, and estimating the delta C of the next kilometer again;
and repeating the loop, and gradually and iteratively calculating the delta C of one kilometer and the residual battery state of charge data C until the residual battery state of charge data C is equal to 0, wherein the loop is ended, and the loop frequency is the residual driving range R of the new energy automobile.
Optionally, the target function of the new energy vehicle charging station site selection is as follows:
C1i＝ei(CFe+CCu)×Tv×p0+mi(CL+CD)×Tv×p0
wherein:
C1iindicates the ith newThe station electric energy loss cost of the energy vehicle charging station;
C2irepresenting the average power consumption cost of a user to and from a new energy vehicle charging station;
CFe，CCurepresenting iron and copper losses generated by the transformer;
eithe number of transformers required by the ith new energy vehicle charging station is represented;
Tvcharging time of a new energy automobile charging station in one day;
p0representing the unit price of electricity purchased from the new energy vehicle charging station to the power grid;
mithe unit price of the transformer required by the ith new energy vehicle charging station is represented;
CLrepresenting that the line loss in the new energy automobile charging station is converted into the loss of a charger;
CDand the loss of the charger is shown.
Optionally, the process of using the improved firefly algorithm to perform location selection of the new energy vehicle charging station includes:
1) initializing each parameter, randomly assigning the initial position of the firefly i, and determining a solution initial value in an optimization model search space;
2) the total constraint violation value for the firefly i state variable is calculated according to the following equation:
wherein:
g represents the total number of control variables in the objective function;
gj(i) representing a constraint associated with a jth state variable;
if S (i) is less than S (j), the firefly i is superior to the firefly j, and all the fireflies are subjected to dominant ranking;
3) if the rank of firefly i is higher than firefly j, then the ith firefly will attract the jth firefly, and at time k + 1, the position of the jth firefly will be updated as follows:
wherein:
β0represents the maximum attraction value between fireflies;
gamma represents a light absorption coefficient, and is related to the distance between fireflies, and the farther the distance is, the larger the light absorption coefficient is, and the value thereof is between 0.01 and 10;
rijrepresents the distance between the ith and jth fireflies:
rij＝||si-sj||
α is a step-size factor, if rij≥αmaxThen take the step factor as alphamaxIf r isij＜αmaxAnd then:
wherein:
αmaxrepresents the maximum step factor when the firefly moves;
t represents the current iteration number;
Dmaxrepresents the maximum number of iterations, which is set to 100;
4) moving all the fireflies according to the steps 2) to 3), and calculating objective function values according to the positions of all the fireflies after moving;
5) judging whether the algorithm meets a convergence condition, if so, outputting a result, and if not, continuing to perform iterative computation until the algorithm converges; and the location where the fireflies gather is the site selection location of the rapid charging station.
In addition, in order to achieve the above object, the present invention further provides a system for secondary processing of remaining mileage of a new energy vehicle, the system comprising:
the battery state acquisition device is used for acquiring battery information data of the new energy automobile in the running process and carrying out data preprocessing on the battery information data;
the battery data processor is used for estimating the battery state of the new energy automobile by using a battery state of charge estimation method based on battery characteristics;
the new energy automobile remaining range processing device is used for predicting the new energy automobile driving range by using a new energy automobile driving range estimation model and selecting the site of a new energy automobile charging station by using an improved firefly algorithm.
In addition, in order to achieve the above object, the present invention further provides a computer readable storage medium, where the computer readable storage medium stores new energy vehicle remaining range processing program instructions, where the new energy vehicle remaining range processing program instructions are executable by one or more processors to implement the steps of the implementation method for secondary processing of the remaining range of a new energy vehicle as described above.
Compared with the prior art, the invention provides a secondary processing algorithm for the remaining mileage of the new energy automobile, which has the following advantages:
firstly, due to the complexity and changeability of the driving road conditions, the current and voltage data of the battery of the electric automobile can show different changes, so that the data-driven intelligent algorithm has certain limitation in estimating the battery conforming state. In the traditional algorithm, when the new energy automobile running data under multiple working conditions are modeled, the learning burden of a learning machine is increased by the training data with wide distribution range and large difference, and finally the accuracy of the model obtained by training is not high. Aiming at the phenomenon, an ME-SVM model algorithm is provided, and the core idea of the algorithm is to divide similar data into parts by utilizing feature clusteringTo the same training data subset by computing data item xiAnd nearest neighbor calculation point x'jDistance L betweeni：
Li＝||xi-x′i||
Computing a subset of data SkData center GkAnd SkDistance D between data items inki：
Dki＝||Gk-xki||
Wherein: x is the number ofkiRepresenting a subset S of datakThe ith data item in (1); for each data subset SkCalculating the de-sampling radius Rk：
vki＝1/Dki
Wherein: v. ofkiRepresenting a radius update weight; mkiRepresenting a data item xkiDistance to its nearest neighbor; by updating each subset S of datakExtracted in its data center GkNearby RkAll data within the range, while data outside this range are no longer placed in the training data set, so that the learning burden on the sub-learning machine (SVM model) of each is reduced, S for each data subsetkThe SVM model is established, and because the data distribution of each data subset is concentrated, each SVM model only needs good local fitting capacity, so that the Gaussian kernel function is selected as the kernel function of the model for fitting, and the estimation effect of local data is optimal; secondly, based on an integrated learning thought, during output, dynamically determining the output weight of each SVM model according to the similarity of the data to be tested and each training data subset, namely, integrating each SVM model by adopting a dynamic weight method, wherein the SVM submodel closer to a battery information data center obtains higher weight:
wt＝1/||Gt-x||α
wherein: h (x) is the integrated output of the N SVM models; w is atThe weight of the tth SVM model; h ist(x) Is the output of the tth SVM model; x is input battery information data; gtFor the t-th data subset StThe data center of (1); α is an output weight coefficient, which is set to 0.4; by integrating and outputting the estimation results of a plurality of SVM models, the generalization capability of the models is ensured.
Meanwhile, for the traditional firefly algorithm, the firefly with high brightness can perform position updating according to a set single-target optimization iteration formula, the diversity of the population is kept, the characteristics of the new energy automobile can be rapidly charged as required at different distribution positions in the space, and the process of going to a certain new energy charging station for charging is similar. In the actual optimization problem solution, a plurality of targets often exist, and different targets are not mutually independent, so that the traditional firefly algorithm is improved, and the constraint violation total value of the firefly i state variable is calculated according to the following formula:
wherein: g represents the total number of control variables in the objective function; gj(i) Representing a constraint associated with a jth state variable; if S (i) < S (j), the firefly i is superior to the firefly j, and the fireflies are subjected to dominance sequencing, compared with the traditional algorithm, the algorithm provided by the invention sequences the fireflies by the influence of the fireflies on variables in the objective function, the fireflies with higher promotion effect or lower inhibition effect on the objective function have higher sequencing, if the sequencing of the firefly i is higher than that of the firefly j, the ith firefly attracts the jth firefly, and at the moment of k +1, the position of the jth firefly is updated according to the following formula:
wherein:
represents the position of firefly j at time k; beta is a0Represents the maximum attraction value between fireflies;
a randomly generated number representing the time k + 1; gamma represents a light absorption coefficient, and is related to the distance between fireflies, and the farther the distance is, the larger the light absorption coefficient is, and the value thereof is between 0.01 and 10; r isijRepresents the distance between the ith and jth fireflies:
rij＝||si-sj||
α is a step-size factor, if rij≥αmaxThen take the step factor as alphamaxIf r isij＜αmaxAnd then:
wherein: alpha is alphamaxRepresents the maximum step factor when the firefly moves; t represents the current iteration number; dmaxRepresents the maximum number of iterations, which is set to 100; the step size factors are limited, so that the step size factors at the early stage are not small, algorithm convergence is accelerated, the situation that the population falls into a local optimal solution is avoided, the step size factors at the later stage are limited, the problems that the step size factors are large and oscillation occurs, and the optimal solution is difficult to maintain are solved, a target function value is calculated according to all the positions of the fireflies after movement, whether the algorithm meets the convergence condition or not is judged, if yes, the result is output, and if not, iterative calculation is continued until convergence; and the location where the fireflies gather is the site selection location of the rapid charging station.
Drawings
Fig. 1 is a schematic flow chart of a secondary processing algorithm for the remaining mileage of a new energy vehicle according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a secondary processing system for remaining mileage of a new energy vehicle according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Estimating the battery state of the new energy automobile by using a battery state-of-charge estimation method based on battery characteristics, and predicting the driving range of the new energy automobile according to a driving range estimation model of the new energy automobile; and meanwhile, according to the battery state of the new energy automobile, the site selection of the new energy automobile charging station is carried out by utilizing an improved firefly algorithm. Referring to fig. 1, a schematic diagram of a secondary processing algorithm for the remaining mileage of the new energy vehicle according to an embodiment of the present invention is shown.
In this embodiment, the secondary processing algorithm for the remaining mileage of the new energy vehicle includes:
and S1, acquiring battery information data of the new energy automobile in the running process, and performing data preprocessing on the battery information data to obtain preprocessed battery information data.
Firstly, acquiring battery information data of a new energy automobile in a running process, wherein the battery information data are binary files, and each time node in the binary files corresponds to a battery information data packet;
further, the invention carries out preprocessing operation on the battery information data, and the preprocessing process of the battery information data comprises the following steps:
1) starting to search downwards from the first piece of battery charge state data in the battery information data until a data item with the battery charge state of 100% and a positive current value is found, and marking the data item as an initial position in the battery discharging process;
2) searching downwards from the initial position of battery discharge until finding a data item with a negative current value, and marking the data item as the position of battery discharge end if the current values of the last three data items of the data item are all negative;
3) setting a time interval range [8,35] needing interpolation processing, discretizing the time range, segmenting according to the time interval of battery information data, marking data points needing interpolation, and if the occurrence time interval is more than 35s, determining that the battery in the time period is in a standing state; interpolating missing values in the battery information data by using a linear nearest interpolation method;
4) the battery information data in the initial position to the end position in the battery discharge process is subjected to deletion processing of an abnormal value including abnormal battery information data in which the total voltage is 0, the total current is not 0, and the like when the battery state of charge is not displayed as 0.
And S2, according to the preprocessed battery information data, estimating the battery state of the new energy automobile by using a battery state of charge estimation method based on battery characteristics.
Further, according to the preprocessed battery information data, the battery state of charge of the new energy automobile is estimated by using a battery state of charge estimation method based on battery characteristics, and the battery state of charge estimation method based on battery characteristics comprises the following steps:
1) dividing the battery information data into N data subsets Sk(x1，x2…), for each data item x in the data subsetiFind k points in its vicinity, and center the k points as data item xiIs nearest neighbor calculation point x'i(ii) a The data item xiThe data contained in the data list is the total voltage, the total current, the battery temperature and the battery charge state data of the battery at the corresponding moment;
2) calculating a data item xiAnd nearest neighbor calculation point x'iDistance L betweeni：
Li＝||xi-x′i||
Computing a subset of data SkData center GkAnd SkDistance D between data items inki：
Dki＝||Gk-xki||
Wherein:
xkirepresenting a subset S of datakThe ith data item in (1);
3) for each data subset SkCalculating the de-sampling radius Rk：
vki＝1/Dki
Wherein:
vkirepresenting a radius update weight;
Mkirepresenting a data item xkiDistance to its nearest neighbor;
updating each data subset SkExtracted in its data center GkNearby RkAll data within the range, while data outside the range is no longer placed in the training data set;
4) for each data subset SkEstablishing SVM models, wherein each data subset is concentrated in data distribution, and each SVM model only needs good local fitting capacity, so that a Gaussian kernel function is selected as a kernel function of the model; meanwhile, because data among data subsets are obviously different, in order to ensure that each SVM model has good estimation performance on corresponding partial data, parameter setting and training are required to be performed on each SVM model one by one. Selecting model parameters by using grid search and cross validation, and selecting the optimal parameters for modeling and storing;
5) and integrating each SVM model by adopting a dynamic weight method:
wt＝1/||Gt-x||α
wherein:
h (x) is the integrated output of the N SVM models;
wtthe weight of the tth SVM model;
ht(x) Is the output of the tth SVM model;
x is input battery information data;
Gtfor the t-th data subset StThe data center of (1);
α is an output weight coefficient, which is set to 0.4;
wherein SVM sub-models closer to the battery information data center will get higher weights.
And S3, predicting the driving range of the new energy automobile by using the driving range estimation model of the new energy automobile.
Furthermore, the method utilizes a new energy automobile driving range estimation model to predict the driving range of the new energy automobile, and the new energy automobile driving range estimation model comprises the following estimation processes:
1) taking the temperature of the battery pack and the charge state data of the battery as input, selecting 1000 battery information data at the past moment for modeling, and constructing an SVR model;
2) estimating delta C of one kilometer in the future by utilizing an SVR model, wherein C represents the charge state data of the battery, and delta C represents the variation of the charge state data of the battery;
3) on the basis, subtracting the delta C from the residual battery charge state data C of the new energy battery to obtain residual battery charge state data C, and estimating the delta C of the next kilometer again;
and repeating the loop, and gradually and iteratively calculating the delta C of one kilometer and the residual battery state of charge data C until the residual battery state of charge data C is equal to 0, wherein the loop is ended, and the loop frequency is the residual driving range R of the new energy automobile.
And S4, the site selection of the new energy automobile charging station is carried out by utilizing the improved firefly algorithm.
Further, the site selection of the new energy automobile charging station is carried out by utilizing an improved firefly algorithm, and the target function of the site selection of the new energy automobile charging station is as follows:
C1i＝ei(CFe+CCu)×Tv×p0+mi(CL+CD)×Tv×p0
wherein:
C1irepresenting the station electric energy loss cost of the ith new energy vehicle charging station;
C2irepresenting the average power consumption cost of a user to and from a new energy vehicle charging station;
CFe，CCurepresenting iron and copper losses generated by the transformer;
eithe number of transformers required by the ith new energy vehicle charging station is represented;
Tvcharging time of a new energy automobile charging station in one day;
p0representing the unit price of electricity purchased from the new energy vehicle charging station to the power grid;
mithe unit price of the transformer required by the ith new energy vehicle charging station is represented;
CLrepresenting that the line loss in the new energy automobile charging station is converted into the loss of a charger;
CDand the loss of the charger is shown.
The improved firefly algorithm flow is as follows:
1) initializing each parameter, randomly assigning the initial position of the firefly i, and determining a solution initial value in an optimization model search space;
2) the total constraint violation value for the firefly i state variable is calculated according to the following equation:
wherein:
g represents the total number of control variables in the objective function;
gj(i) representing a constraint associated with a jth state variable;
if S (i) is less than S (j), the firefly i is superior to the firefly j, and all the fireflies are subjected to dominant ranking;
3) if the rank of firefly i is higher than firefly j, then the ith firefly will attract the jth firefly, and at time k + 1, the position of the jth firefly will be updated as follows:
wherein:
β0represents the maximum attraction value between fireflies;
gamma represents a light absorption coefficient, and is related to the distance between fireflies, and the farther the distance is, the larger the light absorption coefficient is, and the value thereof is between 0.01 and 10;
rijrepresents the distance between the ith and jth fireflies:
rij＝||si-sj||
α is a step-size factor, if rij≥αmaxThen take the step factor as alphamaxIf r isij＜αmaxAnd then:
wherein:
αmaxrepresents the maximum step factor when the firefly moves;
t represents the current iteration number;
Dmaxrepresents the maximum number of iterations, which is set to 100;
4) moving all the fireflies according to the steps 2) to 3), and calculating objective function values according to the positions of all the fireflies after moving;
5) judging whether the algorithm meets a convergence condition, if so, outputting a result, and if not, continuing to perform iterative computation until the algorithm converges; and the location where the fireflies gather is the site selection location of the rapid charging station.
The following describes embodiments of the present invention through an algorithmic experiment and tests of the inventive treatment method. The hardware test environment of the algorithm of the invention is as follows: inter (R) core (TM) i7-6700K CPU with software Matlab2018 a; the comparison method is a Bayes-based secondary processing algorithm and a random forest-based secondary processing algorithm.
In the algorithm experiment, the data set is 10G of new energy automobile running data. In the experiment, the driving data of the new energy automobile is input into the algorithm model, and the accuracy of the driving journey prediction is used as an evaluation index of the feasibility of the method.
According to the experimental result, the prediction accuracy of the driving range of the Bayes secondary processing algorithm is 86.31%, the prediction accuracy of the driving range of the random forest-based secondary processing algorithm is 88.32%, the prediction accuracy of the driving range of the method is 90.22%, and compared with a comparison algorithm, the secondary processing algorithm of the remaining range of the new energy automobile provided by the invention has higher prediction accuracy of the driving range of the new energy automobile.
The invention further provides a secondary processing system for the remaining mileage of the new energy automobile. Referring to fig. 2, an internal structural diagram of a secondary processing system for remaining mileage of a new energy vehicle according to an embodiment of the present invention is shown.
In the present embodiment, the secondary processing system 1 for the remaining mileage of the new energy vehicle at least includes a battery state acquiring device 11, a battery data processor 12, a new energy vehicle remaining mileage processing device 13, a communication bus 14, and a network interface 15.
The battery state acquiring device 11 may be a PC (Personal Computer), a terminal device such as a smart phone, a tablet Computer, and a mobile Computer, or may be a server.
The battery data processor 12 includes at least one type of readable storage medium including flash memory, hard disks, multi-media cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, and the like. The battery data processor 12 may be an internal storage unit of the secondary processing system 1 for the remaining mileage of the new energy vehicle in some embodiments, for example, a hard disk of the secondary processing system 1 for the remaining mileage of the new energy vehicle. The battery data processor 12 may also be an external storage device of the secondary processing system 1 for the remaining mileage of the new energy vehicle in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the secondary processing system 1 for the remaining mileage of the new energy vehicle. Further, the battery data processor 12 may also include both an internal storage unit and an external storage device of the secondary processing system 1 for the remaining mileage of the new energy vehicle. The battery data processor 12 may be used not only to store application software installed in the intelligent road traffic tracking management system 1 and various kinds of data, but also to temporarily store data that has been output or will be output.
The remaining mileage Processing device 13 of the new energy vehicle may be, in some embodiments, a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data Processing chip, and is configured to run program codes stored in the battery data processor 12 or process data, such as remaining mileage Processing program instructions of the new energy vehicle.
The communication bus 14 is used to enable connection communication between these components.
The network interface 15 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication link between the system 1 and other electronic devices.
Optionally, the system 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display may also be referred to as a display screen or a display unit, where appropriate, for displaying information processed in the secondary processing system 1 for the remaining mileage of the new energy vehicle and for displaying a visual user interface.
Fig. 2 shows only the secondary processing system 1 having the components 11 to 15 and the remaining range of the new energy vehicle, and it will be understood by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the secondary processing system 1 for the remaining range of the new energy vehicle, and may include fewer or more components than those shown, or combine some components, or a different arrangement of components.
In the embodiment of the device 1 shown in fig. 2, the battery data processor 12 stores therein program instructions for processing the remaining mileage of the new energy vehicle; the step of executing the program command of the remaining mileage of the new energy vehicle stored in the battery data processor 12 by the remaining mileage processing device 13 of the new energy vehicle is the same as the implementation method of the secondary processing algorithm of the remaining mileage of the new energy vehicle, and is not described here.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium has stored thereon new energy vehicle remaining mileage processing program instructions, where the new energy vehicle remaining mileage processing program instructions are executable by one or more processors to implement the following operations:
acquiring battery information data of a new energy automobile in a running process, and performing data preprocessing on the battery information data to obtain preprocessed battery information data;
according to the preprocessed battery information data, estimating the battery state of the new energy automobile by using a battery state of charge estimation method based on battery characteristics;
predicting the driving range of the new energy automobile by using a driving range estimation model of the new energy automobile;
and (4) carrying out site selection on the new energy automobile charging station by using an improved firefly algorithm.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. The secondary processing algorithm of the remaining mileage of the new energy automobile is characterized by comprising the following steps:
acquiring battery information data of a new energy automobile in a running process, and performing data preprocessing on the battery information data to obtain preprocessed battery information data;
according to the preprocessed battery information data, estimating the battery state of the new energy automobile by using a battery state of charge estimation method based on battery characteristics;
predicting the driving range of the new energy automobile by using a driving range estimation model of the new energy automobile;
and (4) carrying out site selection on the new energy automobile charging station by using an improved firefly algorithm.
2. The secondary processing algorithm for the remaining mileage of a new energy vehicle as claimed in claim 1, wherein the data preprocessing of the battery information data comprises:
1) starting to search downwards from the first piece of battery charge state data in the battery information data until a data item with the battery charge state of 100% and a positive current value is found, and marking the data item as an initial position in the battery discharging process;
2) searching downwards from the initial position of battery discharge until finding a data item with a negative current value, and marking the data item as the position of battery discharge end if the current values of the last three data items of the data item are all negative;
3) setting a time interval range [8,35] needing interpolation processing, discretizing the time range, segmenting according to the time interval of battery information data, marking data points needing interpolation, and if the occurrence time interval is more than 35s, determining that the battery in the time period is in a standing state; interpolating missing values in the battery information data by using a linear nearest interpolation method;
4) the battery information data in the initial position to the end position in the battery discharge process is subjected to deletion processing of an abnormal value including abnormal battery information data in which the total voltage is 0, the total current is not 0, and the like when the battery state of charge is not displayed as 0.
3. The secondary processing algorithm for the remaining mileage of a new energy automobile according to claim 2, wherein the estimating the battery state of the new energy automobile by using the battery state of charge estimation method based on the battery characteristics comprises:
1) dividing the battery information data into N data subsets Sk(x1，x2,..), for each data item x in the data subsetiFind k points in its vicinity, and center the k points as data item xiIs nearest neighbor calculation point x'i(ii) a The data item xiThe data contained in the data list is the total voltage, the total current, the battery temperature and the battery charge state data of the battery at the corresponding moment;
2) calculating a data item xiAnd nearest neighbor calculation point x'iDistance L betweeni：
Li＝||xi-x′i||
Computing a subset of data SkData center GkAnd SkDistance D between data items inki：
Dki＝||Gk-xki||
Wherein:
xkirepresenting a subset S of datakThe ith data item in (1);
3) for each data subset SkCalculating the de-sampling radius Rk：
vki＝1/Dki
Wherein:
vkirepresenting a radius update weight;
Mkirepresenting a data item xkiDistance to its nearest neighbor;
updating each data subset SkExtracted in its data center GkNearby RkAll data within the range, while data outside the range is no longer placed in the training data set;
4) selecting a Gaussian kernel function as a kernel function of the SVM model; selecting model parameters by using grid search and cross validation, and selecting the optimal parameters for modeling and storing;
5) and integrating each SVM model by adopting a dynamic weight method:
wt＝1/||Gt-x||α
wherein:
h (x) is the integrated output of the N SVM models;
wtthe weight of the tth SVM model;
ht(x) Is the output of the tth SVM model;
x is input battery information data;
Gtfor the t-th data subset StThe data center of (1);
α is an output weight coefficient, which is set to 0.4;
wherein SVM sub-models closer to the battery information data center will get higher weights.
4. The secondary processing algorithm for the remaining range of the new energy automobile according to claim 3, wherein the process of predicting the driving range of the new energy automobile by using the driving range estimation model of the new energy automobile comprises the following steps:
1) taking the temperature of the battery pack and the charge state data of the battery as input, selecting 1000 battery information data at the past moment for modeling, and constructing an SVR model;
2) estimating delta C of one kilometer in the future by utilizing an SVR model, wherein C represents the charge state data of the battery, and delta C represents the variation of the charge state data of the battery;
3) on the basis, subtracting the delta C from the residual battery charge state data C of the new energy battery to obtain residual battery charge state data C, and estimating the delta C of the next kilometer again;
and repeating the loop, and gradually and iteratively calculating the delta C of one kilometer and the residual battery state of charge data C until the residual battery state of charge data C is equal to 0, wherein the loop is ended, and the loop frequency is the residual driving range R of the new energy automobile.
5. The secondary processing algorithm for the remaining mileage of the new energy vehicle as claimed in claim 4, wherein the objective function of the new energy vehicle charging station site selection is as follows:
C1i＝ei(CFe+CCu)×Tv×p0+mi(CL+CD)×Tv×p0
wherein:
C1irepresenting the station electric energy loss cost of the ith new energy vehicle charging station;
C2irepresenting the average power consumption cost of a user to and from a new energy vehicle charging station;
CFe，CCurepresenting iron and copper losses generated by the transformer;
eithe number of transformers required by the ith new energy vehicle charging station is represented;
Tvcharging time of a new energy automobile charging station in one day;
p0representing the unit price of electricity purchased from the new energy vehicle charging station to the power grid;
mithe unit price of the transformer required by the ith new energy vehicle charging station is represented;
CLrepresenting that the line loss in the new energy automobile charging station is converted into the loss of a charger;
CDand the loss of the charger is shown.
6. The secondary processing algorithm for the remaining mileage of the new energy vehicle as claimed in claim 5, wherein the process of using the improved firefly algorithm to address the new energy vehicle charging station comprises:
1) initializing each parameter, randomly assigning the initial position of the firefly i, and determining a solution initial value in an optimization model search space;
2) the total constraint violation value for the firefly i state variable is calculated according to the following equation:
wherein:
g represents the total number of control variables in the objective function;
gj(i) representing a constraint associated with a jth state variable;
if S (i) is less than S (j), the firefly i is superior to the firefly j, and all the fireflies are subjected to dominant ranking;
3) if the rank of firefly i is higher than firefly j, then the ith firefly will attract the jth firefly, and at time k +1, the position of the jth firefly will be updated as follows:
wherein:
β0represents the maximum attraction value between fireflies;
gamma represents a light absorption coefficient, and is related to the distance between fireflies, and the farther the distance is, the larger the light absorption coefficient is, and the value thereof is between 0.01 and 10;
rijrepresents the distance between the ith and jth fireflies:
rij＝||si-sj||
α is a step-size factor, if rij≥αmaxThen take the step factor as alphamaxIf r isij＜αmaxAnd then:
wherein:
αmaxrepresents the maximum step factor when the firefly moves;
t represents the current iteration number;
Dmaxrepresents the maximum number of iterations, which is set to 100;
4) moving all the fireflies according to the steps 2) to 3), and calculating objective function values according to the positions of all the fireflies after moving;
5) judging whether the algorithm meets a convergence condition, if so, outputting a result, and if not, continuing to perform iterative computation until the algorithm converges; and the location where the fireflies gather is the site selection location of the rapid charging station.
7. A secondary processing system for the remaining mileage of a new energy automobile is characterized by comprising:
the battery state acquisition device is used for acquiring battery information data of the new energy automobile in the running process and carrying out data preprocessing on the battery information data;
the battery data processor is used for estimating the battery state of the new energy automobile by using a battery state of charge estimation method based on battery characteristics;
the new energy automobile remaining range processing device is used for predicting the new energy automobile driving range by using a new energy automobile driving range estimation model and selecting the site of a new energy automobile charging station by using an improved firefly algorithm.
8. A computer-readable storage medium, wherein the computer-readable storage medium stores thereon new energy vehicle remaining range processing program instructions, which are executable by one or more processors to implement the steps of the implementation method for secondary processing of the remaining range of a new energy vehicle according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110171165.5A CN112810499A (en) | 2021-02-08 | 2021-02-08 | Secondary processing algorithm and system for remaining mileage of new energy automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110171165.5A CN112810499A (en) | 2021-02-08 | 2021-02-08 | Secondary processing algorithm and system for remaining mileage of new energy automobile |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112810499A true CN112810499A (en) | 2021-05-18 |
Family
ID=75863969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110171165.5A Withdrawn CN112810499A (en) | 2021-02-08 | 2021-02-08 | Secondary processing algorithm and system for remaining mileage of new energy automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112810499A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114655074A (en) * | 2021-11-16 | 2022-06-24 | 吉林大学 | Electric automobile actual driving energy consumption estimation method based on Bayesian regression |
-
2021
- 2021-02-08 CN CN202110171165.5A patent/CN112810499A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114655074A (en) * | 2021-11-16 | 2022-06-24 | 吉林大学 | Electric automobile actual driving energy consumption estimation method based on Bayesian regression |
| CN114655074B (en) * | 2021-11-16 | 2024-01-30 | 吉林大学 | Electric vehicle actual running energy consumption estimation method based on Bayesian regression |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3446260B1 (en) | Memory-efficient backpropagation through time | |
| CN113589189B (en) | Lithium battery health condition prediction method and device based on charging and discharging data characteristics | |
| CN110020175B (en) | Search processing method, processing equipment and system | |
| US20220129794A1 (en) | Generation of counterfactual explanations using artificial intelligence and machine learning techniques | |
| CN107870810B (en) | Application cleaning method and device, storage medium and electronic equipment | |
| CN110070382B (en) | Method and device for generating information | |
| Wu et al. | A hybrid-forecasting model reducing Gaussian noise based on the Gaussian support vector regression machine and chaotic particle swarm optimization | |
| WO2022141840A1 (en) | Network architecture search method and apparatus, electronic device, and medium | |
| US20210150368A1 (en) | Systems providing a learning controller utilizing indexed memory and methods thereto | |
| JP2023083276A (en) | Method and device for training information adjustment model of charging station, and product | |
| CN112810499A (en) | Secondary processing algorithm and system for remaining mileage of new energy automobile | |
| Abdulraheem et al. | Hyper-parameter tuning for support vector machine using an improved cat swarm optimization algorithm | |
| CN112561569B (en) | Dual-model-based store arrival prediction method, system, electronic equipment and storage medium | |
| CN117554814A (en) | Battery state of charge prediction method and device, electronic equipment and storage medium | |
| CN104731788A (en) | Processing method and equipment for promote information | |
| CN111489196A (en) | Prediction method and device based on deep learning network, electronic equipment and medium | |
| CN116562427A (en) | Charging load prediction method and device of charging station, storage medium and equipment | |
| CN115099163A (en) | Charge state determining method and device, electronic equipment and storage medium | |
| CN112734005B (en) | Method and device for determining prediction model, electronic equipment and storage medium | |
| CN112308595B (en) | Method and device for determining the state of goods | |
| CN113495213A (en) | Electric quantity prediction model construction method, electric quantity prediction model carrying equipment deployment method and electric quantity prediction model carrying equipment deployment device | |
| CN116542498B (en) | Battery scheduling method, system, device and medium based on deep reinforcement learning | |
| CN115932602A (en) | Battery power estimation method and system based on machine learning | |
| KR102718912B1 (en) | Apparatus and method for updating meta learning model | |
| CN111414944B (en) | Electronic equipment control method and electronic equipment |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210518 |