Electric vehicle charging strategy identification method, charging duration prediction method and system

Abstract

The invention belongs to the technical field of new energy automobiles. The invention provides an electric vehicle charging strategy identification method, a charging time length prediction method and a charging time length prediction system, which can quickly identify a charging strategy from long-time-span historical data under the condition that an original charging strategy is unknown, thereby providing accurate data support for subsequent charging strategy analysis and charging time length prediction, and improving the charging strategy identification accuracy. Through multi-stage efficient charging duration prediction based on multi-source information fusion, the prediction precision of the charging duration is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicles, and in particular to a method for identifying a charging strategy for an electric vehicle, and a method and system for predicting charging time. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] In order to better plan and manage charging infrastructure, charging station operators need to accurately predict charging demand in different time periods and locations. Charging time prediction helps optimize the configuration and scheduling of charging piles and improve the utilization efficiency of charging stations. Accurate prediction of charging time can help grid operators better manage power loads, especially during peak hours, to avoid grid overload and unnecessary waste of electricity. At the same time, it can also promote the use of renewable energy and balance power supply and demand by reasonably scheduling charging time. For electric vehicle users, accurate prediction of charging time can help them better plan their trips, reduce waiting time, and improve the overall car experience. Charging time prediction can help develop more optimized charging strategies to extend battery life and reduce charging costs.

[0004] Since the electrochemical reactions inside the battery are very complex, the external environment is complex, and the operating conditions are changeable, it is very difficult to accurately predict the battery charging time. Currently, the charging time prediction methods for power batteries mainly include model methods and deep learning methods.

[0005] The prediction method based on battery model establishes physical and chemical models of the battery, simulates the behavior of the battery under different charging conditions, and predicts the charging time. It has a high theoretical basis and can explain the physical and chemical phenomena in the charging process. However, the model establishment and parameter calibration are complex, and the accuracy of the model depends on the understanding of the internal mechanism of the battery and the accuracy of the data.

[0006] Deep learning methods use deep learning models (such as LSTM, GRU, etc.) for prediction, which can handle complex nonlinear relationships, have strong generalization capabilities, and can learn potential patterns from large amounts of data. However, they require a large amount of training data, and the model training and parameter adjustment process is relatively complex, requiring high computing resources, making them difficult to apply industrially.

[0007] In addition, most existing technologies predict charging time based on the details of known charging strategies, which cannot be applied to unknown charging strategies. For example, the data set used in the present invention does not have a full charging and discharging process, and there is more than one charging strategy, and the original charging strategy (including the charging current switching point, etc.) is unknown. Summary of the invention

[0008] In order to address the deficiencies in the prior art, the present invention provides an electric vehicle charging strategy identification method, a charging time prediction method and a system, which can quickly identify the charging strategy from historical data with a long time span when the original charging strategy is unknown, thereby providing accurate data support for subsequent charging strategy analysis and charging time prediction, and greatly improving the prediction accuracy of charging time through multi-stage efficient charging time prediction based on multi-source information fusion.

[0009] In order to achieve the above object, the present invention adopts the following technical solution:

[0010] In a first aspect, the present invention provides a method for identifying a charging strategy for an electric vehicle.

[0011] A method for identifying a charging strategy for an electric vehicle includes the following steps:

[0012] Performing charging segment division according to the actual vehicle data of the electric vehicle after cleaning, and constructing a feature matrix according to the charging segment division result and the actual vehicle data of the electric vehicle after cleaning;

[0013] Extracting current features from the feature matrix and performing primary clustering of current levels;

[0014] Extracting time features from the feature matrix, counting the duration of each charging segment at different gears, and constructing a new feature matrix for representing the duration of each charging segment at different gears;

[0015] The new feature matrix is ​​subjected to secondary clustering to obtain identification results of typical charging strategies and special charging strategies.

[0016] As a further limitation of the first aspect of the present invention, the charging segment division is performed according to the actual vehicle data of the electric vehicle after cleaning, including:

[0017] The real vehicle data after data cleaning is screened, and the data with the charging status of charging or charging completed is screened. The filtered data is traversed, and for two adjacent data, it is determined whether the absolute value of the SOC difference is greater than 1 and whether the time difference is greater than five sampling intervals. If so, the two adjacent data have the same charging segment ID; otherwise, the charging segment ID is increased by 1, and the start and end SOCs of each charging segment are checked. The charging segments with the start and end SOC difference less than the set threshold are eliminated to obtain the final charging segment division result.

[0018] As a further limitation of the first aspect of the present invention, performing primary clustering of current levels includes:

[0019] Randomly select a data point from the dataset, and if the data point has been visited, select the next data point;

[0020] Calculate the number of neighbors of the selected data point within the ε radius. If the data point meets the core point condition, a new cluster is formed with the data point as the core: N ε (P)>MinPts, where ε is the maximum distance that defines the neighbors of a point within the ε radius, and MinPts is the minimum number of neighbors required for a point to become a core point;

[0021] Expand all points directly density-reachable to the core point and mark them as belonging to the same cluster; the direct density reachability is: if point q is in the ε neighborhood of point p, and point p is a core point, then point q is a directly density-reachable point of point p;

[0022] For points that cannot be expanded, they are marked as boundary points, and for points that are neither core points nor within the ε neighborhood of any core point, they are marked as noise points;

[0023] Calculate the cluster center of each cluster, Where C is the center of the cluster, n is the number of points in the cluster, and I i is the i-th current value in the cluster.

[0024] As a further limitation of the first aspect of the present invention, performing secondary clustering on the new feature matrix includes:

[0025] Randomly select K initial centroids, where the value of K is 2, to divide the typical charging strategy cluster and the special charging strategy cluster;

[0026] For each charging segment j, calculate its Euclidean distance to each centroid and assign it to the cluster corresponding to the centroid closest to it: Among them, c k is the kth centroid, c ik The value of the kth centroid in the i-th dimension;

[0027] Recompute the centroid of each cluster: Among them, C k is the set of charging fragments in the kth cluster;

[0028] Repeat the steps of assigning clusters and updating centroids until the centroids no longer change or the maximum number of iterations is reached;

[0029] Each charging segment j is assigned a cluster label k, indicating the cluster to which the charging segment j belongs.

[0030] As a further limitation of the first aspect of the present invention, the total current characteristics in the characteristic matrix are extracted, the total current characteristics are linearly fitted by the least square method, the slope characteristics and the mutation time are extracted, the data of the minimum monomer temperature is obtained according to the mutation time point and the probability distribution is calculated;

[0031] The typical charging strategy is approximately two-stage constant current charging. In the first stage, small current ramp charging and preheating are performed. When the minimum cell temperature reaches the set temperature threshold, the secondary constant current charging stage is entered until the battery is fully charged.

[0032] In a second aspect, the present invention provides an electric vehicle charging strategy identification system.

[0033] An electric vehicle charging strategy identification system, comprising:

[0034] The feature matrix construction unit is configured to: divide the charging segments according to the real vehicle data of the electric vehicle after cleaning, and construct the feature matrix according to the charging segment division result and the real vehicle data of the electric vehicle after cleaning;

[0035] The primary clustering unit is configured to: extract the current features in the feature matrix and perform primary clustering of current levels;

[0036] A new feature matrix construction unit is configured to: extract time features in the feature matrix, count the duration of each charging segment at different gears, and construct a new feature matrix for representing the duration of each charging segment at different gears;

[0037] The secondary clustering unit is configured to perform secondary clustering on the new feature matrix to obtain identification results of typical charging strategies and special charging strategies.

[0038] In a third aspect, the present invention provides a method for predicting the charging time of an electric vehicle.

[0039] A method for predicting the charging time of an electric vehicle, which predicts the charging time of a typical charging strategy identified by the method for identifying the charging strategy of an electric vehicle according to the first aspect of the present invention, comprises the following steps:

[0040] The robust least squares method is used to establish the temperature increment-temperature increment time relationship to obtain the prediction result of the charging time in the preheating stage;

[0041] The support vector regression method is used to establish the relationship between charging SOC and current value, and combined with the battery capacity, the charging time prediction result of the secondary constant current charging stage is obtained;

[0042] After the secondary constant current charging stage is completed, when the SOC reaches 99%, a small current is used for energy replenishment to obtain the energy replenishment time;

[0043] The final charging time prediction result is the sum of the charging time prediction result of the preheating stage, the charging time prediction result of the secondary constant current charging stage, and the energy replenishment time.

[0044] As part of the further limitation of the third aspect, the robust least squares method is used to establish the temperature increment-temperature increment time relationship to obtain the prediction result of the charging time in the preheating stage, including: t1 = a*ΔT+b, ΔT = T end -T0, ΔT is the temperature increment, T0 and T end are the minimum monomer temperatures at the start and end of the preheating phase, t1 is the preheating phase time, and a and b are the parameters to be fitted;

[0045] The support vector regression method is used to establish the relationship between charging SOC and current value: I0 = ω*SOC0 + b, where I0 is the starting current of the second stage, SOC0 is the starting SOC of the second stage, ω is the weight vector, and b is the bias term;

[0046] The predicted charging time of the secondary constant current charging stage is: Among them, ΔSOC is the difference between the start and end SOC; I1 is the end current, which is a constant; Q fin is the battery capacity;

[0047] Recharge time is Among them, I end is the charging current.

[0048] As part of the third aspect further defined, the battery capacity Q fin Acquisition, including:

[0049] Select the longest current stable charging segment and use the inverse ampere-hour integration method to calculate the battery capacity of the current charging segment: Where Q is the battery capacity, I(t) is the current at time t, SOC(t0) and SOC(t1) are the start and end SOC of the charging segment, and t0 and t1 are the start and end times of the charging segment;

[0050] Randomly intercept the continuous charging process from the current charging segment, intercept n times, calculate the charging segment capacity respectively, and select the average as the current charging segment capacity: Among them, Q i is the battery capacity calculated each time, Q fin is the final battery capacity;

[0051] Add Savitzky-Golay filter and use robust least squares method to fit the capacity-time curve to get: Q fin =a*Time+b, where Time is time, and a and b are parameters to be fitted.

[0052] In a fourth aspect, the present invention provides a system for predicting charging time of an electric vehicle.

[0053] A system for predicting charging duration of an electric vehicle, which predicts the duration of a typical charging strategy identified by the method for identifying charging strategies of electric vehicles according to the first aspect of the present invention, comprises:

[0054] The first prediction unit is configured to: establish a temperature increment-temperature increment time relationship using a robust least squares method to obtain a prediction result of the charging time in the preheating phase;

[0055] The second prediction unit is configured to: establish the relationship between the charging SOC and the current value by using a support vector regression method, and obtain a prediction result of the charging time in the secondary constant current charging stage in combination with the battery capacity;

[0056] The energy replenishment time acquisition unit is configured to: after the secondary constant current charging stage is completed, when the SOC reaches 99%, use a small current to replenish energy and obtain the energy replenishment time;

[0057] The comprehensive prediction unit is configured to take the sum of the charging time prediction result of the preheating stage, the charging time prediction result of the secondary constant current charging stage and the energy replenishment time as the final charging time prediction result.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] 1. The present invention innovatively proposes a method for identifying charging strategies for electric vehicles, which can quickly identify charging strategies from historical data with a long time span when the original charging strategy is unknown, thereby providing accurate data support for subsequent charging strategy analysis and charging time prediction.

[0060] 2. The present invention innovatively proposes a method for predicting the charging time of electric vehicles, which greatly improves the prediction accuracy of the charging time through multi-stage efficient charging time prediction based on multi-source information fusion.

[0061] 3. The real capacity of the vehicle battery is obscure and difficult to measure. Therefore, the present invention uses the Monte Carlo method combined with the SG filtering algorithm to achieve accurate and rapid estimation of the vehicle battery capacity.

[0062] 4. In order to solve the problem that the preheating time is difficult to obtain, the present invention constructs a preheating stage estimation model based on the robust least squares method, which greatly improves the accuracy of preheating time prediction.

[0063] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0065] Figure 1 A schematic diagram of a flow chart of a method for identifying a charging strategy for an electric vehicle provided in Embodiment 1 of the present invention;

[0066] Figure 2 A schematic diagram of a feature table provided in Example 1 of the present invention;

[0067] Figure 3 A schematic flow chart of a method for predicting charging time of an electric vehicle provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0068] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0069] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0070] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0071] Embodiment 1:

[0072] In charging devices with different power, the charging conditions are very different and there is randomness in practical applications. In the huge amount of historical charging data, the charging conditions are complex and diverse, and the original charging strategy and its various jump conditions are unknown. In view of this, this implementation proposes an electric vehicle charging strategy identification method, which includes the following process:

[0073] S1: Obtaining a real vehicle data set. The real vehicle data set of this implementation method includes data such as time, charging state, total voltage, total current, SOC, and minimum cell temperature.

[0074] S2: Data cleaning. The real vehicle data set has the following characteristics: large data scale, with the number of samples reaching millions of rows; high data feature dimensions and large amount of information; many data anomalies and missing key information. Based on this, the present invention reorders the temporally chaotic data, uses Gaussian filtering to smooth and reduce noise, removes outliers, and uses linear interpolation to fill in the missing data.

[0075] S3: Charging segment division. Since the details of the charging strategy are unknown, only the historical charging and discharging curves are available. The actual operating conditions are complex, the charging and discharging data are mixed together, the charging segments are unlabeled and the number is unknown. In order to analyze the charging strategy, the data must be divided into charging segments first, including:

[0076] The actual vehicle data is filtered, and the data with a charging status of 1 (charging) or 4 (charging completed) is filtered. The filtered data is traversed, and for two adjacent data, the absolute value of their SOC difference is determined to be greater than 1 and the time difference is greater than five sampling intervals. If the above conditions are not met, the two data points are regarded as the same charging segment and have the same charging segment ID; otherwise, the charging segment ID is increased by 1; after labeling all data points (charging segment ID), the start and end SOC of each charging segment are checked, and the charging segments with a start and end SOC difference less than 20% (i.e., the set threshold) are eliminated because their information is too little to reflect the characteristics of the charging strategy.

[0077] S4: Charging strategy identification. The present invention proposes a multi-level clustering-probability distribution collaborative charging strategy identification method based on machine learning. The calculation process is as follows: Figure 1 shown.

[0078] Construct the feature matrix: Take it as input, the feature matrix is ​​as follows:

[0079] X=[Time,U,I,SOC,T,ID] (1);

[0080] Among them, X represents the feature matrix, Time represents time, U represents the total voltage, I represents the total current, SOC represents the battery state of charge, T represents the minimum cell temperature of the battery pack, and ID represents the charging segment ID.

[0081] Current level clustering: Extract current features and use the DBSCAN algorithm to perform current level clustering. As an unsupervised clustering algorithm, the DBSCAN algorithm does not need to predetermine the number and center of clusters. The specific process is as follows:

[0082] a. Select a point to check. Randomly select a point from the data set. If the point has been visited, select the next point.

[0083] b. Determine whether it is a core point. Calculate the number of neighbors of the point within the ε radius. If the point meets the core point conditions, a new cluster is formed with the point as the core. The formula is as follows:

[0084] N ε (P)>MinPts (2);

[0085] Among them, ε is the maximum distance that defines the neighbors of a point within the ε radius, and MinPts is the minimum number of neighbors (including the point itself) required for a point to become a core point.

[0086] c. Expand the cluster. Expand all points directly reachable by the core point and mark them as belonging to the same cluster. The definition of direct density reachability is: if point q is in the ε neighborhood of point p, and point p is a core point, then point q is a direct density reachable point of point p.

[0087] d. Processing boundary points and noise points. For points that cannot be expanded (i.e., not core points but within the ε neighborhood of a core point), mark them as boundary points; for points that are neither core points nor within the ε neighborhood of any core point, mark them as noise points.

[0088] e. Calculate the cluster center of each cluster. The calculation formula is as follows:

[0089]

[0090] Where C is the center of the cluster, n is the number of points in the cluster, and I i is the i-th current value in the cluster.

[0091] f. Output the clustering results. Label each data point with a current level and output the central current value of each current level cluster.

[0092] Generate feature matrix: According to the feature Time, count the duration of each charging segment in different gears to form a feature table, such as Figure 2 For example, in the charging segment with ID 1, the first gear current lasts for 1909 seconds, the second gear current lasts for 11412 seconds, and there is no current at other gears.

[0093] Construct a new feature matrix D to represent the duration of each charging segment in different gears:

[0094]

[0095] Where i represents the total number of gears, j represents the total number of charging segment IDs, t represents the duration, and t d Indicates the duration of all gears in a charging segment.

[0096] Secondary clustering of charging segments: K-means clustering is performed on the feature matrix D. This algorithm can artificially determine the number of clusters to divide typical and special charging strategies. The specific process is as follows:

[0097] A. Randomly select K initial centroids, where the value of K is 2;

[0098] B. For each charging segment j, calculate its Euclidean distance to each centroid and assign it to the cluster corresponding to the nearest centroid, as follows:

[0099]

[0100] Among them, c k is the kth centroid, c ik The value of the kth centroid in the i-th dimension;

[0101] C. Recalculate the centroid of each cluster using the following formula:

[0102]

[0103] Among them, C k is the set of charged fragments in the kth cluster.

[0104] D. Repeat the steps of assigning clusters and updating centroids until the centroids no longer change or the maximum number of iterations is reached.

[0105] E. Result output,Each charging segment j will be assigned a cluster label k, indicating the cluster to which it belongs.

[0106] Key point identification: extract current data, perform least squares linear fitting on it, extract slope characteristics and mutation time, obtain data on minimum monomer temperature T based on the mutation time point and calculate the probability distribution.

[0107] Finally, the data set is divided into typical charging strategies and special charging strategies. It can be determined that the typical charging strategy is approximately two-stage constant current charging. In the first stage, the small current ramp charging and preheating are carried out. When the minimum cell temperature reaches 15 degrees Celsius (set temperature threshold), the secondary constant current charging stage is entered until the battery is fully charged. The subsequent Example 3 predicts the charging duration based on this charging strategy. The number of charging segments using the special charging strategy is small, the charging current fluctuates greatly, and it does not have general characteristics, so it is not specially modeled for duration prediction.

[0108] Embodiment 2:

[0109] This implementation provides an electric vehicle charging strategy identification system, including:

[0110] The feature matrix construction unit is configured to: divide the charging segments according to the real vehicle data of the electric vehicle after cleaning, and construct the feature matrix according to the charging segment division result and the real vehicle data of the electric vehicle after cleaning;

[0111] The primary clustering unit is configured to: extract the current features in the feature matrix and perform primary clustering of current levels;

[0112] A new feature matrix construction unit is configured to: extract time features in the feature matrix, count the duration of each charging segment at different gears, and construct a new feature matrix for representing the duration of each charging segment at different gears;

[0113] The secondary clustering unit is configured to perform secondary clustering on the new feature matrix to obtain identification results of typical charging strategies and special charging strategies.

[0114] It is understandable that the above-mentioned units can be separately or completely combined into one or several other units, or one (some) of the units can be further divided into multiple functionally smaller units, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the function of one unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the electric vehicle charging strategy identification system may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0115] According to another embodiment of the present application, the system described in this embodiment can be constructed, and the electric vehicle charging strategy identification method of the embodiment of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 1 on a general computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0116] Embodiment 3:

[0117] like Figure 3 As shown, this implementation provides a method for predicting the charging time of an electric vehicle, which includes the following processes for the typical charging strategy identified in Example 1:

[0118] The training set and the test set are divided into a ratio of 9:1, and then a charging time prediction model is constructed. The specific process is as follows:

[0119] Capacity estimation: To reduce the marginal error, select the longest current stable charging segment and use the inverse ampere-hour integration method to calculate the battery capacity of the current charging segment:

[0120]

[0121] Where Q is the battery capacity, I(t) is the current at time t, SOC(t0) and SOC(t1) are the start and end SOC of the charging segment, and t0 and t1 are the start and end times of the charging segment.

[0122] In order to reduce the error, combined with the Monte Carlo idea, the continuous charging process is randomly intercepted from the current charging segment, intercepted 5 times, the charging segment capacity is calculated respectively, and the mean is selected as the current charging segment capacity:

[0123]

[0124] Among them, Q i is the battery capacity calculated each time, Q fin is the final battery capacity, where n is 5.

[0125] Add Savitzky-Golay filter, use robust least squares method to fit the capacity-time curve, and finally get the aging correction coefficient:

[0126] Q fin =a*Time+b (9);

[0127] Where Time is the time, a and b are the parameters to be fitted.

[0128] Prediction of charging time in the preheating phase: In cold climates, electric vehicles need to be preheated before charging. Considering the computational complexity and the linear relationship between temperature increment and preheating time, the robust least squares method is used to establish the temperature increment-temperature increment time relationship:

[0129] ΔT=T end -T0 (10);

[0130] t1=a*ΔT+b (11);

[0131] Where ΔT is the temperature increment, T0 and T end are the minimum temperatures of the monomers at the start and end of the preheating phase, t1 is the preheating phase time, and a and b are the parameters to be fitted.

[0132] Prediction of charging time in the second stage: It can be seen that the starting charging current in the second stage and the starting SOC in the second stage show a linear relationship. The support vector regression method (SVR) is used to establish the relationship between the charging SOC and the current value:

[0133] I0=ω*SOC0+b (12);

[0134] Among them, I0 is the starting current of the second stage, SOC0 is the starting SOC of the second stage, ω is the weight vector, and b is the bias term.

[0135] To train the SVR model, the following loss function needs to be minimized:

[0136]

[0137] Among them, C is the regularization function, ε is the tolerance parameter, n is the number of charging segments participating in the training, and i is the charging segment ID.

[0138] Since the charging time needs to be calculated in real time, the charging current needs to be simplified to obtain the average charging current of the charging process. Only the initial current and the final current are taken as the average for simplification. The second stage duration prediction formula is:

[0139]

[0140] Among them, ΔSOC is the difference between the start and end SOC, and I1 is the end current, which is a constant.

[0141] Prediction of charging time in the energy replenishment stage: After the second stage of charging, when the SOC reaches 99%, a small current is still needed for energy replenishment. The charging time of this process is t3:

[0142]

[0143] Among them, I end is the charging current.

[0144] Final charging duration prediction: Add the predicted results of the preheating phase charging duration, the second phase charging duration, and the charging duration of the energy replenishment phase to get the final complete charging duration:

[0145] t total =t1+t2+t3 (16);

[0146] Among them, t total This is the complete charging time prediction result.

[0147] Embodiment 4:

[0148] This implementation provides an electric vehicle charging time prediction system, which predicts the charging time of a typical charging strategy identified by the electric vehicle charging strategy identification method described in Example 1 of the present invention, including:

[0149] The first prediction unit is configured to: establish a temperature increment-temperature increment time relationship using a robust least squares method to obtain a prediction result of the charging time in the preheating phase;

[0150] The second prediction unit is configured to: establish the relationship between the charging SOC and the current value by using a support vector regression method, and obtain a prediction result of the charging time in the secondary constant current charging stage in combination with the battery capacity;

[0151] The energy replenishment time acquisition unit is configured to: after the secondary constant current charging stage is completed, when the SOC reaches 99%, use a small current to replenish energy and obtain the energy replenishment time;

[0152] The comprehensive prediction unit is configured to take the sum of the charging time prediction result of the preheating stage, the charging time prediction result of the secondary constant current charging stage and the energy replenishment time as the final charging time prediction result.

[0153] It is understandable that the above-mentioned units can be separately or completely combined into one or several other units to constitute, or one (some) of the units can be further divided into multiple functionally smaller units to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the functions of one unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the electric vehicle charging time prediction system may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0154] According to another embodiment of the present application, the system described in this embodiment can be constructed, and the method for predicting the charging time of an electric vehicle of an embodiment of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 3 on a general computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium, and run therein.

[0155] Embodiment 5:

[0156] This implementation provides an electronic device, which includes a processor, a communication interface, and a computer-readable storage medium, wherein the processor, the communication interface, and the computer-readable storage medium may be connected via a bus or other means.

[0157] Among them, the communication interface is used to receive and send data, the computer-readable storage medium can be stored in the memory of the electronic device, the computer-readable storage medium is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer-readable storage medium.

[0158] A processor (or CPU (Central Processing Unit)) is the computing core and control core of an electronic device, which is suitable for implementing one or more instructions, and specifically suitable for loading and executing one or more instructions to implement corresponding method flows or corresponding functions.

[0159] The processor is configured to execute the process of embodiment 1 or embodiment 3.

[0160] Embodiment 6:

[0161] This implementation provides a computer-readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the electronic device and, of course, extended storage media supported by the electronic device. The computer-readable storage medium provides a storage space that stores the processing system of the electronic device.

[0162] In addition, the storage space also stores one or more instructions suitable for being loaded and executed by the processor, and these instructions may be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk storage; optionally, it may also be at least one computer-readable storage medium located away from the aforementioned processor.

[0163] In one embodiment, one or more instructions are stored in the computer-readable storage medium; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the process of Example 1 or Example 3.

[0164] Embodiment 7:

[0165] This implementation provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the process of Embodiment 1 or Embodiment 3.

[0166] A person skilled in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0167] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instruction can be stored in a computer-readable storage medium or transmitted by a computer-readable storage medium. The computer instruction can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (for example, coaxial cable, optical fiber, digital line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server, a data center, etc. that contains one or more available media integration. Available media can be magnetic media (for example, floppy disk, hard disk, tape), optical media (for example, DVD), or semiconductor media (for example, solid-state drive (Solid State Disk, SSD)) and the like.

[0168] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying a charging strategy for an electric vehicle, characterized in that: The process includes: Performing charging segment division according to the actual vehicle data of the electric vehicle after cleaning, and constructing a feature matrix according to the charging segment division result and the actual vehicle data of the electric vehicle after cleaning; Extracting current features from the feature matrix and performing primary clustering of current levels; Extracting time features from the feature matrix, counting the duration of each charging segment at different gears, and constructing a new feature matrix for representing the duration of each charging segment at different gears; The new feature matrix is ​​subjected to secondary clustering to obtain identification results of typical charging strategies and special charging strategies.

2. The electric vehicle charging strategy identification method according to claim 1, characterized in that: The charging segments are divided according to the actual vehicle data of the cleaned electric vehicle, including: The real vehicle data after data cleaning is screened, and the data with the charging status of charging or charging completed is screened. The filtered data is traversed, and for two adjacent data, it is determined whether the absolute value of the SOC difference is greater than 1 and whether the time difference is greater than five sampling intervals. If so, the two adjacent data have the same charging segment ID; otherwise, the charging segment ID is increased by 1, and the start and end SOCs of each charging segment are checked. The charging segments with the start and end SOC difference less than the set threshold are eliminated to obtain the final charging segment division result.

3. The electric vehicle charging strategy identification method according to claim 1 or 2, characterized in that: Perform the first-level clustering of current levels, including: Randomly select a data point from the dataset, and if the data point has been visited, select the next data point; Calculate the number of neighbors of the selected data point within the ε radius. If the data point meets the core point condition, a new cluster is formed with the data point as the core: N ε (P)>MinPts, where ε is the maximum distance that defines the neighbors of a point within the ε radius, and MinPts is the minimum number of neighbors required for a point to become a core point; Expand all points directly density-reachable to the core point and mark them as belonging to the same cluster; the direct density reachability is: if point q is in the ε neighborhood of point p, and point p is a core point, then point q is a directly density-reachable point of point p; For points that cannot be expanded, they are marked as boundary points, and for points that are neither core points nor within the ε neighborhood of any core point, they are marked as noise points; Calculate the cluster center of each cluster, Where C is the center of the cluster, n is the number of points in the cluster, and I i is the i-th current value in the cluster.

4. The electric vehicle charging strategy identification method according to claim 1 or 2, characterized in that: Performing secondary clustering on the new feature matrix includes: Randomly select K initial centroids, where the value of K is 2, to divide the typical charging strategy cluster and the special charging strategy cluster; For each charging segment j, calculate its Euclidean distance to each centroid and assign it to the cluster corresponding to the centroid closest to it: Among them, c k is the kth centroid, c ik The value of the kth centroid in the i-th dimension; Recompute the centroid of each cluster: Among them, C k is the set of charging fragments in the kth cluster; Repeat the steps of assigning clusters and updating centroids until the centroids no longer change or the maximum number of iterations is reached; Each charging segment j is assigned a cluster label k, indicating the cluster to which the charging segment j belongs.

5. The electric vehicle charging strategy identification method according to claim 4, characterized in that: Extracting the total current characteristics in the characteristic matrix, performing least squares linear fitting on the total current characteristics, extracting the slope characteristics and the mutation time, obtaining the data of the minimum monomer temperature according to the mutation time point and calculating the probability distribution; The typical charging strategy is approximately two-stage constant current charging. In the first stage, small current ramp charging and preheating are performed. When the minimum cell temperature reaches the set temperature threshold, the secondary constant current charging stage is entered until the battery is fully charged.

6. An electric vehicle charging strategy identification system, characterized in that: include: The feature matrix construction unit is configured to: divide the charging segments according to the real vehicle data of the electric vehicle after cleaning, and construct the feature matrix according to the charging segment division result and the real vehicle data of the electric vehicle after cleaning; The primary clustering unit is configured to: extract the current features in the feature matrix and perform primary clustering of current levels; A new feature matrix construction unit is configured to: extract time features in the feature matrix, count the duration of each charging segment at different gears, and construct a new feature matrix for representing the duration of each charging segment at different gears; The secondary clustering unit is configured to perform secondary clustering on the new feature matrix to obtain identification results of typical charging strategies and special charging strategies.

7. A method for predicting charging time of an electric vehicle, characterized in that: The duration prediction of the typical charging strategy identified by the electric vehicle charging strategy identification method according to any one of claims 1 to 5 includes the following process: The robust least squares method is used to establish the temperature increment-temperature increment time relationship to obtain the prediction result of the charging time in the preheating stage; The support vector regression method is used to establish the relationship between charging SOC and current value, and combined with the battery capacity, the charging time prediction result of the secondary constant current charging stage is obtained; After the secondary constant current charging stage is completed, when the SOC reaches 99%, a small current is used for energy replenishment to obtain the energy replenishment time; The final charging time prediction result is the sum of the charging time prediction result of the preheating stage, the charging time prediction result of the secondary constant current charging stage, and the energy replenishment time.

8. The method for predicting the charging time of an electric vehicle according to claim 7, characterized in that: The robust least squares method is used to establish the temperature increment-temperature increment time relationship, and the charging time prediction results in the preheating stage are obtained, including: t1 = a*ΔT + b, ΔT = T end -T0, ΔT is the temperature increment, T0 and T end are the minimum temperatures of the monomers at the start and end of the preheating phase, t1 is the preheating phase time, and a and b are the parameters to be fitted; The support vector regression method is used to establish the relationship between charging SOC and current value: I0 = ω*SOC0 + b, where I0 is the starting current of the second stage, SOC0 is the starting SOC of the second stage, ω is the weight vector, and b is the bias term; The predicted charging time of the secondary constant current charging stage is: Among them, ΔSOC is the difference between the start and end SOC; I1 is the end current, which is a constant; Q fin is the battery capacity; Recharge time is Among them, I end is the charging current.

9. The method for predicting charging time of an electric vehicle according to claim 8, characterized in that: The battery capacity Q fin Acquisition, including: Select the longest current stable charging segment and use the inverse ampere-hour integration method to calculate the battery capacity of the current charging segment: Where Q is the battery capacity, I(t) is the current at time t, SOC(t0) and SOC(t1) are the start and end SOC of the charging segment, and t0 and t1 are the start and end times of the charging segment; Randomly intercept the continuous charging process from the current charging segment, intercept n times, calculate the charging segment capacity respectively, and select the average as the current charging segment capacity: Among them, Q i is the battery capacity calculated each time, Q fin is the final battery capacity; Add Savitzky-Golay filter and use robust least squares method to fit the capacity-time curve to get: Q fin =a*Time+b, where Time is time, and a and b are parameters to be fitted.

10. An electric vehicle charging time prediction system, characterized in that: The method for identifying a charging strategy for an electric vehicle according to any one of claims 1 to 5 predicts the duration of the typical charging strategy identified, comprising: The first prediction unit is configured to: establish a temperature increment-temperature increment time relationship using a robust least squares method to obtain a prediction result of the charging time in the preheating phase; The second prediction unit is configured to: establish the relationship between the charging SOC and the current value by using a support vector regression method, and obtain a prediction result of the charging time in the secondary constant current charging stage in combination with the battery capacity; The energy replenishment time acquisition unit is configured to: after the secondary constant current charging stage is completed, when the SOC reaches 99%, use a small current to replenish energy and obtain the energy replenishment time; The comprehensive prediction unit is configured to take the sum of the charging time prediction result of the preheating stage, the charging time prediction result of the secondary constant current charging stage and the energy replenishment time as the final charging time prediction result.

Images