Charging method and system of intelligent charging pile

Abstract

The invention relates to the technical field of charging piles, and discloses a charging method and system of an intelligent charging pile, and the method comprises the steps: obtaining an identification code of a to-be-charged vehicle, carrying out the traversal in a vehicle database, determining the service life of a battery of the to-be-charged vehicle according to a traversal result, and when the identification code does not exist in the vehicle database, carrying out the charging of the to-be-charged vehicle. And determining the battery life of the to-be-charged vehicle according to the battery damage model, verifying the charging type, and when the charging type is judged to be incorrect, re-acquiring the charging type of the to-be-charged vehicle by using a clustering algorithm, determining a target charging type, acquiring all historical charging behaviors corresponding to the target charging type, and calculating the battery life of the to-be-charged vehicle according to the historical charging behaviors. And analyzing all historical charging behaviors, determining a charging adjustment index of the charging power based on an analysis result, and charging the to-be-charged vehicle according to the adjusted charging power. According to the invention, the adaptability to charging of vehicles of different brands and models and rechargeable batteries is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of charging piles, and in particular, to a charging method and system for an intelligent charging pile. Background Art

[0002] With the enhancement of global environmental awareness and the increasingly strict restrictions on the emissions of traditional fuel vehicles, the ownership of new energy vehicles has shown an explosive growth in recent years. Higher requirements are put forward for the charging of new energy vehicles. For new energy vehicles of different brands and models, there are differences in electrical parameters such as the rated voltage and current required for charging. At present, on the one hand, the current intelligent charging piles lack adaptability when charging according to different brands and models of charging vehicles. On the other hand, due to the situation of the service life attenuation of the charging batteries of new energy vehicles, the charging piles cannot adaptively charge according to the usage conditions of the charging batteries, resulting in accelerated aging of the batteries, thereby shortening the service life of the batteries, and ultimately may cause failures in the vehicle charging system.

[0003] Therefore, it is necessary to design a charging method and system for an intelligent charging pile to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes a charging method and system for an intelligent charging pile, aiming to solve the problems of lack of adaptability when charging according to different brands and models of charging vehicles, and that the charging pile cannot adaptively charge according to the usage conditions of the charging battery, resulting in accelerated aging of the battery, thereby shortening the service life of the battery, and ultimately may cause failures in the vehicle charging system.

[0005] On the one hand, the present invention proposes a charging method for an intelligent charging pile, including:

[0006] Obtain the identification code of the vehicle to be charged and traverse it in the vehicle database, determine the battery life of the vehicle to be charged according to the traversal result. When the identification code does not exist in the vehicle database, determine the battery life of the vehicle to be charged according to the battery damage model;

[0007] Based on the battery life, determine the charging type of the vehicle to be charged, verify the charging type, and judge whether the charging type is correct based on the historical charging data set of the same charging type. When it is determined that the charging type is incorrect, use the clustering algorithm to re-obtain the charging type of the vehicle to be charged and determine the target charging type;

[0008] Determine the charging power according to the target charging type, obtain all historical charging behaviors corresponding to the target charging type, and analyze all historical charging behaviors. Based on the analysis result, determine the charging adjustment index of the charging power;

[0009] Adjust the charging power based on the charging adjustment index, and charge the vehicle to be charged according to the adjusted charging power.

[0010] Further, when obtaining the identification code of the vehicle to be charged and traversing in the vehicle database, and determining the battery life of the vehicle to be charged according to the traversal result, it includes:

[0011] When the identification code exists in the vehicle database, determine the battery life of the vehicle to be charged according to the vehicle database;

[0012] When the identification code does not exist in the vehicle database, determine the battery life of the vehicle to be charged according to the battery damage model.

[0013] Further, when determining the battery life of the vehicle to be charged according to the battery damage model, it includes:

[0014] Obtain the battery data set of the vehicle to be charged, and split the battery data set into a model training set and a model validation set;

[0015] Pre-select a neural network model, perform iterative training on the neural network model according to the model training set, and evaluate the iteratively trained neural network model according to the model validation set;

[0016] If the triplet loss of the neural network model after the current iterative training is greater than or equal to the triplet loss of the neural network model after the previous iterative training, use cosine annealing to adjust the learning rate, and continue the iterative training until the triplet loss is less than the triplet loss of the neural network model after the previous iterative training;

[0017] If the triplet loss of the neural network model after the current iterative training is less than the triplet loss of the neural network model after the previous iterative training, stop the iterative training, and determine the current iteratively trained neural network model as the battery damage model;

[0018] Determine the battery life of the vehicle to be charged according to the identification code and the battery damage model.

[0019] Further, when determining the charging type of the vehicle to be charged based on the battery life, it includes:

[0020] Compare the battery life with a preset first preset battery life and a second preset battery life respectively, the first preset battery life is greater than the second preset battery life, and determine the charging type of the vehicle to be charged according to the comparison result;

[0021] When the battery life is greater than or equal to the first preset battery life, determine that the charging type of the vehicle to be charged is the fast charging mode;

[0022] When the battery life is less than the first preset battery life and greater than the second preset battery life, determine that the charging type of the vehicle to be charged is the normal mode;

[0023] When the battery life is less than or equal to the second preset battery life, determine that the charging type of the vehicle to be charged is the slow charging mode.

[0024] Further, when determining whether the charging type is correct based on the historical charging data set of the same charging type, it includes:

[0025] Obtain historical charging characteristics according to the historical charging data set, and the historical charging characteristics include historical battery parameters and historical battery life;

[0026] Determine the charging similarity based on the historical battery parameters and historical battery life;

[0027] Compare the charging similarity with the charging similarity threshold, and determine whether the charging type is correct according to the comparison result;

[0028] When the charging similarity is greater than or equal to the charging similarity threshold, determine that the charging type is correct, and determine the charging type as the target charging type;

[0029] When the charging similarity is less than the charging similarity threshold, determine that the charging type is incorrect.

[0030] Further, when it is determined that the charging type is incorrect, use the clustering algorithm to re-obtain the charging type of the vehicle to be charged. When determining the target charging type, it includes:

[0031] Obtain the representative data of each charging type according to the historical charging data set, and combine the representative data with the battery life and identification code of the vehicle to be charged to establish a clustering data set, and extract the feature vectors of each data in the clustering data set;

[0032] Determine that the expected number of clusters k is 3, initialize the parameters of the Gaussian distribution, calculate the probability that each data in the clustering data set belongs to each Gaussian distribution, obtain the responsibility value, select the cluster with the largest responsibility value as the charging type of the battery life again, and determine this charging type as the target charging type.

[0033] Further, when obtaining all historical charging behaviors corresponding to the target charging type, parsing all historical charging behaviors, and determining the charging adjustment index of the charging power based on the parsing result, it includes:

[0034] Analyze all historical charging behaviors to determine power overflow behaviors, normal power behaviors, and power shortage behaviors;

[0035] Construct a first power set with all the powers corresponding to all power overflow behaviors;

[0036] Construct a second power set with all the powers corresponding to all normal power behaviors;

[0037] Construct a third power set with all the powers corresponding to all power shortage behaviors;

[0038] Determine the charging adjustment index of the charging power according to the first power set, the second power set, and the third power set.

[0039] Further, when determining the charging adjustment index of the charging power according to the first power set, the second power set, and the third power set, it includes:

[0040] Obtain the first average value in the first power set, extract a data in the second power set as the standard value, and obtain the third average value in the third power set;

[0041] Obtain the first difference between the first average value and the standard value, obtain the third difference between the standard value and the third average value, and determine the difference ratio n between the first difference and the third difference;

[0042] Preset a first preset charging adjustment index, a second preset charging adjustment index, and a third preset charging adjustment index, where the first preset charging adjustment index is greater than the second preset charging adjustment index, and the second preset charging adjustment index is greater than the third preset charging adjustment index;

[0043] When n ≤ 1, use the first preset charging adjustment index as the charging adjustment index of the charging power;

[0044] When 1 < n ≤ 1.5, use the second preset charging adjustment index as the charging adjustment index of the charging power;

[0045] When 1.5 < n, use the third preset charging adjustment index as the charging adjustment index of the charging power.

[0046] Further, when adjusting the charging power based on the charging adjustment index, it includes:

[0047] The charging power and the charging adjustment index are positively correlated.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows: By obtaining the identification code of the vehicle to be charged and traversing the vehicle database or using the battery damage model to determine the battery life, and based on this, determining the charging type, the adaptability of the intelligent charging pile to charge according to different vehicle brands, models and charging batteries is improved, the aging acceleration of the charging battery caused by inappropriate charging methods is avoided, the service life of the charging battery is extended, thereby reducing the risk of vehicle charging failures. The historical charging data set is used to judge its correctness, and when it is incorrect, the clustering algorithm is used to re-obtain it to ensure the accuracy of the target charging type, so that the charging power output by the intelligent charging pile fits the needs of the vehicle battery, which not only ensures the safety of the charging process, but also prevents safety hazards such as overcharging and overheating caused by improper charging parameters. After determining the charging power according to the target charging type, the charging adjustment index is determined by analyzing the corresponding historical charging behavior, and the charging power is adjusted accordingly, which improves the charging adaptability and flexibility of the intelligent charging pile.

[0049] On the other hand, the present application also provides a charging system for an intelligent charging pile, which is used to apply the above-mentioned charging system for an intelligent charging pile, and includes:

[0050] A data acquisition module, configured to obtain the identification code of the vehicle to be charged and traverse the vehicle database, determine the battery life of the vehicle to be charged according to the traversal result, and when the identification code does not exist in the vehicle database, determine the battery life of the vehicle to be charged according to the battery damage model;

[0051] A charging judgment module, configured to determine the charging type of the vehicle to be charged based on the battery life, verify the charging type, judge whether the charging type is correct based on the historical charging data set of the same charging type, and when it is determined that the charging type is incorrect, use the clustering algorithm to re-obtain the charging type of the vehicle to be charged and determine the target charging type;

[0052] A charging processing module, configured to determine the charging power according to the target charging type, obtain all historical charging behaviors corresponding to the target charging type, and analyze all historical charging behaviors, and determine the charging adjustment index of the target charging type based on the analysis result;

[0053] A charging adjustment module, configured to adjust the charging power based on the charging adjustment index and charge the vehicle to be charged according to the adjusted charging power.

[0054] It can be understood that the above-mentioned charging method and system for an intelligent charging pile have the same beneficial effects, which will not be elaborated here. Description of the Drawings

[0055] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Also, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0056] Figure 1 is a flowchart of a charging method for an intelligent charging pile provided by an embodiment of the present invention;

[0057] Figure 2 is a functional block diagram of a charging system for an intelligent charging pile provided by an embodiment of the present invention. Detailed Embodiments

[0058] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0059] In some embodiments of the present application, referring to Figure 1 as shown, a charging method for an intelligent charging pile includes:

[0060] S100: Obtain the identification code of the vehicle to be charged and traverse it in the vehicle database, determine the battery life of the vehicle to be charged according to the traversal result, and when the identification code does not exist in the vehicle database, determine the battery life of the vehicle to be charged according to the battery damage model;

[0061] S200: Determine the charging type of the vehicle to be charged based on the battery life, verify the charging type, and judge whether the charging type is correct based on the historical charging data set of the same charging type. When it is determined that the charging type is incorrect, use the clustering algorithm to re-obtain the charging type of the vehicle to be charged and determine the target charging type;

[0062] S300: Determine the charging power according to the target charging type, obtain all historical charging behaviors corresponding to the target charging type, and analyze all historical charging behaviors, and determine the charging adjustment index of the charging power based on the analysis result;

[0063] S400: Adjust the charging power based on the charging adjustment index, and charge the vehicle to be charged according to the adjusted charging power.

[0064] Specifically, the identification code (VIN code) is a set of codes that uniquely identifies the vehicle to be charged. The identification code is determined by new energy vehicle manufacturers. The vehicle database is established based on a big data model, which includes information such as the production manufacturers, specific models, production dates, battery types, and battery descriptions of various vehicles. By traversing the identification code in the vehicle database, if a matching record exists, the battery life can be directly determined based on the current usage of the vehicle to be charged. For example, the battery manufacturer mentions in the user manual that the expected service life of this rechargeable battery is 5 years. After leaving the factory, at the node of each annual production date, the battery capacity is expected to decay by 10%-15%. If there is no relevant record in the vehicle database, it may be due to missing data records, the vehicle to be charged being a new model / small niche brand, or the battery information not being entered into the vehicle database in a timely manner. At this time, the battery damage model is used to infer the battery life, laying the foundation for formulating subsequent charging strategies. Based on the battery life, the charging type of the vehicle to be charged is determined and verified. By analyzing the historical charging data set of the same charging type, the historical charging data set represents a charging data set of the vehicle type of the same vehicle to be charged. By comparing with the historical charging data set, it is judged whether the charging type is correct. If it is determined to be incorrect, the clustering algorithm is used to re-analyze to obtain the accurate charging type, thereby determining the target charging type, ensuring the reliability and adaptability of the target charging type, and then being able to formulate a charging plan according to the actual situation of the charging battery. The charging power is determined according to the target charging type. The charging power is determined by the charging pile for the target charging type. For example, in the fast charging mode, the charging power can reach 50-150kW. By collecting and analyzing all historical charging behaviors corresponding to the target charging type, these data are parsed to determine the charging adjustment index of the charging power. The charging adjustment index comprehensively considers various factors in the past charging process and can reflect the charging adjustment strategy for this charging power. The charging power is adjusted based on the charging adjustment index, and the charging pile charges the vehicle to be charged according to the adjusted charging power. It realizes the adaptive charging of intelligent charging piles for different vehicles.

[0065] It can be understood that the battery life of the vehicle to be charged is determined through the identification code and the battery damage model, and then the charging type is matched, ensuring the adaptability of intelligent charging piles to new energy vehicles of different brands and models. Moreover, the charging type is verified according to the historical charging data set, ensuring the reliability and stability of the target charging type, being able to maximize the service life of the charging battery while ensuring the charging efficiency. Secondly, the charging strategy is continuously optimized in a data-driven manner. With the accumulation of data and the optimization of algorithms, the adaptability of intelligent charging piles is continuously improved, thereby reducing the occurrence probability of vehicle charging system failures.

[0066] In some embodiments of the present application, when obtaining the identification code of the vehicle to be charged and traversing the vehicle database to determine the battery life of the vehicle to be charged according to the traversal result, it includes: when the identification code exists in the vehicle database, determining the battery life of the vehicle to be charged according to the vehicle database; when the identification code does not exist in the vehicle database, determining the battery life of the vehicle to be charged according to the battery damage model.

[0067] Specifically, in the process of determining the battery life of the vehicle to be charged, when the identification code of the vehicle to be charged exists in the vehicle database, data can be directly called according to the vehicle database to accurately obtain key information such as the usage duration and health status of the battery. Based on these data, the battery life can be determined, providing strong support for the formulation of subsequent charging plans. When there is no corresponding identification code in the vehicle database, the battery damage model analyzes the characteristic parameters of the charging battery to predict the battery life, effectively avoiding the blind area caused by the lack of data, ensuring that the battery life of each vehicle to be charged can be obtained effectively, enhancing the universality of the intelligent charging pile in charging management of the vehicle to be charged, and laying a foundation for optimizing the charging strategy, ensuring battery safety, and extending the battery service life.

[0068] In some embodiments of the present application, when determining the battery life of the vehicle to be charged according to the battery damage model, it includes: obtaining the battery data set of the vehicle to be charged, splitting the battery data set into a model training set and a model verification set, pre-selecting a neural network model, iteratively training the neural network model according to the model training set, and evaluating the iteratively trained neural network model according to the model verification set. If the triplet loss of the currently iteratively trained neural network model is greater than or equal to the triplet loss of the neural network model after the previous iteration training, use cosine annealing to adjust the learning rate and continue the iterative training until the triplet loss is less than the triplet loss of the neural network model after the previous iteration training. If the triplet loss of the currently iteratively trained neural network model is less than the triplet loss of the neural network model after the previous iteration training, stop the iterative training, and determine the currently iteratively trained neural network model as the battery damage model, and determine the battery life of the vehicle to be charged according to the identification code and the battery damage model.

[0069] Specifically, the battery dataset includes data such as battery type (e.g., lithium-ion battery, lithium iron phosphate battery, etc.), rated capacity, rated voltage, initial state of health, real-time voltage change data, depth of discharge (DOD), and cumulative charge and discharge cycle times. The battery dataset is split into a model training set and a model validation set, and the splitting ratio is preferably 3:2, so that the model training set and the model validation set contain various data to improve the generalization ability of the model. The model training set is used to train the neural network model, and the model validation set is used to evaluate the performance of the trained model. The neural network model contains multiple layers, and each layer is responsible for extracting features at different levels. In the neural network model, the activation function is used for non-linear transformation to help the neural network model capture complex patterns in the data.

[0070] It can be understood that the triplet loss enables the neural network to pull similar data in the model training set closer and push dissimilar data farther away. If the triplet loss of the neural network model after the current iterative training is less than the triplet loss of the neural network model after the previous iterative training, then cosine annealing is used to adjust the learning rate of the model. The process of using cosine annealing to adjust the learning rate is lengthy and mature, and will not be described in detail here. By adjusting the learning rate of the model and continuing iterative training, in each iteration, the model will try to learn the patterns and relationships in the input data to improve its prediction or verification ability until the triplet loss can be less than the triplet loss of the neural network model after the previous iterative training. If the triplet loss of the neural network model after the current iterative training is less than the triplet loss of the neural network model after the previous iterative training, then the iterative training is stopped. At this time, the neural network model has tended to be stable and can approach the global optimal solution, which is determined as the battery damage model, and the battery life of the vehicle to be charged is determined by substituting the identification code into the battery damage model, improving the reliability of the battery life.

[0071] In some embodiments of the present application, when determining the charging type of the vehicle to be charged based on the battery life, it includes: comparing the battery life with a preset first preset battery life and a second preset battery life respectively. The first preset battery life is greater than the second preset battery life. According to the comparison result, the charging type of the vehicle to be charged is determined. When the battery life is greater than or equal to the first preset battery life, it is determined that the charging type of the vehicle to be charged is the fast charging mode. When the battery life is less than the first preset battery life and greater than the second preset battery life, it is determined that the charging type of the vehicle to be charged is the normal mode. When the battery life is less than or equal to the second preset battery life, it is determined that the charging type of the vehicle to be charged is the slow charging mode.

[0072] Specifically, when the battery life is in good condition (greater than or equal to the first preset battery life), it is determined that the charging type is the fast charging mode, which can shorten the waiting time for charging, ensuring both charging efficiency and not causing additional damage to the charging battery. If the battery life is at a medium level (less than the first preset battery life and greater than the second preset battery life), it is determined that the charging type is the normal mode, which can complete the charging task within a reasonable charging duration, avoiding accelerating battery aging due to excessive pursuit of charging speed, thus prolonging the battery service life. When the battery life is low (less than or equal to the second preset battery life), it is determined that the charging type is the slow charging mode, and the slow charging mode reduces the degree of chemical reaction inside the charging battery, effectively protecting the service life of the charging battery. Dynamically determining the charging type of the vehicle to be charged based on the battery life effectively balances the charging efficiency and the protection of the battery, thereby enhancing the adaptability and stability of the intelligent charging pile.

[0073] In some embodiments of the present application, when determining whether the charging type is correct based on the historical charging data set of the same charging type, it includes: obtaining historical charging characteristics from the historical charging data set, where the historical charging characteristics include historical battery parameters and historical battery life, determining the charging similarity based on the historical battery parameters and historical battery life, comparing the charging similarity with the charging similarity threshold, and determining whether the charging type is correct according to the comparison result. When the charging similarity is greater than or equal to the charging similarity threshold, it is determined that the charging type is correct and the charging type is determined as the target charging type. When the charging similarity is less than the charging similarity threshold, it is determined that the charging type is incorrect.

[0074] Specifically, the historical charging data set represents a charging data set of the vehicle type of the same vehicle to be charged. Judging whether the charging type is correct based on the historical charging data set can deeply explore the operation rules and characteristics of the charging battery under the same charging scenario according to the data-driven analysis logic. The historical battery parameters include the historical discharge current and voltage. Comparing the historical battery parameters and historical battery life with the current battery parameters and battery life to determine the charging similarity, and the charging similarity can be determined by means such as cosine similarity and Euclidean distance. The charging similarity threshold is preferably 0.8. When the charging similarity is less than the charging similarity threshold, it is directly determined that the charging type is incorrect. When the charging similarity is greater than or equal to the charging similarity threshold, it is determined that the current charging type is correct and determined as the target charging type, ensuring the adaptability of the charging strategy to the battery state. Moreover, by continuously accumulating and using the historical charging data set, it helps to continuously optimize the judgment logic of the charging type, thus forming a positive feedback loop, enhancing the adaptability of the intelligent charging pile, and at the same time improving the utilization efficiency of charging resources.

[0075] In some embodiments of the present application, when it is determined that the charging type is incorrect, a clustering algorithm is used to re-obtain the charging type of the vehicle to be charged. When determining the target charging type, it includes: obtaining representative data for each charging type according to the historical charging data set, and combining the representative data with the battery life and identification code of the vehicle to be charged to establish a clustering data set, extracting the feature vectors of each data in the clustering data set, determining that the expected number of clusters k is 3, initializing the parameters of the Gaussian distribution, calculating the probability that each data in the clustering data set belongs to each Gaussian distribution, obtaining the responsibility value, selecting the cluster with the largest responsibility value as the charging type of the battery life again, and determining this charging type as the target charging type.

[0076] Specifically, extracting representative data based on the historical charging data set and constructing a clustering data set in combination with the battery life and identification code makes full use of the relevance and features of the data. Setting the expected number of clusters to 3 and optimizing the Gaussian distribution parameters, obtaining the responsibility value by calculating the probability that the data belongs to each Gaussian distribution, and selecting the cluster with the largest responsibility value as the target charging type based on this, realizes the dynamic and accurate identification of the charging type, avoids the error caused by relying only on the preliminary judgment, improves the accuracy of the charging type judgment. The Gaussian mixture model allows automatic adjustment of the classification parameters according to the natural distribution of the data, so as to adapt to different charging types and data patterns, and further improves the adaptability of the intelligent charging pile to charge vehicles of different brands and models and charging batteries.

[0077] In some embodiments of the present application, when obtaining all historical charging behaviors corresponding to the target charging type and analyzing all historical charging behaviors, and determining the charging adjustment index of the charging power based on the analysis results, it includes: analyzing all historical charging behaviors to determine power overflow behaviors, normal power behaviors, and power shortage behaviors, constructing the total power corresponding to all power overflow behaviors into a first power set, constructing the total power corresponding to all normal power behaviors into a second power set, constructing the total power corresponding to all power shortage behaviors into a third power set, and determining the charging adjustment index of the charging power according to the first power set, the second power set, and the third power set.

[0078] In some embodiments of the present application, when determining the charging adjustment index of the charging power according to the first power set, the second power set, and the third power set, it includes: obtaining the first average value in the first power set, extracting a data in the second power set as the standard value, obtaining the third average value in the third power set, obtaining the first difference between the first average value and the standard value, obtaining the third difference between the standard value and the third average value, determining the difference ratio n between the first difference and the third difference, presetting the first preset charging adjustment index, the second preset charging adjustment index, and the third preset charging adjustment index, where the first preset charging adjustment index is greater than the second preset charging adjustment index, and the second preset charging adjustment index is greater than the third preset charging adjustment index. When n ≤ 1, taking the first preset charging adjustment index as the charging adjustment index of the charging power; when 1 < n ≤ 1.5, taking the second preset charging adjustment index as the charging adjustment index of the charging power; when 1.5 < n, taking the third preset charging adjustment index as the charging adjustment index of the charging power.

[0079] In some embodiments of the present application, when adjusting the charging power based on the charging adjustment index, it includes: the charging power is positively correlated with the charging adjustment index.

[0080] Specifically, after determining the charging power for the target charging type, due to the influence of the environment and electromagnetic field on the smart charging pile, even when charging according to the charging power, there will be fluctuations in the charging power. The power overflow behavior, normal power behavior, and power shortage behavior are determined according to the charging power determined by the smart charging pile for the target charging type. For example, in the fast charging mode, the charging power can reach 50 - 150 kW. Therefore, the normal power behavior is within 50 - 150 kW, the power overflow behavior is greater than 150 kW, and the power shortage behavior is less than 50 kW. By analyzing all historical charging behaviors and classifying them into corresponding power sets, the reliability of obtaining the charging adjustment index is ensured. When n ≤ 1, it indicates that the power shortage behavior is relatively more, and at this time, a larger charging adjustment index is required. When 1 < n ≤ 1.5, it indicates that the power overflow behavior is gradually increasing, and at this time, a smaller charging adjustment index is required. When 1.5 < n, it indicates that the power overflow behavior is relatively more, and at this time, an even smaller charging adjustment index is required. Dynamically determining the charging adjustment index according to the difference ratio realizes the intelligent adjustment of the charging power. Since the charging power is positively correlated with the charging adjustment index, when the charging adjustment index is selected due to the power overflow behavior and the value is small, the charging power decreases accordingly, avoiding irreversible damage to the charging battery due to excessive charging power, thereby effectively extending the service life of the battery. When the charging adjustment index is selected due to the power shortage behavior and the value is large, the charging power increases accordingly, quickly compensating for the power shortage situation, thereby reducing the charging waiting time and improving the charging efficiency.

[0081] It is understandable that the positive correlation mechanism enables the intelligent charging pile to intelligently and precisely adjust the charging power according to the real-time situation, which not only ensures the safety and stability of the charging process, but also ensures the adaptability to charge vehicles of different brands and models as well as charging batteries.

[0082] In summary, the beneficial effects of the present invention are as follows: By obtaining the identification code of the vehicle to be charged and traversing in the vehicle database or using the battery damage model to determine the battery life, and based on this, determining the charging type, the adaptability of the intelligent charging pile to charge different vehicle brands, models and charging batteries is improved, avoiding the accelerated aging of the charging battery caused by inappropriate charging methods, extending the service life of the charging battery, thereby reducing the risk of vehicle charging failures. Using the historical charging data set to judge its correctness, and when it is incorrect, using the clustering algorithm to re-obtain it to ensure the accuracy of the target charging type, so that the charging power output by the intelligent charging pile fits the needs of the vehicle battery, which not only ensures the safety of the charging process, but also prevents safety hazards such as overcharging and overheating caused by improper charging parameters. After determining the charging power according to the target charging type, by analyzing the corresponding historical charging behaviors to determine the charging adjustment index, and adjusting the charging power accordingly, the charging adaptability and flexibility of the intelligent charging pile are improved.

[0083] In another preferred manner based on the above embodiments, refer to Figure 2 As shown, this embodiment provides a charging system for an intelligent charging pile, which is used to apply the charging method of the above intelligent charging pile, including:

[0084] A data acquisition module, configured to obtain the identification code of the vehicle to be charged and traverse in the vehicle database, determine the battery life of the vehicle to be charged according to the traversal result, and when the identification code does not exist in the vehicle database, determine the battery life of the vehicle to be charged according to the battery damage model;

[0085] A charging judgment module, configured to determine the charging type of the vehicle to be charged based on the battery life, verify the charging type, judge whether the charging type is correct based on the historical charging data set of the same charging type, and when it is determined that the charging type is incorrect, use the clustering algorithm to re-obtain the charging type of the vehicle to be charged to determine the target charging type;

[0086] A charging processing module, configured to determine the charging power according to the target charging type, obtain all historical charging behaviors corresponding to the target charging type, and analyze all historical charging behaviors, and determine the charging adjustment index of the charging power based on the analysis result;

[0087] A charging adjustment module, configured to adjust the charging power based on the charging adjustment index, and charge the vehicle to be charged according to the adjusted charging power.

[0088] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0090] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, so that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still can modify the specific implementation manners of the present invention or make equivalent replacements. Any modification or equivalent replacement without departing from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A charging method for an intelligent charging pile, characterized in that, Including: Obtain the identification code of the vehicle to be charged and traverse it in the vehicle database, determine the battery life of the vehicle to be charged according to the traversal result. When the identification code does not exist in the vehicle database, determine the battery life of the vehicle to be charged according to the battery damage model; Based on the battery life, determine the charging type of the vehicle to be charged, verify the charging type, and judge whether the charging type is correct based on the historical charging data set of the same charging type. When it is determined that the charging type is incorrect, use the clustering algorithm to re-obtain the charging type of the vehicle to be charged and determine the target charging type; Determine the charging power according to the target charging type, obtain all historical charging behaviors corresponding to the target charging type, and analyze all historical charging behaviors. Based on the analysis result, determine the charging adjustment index of the charging power; Adjust the charging power based on the charging adjustment index, and charge the vehicle to be charged according to the adjusted charging power.

2. The charging method of the intelligent charging pile according to claim 1, characterized in that, When obtaining the identification code of the vehicle to be charged and traversing it in the vehicle database, and determining the battery life of the vehicle to be charged according to the traversal result, it includes: When the identification code exists in the vehicle database, determine the battery life of the vehicle to be charged according to the vehicle database; When the identification code does not exist in the vehicle database, determine the battery life of the vehicle to be charged according to the battery damage model.

3. The charging method of the intelligent charging pile according to claim 2, wherein, When determining the battery life of the vehicle to be charged according to the battery damage model, it includes: Obtain the battery data set of the vehicle to be charged, and split the battery data set into a model training set and a model verification set; Pre-select a neural network model, perform iterative training on the neural network model according to the model training set, and evaluate the iteratively trained neural network model according to the model verification set; If the triplet loss of the current iteratively trained neural network model is greater than or equal to the triplet loss of the previous iteratively trained neural network model, use cosine annealing to adjust the learning rate and continue iterative training until the triplet loss is less than the triplet loss of the previous iteratively trained neural network model; If the triplet loss of the current iteratively trained neural network model is less than the triplet loss of the previous iteratively trained neural network model, stop iterative training and determine the current iteratively trained neural network model as the battery damage model; Determine the battery life of the vehicle to be charged according to the identification code and the battery damage model.

4. The charging method of the intelligent charging pile according to claim 3, characterized in that, When determining the charging type of the vehicle to be charged based on the battery life, it includes: Compare the battery life with a preset first preset battery life and a second preset battery life respectively. The first preset battery life is greater than the second preset battery life, and determine the charging type of the vehicle to be charged according to the comparison result; When the battery life is greater than or equal to the first preset battery life, determine the charging type of the vehicle to be charged as the fast charging mode; When the battery life is less than the first preset battery life and greater than the second preset battery life, determine the charging type of the vehicle to be charged as the normal mode; When the battery life is less than or equal to the second preset battery life, determine that the charging type of the vehicle to be charged is the slow charging mode.

5. The charging method of the intelligent charging pile according to claim 4, characterized in that, When judging whether the charging type is correct based on the historical charging data set of the same charging type, it includes: Obtain historical charging characteristics according to the historical charging data set, where the historical charging characteristics include historical battery parameters and historical battery life; Determine the charging similarity based on the historical battery parameters and historical battery life; Compare the charging similarity with the charging similarity threshold, and judge whether the charging type is correct according to the comparison result; When the charging similarity is greater than or equal to the charging similarity threshold, determine that the charging type is correct, and determine the charging type as the target charging type; When the charging similarity is less than the charging similarity threshold, determine that the charging type is incorrect.

6. The charging method of the intelligent charging pile according to claim 5, characterized in that, When it is determined that the charging type is incorrect, use the clustering algorithm to re-obtain the charging type of the vehicle to be charged. When determining the target charging type, it includes: Obtain the representative data of each charging type according to the historical charging data set, and combine the representative data with the battery life and identification code of the vehicle to be charged to establish a clustering data set, and extract the feature vectors of each data in the clustering data set; Determine that the expected number of clusters k is 3, initialize the parameters of the Gaussian distribution, calculate the probability that each data in the clustering data set belongs to each Gaussian distribution, obtain the responsibility value, select the cluster with the largest responsibility value as the charging type of the battery life again, and determine this charging type as the target charging type.

7. The charging method of the intelligent charging pile according to claim 6, wherein, When obtaining all historical charging behaviors corresponding to the target charging type, analyzing all historical charging behaviors, and determining the charging adjustment index of the charging power based on the analysis result, it includes: Analyze all historical charging behaviors to determine power overflow behaviors, normal power behaviors, and power shortage behaviors; Construct the total power corresponding to all power overflow behaviors into a first power set; Construct the total power corresponding to all normal power behaviors into a second power set; Construct the total power corresponding to all power shortage behaviors into a third power set; Determine the charging adjustment index of the charging power according to the first power set, the second power set, and the third power set.

8. The charging method of the intelligent charging pile according to claim 7, wherein When determining the charging adjustment index of the charging power according to the first power set, the second power set, and the third power set, it includes: Obtain the first average value in the first power set, extract a data in the second power set as the standard value, and obtain the third average value in the third power set; Obtain the first difference between the first average value and the standard value, obtain the third difference between the standard value and the third average value, and determine the difference ratio n between the first difference and the third difference; Preset a first preset charging adjustment index, a second preset charging adjustment index, and a third preset charging adjustment index, where the first preset charging adjustment index is greater than the second preset charging adjustment index, and the second preset charging adjustment index is greater than the third preset charging adjustment index; When n ≤ 1, the first preset charging adjustment index is used as the charging adjustment index of the charging power; When 1 < n ≤ 1.5, the second preset charging adjustment index is used as the charging adjustment index of the charging power; When 1.5 < n, the third preset charging adjustment index is used as the charging adjustment index of the charging power.

9. The charging method of the intelligent charging pile according to claim 8, characterized in that, When adjusting the charging power based on the charging adjustment index, it includes: The charging power and the charging adjustment index are positively correlated.

10. A charging system for an intelligent charging pile, which is used to apply the charging method of the intelligent charging pile according to any one of claims 1-9, characterized in that, It includes: A data acquisition module, configured to obtain the identification code of the vehicle to be charged and traverse it in the vehicle database, determine the battery life of the vehicle to be charged according to the traversal result, and when the identification code does not exist in the vehicle database, determine the battery life of the vehicle to be charged according to the battery damage model; A charging judgment module, configured to determine the charging type of the vehicle to be charged based on the battery life, verify the charging type, judge whether the charging type is correct based on the historical charging data set of the same charging type, and when it is determined that the charging type is incorrect, use the clustering algorithm to re-obtain the charging type of the vehicle to be charged and determine the target charging type; A charging processing module, configured to determine the charging power according to the target charging type, obtain all historical charging behaviors corresponding to the target charging type, and analyze all historical charging behaviors, and determine the charging adjustment index of the charging power based on the analysis result; A charging adjustment module, configured to adjust the charging power based on the charging adjustment index and charge the vehicle to be charged according to the adjusted charging power.

Images