Charging control method of shared charging pile and charging pile

Abstract

The present application belongs to the technical field of new energy automobile charging equipment, and particularly relates to a charging control method and a charging pile for shared charging piles, comprising the following steps: obtaining a contact state parameter of a charging interface of a charging pile, wherein the contact state parameter comprises an accumulated plugging frequency, a contact voltage drop, a charging current and an interface temperature of the charging interface; determining a comprehensive degradation index of the charging interface of the charging pile based on the contact state parameter; predicting a contact resistance of the charging interface of the charging pile in a current and future preset time window according to the comprehensive degradation index; obtaining a maximum charging current that can be output by the charging pile according to the predicted contact resistance; obtaining multi-dimensional operation parameters such as the accumulated plugging frequency, the contact resistance, the interface temperature rise, the temperature rise rate and the abnormal plugging frequency, constructing the comprehensive degradation index, and quantitatively evaluating the degradation state of the charging interface; and combining a hybrid physical-data driven prediction model to realize prediction of a contact resistance change trend.

Description

Technical Field

[0001] This invention belongs to the technical field of new energy vehicle charging equipment, specifically relating to a charging control method for shared charging piles and the charging piles themselves. Background Technology

[0002] With the rapid popularization of new energy vehicles, shared charging stations, as important public charging infrastructure, are widely used in commercial complexes, communities, parking lots, and other scenarios. Compared with private charging stations, shared charging stations are characterized by high-frequency use: a large number of vehicles may connect and disconnect every day, and the frequency of plugging and unplugging the charging gun and vehicle interface is much higher than that of private charging stations. Statistics show that a public charging station can be plugged and unplugged an average of 10 to 30 times per day, while a private charging station is usually only plugged and unplugged 1 to 2 times. This high-frequency use will cause the contact condition of the charging interface to gradually deteriorate.

[0003] Existing technologies mainly rely on fixed temperature or current thresholds for protection, which cannot reflect the long-term degradation of the charging interface and make it difficult to balance charging safety and charging efficiency.

[0004] In view of this, the present invention proposes a charging control method for shared charging piles and a charging pile. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing shared charging piles that cannot adaptively adjust the charging current based on the overall degradation level of the charging interface. This invention provides a charging control method and charging pile for shared charging piles. By collecting contact state parameters, calculating the overall degradation index, and predicting the real-time contact resistance using a hybrid model, the output power is adjusted in real time to achieve adaptive current limiting based on the aging level of the interface, thereby improving charging efficiency while ensuring charging safety.

[0006] To address the aforementioned shortcomings in existing technologies, this invention provides a charging control method for shared charging piles, characterized by comprising the following steps: Step 1: Obtain the contact status parameters of the charging pile's charging interface. The contact status parameters include the cumulative number of insertions and removals of the charging interface, the contact voltage drop, the charging current, and the interface temperature. Cumulative insertion / removal count: A Hall switch and a micro switch are installed inside the charging gun. When the charging gun is inserted into the vehicle interface, the permanent magnet at the vehicle interface triggers the Hall switch, and at the same time, a mechanical latch presses the micro switch. A valid insertion / removal is counted when the response signals of both switches are valid and stable within a preset time window, regardless of whether actual charging occurs after this insertion / removal. The cumulative insertion / removal count is denoted as N.

[0007] Contact voltage drop: The contact voltage drop is the first voltage value at the output terminal of the charging pile. The second voltage value of the charging interface on the vehicle side, fed back by the vehicle's battery management system. The difference; calculate the contact voltage drop. Then, the contact resistance is calculated using the contact voltage drop. .

[0008] Interface temperature: Install at least one temperature sensor (preferably a negative temperature coefficient thermistor) at the metal conductor root of the power terminals (positive and negative terminals for DC charging or L and N terminals for AC charging) of the charging interface to collect the interface temperature T, and simultaneously collect the ambient temperature. .

[0009] Step 2: Based on the contact state parameters, determine the comprehensive degradation index of the charging pile's charging interface; Preferably, the comprehensive degradation index is calculated using the following formula:

[0010] Where N is the cumulative number of insertions and removals. To design the maximum number of insertion and removal cycles, Initial contact resistance, This refers to the static contact resistance. This represents the average dynamic resistance over the most recent charging cycles. The standard deviation of the dynamic resistance, The temperature rise is T, where T is the interface temperature. For ambient temperature, To allow the highest possible interface temperature, M represents the temperature rise rate, and M represents the abnormal insertion / removal count. This is the safety threshold for abnormal insertion and removal. ,as well as For model parameters, For baseline offset, The weight values ​​are assigned.

[0011] Secondly, the contact resistance related parameters , , , It was obtained by fitting the data using the nonlinear least squares method after insertion and extraction life test and constant current aging test. Weighting coefficient Collect full lifecycle data from at least 200 charging piles, and use linear regression or support vector regression to solve the problem with the pre-fault degradation index as the target.

[0012] Step 3: Based on the comprehensive degradation index, predict the contact resistance of the charging interface of the charging pile within the current and future preset time windows; Furthermore, the contact resistance prediction employs a hybrid physics-data driven model, which predicts the contact resistance during the current and subsequent charging processes based on the calculated comprehensive degradation index D and the current charging current I. The physical model is based on the law that contact resistance degrades at an accelerated rate with time and temperature (Arrhenius-Weibull degradation form). Furthermore, the hybrid physics-data driven model includes a physical degradation layer and a data-driven residual correction layer; Secondly, the physical degradation layer establishes a contact resistance degradation model based on the cumulative number of insertions and removals of the charging pile's charging interface, interface temperature, charging current, and comprehensive degradation index, outputting a theoretical predicted contact resistance value, as shown in the following formula:

[0013] Where t is the charging time; The time constant is related to the contact structure; It is the activation energy, which is related to the metal oxidation rate; Let be the Boltzmann constant, and take . ; It is the Weibull shape constant; The electro-induced degradation rate characterizes the additional damage to contact resistance caused by high current. This refers to the real-time charging current.

[0014] Meanwhile, the data-driven residual correction layer learns the predicted residual between the theoretical contact resistance prediction value and the actual contact resistance based on historical operating data, and outputs the residual correction value. Finally, the final predicted contact resistance value is obtained by superimposing the theoretical contact resistance prediction value with the residual correction value.

[0015] The final predicted contact resistance value is: ,in To predict the residuals of the physical model.

[0016] Furthermore, the input features of the data-driven residual correction layer include: the contact resistance sequence, interface temperature sequence, charging current sequence, comprehensive degradation index sequence, temperature rise rate sequence, cumulative insertion and removal times sequence, and the theoretical contact resistance prediction value sequence output by the physical degradation layer. Furthermore, the input features are arranged in chronological order to form a multidimensional time series feature matrix.

[0017] Furthermore, the data-driven residual correction layer is constructed using a Long Short-Term Memory (LSTM) network; Preferably, the long short-term memory network includes: an input layer, a long short-term memory network layer, a fully connected layer, and an output layer; The output layer is used to output the contact resistance prediction residual.

[0018] Preferably, the training process of the Long Short-Term Memory (LSTM) network layer includes: Acquire full lifecycle operation data and interface aging test data for multiple charging piles; The theoretical contact resistance prediction value is calculated using the physical degradation layer based on the aforementioned operational data; Residual labels are constructed based on the difference between the actual contact resistance and the predicted theoretical contact resistance. Using the multidimensional time series feature matrix as input and the residual label as the supervised learning target, the network parameters are optimized through a loss function to train the long short-term memory network. After training is complete, the network weights are deployed to the control unit of the charging pile.

[0019] Furthermore, the loss function is a weighted sum of the data error term and the physical constraint term; Furthermore, the data error term is the difference between the actual contact resistance and the predicted contact resistance; Furthermore, the physical constraint term is the deviation between the predicted contact resistance and the theoretically predicted contact resistance output by the physical degradation layer; Furthermore, the model is trained by jointly optimizing the data error term and the physical constraint term to ensure that the prediction results meet the physical laws of contact resistance degradation.

[0020] Step 4: Based on the predicted contact resistance, obtain the maximum charging current that the charging pile can allow to output; Furthermore, the maximum charging current is determined jointly based on the predicted contact resistance, interface temperature, and overall degradation index. The maximum charging current decreases as the predicted contact resistance increases and as the interface temperature increases, and is constrained by the maximum allowable heat dissipation power, as shown in the following formula:

[0021] in, The maximum allowable heat generation power; t is the charging time; The temperature margin coefficient, which monotonically decreases from 1 to 0 as temperature increases, can be represented by a piecewise function: when hour, ,when hour, ,when hour, ; The degradation boundary coefficient, This is a safety margin resistor.

[0022] The final output current limit also needs to take into account the charging pile's rated current, the cable's current carrying capacity, and the vehicle's requested current.

[0023] Step 5: Adjust the output power of the charging pile in real time according to the maximum charging current; The output power of the charging pile is adjusted in real time based on the calculated maximum charging current.

[0024] Charging is performed according to the adjusted current, and steps one through five are executed cyclically during the charging process, dynamically updating the contact status parameters, degradation index, and predicted contact resistance value. When the predicted contact resistance, measured interface temperature, or overall degradation index exceeds a preset threshold, protective actions such as power reduction, alarm, or charging interruption are executed.

[0025] The present invention also provides a shared charging station, including: a charging gun and a charging socket for establishing an electrical connection with a vehicle; The contact status acquisition module consists of an insertion / removal counting unit, a voltage acquisition unit, and a temperature monitoring unit. The voltage acquisition unit is used to acquire the first voltage value at the output end of the charging pile and receive the second voltage value on the vehicle side of the charging interface from the vehicle battery management system. A control unit, configured to execute the charging control method according to any one of claims 1 to 9; The charging execution module adjusts the output current according to the instructions of the control unit; The communication module is used to exchange data with the vehicle battery management system and the back-end server.

[0026] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention acquires multi-dimensional operating parameters such as cumulative insertion / removal counts, contact resistance, interface temperature rise, temperature rise rate, and abnormal insertion / removal counts to construct a comprehensive degradation index, thereby quantitatively assessing the degradation state of the charging interface. Furthermore, it combines a physical degradation model with a data-driven model to form a hybrid physical-data-driven prediction model, enabling the prediction of contact resistance change trends. Compared to existing technologies that rely solely on real-time temperature or fixed thresholds for protection, this invention can identify potential degradation risks of the charging interface in advance, improving the accuracy of contact state assessment and fault warning capabilities.

[0027] 2. This invention dynamically determines the maximum allowable charging current based on predicted contact resistance, interface temperature, and overall degradation index, and adjusts the charging output power in real time. It maintains a high charging power when the charging interface is in a slightly degraded state, and automatically implements current limiting or protection control when the degradation worsens, ensuring charging safety while reducing unnecessary derating. It balances charging efficiency and equipment reliability, extends the lifespan of the charging interface, and reduces maintenance costs. Attached Figure Description

[0028] Figure 1 This is a control flowchart of a charging control method for a shared charging pile according to the present invention; Figure 2 This is a block diagram of the overall structure of a shared charging pile according to the present invention; Figure 3 This is a block diagram of the hybrid physics-data driven model structure of a charging control method for a shared charging pile according to the present invention. Detailed Implementation

[0029] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0030] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures, and should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0031] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "inner," and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the accompanying drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0032] In the description of this invention, unless otherwise explicitly specified and limited, the term "connection" or similar designation indicating a connection between components should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral part; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0033] Example 1: like Figure 1-3 As shown, this embodiment provides a charging control method for a shared charging pile, which is applied to a DC shared charging pile with a rated power of 120kW and a rated output current of 250A.

[0034] In this embodiment, the control unit pre-stores the degradation model parameters, protection threshold, and weights of the trained Long Short-Term Memory (LSTM) network model, and performs the following steps in real time during the charging process: Step 1: Obtain the contact status parameters of the charging pile's charging interface. The contact status parameters include the cumulative number of insertions and removals of the charging interface, the contact voltage drop, the charging current, and the interface temperature. (1) Number of insertions and removals: The charging gun is equipped with a Hall switch and a micro switch. When the charging gun is inserted into the vehicle's charging port, the permanent magnet at the vehicle's port triggers the Hall switch, and at the same time, the mechanical latch presses the micro switch.

[0035] When both switch signals are valid and stable within the preset time window, it is determined as a valid insertion / removal, and the cumulative number of insertions / removals N is recorded.

[0036] If only a single signal triggers or the signal duration is insufficient, it is determined to be an abnormal insertion / removal, and the number of abnormal insertions / removals M is recorded.

[0037] (2) Contact voltage drop: After charging starts, the voltage acquisition unit collects the output voltage V1 of the charging pile in real time. Simultaneously, the vehicle-side voltage V2 is received from the vehicle battery management system via the CAN bus. Calculate the contact voltage drop: And by combining the current charging current I, the real-time contact resistance is calculated using Ohm's law. .

[0038] (3) Interface temperature acquisition: A temperature sensor is installed at the base of the power terminal of the charging interface to collect the interface temperature T, and the ambient temperature is also collected. ; The interface temperature rise is obtained from the following formula:

[0039] The temperature rise rate is calculated based on continuously collected data. .

[0040] Step 2: Based on the contact state parameters, determine the comprehensive degradation index D of the charging pile's charging interface; Preferably, the comprehensive degradation index is calculated using the following formula:

[0041] Where N is the cumulative number of insertions and removals. To design the maximum number of insertion and removal cycles, Initial contact resistance, This refers to the static contact resistance. This represents the average dynamic resistance over the most recent charging cycles. The standard deviation of the dynamic resistance, The temperature rise is T, where T is the interface temperature. For ambient temperature, To allow the highest possible interface temperature, M represents the temperature rise rate, and M represents the abnormal insertion / removal count. This is the safety threshold for abnormal insertion and removal. ,as well as For model parameters, For baseline offset, The weight values ​​are assigned.

[0042] Step 3: Based on the comprehensive degradation index, predict the contact resistance of the charging interface of the charging pile within the current and future preset time windows; The contact resistance prediction employs a hybrid physics-data driven model, which predicts the contact resistance during the current and subsequent charging processes based on the calculated comprehensive degradation index D and the current charging current I. The physical model is based on the law that contact resistance degrades at an accelerated rate with time and temperature (Arrhenius-Weibull degradation form). The hybrid physics-data driven model includes a physical degradation layer, a feature fusion layer, and a data-driven residual correction layer.

[0043] S31: Calculation of physical degradation layer; The physical degradation layer establishes a contact resistance degradation model based on the cumulative number of insertions and removals N, interface temperature T, charging current I, and comprehensive degradation index D.

[0044] The Arrhenius-Weibull degradation model is preferred for calculating the theoretical contact resistance prediction.

[0045] Where t is the charging time; The time constant is related to the contact structure; It is the activation energy, which is related to the metal oxidation rate; Let be the Boltzmann constant, and take . ; It is the Weibull shape constant; The electro-induced degradation rate characterizes the additional damage to contact resistance caused by high current. This refers to the real-time charging current.

[0046] Among them, the theoretical contact resistance prediction value reflects the development trend of contact resistance under the law of physical degradation.

[0047] S32: Integrate the theoretical contact resistance prediction with historical operating data to construct a time series feature matrix; Preferably, the most recent 30 minutes of running data is used as the input time window.

[0048] S33: The data-driven residual correction layer is implemented using a Long Short-Term Memory (LSTM) network.

[0049] An LSTM network consists of an input layer, a first long short-term memory (LSTM) network layer, a second long short-term memory (LSTM) network layer, a fully connected layer, and an output layer.

[0050] The network consists of a first long short-term memory (LSTM) layer for extracting short-term degradation features, a second LSM layer for extracting long-term degradation features, a fully connected layer for feature mapping, and an output layer for outputting the contact resistance prediction residual. ; The final predicted contact resistance value is:

[0051] The control unit obtains the trend of contact resistance change within a future preset time window based on the predicted value.

[0052] Step 4: Based on the predicted contact resistance, obtain the maximum charging current that the charging pile can allow to output; The maximum charging current is determined based on the predicted contact resistance, interface temperature, and overall degradation index. The maximum charging current decreases as the predicted contact resistance increases and as the interface temperature increases, and is also constrained by the maximum allowable heat dissipation power, as shown in the following formula:

[0053] in, The maximum allowable heat generation power; t is the charging time; The temperature margin coefficient, which monotonically decreases from 1 to 0 as temperature increases, can be represented by a piecewise function: when hour, ,when hour, ,when hour, ; The degradation boundary coefficient is a degradation threshold that decays exponentially with increasing degradation index. This is a safety margin resistor.

[0054] Furthermore, the final output current limit also needs to take into account the charging pile's rated current, the cable's current carrying capacity, and the vehicle's requested current. .

[0055] Step 5: Adjust the output power of the charging pile in real time according to the maximum charging current. To avoid sudden current changes impacting the vehicle battery, the control unit limits the rate of current change and gradually adjusts it to the target output current.

[0056] During the charging process, steps S1 to S5 are periodically repeated to update the contact status parameters, comprehensive degradation index, contact resistance prediction results, and maximum charging current in real time.

[0057] The control unit will activate Level 1 protection, reduce output power, and send an alarm message to the backend server when any of the following conditions occur: The predicted contact resistance exceeds a first preset threshold. The measured interface temperature exceeded the first preset threshold. The overall degradation index exceeds the first preset threshold.

[0058] The control unit will activate secondary protection if any of the following conditions occur, immediately stopping charging and locking the charging gun, awaiting maintenance: The predicted contact resistance exceeds the second preset threshold. The measured interface temperature exceeded the second preset threshold. The overall degradation index exceeds the second preset threshold.

[0059] Example 2: like Figure 2 As shown, this embodiment provides a shared charging station, including: a charging gun and a charging socket, for establishing an electrical connection with a vehicle; The contact status acquisition module consists of an insertion / removal counting unit, a voltage acquisition unit, and a temperature monitoring unit. The voltage acquisition unit is used to acquire the first voltage value at the output end of the charging pile and receive the second voltage value on the vehicle side of the charging interface from the vehicle battery management system. A control unit, configured to execute the charging control method according to any one of claims 1 to 9; The charging execution module adjusts the output current according to the instructions of the control unit; The communication module is used to exchange data with the vehicle battery management system and the back-end server.

[0060] The workflow of the charging pile in this embodiment is completely consistent with the control method described in Embodiment 1, and will not be repeated here.

[0061] Example 3: like Figure 3 As shown, this embodiment illustrates the training method for a hybrid physics-data-driven model.

[0062] S301: Data Acquisition Collect full lifecycle operation data and interface aging test data from multiple shared charging piles.

[0063] The collected data includes: contact resistance, interface temperature, charging current, cumulative number of insertions and removals, comprehensive degradation index, number of abnormal insertions and removals, and fault status information.

[0064] S302: Data Preprocessing The collected data undergoes outlier removal, missing value compensation, and data normalization to form a standard training dataset.

[0065] S303: Theoretical Contact Resistance Calculation The theoretical contact resistance prediction value, Rphy, is obtained by calculating the training data using a physical degradation layer. S304: Residual Label Construction Residual labels are constructed based on the actual contact resistance and the predicted theoretical contact resistance:

[0066] in For actual measurement of contact resistance.

[0067] S305: Feature Matrix Construction The input features are arranged in chronological order to form a multidimensional time series feature matrix, which serves as the input to the neural network.

[0068] S306: LSTM Network Training The construction of a long short-term memory network includes: an input layer, a long short-term memory network layer, a fully connected layer, and an output layer; The output layer is used to output the contact resistance prediction residual.

[0069] Using the time series feature matrix as input, and residual labels It is used as a supervised learning objective for training.

[0070] S307: Physical Constraint Training The loss function is a weighted sum of the data error term and the physical constraint term, as shown in the following formula: Loss = Lossdata + λLossphy Lossdata is used to characterize the error between the actual contact resistance and the predicted contact resistance; Lossphy is used to characterize the deviation between the predicted contact resistance and the predicted theoretical contact resistance.

[0071] By jointly optimizing the data error term and the physical constraint term, the model prediction accuracy is improved and the prediction results are guaranteed to conform to the contact resistance degradation law.

[0072] S308: Model Deployment After training, the model weight parameters are exported and the model weights are deployed to the charging pile control unit. During the charging process, the control unit calls the trained model to perform online prediction, thereby realizing contact resistance prediction and dynamic current limiting control.

[0073] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A charging control method for a shared charging station, characterized in that, include: Obtain the contact status parameters of the charging interface of the charging pile, including the cumulative number of insertions and removals of the charging interface, contact voltage drop, charging current, and interface temperature; Based on the contact state parameters, the comprehensive degradation index of the charging pile's charging interface is determined; Based on the comprehensive degradation index, predict the contact resistance of the charging interface of the charging pile within the current and future preset time windows; Based on the predicted contact resistance, the maximum charging current that the charging pile can allow to output is obtained; The output power of the charging pile is adjusted in real time according to the maximum charging current.

2. The charging control method for a shared charging pile as described in claim 1, characterized in that: The contact voltage drop is the first voltage value at the output terminal of the charging pile. The second voltage value of the charging interface on the vehicle side, fed back by the vehicle's battery management system. The difference between the contact voltage drop and the charging current is used to obtain the contact resistance.

3. The charging control method for a shared charging pile as described in claim 1, characterized in that: The comprehensive degradation index is obtained by weighting the cumulative number of insertions and removals, contact resistance characteristic parameters, interface temperature characteristic parameters, and abnormal insertion and removal characteristic parameters of the charging pile's charging interface. The contact resistance characteristic parameters include static contact resistance and dynamic contact resistance, and the interface temperature characteristic parameters include interface temperature rise and temperature rise rate. The comprehensive degradation index is used to characterize the overall degradation level of the charging interface.

4. The charging control method for a shared charging pile as described in claim 1, characterized in that: The prediction of the contact resistance uses a hybrid physics-data driven model; The hybrid physics-data driven model includes a physics degradation layer and a data-driven residual correction layer. The physical degradation layer establishes a contact resistance degradation model based on the cumulative number of insertions and removals of the charging pile's charging interface, interface temperature, charging current, and comprehensive degradation index, and outputs a theoretical predicted value of the contact resistance. The data-driven residual correction layer learns the predicted residual between the theoretical contact resistance prediction value and the actual contact resistance based on historical operating data, and outputs the residual correction value. The final predicted contact resistance value is obtained by superimposing the theoretical contact resistance prediction value and the residual correction value.

5. The charging control method for a shared charging pile as described in claim 4, characterized in that: The input features of the data-driven residual correction layer include: the historical contact resistance sequence, interface temperature sequence, charging current sequence, comprehensive degradation index sequence, temperature rise rate sequence, cumulative insertion and removal times sequence, and the theoretical contact resistance prediction value sequence output by the physical degradation layer. The input features are arranged in chronological order to form a multidimensional time series feature matrix.

6. The charging control method for a shared charging pile as described in claim 5, characterized in that: The data-driven residual correction layer is constructed using a Long Short-Term Memory (LSTM) network. The Long Short-Term Memory (LSTM) network includes: an input layer, an LSM network layer, a fully connected layer, and an output layer. The output layer is used to output the contact resistance prediction residual.

7. The charging control method for a shared charging pile as described in claim 6, characterized in that: The training process of the Long Short-Term Memory (LSTM) network layer includes: Acquire full lifecycle operation data and interface aging test data for multiple charging piles; The theoretical contact resistance prediction value is calculated using the physical degradation layer based on the aforementioned operational data; Residual labels are constructed based on the difference between the actual contact resistance and the predicted theoretical contact resistance. Using the multidimensional time series feature matrix as input and the residual label as the supervised learning target, the network parameters are optimized through a loss function to train the long short-term memory network. After training is complete, the network weights are deployed to the control unit of the charging pile.

8. The charging control method for a shared charging pile as described in claim 7, characterized in that: The loss function is a weighted sum of the data error term and the physical constraint term; The data error term is the difference between the actual contact resistance and the predicted contact resistance; The physical constraint term is the difference between the predicted contact resistance and the theoretically predicted contact resistance output by the physical degradation layer.

9. The charging control method and charging pile of the shared charging pile as described in claim 1, characterized in that: The formula for calculating the maximum charging current is as follows: ; in, The maximum allowable heat output; t is the charging time; For safety margin resistors; This is the temperature margin coefficient; This represents the degradation boundary coefficient.

10. A shared charging station, characterized in that, include: Charging gun and charging socket; The contact status acquisition module consists of an insertion / removal counting unit, a voltage acquisition unit, and a temperature monitoring unit. The voltage acquisition unit is used to acquire the first voltage value at the output end of the charging pile and receive the second voltage value on the vehicle side of the charging interface from the vehicle battery management system. A control unit, configured to execute the charging control method according to any one of claims 1 to 9; The charging execution module adjusts the output current according to the instructions of the control unit; The communication module is used to exchange data with the vehicle battery management system and the back-end server.

Images