Charging management method and system of charging pile

Abstract

The invention relates to the field of charging management, in particular to a charging management method and system for a charging pile, and the method comprises the steps: obtaining health characteristic labels of all charging vehicles electrically connected with the charging pile, carrying out the collaborative analysis of charging control of all health characteristic labels according to a health feedback model disposed in the charging pile, and obtaining a health feedback model; the charging control method comprises the steps of obtaining a charging control strategy corresponding to each charging vehicle, performing charging processing on each charging vehicle through each charging control strategy, and collecting an electrical performance parameter of each charging vehicle as a monitoring information flow of each charging vehicle; and the health feedback model of the charging pile and the health characteristic label of each charging vehicle are verified and updated based on each monitoring information flow, and each charging control strategy is correspondingly adjusted.

Description

Technical Field

[0001] This invention relates to the field of charging management, specifically a charging management method and system for charging piles. Background Technology

[0002] With the increasing variety of electric vehicle brands and models on the market, there are significant differences in battery types, capacities, and performance among different models. In practical applications, multiple vehicles often connect to charging stations simultaneously. Since different vehicles have different charging needs, improper coordination and management can lead to uneven power distribution at charging stations, resulting in slow charging for some vehicles or even overloading of the charging stations. Charging efficiency and safety are paramount during the charging process. Inappropriate charging strategies can lead to excessively long charging times, impacting the user experience. Furthermore, overcharging and over-discharging can cause battery overheating, short circuits, and other safety hazards, potentially endangering personal safety and property. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a charging management method and system for charging piles, which can solve the problems in the prior art.

[0004] This invention is achieved through the following technical solution: This invention provides a charging management method for charging piles, comprising: Obtain the health characteristic tags of each charging vehicle that is electrically connected to the charging pile; Based on the health feedback model deployed in the charging pile, a collaborative analysis of charging control is performed on each of the health characteristic tags to obtain the charging control strategy for each of the charging vehicles. The charging control strategies described above are used to charge each of the charging vehicles, and the electrical performance parameters of each of the charging vehicles are collected as monitoring information streams for each of the charging vehicles. Based on the monitoring information streams, the health feedback model of the charging pile and the health characteristic labels of the charging vehicles are verified and updated, and the charging control strategies are adjusted accordingly.

[0005] This invention provides a charging management system for charging piles, used to implement the charging management method for charging piles as described in any one of the first aspects, comprising: The tag acquisition module is used to acquire the health characteristic tags of each charging vehicle that is electrically connected to the charging pile. The strategy analysis module is used to perform collaborative analysis of charging control on each of the health characteristic tags based on the health feedback model deployed in the charging pile, so as to obtain the charging control strategy for each of the charging vehicles. The performance monitoring module is used to perform charging processing on each of the charging vehicles through the charging control strategies, and at the same time collect the electrical performance parameters of each of the charging vehicles as a monitoring information stream for each of the charging vehicles. The health verification module is used to verify and update the health feedback model of the charging pile and the health characteristic labels of the charging vehicles based on the monitoring information streams, and to adjust the charging control strategies accordingly.

[0006] In summary, the beneficial effects of this invention are: This invention provides a basis for precise charging by acquiring vehicle health characteristic tags. Through collaborative analysis using a health feedback model, a control strategy can be derived, enabling reasonable allocation of charging for multiple vehicles and improving charging efficiency. During charging, electrical performance parameters are collected to form a monitoring information stream, allowing for real-time monitoring of vehicle charging status. Based on this, the model and tags are verified, updated, and the strategy is adjusted to ensure charging safety, adapt to changes in vehicle status, extend the lifespan of batteries and charging piles, and improve the scientific nature and reliability of overall charging management. Attached Figure Description

[0007] For ease of explanation, the present invention will be described in detail below with reference to specific embodiments and accompanying drawings.

[0008] Figure 1 This is a schematic diagram illustrating the steps of a charging management method for a charging pile according to the present invention; Figure 2 This is a schematic diagram of the charging management system for a charging pile according to the present invention. Detailed Implementation

[0009] All features disclosed in this specification, or all steps in all disclosed methods or processes, may be combined in any way, except for mutually exclusive features and / or steps.

[0010] The following is combined with Figure 1-2 The present invention will be described in detail below.

[0011] like Figure 1 As shown, the present invention provides a charging management method for charging piles, comprising: S1: Obtain the health characteristic labels of each charging vehicle that is electrically connected to the charging pile; S2: Based on the health feedback model deployed in the charging pile, perform collaborative analysis of charging control on each of the health characteristic tags to obtain the charging control strategy for each of the charging vehicles. S3: Charge each of the charging vehicles using the charging control strategies described above, and collect electrical performance parameters of each of the charging vehicles as monitoring information streams for each of the charging vehicles. S4: Based on the monitoring information streams, verify and update the health feedback model of the charging pile and the health characteristic labels of the charging vehicles, and adjust the charging control strategies accordingly.

[0012] In step S1, the health characteristic tags of the charging vehicles need to be pre-registered on a designated network platform. These health characteristic tags may contain important information related to vehicle charging, such as the type, capacity, health status, and charging history of the vehicle's battery. The network platform assigns a unique identification code to each registered charging vehicle. This identification code is like the vehicle's "ID card" on the network platform, used to uniquely identify each charging vehicle.

[0013] When a vehicle is electrically connected to a charging station, the charging station reads the vehicle's identification code. This is usually achieved through the communication interface between the charging station and the vehicle, such as CAN bus or Bluetooth. Based on the identification code read, the charging station retrieves the corresponding health characteristic tag from the network platform.

[0014] Registering vehicle health characteristic tags centrally on an online platform facilitates unified management and maintenance. Different charging stations can obtain vehicle information from this platform, avoiding information fragmentation and confusion. The online platform can serve as an information sharing hub, enabling charging stations, vehicle manufacturers, maintenance personnel, and other relevant parties to access and use this information according to their permissions, thereby improving information utilization efficiency. Since the health status of vehicles changes dynamically, the online platform allows for convenient updates to health characteristic tags, ensuring that the information obtained by charging stations is always up-to-date.

[0015] A unique identification code can accurately identify each charging vehicle. In practical applications, a large number of vehicles may connect to charging stations for charging. Using identification codes can avoid confusion and ensure that the charging station obtains the correct vehicle health characteristic label. The identification code can also serve as an index to associate the vehicle's health characteristic label with other relevant data (such as charging records, maintenance records, etc.), facilitating subsequent data query and analysis.

[0016] When a vehicle is connected to a charging station, timely reading of the identification code ensures that the charging station obtains relevant vehicle information before charging, providing a basis for formulating reasonable charging control strategies. Automated reading of the identification code reduces manual intervention and improves the efficiency and accuracy of charging operations.

[0017] Different vehicles have different health characteristics, such as different battery types and capacities, and their charging needs will also vary. Based on the health characteristic tags obtained, charging stations can develop personalized charging control strategies for each vehicle, improving charging safety and efficiency. The vehicle health status information contained in the health characteristic tags can help charging stations detect potential faults or abnormalities in the vehicle in a timely manner, provide early warnings and handle them in advance, and avoid safety accidents during the charging process.

[0018] In step S2, the power supply performance information and performance degradation risk characteristics of the charging pile in its current state are analyzed using a health feedback model deployed in the charging pile. The power supply performance information may include the charging pile's output power range and voltage stability. The performance degradation risk characteristics involve the probability and related factors of potential charging pile malfunctions or performance degradation. Understanding the current power supply performance information of the charging pile ensures a stable power output during charging, preventing damage to the vehicle battery due to insufficient power or voltage instability. Simultaneously, understanding the performance degradation risk characteristics allows for early prevention of potential charging pile malfunctions, ensuring charging safety. In cases where multiple vehicles are charging simultaneously, power resources can be rationally allocated based on the charging pile's power supply capacity, ensuring each vehicle receives appropriate charging power and improving charging efficiency. Based on the analysis of various health characteristic tags, a list of baseline charging modes and optimized charging management methods for each charging vehicle is obtained. The baseline charging mode is the basic charging method determined according to the vehicle's health characteristic tags, such as constant current charging and constant voltage charging. The list of optimized methods includes optimization measures that can be taken for different vehicle characteristics and charging pile statuses, such as adjusting the charging current and optimizing the charging time. Different vehicles have different health characteristic tags such as battery type, capacity, and health status, requiring different charging modes. Determining the baseline charging mode can provide a basic charging solution for each vehicle, while the list of optimized methods can further optimize the charging process according to actual conditions to meet the personalized needs of the vehicle. By optimizing the charging management method, charging time can be reduced, charging efficiency can be improved, and overcharging or undercharging can be avoided, thus extending the lifespan of the vehicle's battery. Optimize charging management by referring to the list of optimization methods for the baseline charging mode. This step involves selecting appropriate optimization measures from the list and applying them to the baseline charging mode, taking into account the actual conditions of the charging station and the vehicle. The baseline charging mode is just a basic framework; adjustments need to be made based on the performance of the charging station and the real-time status of the vehicle during actual charging. By optimizing the baseline charging mode, the charging process can be made more in line with actual needs, improving charging efficiency.

[0019] Each charging vehicle is assigned an optimization result to form a collaborative execution goal. This means considering the overall situation when multiple vehicles are charging simultaneously, ensuring that the charging optimization schemes of each vehicle can be carried out collaboratively. The execution adaptability of the charging pile to the collaborative execution goal is analyzed based on the power supply performance information to obtain the execution adaptability parameter of the charging pile to the collaborative execution goal. This parameter reflects whether the charging pile can successfully execute the collaborative execution goal under the current power supply capacity.

[0020] Based on the performance degradation risk characteristics, the degradation probability of power supply performance information is analyzed and the degradation status is simulated. Based on the analysis and simulation results, the execution adaptability of the collaborative execution target is analyzed to obtain the execution risk parameter of the charging pile for the collaborative execution target. This parameter takes into account the possible performance degradation of the charging pile and evaluates the feasibility of the collaborative execution target under such circumstances. The execution adaptability parameter and execution risk parameter are used as monitoring conditions to replace the optimization results that make up the collaborative execution target. The executability of the charging pile is evaluated for each optimization result of each charging vehicle. By continuously adjusting the optimization results, it is ensured that the final selected charging control strategy not only conforms to the actual capability of the charging pile, but also reduces the execution risk.

[0021] When multiple vehicles are charging simultaneously, the synergy between their charging schemes needs to be considered. By setting collaborative execution goals and analyzing execution adaptability and risk parameters, it can be ensured that the charging station can provide suitable charging services for multiple vehicles simultaneously. This avoids charging interruptions or malfunctions caused by charging scheme conflicts or insufficient charging station performance. Considering the risk of charging station performance degradation, evaluating and adjusting the optimization results can reduce the probability of malfunctions during charging, ensuring the safety and reliability of charging. Based on the evaluation results, the optimal optimization method is selected to optimize the baseline charging mode, resulting in a charging control strategy for each charging vehicle. This strategy is the best charging scheme determined after comprehensively considering factors such as charging pile performance, vehicle characteristics, and execution risks. By selecting the optimal optimization method based on the evaluation results, various factors can be comprehensively considered to formulate the most suitable charging control strategy for each vehicle, thereby achieving the best balance between charging efficiency, battery life, and charging safety.

[0022] In step S3, based on the charging control strategy of each charging vehicle obtained in the previous steps, the charging pile begins to charge each charging vehicle. This includes accurately delivering electrical energy to the vehicle battery according to parameters such as charging current, voltage, and charging time set according to the strategy. The charging control strategy is formulated based on factors such as the vehicle's health characteristic label and the performance of the charging pile. Charging according to this strategy can ensure that the charging process is carried out within a safe range, avoiding damage to the battery caused by overcharging, over-discharging, overheating, etc., while improving charging efficiency and shortening charging time.

[0023] The electrical performance parameters of the charging vehicle are collected in real time, mainly including voltage, current and temperature data. These data can be collected by sensors between the charging pile and the vehicle. For example, voltage sensors measure the voltage across the battery terminals, current sensors measure the charging current, and temperature sensors measure the temperature of the battery or charging interface. The collected electrical performance parameter data is transmitted to the control system of the charging pile through appropriate communication methods for subsequent processing.

[0024] Voltage, current, and temperature are crucial parameters reflecting the battery status of a charging vehicle. Real-time data collection of these parameters allows for timely monitoring of the battery's charging progress and assessment of whether the charging process is normal. For example, abnormal voltage or current changes may indicate a battery malfunction, while excessively high temperatures can affect battery life or even cause safety incidents. The collected electrical performance parameter data forms the basis for subsequent data processing and analysis, generating monitoring information streams to validate and update the charging pile's health feedback model and the vehicle's health characteristic labels. The collected voltage, current, and temperature performance data undergo frequency domain transformation. Common frequency domain transformation methods, such as Fourier transform, convert the time-domain signal into a frequency-domain signal, allowing analysis of the signal's distribution across different frequency components. Spectral feature vectors are extracted from the frequency-transformed signal. These feature vectors reflect the changing patterns and characteristics of electrical performance parameters, such as the amplitude and phase of certain frequency components. The original electrical performance parameter data may contain a large amount of noise and redundant information. Through frequency domain transformation and feature extraction, useful features can be extracted from the data, more clearly reflecting the battery's state changes. These feature vectors provide more valuable information for subsequent data analysis and fault diagnosis.

[0025] The spectral feature vectors are reduced in dimensionality and fused using the maximum a posteriori probability matrix factorization method. Dimensionality reduction reduces the dimensionality of the data, removes redundant information, and improves the efficiency of data processing. Fusion combines multiple feature vectors into a more representative state monitoring information to more comprehensively reflect the vehicle's charging status. Spectral feature vectors may have high dimensionality, which consumes a lot of computing resources and time to process. Dimensionality reduction can reduce the dimensionality of the data and improve the efficiency of data processing. By fusing multiple feature vectors, information from different aspects can be integrated to generate a more comprehensive and representative state monitoring information that more accurately reflects the vehicle's charging status.

[0026] The status monitoring information for each time period is arranged chronologically to generate a monitoring information stream. This monitoring information stream records the status changes of the charging vehicle throughout the entire charging process. By arranging the status monitoring information for each time period into a monitoring information stream in chronological order, dynamic monitoring of the charging process can be achieved. By analyzing the monitoring information stream, abnormal changes during the charging process can be detected in a timely manner, providing a basis for subsequent charging management decisions. The monitoring information stream is also an important basis for verifying and updating the health feedback model of the charging pile and the health characteristic labels of the vehicle. By comparing the monitoring information stream with the model prediction results or label information, discrepancies can be identified, and the model and labels can then be adjusted and optimized.

[0027] In step S4, electrical performance parameters (such as voltage, current, temperature, etc.) in the monitoring information flow are used in combination with preset evaluation algorithms and rules to evaluate the health status of charging piles and each charging vehicle. For example, the charging and discharging performance of the battery is judged by analyzing the fluctuation of voltage and current, and the heat dissipation of the charging pile and the thermal stability of the vehicle battery are evaluated based on temperature changes. In this way, the health feedback model and each health characteristic label are verified to obtain the error probability characteristics of the health feedback model and each health characteristic label. The error probability characteristics reflect the degree of deviation between the health status predicted by the model and the label and the actual monitored situation.

[0028] As the charging process progresses, the actual health status of the charging station and the vehicle may change. By monitoring the information flow for real-time assessment and verification, deviations between the health feedback model and health characteristic labels and the actual situation can be detected in a timely manner, ensuring the accuracy of the model and labels. Error probability characteristics are the basis for subsequent graded processing. Accurate error assessment can guide the implementation of appropriate handling measures, ensuring the effectiveness of charging management. The error probability characteristics are judged based on preset thresholds to determine whether the error probability characteristics are in the first, second, or third processing level. Different processing levels correspond to different degrees of error, representing different health status deviations and potential risks. Different degrees of error have different impacts on charging safety and efficiency. Through graded processing, different coping strategies can be adopted according to the severity of the error to avoid over-processing or under-processing. For example, small errors can be temporarily adjusted, while larger errors require more in-depth analysis and processing.

[0029] If the error probability characteristic is at the first processing level, it indicates that the error is relatively large and needs to be addressed promptly. In this case, temporary information updates are made to the health feedback model and various health characteristic labels based on the error probability characteristics. For example, the parameters in the model or certain data items in the labels are fine-tuned, and the corresponding charging control strategy is adjusted accordingly, such as slightly adjusting the charging current or voltage. Afterward, the monitoring information flow after the adjustment is continuously tracked, and the decision on whether to retain or eliminate the temporary information update is made based on the subsequent monitoring situation. If the monitoring information flow shows improvement after the adjustment, the update is retained; if there is no improvement or even a deterioration, the update is eliminated. The error at the first processing level is relatively large, and it is necessary to quickly perform temporary information updates and strategy adjustments. This can attempt to improve the charging effect without affecting normal charging. Continuously tracking the monitoring information flow after the adjustment can verify the effectiveness of the adjustment, ensure the correctness of the processing measures, and avoid unnecessary permanent changes.

[0030] If the error probability feature is at the second processing level, it indicates a small error, but there may be a certain risk of health degradation. It is necessary to refer to past risk records to verify whether the current health degradation risk actually exists. Based on the error probability feature, health degradation risk features are generated for charging piles and each charging vehicle, such as battery capacity degradation risk and charging pile power reduction risk. Historical health degradation risk features of charging piles and each charging vehicle are retrieved, and the confidence level of the currently generated health degradation risk features is assessed. By comparing historical data with the current situation, the credibility of the current risk features is determined. Based on the assessment results, it is decided whether to update the health feedback model or various health characteristic labels. If the confidence level is high, an update is performed; if the confidence level is low, observation continues. Errors at the second processing level indicate a potential health degradation risk. Generating health degradation risk features and assessing their confidence level can help determine the authenticity and severity of the risk. Deciding whether to update the model and labels based on the confidence level can avoid unnecessary updates due to misjudgment, and can also promptly identify the real risk and take appropriate measures.

[0031] If the error probability feature is at the third processing level, it means that the error is very small and there is basically no risk of health degradation. Based on the error probability feature, health degradation risk features are generated for the charging pile and each charging vehicle, and these health degradation risk features are recorded. The purpose of recording is to provide a basis for judgment in the subsequent charging process. That is, the accumulated health degradation risk features can prove that the charging pile and each charging vehicle have potential health degradation risks. At the same time, this step is also an auxiliary means to assist the second processing level.

[0032] Beneficially, the health characteristic tags of the charging vehicles are registered on a designated network platform, and the network platform assigns a unique identification code to each registered charging vehicle. When the charging vehicle is electrically connected to the charging pile, the charging pile reads the identification code of the charging vehicle to retrieve the corresponding health characteristic tag from the network platform.

[0033] Vehicle owners or relevant management entities collect various health characteristic information of charging vehicles. This information may include battery type (such as lithium battery, lead-acid battery), battery capacity, battery health status (such as remaining battery life, self-discharge rate, etc.), charging history (including previous charging time, charging power, number of charging times, etc.). This information is organized to ensure its accuracy and completeness. Accurate health characteristic labels are key to developing reasonable charging strategies. Different types and health statuses of batteries have different requirements for parameters such as charging current, voltage, and charging time. For example, the charging characteristics of lithium batteries and lead-acid batteries are very different. Only by providing accurate battery type information can charging stations adopt appropriate charging methods. The organized information is easy for the network platform to store, manage, and analyze. It can statistically analyze a large amount of vehicle charging data, providing data support for subsequent charging management and service optimization.

[0034] Using specific devices or client software, the compiled health characteristic labels are uploaded to a designated network platform. During the upload process, basic vehicle information (such as license plate number, vehicle identification number, etc.) may need to be entered for identity verification to ensure that the information is correctly associated with the corresponding vehicle. The network platform acts as a centralized information storage and management center, enabling different charging piles to access the vehicle's health characteristic labels. This helps to achieve information sharing and improve the overall efficiency and quality of charging services. The network platform also allows for convenient updating and maintenance of the vehicle's health characteristic labels. When the vehicle's battery health status changes or there are new charging history records, updates can be made on the platform in a timely manner to ensure that the information obtained by the charging pile is always up-to-date.

[0035] After receiving the health characteristic tag, the network platform assigns a unique identification code to each registered charging vehicle. This code is usually a string composed of numbers, letters, or a combination of both, and is globally or regionally unique. The unique identification code ensures that each charging vehicle is accurately identified on the network platform. In practical applications, a large number of vehicles may connect to charging piles simultaneously or sequentially. Using the identification code can avoid information confusion and ensure that the charging pile obtains the correct vehicle's health characteristic tag. The identification code can also serve as an index to associate the vehicle's health characteristic tag with other relevant data (such as charging records, maintenance records, etc.), which facilitates data querying and analysis and supports the full lifecycle management of vehicles.

[0036] When a vehicle needs to be charged, it is physically connected to the charging station. While establishing an electrical connection, a communication connection is also established between the two. The communication connection can be achieved through wired (such as CAN bus) or wireless (such as Bluetooth, Wi-Fi). Establishing an electrical connection is a prerequisite for charging, while a communication connection is a necessary condition for the charging station to obtain the vehicle identification code and transmit charging instructions. Only when both are successfully established can subsequent charging operations and data interaction be carried out.

[0037] Charging stations utilize communication interfaces to read the unique identification code from the vehicle being charged. This reading process is typically automated. The charging station sends specific instructions, and the vehicle returns its identification code upon receiving the instructions. Automated identification code reading improves the efficiency and accuracy of charging operations, avoids errors that may occur with manual input, reduces user steps, and enhances the user experience. By acquiring the vehicle's identification code before charging begins, the charging station can obtain the vehicle's health characteristic tags in the shortest possible time, providing a basis for developing personalized charging strategies.

[0038] The charging pile sends a data request to the network platform based on the read identification code. After receiving the request, the network platform looks up the health characteristic tag corresponding to the identification code in its database and returns it to the charging pile. Based on the vehicle's health characteristic tag, the charging pile can formulate a personalized charging strategy for each vehicle. For example, for batteries in poor health, a gentler charging method can be used to extend battery life; for vehicles with high remaining charge, the charging power can be appropriately reduced to avoid overcharging. Understanding the vehicle's health characteristics helps the charging pile monitor the battery status in real time during charging, promptly detect abnormalities, and take corresponding measures to ensure the safety of the charging process.

[0039] Beneficially, the step of performing a collaborative analysis of charging control on each of the health characteristic tags based on the health feedback model deployed in the charging pile to obtain the charging control strategy for each of the charging vehicles includes: S21: Based on the health feedback model deployed in the charging pile, the power supply performance information and performance degradation risk characteristics of the charging pile in the current state are obtained; S22: Based on the analysis of each of the health characteristic labels, obtain a list of the baseline charging mode and the optimization method of charging management for each of the charging piles for each of the charging vehicles; S23: Optimize the charging management of the benchmark charging mode through the optimization method list, and evaluate the feasibility of each optimization result for charging piles based on the power supply performance information and the performance degradation risk characteristics. Based on the evaluation results, select the optimal optimization method to optimize the benchmark charging mode and obtain the charging control strategy for each charging vehicle.

[0040] The health feedback model in a charging pile first collects data related to its own operation. This data may include the charging pile's input voltage, output power, internal circuit temperature, and the operating status of various electrical components. This data can be acquired in real time through various sensors inside the charging pile. Based on the collected data, the health feedback model uses preset algorithms and rules to analyze the charging pile's power supply performance information under the current state. For example, it calculates the charging pile's maximum output power and the stable output voltage range. At the same time, the model also analyzes the charging pile's performance degradation risk, identifies factors that may lead to performance degradation, such as the aging of electrical components and the failure of the heat dissipation system, and derives performance degradation risk characteristics, such as the probability of degradation and the components that may malfunction.

[0041] Understanding the power supply performance of charging stations ensures that they provide stable and appropriate power during charging, preventing damage to vehicle batteries due to insufficient power or unstable voltage. Identifying performance degradation risk characteristics allows for early detection of potential problems, enabling preventative measures and reducing the probability of malfunctions during charging. Furthermore, accurately assessing the power supply capacity of charging stations when multiple vehicles are charging simultaneously helps in the rational allocation of power resources, ensuring each vehicle receives adequate charging power and improving charging efficiency.

[0042] A detailed interpretation of the health characteristic labels of each charging vehicle is conducted to understand information such as battery type, capacity, health status, and charging history. Based on the vehicle's health characteristic labels, combined with industry standards and experience, a baseline charging mode is determined for each charging vehicle. For example, for new lithium battery vehicles, the baseline charging mode may first use constant current charging, and then switch to constant voltage charging when the battery voltage reaches a certain value. Based on the vehicle's health characteristics and charging needs, a list of optimized charging management methods is generated. These optimization methods may include adjusting the magnitude of the charging current, changing the time allocation of charging stages, and adding intermittent charging during the charging process, in order to improve charging efficiency and extend battery life.

[0043] Different vehicles have different battery characteristics and health conditions, requiring different charging modes. Determining a baseline charging mode can provide a basic charging framework for each vehicle, while the list of optimization methods can be further optimized according to the specific conditions of the vehicle to meet its personalized charging needs. By optimizing charging management, charging time can be reduced, charging efficiency can be improved, and overcharging or undercharging can be avoided, thus extending the lifespan of the vehicle's battery.

[0044] By using various optimization methods from the optimization list, the baseline charging mode is tested one by one. For example, the charging current is increased by a certain percentage, or the constant current charging stage is shortened, resulting in multiple optimized charging modes. The baseline charging mode is determined based on general conditions. In actual charging, it may need to be adjusted according to the performance of the charging pile and the real-time status of the vehicle. By optimizing the baseline charging mode, the charging process can be made more in line with actual needs, and the charging effect can be improved.

[0045] For each charging vehicle, an optimized charging mode is selected from the optimization results to form a collaborative execution goal. This means considering the compatibility and synergy between various optimization modes when multiple vehicles are charging simultaneously. Based on the power supply performance information of the charging pile, the collaborative execution goal is analyzed to assess whether the charging pile has sufficient power and voltage to support the collaborative execution goal, thus obtaining execution adaptability parameters, such as the probability that the charging pile can meet the collaborative execution goal. Combining the performance degradation risk characteristics of the charging pile, the degradation probability of the power supply performance information is analyzed and the degradation status is simulated. For example, the simulation shows whether the collaborative execution goal can still be executed smoothly in the case of a failure of a certain electrical component, thereby obtaining execution risk parameters, such as the probability of failure during execution.

[0046] By using adaptive and risk parameters as monitoring conditions, the optimization results that constitute the collaborative execution objective are alternately selected. Different combinations of optimization results are continuously tried, and the feasibility of each optimization result for each charging vehicle with the charging pile is evaluated. Finally, the optimization method that can meet the vehicle charging needs, be effectively executed by the charging pile, and has low risk is selected.

[0047] When multiple vehicles are charging simultaneously, it is necessary to consider the synergy between the charging schemes of each vehicle. By analyzing the execution adaptability parameters and execution risk parameters, it can be ensured that the charging pile can provide appropriate charging services for multiple vehicles at the same time, avoiding charging interruptions or failures caused by charging scheme conflicts or insufficient charging pile performance. Considering the performance degradation risk of the charging pile, evaluating and adjusting the optimization results can reduce the probability of failures during the charging process and ensure the safety and reliability of charging.

[0048] Based on the evaluation results, the optimal optimization method is selected to perform final optimization on the baseline charging mode. The optimized charging mode is then transformed into a specific charging control strategy, including the setting of parameters such as charging current, voltage, and time. This strategy guides the charging piles to charge each vehicle. By selecting the optimal optimization method based on the evaluation results, various factors can be comprehensively considered to formulate the most suitable charging control strategy for each vehicle, thereby achieving the best balance between charging efficiency, battery life, and charging safety.

[0049] Beneficially, the steps for evaluating the feasibility of charging piles based on the power supply performance information and the performance degradation risk characteristics include: S231: Select an optimization result for each of the aforementioned charging vehicles to collectively form a collaborative execution objective; S232: Analyze the execution adaptability of the charging pile to the collaborative execution target based on the power supply performance information to obtain the execution adaptability parameters of the charging pile for the collaborative execution target; S233: Analyze the probability of degradation and simulate the degradation status of the power supply performance information based on the performance degradation risk characteristics, and analyze the execution adaptability of the collaborative execution target based on the analysis and simulation results, so as to obtain the execution risk parameters of the charging pile for the collaborative execution target; S234: Using the execution adaptability parameter and the execution risk parameter as supervision conditions, the optimization results constituting the collaborative execution objective are replaced and selected to evaluate the feasibility of charging piles for each optimization result of each charging vehicle.

[0050] From the multiple optimization results generated for each charging vehicle, one optimization result is selected for each vehicle. These optimization results represent different charging modes or strategy adjustments for each vehicle. The optimization results selected for each charging vehicle are integrated to form a collaborative execution goal. This goal reflects the combination of optimized charging schemes for each vehicle in a scenario where multiple vehicles are charging simultaneously. In actual charging scenarios, multiple vehicles often connect to charging piles at the same time. Forming a collaborative execution goal can comprehensively consider the charging needs of each vehicle, ensure that the optimized charging schemes of each vehicle can cooperate with each other, avoid conflicts between charging schemes, and improve overall charging efficiency.

[0051] The total power, voltage, and other parameters required by the collaborative execution target are compared with the current power supply performance information of the charging pile. For example, if the total output power required by the collaborative execution target is 50kW, and the current maximum stable output power of the charging pile is 60kW, it indicates that there is a certain degree of adaptability in terms of power. Through a series of calculations and evaluations, the execution adaptability parameters of the charging pile for the collaborative execution target are obtained. These parameters can be expressed in the form of percentages, levels, etc., reflecting the degree to which the charging pile can successfully execute the collaborative execution target under the current power supply performance. By analyzing the execution adaptability parameters, it can be determined whether the charging pile has sufficient capacity to execute the collaborative execution target under the current normal state. This helps to avoid the charging process being unable to proceed normally due to insufficient power supply performance of the charging pile, thus ensuring the feasibility and stability of the charging operation.

[0052] Based on the performance degradation risk characteristics of charging piles, an in-depth analysis of power supply performance information is conducted to calculate the probability of power supply performance degradation under various possible degradation conditions. For example, the probability of a 10% reduction in output power due to the aging of a certain electrical component is 20%. The changes in power supply performance of charging piles under different degradation conditions are simulated. For example, the simulation shows how the output power will decrease when the internal temperature of the charging pile rises due to a failure in the heat dissipation system.

[0053] Based on the results of degradation probability analysis and degradation state simulation, the execution adaptability of the collaborative execution target is analyzed again to assess whether the collaborative execution target can still be executed by the charging pile under possible degradation conditions, thereby obtaining the execution risk parameter. This parameter can also be expressed in the form of probability, level, etc., reflecting the degree of execution risk of the collaborative execution target under the condition of charging pile performance degradation.

[0054] Charging piles may experience performance degradation during operation, such as aging of electrical components and poor heat dissipation. Analyzing execution risk parameters can help assess the execution risk of collaborative objectives under these potential degradation conditions in advance. This allows for the full consideration of potential problems when formulating charging strategies, enabling the implementation of corresponding preventive measures and reducing the probability of malfunctions during charging.

[0055] The execution adaptability parameter and execution risk parameter are used as monitoring conditions. For example, a condition is set that the execution adaptability parameter is below 70% or the execution risk parameter is above 30% as a failure to meet the requirements. When the optimization results constituting the collaborative execution objective do not meet the monitoring conditions, the optimization results of some vehicles are replaced. For example, the optimization result originally selected by a vehicle is replaced with another optimization result, a new collaborative execution objective is formed, and the execution adaptability and execution risk are analyzed again on the replaced collaborative execution objective until a collaborative execution objective that meets the monitoring conditions is obtained. This completes the evaluation of the charging pile executability of each optimization result of each charging vehicle.

[0056] By using adaptive and risk parameters as monitoring conditions, and by repeatedly evaluating the optimization results, the most suitable collaborative execution target for the current state and potential risks of the charging pile can be selected. This ensures that the final charging scheme can be executed smoothly under normal conditions and can also resist the risks caused by the performance degradation of the charging pile to a certain extent, thereby improving the reliability and safety of charging management.

[0057] Beneficially, the electrical performance parameters include voltage, current, and temperature. The voltage, current, and temperature performance data of the charging vehicle are collected in real time, and frequency domain transformation and feature extraction are performed on each performance data to obtain a spectral feature vector. The spectral feature vector is then reduced in dimension and fused using the maximum a posteriori probability matrix decomposition method to generate status monitoring information. The status monitoring information for each time period is arranged in time sequence to obtain a monitoring information stream.

[0058] Voltage, current, and temperature sensors are installed in key parts of the charging vehicle. Voltage sensors are typically connected to the positive and negative terminals of the battery to measure the battery voltage. Current sensors are installed in the charging circuit to measure the charging current. Temperature sensors are placed on the battery surface or charging interface and other areas prone to heat to monitor temperature changes. A data acquisition system is used to collect voltage, current, and temperature data in real time at a certain sampling frequency. The sampling frequency is determined based on actual needs and data processing capabilities to ensure accurate capture of data changes.

[0059] Voltage, current, and temperature are key parameters reflecting the state of a vehicle's battery. Real-time acquisition of these data allows for timely understanding of the battery's charging status and determination of whether the charging process is normal. For example, abnormal voltage changes may indicate a battery malfunction, while excessively high temperatures may affect battery life or even cause safety accidents. The collected electrical performance data forms the basis for subsequent frequency domain conversion, feature extraction, and state analysis. Accurate and real-time data can provide a reliable basis for subsequent processing and improve the accuracy of state monitoring.

[0060] The commonly used method for frequency domain transformation of the acquired voltage, current, and temperature time-domain data is the Fast Fourier Transform (FFT). This transforms the time-domain signal into a frequency-domain signal. Through frequency domain transformation, the signal can be decomposed into a combination of different frequency components, thereby allowing a clearer observation of the signal's frequency characteristics. Spectral feature vectors can be extracted from the frequency-domain signal. These feature vectors can include information such as the amplitude, phase, and frequency distribution of different frequency components. For example, the maximum amplitude and average value within a specific frequency range can be extracted as elements of the feature vector.

[0061] Time-domain data often contains significant noise and interference, making it difficult to directly extract useful information. Frequency domain transformation converts the signal to the frequency space, making it easier to identify periodic changes and characteristic frequency components. Feature extraction then extracts the most representative information from the frequency domain signal, providing strong support for subsequent state assessment and fault diagnosis. Spectral feature vectors have clear physical meaning and mathematical representation, facilitating comparison and analysis between different charging vehicles or between different charging stages of the same vehicle. By comparing differences in feature vectors, changes in battery state can be quickly determined.

[0062] The spectral feature vectors are processed using the maximum a posteriori probability matrix factorization method. This method can reduce the dimensionality of high-dimensional spectral feature vectors by considering prior information, removing redundant information while retaining the most important features. The dimensionality-reduced spectral feature vectors are then fused to generate comprehensive status monitoring information. The fusion process can employ methods such as weighted averaging and principal component analysis to merge multiple feature vectors into a more representative vector, thereby comprehensively reflecting the status of the charging vehicle.

[0063] Spectral feature vectors can have high dimensionality, which consumes a lot of computing resources and time to process. Dimensionality reduction can reduce the dimensionality of the data and improve the efficiency of data processing. At the same time, removing redundant information can avoid misjudgment caused by information duplication. By fusing multiple spectral feature vectors to generate comprehensive status monitoring information, different aspects of information can be integrated to more comprehensively reflect the status of charging vehicles. This can avoid the limitations of a single feature vector and improve the accuracy and reliability of status monitoring.

[0064] The status monitoring information for each time period is arranged chronologically to form a monitoring information stream. This information stream records the status changes of the charging vehicle throughout the entire charging process. The monitoring information stream is stored on local storage devices and can also be transmitted to a remote monitoring center via the network for further analysis and processing. By analyzing this information stream, dynamic monitoring of the charging process can be achieved, allowing for the timely detection of abnormal changes and providing a basis for subsequent charging management decisions. Transmitting the monitoring information stream to the remote monitoring center enables centralized monitoring and management of multiple charging piles and charging vehicles. Managers can understand the charging status in real time, promptly handle abnormal events, and improve the quality and safety of charging services.

[0065] Beneficially, the steps for verifying and updating the health feedback model of the charging pile and the health characteristic labels of the charging vehicles based on the monitoring information streams include: S41: The health status of the charging pile and the charging vehicle is evaluated based on the monitoring information flow to verify the health feedback model and the health characteristic label, and to obtain the error probability characteristics of the health feedback model and the health characteristic label. S42: The error probability feature is judged according to a preset threshold to determine whether the error probability feature is in the first processing level, the second processing level or the third processing level; S43: If the error probability feature is in the first processing level, then the health feedback model and each of the health characteristic labels are temporarily updated according to the error probability feature, and the corresponding charging control strategy is adjusted accordingly. Then, the adjusted monitoring information flow is continuously tracked to retain or eliminate the temporary information update. S44: If the error probability feature is in the second processing level, then generate health degradation risk features for the charging pile and each of the charging vehicles according to the error probability feature, and retrieve the historical health degradation risk features of the charging pile and each of the charging vehicles, and evaluate the confidence level of the currently generated health degradation risk features to determine whether to update the health feedback model or each of the health characteristic labels in the future. S45: If the error probability feature is at the third processing level, then generate health degradation risk features for the charging pile and each of the charging vehicles based on the error probability feature, and record the health degradation risk features.

[0066] Data analysis algorithms are used to deeply mine each monitoring information stream. For charging piles, the stability of their output power and voltage fluctuations are analyzed; for charging vehicles, key indicators such as battery voltage, current, temperature change trends and charging efficiency are monitored.

[0067] The analysis results are carefully compared with the expected situations of the charging pile's health feedback model and the health characteristic labels of the charging vehicles. For example, the health feedback model predicts that the output power of the charging pile should be stable within a certain range at a certain time. If the monitoring information stream shows that the actual output power fluctuates too much, there is a discrepancy. Based on the comparison results, the error probability characteristics of the health feedback model and each health characteristic label are calculated by probability statistics. This characteristic can quantify the degree of deviation between the model and the label and the actual situation, such as an error probability of 10%.

[0068] As the charging process progresses, the actual status of the charging piles and charging vehicles will change. By assessing the health status and verifying the information in real time, deviations between the health feedback model and health characteristic labels and the actual situation can be detected in a timely manner, ensuring the accuracy of the model and labels and providing a reliable basis for subsequent decision-making. The error probability characteristics can intuitively reflect the degree of deviation between the model and labels and the actual situation, which is convenient for subsequent graded processing and decision-making.

[0069] Different thresholds are pre-set based on actual needs and experience to classify different processing levels. For example, error probabilities within 5% are classified as the third processing level, 5%-15% as the second processing level, and more than 15% as the first processing level. The calculated error probability characteristics are compared with the preset thresholds to determine the processing level. Different degrees of error have different impacts on charging safety and efficiency. Through graded processing, different coping strategies can be adopted according to the severity of the error to avoid over-processing or under-processing. For example, temporary adjustments can be made for smaller errors, while more in-depth analysis and processing can be carried out for larger errors.

[0070] When the error probability feature is at the first processing level, it indicates a relatively large deviation, requiring timely intervention. Based on the error probability feature, temporary information updates are made to the health feedback model and various health characteristic labels. For example, fine-tuning parameters in the model or certain data items in the labels is performed without permanent modification. Correspondingly, the charging control strategy is adjusted, such as adjusting the charging current based on changes in the actual charging efficiency of the vehicle battery. The adjusted monitoring information stream is continuously collected to observe changes in the status of the charging pile and the charging vehicle. If the monitoring information stream shows an improvement in status, the temporary update is effective and is retained. If the status does not improve or even worsens, the temporary update is eliminated, and the original model and label information are restored. Temporary information updates and strategy adjustments can attempt to improve charging performance without affecting normal charging. Continuous tracking verifies the effectiveness of the adjustments, avoids unnecessary permanent changes, and ensures system stability.

[0071] For the error probability characteristics of the second processing level, health degradation risk characteristics are generated for charging piles and each charging vehicle based on these characteristics. For example, if the analysis reveals abnormal fluctuations in the output power of the charging pile, features such as "unstable output power leading to reduced charging efficiency risk" may be generated. Historical health degradation risk characteristics of the charging piles and each charging vehicle are retrieved. These historical records can reflect the risk development under similar past conditions. The confidence level of the currently generated health degradation risk characteristics is assessed. By comparing the historical records with the current situation, the credibility of the current risk characteristics is determined. For example, if similar power fluctuations in the past have indeed led to reduced charging efficiency, then the confidence level of the current risk characteristics is high. Based on the confidence level assessment results, it is decided whether to update the health feedback model or various health characteristic labels. If the confidence level is high, an update is performed; if the confidence level is low, observation continues without updating. Errors in the second processing level indicate that there may be certain health degradation risks. Generating health degradation risk characteristics and assessing their confidence level can help accurately determine the authenticity and severity of the risks. Deciding whether to update the model and labels based on the confidence level can avoid unnecessary updates due to misjudgments, and can also promptly identify the real risks and take measures.

[0072] For the third processing stage, health degradation risk characteristics are also generated for the charging piles and each charging vehicle based on the error probability characteristics. At this stage, the risk characteristics are usually relatively minor and do not require real-time adjustment. The generated health degradation risk characteristics are recorded in detail, including the specific description of the risk, the probability of occurrence, and the possible scope of impact. These records will serve as an important basis for subsequent repairs, replacement of parts, or vehicle maintenance. At the same time, the records of the third processing stage will serve as the basis for judging the second processing stage when the vehicle is charging in the future. It should be noted that the health degradation risk characteristics generated by the second processing stage will also be recorded as a basis for future judgments.

[0073] Beneficially, it also includes constructing a charging pile layout map for a designated area on a network platform, introducing multiple environmental factors into the charging pile layout map to analyze the theoretical fluctuation characteristics of the electrical performance parameters of the charging vehicles connected to the charging piles in the designated area within a specified time period, and simultaneously monitoring and comparing each of the electrical performance parameters based on the theoretical fluctuation characteristics to generate health assessment information for each charging pile, thereby assisting the monitoring information flow in verifying and updating the health feedback model of the charging piles and the health characteristic labels of each charging vehicle.

[0074] The system collects the geographical location information of all charging piles within a designated area. This information can be obtained through GPS positioning systems or charging pile installation records. Simultaneously, it records basic information for each charging pile, such as type (fast charging, slow charging) and power. Using Geographic Information System (GIS) technology on a network platform, the collected charging pile information is marked on a map to construct a charging pile layout map for the designated area. This map provides a clear understanding of the distribution of charging piles within the designated area, laying the foundation for subsequent analysis and management. Furthermore, the geographical location information of the charging piles is correlated with other relevant information (such as environmental factors and electrical performance parameters) to facilitate comprehensive analysis.

[0075] Identify the environmental factors that need to be introduced. These factors may include weather conditions (temperature, humidity, light, etc.), time factors (daytime, nighttime, weekdays, holidays, etc.), and geographical environment (altitude, terrain, etc.). Data on these environmental factors can be collected through meteorological departments, time recording systems, and other channels. Integrate the environmental factor data with the charging pile layout map so that the map can reflect the distribution of charging piles under different environmental conditions. Environmental factors have a significant impact on the electrical performance parameters of charging vehicles. For example, high temperatures will increase battery temperature, thereby affecting charging efficiency and safety. Introducing environmental factors can more accurately analyze parameter changes during the charging process. By comprehensively considering environmental factors, the analysis of theoretical fluctuation characteristics can be more consistent with reality, improving the accuracy of subsequent health assessments.

[0076] Based on the introduced environmental factors and relevant information about charging piles and charging vehicles, a data analysis model is established. For example, through machine learning algorithms, the influence of different weather conditions and time factors on the electrical performance parameters (voltage, current, temperature) of charging vehicles is analyzed. Using the established model, the electrical performance parameters of charging vehicles connected to charging piles in a specified area are simulated and calculated within a specified time period to obtain theoretical fluctuation characteristics. For example, the fluctuation range of battery temperature and charging current of charging vehicles under high temperature weather is simulated.

[0077] Theoretical fluctuation characteristics can serve as a reference standard to help determine whether the actual electrical performance parameters are normal. Under different environmental conditions, the parameters of charging vehicles will have a certain fluctuation range. By analyzing theoretical fluctuation characteristics, such fluctuations can be predicted in advance. If the actual parameters deviate significantly from the theoretical fluctuation characteristics, it may mean that there are potential problems with the charging pile or charging vehicle, which can be easily detected and dealt with in a timely manner.

[0078] During actual charging, electrical performance parameters of vehicles connected to each charging pile are collected in real time. These parameters can be acquired through sensors in the charging piles and vehicles and transmitted to the network platform. The real-time collected electrical performance parameters are compared and analyzed with theoretical fluctuation characteristics to observe whether the actual parameters are within the theoretical fluctuation range, as well as the magnitude and trend of the deviation. Real-time monitoring of electrical performance parameters can promptly grasp the dynamic changes in the charging process. By comparing with theoretical fluctuation characteristics, abnormal situations can be quickly detected and corresponding measures can be taken. Comparative analysis can verify the accuracy of theoretical fluctuation characteristics and also identify outliers in the actual data, providing reliable data support for subsequent health assessments.

[0079] Based on the comparative analysis results, health assessment indicators are set. For example, if the deviation between actual parameters and theoretical fluctuation characteristics is within a certain range, the charging pile is considered to be in good health; if the deviation exceeds a certain threshold, potential problems are considered. Based on these indicators, health assessment information is generated for each charging pile, such as health level (excellent, good, average, poor) and descriptions of existing problems. This health assessment information quantifies the health status of the charging pile, enabling managers to quickly understand the operational status of each charging pile. It also provides a basis for decisions regarding maintenance and upgrades; for example, charging piles with poor health levels can be prioritized for repair or replacement. The generated health assessment information is integrated with various monitoring information streams, and the results of both are considered comprehensively. For example, if the monitoring information stream shows that the output power of a charging pile is unstable, and the health assessment information also indicates that the charging pile may have a problem in the current environment, the severity of the problem is further confirmed. Based on the integrated information, the health feedback model of the charging pile and the health characteristic labels of each charging vehicle are verified and updated. If it is found that the model and labels deviate significantly from the actual situation, corresponding modifications and adjustments are made. By integrating health assessment information with monitoring information streams, the status of charging piles and charging vehicles can be comprehensively judged from multiple perspectives, improving the accuracy of verification and updates. By continuously verifying and updating the health feedback model and health characteristic labels, the model and labels can be made more consistent with the actual situation, improving the efficiency and safety of charging management.

[0080] like Figure 2As shown, the present invention provides a charging management system for a charging pile, used to implement the charging management method for a charging pile as described in any one of the first aspects, comprising: The tag acquisition module is used to acquire the health characteristic tags of each charging vehicle that is electrically connected to the charging pile. The strategy analysis module is used to perform collaborative analysis of charging control on each of the health characteristic tags based on the health feedback model deployed in the charging pile, so as to obtain the charging control strategy for each of the charging vehicles. The performance monitoring module is used to perform charging processing on each of the charging vehicles through the charging control strategies, and at the same time collect the electrical performance parameters of each of the charging vehicles as a monitoring information stream for each of the charging vehicles. The health verification module is used to verify and update the health feedback model of the charging pile and the health characteristic labels of the charging vehicles based on the monitoring information streams, and to adjust the charging control strategies accordingly.

[0081] In this embodiment, the specific implementation of each module in the above system embodiment is described in the above method embodiment, and will not be repeated here.

[0082] The above description is merely a specific embodiment of the invention, but the scope of protection of the invention is not limited thereto. Any changes or substitutions conceived without creative effort should be included within the scope of protection of the invention.

Claims

1. A charging management method of a charging pile, characterized by, The method comprises: acquiring health characteristic labels of each charging vehicle electrically connected to a charging pile; performing collaborative analysis on each health characteristic label according to a health feedback model deployed in the charging pile to obtain a charging control strategy corresponding to each charging vehicle; performing charging processing on each charging vehicle through each charging control strategy, and collecting electrical performance parameters of each charging vehicle as monitoring information flow of each charging vehicle; verifying and updating the health feedback model of the charging pile and the health characteristic labels of each charging vehicle based on each monitoring information flow, and adjusting each charging control strategy accordingly.

2. The charging management method of claim 1, wherein, The health characteristic labels of the charging vehicles are registered on a designated network platform, and the network platform assigns a unique identification code to each registered charging vehicle. When the charging vehicle is electrically connected to the charging pile, the charging pile reads the identification code of the charging vehicle to retrieve the corresponding health characteristic label from the network platform.

3. The charging management method of claim 1, wherein, The step of performing collaborative analysis on each health characteristic label according to a health feedback model deployed in the charging pile to obtain a charging control strategy corresponding to each charging vehicle comprises: analyzing the health feedback model deployed in the charging pile to obtain electrical energy supply performance information and performance degradation risk characteristics of the charging pile in the current state; analyzing each health characteristic label to obtain a reference charging mode of the charging pile for each charging vehicle and a list of optimization methods for charging management; optimizing the reference charging mode through the list of optimization methods, evaluating the execution feasibility of each optimization result according to the electrical energy supply performance information and the performance degradation risk characteristics, and selecting the optimal optimization method to optimize the reference charging mode based on the evaluation result to obtain the charging control strategy of each charging vehicle.

4. The charging management method of claim 3, wherein, The step of evaluating the execution feasibility of each optimization result according to the electrical energy supply performance information and the performance degradation risk characteristics comprises: selecting one optimization result for each charging vehicle to jointly form a collaborative execution target; analyzing the execution adaptability of the charging pile to the collaborative execution target according to the electrical energy supply performance information to obtain an execution adaptability parameter of the charging pile to the collaborative execution target; analyzing the degradation probability of the electrical energy supply performance information and simulating the degradation condition according to the performance degradation risk characteristics, and analyzing the execution adaptability of the collaborative execution target based on the analysis and simulation results to obtain an execution risk parameter of the charging pile to the collaborative execution target; using the execution adaptability parameter and the execution risk parameter as supervision conditions to replace the optimization results that constitute the collaborative execution target, and evaluating the execution feasibility of each optimization result of each charging vehicle.

5. The charging management method of claim 1, wherein, The electrical performance parameters include voltage, current and temperature, the performance data of voltage, current and temperature of the charging vehicle is collected in real time, and the performance data is subjected to frequency domain conversion and feature extraction to obtain a frequency spectrum feature vector, the frequency spectrum feature vector is subjected to dimension reduction and fusion by a maximum posterior probability matrix decomposition method, state monitoring information is generated, and the state monitoring information of each time period is sequentially arranged to obtain a monitoring information stream.

6. The charging management method of claim 1, wherein, The steps of verifying and updating the health feedback model of the charging pile and the health characteristic label of each charging vehicle based on each monitoring information stream include: The health conditions of the charging pile and each charging vehicle are evaluated based on each monitoring information stream to verify the health feedback model and each health characteristic label, error probability characteristics of the health feedback model and each health characteristic label are obtained; According to a preset threshold, the error probability characteristics are judged to determine whether the error probability characteristics are in a first processing level, a second processing level or a third processing level; If the error probability characteristics are in the first processing level, the health feedback model and each health characteristic label are temporarily updated according to the error probability characteristics, and the corresponding charging control strategy is adjusted, and then the adjusted monitoring information stream is continuously tracked to retain or eliminate the temporary information update; If the error probability characteristics are in the second processing level, health degradation risk characteristics of the charging pile and each charging vehicle are generated according to the error probability characteristics, and the health degradation risk characteristics of the historical records of the charging pile and each charging vehicle are called to evaluate the confidence of the currently generated health degradation risk characteristics to determine whether the health feedback model or each health characteristic label is updated subsequently; If the error probability characteristics are in the third processing level, health degradation risk characteristics of the charging pile and each charging vehicle are generated according to the error probability characteristics, and the health degradation risk characteristics are recorded.

7. The charging management method of claim 1, wherein, Further comprising, constructing a charging pile layout map of a specified area on a network platform, introducing multiple environmental elements into the charging pile layout map to analyze the theoretical fluctuation characteristics of the electrical performance parameters of the charging vehicles electrically connected to the charging piles in the specified area within a specified time period, and simultaneously monitoring and comparing each electrical performance parameter based on the theoretical fluctuation characteristics to generate health evaluation information of each charging pile to assist the verification and update of the health feedback model of the charging pile and the health characteristic label of each charging vehicle by each monitoring information stream.

8. A charging management system of a charging pile, characterized by, A charging management method of a charging pile according to any one of claims 1-7, comprising: a label collection module for obtaining health characteristic labels of each charging vehicle electrically connected to the charging pile; a strategy analysis module for performing cooperative analysis of each health characteristic label according to a health feedback model deployed in the charging pile to obtain a charging control strategy for each charging vehicle; a performance monitoring module configured to perform charging processes on the charging vehicles by using the charging control strategies, and collect electrical performance parameters of the charging vehicles as monitoring information flows of the charging vehicles; a health verification module configured to verify and update a health feedback model of the charging pile and health characteristic labels of the charging vehicles based on the monitoring information flows, and adjust the charging control strategies correspondingly.

Images