International general charging pile and intelligent management system

Abstract

The invention provides an international general charging pile and an intelligent management system, and relates to the technical field of electric vehicle charging piles, and the international general charging pile comprises a multi-standard compatible conversion connector module which is used for integrating conversion connectors of various standards so as to support charging of electric vehicles of different standards on the charging pile; and the connector identification and information transmission module is used for automatically identifying the type of the conversion connector connected to the charging pile through a conversion connector matching algorithm, and if the type of the connector is identified, the type of the connector is transmitted to the automatic adjustment output parameter module. By integrating the functions of the multi-standard compatible adapter, intelligent identification and output adjustment, remote monitoring and management, user-friendly interaction and the like, efficient, convenient and safe charging service is realized, and the charging requirements of electric vehicles with different standards are met.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging piles, and in particular to an internationally universal charging pile and an intelligent management system. Background Art

[0002] Most traditional charging piles can only support a single charging standard, but there are many different charging standards in the electric vehicle market.

[0003] When users drive electric vehicles that do not meet local standards to other countries or regions, they often find it difficult to find suitable charging piles to charge. This problem of incompatible standards has brought great inconvenience to users and also restricted the cross-regional use of electric vehicles.

[0004] In addition, the management methods of traditional charging piles are relatively backward, and the borrowing and returning procedures of conversion connectors are cumbersome and often require manual participation, which not only leads to inefficient management but also increases management costs.

[0005] For example, at some public charging stations, users need to go to the service desk to borrow the adapter and return it to the designated location after charging is completed. This management method not only wastes the user's time, but also brings additional work burden to the managers of the charging station. At the same time, there is a lack of intelligent means for the status monitoring and maintenance of the adapter, which shortens the service life of the adapter and further increases the management cost. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide an internationally universal charging pile and an intelligent management system, which solves the problem of standard incompatibility in the electric vehicle charging pile market.

[0007] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0008] In the first aspect, an international universal charging pile comprises:

[0009] Multi-standard compatible conversion connector module, used to integrate conversion connectors of multiple standards to support charging of electric vehicles of different standards on charging piles;

[0010] The connector identification and information transmission module is used to automatically identify the type of conversion connector connected to the charging pile through the conversion connector matching algorithm. If the connector type is identified, the connector type is transmitted to the automatic output parameter adjustment module;

[0011] Automatically adjust the output parameter module, which is used to automatically detect and intelligently adjust the output current and voltage according to the different standard conversion connectors connected, using the flower pollination algorithm to adapt to the charging needs of different electric vehicles;

[0012] Intelligent management module, which is used to intelligently identify and manage the connector status, and to achieve self-service borrowing and returning of conversion connectors by real-time monitoring of connector usage, location and damage to obtain maintenance reports;

[0013] Remote monitoring module, used to realize remote monitoring, fault diagnosis and data statistical analysis of charging piles through remote servers;

[0014] The user interaction module is used to view the charging status, cost information and operation instructions for borrowing and returning the conversion connector, and supports users to start charging and pay fees.

[0015] Furthermore, the type of the conversion connector connected to the charging pile is automatically identified through the conversion connector matching algorithm. If the connector type is identified, the connector type is transmitted to the automatic output parameter adjustment module, including:

[0016] The sensor at the charging interface of the charging pile continuously monitors the interface status. When the sensor detects that the conversion connector is connected, the built-in camera of the charging pile collects images of the connector and extracts key features in the image, including shape, size and texture, to form a feature vector.

[0017] Compare the feature vector with the standard features in the feature database, calculate the similarity between each standard feature and the feature vector, and determine the matching connector type, i.e., the matching item, based on the similarity;

[0018] The matching items are transmitted to the automatic adjustment output parameter module through the internal communication bus of the charging pile.

[0019] Furthermore, according to the different standard conversion connectors connected, the flower pollination algorithm is used to automatically detect and intelligently adjust the output current and voltage to meet the charging needs of different electric vehicles, including:

[0020] When an electric vehicle is connected to a charging pile, the charging pile's sensor detects the type of adapter connected to identify the charging standard of the electric vehicle;

[0021] Parse the charging standard, obtain the current and voltage ranges and charging speed requirement parameters under the charging standard, and initialize the parameters of the flower pollination algorithm, including population size, number of iterations, and fitness function;

[0022] The final current and voltage combination is searched using a flower pollination algorithm, where each flower represents a current and voltage combination;

[0023] For each flower, the fitness function evaluates the performance of the corresponding flower according to the charging requirements of the electric vehicle, including charging speed, battery protection, and energy efficiency, to obtain the fitness function evaluation result;

[0024] According to the fitness function evaluation results, an iterative search is performed, each flower is continuously adjusted, and the fitness function evaluation and iterative search process is repeated until a preset number of iterations is reached, and the final current and voltage combination is determined according to the fitness value of each flower;

[0025] According to the final current and voltage combination, during the charging process, the charging pile continuously monitors the output of current and voltage and the battery status of the electric vehicle, including power, temperature and internal resistance; if an abnormal situation occurs, including overheating, overcurrent, battery failure, the charging pile immediately takes corresponding protective measures, including reducing output, cutting off power or sounding an alarm;

[0026] When the electric vehicle is fully charged or the user requests to disconnect through the charging pile interface, the charging pile stops outputting current and voltage and completes the charging process to adapt to the charging needs of different electric vehicles.

[0027] Furthermore, the connector status can be intelligently identified and managed, and the use, location and damage of the connector can be monitored in real time to enable self-service borrowing and return of the conversion connector to obtain maintenance reports, including:

[0028] Equip each connector with a unique identifier and initialize basic connector information, including type, specification, production date and initial status;

[0029] Deploy various sensors in the joint usage scenarios, including usage counters, locators, and damage detection sensors, and use sensors to collect joint usage data, location data, and damage data in real time;

[0030] The preset random forest model is used to train and optimize the usage data, location data, and damage data of the joint to obtain the joint status identification results and generate predictive maintenance recommendations;

[0031] When a user selects a borrowed connector through the interactive interface, the user's identity is verified, the connector status is updated to borrowed, and the borrowing time and user information are recorded; when the user returns the connector, the user's identity is verified again, the connector status is updated to available, and the return time and connector usage are recorded;

[0032] Based on real-time and historical data, the joint status is analyzed regularly and a maintenance report is generated. The report content includes joint usage frequency statistics, location distribution map, damage analysis, and predictive maintenance recommendations.

[0033] Furthermore, the preset random forest model is used to train and optimize the usage data, location data, and damage data of the joint to obtain the joint status recognition results and generate predictive maintenance suggestions, including:

[0034] Collect usage data, location data, and damage data of the joint, and divide the collected data into a training set and a test set;

[0035] Based on the training set and test set, build the basic framework of the random forest model and set the parameters of the random forest model, including the number of decision trees, maximum depth, and minimum number of sample splits;

[0036] Use the training set to preliminarily train the random forest model to obtain preliminary training results, and optimize and adjust the random forest model based on the preliminary training results, including increasing or decreasing the number of decision trees and adjusting the feature selection strategy to obtain an optimized random forest model;

[0037] The optimized random forest model is used to predict the test set data. Each decision tree produces a prediction result, and the prediction results of all decision trees are combined to obtain the final joint status identification label.

[0038] Based on the final connector status identification tag, the charging pile's operating data and historical maintenance records, the connector status is analyzed to obtain predictive maintenance recommendations, including recommendations for connector repair, replacement, inspection, and corresponding maintenance time and priority.

[0039] Furthermore, remote monitoring, fault diagnosis and data statistical analysis of charging piles are realized through the remote server, including:

[0040] Based on the operation data of the charging pile, the fault diagnosis model on the remote server is used to predict and diagnose potential faults and generate fault alarm information;

[0041] The remote server collects, organizes and analyzes the operating data of the charging pile, including charging capacity, charging time, connector status, and ambient temperature, and generates various reports and charts, including charging capacity statistics reports and failure rate analysis charts. It also provides customized data statistical analysis services, including charging capacity statistics for a specific time period and failure rate analysis of specific failure types.

[0042] Furthermore, based on the operation data of the charging pile, the potential faults are predicted and diagnosed through the fault diagnosis model on the remote server, and fault alarm information is generated, including:

[0043] Transmit the operation data of the charging pile, including current, voltage, power, temperature, and charging time, to a remote server;

[0044] The fault diagnosis model on the remote server predicts and diagnoses the operation data of the charging pile, and obtains the prediction result of the charging pile status to determine whether the charging pile has an abnormality or fault;

[0045] According to the prediction result of the charging pile status, if the charging pile is detected to have an abnormality or fault, the type of the abnormality or fault is determined, including electrical fault, mechanical fault, and communication fault;

[0046] The causes of the fault are analyzed, including battery aging, poor connector contact, and poor heat dissipation. Based on the type and cause of the fault, the fault diagnosis model generates fault alarm information, including the type of fault, cause of the fault, time of the fault, the identifier of the charging pile, and recommended solutions.

[0047] In the second aspect, an intelligent management system for international universal charging piles includes:

[0048] The charging pile integrates multiple standard conversion connectors to support multiple electric vehicle charging standards;

[0049] When a user borrows a conversion connector, the user can borrow the connector by himself through online payment, so as to intelligently identify and record the borrowing status of the conversion connector;

[0050] The user connects the electric vehicle to the charging pile and selects the corresponding charging standard, which automatically detects the charging requirements of the electric vehicle to obtain the test results;

[0051] According to the detection results, the output parameters of the charging pile, including current and voltage, are intelligently adjusted to suit the selected charging specifications;

[0052] During the charging process, the charging pile continuously monitors the charging status, including key parameters such as current, voltage, and charging time, and handles abnormal situations;

[0053] After charging is completed, the charging pile records the charging data, including charging time, charging amount, electricity consumption information, and generates a corresponding charging report.

[0054] The above solution of the present invention includes at least the following beneficial effects:

[0055] By integrating multiple standard conversion connectors, the charging pile can support multiple electric vehicle charging standards such as national standard, European standard, American standard, Japanese standard and Tesla, which means that no matter which standard electric vehicle the user drives, it can be charged on the charging pile. This improves the convenience of charging and reduces the troubles faced by users due to incompatible charging standards.

[0056] The connector identification and information transmission module can automatically identify the type of the connected conversion connector and pass it to the automatic adjustment output parameter module to ensure the safety and efficiency of the charging process. At the same time, the intelligent management module can intelligently identify and manage the status of the connector, and realize the self-service borrowing and return of the conversion connector by real-time monitoring of the use, location and damage of the connector. This not only improves the utilization rate of the conversion connector, but also reduces management costs and provides users with a convenient charging experience. The generation of maintenance reports also helps to promptly discover and solve potential problems and ensure the long-term stable operation of the charging pile.

[0057] The automatic adjustment output parameter module uses the flower pollination algorithm to automatically detect and intelligently adjust the output current and voltage according to the different standard conversion connectors connected to meet the charging needs of different electric vehicles. This function ensures the safety and efficiency of the charging process and avoids equipment damage or safety accidents that may be caused by current or voltage mismatch.

[0058] The remote monitoring module realizes remote monitoring, fault diagnosis and data statistical analysis of charging piles through remote servers. This enables operators to monitor the operating status of charging piles in real time, discover and handle faults in a timely manner, and improve operation and maintenance efficiency. At the same time, the data statistical analysis function helps operators understand charging needs, optimize resource allocation, and provide strong support for future charging facility construction.

[0059] The user interaction module provides a user-friendly interface, allowing users to easily view charging status, cost information, and operating instructions for borrowing and returning adapters. In addition, the module also supports users to start charging and pay for fees, realizing self-service charging services. This not only improves the user experience, but also helps to improve the utilization rate and service quality of charging piles. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic diagram of an international universal charging pile provided by an embodiment of the present invention.

[0061] Figure 2 It is a flow chart of an intelligent management system for an internationally universal charging pile provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0063] like Figure 1As shown, an embodiment of the present invention provides an international universal charging pile, comprising:

[0064] The multi-standard compatible conversion connector module 11 is used to integrate conversion connectors of multiple standards to support charging of electric vehicles of different standards on charging piles;

[0065] The connector identification and information transmission module 12 is used to automatically identify the type of the conversion connector connected to the charging pile through the conversion connector matching algorithm. If the connector type is identified, the connector type is transmitted to the automatic output parameter adjustment module;

[0066] The automatic output parameter adjustment module 13 is used to automatically detect and intelligently adjust the output current and voltage according to the connected conversion connectors of different standards using the flower pollination algorithm to adapt to the charging requirements of different electric vehicles;

[0067] The intelligent management module 14 is used to intelligently identify and manage the joint status, and to realize the self-service borrowing and returning of the conversion joint by real-time monitoring of the use, location and damage of the joint, so as to obtain a maintenance report;

[0068] The remote monitoring module 15 is used to realize remote monitoring, fault diagnosis and data statistical analysis of the charging pile through a remote server;

[0069] The user interaction module 16 is used to view the charging status, fee information and operation instructions for borrowing and returning the conversion connector, and supports the user to start charging and pay fees.

[0070] In the embodiment of the present invention, the multi-standard compatible conversion connector module 11 improves the versatility of the charging pile, so that electric vehicles of different standards can be charged on the same charging pile, which is convenient for electric vehicle users and reduces the construction cost and maintenance cost of the charging pile, because there is no need to set up a separate charging pile for each electric vehicle standard.

[0071] The connector identification and information transmission module 12 realizes automatic identification of the conversion connector, improves the intelligence level of the charging process, and transmits connector type information quickly and accurately.

[0072] The automatic output parameter adjustment module 13 uses the flower pollination algorithm to automatically detect and intelligently adjust the output current and voltage, ensuring the safety and efficiency of the charging process, adapting to the charging needs of different electric vehicles, and improving the compatibility of charging piles and user satisfaction.

[0073] The intelligent management module 14 realizes intelligent identification and management of the conversion connector, improving the use efficiency and management level of the connector. By real-time monitoring of the connector status, connector damage or abnormal conditions can be discovered and handled in a timely manner, ensuring the smooth progress of the charging process. Supporting self-service borrowing and returning of the conversion connector facilitates user use and reduces the workload of management personnel.

[0074] The remote monitoring module 15 realizes remote monitoring of the charging pile, and can understand the operation status and working conditions of the charging pile anytime and anywhere. It supports fault diagnosis and data statistical analysis, and provides strong support for the maintenance and optimization of the charging pile.

[0075] The user interaction module 16 provides an intuitive and easy-to-use user interface, which allows users to view charging status, cost information, and operation instructions for borrowing and returning conversion connectors. It supports users to start charging and pay for fees, thereby improving the convenience of the charging process and user experience.

[0076] In a preferred embodiment of the present invention, a plurality of standard conversion connectors are integrated to support charging of electric vehicles of different standards on charging piles, which may include:

[0077] First, investigate the mainstream electric vehicle charging standards on the market, such as China's GB / T, Europe's Type 2, North America's SAEJ1772, and Japan's CHAdeMO, etc. According to the survey results, determine the types and quantities of conversion connectors that need to be integrated. Design the charging interface of the charging pile to ensure that it can stably and safely connect to various conversion connectors. Design corresponding conversion connectors for each charging standard to ensure that they can be tightly and safely connected to the charging interface of the charging pile. The conversion connector contains necessary circuits and components to achieve the conversion and transmission of electrical energy. According to the requirements of each charging standard, design the electrical connection and conversion circuit inside the conversion connector to ensure that the conversion connector can accurately convert electrical energy and meet the charging needs of electric vehicles. Set up necessary protection circuits inside the conversion connector, such as overcurrent protection, overvoltage protection, etc., to ensure the safety of the charging process. Considering that the conversion connector may be exposed to harsh environments, its waterproof, dustproof and corrosion resistance should be enhanced.

[0078] Develop unified conversion connector interface standards to ensure that they can be seamlessly connected to the charging interface of the charging pile. Considering possible interface upgrades or changes in the future, the interface design should have certain compatibility and scalability. Design each conversion connector as an independent module to facilitate installation, maintenance and replacement. Set up a connector identification module inside the charging pile to automatically identify the type of connected conversion connector. Based on the identification results, the charging pile can automatically adjust the output parameters to meet the charging needs of different electric vehicles. Establish an intelligent management system to monitor and manage the use of conversion connectors in real time, including usage time, damage, etc.

[0079] In a preferred embodiment of the present invention, the type of conversion connector connected to the charging pile is automatically identified through a conversion connector matching algorithm. If the connector type is identified, the connector type is transmitted to the automatic output parameter adjustment module, which may include:

[0080] The sensor at the charging interface of the charging pile continuously monitors the interface status. When the sensor detects that the conversion connector is connected, the built-in camera of the charging pile collects images of the connector and extracts key features in the image, including shape, size and texture, to form a feature vector.

[0081] Compare the feature vector with the standard features in the feature database, calculate the similarity between each standard feature and the feature vector, and determine the matching connector type, i.e., the matching item, based on the similarity;

[0082] The matching items are transmitted to the automatic adjustment output parameter module through the internal communication bus of the charging pile.

[0083] In an embodiment of the present invention, a variety of sensors are installed inside the charging pile, which can monitor the physical state of the charging interface in real time, such as whether an object is inserted, the depth of insertion, whether the contact is good, etc. The sensor transmits the monitored data to the control unit of the charging pile in the form of an electrical signal. After receiving the signal from the sensor, the control unit determines whether a conversion connector is connected. Once the connector is detected, the control unit triggers the built-in camera of the charging pile to collect images. The camera captures the appearance image of the connector and transmits the image data to the image processing module. After the image processing module receives the image data from the camera, it uses the image processing algorithm to analyze the image and extract key features in the image, such as the shape and contour of the connector, size, and surface texture. These features are encoded into feature vectors.

[0084] The charging pile has a feature database stored inside, which contains the feature vectors of various standard conversion connectors. The image processing module compares the extracted feature vectors with the standard features in the database one by one. During the comparison process, the image processing module calculates the similarity between each standard feature and the feature vector. The calculated similarity value is used to determine which standard feature matches the current feature vector.

[0085] The image processing module determines the standard feature that best matches the current feature vector based on the calculated similarity value. The connector type corresponding to this standard feature is the match. Once the match is determined, the image processing module passes the information of the match to the automatic output parameter adjustment module through the communication bus inside the charging pile. The communication bus can be a CAN bus, Ethernet, etc., which is used for data transmission between the modules inside the charging pile.

[0086] Assume that the charging pile supports two charging standards: China GB / T and Europe Type 2. Sensors and cameras are installed at the charging interface of the charging pile. When an electric car that supports the GB / T standard is connected to the charging pile, the sensor detects that the connector is plugged in, and the camera starts to collect images of the connector. The image processing module extracts the feature vector of the connector, including its unique shape, size, and texture. The feature vector is compared with the standard features in the feature database, and it is found that the feature vector with the GB / T standard has the highest similarity. Therefore, the match is determined to be the GB / T standard. The match is passed to the automatic output parameter adjustment module through the communication bus, and the module automatically adjusts the charging current and voltage according to the GB / T standard.

[0087] After automatically identifying the type of conversion connector, the charging pile can quickly adjust the output parameters, reduce user waiting time, and improve charging efficiency. Supporting automatic identification of conversion connectors of multiple charging standards allows the charging pile to be compatible with more types of electric vehicles and expand the scope of charging services. By accurately matching the type of conversion connector, the charging pile can ensure that the output parameters match the charging needs of the electric vehicle and avoid safety hazards such as overcharging and overcurrent. The automatic identification and adjustment function reduces the need for manual intervention and reduces the maintenance cost and workload of the charging pile. Users do not need to manually select the charging standard, and the charging pile can automatically identify and adjust, which improves the user's convenience and satisfaction.

[0088] In a preferred embodiment of the present invention, the calculation formula for the similarity between each standard feature and the feature vector is:

[0089]

[0090] Among them, S represents the similarity between two feature vectors; a, b, h represent adjustment parameters; n represents the dimension of the feature vector; i represents the index variable; v i represents the component of the eigenvector v in the i-th dimension; v s,i represents the standard eigenvector v s The component in the i-th dimension; y represents the power parameter of the logarithmic transformation term; e represents the base of the natural logarithm; f represents the coefficient parameter of the exponential transformation term; θ represents a non-zero constant; z represents the power parameter of the fractional transformation term.

[0091] In the embodiment of the present invention, the feature vector v to be compared and the standard feature vector v are determined s . Both vectors have n dimensions, where n is the dimension of the feature vector.

[0092] For each dimension i (from 1 to n), compute the eigenvector v and the normalized eigenvector v s The square of the difference in this dimension, that is, (v i -v s,i) 2 , sum the squares of the differences in all dimensions to get the square of the Euclidean distance Taking the square root of this sum gives the Euclidean distance Logarithmically transform the Euclidean distance, adding 1 first to avoid the case where the logarithm is undefined

[0093] Raising the logarithmic result to the power y is Multiply the result by the adjustment parameter a to get Euclidean distance Multiply by the coefficient parameter f and calculate the exponential of the product Multiply the result by the adjustment parameter b to get

[0094] Euclidean distance Dividing by itself plus a nonzero constant θ gives Raising the result to the power z yields Multiply the result by the adjustment parameter h to get Add the above three transformation results to get the denominator Take the reciprocal of the denominator to get the similarity S.

[0095] By combining logarithmic, exponential and fractional transformations, the formula can fully capture various similarity characteristics between feature vectors, including nonlinear relationships and small differences. The adjustment parameters a, b, h, power parameters y, z and coefficient parameters f, θ provide a high degree of flexibility, where the sum of a, b, h is equal to 1, where a = 0.3, b = 0.3, h = 0.4, where power parameters y = 2, z = 2, coefficient parameters f = 2, θ = 0.1; By adjusting the parameters, the formula can adapt to different data distributions and feature vector comparison tasks, and can work effectively for both high-dimensional sparse vectors and low-dimensional dense vectors. The fractional transformation term provides a smooth transition, so that the similarity changes gradually between close and long distances, avoiding abrupt changes in the similarity curve.

[0096] In a preferred embodiment of the present invention, according to the connected conversion connectors of different standards, the output current and voltage are automatically detected and intelligently adjusted using the flower pollination algorithm to adapt to the charging requirements of different electric vehicles, which may include:

[0097] When an electric vehicle is connected to a charging pile, the charging pile's sensor detects the type of adapter connected to identify the charging standard of the electric vehicle;

[0098] Parse the charging standard, obtain the current and voltage ranges and charging speed requirement parameters under the charging standard, and initialize the parameters of the flower pollination algorithm, including population size, number of iterations, and fitness function;

[0099] The final current and voltage combination is searched using a flower pollination algorithm, where each flower represents a current and voltage combination;

[0100] For each flower, the fitness function evaluates the performance of the corresponding flower according to the charging requirements of the electric vehicle, including charging speed, battery protection, and energy efficiency, to obtain the fitness function evaluation result;

[0101] According to the fitness function evaluation results, an iterative search is performed, each flower is continuously adjusted, and the fitness function evaluation and iterative search process is repeated until a preset number of iterations is reached, and the final current and voltage combination is determined according to the fitness value of each flower;

[0102] According to the final current and voltage combination, during the charging process, the charging pile continuously monitors the output of current and voltage and the battery status of the electric vehicle, including power, temperature and internal resistance; if an abnormal situation occurs, including overheating, overcurrent, battery failure, the charging pile immediately takes corresponding protective measures, including reducing output, cutting off power or sounding an alarm;

[0103] When the electric vehicle is fully charged or the user requests to disconnect through the charging pile interface, the charging pile stops outputting current and voltage and completes the charging process to adapt to the charging needs of different electric vehicles.

[0104] In an embodiment of the present invention, when the charging pile is started, all sensors are initialized, including sensors for detecting the type of conversion connector. The charging interface is continuously monitored to detect whether the electric vehicle is connected. Once the connection is detected, the sensor reads the physical or electronic identification of the conversion connector, identifies the type of conversion connector through a built-in database or communication protocol, and then determines the charging standard of the electric vehicle. According to the identified conversion connector type, the corresponding charging standard is retrieved from the database or standard protocol, including the current and voltage range, charging speed requirements, etc. The parameters of the flower pollination algorithm are set, including the population size (i.e., the number of candidate current and voltage combinations), the number of iterations (the number of cycles of the search process), and the fitness function (an indicator for evaluating the performance of the current and voltage combination). The initial population is randomly generated or generated based on historical data, and each individual represents a current and voltage combination. For each individual, the fitness function is used to evaluate its performance, taking into account factors such as charging speed, battery protection, and energy efficiency. According to the fitness evaluation results, the flower pollination algorithm (such as global and local pollination strategies) is applied to adjust the individuals in the population to generate new current and voltage combinations. Fitness evaluation and iterative search are performed cyclically until the preset number of iterations is reached. The population is sorted according to the fitness value of each individual, and the individual with the highest fitness is selected as the final current and voltage combination.

[0105] During the charging process, the current and voltage outputs as well as the battery status (charge, temperature, internal resistance) of the electric vehicle are continuously monitored. Thresholds are set to detect abnormal conditions such as overheating, overcurrent, or battery failure. Once an abnormality is detected, protective measures are immediately taken, such as reducing output, cutting off power, or sounding an alarm, to ensure charging safety. The battery charge is monitored to determine whether the charging completion conditions are met, and respond to disconnection requests from the user through the charging pile interface. When the charging completion conditions are met or the user requests, the current and voltage outputs are stopped to complete the charging process.

[0106] Assume that an electric car supporting the CCS1 standard is connected to a charging pile. The sensor of the charging pile detects the connection and identifies that the adapter is of CCS1 type. The charging pile retrieves the charging parameters of the CCS1 standard from the database and learns that the maximum current supported is 125A, the voltage range is 200V-500V, and fast charging is supported. The population size of the flower pollination algorithm is set to 50, the number of iterations is 100, and the fitness function comprehensively considers the charging speed, battery temperature, and internal resistance changes. The algorithm starts iterative search. In each iteration, the impact of each current and voltage combination on the battery charging speed and safety is evaluated, and the combination is adjusted to optimize the fitness. After 100 iterations, the current and voltage combination with the highest fitness (such as 100A, 400V) is selected as the final output. During the charging process, the charging pile continuously monitors the output and battery status. When the battery temperature is close to the safety upper limit, the output is automatically reduced to protect the battery. When the battery power reaches 90%, the charging pile stops output and charging is completed.

[0107] The flower pollination algorithm automatically searches for the optimal current and voltage combination, realizing the intelligentization and automation of the charging process and improving the charging efficiency and safety. It can identify and adapt to the charging standards of different electric vehicles, ensuring the wide compatibility and adaptability of charging piles. By optimizing the current and voltage combination, energy waste is reduced and energy efficiency in the charging process is improved. Real-time monitoring and anomaly detection mechanisms ensure the safety of the charging process and effectively prevent safety risks such as overheating, overcurrent and battery failure. It quickly responds to user requests and provides convenient charging services, improving user experience and satisfaction. By collecting and analyzing charging data, algorithm parameters and charging strategies can be continuously optimized to further improve charging efficiency and safety.

[0108] In a preferred embodiment of the present invention, the calculation formula of the fitness function is:

[0109]

[0110] w 1 、w 2 、w 3 、w 4 、w 5 Represents the weight coefficient, for example, it can be: w 1 =0.2, w 2 =0.2, w 3 =0.1, w 4 =0.3, w 5 =0.2; α, β, γ, δ, ∈ represent exponential parameters, for example, they may be: α=2, β=3, γ=2, δ=4, ∈=2; V a Indicates the current charging voltage; V max Indicates the maximum voltage under the charging standard; Tb Indicates the current battery temperature; T o Indicates the target operating temperature of the battery; T r Indicates the acceptable range of battery temperature; I o Indicates the current output current; I max Indicates the maximum current under the charging standard; E c Indicates the energy consumed; E t Represents the total energy capacity of the battery; R b Indicates the current internal resistance of the battery; R max Indicates the maximum acceptable value of the battery's internal resistance.

[0111] In the embodiment of the present invention, the weight coefficient w is initialized according to the charging standard and the characteristics of the electric vehicle. 1 、w 2 、w 3 、w 4 、w 5 And exponential parameters α, β, γ, δ, ∈. These parameters need to be fine-tuned based on actual tests and experience. Set the maximum voltage V under the charging standard max , Maximum current I max 、Battery target operating temperature T o , Acceptable range of battery temperature T r , the total energy capacity of the battery E t and the maximum acceptable value of the battery internal resistance R max During the charging process, the charging pile continuously collects the current charging voltage V a 、Current output current I o 、Current battery temperature T b , the energy consumed E c and the battery current internal resistance R b . Using the collected real-time data and initialized parameters, calculate the fitness function F:

[0112] Voltage Adaptability Section Evaluates how well the current voltage is being utilized relative to the maximum voltage.

[0113] Temperature adaptation part Evaluate how close the battery temperature is to the target temperature, taking into account the temperature acceptance range.

[0114] Current adaptability part Evaluates the current utilization relative to the maximum current and acts as a negative term to limit excessive current.

[0115] Energy efficiency fitness part The ratio of consumed energy to total energy is evaluated and used as a negative term to encourage efficient charging.

[0116] Internal resistance adaptability part Evaluates the battery's current internal resistance relative to the maximum acceptable value.

[0117] The fitness value of each part is calculated according to the weight coefficient w 1 、w 2 、w 3 、w 4 、w 5 The weighted sum is used to obtain the final fitness function value F. In each iteration of the flower pollination algorithm, the calculated fitness function value F is used to evaluate the performance of each current and voltage combination. According to the fitness evaluation results, the current and voltage combination is adjusted to search for a better solution. According to the searched optimal current and voltage combination, the output of the charging pile is adjusted to meet the charging needs of the electric vehicle. By comprehensively considering multiple factors such as voltage, current, temperature, energy efficiency and internal resistance, the fitness function can guide the algorithm to search for a better current and voltage combination, thereby improving the charging efficiency. The temperature and internal resistance parts of the fitness function can ensure that the battery maintains a suitable temperature and internal resistance range during the charging process, which helps to extend the battery life and maintain battery performance.

[0118] By identifying the charging standards of different electric vehicles and adjusting the charging parameters according to the standards, charging piles can be compatible with a variety of electric vehicles and improve the utilization rate of charging facilities. The current and temperature parts of the fitness function can limit excessive current and temperature, prevent safety accidents during charging, and ensure the safety of the charging process. By considering energy efficiency factors, the fitness function can guide the algorithm to search for more energy-saving charging solutions, reduce energy waste, and improve energy efficiency. By intelligently adjusting charging parameters, charging piles can provide faster and safer charging services, improving user experience and satisfaction. At the same time, compatibility with charging standards for a variety of electric vehicles also helps to improve the convenience and ease of use of charging facilities.

[0119] In a preferred embodiment of the present invention, the connector status is intelligently identified and managed, and the use, location and damage of the connector are monitored in real time to achieve self-service borrowing and returning of the conversion connector to obtain a maintenance report, which may include:

[0120] Equip each connector with a unique identifier and initialize basic connector information, including type, specification, production date and initial status;

[0121] Deploy various sensors in the joint usage scenarios, including usage counters, locators, and damage detection sensors, and use sensors to collect joint usage data, location data, and damage data in real time;

[0122] The preset random forest model is used to train and optimize the usage data, location data, and damage data of the joint to obtain the joint status identification results and generate predictive maintenance recommendations;

[0123] When a user selects a borrowed connector through the interactive interface, the user's identity is verified, the connector status is updated to borrowed, and the borrowing time and user information are recorded; when the user returns the connector, the user's identity is verified again, the connector status is updated to available, and the return time and connector usage are recorded;

[0124] Based on real-time and historical data, the joint status is analyzed regularly and a maintenance report is generated. The report content includes joint usage frequency statistics, location distribution map, damage analysis, and predictive maintenance recommendations.

[0125] In an embodiment of the present invention, a database table is designed to store a unique identifier (such as a QR code, RFID tag, etc.) and basic information (type, specification, production date, initial state, etc.) of the connector. When the connector is produced or put into storage, a unique identifier is assigned to each connector, and its basic information is entered into the database. According to the needs of the connector usage scenario, a suitable sensor type (such as a usage counter, a locator, a damage detection sensor, etc.) is selected. The sensor is installed on the connector or related equipment, and it is ensured that the sensor can work normally, and the usage data, location data and damage data of the connector are collected in real time.

[0126] Write a sensor data acquisition program to read data from the sensor periodically or in real time. Send the collected data to the data processing center for storage and analysis. Collect historical data, including usage data, location data, and damage data of the joint, as well as the corresponding joint status labels. Use this data to train the random forest model, adjust the model parameters to optimize performance, and deploy the trained model to the data processing center for real-time prediction of the joint status. When new sensor data is received, use the trained random forest model to make predictions and obtain the joint status recognition results. Generate predictive maintenance recommendations (such as regular inspections, replacement of parts, etc.) based on the joint status recognition results and preset rules.

[0127] On the production line, each joint is labeled with a QR code that contains the joint's unique identifier and basic information. Usage counters, locators, and damage detection sensors are installed at key locations on the production line. The usage counter records the number of times the joint is used, the locator tracks the joint's position in real time, and the damage detection sensor monitors the physical condition of the joint. The sensor data acquisition program periodically reads data from the sensor and sends the data to the data processing center. The random forest model is trained using historical data, and the model performance is continuously optimized based on new data. When new sensor data is received, the model predicts the state of the joint (such as normal, damaged, about to be damaged, etc.) and generates maintenance recommendations based on the state (such as immediate replacement, regular inspection, etc.).

[0128] Through automated and intelligent joint management, the need for manual intervention is reduced and management efficiency is improved. Through predictive maintenance suggestions, joint problems can be discovered and handled in a timely manner, avoiding production interruptions and additional repair costs caused by joint failures. Real-time monitoring of the status of joints can timely discover and handle potential safety hazards, ensuring the safe operation of the production line. By analyzing the frequency of use and location distribution of joints, the layout and use strategy of joints can be optimized to improve the utilization rate of joints. The self-service borrowing and returning function allows users to obtain and return joints conveniently and quickly, improving the user experience. By collecting and analyzing joint data, strong data support can be provided for management decisions, helping management make more informed decisions.

[0129] In another preferred embodiment of the present invention, the usage data, location data and damage data of the joint are trained and optimized by a preset random forest model to obtain a joint state recognition result and generate a predictive maintenance suggestion, which may include:

[0130] Collect usage data, location data, and damage data of the joint, and divide the collected data into a training set and a test set;

[0131] Based on the training set and test set, build the basic framework of the random forest model and set the parameters of the random forest model, including the number of decision trees, maximum depth, and minimum number of sample splits;

[0132] Use the training set to preliminarily train the random forest model to obtain preliminary training results, and optimize and adjust the random forest model based on the preliminary training results, including increasing or decreasing the number of decision trees and adjusting the feature selection strategy to obtain an optimized random forest model;

[0133] The optimized random forest model is used to predict the test set data. Each decision tree produces a prediction result, and the prediction results of all decision trees are combined to obtain the final joint status identification label.

[0134] Based on the final connector status identification tag, the charging pile's operating data and historical maintenance records, the connector status is analyzed to obtain predictive maintenance recommendations, including recommendations for connector repair, replacement, inspection, and corresponding maintenance time and priority.

[0135] In an embodiment of the present invention, the usage data (such as the number of charging times, charging time, charging current, etc.), location data (such as the specific location of the connector on the charging pile) and damage data (such as the time of connector damage, damage type, etc.) of the connector are collected through the sensor of the charging pile. The collected data is cleaned to remove outliers, duplicate values, etc. to ensure the accuracy and consistency of the data. The cleaned data is divided into a training set and a test set according to a certain ratio. The training set is used for model training and parameter optimization, and the test set is used for model verification and performance evaluation. Initialize an empty random forest model framework, define a set of decision trees in the framework, and store multiple decision trees generated during the training process. Set the basic parameters of the random forest model, which will affect the training process and final performance of the model. For example, the number of decision trees determines the integration scale of the model, the maximum depth controls the complexity of the tree, and the minimum number of sample splits prevents overfitting.

[0136] The random forest model is initially trained using the training set data. During the training process, each decision tree splits and grows according to the input features (joint usage data, location data, damage data) and labels (joint status). The performance of the initially trained model is evaluated using the test set data, and the model's accuracy, recall, F1 score and other indicators are calculated. Based on the preliminary training results and performance evaluation indicators, the random forest model is optimized and adjusted. For example, if the model's accuracy is low, you can consider increasing the number of decision trees or adjusting the feature selection strategy; if the model's complexity is too high, you can consider reducing the maximum depth of the decision tree or increasing the minimum number of sample splits.

[0137] The optimized random forest model is used to predict the test set data. Each decision tree independently obtains a prediction result (i.e., joint status label) based on the input features. The prediction results of all decision trees are combined and weighted average is used to obtain the final joint status identification label. The weighted average method refers to the weighted average of the prediction results according to the weight of each decision tree.

[0138] Combined with the final connector status identification tag, the operating data of the charging pile (such as current, voltage, charging time, etc.) and historical maintenance records, the connector status is deeply analyzed. For example, if the connector status is identified as damaged, it is necessary to further analyze the type, cause and possible consequences of the damage. Generate predictive maintenance recommendations based on the analysis results and actual conditions. For example, if the connector is severely damaged, it is recommended to replace it immediately; if the connector has minor damage or signs of aging, regular inspection and maintenance can be recommended; if the connector status is normal, it can be recommended to perform routine inspections as planned. At the same time, the corresponding maintenance time and priority need to be determined based on the urgency and importance of the maintenance.

[0139] Assume that the charging station is equipped with a variety of sensors to collect the usage data (such as the number of charges and the charging time), location data (such as the location of the connector in the charging station), and damage data (such as whether the connector is damaged and the degree of damage) of the connector in real time. Use the collected data as the training set, set the parameters of the random forest model (such as the number of decision trees = 100, the maximum depth = 10, and the minimum number of sample splits = 2), and perform preliminary training on the model. According to the preliminary training results, it is found that the model has a low accuracy rate when identifying slightly damaged connectors. Therefore, the number of decision trees is increased to 200, the feature selection strategy is adjusted, redundant features are removed, and the model is retrained. The optimized model is used to predict the test set data and obtain the connector status identification label. Compared with the real label of the test set, it is found that the accuracy of the model has increased to 95%. Based on the connector status identification label, the operation data of the charging pile, and the historical maintenance records, predictive maintenance recommendations are generated. For example, for connectors that are identified as about to be damaged, it is recommended to inspect and maintain them before the next charge; for connectors that are already damaged, it is recommended to replace them immediately.

[0140] By optimizing the parameters and feature selection strategy of the random forest model, the accuracy of connector status identification is improved, and the cases of misjudgment and missed judgment are reduced. Through predictive maintenance suggestions, connector problems can be discovered and handled in a timely manner, avoiding charging interruptions and additional repair costs caused by connector failures. Accurate identification of connector status can ensure the normal operation of charging piles, reduce charging delays and waiting time caused by connector problems, and improve charging efficiency. Timely detection and handling of damaged connectors can avoid safety accidents caused by connector failures and ensure the safety of users and charging stations. By analyzing connector status identification tags, charging pile operation data, and historical maintenance records, strong data support can be provided for management decisions, helping management make more informed decisions.

[0141] In a preferred embodiment of the present invention, remote monitoring, fault diagnosis and data statistical analysis of charging piles are realized through a remote server, which may include:

[0142] Based on the operation data of the charging pile, the fault diagnosis model on the remote server is used to predict and diagnose potential faults and generate fault alarm information;

[0143] The remote server collects, organizes and analyzes the operating data of the charging pile, including charging capacity, charging time, connector status, and ambient temperature, and generates various reports and charts, including charging capacity statistics reports and failure rate analysis charts. It also provides customized data statistical analysis services, including charging capacity statistics for a specific time period and failure rate analysis of specific failure types.

[0144] In an embodiment of the present invention, the charging pile sends operating data (such as charging amount, charging time, connector status, ambient temperature, etc.) to a remote server in real time through a built-in communication module (such as 4G / 5G, Wi-Fi, etc.). The remote server is provided with a data receiving interface to ensure that the data sent by the charging pile can be received stably and efficiently. A fault diagnosis model is deployed on the remote server, and the fault diagnosis model is trained using historical fault data to optimize the model parameters and improve the prediction and diagnosis capabilities of the model. When the operating data of the charging pile is received, the data is input into the fault diagnosis model, and the model predicts and diagnoses potential faults and generates fault alarm information.

[0145] According to the output of the fault diagnosis model, determine whether the charging pile has potential faults. If there is a fault, generate fault alarm information, including detailed information such as fault type, fault level, and fault location. Send the fault alarm information to relevant personnel in a timely manner through SMS, email, APP push, etc. for timely processing. The remote server cleans and preprocesses the received charging pile operation data to remove outliers and noise to ensure data quality. The cleaned data is sorted according to specific formats and rules and stored in the database. Use data analysis tools or algorithms to analyze the sorted data and mine valuable information in the data. Based on the results of data analysis, generate various reports and charts, such as charging quantity statistics reports, failure rate analysis charts, etc. Reports and charts should clearly and intuitively display the operation and failure conditions of the charging pile, so that relevant personnel can understand and analyze them.

[0146] The remote server provides a customized data statistics and analysis service interface, allowing users to select specific time periods, fault types and other parameters for query according to their needs. The server screens and analyzes the data in the database based on the parameters selected by the user and generates corresponding reports and charts. The generated reports and charts are returned to the user through the API interface or Web page.

[0147] The charging piles in the charging station send the operation data to the remote server in real time through the 4G network. A fault diagnosis model based on random forest is deployed on the remote server, which is trained with historical fault data. When the operation data of the charging pile is received, the model predicts and diagnoses the potential fault. If the fault diagnosis model finds that the charging pile has a potential fault (such as battery overheating, charging interface damage, etc.), a fault alarm message is generated and sent to the manager of the charging station via SMS. The remote server cleans, organizes and analyzes the received charging pile operation data to mine valuable information in the data. Based on the results of the data analysis, a charging capacity statistical report and a fault rate analysis chart are generated. The report shows the daily charging capacity changes of the charging station, and the chart shows the distribution of the fault rate of different types of faults. The charging station manager can select a specific time period and fault type for query through the web page of the remote monitoring system. For example, they can select battery overheating faults in the past month for query, and the server will generate corresponding reports and charts based on the selection.

[0148] Through remote monitoring and fault diagnosis models, potential faults of charging piles can be discovered in time, and fault alarm information can be generated, which improves the fault response speed and reduces the charging interruption time caused by faults. Through data analysis and customized services, the operation and fault conditions of charging piles can be understood more accurately, and targeted maintenance suggestions can be provided to maintenance personnel, reducing maintenance costs. Accurately identifying the fault conditions of charging piles can ensure the normal operation of charging piles, reduce charging delays and waiting time caused by faults, and improve charging efficiency. Timely discovery and handling of potential faults of charging piles can avoid safety accidents caused by faults and ensure the safety of users and charging stations. Through data analysis and report generation, strong data support can be provided for the management decisions of charging stations, helping management to make more informed decisions, such as optimizing the layout of charging piles and improving charging efficiency.

[0149] In another preferred embodiment of the present invention, predicting and diagnosing potential faults through a fault diagnosis model on a remote server and generating fault alarm information may include:

[0150] Transmit the operation data of the charging pile, including current, voltage, power, temperature, and charging time, to a remote server;

[0151] The fault diagnosis model on the remote server predicts and diagnoses the operation data of the charging pile, and obtains the prediction result of the charging pile status to determine whether the charging pile has an abnormality or fault;

[0152] According to the prediction result of the charging pile status, if the charging pile is detected to have an abnormality or fault, the type of the abnormality or fault is determined, including electrical fault, mechanical fault, and communication fault;

[0153] The causes of the fault are analyzed, including battery aging, poor connector contact, and poor heat dissipation. Based on the type and cause of the fault, the fault diagnosis model generates fault alarm information, including the type of fault, cause of the fault, time of the fault, the identifier of the charging pile, and recommended solutions.

[0154] In an embodiment of the present invention, the built-in sensor of the charging pile collects operating data such as current, voltage, power, temperature, and charging time in real time. The charging pile packages the collected operating data according to a predefined protocol and format through a built-in communication module (such as 4G / 5G, Wi-Fi, etc.). The packaged data is transmitted to the remote server through the network. The server sets a data receiving interface to ensure that the data sent by the charging pile can be received stably and efficiently. The fault diagnosis model is deployed on the remote server. The fault diagnosis model is pre-trained using a large amount of historical charging pile operation data and corresponding fault labels to optimize model parameters and improve the prediction and diagnosis capabilities of the model. When the operating data of the charging pile is received, the server inputs the data into the fault diagnosis model, and the model predicts and diagnoses the status of the charging pile to obtain the prediction result of the charging pile status.

[0155] The fault diagnosis model determines whether the charging pile has an abnormality or fault based on the prediction results. If the prediction results show that the charging pile is abnormal or has a fault, the next step is to analyze the fault type and cause. The fault diagnosis model further analyzes the type of abnormality or fault based on the operation data and prediction results of the charging pile. Fault types include electrical faults (such as overcurrent, overvoltage, short circuit, etc.), mechanical faults (such as connector damage, transmission component wear, etc.), and communication faults (such as data loss, communication interruption, etc.). Combined with the operation data and fault type of the charging pile, the fault diagnosis model analyzes the specific cause of the fault. Electrical faults may be caused by battery aging, circuit short circuit, etc.; mechanical faults may be caused by poor connector contact, transmission component wear, etc.; communication faults may be caused by network instability, equipment failure, etc. According to the fault type and cause, the fault diagnosis model generates fault alarm information, which includes the fault type, fault cause, time of fault occurrence, identifier of the charging pile (such as serial number, location information, etc.) and recommended solutions (such as replacing the battery, checking the connector, restarting the device, etc.). The fault alarm information is sent to relevant personnel in a timely manner through SMS, email, APP push, etc., so that they can be handled in time.

[0156] The charging piles in the charging station transmit operating data such as current, voltage, power, temperature, and charging time to the remote server in real time through the 4G network. A neural network-based fault diagnosis model is deployed on the remote server. When the operating data of the charging pile is received, the model predicts and diagnoses the status of the charging pile and finds that the current of a certain charging pile is abnormally high. Based on the prediction results, the fault diagnosis model determines that there is an electrical fault in the charging pile. After further analysis, it is determined that the fault type is an overcurrent fault. Combined with the operating data of the charging pile, the fault diagnosis model analyzes that the cause of the fault may be that the internal resistance increases due to battery aging, causing the current to be abnormally high. The fault diagnosis model generates fault alarm information, including the fault type (overcurrent fault), fault cause (battery aging), time of fault occurrence, identifier of the charging pile, and recommended solution (replace the battery). The fault alarm information is sent to the management personnel of the charging station via SMS. After receiving the alarm information, the management personnel will go to the site to deal with the fault in time.

[0157] By predicting and diagnosing the operation data of the charging pile through the fault diagnosis model on the remote server, the abnormal or faulty state of the charging pile can be accurately identified, and the accuracy of fault detection can be improved. The fault diagnosis model can detect the abnormality or fault of the charging pile in time, and generate fault alarm information to send to relevant personnel, shortening the fault response time and reducing the charging interruption time caused by the fault. Through the fault type and cause provided in the fault alarm information and the recommended solution, maintenance personnel can perform fault troubleshooting and repair more accurately, reducing maintenance costs. Timely detection and handling of charging pile faults can avoid safety accidents caused by faults and ensure the safety of users and charging stations. By analyzing the fault data and operation data of the charging pile, the charging station manager can understand the usage and fault conditions of the charging pile, providing data support for optimizing the operation of the charging station. For example, the layout of the charging pile can be adjusted according to the fault data, and the charging efficiency can be improved.

[0158] like Figure 2 As shown, an embodiment of the present invention further provides an intelligent management system for international universal charging piles, including:

[0159] The charging pile integrates multiple standard conversion connectors to support multiple electric vehicle charging standards;

[0160] When a user borrows a conversion connector, the user can borrow the connector by himself through online payment, so as to intelligently identify and record the borrowing status of the conversion connector;

[0161] The user connects the electric vehicle to the charging pile and selects the corresponding charging standard, which automatically detects the charging requirements of the electric vehicle to obtain the test results;

[0162] According to the detection results, the output parameters of the charging pile, including current and voltage, are intelligently adjusted to suit the selected charging specifications;

[0163] During the charging process, the charging pile continuously monitors the charging status, including key parameters such as current, voltage, and charging time, and handles abnormal situations;

[0164] After charging is completed, the charging pile records the charging data, including charging time, charging amount, electricity consumption information, and generates a corresponding charging report.

[0165] It should be noted that this method is a method corresponding to the above-mentioned international universal charging pile. All implementation methods in the above-mentioned international universal charging pile embodiment are applicable to this embodiment and can achieve the same technical effect.

[0166] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An international universal charging pile, characterized in that: include: Multi-standard compatible conversion connector module, used to integrate conversion connectors of multiple standards to support charging of electric vehicles of different standards on charging piles; The connector identification and information transmission module is used to automatically identify the type of conversion connector connected to the charging pile through the conversion connector matching algorithm. If the connector type is identified, the connector type is transmitted to the automatic output parameter adjustment module; The module for automatically adjusting output parameters is used to automatically detect and intelligently adjust the output current and voltage based on the connected conversion connectors of different standards using the flower pollination algorithm to adapt to the charging needs of different electric vehicles; Intelligent management module, which is used to intelligently identify and manage the connector status, and to achieve self-service borrowing and returning of conversion connectors by real-time monitoring of connector usage, location and damage to obtain maintenance reports; Remote monitoring module, used to realize remote monitoring, fault diagnosis and data statistical analysis of charging piles through remote servers; The user interaction module is used to view the charging status, cost information and operation instructions for borrowing and returning the conversion connector, and supports users to start charging and pay fees.

2. The international universal charging pile according to claim 1, characterized in that: The conversion connector matching algorithm is used to automatically identify the type of conversion connector connected to the charging pile. If the connector type is identified, the connector type is passed to the automatic output parameter adjustment module, including: The sensor at the charging port of the charging pile continuously monitors the port status. When the sensor detects that the conversion connector is connected, the built-in camera of the charging pile collects images of the connector and extracts key features in the image, including shape, size and texture, to form a feature vector. Compare the feature vector with the standard features in the feature database, calculate the similarity between each standard feature and the feature vector, and determine the matching connector type, i.e., the matching item, based on the similarity; The matching items are transmitted to the automatic adjustment output parameter module through the internal communication bus of the charging pile.

3. The international universal charging pile according to claim 2, characterized in that: According to the different standard conversion connectors connected, the flower pollination algorithm is used to automatically detect and intelligently adjust the output current and voltage to meet the charging needs of different electric vehicles, including: When an electric vehicle is connected to a charging pile, the charging pile's sensor detects the type of adapter connected to identify the charging standard of the electric vehicle; Parse the charging standard, obtain the current and voltage ranges and charging speed requirement parameters under the charging standard, and initialize the parameters of the flower pollination algorithm, including population size, number of iterations, and fitness function; The final current and voltage combination is searched using a flower pollination algorithm, where each flower represents a current and voltage combination.

4. The international universal charging pile according to claim 3, characterized in that: According to the different standard conversion connectors connected, the flower pollination algorithm is used to automatically detect and intelligently adjust the output current and voltage to meet the charging needs of different electric vehicles, including: For each flower, the fitness function evaluates the performance of the corresponding flower according to the charging requirements of the electric vehicle, including charging speed, battery protection, and energy efficiency, to obtain the fitness function evaluation result; According to the fitness function evaluation results, an iterative search is performed, each flower is continuously adjusted, and the fitness function evaluation and iterative search process is repeated until the preset number of iterations is reached, and the final current and voltage combination is determined according to the fitness value of each flower.

5. The international universal charging pile according to claim 4, characterized in that: According to the different standard conversion connectors connected, the flower pollination algorithm is used to automatically detect and intelligently adjust the output current and voltage to meet the charging needs of different electric vehicles, including: According to the final current and voltage combination, during the charging process, the charging pile continuously monitors the output of current and voltage and the battery status of the electric vehicle, including power, temperature and internal resistance; if an abnormal situation occurs, including overheating, overcurrent, battery failure, the charging pile immediately takes corresponding protective measures, including reducing output, cutting off power or sounding an alarm; When the electric vehicle is fully charged or the user requests to disconnect through the charging pile interface, the charging pile stops outputting current and voltage and completes the charging process to adapt to the charging needs of different electric vehicles.

6. The international universal charging pile according to claim 5, characterized in that: Intelligently identify and manage connector status, and enable self-service borrowing and returning of conversion connectors by real-time monitoring of connector usage, location, and damage to obtain maintenance reports, including: Equip each connector with a unique identifier and initialize basic connector information, including type, specification, production date and initial status; Deploy various sensors in the joint usage scenarios, including usage counters, locators, and damage detection sensors, and use sensors to collect joint usage data, location data, and damage data in real time; The preset random forest model is used to train and optimize the usage data, location data, and damage data of the joint to obtain the joint status identification results and generate predictive maintenance recommendations; When a user selects a borrowed connector through the interactive interface, the user's identity is verified, the connector status is updated to borrowed, and the borrowing time and user information are recorded; when the user returns the connector, the user's identity is verified again, the connector status is updated to available, and the return time and connector usage are recorded; Based on real-time and historical data, the joint status is analyzed regularly and a maintenance report is generated. The report content includes joint usage frequency statistics, location distribution map, damage analysis, and predictive maintenance recommendations.

7. The international universal charging pile according to claim 6, characterized in that: The preset random forest model is used to train and optimize the usage data, location data, and damage data of the joint to obtain the joint status identification results and generate predictive maintenance suggestions, including: Collect usage data, location data, and damage data of the joint, and divide the collected data into a training set and a test set; Based on the training set and test set, build the basic framework of the random forest model and set the parameters of the random forest model, including the number of decision trees, maximum depth, and minimum number of sample splits; Use the training set to preliminarily train the random forest model to obtain preliminary training results, and optimize and adjust the random forest model based on the preliminary training results, including increasing or decreasing the number of decision trees and adjusting the feature selection strategy to obtain an optimized random forest model; The optimized random forest model is used to predict the test set data. Each decision tree produces a prediction result, and the prediction results of all decision trees are combined to obtain the final joint status identification label. Based on the final connector status identification tag, the charging pile's operating data and historical maintenance records, the connector status is analyzed to obtain predictive maintenance recommendations, including recommendations for connector repair, replacement, inspection, and corresponding maintenance time and priority.

8. The international universal charging pile according to claim 7, characterized in that: Through the remote server, remote monitoring, fault diagnosis and data statistical analysis of charging piles are realized, including: Based on the operation data of the charging pile, the fault diagnosis model on the remote server is used to predict and diagnose potential faults and generate fault alarm information; The remote server collects, organizes and analyzes the operating data of the charging pile, including charging capacity, charging time, connector status, and ambient temperature, and generates various reports and charts, including charging capacity statistics reports and failure rate analysis charts. It also provides customized data statistical analysis services, including charging capacity statistics for a specific time period and failure rate analysis of specific failure types.

9. The international universal charging pile according to claim 8, characterized in that: Based on the operation data of the charging pile, the fault diagnosis model on the remote server is used to predict and diagnose potential faults and generate fault alarm information, including: Transmit the operation data of the charging pile, including current, voltage, power, temperature, and charging time, to a remote server; The fault diagnosis model on the remote server predicts and diagnoses the operation data of the charging pile, and obtains the prediction result of the charging pile status to determine whether the charging pile has an abnormality or fault; According to the prediction result of the charging pile status, if the charging pile is detected to have an abnormality or fault, the type of the abnormality or fault is determined, including electrical fault, mechanical fault, and communication fault; The causes of the fault are analyzed, including battery aging, poor connector contact, and poor heat dissipation. Based on the type and cause of the fault, the fault diagnosis model generates fault alarm information, including the type of fault, cause of the fault, time of the fault, the identifier of the charging pile, and recommended solutions.

10. An intelligent management system for international universal charging piles, the method realizing the international universal charging piles as claimed in any one of claims 1 to 9, characterized in that: The system implements the following functions: The charging pile integrates multiple standard conversion connectors to support multiple electric vehicle charging standards; When a user borrows a conversion connector, the user can borrow the connector by himself through online payment, so as to intelligently identify and record the borrowing status of the conversion connector; The user connects the electric vehicle to the charging pile and selects the corresponding charging standard, which automatically detects the charging requirements of the electric vehicle to obtain the test results; According to the detection results, the output parameters of the charging pile, including current and voltage, are intelligently adjusted to suit the selected charging specifications; During the charging process, the charging pile continuously monitors the charging status, including key parameters such as current, voltage, and charging time, and handles abnormal situations; After charging is completed, the charging pile records the charging data, including charging time, charging amount, electricity consumption information, and generates a corresponding charging report.

Images