A charging pile intelligent operation and maintenance management method and device, a computer device, and a medium

Abstract

The application relates to a charging pile intelligent operation and maintenance management method and device, computer equipment and a medium. The method comprises collecting battery state parameters and charging pile operation state parameters; trend extraction is performed on the time sequence change of the battery state parameters and the charging pile operation state parameters, and correlation analysis is performed to generate a multi-dimensional state index representing the current operation state of the charging object and the charging equipment; based on the multi-dimensional state index, a corresponding control strategy is selected from a charging control strategy set, and stage control parameters set for different residual capacity intervals in the control strategy are adaptively evaluated with the current state index; and according to the adaptivity evaluation result, a charging operation of the corresponding strategy is performed. The application has the effect of improving the charging control efficiency of the charging pile.

Description

Technical Field

[0001] This application relates to the technical field of charging pile management, and in particular to a method, device, computer equipment and medium for intelligent operation and maintenance management of charging piles. Background Technology

[0002] Currently, with the widespread adoption of new energy vehicles, charging piles, as basic supporting infrastructure, undertake the task of providing high-frequency charging services daily. In order to improve charging efficiency and operational stability, some charging pile systems have begun to introduce remote monitoring and parameter control functions based on the Internet of Things (IoT) architecture, enabling preliminary monitoring and management of battery status and equipment operation.

[0003] Existing charging pile operation and maintenance management solutions typically adopt static control parameter configuration methods, but lack the ability to evaluate the performance status of the actual charging object in real time, and have not established a dynamic matching mechanism between charging strategies and equipment operating status. As a result, when faced with different battery health levels, complex load environments, or changes in operating status, they cannot adaptively optimize control strategies, thereby affecting charging efficiency and equipment stability.

[0004] The existing technical solutions mentioned above have the following drawbacks: the existing charging pile operation and maintenance management methods have poor optimization mechanisms for charging control strategies, making it difficult to achieve adaptive and efficient charging control, and therefore there is room for improvement. Summary of the Invention

[0005] To improve the charging control efficiency of charging piles, this application provides a method, device, computer equipment, and medium for intelligent operation and maintenance management of charging piles.

[0006] The above-mentioned objective of this application is achieved through the following technical solution:

[0007] A smart operation and maintenance management method for charging piles based on the Internet of Things, the method comprising:

[0008] Collect battery status parameters and charging pile operating status parameters;

[0009] Trend extraction is performed on the time series changes of the battery state parameters and the charging pile operating state parameters, and correlation analysis is conducted to generate a multi-dimensional state index representing the current operating state of the charging object and the charging equipment.

[0010] Based on the multidimensional state index, a corresponding control strategy is selected from the charging control strategy set, and the adaptability of the stage control parameters set in the control strategy for different remaining power ranges with the current state index is evaluated.

[0011] Based on the compatibility assessment results, execute the corresponding charging operation strategy.

[0012] By adopting the above technical solutions, and collecting battery status parameters and charging pile operating status parameters, real-time monitoring of the charging object and equipment operating status can be achieved, providing accurate basic information for subsequent control strategy selection and improving the proactiveness of operation and maintenance response. By extracting trends and performing correlation analysis on the time series changes of the collected parameters, the evolution patterns of equipment status and battery response characteristics can be discovered, thereby avoiding the strategy mismatch problem caused by static parameter judgment and improving the flexibility of status assessment. By selecting control strategies based on multi-dimensional status indexes and performing adaptation evaluation, the most suitable solution for the current status can be quickly identified from multiple alternative strategies, thereby avoiding the decrease in charging efficiency or equipment damage caused by strategy invocation mismatch. By executing charging operations according to the adaptation results, the control strategy can be dynamically adjusted to adapt to the actual operating status, thereby improving the stability, safety and intelligence level of the overall charging process.

[0013] In one example, this application can be further configured as follows: The step of extracting trends from the time-series changes of the battery state parameters and the charging pile operating state parameters, performing correlation analysis, and generating a multi-dimensional state index representing the current operating state of the charging object and the charging equipment specifically includes:

[0014] Set a sliding time window, extract the slope and relative rate of change of voltage, SOC state value and temperature in the battery state parameters, and obtain the battery trend feature vector characterizing the current response trend of the battery;

[0015] By calculating the correlation index between the current fluctuation frequency and the temperature rise rate in the operating status parameters of the charging pile, a trend feature vector of the pile body that characterizes the load change characteristics of the equipment is obtained.

[0016] Based on the battery trend feature vector and the pile trend feature vector, a state index structure containing multiple dimensions is constructed, and index quantization encoding is performed based on the threshold range corresponding to the feature values ​​of each dimension to obtain the multi-dimensional state index.

[0017] By adopting the above technical solutions, and by constructing battery trend feature vectors and charging pile trend feature vectors, the electrical response changes of the charging object and the load-bearing capacity of the charging pile can be reflected respectively, thereby improving the comprehensiveness and accuracy of state modeling. By merging the two trend vectors into a multi-dimensional state index and performing quantization encoding, complex operating states can be mapped into a unified index structure, thereby reducing the processing pressure of the control system on multi-source raw data and improving the efficiency and standardization of strategy invocation.

[0018] In one example, this application can be further configured as follows: the step of obtaining a pile trend feature vector characterizing the load change characteristics of the equipment by calculating the correlation index between the current fluctuation frequency and the temperature rise rate in the operating status parameters of the charging pile specifically includes:

[0019] Acquire a current data sequence with a preset period, identify the number of fluctuation events in the current data sequence that exceed a preset fluctuation threshold, and then calculate the fluctuation frequency per unit time as a characteristic of the device current stability.

[0020] Obtain the temperature change curve within the cycle, and calculate the average slope and fluctuation amplitude of the temperature change curve as indicators of temperature change.

[0021] A correlation function is constructed between the current stability characteristic and the temperature rise change index to obtain the corresponding cooperative change coefficient, and the cooperative change coefficient is used as the core component to generate the trend feature vector of the pile body.

[0022] By adopting the above technical solution, and by extracting the current fluctuation frequency and temperature rise change index and calculating their synergistic change coefficient, the thermal-electric load coupling relationship of the charging pile under high power output conditions can be effectively captured, thereby realizing in-depth modeling of the equipment operating pressure and improving the judgment ability of the control strategy under high load conditions and the level of safety redundancy design.

[0023] In one example, this application can be further configured as follows: based on the multi-dimensional state index, selecting a corresponding control strategy from the charging control strategy set, and evaluating the adaptability of the stage control parameters set for different remaining power ranges in the control strategy with the current state index, specifically including:

[0024] Based on the battery charging adaptability level and charging pile load capacity level in the multidimensional state index, the control strategy with corresponding weight is called from multiple candidate control strategies.

[0025] The stage control parameters corresponding to each remaining power segment of the control strategy are compared with the current state index item by item, and the fit score of the stage control parameters is calculated.

[0026] By adopting the above technical solution, and by selecting a strategy based on the battery adaptability level and the charging pile bearing level in the state index and calculating the adaptation score of the stage control parameters, it is possible to achieve accurate matching between the charging control strategy and the current state of the equipment, thereby improving the rationality of strategy invocation, avoiding abnormal battery response or charging pile overload due to parameter mismatch, and further improving charging efficiency and equipment stability.

[0027] In one example, this application can be further configured as follows: the charging operation based on the adaptation evaluation result, according to the corresponding strategy, specifically includes:

[0028] When the fit score meets the preset threshold, the charging operation of the corresponding stage control parameters is executed according to the control strategy.

[0029] When the fit score is lower than a preset threshold, the power output limit, voltage setting value and / or stage switching timing in the current strategy are adjusted within a preset range, and the adjusted fit score is recalculated.

[0030] If the adjusted fit score does not reach the re-evaluation threshold, a suboptimal strategy is selected for refitting, and the corresponding stage control parameters are reconfigured.

[0031] By adopting the above technical solution, local optimization can be quickly achieved without completely changing the strategy by fine-tuning the control parameters within the range when the fit score is insufficient. This enhances the flexibility of the strategy and improves the response speed and stability of local control. By selecting a suboptimal strategy to rematch the control parameters after the fine-tuning is ineffective, a fault-tolerant mechanism can be established for strategy switching, thereby ensuring the continuity of the control process and reducing the risk of equipment shock and service interruption caused by strategy mismatch.

[0032] In one example, this application can be further configured such that the intelligent operation and maintenance management method for charging piles also includes:

[0033] During the execution of charging control, execution feedback information corresponding to the control strategy is collected. The execution feedback information includes changes in charging efficiency, battery temperature rise response, and execution time overhead.

[0034] The mapping relationship between the multidimensional state index and the control strategy is adjusted and updated based on the execution feedback information.

[0035] By adopting the above technical solutions, and by collecting execution feedback information during the charging process and analyzing its compatibility with the control strategy, a quantitative evaluation of the actual effect of the strategy can be achieved, thereby enhancing the traceability and iterative capability of the strategy system. By dynamically adjusting the mapping relationship between the state index and the strategy based on the feedback results, a self-learning mechanism can be constructed, thereby enabling the strategy library to be continuously optimized with the running effect, and improving the adaptability and intelligent evolution capability of the system in the long-term operation process.

[0036] The second objective of this invention is achieved through the following technical solution:

[0037] A smart operation and maintenance management device for charging piles, characterized in that the device comprises:

[0038] The data acquisition module is used to collect battery status parameters and charging pile operating status parameters;

[0039] The trend modeling module is used to extract trends from the time series changes of the battery state parameters and the charging pile operating state parameters, perform correlation analysis, and generate a multi-dimensional state index representing the current operating state of the charging object and the charging equipment.

[0040] The strategy matching module is used to select the corresponding control strategy from the charging control strategy set based on the multi-dimensional state index, and to evaluate the compatibility between the stage control parameters set for different remaining power ranges in the control strategy and the current state index.

[0041] The control execution module is used to execute the charging operation of the corresponding strategy based on the adaptation evaluation results.

[0042] By adopting the above technical solutions, and collecting battery status parameters and charging pile operating status parameters, real-time monitoring of the charging object and equipment operating status can be achieved, providing accurate basic information for subsequent control strategy selection and improving the proactiveness of operation and maintenance response. By extracting trends and performing correlation analysis on the time series changes of the collected parameters, the evolution patterns of equipment status and battery response characteristics can be discovered, thereby avoiding the strategy mismatch problem caused by static parameter judgment and improving the flexibility of status assessment. By selecting control strategies based on multi-dimensional status indexes and performing adaptation evaluation, the most suitable solution for the current status can be quickly identified from multiple alternative strategies, thereby avoiding the decrease in charging efficiency or equipment damage caused by strategy invocation mismatch. By executing charging operations according to the adaptation results, the control strategy can be dynamically adjusted to adapt to the actual operating status, thereby improving the stability, safety and intelligence level of the overall charging process.

[0043] The above-mentioned objective three of this application is achieved through the following technical solution:

[0044] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described intelligent operation and maintenance management method for charging piles.

[0045] The fourth objective of this application is achieved through the following technical solution:

[0046] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described intelligent operation and maintenance management method for charging piles.

[0047] In summary, this application includes the following beneficial technical effects:

[0048] 1. By collecting battery status parameters and charging pile operating status parameters, real-time monitoring of the charging object and equipment's operating status can be achieved, providing accurate basic information for subsequent control strategy selection and improving the proactiveness of operation and maintenance response. By extracting trends and performing correlation analysis on the time-series changes of the collected parameters, the evolution patterns of equipment status and battery response characteristics can be uncovered, thus avoiding strategy mismatch problems caused by static parameter judgment and improving the flexibility of status assessment. By selecting control strategies based on multi-dimensional status indexes and performing adaptation evaluation, the most suitable solution for the current state can be quickly identified from multiple alternative strategies, thus avoiding charging efficiency degradation or equipment damage caused by strategy mismatch. By executing charging operations based on adaptation results, the control strategy can be dynamically adjusted to adapt to the actual operating state, thereby improving the overall stability, safety, and intelligence level of the charging process.

[0049] 2. By constructing battery trend feature vectors and charging pile trend feature vectors, the changes in the electrical response of the charging object and the load-bearing capacity of the charging pile can be reflected respectively, thereby improving the comprehensiveness and accuracy of state modeling; by merging the two trend vectors into a multi-dimensional state index and quantizing and encoding it, complex operating states can be mapped into a unified index structure, thereby reducing the processing pressure of the control system on multi-source raw data and improving the efficiency and standardization of strategy invocation.

[0050] 3. By extracting the current fluctuation frequency and temperature rise change index and calculating their coordinated change coefficient, the thermal-electric load coupling relationship of the charging pile under high power output conditions can be effectively captured, thereby realizing in-depth modeling of the equipment operating pressure and improving the judgment ability of the control strategy under high load conditions and the level of safety redundancy design. Attached Figure Description

[0051] Figure 1 This is a flowchart of a charging pile intelligent operation and maintenance management method in one embodiment of this application;

[0052] Figure 2 This is a schematic block diagram of a charging pile intelligent operation and maintenance management device according to one embodiment of this application;

[0053] Figure 3 This is a schematic diagram of a device according to one embodiment of this application. Detailed Implementation

[0054] The present application will be further described in detail below with reference to the accompanying drawings.

[0055] In one embodiment, such as Figure 1 As shown, this application discloses an intelligent operation and maintenance management method for charging piles, which specifically includes the following steps:

[0056] S10: Collect battery status parameters and charging pile operation status parameters.

[0057] Specifically, the data acquisition module deployed inside the charging pile automatically obtains battery information from the battery management interface of the connected vehicle. At the same time, combined with the operating data measured by the sensors of the charging pile itself, it completes the real-time acquisition of battery status parameters, including the current battery voltage, current, temperature, and SOC value. It also acquires the charging pile's own operating status parameters, including output current, voltage, internal temperature, and switch control status. In the charging area scenario of a smart community, the data acquisition action can be uniformly scheduled through the edge gateway for the data acquisition tasks of each charging pile, so as to standardize the operating status of each pile and report it in parallel for subsequent centralized decision analysis.

[0058] S20: Extract trends from the time series changes of battery state parameters and charging pile operating state parameters, perform correlation analysis, and generate a multi-dimensional state index representing the current operating state of the charging object and charging equipment.

[0059] Specifically, the collected parameter data is cached in chronological order and formed into a rolling time series. A sliding analysis window is used to perform continuous value change rate statistics on each type of parameter, extracting features such as temperature slope, current fluctuation rate, and SOC change trend. At the same time, the change trajectory between battery parameters and charging pile parameters is jointly calculated to analyze whether there is a linkage between the two under different load stages. By extracting these stability and load sensitivity indicators, a set of numerical vector structures for comprehensively representing the current charging state is constructed as input for subsequent strategy decisions. In the smart community scenario, it can realize the compatibility and unified state classification processing of different brand battery systems in the public charging pile network.

[0060] S30: Based on the multi-dimensional state index, select the corresponding control strategy from the charging control strategy set, and evaluate the adaptability of the stage control parameters set in the control strategy for different remaining power ranges with the current state index.

[0061] Specifically, the generated multidimensional state index is used as the current state input. A query and matching process is performed from the preset set of charging control strategies to select candidate control strategies corresponding to the state index. The control parameters corresponding to each power stage interval defined in the strategy, such as the target charging mode, voltage adjustment range, and power limit, are matched and compared with the feature values ​​of each dimension in the current state index. Based on the comparison results, a suitability score is calculated. The suitability reflects the degree of fit between the control strategy parameters and the current battery charging capacity and the load capacity of the charging pile. In smart community scenarios, it can be used to determine whether a public charging pile is suitable for the current vehicle to fast charge, avoiding abnormal operation of equipment or battery caused by unsuitable strategies.

[0062] S40: Based on the compatibility assessment results, execute the charging operation according to the corresponding strategy.

[0063] Specifically, the adaptation evaluation results of the previous stage are compared with the preset adaptation threshold. If the score is above the threshold, the control parameter set corresponding to the strategy is loaded, including current, voltage and mode configuration items. These parameters are then sent to the charging controller module through control commands, thereby driving the actual charging process to start and execute according to the preset rhythm. In high-density areas such as underground garages in smart communities, this step supports completing strategy judgment and initial control parameter activation within 5 seconds after vehicle access, ensuring that the power output closed loop is quickly completed during the initial connection period of the vehicle, making the power supply system of the entire community operate more stably.

[0064] In one embodiment, step S20 involves extracting trends from the time-series changes of battery state parameters and charging pile operating state parameters, performing correlation analysis, and generating a multi-dimensional state index characterizing the current operating state of the charging object and charging equipment. Specifically, this includes:

[0065] S21: Set a sliding time window, extract the slope and relative rate of change of voltage, SOC value and temperature in the battery state parameters, and obtain the battery trend feature vector that characterizes the current response trend of the battery.

[0066] Specifically, within a set sliding time window, battery voltage, SOC value, and temperature data points are continuously acquired. The fitting slope of these data points is calculated using the least squares method as the main parameter of the change trend. At the same time, the ratio of the change amplitude between adjacent sampling points is recorded to form a relative change rate index. These trend features are then combined and encoded in vector form to describe the battery's response activity and charging state evolution trend in the current time period. For example, in the slow charging area of ​​a smart community garage, this trend vector can be used to quickly determine whether the battery is in an acceptable fast charging state, thereby avoiding the abnormal response of the battery caused by the incorrect issuance of high-power strategies.

[0067] S22: By calculating the correlation index between current fluctuation frequency and temperature rise rate in the charging pile's operating status parameters, a trend feature vector of the pile body that characterizes the load change characteristics of the equipment is obtained.

[0068] Specifically, the time series data of the charging pile output current and shell temperature are analyzed. First, the number of fluctuations per unit time is identified according to the set current fluctuation threshold to form the current fluctuation frequency. Then, the average rate of change and fluctuation amplitude of the temperature rise trend within the corresponding time period are calculated. These two indicators are constructed as temperature rise change indicators. Then, a collaborative function is constructed based on the two to judge the correlation between their change trajectories. The value of this collaborative relationship is quantified as a characteristic quantity of the load bearing trend. Together with the temperature rise indicator, it constitutes the pile body trend feature vector, which is used to determine whether the charging pile is currently in a normal load state or has the possibility of overload warning. In smart communities, it can be combined with historical statistical models to identify the overheating trend of the pile body caused by multiple vehicles operating concurrently or high-frequency rotation in advance.

[0069] S23: Based on the battery trend feature vector and the pile trend feature vector, construct a state index structure containing multiple dimensions, and perform index quantization encoding based on the threshold range corresponding to the feature values ​​of each dimension to obtain a multi-dimensional state index.

[0070] Specifically, the battery trend feature vector and the pile trend feature vector obtained above are concatenated into a set of high-dimensional state vectors according to a preset field structure. Multiple discrimination interval labels are set for the feature values ​​in each dimension. For example, a voltage slope less than 0.1 is set as level 1, and a temperature rise rate greater than 5 is set as level 3. Then, a threshold matching operation is performed on the feature values ​​of each dimension, and the matching results are uniformly recorded in discrete encoding form. Finally, a quantized state index for state classification and policy mapping is generated. This index can be used as the input key value of the control logic. In the smart community scenario, it supports the generation of standardized adaptation mapping rules for different devices and battery types, thereby reducing the risk of policy confusion caused by heterogeneous terminal access.

[0071] In one embodiment, step S22, namely, by calculating the correlation index between the current fluctuation frequency and the temperature rise rate in the charging pile's operating status parameters, a trend feature vector characterizing the load change characteristics of the charging pile is obtained, specifically including:

[0072] S221: Obtain a current data sequence with a preset period, identify the number of fluctuation events in the current data sequence that exceed a preset fluctuation threshold, and then calculate the fluctuation frequency per unit time as a characteristic of the device current stability.

[0073] Specifically, the output current of the charging pile is continuously sampled based on a set time period. The sampled value sequence is extracted within each time window, and a current fluctuation threshold is set as a judgment condition. The positive and negative jump points exceeding the threshold during continuous sampling are identified. The total number of jump points in the entire time period is counted, and the current fluctuation frequency per unit time is calculated. This frequency value is used to reflect the stability state of the device output during actual operation. In smart communities, this method can effectively detect current disturbances caused by users frequently plugging and unplugging vehicles or sudden multi-vehicle charging during peak hours, providing an important reference for strategy adjustment.

[0074] S222: Obtain the temperature change curve within the period, and calculate the average slope and fluctuation amplitude of the temperature change curve as indicators of temperature change.

[0075] Specifically, the casing temperature or internal thermistor data is read within a time period consistent with the current sampling period to form a continuous temperature change curve. The average temperature rise slope is obtained by linear fitting on this curve as a trend indicator. At the same time, the maximum-minimum temperature difference of the entire curve within this time period is calculated as a fluctuation amplitude indicator. These two indicators are used to determine whether the thermal response of the equipment is stable and whether the temperature rise is within the normal range. In the deployment environment of smart communities, this method can promptly identify abnormal temperature rise trends caused by poor heat dissipation or equipment aging, providing a basis for triggering power protection or strategy replacement in advance.

[0076] S223: Construct a correlation function between current stability characteristics and temperature rise change index, obtain the corresponding synergistic change coefficient, and use the synergistic change coefficient as the core component to generate the pile trend feature vector.

[0077] Specifically, the calculated current fluctuation frequency, average temperature rise slope, and fluctuation amplitude are used as input variables. Pearson correlation analysis is used to establish a functional relationship to characterize the coupling strength between current instability and temperature rise amplitude changes within a specific period. The calculation results are output as a co-variation coefficient. The larger the coefficient, the stronger the coupling between electrical and thermal loads during equipment operation, indicating that the charging pile is in a high-load, high-heat-risk state. This coefficient is then written into the pile's trend feature vector as a core feature quantity for subsequent state index fusion judgment. In smart communities, this can serve as an important basis for identifying whether the equipment is on the edge of critical load, improving the accuracy of strategy adaptation.

[0078] In one embodiment, such as Figure 2 As shown, in step S30, based on the multi-dimensional state index, a corresponding control strategy is selected from the charging control strategy set, and the adaptation of the stage control parameters set in the control strategy for different remaining power ranges with the current state index is evaluated. Specifically, this includes:

[0079] S31: Based on the battery charging adaptability level and charging pile load capacity level in the multi-dimensional state index, call the control strategy with corresponding weight from multiple candidate control strategies.

[0080] Specifically, the dimension values ​​representing the battery charging adaptability level and the dimension values ​​representing the pile load bearing capacity level are extracted from the state index structure. These dimension values ​​are then combined as state keywords and input into the control strategy matching module. The strategy matching score is calculated based on the weight priority and the range of the adaptation index in the preset strategy set. The target control strategy that best matches the current state is selected from the strategy with the highest score. This strategy will be used to set the charging control parameters for the current time period. In smart communities, this method supports the rapid execution of strategy invocation actions after a user makes a reservation for charging access. It is especially suitable for concurrent scenarios where multiple battery types and pile power levels are inconsistent in the same site.

[0081] S32: Compare the stage control parameters corresponding to each remaining power segment of the control strategy with the current state index item by item, and calculate the fit score of the stage control parameters.

[0082] Specifically, the control parameters corresponding to each SOC segment in the control strategy are read, including the target charging mode, voltage setpoint, power output limit, and stage switching conditions. These parameters are then compared with the feature values ​​of each dimension in the current state index. A corresponding error tolerance range is set for each parameter dimension. If the strategy parameter falls within the tolerance range, it is recorded as a matching item. Finally, all matching items are scored and the overall adaptability score is calculated according to the set weight. This score is used to evaluate whether the current strategy is highly adapted to the device state. In smart community scenarios, it is applicable to high-precision intelligent control areas, enabling a quantitative evaluation of the dynamic adjustment capability of the strategy under different vehicles and scenarios.

[0083] In one embodiment, step S40, which involves performing a charging operation according to the adaptation evaluation result, specifically includes:

[0084] S41: When the fit score meets the preset threshold, the charging operation of the corresponding stage control parameters is executed according to the control strategy.

[0085] Specifically, the system loads the stage parameters corresponding to the remaining battery SOC range in the current control strategy, and sends control commands to the control terminal sequentially according to the stage definition. These commands include setting current and voltage output limits, voltage ramp-up rate, power limit, etc. The system also combines the operating temperature and stability parameters of the current stage to determine the output step size, ensuring smooth stage switching. In smart communities, this method can prevent power system fluctuations caused by sudden changes in the battery state of different vehicles, and improve the smoothness of the substation response and the service life of the equipment.

[0086] S42: When the adaptation score is lower than the preset threshold, the power output limit, voltage setting value and / or stage switching timing in the current strategy are adjusted within the preset range, and the adjusted adaptation score is recalculated.

[0087] Specifically, parameters in the current control strategy that do not meet the adaptation conditions are adjusted within a certain range. This includes increasing the upper limit of the voltage setpoint by no more than 0.5V, decreasing the upper limit of power by no more than 5%, and moving the SOC segment boundary by no more than ±1% to the left or right. After each adjustment is completed, the state index is re-scored based on the updated parameters to evaluate whether the locally optimized strategy has a higher adaptability to the current device state. In a smart community environment, this mechanism can make the same strategy template more flexible to adapt to combinations of different battery vehicle models and different load piles, thereby improving the versatility of the control strategy.

[0088] S43: If the adjusted fit score does not reach the re-evaluation threshold, select the suboptimal strategy for refitting and reconfigure the corresponding stage control parameters.

[0089] Specifically, when the evaluation score still fails to reach the execution threshold after multiple parameter fine-tunings, the suboptimal strategy in the control strategy set is used as a substitute. The next most suitable strategy is selected according to the priority identifier or index distance matching result. Then, the segmented control parameters of the strategy are reloaded step by step for matching calculation to confirm its adaptability level with the current state. If the requirements are met, the strategy is executed; otherwise, the next round of strategy retrieval process continues. In smart community scenarios, this mechanism can maintain strategy stability in extreme environments such as high temperatures at night or peak concurrent charging, ensuring that the control logic does not fall into output gaps or abnormal strategy execution paths under various operating conditions.

[0090] In one embodiment, the intelligent operation and maintenance management method for charging piles further includes:

[0091] S50: During the execution of charging control, the system collects execution feedback information corresponding to the control strategy. The execution feedback information includes changes in charging efficiency, battery temperature rise response, and execution time overhead.

[0092] Specifically, after each round of charging control strategy is issued and executed, real-time operating data during the charging process is recorded synchronously, including the actual charging current and voltage output trajectory, the fitting slope of the SOC growth curve, the continuous rate of increase in battery temperature, and the start and end times of the charging cycle. By extracting these data in a structured manner, charging efficiency indicators and temperature rise response curves are formed. At the same time, the time taken from the start of the control strategy to reaching the charging target at each stage is recorded as an evaluation indicator of execution time. In a smart community environment, this process can be uniformly collected by the gateway from the execution feedback information of multiple charging piles within the jurisdiction and uploaded to the platform, so that the strategy execution effect of different vehicles under different states can be compared horizontally, providing an objective evaluation data basis for subsequent control strategy optimization.

[0093] S60: Adjust and update the mapping relationship between the multidimensional state index and the control strategy based on the execution feedback information.

[0094] Specifically, the matching relationship between feedback information and the original state index and control strategy is written into the dynamic mapping optimization module as a set of historical data. In this module, the strategy adaptability performance is normalized and scored based on the feedback results. If multiple consecutive feedback executions show that the matching effect between the strategy and the state index is significantly lower than that of other strategy combinations, the index-strategy mapping relationship adjustment mechanism is triggered, which reduces the priority of the strategy in this type of state or replaces it with a new strategy. At the same time, the feedback information during the adjustment process is retained as the basis for updating. In the smart community charging platform, this mechanism can realize cross-time period strategy self-learning and dynamic adjustment, so that the entire platform strategy library can continuously adapt to the operating trends such as vehicle type evolution and equipment aging.

[0095] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0096] In one embodiment, a smart operation and maintenance management device for charging piles is provided, which corresponds one-to-one with the smart operation and maintenance management method for charging piles described in the above embodiments. For example... Figure 2 As shown, the intelligent operation and maintenance management device for charging piles includes a data acquisition module, a trend modeling module, a strategy matching module, and a control execution module. Detailed descriptions of each functional module are as follows:

[0097] The data acquisition module is used to collect battery status parameters and charging pile operating status parameters;

[0098] The trend modeling module is used to extract trends from the time series changes of battery state parameters and charging pile operating state parameters, perform correlation analysis, and generate a multi-dimensional state index representing the current operating state of the charging object and charging equipment.

[0099] The strategy matching module is used to select the corresponding control strategy from the charging control strategy set based on the multi-dimensional state index, and evaluate the adaptability of the stage control parameters set in the control strategy for different remaining power ranges with the current state index.

[0100] The control execution module is used to execute the charging operation of the corresponding strategy based on the adaptation evaluation results.

[0101] Optionally, the trend modeling module specifically includes:

[0102] The battery trend extraction submodule is used to set a sliding time window, extract the slope and relative rate of change of voltage, SOC value and temperature in battery state parameters, and obtain a battery trend feature vector that characterizes the current response trend of the battery.

[0103] The equipment load identification submodule is used to obtain the pile trend feature vector that characterizes the equipment load change by calculating the correlation index between the current fluctuation frequency and the temperature rise rate in the charging pile's operating status parameters.

[0104] The state index generation submodule is used to construct a state index structure with multiple dimensions based on the battery trend feature vector and the pile trend feature vector, and to perform index quantization encoding based on the threshold range corresponding to the feature values ​​of each dimension to obtain a multi-dimensional state index.

[0105] Optionally, the device load identification submodule specifically includes:

[0106] The current stability extraction unit is used to acquire a current data sequence with a preset period, identify the number of fluctuation events in the current data sequence that exceed a preset fluctuation threshold, and then calculate the fluctuation frequency per unit time as the current stability feature of the device.

[0107] The temperature rise index extraction unit is used to obtain the temperature change curve within the period and calculate the average slope and fluctuation amplitude of the temperature change curve as the temperature rise change index.

[0108] The feature fusion analysis unit is used to construct the correlation function between current stability characteristics and temperature rise change index, obtain the corresponding synergistic change coefficient, and use the synergistic change coefficient as the core component to generate the pile trend feature vector.

[0109] Optionally, the strategy matching module specifically includes:

[0110] The strategy filtering submodule is used to call the corresponding weighted control strategy from multiple candidate control strategies based on the battery charging adaptability level and charging pile load capacity level in the multi-dimensional state index.

[0111] The parameter adaptation analysis submodule is used to compare the stage control parameters corresponding to each remaining power segment of the control strategy with the current state index item by item, and calculate the adaptation score of the stage control parameters.

[0112] Optionally, the control execution module specifically includes:

[0113] The strategy execution submodule is used to perform the charging operation of the corresponding stage control parameters according to the control strategy when the fit score meets the preset threshold.

[0114] The parameter fine-tuning submodule is used to adjust the power output limit, voltage setting and / or stage switching timing in the current strategy within a preset range when the fit score is lower than the preset threshold, and recalculate the adjusted fit score.

[0115] The strategy replacement submodule is used to select a suboptimal strategy for refitting and reconfigure the corresponding stage control parameters if the adjusted fit score does not reach the re-evaluation threshold.

[0116] Optionally, intelligent operation and maintenance management methods for charging piles also include:

[0117] The feedback acquisition module is used to collect execution feedback information corresponding to the control strategy during the charging control process. The execution feedback information includes changes in charging efficiency, battery temperature rise response, and execution time overhead.

[0118] The strategy optimization module is used to adjust and update the mapping relationship between the multidimensional state index and the control strategy based on the execution feedback information.

[0119] Specific limitations regarding the intelligent operation and maintenance management device for charging piles can be found in the limitations of the intelligent operation and maintenance management method for charging piles mentioned above, and will not be repeated here. Each module in the aforementioned intelligent operation and maintenance management device for charging piles can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0120] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a smart operation and maintenance management method for charging piles.

[0121] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0122] Collect battery status parameters and charging pile operating status parameters;

[0123] Trends are extracted from the time series changes of battery state parameters and charging pile operating state parameters, and correlation analysis is performed to generate a multi-dimensional state index representing the current operating state of the charging object and the charging equipment.

[0124] Based on the multi-dimensional state index, the corresponding control strategy is selected from the charging control strategy set, and the adaptability of the stage control parameters set in the control strategy for different remaining power ranges with the current state index is evaluated.

[0125] Based on the compatibility assessment results, execute the corresponding charging operation strategy.

[0126] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0127] Collect battery status parameters and charging pile operating status parameters;

[0128] Trends are extracted from the time series changes of battery state parameters and charging pile operating state parameters, and correlation analysis is performed to generate a multi-dimensional state index representing the current operating state of the charging object and the charging equipment.

[0129] Based on the multi-dimensional state index, the corresponding control strategy is selected from the charging control strategy set, and the adaptability of the stage control parameters set in the control strategy for different remaining power ranges with the current state index is evaluated.

[0130] Based on the compatibility assessment results, execute the corresponding charging operation strategy.

[0131] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0132] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0133] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for intelligent operation and maintenance management of charging piles, characterized in that, The method includes: Collect battery status parameters and charging pile operating status parameters; Trend extraction is performed on the time series changes of the battery state parameters and the charging pile operating state parameters, and correlation analysis is conducted to generate a multi-dimensional state index representing the current operating state of the charging object and the charging equipment. Based on the multidimensional state index, a corresponding control strategy is selected from the charging control strategy set, and the adaptability of the stage control parameters set in the control strategy for different remaining power ranges with the current state index is evaluated. Based on the compatibility assessment results, execute the corresponding charging operation strategy; Specifically, the process of extracting trends from the time-series changes of the battery state parameters and the charging pile operating state parameters, performing correlation analysis, and generating a multi-dimensional state index representing the current operating state of the charging object and the charging equipment includes: Set a sliding time window, extract the slope and relative rate of change of voltage, SOC state value and temperature in the battery state parameters, and obtain the battery trend feature vector characterizing the current response trend of the battery; By calculating the correlation index between the current fluctuation frequency and the temperature rise rate in the operating status parameters of the charging pile, a trend feature vector of the pile body that characterizes the load change characteristics of the equipment is obtained. Based on the battery trend feature vector and the pile trend feature vector, a state index structure containing multiple dimensions is constructed, and index quantization encoding is performed based on the threshold range corresponding to the feature values ​​of each dimension to obtain the multi-dimensional state index. The process involves calculating the correlation index between the current fluctuation frequency and the temperature rise rate in the operating status parameters of the charging pile to obtain a trend feature vector representing the load change characteristics of the equipment. Specifically, this includes: Acquire a current data sequence with a preset period, identify the number of fluctuation events in the current data sequence that exceed a preset fluctuation threshold, and then calculate the fluctuation frequency per unit time as a characteristic of the device current stability. Obtain the temperature change curve within the cycle, and calculate the average slope and fluctuation amplitude of the temperature change curve as indicators of temperature change. A correlation function is constructed between the current stability characteristic and the temperature rise change index to obtain the corresponding cooperative change coefficient, and the cooperative change coefficient is used as the core component to generate the trend feature vector of the pile body.

2. The intelligent operation and maintenance management method for charging piles according to claim 1, characterized in that, The step of selecting a corresponding control strategy from the charging control strategy set based on the multi-dimensional state index, and evaluating the adaptability of the stage control parameters set for different remaining power ranges in the control strategy with the current state index, specifically includes: Based on the battery charging adaptability level and charging pile load capacity level in the multidimensional state index, the control strategy with corresponding weight is called from multiple candidate control strategies. The stage control parameters corresponding to each remaining power segment of the control strategy are compared with the current state index item by item, and the fit score of the stage control parameters is calculated.

3. The intelligent operation and maintenance management method for charging piles according to claim 2, characterized in that, The step of executing the charging operation according to the corresponding strategy based on the compatibility evaluation result specifically includes: When the fit score meets the preset threshold, the charging operation of the corresponding stage control parameters is executed according to the control strategy. When the fit score is lower than a preset threshold, the power output limit, voltage setting value and / or stage switching timing in the current strategy are adjusted within a preset range, and the adjusted fit score is recalculated. If the adjusted fit score does not reach the re-evaluation threshold, a suboptimal strategy is selected for refitting, and the corresponding stage control parameters are reconfigured.

4. The intelligent operation and maintenance management method for charging piles according to claim 1, characterized in that, The intelligent operation and maintenance management method for charging piles also includes: During the execution of charging control, execution feedback information corresponding to the control strategy is collected. The execution feedback information includes changes in charging efficiency, battery temperature rise response, and execution time overhead. The mapping relationship between the multidimensional state index and the control strategy is adjusted and updated based on the execution feedback information.

5. A smart operation and maintenance management device for charging piles, characterized in that, The device includes: The data acquisition module is used to collect battery status parameters and charging pile operating status parameters; The trend modeling module is used to extract trends from the time series changes of the battery state parameters and the charging pile operating state parameters, perform correlation analysis, and generate a multi-dimensional state index representing the current operating state of the charging object and the charging equipment. The strategy matching module is used to select the corresponding control strategy from the charging control strategy set based on the multi-dimensional state index, and to evaluate the compatibility between the stage control parameters set for different remaining power ranges in the control strategy and the current state index. The control execution module is used to execute the charging operation of the corresponding strategy based on the adaptation evaluation results; The trend modeling module specifically includes: The battery trend feature vector acquisition submodule is used to set a sliding time window, extract the slope and relative rate of change of voltage, SOC state value and temperature in the battery state parameters, and obtain the battery trend feature vector characterizing the current response trend of the battery. The pile trend feature vector acquisition submodule is used to obtain the pile trend feature vector characterizing the load change characteristics of the equipment by calculating the correlation index between the current fluctuation frequency and the temperature rise rate in the operating status parameters of the charging pile. The multidimensional state index acquisition submodule is used to construct a state index structure containing multiple dimensions based on the battery trend feature vector and the pile trend feature vector, and to perform index quantization encoding based on the threshold range corresponding to the feature values ​​of each dimension to obtain the multidimensional state index. The submodule for obtaining the trend feature vector of the pile body specifically includes: The device current stability feature acquisition unit is used to acquire a current data sequence of a preset period, identify the number of fluctuation events in the current data sequence that exceed a preset fluctuation threshold, and then calculate the fluctuation frequency per unit time as the device current stability feature. The temperature rise change index acquisition unit is used to acquire the temperature change curve within the cycle and calculate the average slope and fluctuation amplitude of the temperature change curve as the temperature rise change index. A unit is used to construct the correlation function between the current stability characteristics and the temperature rise change index, obtain the corresponding cooperative change coefficient, and use the cooperative change coefficient as the core component to generate the pile trend feature vector.

6. The intelligent operation and maintenance management device for charging piles according to claim 5, characterized in that, The trend modeling module specifically includes: The battery trend extraction submodule is used to set a sliding time window, extract the slope and relative rate of change of voltage, SOC state value and temperature in the battery state parameters, and obtain a battery trend feature vector that characterizes the current response trend of the battery. The equipment load identification submodule is used to obtain a pile trend feature vector that characterizes the equipment load change characteristics by calculating the correlation index between the current fluctuation frequency and the temperature rise rate in the operating status parameters of the charging pile. The state index generation submodule is used to construct a state index structure containing multiple dimensions based on the battery trend feature vector and the pile trend feature vector, and to perform index quantization encoding based on the threshold range corresponding to the feature values ​​of each dimension to obtain the multi-dimensional state index.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent operation and maintenance management method for charging piles as described in any one of claims 1 to 4.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent operation and maintenance management method for charging piles as described in any one of claims 1 to 4.

Images