Wind-solar integrated power generation-oriented automatic cabin-adjusting rechargeable battery module control system

Abstract

The invention relates to the field of new energy and artificial intelligence, and discloses a wind-solar integrated power generation-oriented automatic cabin-adjusting rechargeable battery module control system, which comprises a power generation bus of which the charging input end is connected to a wind-solar integrated power generation system, and a charging output end is connected with a rechargeable battery in a charging groove, the power conversion module is used for converting power input by a power generation bus into voltage-adjustable output power. Comprising a charging groove, a pop-up groove, a plurality of slots and a battery adjusting mechanical structure, the slots are used for storing batteries to be charged, and the battery adjusting mechanical structure sequentially sends the batteries to be charged into the charging groove and transfers the batteries to the pop-up groove after being fully charged; and according to the real-time data of the rechargeable battery acquired by the voltage sampling module, the current sampling module and the temperature monitoring module, the output voltage and current of the DC conversion module are adjusted, and the charging process is controlled. The charging device has the advantage that the complexity and the size of the charging device are reduced.

Description

Technical Field

[0001] The present invention relates to the fields of new energy and artificial intelligence, and specifically to an automatic bin - adjusting charging battery module control system for integrated wind - solar power generation. Background Technique

[0002] With the increasingly fierce global strategic competition in the new energy industry, lithium rechargeable batteries with various advantages have been widely used in the field of new energy storage batteries. During the charging process of lithium batteries, multiple charging stages are required, causing a series of chemical reactions inside the lithium batteries. The charging voltage and current are different in different stages, and fine adjustment and control of the charging voltage and current are needed. To use the rechargeable battery for a long time and safely, it is also necessary to monitor the voltage and temperature of the battery and estimate the remaining power of the storage battery. Therefore, the battery management device is very complex. Traditional parallel or series charging modules charge multiple batteries synchronously. It is impossible to ensure that the current and voltage of each lithium battery are exactly the same. Coupled with the influence of the output accuracy of the charging equipment, it is difficult to ensure the consistency of each lithium battery, doubling the complexity of the charging operation. Therefore, it is very necessary to design an automatic bin - adjusting charging battery module control system for integrated wind - solar power generation that reduces the complexity and volume of the charging device. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention provides an automatic bin - adjusting charging battery module control system for integrated wind - solar power generation, which has the advantages of reducing the complexity and volume of the charging device and solves the problems in the above - mentioned background technique.

[0004] To achieve the above - mentioned purpose of reducing the complexity and volume of the charging device, the present invention provides the following technical solution: An automatic bin - adjusting charging battery module control system for integrated wind - solar power generation, including: DC conversion module: The charging input end is connected to the power generation bus of the wind - power integrated generation system, and the charging output end is connected to the charging battery in the charging slot, and is used to convert the power input from the power generation bus into an output power with adjustable voltage. Automatic bin - adjusting mechanism: including a charging slot, a pop - out slot, a plurality of slots and a battery bin - adjusting mechanical structure. The slots are used to store the batteries to be charged, and the bin - adjusting mechanical structure sequentially sends the batteries to be charged into the charging slot and transfers the battery to the pop - out slot after it is fully charged. Control module; According to the real - time data of the charging battery obtained by the voltage sampling module, current sampling module and temperature monitoring module, adjust the output voltage and current of the DC conversion module and control the charging process.

[0005] Preferably, the control process executed by the control module includes: Detect the status of each sub - module after starting the system; Detect whether the battery is inserted into the charging slot. If there is no battery, the battery in the slot is called into the charging slot through the automatic bin adjustment structure; During the charging process, continuously collect the voltage, current and temperature data of the battery; Dynamically adjust the charging voltage and current according to the target parameters corresponding to the charging stage to achieve multi-stage fine charging; After the battery is fully charged, control the automatic bin adjustment structure to transfer the battery to the ejection slot and introduce the next battery to continue charging.

[0006] Preferably, the automatic bin adjustment structure has a cyclic charging function, supports automatically introducing a new battery for the next round of charging after the fully charged battery is ejected from the ejection slot, and has a standby monitoring mechanism. If there is no battery to be charged in the slot, it automatically enters the low-power standby state, continuously detects the slot status, and is automatically awakened and starts the charging process after a new battery is inserted.

[0007] A control method for an automatic bin adjustment charging battery module for integrated wind-solar power generation includes the following steps: Obtain the input power parameters of the integrated wind-solar power generation system under different operating scenarios, combine the operating parameters of the battery module, and use the feature aggregation algorithm to construct a charging state feature data set; Based on the charging state feature data set, apply the hierarchical clustering algorithm and the charging stage recognition model to segment and identify the charging process, distinguish typical charging states, and automatically match the stage target charging parameters according to the battery type; According to the identified charging stage, combine the reinforcement learning control strategy to construct a real-time voltage and current adjustment mechanism, and dynamically adjust the output power according to the battery response feedback during the charging process; During the dynamic charging control process, evaluate the response stability index of the battery module in real time, monitor whether the charging parameters reach the stable interval. If so, trigger the automatic bin adjustment strategy and preferentially select the battery group with similar charging states to access the charging process; Apply the multi-source scheduling optimization algorithm to dynamically allocate wind-solar power generation resources, revise the charging scheduling plan in real time, and generate an energy efficiency optimization report.

[0008] Preferably, the process of constructing the charging state feature data set using the feature aggregation algorithm is as follows: Collect the photovoltaic power output, grid power feeding ratio, wind energy volatility parameters and environmental meteorological factors of the integrated wind-solar power generation system at different operating times, and synchronously obtain the operating characteristics of the battery module; Perform data standardization processing on the collected data, unify the scale range of each feature data, and construct a time series sample of the charging state through the time window mechanism; Introduce the moving average and weighted dynamic smoothing algorithms to extract the representative statistical features reflecting the actual response behavior of the battery module; Based on the multi-dimensional feature fusion mechanism, the input features of wind-solar power generation and the response features of the battery module are jointly aggregated to form a multi-source heterogeneous fusion feature vector; Construct a charging state feature dataset with the aggregated multi-dimensional feature vector.

[0009] Preferably, the process of segmenting the charging process using the hierarchical clustering algorithm and the charging stage recognition model is as follows: Input the constructed charging state feature dataset into the hierarchical clustering model, and perform clustering analysis on different charging states by combining the Euclidean distance and the Mahalanobis distance joint similarity metric; Set the hierarchical depth control parameter of the clustering tree, and retain the charging stage clusters through the pruning strategy; For each cluster, use the charging stage recognition model to perform label classification and determine whether the label belongs to the typical stage; During the recognition process, combine the historical annotation data and the model supervision and verification mechanism; Finally, form the multi-stage segmentation result of the charging process.

[0010] Preferably, the process of automatically matching the stage target charging parameters according to the battery type is as follows: According to the segmentation recognition result, call the built-in battery type recognition module of the system to obtain the type of the battery module currently connected to the charging process; According to the identified battery type, match the corresponding stage voltage, current, and temperature rise safety threshold parameters in the preset charging parameter database; During the target parameter matching process, consider the influencing factors and dynamically adjust the adaptation interval of the target parameters; Combine the charging stage classification label, automatically bind the target parameter template of each stage, and form a complete charging stage target parameter configuration file.

[0011] Preferably, the process of constructing the voltage and current real-time adjustment mechanism by combining the reinforcement learning control strategy is as follows: Based on the stage target charging parameter configuration file, set the reward function of the reinforcement learning model, with the goal of minimizing the charging time and maximizing the energy conversion efficiency; Define the state space as the current SOC, voltage, current, and environmental temperature parameters of the battery, and the action space as the amplitude values for adjusting the output power and the charging voltage and current; Use the proximal policy optimization algorithm to train the control strategy, and the reinforcement learning model continuously updates the strategy through online feedback; During the actual charging process, the control model dynamically generates control actions according to the real-time feedback signal of the battery module.

[0012] Preferably, the process of monitoring whether the charging parameters reach the stable interval is as follows: During the execution of the real-time voltage and current adjustment mechanism based on reinforcement learning, continuously collect the key response parameters of the currently connected battery module, and record these parameters at multiple points within the set time sliding window; For each key parameter, apply the sliding window statistical algorithm to calculate the mean, standard deviation, and volatility within the window period, and compare them with the preset stability threshold; Set the stable interval judgment criterion and construct a multi-factor stability evaluation index system; If the volatility of the key parameter is less than the set stable threshold in multiple consecutive sliding window periods, it is determined that the charging process of the current battery module has entered the convergent stable state; If the volatility of the key parameter is greater than or equal to the set stable threshold in multiple consecutive sliding window periods, it is determined that the charging process of the current battery module has not entered the convergent stable state.

[0013] Preferably, the process of generating the energy efficiency optimization report is as follows: After completing the charging stage control and automatic warehouse adjustment process, statistically analyze the utilization efficiency, average conversion efficiency, and warehouse adjustment response delay of the wind-solar power generation resources during the entire charging process; Combined with the energy received by each module during the charging process and the achievement rate of the target charging parameters, calculate the comprehensive energy efficiency indicators, including the energy input density per unit time and the number of power dispatching times per unit of electricity; Introduce a multi-source scheduling optimization algorithm to analyze the resource scheduling path and battery pack switching strategy during the completed charging process, and identify the existing redundant paths and energy consumption waste points; Automatically generate an energy efficiency optimization report in combination with the system operation log and charging behavior record.

[0014] Compared with the prior art, the present invention provides a control system for an automatic warehouse adjustment charging battery module for integrated wind-solar power generation, having the following beneficial effects: By integrating the multi-source input characteristics of the wind-solar integrated power generation system with the operating status of the battery module, a high-dimensional charging state feature dataset is constructed using a feature aggregation algorithm, significantly enhancing the system's precise perception ability of charging behavior under complex operating conditions; introducing a hierarchical clustering algorithm and a stage recognition model to achieve fine-grained segmentation of the charging process and classification of typical stages, and then matching the optimal stage target parameters according to the battery type, effectively enhancing the system's adaptability and intelligent level; combining a reinforcement learning control strategy to construct a real-time voltage and current adjustment mechanism to achieve dynamic and precise control of the charging process, optimizing the charging efficiency while ensuring battery safety; at the same time, through real-time monitoring of the battery response stability and judgment of the stable interval, combined with an automatic binning strategy, to ensure the balance of battery pack access and the continuity of system operation; further using a multi-source scheduling optimization algorithm to dynamically adjust the wind-solar power generation resource allocation path, improving the real-time performance of resource scheduling and energy conversion efficiency, and generating an optimization report containing multi-dimensional energy efficiency indicators, scheduling strategy suggestions and performance evolution trends, comprehensively enhancing the intelligent management level, charging energy efficiency and operation and maintenance decision-making ability of system operation, with good engineering practical value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic structural diagram of the present invention; Figure 2 is a schematic method diagram of the present invention; Figure 3 is a structural diagram of the automatic binning module of the present invention; Figure 4 is a working flow chart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment 1: Please refer to Figure 1 As shown, a control system for an automatic binning charging battery module for wind-solar integrated power generation according to an embodiment of the present invention includes: DC conversion module: The charging input end is connected to the power generation bus of the wind-power integrated power generation system, and the charging output end is connected to the charging battery in the charging tank, and is used to convert the power input from the power generation bus into an output power with adjustable voltage; Automatic battery swapping mechanism: It includes a charging slot, a pop-out slot, multiple slots, and a battery swapping mechanical structure. The slots are used to store batteries to be charged. The swapping mechanical structure sequentially sends the batteries to be charged into the charging slot and transfers the charged batteries to the pop-out slot after charging. Control module: Based on the real-time data of the charging battery obtained by the voltage sampling module, current sampling module, and temperature monitoring module, it adjusts the output voltage and current of the DC conversion module to control the charging process.

[0018] The control process executed by the control module includes: After starting the system, it detects the status of each sub-module; It detects whether a battery is inserted into the charging slot. If there is no battery, it calls the battery in the slot into the charging slot through the automatic swapping structure; During the charging process, it continuously collects the voltage, current, and temperature data of the battery; It dynamically adjusts the charging voltage and current according to the target parameters corresponding to the charging stage to achieve multi-stage fine charging; After the battery is fully charged, it controls the automatic swapping structure to transfer the battery to the pop-out slot and introduce the next battery to continue charging.

[0019] The automatic swapping structure has a cyclic charging function, supports automatically introducing a new battery for the next round of charging after the fully charged battery pops out from the pop-out slot, and has a standby monitoring mechanism. If there is no battery to be charged in the slot, it automatically enters the low-power standby state, continuously detects the status of the slot, and automatically wakes up and starts the charging process after a new battery is inserted.

[0020] Embodiment 2: As Figure 2 shown, a control method for an automatic battery swapping and charging battery module for integrated wind-solar power generation includes the following steps: S1: Obtain the input power parameters of the integrated wind-solar power generation system under different operating scenarios, combine the operating parameters of the battery module, and construct a charging state feature data set using a feature aggregation algorithm.

[0021] The process of constructing the charging state feature data set using the feature aggregation algorithm in S1 is as follows: Collect the photovoltaic power output, grid power feeding ratio, wind energy volatility parameters, and environmental meteorological factors of the integrated wind-solar power generation system during different operating periods, and simultaneously obtain the operating characteristics of the battery module such as voltage, current, temperature, and state of charge; obtain the power output value of the photovoltaic module, the volatility parameters of wind energy, the grid power feeding ratio, and environmental meteorological factors to comprehensively reflect the input state of renewable energy; simultaneously record the operating state parameters of the battery module, including voltage, current, temperature, and state of charge, to ensure obtaining the corresponding relationship between energy input and the response of the storage unit. All collected data needs to be timestamped and continuously recorded at a unified sampling period; Perform data standardization on the collected data to unify the scale range of each feature data, and construct time series samples of the charging state through the time window mechanism; for the collected data of multiple physical quantities, use the standardization processing method to unify the numerical ranges of different dimensional features. For example, through Z-score standardization or Min-Max normalization, map various features to the same scale interval to avoid affecting subsequent analysis due to unit or order of magnitude differences. Based on the set time window mechanism, slice the continuous data to construct time series samples of the charging state with time continuity; Introduce the moving average and weighted dynamic smoothing algorithms to extract representative statistical features reflecting the actual response behavior of the battery module; use the moving average algorithm to denoise the data within each time window to eliminate the interference of high-frequency fluctuations, and introduce the weighted dynamic smoothing algorithm to extract representative statistical features within each time window, such as mean value, maximum value, minimum value, standard deviation, change rate, etc., to quantify the dynamic behavior characteristics of the charging process; Based on the multi-dimensional feature fusion mechanism, jointly aggregate the wind-solar power generation input features and the battery module response features to form a multi-source heterogeneous fusion feature vector; after aligning the input features related to wind-solar power generation and the response features of the battery module according to the time stamp, aggregate them through the multi-dimensional feature fusion mechanism, splice the environmental input features and the battery response features within the same time window, and combine the weighted strategy or fusion algorithm to extract the most representative information to construct a fusion feature vector that can simultaneously reflect the input disturbance and the response behavior. The feature vector has the integration ability of multi-source heterogeneous features and can comprehensively describe the charging state at that moment; construct a charging state feature data set with the aggregated multi-dimensional feature vector.

[0022] S2: Based on the charging state feature data set, apply the hierarchical clustering algorithm and the charging stage recognition model to segment and identify the charging process, distinguish typical charging states, and automatically match the stage target charging parameters according to the battery type.

[0023] The process of segmenting and identifying the charging process by applying the hierarchical clustering algorithm and the charging stage recognition model in the above S2 is as follows: Input the constructed charging state feature data set into the hierarchical clustering model, and perform clustering analysis on different charging states by combining the Euclidean distance and the Mahalanobis distance joint similarity metric; use the previously constructed charging state feature data set as the input data and input it into the hierarchical clustering model for preliminary analysis. Adopt the joint similarity metric method that combines the Euclidean distance and the Mahalanobis distance, introduce the covariance structure between features on the basis of considering numerical differences, enhance the ability to depict the internal correlation between different charging states, and construct a hierarchical merged clustering tree structure through the distance matrix; Set the hierarchical depth control parameter of the clustering tree, and retain the charging stage clusters with significant representativeness through the pruning strategy; introduce the pruning strategy to trim the clustering tree structure, filter out redundant small classes with too deep levels or unclear boundaries, and only retain the clustering clusters with significant representativeness; each retained cluster corresponds to a potential stage in the charging process, with a consistent characteristic behavior pattern and physical meaning; For each type of cluster, use the charging stage recognition model to classify its label and determine whether it belongs to typical stages such as constant current charging, constant voltage charging, trickle charging, and maintenance charging; for each clustering cluster, input it into the trained charging stage recognition model to perform discriminant analysis on its overall feature distribution; according to the model determination result, classify each type of cluster into the typical charging stage labels, such as constant current charging stage, constant voltage charging stage, trickle charging stage, maintenance charging stage, etc., to complete the transition from unsupervised clustering to supervised recognition; During the recognition process, combine historical annotation data with the model supervision and verification mechanism to improve the accuracy and generalization ability of segment recognition; Finally, form the multi-stage segmentation result of the charging process.

[0024] The process of automatically matching the stage target charging parameters according to the battery type in S2 is as follows: According to the segmentation recognition result, call the built-in battery type recognition module of the system to obtain the type of the battery module currently connected to the charging process, including lithium-ion batteries, lithium iron phosphate batteries, nickel-metal hydride batteries, etc.; According to the identified battery type, match the corresponding stage voltage, current, and temperature rise safety threshold parameters in the preset charging parameter database; according to the identified battery type, access and match the locally preset charging parameter database, which stores the standard target parameters of various battery types at different charging stages, including: the target current and voltage range in the constant current stage; the target voltage and termination current threshold in the constant voltage stage; the target power and time lower limit in the trickle stage; safety control parameters, such as the upper limit of the temperature rise rate and the critical value of the internal resistance increase; extract the stage target voltage, current, temperature rise and other parameter templates matching the current battery type; During the target parameter matching process, consider influencing factors such as the ambient temperature, battery cycle life status, and health, and dynamically adjust the adaptation interval of the target parameters; on the basis of performing standard parameter matching, further introduce a dynamic adaptation mechanism to adjust the stage target parameters to adapt to the actual working conditions, mainly including: The current ambient temperature: if the ambient temperature is too high, appropriately reduce the upper limit of the constant current or shorten the constant voltage duration; The battery cycle life status: if it is already in the high aging stage, increase the safety margin and reduce the peak current; Battery health: Dynamically adjust the termination condition according to the SOH value. For example, if SOH < 80%, trickle charging will be terminated in advance; Combine the charging stage classification tags, automatically bind the target parameter templates for each stage, and form a complete charging stage target parameter configuration file; Structurally bind the target parameters after adaptation according to the stage classification tags and form a complete target configuration file: Bind the target current, voltage, and termination conditions for the constant current stage; Bind the target voltage and current threshold for the constant voltage stage; Bind the target power and maintenance duration for the trickle charging stage; The configuration file is used as the input constraint condition for the reinforcement learning controller and the voltage and current adjustment mechanism, and is dynamically referenced in the actual control process.

[0025] S3: According to the identified charging stage, combine the reinforcement learning control strategy to construct a real-time voltage and current adjustment mechanism, and dynamically adjust the output power according to the battery response feedback during the charging process.

[0026] The process of constructing the real-time voltage and current adjustment mechanism by combining the reinforcement learning control strategy in S3 is as follows: Based on the stage target charging parameter configuration file, set the reward function of the reinforcement learning model. The goal is to minimize the charging time and maximize the energy conversion efficiency, while ensuring that the safety indicators during the charging process are not triggered; According to the control requirements of the charging system in different stages, construct the stage target charging parameter configuration file, and set indicators including the target charging time, energy conversion efficiency, and safe operation constraints; Based on this, design the reward function of the reinforcement learning model: Give positive rewards when the charging time is shortened and the energy conversion efficiency is improved; If safety warnings such as overheating, overvoltage, or current overshoot occur during the charging process, a penalty term will be imposed; At the same time, introduce a penalty smoothing coefficient to balance the relationship between policy exploration and stability. The reward function drives the model to tend to generate control actions that take into account both efficiency and safety during the control policy training process. Define the state space as the current SOC, voltage, current, and environmental temperature parameters of the battery, and the action space as the amplitude values for adjusting the output power and the charging voltage and current; Use the proximal policy optimization algorithm for control policy training. The reinforcement learning model continuously updates the policy through online feedback; By simulating multiple charging cycles, the reinforcement learning agent generates control actions based on the policy network and obtains feedback from the environment, iteratively updating the policy network and the value function network; Use the clipped objective function and the experience replay mechanism to improve the policy stability and sample utilization rate during the training process; Perturbation factors can be introduced during the training process to simulate abnormal scenarios; During the actual charging process, the control model dynamically generates control actions according to the real-time feedback signals of the battery module, such as voltage mutation rate, current volatility, etc.

[0027] S4: During the dynamic charging control process, the response stability index of the battery module is evaluated in real time, and whether the charging parameters reach the stable range is monitored. If so, the automatic binning strategy is triggered, and the battery packs with similar charging states are preferentially selected to access the charging process.

[0028] The process of monitoring whether the charging parameters reach the stable range in S4 is as follows: During the execution of the real-time voltage and current adjustment mechanism based on reinforcement learning, the key response parameters of the currently connected battery module are continuously collected, including but not limited to voltage, current, temperature rise rate, internal resistance change rate, etc., and multiple points of these parameters are recorded within the set time sliding window; For each key parameter, the sliding window statistical algorithm is applied to calculate the mean value, standard deviation and volatility within the window period, and compared with the preset stability threshold; Set the stable range judgment criteria, including the maximum allowable volatility, the minimum mean change rate, and the stability factor of the coupling relationship between parameters, and construct a multi-factor stability evaluation index system; preset the stability judgment threshold for each key parameter, including but not limited to: the maximum allowable volatility; the minimum mean change rate; the parameter coupling stability factor: for example, the temperature rise rate and the current change should be negatively correlated. If the correlation coefficient |r| < 0.3, it is determined to be unstable; these indicators constitute a multi-factor stability evaluation index system, which is used to determine whether the current charging process is in a convergent and stable state.

[0029] If the volatility of the key parameter is less than the set stable threshold in multiple consecutive sliding window periods, it is determined that the charging process of the current battery module has entered the convergent and stable state; If the volatility of the key parameter is greater than or equal to the set stable threshold in multiple consecutive sliding window periods, it is determined that the charging process of the current battery module has not entered the convergent and stable state.

[0030] S5: Apply the multi-source scheduling optimization algorithm to dynamically allocate the wind-solar power generation resources, and revise the charging scheduling plan in real time to generate an energy efficiency optimization report.

[0031] The process of generating the energy efficiency optimization report in S5 is as follows: After completing the charging stage control and the automatic binning process, the utilization efficiency, average conversion efficiency and binning response delay of the wind-solar power generation resources during the entire charging process are counted; Utilization efficiency of wind-solar power generation resources: Compare the actual output power of the photovoltaic module and the wind power unit with the theoretical maximum output power, and calculate the average utilization rate; Average energy conversion efficiency: Statistically calculate the ratio of the total input power of wind and light to the total energy effectively absorbed by the battery module, which reflects the end-to-end energy transmission efficiency; Adjustment response time delay: Record the interval between the time when the automatic adjustment instruction is issued and the time when the battery pack is actually switched over. Extract the average value and the maximum value of multiple responses as the evaluation index for the system control reaction speed; Combine the energy received by each module during the charging process and the achievement rate of the target charging parameters, and calculate the comprehensive energy efficiency index, including the energy input density per unit time and the number of scheduling times per unit of electricity; Calculate the following energy efficiency related parameters: Energy reception statistics: Statistically calculate the energy absorbed by each module per unit time to form a module-energy mapping table; Target parameter achievement rate: Judge whether each module reaches the preset charging voltage / current target in each stage, and statistically calculate the achievement ratio; Energy input density per unit time: Reflect the energy charging efficiency completed by the system as a whole within a certain time window; Number of scheduling times per unit of electricity: Evaluate the number of adjustment / scheduling actions required for the system to charge 1 kWh of energy, and use it to judge the complexity and energy consumption of the control strategy; Introduce a multi-source scheduling optimization algorithm to analyze the resource scheduling path and battery pack switching strategy during the completed charging process, and identify existing redundant paths and energy consumption waste points; Use the recorded wind-solar power output flow direction, battery pack switching sequence, power adjustment curve, etc. in the system to reconstruct the actual resource scheduling path diagram; Identify path nodes with high frequency but low benefits, and mark them as scheduling redundant points; Analyze the energy loss areas caused by factors such as time delay and path overlap in the path, and determine them as energy consumption waste points to provide a basis for subsequent optimization; Combine the system operation log and the charging behavior record to automatically generate an energy efficiency optimization report including content such as the energy utilization efficiency curve, scheduling strategy optimization suggestions, and battery performance evolution trend diagram.

[0032] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0033] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An automatic tuning bin charging battery module control system for integrated wind and solar power generation, characterized in that, Including: DC conversion module: The charging input terminal is connected to the power generation bus of the wind-solar integrated power generation system, and the charging output terminal is connected to the charging battery in the charging tank, which is used to convert the power input from the power generation bus into an output power supply with adjustable voltage; Automatic battery transfer mechanism: It includes a charging tank, a pop-up tank, multiple slots and a battery transfer mechanical structure. The slots are used to store the batteries to be charged. The transfer mechanical structure sequentially sends the batteries to be charged into the charging tank and transfers the batteries to the pop-up tank after they are fully charged; Control module; According to the real-time data of the charging battery obtained by the voltage sampling module, current sampling module and temperature monitoring module, it adjusts the output voltage and current of the DC conversion module to control the charging process.

2. The automatic bin adjustment charging battery module control system for integrated wind and solar power generation according to claim 1, wherein The control process executed by the control module includes: Detect the status of each sub-module after starting the system; Detect whether there is a battery inserted into the charging tank. If there is no battery, call the battery in the slot into the charging tank through the automatic battery transfer structure; During the charging process, continuously collect the voltage, current and temperature data of the battery; Dynamically adjust the charging voltage and current according to the target parameters corresponding to the charging stage to achieve multi-stage fine charging; After the battery is fully charged, control the automatic battery transfer structure to transfer the battery to the pop-up tank and introduce the next battery to continue charging.

3. The automatic storage bin adjustment and charging battery module control system for integrated wind and solar power generation according to claim 1, wherein, The automatic battery transfer structure has a cyclic charging function, supports automatically introducing a new battery for the next round of charging after the fully charged battery pops out of the pop-up tank, and has a standby monitoring mechanism. If there is no battery to be charged in the slot, it automatically enters the low-power standby state, continuously detects the slot status, and automatically wakes up and starts the charging process after a new battery is inserted.

4. A control method for an automatic bin - adjusting charging battery module for integrated wind - solar power generation, which is applied to the system described in any one of claims 1 - 3, and is characterized in that, Including the following steps: Obtain the input power parameters of the wind-solar integrated power generation system under different operating scenarios, combine the operating parameters of the battery module, and use the feature aggregation algorithm to construct a charging state feature dataset; Based on the charging state feature dataset, apply the hierarchical clustering algorithm and the charging stage recognition model to segment and identify the charging process, distinguish typical charging states, and automatically match the stage target charging parameters according to the battery type; According to the identified charging stage, combine the reinforcement learning control strategy to construct a real-time voltage and current adjustment mechanism, and dynamically adjust the output power according to the battery response feedback during the charging process; During the dynamic charging control process, real-time evaluate the response stability index of the battery module, monitor whether the charging parameters reach the stable interval. If so, trigger the automatic battery transfer strategy and preferentially select the battery group with similar charging states to access the charging process; Apply the multi-source scheduling optimization algorithm, dynamically allocate the wind-solar power generation resources, and make real-time corrections to the charging scheduling plan to generate an energy efficiency optimization report.

5. The control method of an automatic bin-adjusting charging battery module for integrated wind-solar power generation according to claim 4, wherein The process of constructing the charging state feature dataset using the feature aggregation algorithm is as follows: Collect the photovoltaic power output, grid power feeding ratio, wind energy volatility parameters and environmental meteorological factors of the wind-solar integrated power generation system at different operating times, and simultaneously obtain the operating characteristics of the battery module; Perform data standardization processing on the collected data, unify the scale range of each feature data, and construct a time series sample of the charging state through the time window mechanism; Introduce the moving average and weighted dynamic smoothing algorithms to extract representative statistical features; Based on the multi-dimensional feature fusion mechanism, the input features of wind-solar power generation and the response features of the battery module are jointly aggregated to form a multi-source heterogeneous fusion feature vector; Construct a charging state feature dataset with the aggregated multi-dimensional feature vector.

6. The control method of an automatic bin-adjusting charging battery module for integrated wind-solar power generation according to claim 5, characterized in that, The process of segmenting the charging process using the hierarchical clustering algorithm and the charging stage recognition model is as follows: Input the constructed charging state feature dataset into the hierarchical clustering model, and perform clustering analysis on different charging states by combining the Euclidean distance and the Mahalanobis distance joint similarity metric; Set the hierarchical depth control parameter of the clustering tree, and retain the charging stage clusters through the pruning strategy; For each cluster, use the charging stage recognition model to perform label classification and determine whether the label belongs to the typical stage; During the recognition process, combine the historical annotation data and the model supervision and verification mechanism; Finally, form the multi-stage segmentation result of the charging process.

7. A control method for an automatic bin-adjusting charging battery module for integrated wind-solar power generation according to claim 6, characterized in that The process of automatically matching the stage target charging parameters according to the battery type is as follows: According to the segmentation recognition result, call the built-in battery type recognition module of the system to obtain the type of the battery module currently connected to the charging process; According to the identified battery type, match the corresponding stage voltage, current, and temperature rise safety threshold parameters in the preset charging parameter database; During the target parameter matching process, consider the influencing factors and dynamically adjust the adaptation interval of the target parameters; Combine the charging stage classification label to automatically bind the target parameter template of each stage to form a complete charging stage target parameter configuration file.

8. A control method for an automatic bin-adjusting charging battery module for integrated wind-solar power generation according to claim 7, characterized in that The process of constructing the voltage and current real-time adjustment mechanism by combining the reinforcement learning control strategy is as follows: Based on the stage target charging parameter configuration file, set the reward function of the reinforcement learning model, with the goal of minimizing the charging time and maximizing the energy conversion efficiency; Define the state space as the current SOC, voltage, current, and environmental temperature parameters of the battery, and the action space as the amplitude values for adjusting the output power and the charging voltage and current; Use the proximal policy optimization algorithm to train the control strategy, and the reinforcement learning model continuously updates the strategy through online feedback; During the actual charging process, the control model dynamically generates control actions according to the real-time feedback signal of the battery module.

9. A control method for an automatic bin-adjusting charging battery module for integrated wind-solar power generation according to claim 8, characterized in that, The process of monitoring whether the charging parameters reach the stable interval is as follows: During the execution of the voltage and current real-time adjustment mechanism based on reinforcement learning, continuously collect the key response parameters of the currently connected battery module, and perform multi-point recording of the above parameters within the set time sliding window; For each key parameter, use the sliding window statistical algorithm to calculate the mean, standard deviation, and volatility within the window period, and compare them with the preset stability threshold; Set the stable interval judgment criterion and construct a multi-factor stability evaluation index system; If the volatility of the key parameter is less than the set stability threshold in consecutive multiple sliding window periods, it is determined that the charging process of the current battery module has entered the convergence and stable state; If the volatility of the key parameter is greater than or equal to the set stability threshold in consecutive multiple sliding window periods, it is determined that the charging process of the current battery module has not entered the convergence and stable state.

10. The control method of an automatic bin-adjusting charging battery module for integrated wind-solar power generation according to claim 9, wherein, The process of generating the energy efficiency optimization report is as follows: After completing the charging stage control and automatic warehouse adjustment process, calculate the utilization efficiency, average conversion efficiency, and warehouse adjustment response delay of wind and solar power generation resources during the entire charging process; Combined with the energy received by each module during the charging process and the achievement rate of the target charging parameters, calculate comprehensive energy efficiency indicators, including the energy input density per unit time and the number of power dispatch times per unit of electricity; Introduce a multi-source scheduling optimization algorithm to analyze the resource scheduling path and battery pack switching strategy during the completed charging process, and identify existing redundant paths and energy consumption waste points; Automatically generate an energy efficiency optimization report in combination with the system operation log and charging behavior record.

Images