Lithium ion battery centralized charging management system

Abstract

The invention relates to the technical field of battery charging, in particular to a lithium ion battery centralized charging management system, which comprises a state acquisition module, a state management module, a state retrieval module and a charging inspection module, the method comprises the following steps: determining a currently charged target battery and charging nodes of each battery, and taking current, voltage and temperature of each charging node as the charging state of the target battery; based on the charging state of the target battery, peak conditions of current and voltage of each charging node are introduced, and the transition probability and the peak probability of each charging state under the peak conditions are analyzed; selecting a target charging state according to the charging state of the target battery and the peak probability, comparing whether the charging nodes of the target charging state in two adjacent retrieves are consistent or not, and if yes, recording the charging nodes; comparing the recording times of the charging nodes, judging whether each charging node is abnormal or not, and completing the retrieval of each charging node; the efficiency of battery centralized charging and the accuracy of charging node selection are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of battery charging, in particular to a centralized charging management system for lithium-ion batteries. Background Art

[0002] With the increasing popularity of electric vehicles and energy storage systems, the demand for centralized lithium-ion battery charging has surged. Traditional charging technologies struggle to meet the demands for large-scale, efficient, and safe charging. Due to the varying states of different batteries, different charging nodes are needed to adjust the current battery charging schedule and improve the efficiency of charging node selection within the battery charging scheduling solution.

[0003] For example, Chinese patent publication number CN116154914A discloses a battery charging management method and device, wherein the method includes: obtaining an active handshake signal from the battery to be charged before charging begins; performing a self-test on the battery to be charged based on the active handshake signal to determine whether the battery to be charged has any abnormality; if the battery to be charged has no abnormality, determining a corresponding charging mode to perform a charging operation on the battery to be charged.

[0004] For example, Chinese patent publication number CN115395613A discloses a battery charging management method, device, electronic device and storage medium, wherein the method includes: obtaining a historical charging log of a target battery at at least one battery swap station; determining the charging change data and charging management attributes corresponding to the target battery in at least one charging stage based on the historical charging log of at least one battery swap station, wherein the charging management attributes include the average charging voltage, average charging current, average battery temperature and average battery voltage corresponding to the corresponding charging stage; based on the charging change data and the corresponding charging management attributes corresponding to each charging stage, determining the charging strategy of the target charging pile when charging the target battery, so as to charge the target battery based on the charging strategy.

[0005] In the prior art, the use of temperature information to match the battery status to identify abnormal battery status, and the use of recorded data during charging to describe the battery charging status are respectively described; however, these battery processings do not take into account the different charging nodes required for each battery in the scenario of centralized charging of multiple batteries, resulting in the need to schedule the current, voltage and other data of multiple charging nodes to find the node that is most suitable for charging the current battery, so as to achieve the accuracy of scheduling of each charging node under centralized charging. Summary of the Invention

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: a centralized charging management system for lithium-ion batteries, including: a status acquisition module, used to determine the target battery currently being charged and the charging nodes of each battery, and use the current, voltage and temperature of each charging node as the charging status of the target battery.

[0007] The state management module is used to introduce the peak conditions of the current and voltage of each charging node based on the charging state of the target battery, and determine the charging state value of each charging node under peak conditions; analyze the transition probability of each charging state under peak conditions, and if the transition probability is greater than a preset threshold, obtain the charging cycle of each charging node, perform threshold search on each charging point based on the charging cycle, and determine the peak probability under each charging state.

[0008] The state retrieval module is used to control battery charging based on the peak probability under each charging state, select the target charging state according to the charging state and peak probability of the target battery, compare whether the target charging state is consistent at the charging nodes retrieved twice in a row, and record the charging node if they are the same.

[0009] The charging inspection module is used to compare the number of times recorded by the charging nodes, determine whether each charging node is abnormal, and complete the retrieval of each charging node.

[0010] The beneficial effects of the present invention are as follows: 1. The present invention collects multi-dimensional data such as current, voltage, and temperature in real time, and uses the connection relationship between nodes to build a global map. Then, based on the connection relationship between the target battery and multiple charging nodes, the target battery is combined with the charging nodes distributed at the edge to ensure high-frequency sampling during data processing, providing a basis for subsequent status management.

[0011] 2. The present invention obtains the corresponding peak value, establishes the state interval, and quantifies the situation where the current and voltage peak values appear in different intervals through the transition probability, so as to verify how each charging node performs the corresponding state transition when reaching the peak state, so that the relevant dynamics of multiple charging nodes related to the target battery in the centralized charging scenario can be identified in time, which is convenient for selecting the corresponding charging node to adjust the charging status of the target battery under the battery scheduling decision; at the same time, the change trend of the target battery and the related charging nodes can be identified according to the transition probability, which is convenient for early warning of the peak value that exceeds the normal range, and realizes the scheduling management of multiple charging nodes, anomaly detection and node status query in the centralized charging scenario.

[0012] 3. The present invention obtains query records of charging nodes based on the target battery and the node type of each node, as well as the different situations of each charging node during retrieval, and generates a minimum common subset corresponding to each charging node. It then classifies the charging node status and makes abnormal decisions by identifying abnormal probabilities, thereby realizing the retrieval of the optimal operating charging node in multiple scenarios such as charging scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below with reference to the accompanying drawings and examples.

[0014] Figure 1 It is a system framework diagram of a lithium-ion battery centralized charging management system.

[0015] Figure 2 The present invention is a flow chart of a state management module of a lithium-ion battery centralized charging management system.

[0016] Figure 3 The present invention is a flow chart of a status retrieval module of a centralized charging management system for lithium-ion batteries.

[0017] Figure 4 The present invention is a flow chart of a charging inspection module of a centralized charging management system for lithium-ion batteries. DETAILED DESCRIPTION

[0018] The following embodiments of the present invention are described in detail. The embodiments described below are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention. Where specific techniques or conditions are not specified in the embodiments, the techniques or conditions described in the literature in the art or in the product specifications shall be followed.

[0019] See Figure 1 A lithium-ion battery centralized charging management system includes: a status acquisition module, a status management module, a status retrieval module and a charging inspection module; wherein the output end of the status acquisition module is connected to the status management module, the output end of the status management module is connected to the status retrieval module, and the output end of the status retrieval module is connected to the charging inspection module.

[0020] The state acquisition module is used to determine the target battery currently being charged and the charging nodes of each battery, and use the current, voltage and temperature of each charging node as the charging state of the target battery.

[0021] The state management module is used to introduce the peak conditions of the current and voltage of each charging node based on the charging state of the target battery, and determine the charging state value of each charging node under peak conditions; analyze the transition probability of each charging state under peak conditions, and if the transition probability is greater than a preset threshold, obtain the charging cycle of each charging node, perform threshold search on each charging point based on the charging cycle, and determine the peak probability under each charging state.

[0022] The state retrieval module is used to control battery charging based on the peak probability under each charging state, select the target charging state according to the charging state and peak probability of the target battery, compare whether the target charging state is consistent at the charging nodes retrieved twice in a row, and record the charging node if they are the same.

[0023] The charging inspection module is used to compare the number of times recorded by the charging nodes, determine whether each charging node is abnormal, and complete the retrieval of each charging node.

[0024] The charging node of each battery represents a unit that can be connected to the target battery, such as a physical data interface. The charging node can collect battery status data to execute battery control instructions. Usually, the target battery corresponds to at least one charging node. At the same time, the target battery represents the object that the current charging strategy mainly regulates, including one or more target batteries.

[0025] When the collector is in charging state, the status acquisition module describes the charging status of the target battery by the position of each charging node and the collected current, voltage and temperature. It also records the situation where the current and voltage reach the maximum value, and records the normal completion of a charging cycle to evaluate whether the battery charging status has changed.

[0026] Therefore, the implementation method of the status acquisition module includes: using the location of each charging node to calculate the average current, voltage and temperature of each charging node, and using the connection relationship between each charging node to establish a mapping relationship between the target battery, charging node and charging status.

[0027] Each charging node is connected in sequence according to the average value of its current, voltage and temperature to obtain a mapping relationship between at least one charging node and the charging state; the charging node and the charging state are combined according to the corresponding target battery to obtain a mapping relationship between the target battery, the charging node and the charging state.

[0028] The connection relationship between each charging node will explain how the charging nodes set for multiple target batteries are connected in the centralized battery charging scenario. The required mapping relationship is formed according to the connection form of these charging nodes. It is convenient to detect whether the current or voltage peak of a charging node is too high or the probability of occurrence is too high, which will affect the charging of multiple target batteries and thus create charging risks. At the same time, in addition to the average value of the current and voltage values collected, the peak values near the upper and lower limits are actively determined to verify whether the current fluctuation is abnormal.

[0029] Here, emphasis is placed on evaluating and selecting the node most suitable for charging the target battery based on the real-time operating parameters of the charging node, such as current, voltage, and temperature. This ensures that the selected charging node can not only meet the basic charging requirements of the target battery, but also can charge under optimal conditions, thereby ensuring charging efficiency and battery health.

[0030] Preferably, determining the target battery currently being charged and the charging nodes of each battery also includes: determining the number of target batteries and charging nodes, and sequentially detecting the current, voltage and temperature of the target batteries and charging nodes under different numbers; if the current, voltage and temperature are in an abnormal state, the data of the time period corresponding to the abnormal state is output as the charging state of the target battery.

[0031] In one embodiment of the present invention, the peak condition indicates that during the time period when the current peak or voltage peak occurs at each charging node, a parameter such as voltage, current, or temperature significantly exceeds its normal fluctuation range in a short period of time, reaching or approaching a safety threshold, and a transient abnormal state occurs. The time point when this abnormal state is reached and the value of a certain parameter are used as the peak state identified at this time. At the same time, this transient abnormal state can also be marked with a label, and the marked label is used as the peak condition.

[0032] For example, the peak conditions obtained are mainly based on the values of current and voltage. When the moving average value of voltage or current in a continuous time window exceeds its standard safety threshold and appears for more than 3 consecutive sampling points, the data is recorded and marked as a peak condition. At the same time, the corresponding time point and the corresponding value range of the peak condition are recorded. At this time, the safety threshold can be set by selecting the average value in the historical data plus three times the standard deviation to verify the current potential peak, and identify the abnormal state that approaches or exceeds the safety threshold.

[0033] The voltage and current within this time period are then segmented to obtain multiple state intervals, each of which represents a different range of voltage and current values. The state intervals are used to calculate the voltage and the probability of the voltage reaching each state interval. For example, after using the implicit Maldivian model to calculate its probability transfer, the charging cycles in which these voltage and current intervals exist are selected to identify charging time periods with voltage and current correlation peak problems.

[0034] like Figure 2 As shown, the transfer probability of each charging state under peak conditions can be expressed as follows: regional planning of charging nodes and encoding of charging nodes in a preset order; obtaining at least one peak condition of the target battery, and establishing the state interval between each charging node based on the numerical interval corresponding to the peak condition.

[0035] Based on the state interval in which the peak conditions of the charging node occur, a transfer probability model for a single charging node is established. Based on the charging state value of the target battery and the adjacent charging nodes at the most recent moment, a transfer probability model for multiple charging nodes is established. Based on the state interval, the peak conditions of each charging node in the same charging cycle are compared to see whether they are consistent. If the peak conditions are consistent, the transfer probability of the corresponding charging state is calculated using the transfer probability model of a single charging node. If the peak conditions are inconsistent, the transfer probability of the current adjacent charging cycle is calculated using the transfer probability model of multiple charging nodes.

[0036] The single-node transfer probability model is a direct model established for a single charging node based on its peak condition state interval. This model reflects the dynamic characteristics of the node during independent operation by quantifying the node's jump probability in different state intervals; that is, it describes the current, voltage, and temperature values of a single node in different time periods during charging.

[0037] The transfer probability model for multiple charging nodes is extended to multiple charging nodes. The combined charge state value of the target battery and the spatiotemporal correlation of adjacent nodes form a joint transfer probability model. This model describes the overall behavioral characteristics of the charging network by introducing a coupling relationship between nodes. It is mainly used to indicate whether there are anomalies in the current, voltage, and temperature of multiple groups of adjacent charging nodes at the closest moment, to demonstrate that each charging node can perform charging distribution normally. That is, the adjacent charging node closest to the charging stage of the target battery on the charging timeline is used as the analysis target to determine the charging nodes that are closely related in time, space, or function. For example, when the target battery experiences a voltage or current peak, the charging parameters of the adjacent nodes are adjusted to prevent system-level overload, thereby achieving common state recognition and control of multiple charging nodes.

[0038] The results of the two models are then evaluated using a unified charging cycle approach, with peak conditions at each charging node simultaneously verified. If the peak conditions of all nodes match, the model for a single charging node is used for calculations, and the coordinated transition probabilities between state intervals are determined using the state intervals of all charging nodes. If peak conditions are inconsistent, the multi-node model is used to switch to adjacent groups of charging nodes at nearby moments for analysis, identifying the transition probabilities of their charging states across the cycle.

[0039] The transition probability for a single node is calculated using the Bayesian theorem across all state intervals within the current charging cycle. For multiple nodes, the Markov Chain Monte Carlo method is used to estimate the transition probability distribution using sampled data from adjacent cycles, sequentially describing the relative distribution probabilities of the current, voltage, and temperature of the current target battery.

[0040] For the state interval where the peak condition does not occur, the transition probability model of a single charging node is used to calculate the transition probability of the peak interval from the state interval where the peak condition does not occur to the adjacent state interval, which is used as the output transition probability.

[0041] For the state interval where the peak condition does not occur, the global state interval analysis is used to explain the probability of the interval size changing of the numerical interval corresponding to the current, voltage and temperature when there is no peak condition, using the transition probability from the state interval to the adjacent state interval.

[0042] Preferably, the transfer probability model of a single charging node is expressed as: the current represented by the charging state ,Voltage and temperature , the Bayesian theorem of the set corresponds to the value of the posterior probability to set the transition probability of a single charging node; the transition probability of a single charging node represents the variable represented by the state interval with peak conditions at the corresponding moment from one state to another, such as the value from 3.8V to 3.9V, which represents the data-oriented change relationship. Assume that the state variables corresponding to current, voltage and temperature are , the state variable represents the value of current, voltage and temperature at time t. At this time, since it is for three variables, when calculating, it will be judged by extracting the value from the observed time series according to whether the state variable belongs to any of current, voltage and temperature; the value of current, voltage and temperature observed at time t is composed of , ;in, 、 、 Represent the values of current, voltage and temperature at time t respectively.

[0043] Then we get the posterior probability: ;in, represents the posterior probability, Represents a time series of observations, representing the posterior probability of the corresponding state variable from the first value to the t-th value; Represents the likelihood probability, indicating that Observed probability; Represents the prior probability, which means that the When, status The probability of , that is, the value represented by its probability at t-1; represents the probability of evidence, a constant used for normalization to ensure that the sum of its posterior probabilities is 1, , combining the corresponding likelihood probabilities and prior probabilities according to their corresponding state variables to obtain their product sum. After completing the corresponding posterior probability calculation, the resulting multiple posterior probabilities can be used to determine the relative probabilities of each value during the transition within the state interval corresponding to the current peak condition. This allows us to understand whether the current, voltage, and temperature of the target battery fluctuate frequently and whether there are any sudden increases, thus preventing failures at individual nodes.

[0044] The likelihood probability is obtained by calculating the observed current, voltage and temperature in the form of Gaussian distribution and expressing them in terms of the probability value corresponding to the Gaussian distribution, such as ;in, represents the average value of the current, Represents the standard deviation of the current. When the state variable is current, this method is used to set its likelihood probability. The same method is used when the state variables are voltage and temperature. Finally, the probability product of the sum of these three is used as the output transition probability to represent the changes in the data related to the corresponding single charging node in its state interval.

[0045] Then, for the state intervals where the peak conditions do not appear, the transfer probability model of a single charging node is used, and the adjacent state intervals are used as the main calculation interval content to obtain the calculated transfer probability.

[0046] Preferably, the transfer probability model of multiple charging nodes is expressed as follows: taking any two charging nodes from the multiple charging nodes as a group, obtaining multiple sampling points at the closest moments in adjacent charging cycles to form their state vectors: and the state vector , ; , these two state vectors indicate that the two charging nodes selected at this time meet the charging state value of the target battery and the adjacent charging nodes at the closest moment. There are N elements in the state vector.

[0047] Then calculate its state distribution vector as the output transition probability.

[0048] ;in, The state distribution vector representing the probability of being in state vector x at time t+1, indicating that the system is in; The state distribution vector represents the probability of being in state vector y at time t. The state vector y at this time describes the joint distribution probability of multiple values collected by it, which represents the correlation between multiple charging nodes at adjacent times. The sum of y represents the calculation method of summing and accumulating the elements existing in the state vector y at the closest time. Represents the probability of going from state vector y to state vector x. This probability represents the conditional probability, that is, the conditional probability of two charging nodes selecting two values at the same time. This data can be calculated through historical data. At this time, the values of the state distribution vectors calculated respectively for current, voltage, and temperature are multiplied and used as the output transition probability.

[0049] The implementation method of determining the peak probability under each charging state also includes: obtaining the maximum charge capacity of the corresponding target battery in each state interval, and extracting the peak condition under the corresponding charging cycle based on the charging cycle required for the maximum charge capacity.

[0050] Each state interval is managed in batches, based on the state interval corresponding to the peak condition. When the same peak condition is met in each state interval, the peak probability for each charging state is recorded and output. The peak probability represents the ratio of the data volume corresponding to the peak condition to the data volume within the current state interval, indicating the probability of the peak condition occurring.

[0051] At the same time, for the preset threshold value greater than the transition probability, the preset threshold value is set based on historical data, and the 95% score value of the transition probability in the historical data is adopted as the preset threshold value used here; it should be noted that the preset threshold value of the transition probability will adjust the threshold value of the historical data corresponding to the corresponding model according to the different models selected by the transition probability to describe the data extraction of multiple models.

[0052] In one embodiment of the present invention, the implementation method of selecting the target charging state based on the charging state and peak probability of the target battery in the state retrieval module includes: counting the peak probability of each target battery in each charging state and recording the probability of an abnormal event occurring in the target battery; taking the target battery where the abnormal event occurs as the starting point, and selecting the charging state of the charging node adjacent to the target battery as the target charging state.

[0053] like Figure 3 As shown, the implementation method of comparing the target charging status of the charging nodes retrieved twice adjacently in the status retrieval module includes: taking the charging node as input data, comparing whether the node type of each charging node is an alternative charging type, and retrieving the charging node with the target charging status retrieved for the first time.

[0054] The implementation method of comparing whether the node type of each charging node is an alternative charging type also includes: if it is an alternative charging type, respectively extracting the charging status of the corresponding charging node to form a state interval corresponding to each charging node, calculating the similarity between each state interval based on the maximum peak probability in each state interval, and taking the charging node corresponding to the group of state intervals with the largest similarity value as the charging node for the first search.

[0055] If it is not an alternative charging type, the charging occupancy cost of the corresponding charging node is obtained, where the charging occupancy cost is the ratio of the time when the current flows through the charging node during charging in the network corresponding to the overall charging node to the charging time of the entire network; using the charging occupancy cost as the search condition, the charging node corresponding to the target battery during charging is retrieved, and the corresponding charging node is used as the charging node for the first search.

[0056] Based on the guided charging sequence of each charging node, each charging node is searched to obtain the charging node whose target charging state is in the second search.

[0057] Guiding charging sequence refers to the process of assigning charging priority or queuing order to devices to be charged among multiple charging nodes; this process includes but is not limited to the time when the device starts connecting, the remaining power of the target battery, the device type corresponding to the target battery, and the charging power of the target battery. These will determine the priority of the target battery in centralized charging management and affect the time it takes for the target battery to complete charging. The charging node retrieved for the second time is mainly measured by whether the target node in the priority calculation is consistent with the current target node retrieved for the first time; at this time, the power resources under centralized management are allocated by comparing the status intervals or charging occupancy costs of the charging nodes to prevent excessive use of some charging nodes and restrictions on some charging nodes.

[0058] The second search is to select the relative priority of the charging node for explanation, and compare the corresponding situation of the charging node in the current first search with its priority to determine whether the charging node used by the current target battery can achieve the optimal one.

[0059] The first search mainly identifies whether there is an abnormal state, and the second search verifies the consistency of its nodes to ensure that the abnormal nodes are not selected repeatedly; it prevents the charging node data from being relatively independent and not being centrally integrated, resulting in asymmetric actual detection data of each node under global analysis and abnormal node selection.

[0060] That is, the implementation method of the second search for the charging node includes: using the time when the device starts connecting, the remaining power of the target battery, the device type corresponding to the target battery and the charging power of the target battery as the charging tag of the charging node.

[0061] The charging node is searched with the charging tag to obtain the charging event stream of each charging node. The charging event stream indicates whether the current charging node is charging normally, as well as the real-time charging amount, when the charging node is judged based on the time when the device starts connecting, the remaining power of the target battery, the device type corresponding to the target battery, and the charging power of the target battery. The completion time is combined with whether there are abnormal charging events as the charging event stream described at this time.

[0062] The charging event stream corresponding to the target charging state is used to generate at least one management branch, with the charging nodes within the management branch serving as the charging nodes for the second search. This management branch represents the ratio of the expected charging completion time to the normal completion time for multiple target batteries before and after charging is complete. The data corresponding to the charging of multiple groups of target batteries under these ratios serves as the management branch at this point, describing the charging nodes that have completed charging at different priorities. These groups of charging nodes that have completed charging at different priorities are then compared with the charging nodes from the first search to determine whether the current charging node is optimal.

[0063] Compare the charging nodes retrieved in the first search with those retrieved in the second search, and compare whether the charging nodes included in the first search exist in the charging nodes retrieved in the second search. If so, extract the corresponding charging nodes and record each charging node according to the data included in the two searches.

[0064] If it does not exist, based on the distribution position of each charging node during the first retrieval, take the charging node of the first retrieval as the starting point, connect the charging node of the first retrieval with the charging node of the second retrieval, obtain the shortest path between each charging node of the first retrieval and the second retrieval, and record the charging node corresponding to the shortest path.

[0065] In one embodiment of the present invention, during the charging inspection, the data marked by each charging node in each module is mainly used to analyze whether the current charging node can meet the charging needs of the current target battery, and whether the data corresponding to the charging node can meet the fast charging of the target battery in a centralized charging scenario.

[0066] like Figure 4 As shown, the implementation method of the charging inspection module includes: based on the number of records of each charging node, extracting the minimum common subset of each charging node under multiple inspections, and forming a deep query network with the elements corresponding to the minimum common subset of each charging node.

[0067] Each time a charging node retrieves a record, the status retrieval module retrieves the data. Each time a charging node retrieves a record, it performs a consistency check based on data such as peak probability, alternative charging type, charging cost, the ratio of the device's expected charging completion time to the normal completion time, and the time the relevant device started connecting. Based on this corresponding data, each charging node can be combined to verify the minimum common subset corresponding to the retrieved content. This common subset contains the retrieved content. If a charging node has a high number of records and its current, voltage, and temperature are stable, the multiple charging nodes corresponding to the minimum common subset represent nodes that can be relied upon for centralized charging. If a charging node has a low number of records, it is more likely to be designed for specific needs and can serve as a backup node for different devices. Furthermore, if the minimum common subset shows unstable current, voltage, and temperature, the number of records can be used to identify problematic charging nodes and identify charging nodes that are unstable under specific conditions, thereby enabling dynamic decision-making under various charging strategies.

[0068] For the deep query network, the minimum common subset of each charging node is used as the embedding vector, and the embedding vector is sequentially combined into the input layer, hidden layer, and output layer. The output layer outputs the abnormality probability using the Sigmoid function; the convolution kernel of the input layer is set to 3×3, and the fully connected layer set in the hidden layer is sequentially connected from 256 nodes to 128 nodes to 64 nodes. After initializing and eliminating the dimension of various data contained in the minimum common subset, the abnormality probability corresponding to the corresponding data is verified, and then this abnormality probability is associated with the number of records to find the more stable charging nodes, so as to complete the retrieval of each charging node when making charging decisions.

[0069] A deep query network is used to compare the abnormal probability of charging nodes under different recording times, and each charging node is output with the abnormal probability.

[0070] Preferably, when each charging node is output with an abnormal probability, it also includes receiving the minimum common subset of each charging node, and dividing each charging node into stable extreme value nodes and unstable extreme value nodes according to the number of records and the abnormal probability, and in turn according to the maximum and minimum values of the corresponding data in the minimum common subset within the corresponding charging cycle; stable extreme value nodes represent extreme value nodes with a large number of records and a low abnormal probability, which may represent extreme conditions in the normal charging process. These nodes will represent the charging conditions of different charging nodes after the scheduling is adjusted. These charging nodes will represent the part that each charging node can rely on after scheduling. Unstable extreme value nodes represent extreme value nodes with a small number of records but a high abnormal probability, which may represent potential faults or abnormal charging behaviors; these charging nodes represent the nodes that are mainly targeted when searching for charging nodes. At the same time, when obtaining stable extreme value nodes, their maximum values need to be verified multiple times to prevent problems such as current overload and voltage overload after scheduling.

[0071] The values of the stable extreme value nodes and the unstable extreme value nodes are monitored. If the charging nodes corresponding to the stable extreme value nodes and the unstable extreme value nodes are abnormal, the corresponding abnormal nodes will be output; otherwise, the stable extreme value nodes and the unstable extreme value nodes will be output.

[0072] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention, which are still covered by the scope of protection of the present invention.

Claims

1. A lithium-ion battery centralized charging management system, characterized in that: include: The state acquisition module is used to determine the target battery currently being charged and the charging nodes of each battery, and use the current, voltage and temperature of each charging node as the charging state of the target battery; The state management module is used to determine the state of charge value of each charging node under the peak conditions of the current and voltage of each charging node based on the target battery's state of charge. The module also analyzes the transition probability of each charging state under the peak conditions. If the transition probability is greater than a preset threshold, the module obtains the charging cycle of each charging node and performs a threshold search on each charging node based on the charging cycle to determine the peak probability of each charging state. The state retrieval module is used to control battery charging based on the peak probability of each charging state. The target charging state is selected based on the charging state and peak probability of the target battery. The target charging state is compared to see if the charging nodes retrieved from two adjacent locations are consistent. If they are the same, the charging node is recorded. The charging inspection module is used to compare the number of times recorded by the charging nodes, determine whether each charging node is abnormal, and complete the retrieval of each charging node.

2. A lithium-ion battery centralized charging management system according to claim 1, characterized in that: The implementation methods of the status acquisition module include: Based on the location of each charging node, the average value of the current, voltage and temperature of each charging node is calculated, and the connection relationship between each charging node is calculated; Each charging node is connected in sequence according to the average value of its current, voltage and temperature to obtain a mapping relationship between at least one charging node and the charging state; the charging node and the charging state are combined according to the corresponding target battery to obtain a mapping relationship between the target battery, the charging node and the charging state.

3. The lithium-ion battery centralized charging management system according to claim 1, characterized in that: Determining the target battery currently being charged and the charging node of each battery also includes: Determine the number of target batteries and charging nodes, and sequentially detect the current, voltage, and temperature of target batteries and charging nodes under different numbers. If the current, voltage, and temperature are in an abnormal state, the data for the time period corresponding to the abnormal state is output as the charging state of the target battery.

4. A lithium-ion battery centralized charging management system according to claim 1, characterized in that: The transition probability of each charging state under peak conditions can be expressed as: Perform regional planning for charging nodes and encode the charging nodes in a preset order; obtain at least one peak condition of the target battery and establish a state interval between each charging node based on the numerical interval corresponding to the peak condition; Based on the state interval of the charging node's peak condition, a transfer probability model for a single charging node is established. Based on the target battery's state of charge value and the nearest adjacent charging nodes, a transfer probability model for multiple charging nodes is established. Based on the state interval, the peak conditions of each charging node in the same charging cycle are compared to see if they are consistent. If the peak conditions are consistent, the transition probability model of a single charging node is used to calculate the transition probability of the corresponding charging state. If the peak conditions are inconsistent, the transition probability models of multiple charging nodes are used to calculate the transition probability of the current adjacent charging cycle; For the state interval where the peak condition does not occur, the transition probability model of a single charging node is used to calculate the transition probability of the peak interval from the state interval where the peak condition does not occur to the adjacent state interval, which is used as the output transition probability.

5. A lithium-ion battery centralized charging management system according to claim 4, characterized in that: The implementation method of determining the peak probability in each charging state also includes: Obtain the maximum charge capacity of the corresponding target battery in each state interval, and extract the peak conditions under the corresponding charging cycle based on the charging cycle required for the maximum charge capacity; The state intervals corresponding to the peak conditions are used to manage each state interval in batches. When each state interval meets the same peak condition, the peak probability under each charging state is recorded and the peak probability is output.

6. The lithium-ion battery centralized charging management system according to claim 1, characterized in that: The implementation method of comparing the target charging status of charging nodes retrieved twice in the status retrieval module includes: Taking the charging node as input data, compare the node type of each charging node to see if it is an alternative charging type, and retrieve the charging node whose target charging state is in the first retrieval; Based on the guided charging order of each charging node, each charging node is searched to obtain the charging node with the target charging state in the second search; Compare the charging nodes retrieved in the first search with those retrieved in the second search, and compare whether the charging nodes included in the first search exist in the charging nodes retrieved in the second search. If so, extract the corresponding charging nodes and record each charging node according to the data included in the two searches. If it does not exist, based on the distribution position of each charging node during the first retrieval, take the charging node of the first retrieval as the starting point, connect the charging node of the first retrieval with the charging node of the second retrieval, obtain the shortest path between each charging node of the first retrieval and the second retrieval, and record the charging node corresponding to the shortest path.

7. A lithium-ion battery centralized charging management system according to claim 6, characterized in that: The implementation method of comparing whether the node type of each charging node is an alternative charging type also includes: If it is an alternative charging type, the charging status of the corresponding charging nodes is extracted respectively to form the state interval corresponding to each charging node. The similarity between each state interval is calculated based on the maximum peak probability in each state interval. The charging nodes corresponding to the state interval with the largest similarity value are selected as the charging nodes for the first search; If it is not an alternative charging type, the charging occupancy cost of the corresponding charging node is obtained, and the charging occupancy cost is used as the search condition to search for the charging node corresponding to the target battery when charging, and the corresponding charging node is used as the charging node for the first search.

8. The lithium-ion battery centralized charging management system according to claim 6, characterized in that: The implementation of the charging node for the second retrieval includes: The charging tag of the charging node is the time when the device starts connecting, the remaining power of the target battery, the device type corresponding to the target battery, and the charging power of the target battery; Search charging nodes with charging tags to obtain the charging event stream of each charging node; At least one management branch is generated by using the charging event flow corresponding to the target charging state, and the charging nodes in the management branch are used as charging nodes for the second search.

9. The lithium-ion battery centralized charging management system according to claim 1, characterized in that: The implementation of the charging check module includes: Based on the number of records of each charging node, the minimum common subset of each charging node under multiple inspections is extracted, and the elements corresponding to the minimum common subset of each charging node are used to form a deep query network; A deep query network is used to compare the abnormal probability of charging nodes under different recording times, and each charging node is output with the abnormal probability.

10. A lithium-ion battery centralized charging management system according to claim 9, characterized in that: Outputting each charging node according to anomaly probability also includes receiving a minimum common subset of each charging node, and classifying each charging node into a stable extreme value node and an unstable extreme value node according to the number of records and the anomaly probability, and in turn according to the maximum value and the minimum value of the corresponding data in the minimum common subset within the corresponding charging cycle; The values of the stable extreme value nodes and the unstable extreme value nodes are monitored. If the charging nodes corresponding to the stable extreme value nodes and the unstable extreme value nodes are abnormal, the corresponding abnormal nodes will be output; otherwise, the stable extreme value nodes and the unstable extreme value nodes will be output.

Images