New energy battery swap station dispatching control method, device, system, medium and terminal

Abstract

The application provides a new energy battery swap station scheduling control method, device, system, medium and terminal. The method comprises the following steps: generating charging demand distribution results and equipment risk warning information in a future time period based on a pre-constructed charging demand prediction model and an equipment life prediction model; matching the current battery swap station operation scene with a pre-set scene template library to determine the initial value of the dynamic coefficient of the charging cabin weight model, and dynamically calibrating the initial value; calculating the real-time weight value of each charging cabin according to the real-time battery data, the calibrated dynamic coefficient, the charging demand distribution results in the future time period and the equipment risk warning information; generating and issuing the charging cabin scheduling instruction according to the real-time weight value of each charging cabin and the pre-set constraint condition; and evaluating and optimizing the scheduling effect according to the pre-set evaluation index. The application can improve the scheduling efficiency of the charging cabin of the battery swap station, and meet the core needs of different operation scenes.

Description

Technical Field

[0001] This application relates to the field of new energy replenishment technology, and in particular to a new energy battery swapping station scheduling and control method, device, system, medium and terminal. Background Technology

[0002] With the increasing popularity of electric heavy-duty trucks, megawatt-level charging piles have become the core equipment of heavy-duty truck battery swapping stations. Existing charging piles typically contain multiple charging compartments, each of which can independently charge the battery pack, thus enabling centralized and efficient charging.

[0003] However, in actual scheduling, a single scheduling logic is usually adopted, such as simple polling or priority strategy to allocate charging tasks. This results in some units being used frequently while others are idle, and it cannot match the diverse needs of actual operation scenarios. For example, peak charging scenarios require efficiency priority, equipment maintenance scenarios require loss control priority, and battery balancing scenarios require SOH (State of Health) optimization priority, etc., which leads to low efficiency of scenario-based operation.

[0004] Furthermore, existing charging task scheduling systems only allocate tasks based on real-time data, which cannot predict the peak hours and regional distribution of future charging demand, nor can they reserve suitable charging spaces in advance, resulting in both peak congestion and off-peak idleness.

[0005] Meanwhile, the current unbalanced use of charging compartments leads to excessive aging of some charging equipment components, while other charging equipment remains idle for a long time, resulting in resource waste. This reduces the overall lifespan and utilization rate of the equipment. However, the current technology mainly manages the key components of charging equipment through "real-time statistics" and has not established a model to predict the attenuation trend. It is impossible to avoid high-loss task allocation in advance, resulting in passive equipment lifespan management.

[0006] In addition, existing technologies lack a quantitative evaluation system for scheduling effectiveness, strategy optimization relies on human experience, cannot iterate autonomously based on long-term operational data, and are difficult to adapt to the dynamic changes in the operating status of battery swapping stations.

[0007] Therefore, it is necessary to provide a scheduling and control method, device, system, medium, and terminal for new energy battery swapping stations to solve the above-mentioned problems in the existing technology. Summary of the Invention

[0008] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a scheduling and control method, device, system, medium and terminal for new energy battery swapping stations, which can solve the technical problems of weak scenario adaptability, lack of predictive scheduling mechanism, lagging equipment life management and lack of closed-loop self-optimization capability in the prior art.

[0009] To achieve the above and other related objectives, the first aspect of this application provides a scheduling and control method for new energy battery swapping stations, comprising: generating charging demand distribution results and equipment risk warning information for a future time period based on collected historical data and real-time equipment operation data, and based on a pre-constructed charging demand prediction model and equipment lifespan prediction model; matching the current battery swapping station operation scenario with a preset scenario template library, and determining the initial value of the dynamic coefficient of the charging bay weight model based on the matched operation scenario; dynamically calibrating the dynamic coefficient based on the core indicators of the matched operation scenario to obtain the calibrated dynamic coefficient; calculating the real-time weight value of each charging bay based on the charging bay weight model based on real-time acquired battery data, the calibrated dynamic coefficient, the charging demand distribution results for a future time period, and the equipment risk warning information; generating a charging bay scheduling instruction based on the calculated real-time weight value of each charging bay and preset constraints, and issuing the generated charging bay scheduling instruction to the corresponding charging bay; evaluating the scheduling effect executed according to the charging bay scheduling instruction based on preset evaluation indicators to generate a scheduling effect evaluation report, and optimizing based on the scheduling effect evaluation report.

[0010] In some embodiments of the first aspect of this application, the charging compartment weight model is as follows:

[0011] ;

[0012] in, for The first moment Real-time weight value of each charging compartment; , , , and for The dynamic coefficients at time t, and satisfying ; for The first moment The resting time of each charging case; for The first moment The remaining lifespan of the equipment in each charging compartment; for The first moment Fault risk level of each charging compartment; for The battery health status value at any given time; for The battery state of charge value at any given time.

[0013] In some embodiments of the first aspect of this application, the evaluation metrics include efficiency metrics, safety metrics, and economic metrics.

[0014] In some embodiments of the first aspect of this application, the specific process of optimizing based on the scheduling effect evaluation report includes: calculating the maximum comprehensive score of the evaluation indicators based on efficiency indicators, safety indicators, and economic indicators, and using the maximum comprehensive score of the evaluation indicators as the reward objective; constructing a reinforcement learning agent based on a deep Q-network model; and updating and optimizing the charging demand prediction model, the device life prediction model, and the scenario template library based on the constructed reinforcement learning agent.

[0015] In some embodiments of the first aspect of this application, the construction process of the charging demand prediction model includes: acquiring historical data of battery swapping stations within a historical time period, and extracting time features, environmental features, operational features, and external features from the historical data of the battery swapping stations; inputting the extracted time features, environmental features, operational features, and external features into an LSTM-XGBoost hybrid model for training to construct a charging demand prediction model; wherein, the LSTM model is used to learn the sequence features in the input features, and the XGBoost model is used to learn the nonlinear features in the input features; deploying the constructed charging demand prediction model to generate charging demand distribution results for future time periods; the charging demand distribution results include the number of charging demands, the required type of charging battery, and the urgency of the charging demand for future time periods.

[0016] In some embodiments of the first aspect of this application, the construction process of the equipment life prediction model includes: acquiring real-time operating data, historical loss data, and working environment data of charging equipment in a battery swapping station, and preprocessing the acquired real-time operating data, historical loss data, and working environment data; inputting the preprocessed real-time operating data, historical loss data, and working environment data into a fusion model for training to construct an equipment life prediction model; the architecture of the fusion model integrates a fault tree analysis mechanism and a Kalman filter; wherein, the fault tree analysis mechanism is used to identify preset key failure links and high-risk combination features; the Kalman filter is used to correct the predicted values ​​output by the fusion model; and the equipment life prediction model is deployed to generate equipment risk warning information; the equipment risk warning information includes the equipment life decay rate, equipment life prediction value, and high loss risk warning information within a future time period.

[0017] To achieve the above and other related objectives, a second aspect of this application provides a new energy battery swapping station scheduling and control device, comprising: a prediction and initialization module, used to generate charging demand distribution results and equipment risk warning information for a future time period based on collected historical data and real-time equipment operation data, and on a pre-built charging demand prediction model and equipment lifespan prediction model; a scenario matching module, used to match the current battery swapping station operation scenario with a preset scenario template library, determine the initial value of the dynamic coefficient of the charging bay weight model based on the matched operation scenario; and dynamically calibrate the dynamic coefficient based on the core indicators of the matched operation scenario to obtain the calibrated dynamic coefficient. The system comprises: a dynamic coefficient module; a weight calculation module, used to calculate the real-time weight value of each charging compartment based on the real-time acquired battery data, calibrated dynamic coefficients, charging demand distribution results within a future time period, and equipment risk warning information, using a charging compartment weight model; a scheduling execution module, used to generate charging compartment scheduling instructions based on the calculated real-time weight values ​​of each charging compartment and preset constraints, and to send the generated charging compartment scheduling instructions to the corresponding charging compartments; and an evaluation and optimization module, used to evaluate the scheduling effect executed according to the charging compartment scheduling instructions based on preset evaluation indicators, to generate a scheduling effect evaluation report, and to optimize based on the scheduling effect evaluation report.

[0018] To achieve the above and other related objectives, a third aspect of this application provides a new energy battery swapping station system, comprising: station control equipment, a main control board, a main charging device, a data center equipped with a new energy battery swapping station scheduling and control device, multiple slave control boards, and slave charging devices corresponding to the slave control boards;

[0019] The new energy battery swapping station scheduling and control device is used to generate charging demand distribution results and equipment risk warning information for future time periods based on collected historical data and real-time equipment operation data, and pre-built charging demand prediction models and equipment lifespan prediction models; match the current battery swapping station operation scenario with a preset scenario template library, and determine the initial value of the dynamic coefficient of the charging bay weight model based on the matched operation scenario; dynamically calibrate the dynamic coefficient based on the core indicators of the matched operation scenario to obtain the calibrated dynamic coefficient; calculate the real-time weight value of each charging bay based on the charging bay weight model based on real-time battery data, calibrated dynamic coefficient, charging demand distribution results for future time periods, and equipment risk warning information; generate charging bay scheduling instructions based on the calculated real-time weight values ​​of each charging bay and preset constraints, and send the generated charging bay scheduling instructions to the corresponding charging bays; evaluate the scheduling effect executed according to the charging bay scheduling instructions based on preset evaluation indicators to generate a scheduling effect evaluation report, and optimize based on the scheduling effect evaluation report;

[0020] The data platform is communicatively connected to the station control equipment and the main control board, and is used to transmit the charging bay scheduling instructions generated by the new energy battery swapping station scheduling and control device to the main control board.

[0021] The main control board is communicatively connected to the main charging device and the slave control board, respectively, and is used to transmit the received charging compartment scheduling instructions to the main charging device and the slave control board.

[0022] The control board is communicatively connected to the charging device and is used to send the received charging compartment scheduling instructions to the charging device for execution.

[0023] In some embodiments of the third aspect of this application, the main charging device includes an AC contactor, a power module, and a relay control box, wherein the input terminal of the power module is connected to the output terminal of the AC contactor, and the output terminal of the power module is connected to the input terminal of a relay in the relay control box.

[0024] In some embodiments of the third aspect of this application, the charging device includes a fuse, a DC contactor, an insulation module, and an energy metering module. The input terminal of the fuse is connected to the output terminal of a relay in the relay control box; the output terminal of the fuse is connected to the input terminal of the DC contactor; and the output terminal of the DC contactor is connected to the insulation module and the energy metering module.

[0025] To achieve the above and other related objectives, a fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method.

[0026] To achieve the above and other related objectives, a fifth aspect of this application provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the method.

[0027] As described above, the new energy battery swapping station scheduling and control method, device, system, medium, and terminal of this application have the following beneficial effects:

[0028] By leveraging historical data and real-time equipment operation data, and based on pre-built charging demand prediction models and equipment lifespan prediction models, the system generates charging demand distribution results and equipment risk warning information for future time periods. This enables accurate prediction of charging demand distribution and equipment risk warning information for future time periods, supporting charging station scheduling and resource reservation. Next, the system matches the current battery swapping station operation scenario with a pre-set scenario template library. Based on the matched operation scenario, the initial dynamic coefficient values ​​of the charging station weight model are determined, and the dynamic coefficients are dynamically calibrated based on the core indicators of the matched operation scenario to obtain calibrated dynamic coefficients. Finally, based on real-time battery data, the calibrated dynamic coefficients, the charging demand distribution results for future time periods, and the equipment lifespan prediction models, the system generates accurate predictions of charging demand distribution and equipment risk warning information for future time periods, supporting charging station scheduling and resource reservation. The system prepares risk warning information and calculates the real-time weight value of each charging compartment based on a charging compartment weight model. Then, based on the calculated real-time weight values ​​and preset constraints, it generates charging compartment scheduling instructions and sends these instructions to the corresponding charging compartments for scheduling. This enables rapid switching and dynamic adaptation of scheduling strategies under different operational scenarios, thus meeting diverse needs. Finally, it evaluates the scheduling effect based on preset evaluation indicators to generate a scheduling effect evaluation report. The system then optimizes the scheduling strategy based on this report, achieving autonomous iterative optimization and improving long-term operational adaptability. In short, this application constitutes a fully intelligent closed-loop scheduling strategy that improves the charging efficiency of the charging compartments. Attached Figure Description

[0029] Figure 1 The diagram shown is a flowchart illustrating the scheduling and control method for new energy battery swapping stations in one embodiment of this application.

[0030] Figure 2 The diagram shown is a schematic representation of the working principle of the new energy battery swapping station scheduling and control method in one embodiment of this application.

[0031] Figure 3 The diagram shown is a block diagram of a new energy battery swapping station scheduling and control device in one embodiment of this application.

[0032] Figure 4 The diagram shown is a block diagram of a new energy battery swapping station system according to one embodiment of this application.

[0033] Figure 5 The diagram shown is a schematic of the main charging device and the slave charging device in a new energy battery swapping station system according to an embodiment of this application.

[0034] Figure 6 The diagram shown is a schematic representation of the internal structure of a relay control box in one embodiment of this application.

[0035] Figure 7 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0036] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0037] In the embodiments of this application, terms such as "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect. For example, "first XX" and "second XX" are merely used to distinguish different XXs and do not limit their order. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply that they are different.

[0038] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0039] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0040] Before providing a further detailed description of the present invention, the nouns and terms used in the embodiments of the present invention are explained, and the nouns and terms used in the embodiments of the present invention are subject to the following interpretations:

[0041] <1> Deep Q-Network (DQN) model: It is an innovative method that combines deep learning with Q-learning. It uses deep neural networks to approximate the Q-value function, thereby enabling it to handle problems in high-dimensional state spaces.

[0042] <2> LSTM (Long Short Term Memory) model: It is a special type of recurrent neural network (RNN) designed to solve the gradient vanishing and gradient explosion problems of traditional RNNs when processing long sequence data. It achieves selective memory and forgetting of information by introducing forget gate, input gate, and output gate, as well as cell state, thereby better capturing long-term dependencies in the sequence.

[0043] <3> XGBoost (eXtreme Gradient Boosting) is an optimized distributed gradient boosting framework designed to efficiently process large-scale datasets. It achieves fast and accurate machine learning model training through parallel tree boosting algorithms (GBDT / GBM), supports operation in various distributed environments (such as Hadoop, Spark, Dask, etc.), and can handle problems with billions of samples.

[0044] <4> Fault Tree Analysis (FTA) is a system failure analysis method based on logical reasoning. It identifies the logical path leading to the top failure event in a complex system by combining low-order events using Boolean logic.

[0045] <5> Kalman filter: It is a highly efficient recursive filter (autoregressive filter) that can estimate the state of a dynamic system from a series of incomplete and noisy measurements. The Kalman filter considers the joint distribution of each measurement at different times and then generates an estimate of the unknown variable, so it is more accurate than the estimation method based on a single measurement.

[0046] <5> State of Health (SOH) value: It is a core indicator for measuring the degree of battery degradation and remaining lifespan. Its accurate assessment directly affects the operational safety of new energy equipment, range prediction, and the formulation of operation and maintenance strategies.

[0047] <6> State of Charge (SOC) is an important term in battery management. It refers to the percentage of a battery's remaining charge relative to its nominal capacity. It reflects the battery's state of charge and is expressed as a percentage between the current available charge and the nominal capacity when the battery is fully charged.

[0048] <7> PyTorch is an open-source deep learning framework for machine learning and deep learning, released by Facebook in 2016. It mainly implements automatic differentiation and introduces dynamic computation graphs to make model building more flexible. It can be divided into two parts: front-end and back-end. The front-end is the Python API that interacts directly with the user, and the back-end is the part implemented internally by the framework, including Autograd, which is an automatic differentiation engine.

[0049] To facilitate understanding of the embodiments of this application, in conjunction with Figure 1 and Figure 2 Detailed explanation. Figure 1 A flowchart illustrating a new energy battery swapping station scheduling and control method according to an embodiment of the present invention is shown. Figure 2 This illustration shows a schematic diagram illustrating the working principle of a new energy battery swapping station scheduling and control method according to an embodiment of the present invention. The new energy battery swapping station scheduling and control method in this embodiment includes the following steps:

[0050] Step S11: Based on the collected historical data and real-time equipment operation data, generate the charging demand distribution results and equipment risk warning information for the future time period based on the pre-built charging demand prediction model and equipment life prediction model.

[0051] By constructing a charging demand prediction model and an equipment lifespan prediction model based on collected historical data and real-time equipment operation data, a dual-dimensional prediction model is obtained. This model enables advance prediction of the charging demand distribution and equipment risk warning information for future time periods. Based on the predicted data, advance scheduling and resource reservation are carried out, improving the foresight of resource allocation.

[0052] In some embodiments of this application, the construction process of the charging demand prediction model includes: acquiring historical data of battery swapping stations within a historical time period, and extracting time features, environmental features, operational features, and external features from the historical data of the battery swapping stations; inputting the extracted time features, environmental features, operational features, and external features into an LSTM-XGBoost hybrid model for training to construct a charging demand prediction model; wherein, the LSTM model is used to learn the sequence features in the input features, and the XGBoost model is used to learn the nonlinear features in the input features; deploying the constructed charging demand prediction model to generate charging demand distribution results for future time periods; the charging demand distribution results include the number of charging demands, the required battery type, and the urgency of the charging demand for future time periods.

[0053] Specifically, the system first acquires relevant historical data from battery swapping stations within a given time period. Feature extraction is then performed on this historical data, extracting time features, environmental features, operational features, and external features. This provides multi-dimensional input features for the model. The model training set consists of nearly three months of historical data from the battery swapping stations, with a sample size exceeding 100,000 records, ensuring the model's prediction accuracy and achieving a prediction accuracy rate of over 90%. For example, time features include time periods, weekdays or weekends, and holidays; environmental features include temperature data and weather conditions; operational features include the charging volume and heavy truck entry / exit frequency over the past seven days; and external features include regional peak logistics season markers and policy-related traffic restrictions.

[0054] Then, the extracted time features, environmental features, operational features, and external features are input into an LSTM-XGBoost hybrid model for training. The LSTM model extracts time-series features from the input to capture intraday demand fluctuations, while the XGBoost model fits non-linear features, such as the impact of extreme weather on charging demand. Through continuous training iterations until convergence, a charging demand prediction model is obtained. Finally, the trained charging demand prediction model is deployed to output the quantity of charging demand, the required battery type, and the urgency level of charging demand within a future time period. For example, it shows the hourly charging demand quantity for the next 24 hours, battery types categorized by SOH / SOC range, and charging demand urgency levels from 1 to 3.

[0055] By using a charging demand prediction model to forecast the amount of charging demand, the type of rechargeable battery required, and the urgency of the charging demand in the future, the system can schedule applications based on this data. For example, during periods of high urgency (e.g., 8-12 am), 40% of the high-power charging bays (400kW) can be reserved in advance, while during off-peak periods (10 pm-6 am), 60% of the charging bays can be scheduled to enter energy-saving standby mode, thereby reducing power consumption by 50% and saving resources.

[0056] In some embodiments of this application, the construction process of the equipment life prediction model includes: acquiring real-time operating data, historical loss data, and working environment data of charging equipment in the battery swapping station, and preprocessing the acquired real-time operating data, historical loss data, and working environment data; inputting the preprocessed real-time operating data, historical loss data, and working environment data into a fusion model for training to construct the equipment life prediction model; the architecture of the fusion model integrates a fault tree analysis mechanism and a Kalman filter; wherein, the fault tree analysis mechanism is used to identify preset key failure links and high-risk combination features; the Kalman filter is used to correct the predicted values ​​output by the fusion model; and the equipment life prediction model is deployed to generate equipment risk warning information; the equipment risk warning information includes the equipment life decay rate, equipment life prediction value, and high loss risk warning information within a future time period.

[0057] Specifically, the first step is to acquire real-time operating data, historical loss data, and operating environment data of the charging equipment in the battery swapping station. Then, the acquired real-time operating data, historical loss data, and operating environment data are standardized and normalized to convert them into a format suitable for model input. For example, real-time operating data of the charging equipment includes the temperature of the power module and the fluctuation value of the contactor's pull-in voltage; historical loss data includes the cumulative operating time, number of start-stop cycles, and number of overload cycles for each component of the equipment; and operating environment data includes operating temperature and humidity.

[0058] Then, the normalized real-time operating data, historical loss data, and operating environment data are input into the fusion model for training. The fusion model architecture integrates a fault tree analysis mechanism and a Kalman filter, and also includes, for example, a preliminary predictor trained based on an LSTM model. Specifically, the preliminary predictor learns the degradation patterns of the equipment from the input data and outputs preliminary prediction information. Based on the integrated fault tree analysis mechanism, it identifies preset key failure links and high-risk combination features according to the preliminary warning information output by the preliminary predictor. For example, the causal relationship between "excessive temperature" and "power module aging" is set as a key failure link, and the simultaneous occurrence of "high temperature" and "high start-stop frequency" is set as a high-risk combination feature. The identified key failure links and high-risk combination features are then output and injected into the training phase of the preliminary predictor, ultimately obtaining an enhanced predictor optimized by fault tree analysis knowledge. The enhanced predictor predicts the equipment lifespan at the next moment and acquires the current real-time operating data of the equipment. Based on the Kalman filter, it fuses the predicted equipment lifespan with the real-time operating data of the equipment to correct the predicted equipment lifespan and achieve accurate prediction of the remaining equipment lifespan. Through continuous training and iteration until convergence, a device life prediction model is trained. Finally, the trained device life prediction model is used to output the device life decay rate, device life prediction value, and high loss risk warning information for future time periods. For example, the life decay rate of each component of the charging device, the remaining life prediction value (error ≤ 5%), and the high loss risk warning (triggered when the remaining life is ≤ 20% of the design life) within the next 30 days.

[0059] By using a device lifespan prediction model to predict the rate of device lifespan decay, the predicted device lifespan, and high-loss risk warning information in the future, and scheduling and execution are carried out based on these predicted device data, for example, high-load tasks (such as 400kW charging) are preferentially assigned to devices with ≥80% remaining lifespan, while high-risk warning devices only undertake tasks with ≤50% of their rated power until maintenance is completed, thereby avoiding the allocation of high-loss tasks in advance and effectively managing device lifespan.

[0060] Step S12: Match the current battery swapping station operation scenario with the preset scenario template library, determine the initial value of the dynamic coefficient of the charging compartment weight model based on the matched operation scenario, and dynamically calibrate the dynamic coefficient based on the core indicators of the matched operation scenario to obtain the calibrated dynamic coefficient.

[0061] Step S13: Based on the real-time battery data, calibrated dynamic coefficients, charging demand distribution results in the future time period, and equipment risk warning information, calculate the real-time weight value of each charging compartment based on the charging compartment weight model.

[0062] By constructing a scenario-based weight template system, we can achieve rapid switching and dynamic adaptation of scheduling strategies under different operational scenarios, thus solving the problem that a single strategy cannot meet diverse needs.

[0063] In some embodiments of this application, the charging compartment weight model is as follows:

[0064] Formula (1);

[0065] in, for The first moment Real-time weight value of each charging compartment; , , , and for The dynamic coefficients at time t, and satisfying ; for The first moment The resting time of each charging case; for The first moment The remaining lifespan of the equipment in each charging compartment; for The first moment Fault risk level of each charging compartment; for The battery health status value at any given time; for The battery state of charge value at any given time.

[0066] Specifically, for Moment The dynamic coefficient is calculated using the following formula:

[0067] Formula (2);

[0068] in, Based on the base coefficient (0.2~0.25), The rate of degradation of battery health status; This represents the historically best degradation rate. Based on the battery's state of equilibrium (SOH) degradation rate. Compared with the historical best decay rate The ratio is dynamically adjusted to ensure that batteries with faster degradation are charged first.

[0069] for Moment The dynamic coefficient is calculated using the following formula:

[0070] Formula (3);

[0071] in, Based on the base coefficient (0.25~0.3), This represents the waiting time for the heavy truck to arrive at the battery swapping station. The design of formula (3) allows for prioritizing charging based on the battery's state of charge value, ensuring that urgent needs are met first.

[0072] for The settling time coefficient at any given time incorporates an ambient temperature correction factor. (Based on the temperature of the charging area), the calculation formula is as follows:

[0073] Formula (4);

[0074] Formula (5);

[0075] in, The base coefficient is 0.15~0.2. This refers to the ambient temperature. The more extreme the ambient temperature (too high or too low), the better. The larger, The higher the sensitivity to the length of time the battery has been idle, the more priority should be given to scheduling batteries that have been idle for a long time to avoid performance loss caused by environmental factors.

[0076] for The remaining life factor of the equipment at any given time is based on the remaining life of each component of the equipment. With design life The ratio adjustment is calculated using the following formula:

[0077] Formula (6);

[0078] in, Based on a base coefficient (0.15~0.2), the shorter the remaining lifespan of the components, The lower the value, the less frequently the compartment is used, extending the equipment's lifespan; the longer the remaining lifespan, the better. The higher the value, the better the equipment utilization rate.

[0079] for The fault risk coefficient at any given moment, combined with the real-time fault risk value. (Based on parameters such as insulation resistance and contactor temperature, adjustments are made using a Bayesian network, with values ​​ranging from 0 to 1.) The calculation formula is as follows:

[0080] Formula (7);

[0081] in, Based on a baseline coefficient (0.05~0.1), the higher the risk of failure, The lower the value, the less likely the charging compartment will be to be involved in scheduling, thus reducing safety hazards.

[0082] Based on the core operation scenarios of the battery swapping station, for example, three basic scenario templates are preset, namely, the scenarios in the scenario template library include peak charging scenario, equipment maintenance scenario and battery balancing scenario. The scenario templates achieve scenario adaptation through the differentiation of the initial values ​​of dynamic coefficients. The initial values ​​of dynamic coefficients calculated according to formulas (2) to (7) are shown in Table 1 below:

[0083] Table 1 Initial values ​​of dynamic coefficients for different scenarios:

[0084]

[0085] When the operation scenario of a battery swapping station changes (supporting automatic triggering or manual switching), a dynamic coefficient calibration will be performed every 5 minutes, for example. The calibration is based on the core indicators of the current scenario. Specifically, when the operation scenario is a peak charging scenario, the core objective is to improve charging efficiency. If the average waiting time is greater than 15 minutes, β(t) will be increased by 0.05; if the average waiting time is ≤10 minutes, β(t) will be decreased by 0.03. When the operation scenario is an equipment maintenance scenario, the core objective is to reduce equipment wear. If the load rate of the equipment to be maintained is greater than 10%, δ(t) will be decreased by 0.04. When the operation scenario is a battery balancing scenario, the core objective is to optimize battery SOH. If the maximum difference in battery SOH does not decrease, α(t) will be increased by 0.05.

[0086] By constructing a three-level weight system consisting of a charging bay weight model, a scenario template library, and real-time dynamic calibration, accurate adaptation to different battery swapping station operation scenarios can be achieved. Furthermore, based on real-time battery data, calibrated dynamic coefficients, charging demand distribution results in the future time period, and equipment risk warning information, the real-time weight value of each charging bay is calculated based on the charging bay weight model, which serves as the basis for subsequent scheduling.

[0087] Step S14: Generate a charging compartment scheduling instruction based on the calculated real-time weight value of each charging compartment and the preset constraints, and send the generated charging compartment scheduling instruction to the corresponding charging compartment.

[0088] For example, the preset constraints are that the interval between adjacent charging compartments should be greater than or equal to 30 minutes and high-risk equipment should be avoided.

[0089] Step S15: Evaluate the scheduling effect of the charging compartment scheduling command according to the preset evaluation indicators, generate a scheduling effect evaluation report, and optimize according to the scheduling effect evaluation report.

[0090] By constructing a fully closed-loop self-learning mechanism for scheduling effect evaluation and model optimization, the scheduling strategy can be autonomously iterated, thus forming a closed-loop autonomous optimization strategy.

[0091] In some embodiments of this application, the evaluation metrics include efficiency metrics, safety metrics, and economic metrics.

[0092] Specifically, a multi-dimensional quantitative evaluation index library is established to comprehensively evaluate scheduling effectiveness from three dimensions: efficiency, safety, and economy. The core indicators, target thresholds, data sources, and dimension weights for different evaluation dimensions are shown in Table 2 below:

[0093] Table 2. Specific indicators under different evaluation dimensions:

[0094]

[0095] In some embodiments of this application, the specific process of optimizing based on the scheduling effect evaluation report includes: calculating the maximum comprehensive score of the evaluation indicators based on efficiency indicators, safety indicators, and economic indicators, and using the maximum comprehensive score of the evaluation indicators as the reward objective; constructing a reinforcement learning agent based on a deep Q-network model; and updating and optimizing the charging demand prediction model, the device life prediction model, and the scenario template library based on the constructed reinforcement learning agent.

[0096] Specifically, the comprehensive score of the evaluation indicators is maximized based on efficiency, safety, and economic indicators. This maximization of the comprehensive score serves as the reward objective, enabling the construction of a reinforcement learning agent to autonomously optimize the scheduling strategy. The state space is defined by the current scenario type, the status of each storage unit's equipment, the battery status, and the predicted demand distribution; the action space is defined by weight coefficient adjustment, storage unit allocation decisions, and scenario template parameter optimization; and a standardized scoring mechanism is formulated for each dimension of the indicators as the reward function. The reinforcement learning agent is constructed based on a deep Q-network model, specifically a DQN (Deep Q-Network) agent built using the PyTorch framework. The experience replay pool has a capacity of 100,000 entries, and the learning rate is 0.001. Model parameters are updated after daily operation (iteration time ≤ 30 minutes), and monthly iterations are performed based on the full dataset. Finally, the constructed reinforcement learning agent is used to update and optimize the charging demand prediction model, the equipment lifespan prediction model, and the scenario template library.

[0097] The new energy battery swapping station scheduling and control method provided in this application achieves precise matching of different operating scenarios through a pre-set scenario-based template library and dynamic calibration mechanism. This results in improved charging efficiency during peak charging scenarios, reduced equipment loss during equipment maintenance scenarios, and optimized battery health during battery balancing scenarios, thus achieving precise adaptation to operating scenarios. Furthermore, pre-reserving suitable charging bay spaces reduces waiting time during peak hours to less than 15 minutes, reduces equipment energy consumption during off-peak hours, and improves resource utilization. At the same time, the prediction of equipment component lifespan reduces high-loss failures, and battery balancing scheduling controls the state of energy loss (SOH) degradation rate, extending the lifespan of batteries and equipment. In addition, the reinforcement learning mechanism continuously optimizes the scheduling strategy, adapting to changes in the operating status of battery swapping stations in multiple scenarios without manual intervention, thereby enhancing operational adaptability.

[0098] Figure 3 This is a schematic block diagram of the new energy battery swapping station scheduling and control device provided in the embodiments of this application. Figure 3 As shown, the new energy battery swapping station dispatch control device 300 includes:

[0099] The prediction initialization module 301 is used to generate the charging demand distribution results and equipment risk warning information for a future time period based on the collected historical data and real-time equipment operation data, and on the basis of the pre-built charging demand prediction model and equipment life prediction model.

[0100] The scenario matching module 302 is used to match the current operation scenario of the battery swapping station with the preset scenario template library, determine the initial value of the dynamic coefficient of the charging compartment weight model based on the matched operation scenario, and dynamically calibrate the dynamic coefficient based on the core indicators of the matched operation scenario to obtain the calibrated dynamic coefficient.

[0101] The weight calculation module 303 is used to calculate the real-time weight value of each charging compartment based on the charging compartment weight model, according to the real-time acquired battery data, the calibrated dynamic coefficient, the charging demand distribution results in the future time period and the equipment risk warning information.

[0102] The scheduling execution module 304 is used to generate a charging compartment scheduling instruction based on the calculated real-time weight value of each charging compartment and the preset constraints, and to send the generated charging compartment scheduling instruction to the corresponding charging compartment.

[0103] The evaluation and optimization module 305 is used to evaluate the scheduling effect of the charging compartment scheduling instruction according to the preset evaluation indicators, generate a scheduling effect evaluation report, and optimize according to the scheduling effect evaluation report.

[0104] The new energy battery swapping station scheduling and control device provided in this application integrates scenario adaptation, intelligent prediction and self-learning capabilities to form a full-process intelligent control strategy of prediction-scheduling-evaluation-optimization, which simultaneously improves charging efficiency, battery life and equipment reliability.

[0105] It should be understood that the specific process of each module performing the above-mentioned steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0106] It should also be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0107] Figure 4 This is a block diagram of the new energy battery swapping station system provided in the embodiments of this application. Figure 4 As shown, the new energy battery swapping station system includes: station control equipment, main control board, main charging equipment, data center equipped with new energy battery swapping station scheduling and control device, multiple slave control boards, and slave charging equipment corresponding to the slave control boards;

[0108] The new energy battery swapping station scheduling and control device is used to generate charging demand distribution results and equipment risk warning information for future time periods based on collected historical data and real-time equipment operation data, and pre-built charging demand prediction models and equipment lifespan prediction models; match the current battery swapping station operation scenario with a preset scenario template library, and determine the initial value of the dynamic coefficient of the charging bay weight model based on the matched operation scenario; dynamically calibrate the dynamic coefficient based on the core indicators of the matched operation scenario to obtain the calibrated dynamic coefficient; calculate the real-time weight value of each charging bay based on the charging bay weight model based on real-time battery data, calibrated dynamic coefficient, charging demand distribution results for future time periods, and equipment risk warning information; generate charging bay scheduling instructions based on the calculated real-time weight values ​​of each charging bay and preset constraints, and send the generated charging bay scheduling instructions to the corresponding charging bays; evaluate the scheduling effect executed according to the charging bay scheduling instructions based on preset evaluation indicators to generate a scheduling effect evaluation report, and optimize based on the scheduling effect evaluation report;

[0109] The data platform is communicatively connected to the station control equipment and the main control board, respectively, and is used to transmit the charging bay scheduling instructions generated by the new energy battery swapping station scheduling control device to the main control board; the main control board is communicatively connected to the main charging equipment and the slave control board, respectively, and is used to transmit the received charging bay scheduling instructions to the main charging equipment and the slave control board; the slave control board is communicatively connected to the slave charging equipment, and is used to send the received charging bay scheduling instructions to the slave charging equipment for execution.

[0110] The new energy battery swapping station system provided in this application is based on a three-tier architecture of "station control equipment - power battery - charging equipment," and incorporates a data platform to construct a full-link intelligent control system encompassing "perception-prediction-decision-execution-evaluation-optimization." The data platform undertakes core functions such as historical data storage, prediction model calculation, scenario template management, and self-learning optimization. It achieves bidirectional communication with the station control equipment and charging equipment via Ethernet and acquires relevant data from the battery management system (BMS) in real time.

[0111] Specifically, the system first performs a prediction initialization every hour. The data platform runs the charging demand prediction model and the equipment lifespan prediction model, outputting the charging demand distribution results and equipment risk warning information for the next hour, and synchronizing them to the station control equipment. Then, scenario matching is performed in real time. The system automatically identifies the current operating scenario type or receives manual scenario instructions and calls the corresponding scenario template library for matching, thereby determining the initial value of the dynamic coefficient. Next, weight calculation is performed every minute. Combining the real-time collected battery data with the aforementioned prediction results, the weight value of each charging compartment is calculated. Then, scheduling instructions are executed in real time. Charging tasks are allocated based on weight sorting and constraints, and parameter mutations are monitored in real time. Emergency rescheduling is triggered when an anomaly occurs. Finally, a scheduling effect evaluation report is generated every hour, and the model parameters are optimized daily through reinforcement learning algorithms, and the scenario templates and prediction models are updated, thus forming a closed loop.

[0112] In some embodiments of this application, such as Figure 5 and Figure 6 As shown, the main charging device includes an AC contactor, a power module, and a relay control box. The input terminal of the power module is connected to the output terminal of the AC contactor, and the output terminal of the power module is connected to the input terminal of the relay in the relay control box.

[0113] Specifically, the main charging circuit includes an AC contactor, n power modules, and a corresponding relay control box for each power module. The AC contactor controls the on / off state of the AC input to the power modules, and the relays in the relay control box control the on / off state of each circuit, thus determining which battery compartment is charged. Each power module, acting as an input, can only control the on / off state of one relay at a time, thus producing an output. It should be noted that n is a positive integer, such as 1, 2, 3, 4, ...

[0114] In some embodiments of this application, such as Figure 5 As shown, the charging device includes a fuse, a DC contactor, an insulation module, and an energy metering module. The input terminal of the fuse is connected to the output terminal of the relay in the relay control box; the output terminal of the fuse is connected to the input terminal of the DC contactor; and the output terminal of the DC contactor is connected to the insulation module and the energy metering module.

[0115] Specifically, the charging circuit includes a fuse, a DC contactor, an insulation module, an energy metering module, and a charging connector for the m-th charging compartment. The DC contactor controls the on / off state of the output from the charging circuit; the energy metering module measures the consumed energy; the fuse serves as a short-circuit protection device; and the insulation module monitors the electrical insulation status between the high-voltage charging circuit and the equipment grounding to prevent safety accidents caused by insulation failure. It should be noted that m is a positive integer, such as 1, 2, 3, 4, etc.

[0116] Furthermore, the design and operation of the new energy battery swapping station system provided in this application are as follows: First, data acquisition equipment is deployed. The data platform uses an industrial-grade server to deploy the core software modules for data acquisition, prediction models, scenario template library management, and self-learning optimization. It supports Ethernet communication interfaces with a communication latency of less than or equal to 100ms. The charging equipment is equipped with hardware such as power modules, AC contactors, and DC contactors, and needs to respond to the scheduling commands of the data platform in real time. The sensing and communication design is that battery data is acquired through the CAN 2.0 bus, and device data is acquired through buses such as Ethernet and serial ports. All data is aggregated to the data platform through industrial Ethernet to ensure data transmission stability. Secondly, the model was specifically designed. The development environment was Python 3.8, TensorFlow 2.8.0 (prediction model), PyTorch 1.12.0 (reinforcement learning module), and GCC 9.4.0 (weight calculation module) as the C language compiler. The station control system was developed based on Qt 5.15. The training parameters for the prediction model were: an LSTM network with two hidden layers (128 neurons per layer), a dropout rate of 0.2, 50 iterations, a batch size of 64, an XGBoost algorithm with a learning rate of 0.1, a tree depth of 6, and 100 iterations. The reinforcement learning parameters were: a DQN agent with an experience replay pool capacity of 100,000 records, an exploration rate that linearly decayed from 0.9 to 0.1 (decay period of 1000 rounds), and a target network update frequency of once every 100 steps. The weight calculation module was compiled into a dynamic link library (DLL) using C language, with a single calculation time of ≤80ms to ensure real-time performance. Data acquisition adopted a multi-threaded mechanism, and the data update cycle of each link met the sampling frequency requirements. Finally, the scheduling instructions and dynamic feedback optimization are executed, specifically as follows: key parameters are monitored in real time, and when the trigger weight coefficient changes, the weight values ​​of all charging compartments are recalculated; based on the new weight values, tasks are preferentially assigned to high-weight compartments, and charging parameters are adjusted (e.g., reducing output power to extend the service life of key components); after task switching, the operating data of the new compartments is collected every 5 minutes to verify the scheduling effect; if new parameter changes occur, the above feedback process is repeated until the system returns to stability; after the emergency is handled, an "emergency scheduling log" is automatically generated, recording the parameter mutation time, dynamic weight adjustment process, and processing results for subsequent model optimization.

[0117] Figure 7 This is a schematic block diagram of the electronic terminal provided in an embodiment of this application. Figure 7As shown, the electronic terminal 700 includes at least one processor 701, a memory 702, at least one network interface 703, and a user interface 705. The various components in the electronic terminal 700 are coupled together via a bus system 704. It is understood that the bus system 704 is used to implement communication between these components. In addition to a data bus, the bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 7 The general will label all buses as bus systems.

[0118] The user interface 705 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0119] It is understood that memory 702 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0120] In this embodiment of the invention, the memory 702 is used to store various types of data to support the operation of the electronic terminal 700. Examples of this data include: any executable program for operation on the electronic terminal 700, such as operating system 7021 and application program 7022; operating system 7021 includes various system programs, such as framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. Application program 7022 may include various applications, such as media player, browser, etc., for implementing various application services. The methods provided in this embodiment of the invention can be included in application program 7022.

[0121] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 701. Processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 701 or by instructions in software form. The processor 701 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 701 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 701 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0122] In an exemplary embodiment, the electronic terminal 700 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to execute the aforementioned method.

[0123] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when executed on a computer, causes the computer to perform... Figures 1 to 2 The method of any of the embodiments shown.

[0124] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0125] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0126] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0128] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0129] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0130] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0131] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] In summary, addressing the technical problems of weak adaptability to existing scenarios, lack of predictive scheduling mechanisms, lagging equipment lifespan management, and lack of closed-loop self-optimization capabilities, this application provides a scheduling and control method, device, system, medium, and terminal for new energy battery swapping stations. Based on collected historical data and real-time equipment operation data, and grounded in pre-built charging demand prediction models and equipment lifespan prediction models, it generates charging demand distribution results and equipment risk warning information for future time periods. This enables accurate prediction of charging demand distribution and equipment risk warning information for future time periods, supporting charging bay scheduling and resource reservation. Furthermore, it matches the current battery swapping station operation scenario with a pre-set scenario template library, determines the initial dynamic coefficient values ​​of the charging bay weight model based on the matched operation scenario, and dynamically calibrates the dynamic coefficients based on the core indicators of the matched operation scenario to obtain the calibrated dynamic coefficients. Then, based on real-time battery data, calibrated dynamic coefficients, charging demand distribution results within the future time period, and equipment risk warning information, the real-time weight value of each charging compartment is calculated based on the charging compartment weight model. Next, charging compartment scheduling instructions are generated based on the calculated real-time weight values ​​of each charging compartment and preset constraints, and these instructions are sent to the corresponding charging compartments for scheduling. This enables rapid switching and dynamic adaptation of scheduling strategies under different operating scenarios, thereby meeting diverse scenario requirements. Finally, the scheduling effect executed according to the charging compartment scheduling instructions is evaluated based on preset evaluation indicators to generate a scheduling effect evaluation report. Optimization is then performed based on the scheduling effect evaluation report, achieving autonomous iterative optimization of the scheduling strategy and improving long-term operational adaptability. In other words, this application constitutes a full-process intelligent closed-loop scheduling strategy, improving the charging efficiency of the charging compartments. Therefore, this application effectively overcomes various shortcomings in the prior art and has high industrial application value.

[0133] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A scheduling and control method for new energy battery swapping stations, characterized in that, include: Based on collected historical data and real-time equipment operation data, and using pre-built charging demand prediction models and equipment lifespan prediction models, the system generates charging demand distribution results and equipment risk warning information for future time periods. The current battery swapping station operation scenario is matched with a preset scenario template library, and the initial values ​​of the dynamic coefficients of the charging compartment weight model are determined based on the matched operation scenario. The dynamic coefficients are dynamically calibrated based on the core indicators of the matched operational scenario to obtain the calibrated dynamic coefficients. Based on real-time battery data, calibrated dynamic coefficients, charging demand distribution results in the future time period, and equipment risk warning information, the real-time weight value of each charging compartment is calculated based on the charging compartment weight model. Based on the calculated real-time weight values ​​of each charging compartment and the preset constraints, a charging compartment scheduling instruction is generated and sent to the corresponding charging compartment. The scheduling effect of the charging compartment scheduling command is evaluated according to the preset evaluation indicators to generate a scheduling effect evaluation report, and optimization is carried out based on the scheduling effect evaluation report.

2. The new energy battery swapping station scheduling and control method according to claim 1, characterized in that, The weighting model for the charging compartment is as follows: ； in, for The first moment Real-time weight value of each charging compartment; , , , and for The dynamic coefficients at time t, and satisfying ; for The first moment The resting time of each charging case; for The first moment The remaining lifespan of the equipment in each charging compartment; for The first moment Fault risk level of each charging compartment; for The battery health status value at any given time; for The battery state of charge value at any given time.

3. The new energy battery swapping station scheduling and control method according to claim 1, characterized in that, The evaluation indicators include efficiency indicators, safety indicators, and economic indicators.

4. The new energy battery swapping station scheduling and control method according to claim 3, characterized in that, The specific process of optimization based on the scheduling effect evaluation report includes: The comprehensive score of the evaluation indicators is calculated based on efficiency, safety, and economic indicators, and the comprehensive score of the evaluation indicators is used as the reward objective. A reinforcement learning agent is constructed based on a deep Q-network model. The charging demand prediction model, equipment lifespan prediction model, and scenario template library are updated and optimized based on the constructed reinforcement learning agent.

5. The new energy battery swapping station scheduling and control method according to claim 1, characterized in that, The construction process of the charging demand prediction model includes: Acquire historical data of battery swapping stations within a historical time period, and extract time features, environmental features, operational features, and external features from the historical data of the battery swapping stations; The extracted time features, environmental features, operational features, and external features are input into the LSTM-XGBoost hybrid model for training to construct a charging demand prediction model; wherein, the LSTM model is used to learn the sequence features in the input features, and the XGBoost model is used to learn the nonlinear features in the input features. The constructed charging demand prediction model is deployed to generate charging demand distribution results for future time periods; the charging demand distribution results include the number of charging demands, the type of rechargeable battery required, and the urgency of the charging demand for future time periods.

6. The new energy battery swapping station scheduling and control method according to claim 1, characterized in that, The construction process of the equipment life prediction model includes: Acquire real-time operating data, historical loss data, and working environment data of charging equipment in the battery swapping station, and preprocess the acquired real-time operating data, historical loss data, and working environment data; Preprocessed real-time operating data, historical loss data, and working environment data are input into a fusion model for training to construct an equipment life prediction model. The architecture of the fusion model integrates a fault tree analysis mechanism and a Kalman filter. The fault tree analysis mechanism is used to identify preset key failure links and high-risk combination characteristics. The Kalman filter is used to correct the predicted values ​​output by the fusion model. The equipment life prediction model is deployed to generate equipment risk warning information; the equipment risk warning information includes the equipment life decay rate, the predicted equipment life, and high loss risk warning information within a future time period.

7. A dispatching and control device for a new energy battery swapping station, characterized in that, include: The prediction initialization module is used to generate charging demand distribution results and equipment risk warning information for future time periods based on the collected historical data and real-time equipment operation data, and on the basis of the pre-built charging demand prediction model and equipment life prediction model. The scenario matching module is used to match the current operation scenario of the battery swapping station with the preset scenario template library, and determine the initial value of the dynamic coefficient of the charging compartment weight model based on the matched operation scenario. The dynamic coefficients are dynamically calibrated based on the core indicators of the matched operational scenario to obtain the calibrated dynamic coefficients. The weight calculation module is used to calculate the real-time weight value of each charging compartment based on the charging compartment weight model, according to the real-time battery data, the calibrated dynamic coefficient, the charging demand distribution results in the future time period and the equipment risk warning information. The scheduling execution module is used to generate charging compartment scheduling instructions based on the calculated real-time weight values ​​of each charging compartment and preset constraints, and to send the generated charging compartment scheduling instructions to the corresponding charging compartments. The evaluation and optimization module is used to evaluate the scheduling effect of the charging compartment scheduling instruction according to the preset evaluation indicators, generate a scheduling effect evaluation report, and optimize according to the scheduling effect evaluation report.

8. A new energy battery swapping station system, characterized in that, include: The system includes station control equipment, a main control board, main charging equipment, a data center equipped with a new energy battery swapping station scheduling and control device, multiple slave control boards, and slave charging equipment corresponding to the slave control boards. The new energy battery swapping station scheduling and control device is used to generate charging demand distribution results and equipment risk warning information for future time periods based on collected historical data and real-time equipment operation data, and pre-built charging demand prediction models and equipment lifespan prediction models; match the current battery swapping station operation scenario with a preset scenario template library, and determine the initial value of the dynamic coefficient of the charging bay weight model based on the matched operation scenario; dynamically calibrate the dynamic coefficient based on the core indicators of the matched operation scenario to obtain the calibrated dynamic coefficient; calculate the real-time weight value of each charging bay based on the charging bay weight model based on real-time battery data, calibrated dynamic coefficient, charging demand distribution results for future time periods, and equipment risk warning information; generate charging bay scheduling instructions based on the calculated real-time weight values ​​of each charging bay and preset constraints, and send the generated charging bay scheduling instructions to the corresponding charging bays; evaluate the scheduling effect executed according to the charging bay scheduling instructions based on preset evaluation indicators to generate a scheduling effect evaluation report, and optimize based on the scheduling effect evaluation report; The data platform is communicatively connected to the station control equipment and the main control board, and is used to transmit the charging bay scheduling instructions generated by the new energy battery swapping station scheduling and control device to the main control board. The main control board is communicatively connected to the main charging device and the slave control board, respectively, and is used to transmit the received charging compartment scheduling instructions to the main charging device and the slave control board. The control board is communicatively connected to the charging device and is used to send the received charging compartment scheduling instructions to the charging device for execution.

9. The new energy battery swapping station system according to claim 8, characterized in that, The main charging device includes an AC contactor, a power module, and a relay control box. The input terminal of the power module is connected to the output terminal of the AC contactor, and the output terminal of the power module is connected to the input terminal of the relay in the relay control box.

10. The new energy battery swapping station system according to claim 9, characterized in that, The charging device includes a fuse, a DC contactor, an insulation module, and an energy metering module. The input terminal of the fuse is connected to the output terminal of the relay in the relay control box; the output terminal of the fuse is connected to the input terminal of the DC contactor; and the output terminal of the DC contactor is connected to the insulation module and the energy metering module.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

12. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method as described in any one of claims 1 to 6.

Images