An intelligent temperature control method and system applicable to outdoor energy storage power supplies

Abstract

The present invention discloses an intelligent temperature control method and system applicable to outdoor energy storage power supplies, including: constructing a digital model of a target outdoor energy storage power supply, extracting the ideal operating condition characteristics of the target energy storage power supply, and setting several combinations of operating condition parameters for different operating condition scenarios; importing them into the digital model of the outdoor energy storage power supply for internal temperature simulation of the power supply, and constructing an internal temperature analysis model of the energy storage power supply based on the simulation results; obtaining real-time power operation monitoring information, using the internal temperature analysis model to predict the internal temperature change of the power supply in the real-time operating scenario, and determining whether regulation is required; extracting the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, analyzing whether there is a risk of internal condensation in the power supply in the current outdoor operating scenario, and if there is a risk, performing intelligent regulation and risk warning, thereby improving the operation safety and stability of the outdoor energy storage power supply under multi-scenario use.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control for outdoor energy storage power supplies, and particularly to an intelligent temperature control method and system applicable to outdoor energy storage power supplies. Background Art

[0002] With the wide application of renewable energy, outdoor energy storage power supply systems play an increasingly important role in ensuring the stability of power supply. However, the complexity of the outdoor environment poses higher requirements for the thermal management of energy storage systems. During the charging and discharging process, the battery generates a large amount of heat. If the heat cannot be dissipated in a timely and effective manner, it may cause the battery temperature to rise, affecting its performance and lifespan, and even leading to safety accidents. Traditional temperature control schemes mostly adopt a passive heat dissipation mode with fixed threshold control, relying on a preset temperature range to trigger the start and stop of the fan or the operation of the heating module, and it is difficult to adapt to the violently fluctuating temperature and humidity conditions and dynamic load characteristics in the outdoor environment. In areas with large temperature differences between day and night, high humidity and frequent rain, or frequent sandstorms, such methods are prone to cause the accumulation of risks of local overheating or condensation, which may further trigger chain failures such as battery pack capacity attenuation, oxidation of electrical connection points, and even thermal runaway.

[0003] Therefore, in order to meet the operation requirements and operation safety of outdoor energy storage power supplies under complex climate conditions, there is an urgent need for a temperature control method that can real-time monitor the environment and battery pack temperature, intelligently analyze the thermal response, and quickly execute heating or cooling regulation, so as to improve the use safety and lifespan of the energy storage power supply. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and provides an intelligent temperature control method and system applicable to outdoor energy storage power supplies, and an important purpose thereof is to improve the safety and stability of outdoor energy storage power supplies during outdoor operation.

[0005] To achieve the above object, the first aspect of the present invention provides an intelligent temperature control method applicable to outdoor energy storage power supplies, including:

[0006] Construct a digital model of the target outdoor energy storage power supply, extract the ideal operating condition characteristics of the target energy storage power supply through the equipment specification of the target outdoor energy storage power supply, and set a combination of operating condition parameters for several different operating condition scenarios to obtain a final operating condition data set;

[0007] Import the final operating condition data set into the outdoor energy storage power supply digital model for power internal temperature simulation, and construct an internal temperature analysis model of the energy storage power supply based on the simulation results of different operating conditions;

[0008] Conduct real-time operation monitoring on the target outdoor energy storage power supply to obtain real-time power operation monitoring information, use the internal temperature analysis model to predict the change of the power internal temperature in the real-time operation scenario, and judge whether regulation is required;

[0009] Extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, and analyze whether there is a risk of condensation inside the power supply in the current outdoor operation scenario. If there is a risk, perform intelligent regulation and risk warning.

[0010] In this solution, the construction of the digital model of the target outdoor energy storage power supply specifically includes:

[0011] Perform external structure scanning on the target outdoor energy storage power supply through a three-dimensional laser scanner to obtain external structure point cloud data, and perform internal structure scanning on the outdoor energy storage power supply through a microfocus CT scanner to obtain internal structure point cloud data, obtaining a point cloud data set;

[0012] Based on the point cloud data set, use the principal component analysis algorithm to obtain the initial transformation matrix, calculate the covariance matrix of the two point clouds and perform eigenvalue decomposition, select the eigenvector corresponding to the largest eigenvalue as the initial rotation axis, and the centroid coordinate difference as the initial translation vector, and fuse the internal structure point cloud data and the external structure point cloud data for coordinate iterative registration;

[0013] In each iteration, for each sampling point in the source point cloud, use the approximate nearest neighbor algorithm to quickly locate the corresponding point in the KD-Tree of the target point cloud, and exclude non-matching point pairs through a preset distance threshold. After registration, use 3D modeling software to establish the initial geometric model of the target outdoor energy storage power supply;

[0014] Among them, the KD-Tree uses the variance maximization criterion to define the splitting dimension during the construction process and establishes a hierarchical index structure through a breadth-first search strategy;

[0015] Perform multi-physics field coupling mesh division on the initial geometric model of the target outdoor energy storage power supply, use the advancing front method to generate unstructured hybrid meshes, obtain the equipment specification of the target outdoor energy storage power supply, and define the thermal sensitive area mesh and the fluid area mesh through the equipment specification;

[0016] Obtain the geometric model of the energy storage power supply after mesh division is completed, extract the preparation material characteristics of the target outdoor energy storage power supply through the equipment specification, and use the extracted preparation material characteristics to define the material properties of the energy storage power supply geometric model, obtaining the outdoor energy storage power supply digital model.

[0017] In this solution, the extraction of the ideal operating condition characteristics of the target energy storage power supply through the equipment specification of the target outdoor energy storage power supply, and the setting of several operating condition parameter combinations for different operating condition scenarios, obtaining the final operating condition data set, specifically includes:

[0018] Obtain the device specification of the target outdoor energy storage power supply, and extract the ideal operating condition characteristics of the target energy storage power supply from the device specification, including the operating environment temperature range, charge and discharge rate range, heat dissipation mode, and altitude pressure range, to obtain the ideal operating condition characteristic information;

[0019] Define the operating environment temperature, charge and discharge rate, altitude pressure, and heat dissipation mode as variables to generate a high-dimensional hypercube, set variable constraint conditions based on the ideal operating characteristic information, and generate a direction number matrix in combination with Gray code encoding;

[0020] Calculate the base-2 fractional sequence for each dimension according to the direction number matrix to generate a parameter point set, use recursive exclusive OR operations to generate Sobol sequence points bit by bit based on the parameter point set, and normalize the coordinate values of each point;

[0021] Based on the normalized Sobol sequence points, use piecewise linear transformation to map continuous parameters to the ideal operating interval of the device, map the discrete heat dissipation mode to a three-dimensional continuous vector through embedded space encoding, calculate the cosine similarity between the sequence points and the discrete mode vector, and perform mode assignment in combination with a preset matching threshold to generate several operating condition parameter combinations, obtaining an initial operating condition data set;

[0022] Generate a parameter space through the initial operating condition data set, introduce the K-means clustering algorithm to determine the optimal number of clusters according to the silhouette coefficient, and use Mahalanobis distance as the distance metric to perform iterative clustering to partition the parameter space;

[0023] After completing the partitioning of the parameter space, for each cluster, calculate the reciprocal of the distance between the samples within the cluster and the centroid as the selection basis for selecting representative points, perform Gaussian mixture fitting on the parameter distribution characteristics according to the selected representative points, evaluate the subclass similarity through JS divergence and merge them to obtain the final operating condition data set.

[0024] In this solution, import the final operating condition data set into the outdoor energy storage power supply digital model for power internal temperature simulation, and construct an internal temperature analysis model of the energy storage power supply based on the simulation results of different operating conditions, specifically including:

[0025] Obtain the final operating condition data set, import the final operating condition data set into the constructed outdoor energy storage power supply digital model for simulation, analyze the internal temperature changes of the target outdoor energy storage power supply under different operating condition scenarios, and obtain the internal temperature simulation information;

[0026] Based on the internal temperature simulation information, construct an internal temperature simulation field for different operating condition scenarios, and extract the temperature field simulation characteristics from the internal temperature simulation fields of each operating condition scenario to obtain the temperature field characteristics of each operating condition scenario;

[0027] Take the temperature field simulation characteristics of each operating condition scenario as the observed variables, and construct the dynamic Bayesian network nodes by combining the operating condition scenarios corresponding to each observed variable. Among them, the temperature field simulation characteristics are the child nodes, and the operating condition scenario parameters are the parent nodes;

[0028] Calculate the mutual information value between the child node and the parent node, and judge the calculated mutual information value and the preset threshold. If it is greater than the preset threshold, define the corresponding parent node as the dependent parent node to obtain the initial dependence set;

[0029] Based on the initial dependence set, initialize the network topology, and perform redundant edge pruning through conditional independence testing to characterize the causal relationship between the child node and the dependent parent node, and obtain the causal relationship topology diagram;

[0030] Extract the temperature field simulation characteristics corresponding to each child node through the causal relationship topology diagram, extract the statistical characteristics of temperature changes through a sliding window, use a change point detection algorithm to detect mutation points, and divide the temperature data segment between adjacent change points into independent state intervals;

[0031] Input the independent state interval and the corresponding motion condition scenario parameters into the dynamic Bayesian network to obtain the state transition probability matrix and the observation probability distribution, and construct a conditional probability table. Construct and train the internal temperature analysis model of the energy storage power supply through the conditional probability table and the final operating condition data set.

[0032] In this solution, the real-time operation monitoring of the target outdoor energy storage power supply is carried out to obtain real-time power operation monitoring information, and the internal temperature analysis model is used to predict the internal temperature change of the power supply under the real-time operation scenario, and judge whether regulation is needed. Specifically, it includes:

[0033] Based on the sensor array in the outdoor energy storage power supply, the real-time operation monitoring of the target outdoor energy storage power supply is carried out to obtain real-time power operation monitoring information. The real-time power operation monitoring information includes power operation environment monitoring data and power operation status monitoring data;

[0034] After preprocessing the real-time power operation monitoring information, input it into the internal temperature analysis model of the energy storage power supply to predict the future internal temperature change of the target power supply under the current operation scenario and operating conditions, and obtain the internal temperature change prediction information;

[0035] Based on the internal temperature change prediction information, use the time series characteristics to convert the internal temperature change prediction result into a time series state sequence, and use a preset sliding window to slide in the time series state sequence;

[0036] The preset temperature anomaly determination rule is used to detect the temperature anomaly time nodes within the sliding window during the sliding process, and generate temperature anomaly detection information by combining the corresponding temperature data;

[0037] Based on the temperature anomaly detection information, calculate the time intervals when the target outdoor energy storage power supply has different degrees of temperature anomalies, which is defined as the temperature regulation buffer time. Combine the current heat dissipation mode and real-time temperature characteristics of the target outdoor energy storage power supply to retrieve the regulation strategy in the preset strategy library, and perform intelligent regulation on the target outdoor energy storage power supply through the retrieved regulation strategy.

[0038] In this solution, the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply are extracted based on the real-time power operation monitoring information, and it is analyzed whether there is a risk of internal condensation in the power supply under the current outdoor operation scenario. If there is a risk, intelligent regulation and risk warning are carried out, specifically including:

[0039] Obtain the real-time power operation monitoring information, extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, and obtain the internal temperature and humidity monitoring characteristic information;

[0040] Obtain the internal temperature change prediction information, combine the internal temperature and humidity monitoring characteristic information to construct the internal temperature and humidity field of the target outdoor energy storage power supply, and define the relative humidity and dew point temperature as the basis for judging internal condensation in the power supply;

[0041] Introduce the indirect method to analyze the relative humidity and dew point temperature inside the target outdoor energy storage power supply in the current operating environment through the internal temperature and humidity field of the target outdoor energy storage power supply, and judge it with the preset risk threshold;

[0042] If it is greater than the preset risk threshold, obtain the internal temperature characteristics and heat dissipation mode of the target outdoor energy storage power supply at the current moment, and perform regulation judgment in combination with the internal temperature change prediction information;

[0043] Extract the temperature change trend of the target outdoor energy storage power supply at a future moment through the internal temperature change prediction information. If it is a downward trend or a stable trend, switch the heat dissipation mode of the target outdoor energy storage power supply to the next heat dissipation level;

[0044] If the temperature change trend of the target outdoor energy storage power supply at a future moment is an upward trend, and the current heat dissipation mode is the highest heat dissipation level, then switch the real-time operation efficiency mode of the target outdoor energy storage power supply, and generate an internal condensation warning of the power supply for prompt.

[0045] The second aspect of the present invention provides an intelligent temperature control system applicable to outdoor energy storage power supplies. The system includes: a memory and a processor. The memory contains an intelligent temperature control method program applicable to outdoor energy storage power supplies. When the intelligent temperature control method program applicable to outdoor energy storage power supplies is executed by the processor, the following steps are implemented:

[0046] Construct a digital model of the target outdoor energy storage power supply, extract the ideal operating condition characteristics of the target energy storage power supply through the device specification of the target outdoor energy storage power supply, and set several combinations of operating condition parameters for different operating condition scenarios to obtain the final operating condition data set;

[0047] Import the final operating condition data set into the digital model of the outdoor energy storage power supply for power internal temperature simulation, and construct an internal temperature analysis model of the energy storage power supply based on the simulation results of different operating conditions;

[0048] Conduct real-time operation monitoring on the target outdoor energy storage power supply to obtain real-time power operation monitoring information, use the internal temperature analysis model to predict the change of the power internal temperature in the real-time operation scenario, and judge whether regulation is required;

[0049] Extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, analyze whether there is a risk of internal condensation in the power supply in the current outdoor operation scenario, and if there is a risk, perform intelligent regulation and risk warning.

[0050] The present invention discloses an intelligent temperature control method and system applicable to outdoor energy storage power supplies, including: constructing a digital model of the target outdoor energy storage power supply, extracting the ideal operating condition characteristics of the target energy storage power supply, and setting several combinations of operating condition parameters for different operating condition scenarios; importing into the digital model of the outdoor energy storage power supply for power internal temperature simulation, and constructing an internal temperature analysis model of the energy storage power supply based on the simulation results; obtaining real-time power operation monitoring information, using the internal temperature analysis model to predict the change of the power internal temperature in the real-time operation scenario, and judging whether regulation is required; extracting the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, analyzing whether there is a risk of internal condensation in the power supply in the current outdoor operation scenario, and if there is a risk, performing intelligent regulation and risk warning, so as to improve the operation safety and stability of outdoor energy storage power supplies under multi-scenario use. Description of the Drawings

[0051] To more clearly illustrate the technical solutions in the embodiments or exemplary examples of the present invention, the following will briefly introduce the drawings required for use in the description of the embodiments or exemplary examples. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the ones shown in these drawings.

[0052] Figure 1 Flowchart of an intelligent temperature control method applicable to an outdoor energy storage power supply provided by an embodiment of the present invention;

[0053] Figure 2 Flowchart of a method for monitoring internal condensation of a power supply applicable to an outdoor energy storage power supply provided by an embodiment of the present invention;

[0054] Figure 3 Block diagram of an intelligent temperature control system applicable to an outdoor energy storage power supply provided by an embodiment of the present invention;

[0055] The realization, functional characteristics and advantages of the object of the present invention will be further described in conjunction with the embodiments and with reference to the drawings. Detailed implementation manners

[0056] In order to be able to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0057] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0058] Figure 1 Flowchart of an intelligent temperature control method applicable to an outdoor energy storage power supply provided by an embodiment of the present invention;

[0059] As Figure 1 shown, the present invention provides a flowchart of an intelligent temperature control method applicable to an outdoor energy storage power supply, including:

[0060] S102, constructing a digital model of the target outdoor energy storage power supply, extracting the ideal operating condition characteristics of the target energy storage power supply through the device specification of the target outdoor energy storage power supply, and setting a combination of operating condition parameters for several different operating condition scenarios to obtain a final operating condition data set;

[0061] S104. Import the final operating condition data set into the digital model of the outdoor energy storage power supply for internal temperature simulation of the power supply, and construct an internal temperature analysis model of the energy storage power supply based on the simulation results of different operating conditions;

[0062] S106. Conduct real-time operation monitoring on the target outdoor energy storage power supply to obtain real-time power operation monitoring information, use the internal temperature analysis model to predict the internal temperature change of the power supply in the real-time operation scenario, and determine whether regulation is required;

[0063] S108. Extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, analyze whether there is a risk of internal condensation in the power supply in the current outdoor operation scenario, and if there is a risk, perform intelligent regulation and risk warning.

[0064] Further, in a preferred embodiment of the present invention, the construction of the digital model of the target outdoor energy storage power supply specifically includes:

[0065] Perform external structure scanning on the target outdoor energy storage power supply through a 3D laser scanner to obtain external structure point cloud data, and perform internal structure scanning on the outdoor energy storage power supply through a microfocus CT scanner to obtain internal structure point cloud data, obtaining a point cloud data set;

[0066] Based on the point cloud data set, use the principal component analysis algorithm to obtain an initial transformation matrix, calculate the covariance matrix of the two point clouds and perform eigenvalue decomposition, select the eigenvector corresponding to the largest eigenvalue as the initial rotation axis, and the centroid coordinate difference as the initial translation vector, and fuse the internal structure point cloud data and the external structure point cloud data for coordinate iterative registration;

[0067] In each iteration, for each sampling point in the source point cloud, use the approximate nearest neighbor algorithm to quickly locate the corresponding point in the KD-Tree of the target point cloud, and exclude the mismatched point pairs through a preset distance threshold. After registration, use 3D modeling software to establish the initial geometric model of the target outdoor energy storage power supply;

[0068] Among them, the KD-Tree adopts the variance maximization criterion to define the segmentation dimension during construction, and establishes a hierarchical index structure through a breadth-first search strategy;

[0069] Perform multi-physical field coupling mesh division on the initial geometric model of the target outdoor energy storage power supply, use the advancing front method to generate unstructured hybrid meshes, obtain the equipment specification of the target outdoor energy storage power supply, and define the thermal sensitive area mesh and the fluid area mesh through the equipment specification;

[0070] Obtain the geometric model of the energy storage power supply after mesh generation is completed. Extract the material characteristics of the target outdoor energy storage power supply from the device specification sheet. Use the extracted material characteristics to define the material properties of the energy storage power supply geometric model, and obtain the digital model of the outdoor energy storage power supply.

[0071] It should be noted that during the process of constructing the digital model of the outdoor energy storage power supply, first, the point cloud datasets of the external housing and internal components of the device are obtained through a 3D laser scanner and a microfocus CT scanner respectively, generating a heterogeneous point cloud dataset containing surface curvature features and internal topological relationships. The initial spatial alignment of the internal and external point clouds is achieved through the principal component analysis algorithm. Calculate the three-dimensional covariance matrix of the external point cloud and the internal point cloud, perform singular value decomposition to obtain the eigenvector corresponding to the largest eigenvalue as the rotation reference axis, and calculate the initial translation transformation matrix in combination with the centroid coordinate difference to transform the internal structure point cloud into the external coordinate system framework. In the iterative registration stage, the iterative closest point (ICP) algorithm is used for fine alignment. In each iteration process, a KD-Tree spatial index is constructed for the source point cloud, the variance maximization criterion is used to select the segmentation dimension, and an octree structure is established through breadth-first search to accelerate the nearest neighbor query. When the average registration error change rate for three consecutive iterations is less than the preset threshold, the optimization is terminated, and finally, the spatial alignment of the internal and external point clouds is achieved. Subsequently, a surface model is generated through the surface reconstruction module of the 3D modeling software, and the surface is discretized using the adaptive triangulation algorithm to obtain the initial geometric model. In the mesh generation stage, the advancing front method is applied to generate an unstructured hybrid mesh, boundary layer meshes are arranged in the thermally sensitive areas, the first layer height is set to 0.05 mm, and the growth rate is 1.2. The fluid area uses tetrahedron-prism hybrid elements, and the minimum element quality factor is controlled above 0.4. When finally defining the material properties based on the device specification sheet, a multi-layer material distribution model is adopted, and discrete material parameters (such as thermal conductivity, specific heat capacity, emissivity, etc.) are mapped to the corresponding mesh areas through voxelization to construct a digital twin model with the ability to solve multi-physical fields.

[0072] Furthermore, in a preferred embodiment of the present invention, the ideal operating condition characteristics of the target energy storage power supply are extracted from the device specification sheet of the target outdoor energy storage power supply, and several combinations of operating condition parameters for different operating condition scenarios are set to obtain the final operating condition dataset, specifically including:

[0073] Obtain the device specification sheet of the target outdoor energy storage power supply, and extract the ideal operating condition characteristics of the target energy storage power supply from the device specification sheet, including the operating environment temperature range, charge-discharge rate range, heat dissipation mode, and altitude pressure range, to obtain the ideal operating condition characteristic information;

[0074] Define the operating environment temperature, charge-discharge rate, altitude pressure, and heat dissipation mode as variables to generate a high-dimensional hypercube, set variable constraint conditions based on the ideal operating characteristic information, and generate a direction number matrix in combination with Gray code encoding;

[0075] Calculate the base-2 fractional sequences of each dimension according to the direction number matrix to generate a parameter point set, use recursive exclusive-or operations to generate Sobol sequence points bit by bit based on the parameter point set, and normalize the coordinate values of each point;

[0076] Based on the normalized Sobol sequence points, use piecewise linear transformation to map continuous parameters to the ideal operating interval of the device, map the discrete heat dissipation mode to a three-dimensional continuous vector through embedded space encoding, calculate the cosine similarity between the sequence points and the discrete mode vector, and combine the preset matching threshold for mode assignment to generate several combinations of operating condition parameters to obtain an initial operating condition data set;

[0077] Generate a parameter space through the initial operating condition data set, introduce the K-means clustering algorithm to determine the optimal number of clusters according to the silhouette coefficient, and use the Mahalanobis distance as the distance metric for iterative clustering to partition the parameter space;

[0078] After completing the partitioning of the parameter space, for each cluster, calculate the reciprocal of the distance between the samples within the cluster and the centroid as the selection basis for representative point selection, perform Gaussian mixture fitting of the parameter distribution characteristics according to the selected representative points, evaluate the subclass similarity through JS divergence and merge them to obtain the final operating condition data set.

[0079] It should be noted that first, based on the device specification, the boundary constraints of the operating parameters are extracted, and a hybrid-dimensional space including continuous variables such as environmental temperature and charge-discharge rate and discrete variables such as heat dissipation modes is established. The Sobol sequence generation strategy is adopted to ensure uniform coverage of the parameter space. The direction number matrix is constructed by Gray code encoding to guide the generation of basis vectors in each dimension. The quasi-random point set with low discrepancy is generated by recursive exclusive OR operation. After normalization, the continuous parameters are mapped to the physical interval allowed by the device. For the discrete heat dissipation mode parameters, a three-dimensional continuous coding space is designed to map the eigenvectors of different heat dissipation strategies, and the intelligent association between discrete parameters and the continuous space is realized through cosine similarity threshold matching. Subsequently, an improved K-means clustering algorithm is introduced. The optimal number of clusters is determined based on silhouette coefficient analysis. The Mahalanobis distance is used to replace the traditional Euclidean distance to eliminate the influence of dimension difference and correlation between parameters. After clustering, the distance reciprocal weighting strategy is adopted to screen representative points within each subclass cluster, and the sample points that can not only represent the distribution characteristics within the cluster but also be close to the boundary of potential extreme operating conditions are preferentially selected. Subsequently, the parameter distributions of each subclass are fitted by the Gaussian mixture model, and the JS divergence is used to quantify the distribution similarity between subclasses. The subclasses with similarity exceeding the threshold are merged to eliminate redundant parameter combinations. Finally, an operating condition dataset with both spatial coverage and physical representativeness is generated to ensure that the simulation analysis can capture the characteristics of typical operating conditions and cover critical failure scenarios.

[0080] Further, in a preferred embodiment of the present invention, importing the final operating condition dataset into the outdoor energy storage power digital model for internal temperature simulation of the power supply, and constructing an internal temperature analysis model of the energy storage power supply based on the simulation results of different operating conditions, specifically including:

[0081] Obtain the final operating condition dataset, import the final operating condition dataset into the constructed outdoor energy storage power digital model for simulation, analyze the internal temperature changes of the target outdoor energy storage power supply under different operating condition scenarios, and obtain internal temperature simulation information;

[0082] Based on the internal temperature simulation information, construct an internal temperature simulation field for different operating condition scenarios, and extract temperature field simulation features through the internal temperature simulation fields of each operating condition scenario to obtain the temperature field features of each operating condition scenario;

[0083] Take the temperature field simulation features of each operating condition scenario as observation variables, and construct dynamic Bayesian network nodes in combination with the operating condition scenarios corresponding to each observation variable, where the temperature field simulation features are child nodes and the operating condition scenario parameters are parent nodes;

[0084] Calculate the mutual information value between the child node and the parent node, and judge the calculated mutual information value with a preset threshold. If it is greater than the preset threshold, define the corresponding parent node as a dependent parent node to obtain an initial dependency set;

[0085] Initialize the network topology based on the initial dependency set, prune redundant edges through conditional independence tests, characterize the causal relationship between child nodes and dependent parent nodes, and obtain a causal relationship topology graph;

[0086] Extract the temperature field simulation features corresponding to each child node through the causal relationship topology graph, extract the statistical features of temperature changes through a sliding window, use a change point detection algorithm to detect mutation points, and divide the temperature data segment between adjacent change points into independent state intervals;

[0087] Input the independent state interval and the corresponding motion condition scenario parameters into a dynamic Bayesian network to obtain a state transition probability matrix and an observation probability distribution, and construct a conditional probability table. Construct and train an internal temperature analysis model of the energy storage power supply through the conditional probability table and the final operating condition data set.

[0088] It should be noted that the final operating condition data set is input into a high-fidelity digital twin model for multi-physical field coupling simulation. The simulation process is based on the unsteady heat conduction equation (considering the anisotropic thermal conductivity of materials) and the k-epsilon turbulence model (for the fluid domain of the heat dissipation duct). The spatio-temporal evolution process of the temperature field is discretely solved by the finite volume method, and the temperature sequence of the temperature measurement points inside the device and the three-dimensional heat flux density field are output. Key thermodynamic features are extracted based on the temperature simulation data. Subsequently, temperature features (such as the maximum temperature rise rate, the magnitude of the temperature gradient, and the divergence of the heat flux density vector) are used as child nodes, and operating condition parameters (such as ambient temperature, charge and discharge rate, etc.) are used as parent nodes, and a time lag operator is introduced to establish a cross-time slice dependency relationship to construct a dynamic Bayesian network. The KL divergence is used to calculate the mutual information between the parent and child nodes, and a threshold is set to screen significant correlation parameters to establish an initial network dependency relationship. Network pruning is implemented through conditional independence tests, and the partial correlation coefficient is used to test the conditional independence of the third order and above, and redundant edges are removed to form a minimum sufficient causal graph.

[0089] Furthermore, for the temperature time series state division, an adaptive sliding window mechanism is designed: the initial window length is 60 seconds, and the window size is dynamically adjusted by calculating the decay rate of the local autocorrelation coefficient of the data within the window (the time required to decay to 0.2), and the minimum window is compressed to 5 seconds to capture transient transitions. Bayesian online change point detection algorithm is used for change point detection, and the posterior probability of the change point is calculated by combining the conjugate prior distribution. When the probability exceeds the preset threshold, it is marked as a valid change point. In the dynamic Bayesian network training session, a two-layer network structure containing hidden state nodes is constructed. The lower-layer network represents the static causal relationship between the operating conditions parameters and the temperature characteristics, and the upper-layer state transition network models the temporal evolution law of the temperature state. The expectation maximization (EM) algorithm is used to jointly optimize the state transition probability matrix and the observation probability distribution, and the forward-backward algorithm is used to calculate the smoothed probability to update the conditional probability table. The final model realizes real-time temperature prediction through variational inference, realizes the dynamic deduction of the temperature field evolution trend and the early warning of abnormal states.

[0090] Furthermore, in a preferred embodiment of the present invention, the real-time operation monitoring of the target outdoor energy storage power supply is performed to obtain real-time power operation monitoring information, and the internal temperature analysis model is used to predict the internal temperature change of the power supply under the real-time operation scenario, and it is judged whether regulation is needed, specifically including:

[0091] The real-time operation monitoring of the target outdoor energy storage power supply is performed based on the sensor array in the outdoor energy storage power supply to obtain real-time power operation monitoring information, and the real-time power operation monitoring information includes power operation environment monitoring data and power operation status monitoring data;

[0092] After the real-time power operation monitoring information is preprocessed, it is input into the internal temperature analysis model of the energy storage power supply to predict the future internal temperature change of the target power supply under the current operation scenario and operating conditions, and obtain the internal temperature change prediction information;

[0093] Based on the internal temperature change prediction information, the internal temperature change prediction result is converted into a time series state sequence by using time series features, and a preset sliding window is used to slide in the time series state sequence;

[0094] A preset temperature anomaly determination rule is set, and during the sliding process, the temperature anomaly time series nodes in the sliding window are detected by using the temperature anomaly determination rule, and the temperature anomaly detection information is generated by combining the corresponding temperature data;

[0095] Based on the temperature anomaly detection information, the time interval for the target outdoor energy storage power supply to have different degrees of temperature anomalies is calculated, which is defined as the temperature regulation buffer time, and the regulation strategy is retrieved in the preset strategy library by combining the current heat dissipation mode and real-time temperature characteristics of the target outdoor energy storage power supply, and the target outdoor energy storage power supply is intelligently regulated by the retrieved regulation strategy.

[0096] It should be noted that the temperature, humidity and other data of the key areas inside the device (battery cell module, power conversion unit, heat dissipation air duct) are collected in real time through an embedded sensor array, and the operating state parameters such as charge and discharge current, bus voltage, and heat dissipation fan speed are synchronously monitored. Adaptive Kalman filtering is used to eliminate sensor noise, the phase difference caused by different sampling frequencies is compensated by a spatio-temporal alignment engine, and an interpolation algorithm is used to reconstruct the three-dimensional temperature field distribution. Subsequently, the preprocessed multi-dimensional data stream is input into a pre-trained internal temperature analysis model of the energy storage power supply. This model is based on an attention-enhanced spatio-temporal graph convolutional network architecture, and the discrete form of the heat conduction partial differential equation is embedded as a physical constraint term in the input layer. The temperature change trend features are extracted through stacked temporal convolutional modules, and the thermal coupling effect is captured by the spatial graph attention module. The probability distribution prediction of the temperature change in each region within a 15-minute time window in the future is output, and a temperature evolution trajectory with a confidence interval is generated. The continuous prediction values are discretized into a discrete state sequence, and the dynamic time warping algorithm is applied to align the historical state sequence to construct a state transition chain with timestamps. The sliding window mechanism sets a window length of 30 seconds and a step length of 10 seconds, and feature indicators such as temperature change rate, local gradient magnitude, and cumulative temperature rise are integrated within the window. The temperature anomaly determination rule engine combines physical thresholds and statistical process control methods: when it is detected that the temperature within the window exceeds the material temperature resistance limit threshold, or the cumulative temperature rise exceeds the three-sigma control limit, it is marked as a temperature anomaly event, and an anomaly feature vector including the anomaly level, spatial location, and evolution rate is generated. Further, based on the spatio-temporal characteristics of the anomaly event, the predicted duration for the real-time internal temperature to climb to the abnormal temperature is calculated, which is defined as the temperature regulation buffer time. Combining the current heat dissipation mode and real-time temperature characteristics of the target outdoor energy storage power supply, a regulation strategy is retrieved from a preset strategy library, and the target outdoor energy storage power supply is intelligently regulated through the retrieved regulation strategy, so as to ensure the safety and stability of the target outdoor power supply during operation.

[0097] Figure 2 The flowchart of a method for monitoring internal condensation of a power supply applicable to an outdoor energy storage power supply provided by an embodiment of the present invention;

[0098] As Figure 2 shown, the present invention provides a flowchart of a method for monitoring internal condensation of a power supply applicable to an outdoor energy storage power supply, including:

[0099] Further, in a preferred embodiment of the present invention, the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply are extracted based on the real-time power operation monitoring information, and it is analyzed whether there is a risk of internal condensation in the power supply under the current outdoor operation scenario. If there is a risk, intelligent regulation and risk warning are performed, specifically including:

[0100] S202. Obtain real-time power operation monitoring information, extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, and obtain the internal temperature and humidity monitoring characteristic information.

[0101] S204. Obtain the internal temperature change prediction information, construct the internal temperature and humidity field of the target outdoor energy storage power supply in combination with the internal temperature and humidity monitoring characteristic information, and define the relative humidity and dew point temperature as the basis for judging condensation inside the power supply.

[0102] S206. Introduce the indirect method to analyze the relative humidity and dew point temperature inside the target outdoor energy storage power supply in the current operating environment through the internal temperature and humidity field of the target outdoor energy storage power supply, and make a judgment with a preset risk threshold.

[0103] S208. If it is greater than the preset risk threshold, obtain the internal temperature characteristics and heat dissipation mode of the target outdoor energy storage power supply at the current moment, and make a regulation judgment in combination with the internal temperature change prediction information.

[0104] S210. Extract the temperature change trend of the target outdoor energy storage power supply at a future moment through the internal temperature change prediction information. If it is a downward trend or a stable trend, switch the heat dissipation mode of the target outdoor energy storage power supply to the next heat dissipation level.

[0105] S212. If the temperature change trend of the target outdoor energy storage power supply at a future moment is an upward trend and the current heat dissipation mode is the highest heat dissipation level, switch the real-time operation efficiency mode of the target outdoor energy storage power supply, and generate a condensation warning inside the power supply for prompt.

[0106] It should be noted that in the complex and changeable outdoor environmental conditions, condensation is likely to occur inside the power supply due to sudden temperature changes or high humidity environments. This can lead to corrosion of electronic components, degradation of insulation performance, and even short-circuit faults. Especially under special climate conditions such as large temperature differences between day and night, high humidity along the coast, or rainy seasons, the risk of condensation increases significantly, which may cause irreversible damage such as performance attenuation of the battery pack and oxidation of contactor contacts. In severe cases, it may even trigger safety accidents such as thermal runaway. Furthermore, the original temperature and humidity data of key areas inside the device (including the gaps between battery cell modules, the surfaces of power devices, the heat dissipation air ducts, etc.) are continuously collected through a distributed high-precision sensor network. A noise reduction algorithm based on wavelet packet transform is used to eliminate environmental interference, and multi-source asynchronous sampling data is aligned through spatio-temporal registration technology. Based on the preprocessed monitoring data, characteristic parameters such as the temperature change rate, humidity gradient, and heat flux density of each area are extracted, and a multi-dimensional temperature and humidity characteristic matrix containing spatial position encoding is constructed. At the same time, combined with the temperature prediction information output by the digital twin model, the dynamic temperature and humidity field inside the device is reconstructed through an interpolation algorithm. Subsequently, the relative humidity and dew point temperature are defined as the core evaluation indicators of the condensation risk, and the indirect method is used to analyze the relative humidity and dew point temperature inside the target outdoor energy storage power supply under the current operating environment. Specifically, first, the dry bulb temperature is converted to Kelvin temperature, the saturated water vapor partial pressure is calculated, the relative humidity is obtained through the water vapor partial pressure and the saturated water vapor partial pressure, and the dew point temperature is calculated and compared with the preset risk threshold to carry out regulation. For the situation where the predicted temperature will tend to be stable or decrease, the cooling intensity is gradually reduced according to the preset cooling mode upgrade path (such as switching from forced air cooling to natural convection); when the predicted temperature continues to rise and the cooling system has reached its maximum capacity, the charge and discharge strategy is dynamically adjusted through the power electronic control module, and a warning prompt is given to ensure the safe and stable operation of the outdoor energy storage power supply in a complex environment.

[0107] Figure 3 An intelligent temperature control system 3 applicable to an outdoor energy storage power supply provided by an embodiment of the present invention includes: a memory 31 and a processor 32. The memory 31 contains an intelligent temperature control method program applicable to the outdoor energy storage power supply. When the intelligent temperature control method program applicable to the outdoor energy storage power supply is executed by the processor 32, the following steps are implemented:

[0108] Construct a digital model of the target outdoor energy storage power supply, extract the ideal operating condition characteristics of the target energy storage power supply through the device specification of the target outdoor energy storage power supply, and set the operating condition parameter combinations of several different operating condition scenarios to obtain the final operating condition data set;

[0109] Import the final operating condition data set into the outdoor energy storage power supply digital model for internal temperature simulation of the power supply, and construct an internal temperature analysis model of the energy storage power supply based on the simulation results of different operating conditions;

[0110] Monitor the real-time operation of the target outdoor energy storage power supply to obtain real-time power operation monitoring information, use the internal temperature analysis model to predict the internal temperature change of the power supply in the real-time operation scenario, and determine whether regulation is required;

[0111] Extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, analyze whether there is a risk of internal condensation of the power supply in the current outdoor operation scenario, and if there is a risk, perform intelligent regulation and risk warning.

[0112] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed may be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0113] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, in each embodiment of the present invention, the various functional units can all be integrated in one processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0115] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: mobile storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical disks and other various media that can store program codes.

[0116] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0117] As described above, the foregoing are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An intelligent temperature control method applicable to outdoor energy storage power supplies, characterized in that, Including: Construct a digital model of the target outdoor energy storage power supply, extract the ideal operating condition characteristics of the target energy storage power supply from the device specification of the target outdoor energy storage power supply, and set several combinations of operating condition parameters for different operating condition scenarios to obtain the final operating condition dataset; Import the final operating condition dataset into the digital model of the outdoor energy storage power supply for internal temperature simulation of the power supply, and construct an internal temperature analysis model of the energy storage power supply based on the simulation results of different operating conditions; Conduct real-time operation monitoring on the target outdoor energy storage power supply to obtain real-time power operation monitoring information, use the internal temperature analysis model to predict the change of the internal temperature of the power supply in the real-time operation scenario, and judge whether regulation is required; Extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, analyze whether there is a risk of internal condensation of the power supply in the current outdoor operation scenario, and if there is a risk, perform intelligent regulation and risk warning; Among them, the step of importing the final operating condition dataset into the digital model of the outdoor energy storage power supply for internal temperature simulation of the power supply and constructing an internal temperature analysis model of the energy storage power supply based on the simulation results of different operating conditions specifically includes: Obtain the final operating condition dataset, import the final operating condition dataset into the constructed digital model of the outdoor energy storage power supply for simulation, analyze the internal temperature change of the target outdoor energy storage power supply under different operating condition scenarios, and obtain internal temperature simulation information; Construct an internal temperature simulation field for different operating condition scenarios based on the internal temperature simulation information, extract temperature field simulation characteristics through the internal temperature simulation fields of each operating condition scenario, and obtain the temperature field characteristics of each operating condition scenario; Use the temperature field simulation characteristics of each operating condition scenario as observation variables, and combine the operating condition scenarios corresponding to each observation variable to construct dynamic Bayesian network nodes, where the temperature field simulation characteristics are child nodes and the operating condition scenario parameters are parent nodes; Calculate the mutual information value between the child node and the parent node, and compare the calculated mutual information value with a preset threshold. If it is greater than the preset threshold, define the corresponding parent node as a dependent parent node to obtain an initial dependency set; Perform network topology initialization based on the initial dependency set, perform redundant edge pruning through conditional independence testing, and characterize the causal relationship between the child node and the dependent parent node to obtain a causal relationship topology graph; Extract the temperature field simulation characteristics corresponding to each child node through the causal relationship topology graph, extract the statistical characteristics of temperature changes through a sliding window, perform change point detection using a change point detection algorithm, and divide the temperature data segment between adjacent change points into independent state intervals; Input the independent state intervals and the corresponding motion condition scenario parameters into the dynamic Bayesian network to obtain a state transition probability matrix and an observation probability distribution, and construct a conditional probability table. Construct and train an internal temperature analysis model of the energy storage power supply through the conditional probability table and the final operating condition dataset.

2. The intelligent temperature control method for an outdoor energy storage power supply according to claim 1, wherein, The construction of the digital model of the target outdoor energy storage power supply specifically includes: The external structure point cloud data of the target outdoor energy storage power supply is obtained by scanning the external structure with a three-dimensional laser scanner, and the internal structure point cloud data of the outdoor energy storage power supply is obtained by scanning the internal structure with a micro-focus CT scanner to obtain a point cloud data set; Based on the point cloud data set, the initial transformation matrix is obtained by using the principal component analysis algorithm. The covariance matrix of the two point clouds is calculated and eigen-decomposed. The eigenvector corresponding to the largest eigenvalue is selected as the initial rotation axis, and the centroid coordinate difference is used as the initial translation vector. The internal structure point cloud data and the external structure point cloud data are fused for coordinate iterative registration; In each iteration, for each sampling point in the source point cloud, the approximate nearest neighbor algorithm is used to quickly locate the corresponding point in the KD-Tree of the target point cloud, and the mismatched point pairs are excluded by a preset distance threshold. After registration, the initial geometric model of the target outdoor energy storage power supply is established by using 3D modeling software; Among them, the variance maximization criterion is adopted to define the splitting dimension during the construction of the KD-Tree, and a hierarchical index structure is established through the breadth-first search strategy; Multi-physics field coupled mesh generation is performed on the initial geometric model of the target outdoor energy storage power supply. The advancing front method is used to generate unstructured hybrid meshes, and the equipment specification of the target outdoor energy storage power supply is obtained. The thermal sensitive area mesh and the fluid area mesh are defined through the equipment specification; The geometric model of the energy storage power supply after mesh generation is obtained. The preparation material characteristics of the target outdoor energy storage power supply are extracted through the equipment specification, and the material attributes of the energy storage power supply geometric model are defined by using the extracted preparation material characteristics to obtain the digital model of the outdoor energy storage power supply.

3. The intelligent temperature control method for an outdoor energy storage power supply according to claim 1, characterized in that, The ideal operating condition characteristics of the target energy storage power supply are extracted through the equipment specification of the target outdoor energy storage power supply, and several combinations of operating condition parameters for different operating condition scenarios are set to obtain the final operating condition data set, specifically including: The equipment specification of the target outdoor energy storage power supply is obtained, and the ideal operating condition characteristics of the target energy storage power supply are extracted, including the operating environment temperature range, charge and discharge rate range, heat dissipation mode, and altitude pressure range, to obtain the ideal operating condition characteristic information; The operating environment temperature, charge and discharge rate, altitude pressure, and heat dissipation mode are defined as variables to generate a high-dimensional hypercube. Based on the ideal operating condition characteristic information, variable constraint conditions are set, and a direction number matrix is generated by combining Gray code encoding; According to the direction number matrix, the base-2 fractional sequences of each dimension are calculated to generate a parameter point set. Based on the parameter point set, the Sobol sequence points are generated bit by bit by using recursive exclusive-or operations, and the coordinate values of each point are normalized; Based on the normalized Sobol sequence points, the continuous parameters are mapped to the ideal operating interval of the equipment by using piecewise linear transformation. The discrete heat dissipation mode is mapped to a three-dimensional continuous vector by embedded space encoding. The cosine similarity between the sequence points and the discrete mode vector is calculated, and pattern assignment is performed by combining a preset matching threshold to generate several combinations of operating condition parameters to obtain the initial operating condition data set; Generate a parameter space from the initial operating condition data set, introduce the K-means clustering algorithm to determine the optimal number of clusters according to the silhouette coefficient, and use the Mahalanobis distance as the distance metric to perform iterative clustering to partition the parameter space; After completing the partitioning of the parameter space, for each cluster, calculate the reciprocal of the distance between the samples within the cluster and the centroid as the selection basis for selecting representative points. Based on the selected representative points, perform Gaussian mixture fitting of the parameter distribution characteristics, evaluate the subclass similarity through the JS divergence, and merge them to obtain the final operating condition data set.

4. The intelligent temperature control method for an outdoor energy storage power supply according to claim 1, characterized in that, Perform real-time operation monitoring on the target outdoor energy storage power supply to obtain real-time power operation monitoring information, and use the internal temperature analysis model to predict the internal temperature change of the power supply under the real-time operation scenario, and determine whether regulation is required. Specifically, it includes: Perform real-time operation monitoring on the target outdoor energy storage power supply based on the sensor array in the outdoor energy storage power supply to obtain real-time power operation monitoring information. The real-time power operation monitoring information includes power operation environment monitoring data and power operation status monitoring data; After preprocessing the real-time power operation monitoring information, input it into the internal temperature analysis model of the energy storage power supply to predict the future internal temperature change of the target power supply under the current operation scenario and operating conditions, and obtain the internal temperature change prediction information; Based on the internal temperature change prediction information, use the time series characteristics to transform the internal temperature change prediction result into a time series state sequence, and use a preset sliding window to slide in the time series state sequence; Preset the temperature anomaly determination rule, and use the temperature anomaly determination rule to detect the temperature anomaly time series nodes within the sliding window during the sliding process, and generate temperature anomaly detection information in combination with the corresponding temperature data; Based on the temperature anomaly detection information, calculate the time interval of different degrees of temperature anomalies occurring in the target outdoor energy storage power supply, which is defined as the temperature regulation buffer time. Combine the current heat dissipation mode and real-time temperature characteristics of the target outdoor energy storage power supply to retrieve the regulation strategy in the preset strategy library, and perform intelligent regulation on the target outdoor energy storage power supply through the retrieved regulation strategy.

5. An intelligent temperature control method for an outdoor energy storage power supply according to claim 1, characterized in that, Extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information, and analyze whether there is a risk of internal condensation in the power supply under the current outdoor operation scenario. If there is a risk, perform intelligent regulation and risk warning. Specifically, it includes: Obtain the real-time power operation monitoring information, and extract the internal temperature and humidity monitoring characteristics of the target outdoor energy storage power supply based on the real-time power operation monitoring information to obtain the internal temperature and humidity monitoring characteristic information; Obtain the internal temperature change prediction information, and construct the internal temperature and humidity field of the target outdoor energy storage power supply in combination with the internal temperature and humidity monitoring characteristic information. Define the relative humidity and dew point temperature as the basis for judging internal condensation in the power supply; Introduce the indirect method to analyze the relative humidity and dew point temperature inside the target outdoor energy storage power supply under the current operating environment through the internal temperature and humidity field of the target outdoor energy storage power supply, and make a judgment with the preset risk threshold; If it is greater than the preset risk threshold, obtain the internal temperature characteristics and heat dissipation mode of the target outdoor energy storage power supply at the current moment, and perform a regulation determination in combination with the internal temperature change prediction information; Extract the temperature change trend of the target outdoor energy storage power supply at a future moment through the internal temperature change prediction information. If it is a downward trend or a stable trend, switch the heat dissipation mode of the target outdoor energy storage power supply to the next heat dissipation level; If the temperature change trend of the target outdoor energy storage power supply at a future moment is an upward trend and the current heat dissipation mode is the highest heat dissipation level, switch the real-time operation efficiency mode of the target outdoor energy storage power supply and generate a condensation warning inside the power supply for prompt.

6. An intelligent temperature control method system applicable to outdoor energy storage power supplies, characterized in that, The system includes: a memory and a processor. The memory contains an intelligent temperature control method program applicable to an outdoor energy storage power supply. When the intelligent temperature control method program applicable to the outdoor energy storage power supply is executed by the processor, the steps of the intelligent temperature control method applicable to the outdoor energy storage power supply described in any one of claims 1-5 above are implemented.

Images