Performance testing method and system for energy storage power supply

Abstract

The present invention relates to the field of power supply performance testing, and in particular to a performance testing method and system for energy storage power supplies. The method comprises the following steps: obtaining real-time energy storage power supply state parameters and surface temperature images of energy storage power supplies; generating surface time-series temperature change data based on the surface temperature images of energy storage power supplies; quantifying the fluctuation trend of the surface time-series temperature change data to obtain power supply temperature distribution trend data; performing temperature distribution space mapping processing on the surface temperature image of the energy storage power supply based on the power supply temperature distribution trend data to generate a power supply temperature distribution network; constructing a power supply temperature distribution scene graph based on the power supply temperature distribution network; obtaining multi-view images of the energy storage power supply; obtaining spatial orientation data of each image based on the multi-view images of the energy storage power supply; performing three-dimensional reconstruction processing on the multi-view images of the energy storage power supply based on the spatial orientation data of each image to construct a three-dimensional structure model of the power supply. The present invention realizes efficient and accurate performance testing of energy storage power supplies.

Description

Technical Field

[0001] The present invention relates to the field of power supply performance testing, and in particular to a performance testing method and system for an energy storage power supply. Background Art

[0002] With the rapid development of renewable energy and electric transportation, energy storage power supplies, as important equipment for energy storage and release, are widely used in power grid peak regulation, peak-valley filling, emergency backup power supplies, electric vehicles and other fields. The performance test of energy storage power supplies is a key step in evaluating their performance indicators and effectively utilizing energy. However, traditional energy storage power supply performance testing relies on manual monitoring and laboratory testing, which has the problems of low test efficiency, strong subjectivity and inaccuracy in analysis results. With the continuous advancement of energy storage technology and the increasing complexity of application scenarios, an intelligent energy storage power supply performance testing method is urgently needed to meet the urgent needs of modern power systems for the reliability of energy storage power supply performance. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a performance testing method and system for an energy storage power supply to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a performance testing method for an energy storage power supply, comprising the following steps:

[0005] Step S1: acquiring real-time energy storage power supply state parameters and energy storage power supply surface temperature image; quantifying the fluctuation trend of the energy storage power supply surface temperature image to obtain power supply temperature distribution trend data;

[0006] Step S2: Based on the power supply temperature distribution trend data, the surface temperature image of the energy storage power supply is subjected to temperature distribution space mapping processing to construct a power supply temperature distribution scene diagram;

[0007] Step S3: Acquire multi-view images of the energy storage power supply; perform three-dimensional reconstruction processing on the multi-view images of the energy storage power supply to construct a three-dimensional structure model of the power supply;

[0008] Step S4: Quantitatively mine the power consumption performance of the real-time energy storage power supply state parameters to generate power consumption performance evaluation data;

[0009] Step S5: dynamically rendering the power supply three-dimensional structure model according to the power supply temperature distribution scene diagram to construct a power supply temperature trend rendering model;

[0010] Step S6: Based on the power consumption performance evaluation data, the power temperature trend rendering model is subjected to abnormal temperature area location segmentation processing and performance failure probability calculation, thereby obtaining performance failure probability data; and a power performance failure decision model is constructed based on the performance failure probability data.

[0011] The present invention can obtain the working state and temperature information of the power supply by acquiring the real-time energy storage power supply state parameters and surface temperature image, and provide basic data for subsequent performance testing. The generated surface time series temperature change data can reflect the change trend of the power supply temperature, and provide an important basis for analyzing the power supply performance and faults. The power supply temperature distribution trend data can help understand the temperature distribution inside the power supply, and provide more comprehensive information for performance testing. The temperature distribution space mapping processing can apply the power supply temperature distribution trend data to the energy storage power supply surface temperature image to form a power supply temperature distribution network, and further reveal the distribution of the internal temperature of the power supply. The generated power supply temperature distribution scene diagram can intuitively display the temperature distribution of various parts of the power supply, and provide a visual reference for performance testing. Acquiring multi-view images of the energy storage power supply can provide power supply image data from multiple viewpoints, and provide more comprehensive information for subsequent three-dimensional reconstruction and performance testing. By acquiring the spatial orientation data of each image, the position and angle of the image in the three-dimensional space can be determined, and accurate positioning information can be provided for subsequent three-dimensional reconstruction. The constructed power supply three-dimensional structure model can present the appearance and internal structure of the power supply in three-dimensional form, and provide a more realistic scene for performance testing. The generated battery capacity attenuation data can reflect the change of battery capacity over time, and provide a reference for performance testing. The test provides information on battery life. Through the analysis of turnover efficiency response, the energy conversion efficiency of the power supply under different working conditions can be understood, and energy efficiency evaluation indicators can be provided for performance testing. The power consumption performance evaluation data is obtained by quantitatively analyzing the power turnover efficiency response and battery capacity attenuation data, which can evaluate the power consumption performance and stability of the power supply. The temperature trend prediction can predict the change trend of the power supply temperature in the future based on the power supply temperature distribution scene diagram, which is helpful to discover potential temperature anomalies in advance. By dynamically rendering the three-dimensional structure model of the power supply, the temperature trend prediction can be applied to the three-dimensional model of the power supply to form a power supply temperature trend rendering model, which further intuitively displays the change of the power supply temperature. The abnormal temperature area positioning and segmentation processing can locate the temperature abnormal area through the analysis of the power supply temperature trend rendering model, which is helpful to discover the performance faults in the power supply. The performance failure probability calculation of the abnormal temperature area model using the power consumption performance evaluation data can evaluate the probability of performance failure in the temperature abnormal area, providing a basis for fault prediction and maintenance. The power supply performance failure decision model is constructed based on the performance failure probability data, which can assist decision makers in making corresponding maintenance or replacement decisions when abnormal temperature areas are found, thereby improving the performance and reliability of the power supply.

[0012] Preferably, step S1 comprises the following steps:

[0013] Step S11: performing transient multi-frequency voltage excitation processing on the energy storage power supply to obtain real-time energy storage power supply state parameters, and performing power supply thermal imaging detection to extract the surface temperature image of the energy storage power supply;

[0014] Step S12: performing temperature difference distribution recognition on the surface temperature image of the energy storage power source to generate surface temperature difference distribution data;

[0015] Step S13: performing time-series temperature fluctuation analysis on the surface temperature difference distribution data to generate surface time-series temperature change data;

[0016] Step S14: quantifying the fluctuation trend of the surface temporal temperature variation data to obtain power supply temperature distribution trend data.

[0017] The present invention can excite the energy storage power supply through transient multi-frequency voltage excitation processing, and obtain real-time power supply state parameters. These parameters may include information such as voltage, current, and power, which are used to understand the working state of the power supply, perform power supply thermal imaging detection and extract the surface temperature image of the energy storage power supply, and obtain the temperature distribution of the power supply surface. The energy storage power supply generates heat during operation. The temperature change of the power supply surface can be intuitively observed through thermal imaging detection. By performing temperature difference distribution recognition on the surface temperature image of the energy storage power supply, the temperature difference in different areas of the power supply surface can be analyzed. The temperature difference distribution data can reflect the heat distribution of different parts of the power supply, and the heat dissipation performance of the power supply can be evaluated. By performing time series analysis on the surface temperature difference distribution data, the change of the power supply surface temperature over time can be observed. The time series temperature change data can reveal the temperature fluctuation of the power supply during operation, and help understand the heat accumulation and heat dissipation of the power supply. By quantifying the fluctuation trend of the surface time series temperature change data, the change trend of the power supply temperature can be quantified. The power supply temperature distribution trend data can reflect the temperature change law of the power supply under different working states, and provide an important basis for subsequent performance testing. These trend data are helpful to understand the temperature distribution of the power supply, find abnormal temperature changes, and evaluate the thermal management performance of the power supply.

[0018] Preferably, the specific steps of step S2 are:

[0019] Step S21: performing power supply surface view recognition based on the energy storage power supply surface temperature image to construct a power supply surface coordinate system;

[0020] Step S22: performing temperature distribution space mapping processing on the power supply surface coordinate system based on the power supply temperature distribution trend data to generate a power supply temperature distribution network;

[0021] Step S23: performing interpolation smoothing optimization on the power supply temperature distribution network to obtain an optimized power supply temperature distribution network;

[0022] Step S24: performing discrete voxel decomposition on the optimized power supply temperature distribution network to obtain a plurality of temperature segmentation units;

[0023] Step S25: performing inter-unit temperature correlation characteristic analysis based on multiple temperature segmentation units to generate unit temperature correlation characteristic data;

[0024] Step S26: performing global convolution feature activation processing on the optimized power supply temperature distribution network based on the unit temperature associated feature data to construct a power supply temperature distribution scene graph.

[0025] The present invention can perform image processing on the surface of the energy storage power supply through power supply surface view recognition, identify the geometric shape and component position of the power supply, so that the power supply surface coordinate system can be established to provide accurate spatial reference for subsequent temperature distribution analysis. By mapping the power supply temperature distribution trend data to the power supply surface coordinate system, a power supply temperature distribution network can be established. This network can associate the temperature value of each position with its corresponding coordinates to form a spatial temperature distribution model. Through interpolation smoothing optimization, the power supply temperature distribution network can be processed to fill in possible temperature data missing or noise, so that a more accurate and smooth power supply temperature distribution network can be obtained, and the accuracy and reliability of subsequent analysis can be improved. Through discrete voxel decomposition, the optimized power supply temperature can be The distribution network is decomposed into multiple temperature segmentation units. Each temperature segmentation unit represents a small area on the surface of the power supply and has its own temperature characteristics, which facilitates the analysis and comparison of local temperature changes. By performing temperature correlation feature analysis on multiple temperature segmentation units, the temperature relationship and interaction between different units can be revealed. These unit temperature correlation feature data can provide information about the internal heat transfer and heat dissipation of the power supply, and provide more detailed temperature distribution characteristics for performance testing. Through global convolution feature activation processing, the unit temperature correlation feature data can be used to process the optimized power supply temperature distribution network and construct a power supply temperature distribution scene graph. This scene graph can more intuitively display the overall characteristics of the internal temperature distribution of the power supply and help understand the thermal distribution of the power supply.

[0026] Preferably, the specific steps of step S3 are:

[0027] Step S31: Acquire multi-view images of the energy storage power source;

[0028] Step S32: performing image spatial orientation analysis on the multi-view images of the energy storage power source to obtain spatial orientation data of each image;

[0029] Step S33: performing component node recognition on the multi-view image of the energy storage power source to mark the power source component nodes;

[0030] Step S34: performing node space layout analysis on power supply component nodes to generate component node space layout data;

[0031] Step S35: Perform three-dimensional reconstruction processing on the spatial layout data of the component nodes based on the spatial orientation data of each image to construct a three-dimensional structural model of the power supply.

[0032] The present invention can obtain image information of multiple angles and perspectives of the power supply by acquiring multi-view images. These images can provide key information such as the external shape, component layout and component position of the power supply, providing the necessary data basis for subsequent analysis and testing. Through image spatial orientation analysis, the position and direction of each image in the power supply space can be determined, so that the spatial coordinate system of each image can be established, providing the corresponding relationship between the image and the actual space of the power supply, and providing accurate positioning information for subsequent three-dimensional reconstruction and spatial analysis. Through component node recognition, the component node position of the power supply can be accurately marked in the image. These nodes represent the key components or connection points of the power supply, and can provide important information about the power supply structure. Marking component nodes is helpful for subsequent Structural analysis and spatial layout analysis. Through node spatial layout analysis, the spatial relationship and layout between power supply component nodes can be determined. These data can describe the relative position, connection relationship and spatial hierarchy of the internal components of the power supply. The node spatial layout data helps to understand the structural characteristics of the power supply and the spatial constraints between components. Through three-dimensional reconstruction processing, the spatial orientation data of each image and the component node spatial layout data can be combined to generate a three-dimensional structural model of the power supply. This model can provide a visual representation of the geometry, relative position and spatial layout of the internal components of the power supply. The three-dimensional structural model of the power supply helps to deeply understand the internal structure of the power supply and the relationship between components, and provide a more comprehensive information basis for performance testing and analysis.

[0033] Preferably, the specific steps of step S35 are:

[0034] Calculate the spatial pixel coordinates of the power supply component nodes based on the multi-view images of the energy storage power supply to obtain the pixel coordinates of the component nodes;

[0035] Perform node feature space registration on the power component nodes according to the spatial orientation data of each image to obtain node space matching association data;

[0036] Based on the node space matching association data, the three-dimensional coordinates of the component node pixel coordinates are reversely calculated to obtain the three-dimensional position coordinates of the component;

[0037] Based on the three-dimensional position coordinates of the components, point cloud modeling is performed on the spatial layout data of the component nodes to generate a preliminary power supply point cloud model;

[0038] Identify the point cloud normal distribution of the preliminary power point cloud model and extract the normal feature direction;

[0039] Based on the normal feature direction, the base surface is accurately divided to obtain multiple point cloud model base surfaces;

[0040] Based on multiple point cloud model base surfaces, a preliminary power point cloud model is subjected to three-dimensional reconstruction to obtain a power structure model;

[0041] The morphological surface deviation of the power supply structure model is optimized to construct a three-dimensional structure model of the power supply.

[0042] By analyzing and processing multi-view images, the present invention can calculate the pixel coordinates of the power supply component nodes in the image, and these pixel coordinates can provide accurate position information of the component nodes on the image, and provide basic data for subsequent node feature space registration and three-dimensional coordinate inverse calculation. Through node feature space registration, the component nodes in different images can be matched and associated, and a spatial correspondence between them can be established. The spatial matching association data of these nodes can provide the relative position and geometric relationship of the component nodes in the three-dimensional space, and provide accurate spatial information for the subsequent three-dimensional coordinate inverse calculation and point cloud modeling. Through the three-dimensional coordinate inverse calculation, the pixel coordinates of the component nodes can be converted into position coordinates in the three-dimensional space using the node space matching association data. These component three-dimensional position coordinates can provide accurate position information of the power supply component in the real space, and provide accurate spatial coordinates for subsequent point cloud modeling and three-dimensional reconstruction processing. By performing point cloud modeling on the component three-dimensional position coordinates, the position information of the component nodes can be expressed in the form of point clouds. The preliminary power point cloud model provides a rough shape of the power supply component in the three-dimensional space. The shape and layout information provides a basis for subsequent 3D reconstruction and structural optimization. Through point cloud normal distribution recognition, the normal direction of each point in the preliminary power point cloud model can be calculated. The normal feature direction provides the orientation information of the surface of the power component, which is helpful for the subsequent point cloud model division and reconstruction. Through the precise division of the base surface, the preliminary power point cloud model can be divided into multiple base surface areas. These base surface areas represent different surfaces or parts of the power component, providing a more accurate division and processing basis for the subsequent 3D reconstruction and morphological surface deviation optimization. Through 3D reconstruction, the preliminary power point cloud model can be reconstructed based on multiple point cloud model base surfaces. The power structure model provides the complete 3D geometric shape and structural information of the power component, providing an accurate geometric representation and spatial layout for the performance test of the power supply. Through morphological surface deviation optimization, the power structure model can be refined and optimized to reduce the morphological surface deviation between components, so that a more accurate and realistic 3D structure model of the power supply can be generated, providing the spatial relationship and geometric constraint information between the power components, and providing a more accurate basis for performance testing and analysis.

[0043] Preferably, the specific steps of step S4 are:

[0044] Step S41: performing battery capacity decay analysis on the real-time energy storage power supply state parameters to generate battery capacity decay data;

[0045] Step S42: performing multi-time point power calculation on the real-time energy storage power supply state parameters, thereby obtaining a power supply time sequence power curve;

[0046] Step S43: performing a turnover efficiency response analysis on the power supply timing power curve to generate power supply turnover efficiency response data;

[0047] Step S44: Quantitative mining of power consumption performance is performed on the power turnover efficiency response data and the battery capacity attenuation data to generate power consumption performance evaluation data.

[0048] The present invention can evaluate the attenuation of battery capacity by analyzing the real-time energy storage power supply state parameters. The battery capacity attenuation data provides information on the change of battery storage energy over time, which can be used to judge the degree of degradation of battery performance and predict battery life, and provide a basis for subsequent power consumption performance evaluation. By performing multi-time point power calculation on the real-time energy storage power supply state parameters, the output power value of the power supply at different time points can be obtained. The power supply timing power curve provides information on the change of power supply output power over time, which can describe the power characteristics of the power supply under different working states, and provide a basis for subsequent turnover efficiency response analysis and power consumption performance evaluation. By performing turnover efficiency response analysis on the power supply timing power curve, the energy conversion efficiency of the power supply under different load conditions can be evaluated. The power supply turnover efficiency response data provides information on the energy conversion efficiency of the power supply under different workloads, which can be used to analyze the performance quality and energy utilization of the power supply. By performing power consumption performance quantitative mining on the power supply turnover efficiency response data and the battery capacity attenuation data, the power consumption performance of the power supply can be comprehensively evaluated. The power consumption performance evaluation data provides quantitative analysis results of key indicators such as the energy conversion efficiency and battery life of the power supply in actual operation, which can be used to judge the performance quality of the power supply and predict the long-term operation capability of the power supply.

[0049] Preferably, the specific steps of step S5 are:

[0050] Step S51: performing temperature trend evolution processing on the power supply temperature distribution scene graph to generate temperature trend evolution data;

[0051] Step S52: performing temperature trend prediction on the power supply temperature distribution scene graph based on the temperature trend evolution data to obtain a temperature trend prediction scene graph;

[0052] Step S53: dynamically rendering the power supply three-dimensional structure model according to the temperature trend prediction scene graph to construct a power supply temperature trend rendering model.

[0053] The present invention can simulate the change of power supply temperature over time by performing temperature trend evolution processing on the power supply temperature distribution scene graph. The temperature trend evolution data provides the temperature value of the power supply at different time points, which can be used to analyze the thermal characteristics, heat conduction effect and temperature change law of the power supply. By making predictions based on the temperature trend evolution data, the change of the power supply temperature at future time points can be inferred. The temperature trend prediction scene graph provides the temperature distribution of the power supply at future time points, which can be used to predict the temperature change trend of the power supply under different workloads and environmental conditions, and provide guidance for designing and optimizing the heat dissipation system of the power supply. By dynamically rendering the temperature trend prediction scene graph, the temperature change can be visualized on the three-dimensional structural model of the power supply. The power supply temperature trend rendering model shows the temperature distribution of the power supply at different time points, and the hot spot positions and temperature changes of each component of the power supply can be intuitively observed, providing a reference for optimizing the heat dissipation design and thermal management strategy of the power supply.

[0054] Preferably, the specific steps of step S6 are:

[0055] Step S61: performing abnormal temperature trend analysis on the power supply temperature trend rendering model to generate abnormal temperature trend data;

[0056] Step S62: performing abnormal temperature region positioning and segmentation processing on the power supply temperature trend rendering model based on the abnormal temperature trend data to obtain an abnormal temperature region model;

[0057] Step S63: quantifying the overheat power consumption of the abnormal temperature area model using the power consumption performance evaluation data, and generating overheat power consumption data of the abnormal temperature area;

[0058] Step S64: Calculate the performance failure probability of the overheat power consumption data in the abnormal temperature area, thereby obtaining performance failure probability data;

[0059] Step S65: Perform fault test decision analysis on the performance fault probability data to construct a power supply performance fault test model.

[0060] The present invention can detect abnormal temperature changes by performing abnormal temperature trend analysis on the power supply temperature trend rendering model. The abnormal temperature trend data provides the time evolution information of the abnormal temperature area, which can be used to discover the temperature abnormality that occurs in the power supply within a specific time period, and provide a basis for subsequent fault diagnosis and prevention. By analyzing and processing the abnormal temperature trend data, the area with abnormal temperature in the power supply can be located and segmented. The abnormal temperature area model provides the spatial distribution of abnormal temperature in the power supply, which can help determine the specific abnormal temperature area and provide guidance for subsequent fault diagnosis and thermal management strategies. By performing power consumption quantitative analysis on the abnormal temperature area model, the degree of overheating of the power supply by the abnormal temperature area can be evaluated. The overheating power consumption data of the abnormal temperature area provides the power consumption of the abnormal temperature area, which can be used to analyze the degree of influence of the abnormal temperature area on the power supply performance and reliability, and provide a reference for optimizing the power supply design and improving the thermal management strategy. By performing probability calculation on the overheating power consumption data of the abnormal temperature area, the probability of power supply performance failure can be evaluated. The performance failure probability data provides the probability information of the abnormal temperature area causing the performance failure, which can be used to judge the reliability of the power supply and predict the risk of performance failure, and provide a basis for formulating targeted maintenance and repair strategies. By analyzing and making decisions based on performance failure probability data, targeted fault handling strategies can be developed. The power supply performance failure decision model provides a decision basis based on performance failure probability, which can help decision makers determine when to take maintenance, repair or replacement measures to ensure the reliability and performance of the power supply.

[0061] In this specification, a performance test system of an energy storage power supply is provided, which is used to perform the performance test method of the energy storage power supply as described above, including:

[0062] The time series temperature module obtains the real-time energy storage power supply status parameters and the energy storage power supply surface temperature image; quantifies the fluctuation trend of the energy storage power supply surface temperature image to obtain the power supply temperature distribution trend data;

[0063] The temperature distribution module performs temperature distribution space mapping processing on the surface temperature image of the energy storage power supply based on the power supply temperature distribution trend data, and constructs a power supply temperature distribution scene diagram;

[0064] The three-dimensional reconstruction module obtains multi-view images of the energy storage power supply; performs three-dimensional reconstruction processing on the multi-view images of the energy storage power supply to construct a three-dimensional structural model of the power supply;

[0065] The power consumption performance module conducts quantitative mining of power consumption performance of real-time energy storage power supply status parameters and generates power consumption performance evaluation data;

[0066] The temperature trend prediction module dynamically renders the power supply three-dimensional structure model according to the power supply temperature distribution scene diagram to build a power supply temperature trend rendering model;

[0067] The fault decision module locates and segments the abnormal temperature area and calculates the performance fault probability of the power supply temperature trend rendering model based on the power supply power consumption performance evaluation data, thereby obtaining the performance fault probability data; and constructs the power supply performance fault decision model based on the performance fault probability data.

[0068] The present invention can obtain the state information and surface temperature distribution of the power supply by acquiring the real-time energy storage power supply state parameters and the surface temperature image of the energy storage power supply, and provide necessary data for subsequent performance testing. By processing the surface temperature image of the energy storage power supply, the time-series change data of the power supply temperature can be obtained, and its fluctuation trend is quantified to obtain the trend data of the power supply temperature distribution, and the temperature change of the power supply can be further understood. By acquiring the multi-view image of the energy storage power supply and performing three-dimensional reconstruction processing, a three-dimensional structural model of the power supply can be constructed, providing the spatial information of the power supply, and providing a basis for subsequent performance testing and analysis. By analyzing the real-time energy storage power supply state parameters, battery capacity decay data and power supply turnover efficiency response data can be generated. Further power consumption performance analysis can be performed on these data to obtain power consumption performance evaluation data of the power supply, and the battery capacity decay and turnover efficiency of the power supply during use can be understood. By analyzing the real-time energy storage power supply state parameters, battery capacity decay data and power supply turnover efficiency response data can be generated. Further power consumption performance analysis can be performed on these data to obtain power consumption performance evaluation data of the power supply, and the battery capacity decay and turnover efficiency of the power supply during use can be understood. By processing the temperature trend model, the abnormal temperature area in the power supply can be located and segmented. Using performance failure probability data, a power supply performance failure decision model can be constructed to help determine and predict power supply performance failure situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A schematic diagram of the steps of a performance testing method for an energy storage power supply according to the present invention;

[0070] Figure 2 Detailed implementation flow chart of step S1;

[0071] Figure 3 Detailed implementation flow chart of step S2;

[0072] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0073] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0074] The present application example provides a performance test method and system for an energy storage power supply. The execution subject of the performance test method and system for an energy storage power supply includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as a general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0075] See also Figures 1 to 4 The present invention provides a performance test method for an energy storage power supply, the performance test method for an energy storage power supply comprising the following steps:

[0076] Step S1: acquiring real-time energy storage power supply state parameters and energy storage power supply surface temperature image; quantifying the fluctuation trend of the energy storage power supply surface temperature image to obtain power supply temperature distribution trend data;

[0077] Step S2: Based on the power supply temperature distribution trend data, the surface temperature image of the energy storage power supply is subjected to temperature distribution space mapping processing to construct a power supply temperature distribution scene diagram;

[0078] Step S3: Acquire multi-view images of the energy storage power supply; perform three-dimensional reconstruction processing on the multi-view images of the energy storage power supply to construct a three-dimensional structure model of the power supply;

[0079] Step S4: Quantitatively mine the power consumption performance of the real-time energy storage power supply state parameters to generate power consumption performance evaluation data;

[0080] Step S5: dynamically rendering the power supply three-dimensional structure model according to the power supply temperature distribution scene diagram to construct a power supply temperature trend rendering model;

[0081] Step S6: Based on the power consumption performance evaluation data, the power temperature trend rendering model is subjected to abnormal temperature area location segmentation processing and performance failure probability calculation to obtain performance failure probability data; and a power performance failure decision model is constructed based on the performance failure probability data.

[0082] The present invention can obtain the working state and temperature information of the power supply by acquiring the real-time energy storage power supply state parameters and surface temperature image, and provide basic data for subsequent performance testing. The generated surface time series temperature change data can reflect the change trend of the power supply temperature, and provide an important basis for analyzing the power supply performance and faults. The power supply temperature distribution trend data can help understand the temperature distribution inside the power supply, and provide more comprehensive information for performance testing. The temperature distribution space mapping processing can apply the power supply temperature distribution trend data to the energy storage power supply surface temperature image to form a power supply temperature distribution network, and further reveal the distribution of the internal temperature of the power supply. The generated power supply temperature distribution scene diagram can intuitively display the temperature distribution of various parts of the power supply, and provide a visual reference for performance testing. Acquiring multi-view images of the energy storage power supply can provide power supply image data from multiple viewpoints, and provide more comprehensive information for subsequent three-dimensional reconstruction and performance testing. By acquiring the spatial orientation data of each image, the position and angle of the image in the three-dimensional space can be determined, and accurate positioning information can be provided for subsequent three-dimensional reconstruction. The constructed power supply three-dimensional structure model can present the appearance and internal structure of the power supply in three-dimensional form, and provide a more realistic scene for performance testing. The generated battery capacity attenuation data can reflect the change of battery capacity over time, and provide a reference for performance testing. The test provides information on battery life. Through the analysis of turnover efficiency response, the energy conversion efficiency of the power supply under different working conditions can be understood, and energy efficiency evaluation indicators can be provided for performance testing. The power consumption performance evaluation data is obtained by quantitatively analyzing the power turnover efficiency response and battery capacity attenuation data, which can evaluate the power consumption performance and stability of the power supply. The temperature trend prediction can predict the change trend of the power supply temperature in the future based on the power supply temperature distribution scene diagram, which is helpful to discover potential temperature anomalies in advance. By dynamically rendering the three-dimensional structure model of the power supply, the temperature trend prediction can be applied to the three-dimensional model of the power supply to form a power supply temperature trend rendering model, which further intuitively displays the change of the power supply temperature. The abnormal temperature area positioning and segmentation processing can locate the temperature abnormal area through the analysis of the power supply temperature trend rendering model, which is helpful to discover the performance faults in the power supply. The performance failure probability calculation of the abnormal temperature area model using the power consumption performance evaluation data can evaluate the probability of performance failure in the temperature abnormal area, providing a basis for fault prediction and maintenance. The power supply performance failure decision model is constructed based on the performance failure probability data, which can assist decision makers in making corresponding maintenance or replacement decisions when abnormal temperature areas are found, thereby improving the performance and reliability of the power supply.

[0083] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a performance test method for an energy storage power supply of the present invention. In this example, the steps of the performance test method for an energy storage power supply include:

[0084] Step S1: acquiring real-time energy storage power supply state parameters and energy storage power supply surface temperature image; quantifying the fluctuation trend of the energy storage power supply surface temperature image to obtain power supply temperature distribution trend data;

[0085] In this embodiment, real-time energy storage power supply state parameters, such as current, voltage, capacity, charge and discharge state, etc., are obtained through sensors or monitoring equipment. These parameters reflect the current working state of the energy storage power supply. An infrared thermal imager or other thermal imaging equipment is used to scan the surface of the energy storage power supply to obtain a temperature distribution image of the surface of the energy storage power supply. The thermal imaging equipment can map different temperature areas into a heat map to provide visual temperature information. Time series analysis is performed on the surface temperature image of the energy storage power supply to extract temperature data at different time points. This can be done by analyzing and sampling the image to extract the relationship between the temperature value and time. The surface time series temperature change data is subjected to fluctuation analysis. Statistical methods or signal processing techniques, such as Fourier transform, wavelet transform, etc., can be used. These methods can extract the fluctuation properties of the temperature data, including amplitude, frequency, period, etc. According to the results of the fluctuation trend quantification, the trend data of the power supply temperature distribution is obtained. These data can characterize the overall change trend of the power supply temperature, including temperature rise, fall, stability, etc.

[0086] Step S2: Based on the power supply temperature distribution trend data, the surface temperature image of the energy storage power supply is subjected to temperature distribution space mapping processing to construct a power supply temperature distribution scene diagram;

[0087] In this embodiment, the power supply temperature distribution trend data is associated with the energy storage power supply surface temperature image. The temperature distribution trend data is mapped to each pixel of the energy storage power supply surface temperature image using an interpolation or mapping algorithm. A power supply temperature distribution network is constructed based on the energy storage power supply surface temperature image after the temperature distribution space mapping process. Each pixel is used as a network node, and the connection between nodes represents the temperature relationship between adjacent pixels. On the power supply temperature distribution network, a power supply temperature distribution scene graph is constructed based on the temperature relationship and connection strength between nodes. The scene graph can be a two-dimensional or three-dimensional visual image that reflects the spatial characteristics and changing trends of the power supply temperature distribution.

[0088] Step S3: Acquire multi-view images of the energy storage power supply; perform three-dimensional reconstruction processing on the multi-view images of the energy storage power supply to construct a three-dimensional structure model of the power supply;

[0089] In this embodiment, a camera or image acquisition device with multiple viewing angles is used to shoot the energy storage power supply to obtain multi-view images of the energy storage power supply, ensuring that the viewing angle covers all directions and angles of the energy storage power supply, and performing image processing and computer vision algorithm on each image to extract spatial orientation data of each image, which may include information such as internal and external parameters of the camera, viewing angle direction, and viewing angle distance of the image. A three-dimensional reconstruction algorithm is used to perform three-dimensional reconstruction processing on the multi-view images of the energy storage power supply according to the spatial orientation data of each image, which may include stereo matching, point cloud reconstruction, voxelization, and other steps, and feature points or pixel points in the viewing angle images are converted into three-dimensional coordinate points of the energy storage power supply. A three-dimensional structural model of the power supply is constructed according to the viewing angle images of the energy storage power supply that have been three-dimensionally reconstructed and the obtained three-dimensional coordinate points. This can be done by using three-dimensional modeling software or algorithms to connect or fill the coordinate points to generate a three-dimensional model of the power supply.

[0090] Step S4: Quantitatively mine the power consumption performance of the real-time energy storage power supply state parameters to generate power consumption performance evaluation data;

[0091] In this embodiment, real-time energy storage power supply state parameters, such as current, voltage, capacity, etc., are used to generate battery capacity decay data. This can be achieved by monitoring the battery charging and discharging process, recording the battery capacity value at each time point, and analyzing and calculating the capacity change. Real-time energy storage power supply state parameters are used to perform response analysis on the power supply turnover efficiency. This can be achieved by calculating the input power and output power at each time point, as well as the corresponding energy loss, to obtain the power supply turnover efficiency. According to different working states and load conditions, power supply turnover efficiency response data is generated. Combined with the power supply turnover efficiency response data and battery capacity decay data, power consumption performance is quantitatively mined. This can be achieved by analyzing indicators such as the power supply's energy conversion efficiency, energy loss, and capacity decay rate to evaluate the power consumption performance of the power supply. Based on the analysis of the power supply turnover efficiency response data and the battery capacity decay data, power consumption performance evaluation data is generated. This can include the power supply's energy conversion efficiency curve, capacity decay curve, energy consumption curve, etc., which are used to evaluate the power consumption performance of the power supply under different working conditions.

[0092] Step S5: dynamically rendering the power supply three-dimensional structure model according to the power supply temperature distribution scene diagram to construct a power supply temperature trend rendering model;

[0093] In this embodiment, the temperature trend of the power supply is predicted using historical temperature distribution data and related temperature change models. This can use machine learning methods, time series analysis and other technologies to predict temperature changes in the future based on trends and patterns of historical data. Based on the prediction of the power supply temperature, a temperature trend prediction scene graph is generated, which can map the predicted temperature value to the three-dimensional structural model of the power supply to form a scene graph representing the temperature trend. The color or texture of each point or area can be adjusted according to the temperature change to reflect the temperature distribution of different parts of the power supply. The temperature trend prediction scene graph is merged with the three-dimensional structural model of the power supply for dynamic rendering. This can give the three-dimensional structural model of the power supply a corresponding temperature effect based on the temperature information in the temperature trend prediction scene graph. For example, by changing the color, transparency or texture of the model surface to simulate the temperature distribution of the power supply in different areas and time points, the temperature trend rendering model of the power supply is constructed in combination with the temperature trend prediction scene graph and the dynamic rendering of the three-dimensional structural model of the power supply. The model can provide a visual presentation of the temperature change of the power supply over time, so that the user can intuitively observe and analyze the temperature trend of the power supply.

[0094] Step S6: Based on the power consumption performance evaluation data, the power temperature trend rendering model is subjected to abnormal temperature area location segmentation processing and performance failure probability calculation, thereby obtaining performance failure probability data; and a power performance failure decision model is constructed based on the performance failure probability data.

[0095] In this embodiment, based on the power supply temperature trend rendering model, the abnormal temperature area is positioned and segmented. This can use image processing technology, computer vision algorithm and other methods to identify the temperature abnormal area and segment it to form an abnormal temperature area model. These abnormal temperature areas may be areas with potential faults or abnormalities in the power supply. Based on the power supply power consumption performance evaluation data, the abnormal temperature area model is calculated for the performance failure probability. This can use statistical analysis methods, machine learning algorithms, etc., combined with the location, shape, temperature change trend and other characteristics of the abnormal temperature area, to infer the probability of performance failure in the area. The source power consumption performance evaluation data provides power supply performance status and failure information, which is used to assist in determining the failure probability of the abnormal temperature area. Based on the performance failure probability calculation of the abnormal temperature area model, performance failure probability data of each abnormal temperature area is obtained. These data can be used to evaluate the possibility of performance failure in each abnormal temperature area, thereby providing a basis for subsequent fault diagnosis and decision-making. Based on the performance failure probability data, a performance failure decision model of the power supply is constructed. This can use decision trees, probability models, rule engines and other methods to formulate corresponding decision strategies according to the performance failure probabilities of different abnormal temperature areas. The decision model can help determine the type and severity of performance failures in the power supply and provide corresponding fault handling suggestions.

[0096] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0097] Step S11: performing transient multi-frequency voltage excitation processing on the energy storage power supply to obtain real-time energy storage power supply state parameters, and performing power supply thermal imaging detection to extract the surface temperature image of the energy storage power supply;

[0098] Step S12: performing temperature difference distribution recognition on the surface temperature image of the energy storage power source to generate surface temperature difference distribution data;

[0099] Step S13: performing time-series temperature fluctuation analysis on the surface temperature difference distribution data to generate surface time-series temperature change data;

[0100] Step S14: quantifying the fluctuation trend of the surface temporal temperature variation data to obtain power supply temperature distribution trend data.

[0101] In this embodiment, a transient multi-frequency voltage excitation is applied to the energy storage power supply, and the response of the power supply is stimulated by changing parameters such as the voltage frequency and amplitude, and the output current, voltage and other related parameters of the energy storage power supply are monitored to obtain real-time state parameters of the energy storage power supply, and thermal imaging detection of the power supply is performed. A temperature image of the surface of the energy storage power supply is obtained using a thermal imager or an infrared camera, and the surface temperature image of the energy storage power supply is processed and analyzed to identify the temperature difference distribution in the image, that is, the temperature difference between different regions, and to extract and record the surface temperature difference distribution data, including the temperature difference and distribution of different regions. The surface temperature difference distribution data is subjected to time series analysis, and the temperature difference values ​​at different time points are arranged in chronological order. The fluctuation of the temperature difference values, including amplitude, period, trend, etc., is analyzed, and the surface time series temperature change data, that is, the temperature difference values ​​at different time points and their change trend, are extracted and recorded. The surface time series temperature change data is further quantitatively analyzed, and the amplitude, frequency, change rate and other indicators of the fluctuation are calculated according to the fluctuation of the temperature change. The quantified data is used to describe the trend of the power supply temperature distribution, including the rising or falling trend of the temperature, the intensity of the fluctuation, etc.

[0102] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0103] Step S21: performing power supply surface view recognition based on the energy storage power supply surface temperature image to construct a power supply surface coordinate system;

[0104] Step S22: performing temperature distribution space mapping processing on the power supply surface coordinate system based on the power supply temperature distribution trend data to generate a power supply temperature distribution network;

[0105] Step S23: performing interpolation smoothing optimization on the power supply temperature distribution network to obtain an optimized power supply temperature distribution network;

[0106] Step S24: performing discrete voxel decomposition on the optimized power supply temperature distribution network to obtain a plurality of temperature segmentation units;

[0107] Step S25: performing inter-unit temperature correlation characteristic analysis based on multiple temperature segmentation units to generate unit temperature correlation characteristic data;

[0108] Step S26: performing global convolution feature activation processing on the optimized power supply temperature distribution network based on the unit temperature associated feature data to construct a power supply temperature distribution scene graph.

[0109] In this embodiment, a surface temperature image of an energy storage power supply is obtained, and computer vision techniques such as image segmentation and feature extraction are used to process and analyze the image, identify key feature points or feature areas on the power supply surface, such as edges, connection points, and markers, and establish a coordinate system for the power supply surface based on the identified feature points or feature areas, determine the direction and scale of the coordinate axis, map the power supply surface coordinate system to a spatial grid, associate each grid point with the corresponding coordinate, map the power supply temperature distribution trend data to the corresponding grid point according to the coordinate system, obtain the temperature value of each grid point, construct a power supply temperature distribution network, that is, connect the grid point with its adjacent points to form a network structure, interpolate the temperature values ​​in the power supply temperature distribution network, fill in the missing or incomplete data that may exist, apply a smoothing algorithm such as Gaussian filtering, mean filtering, etc., smooth the temperature values, reduce the influence of noise and outliers, and the optimized power supply temperature distribution network will have a more continuous and smooth temperature distribution, and the optimized power supply The temperature distribution network is discretized to divide the continuous temperature distribution into multiple discrete temperature units. The size and shape of the temperature segmentation unit are determined, which can be a square, rectangle or any shape. It is set according to application requirements, and each temperature segmentation unit is associated with the grid points it contains. The temperature value of each unit is recorded, and the temperature relationship between each temperature segmentation unit and its adjacent units is analyzed. The temperature difference, temperature gradient or other related features between the units are calculated to describe the temperature correlation between the units, and unit temperature correlation feature data is generated. The temperature correlation feature value of each unit is recorded. The unit temperature correlation feature data is used to perform global convolution feature activation processing. A convolutional neural network or other feature extraction methods are used to process and analyze the temperature data in the optimized power supply temperature distribution network, extract the scene features of the power supply temperature distribution, such as local temperature changes, hot spot distribution, temperature gradient, etc., construct a power supply temperature distribution scene graph, and present the extracted features in a visual way to help users intuitively understand the temperature distribution of the power supply.

[0110] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0111] Step S31: Acquire multi-view images of the energy storage power source;

[0112] Step S32: performing image spatial orientation analysis on the multi-view images of the energy storage power source to obtain spatial orientation data of each image;

[0113] Step S33: performing component node recognition on the multi-view image of the energy storage power source to mark the power source component nodes;

[0114] Step S34: performing node space layout analysis on power supply component nodes to generate component node space layout data;

[0115] Step S35: Perform three-dimensional reconstruction processing on the spatial layout data of the component nodes based on the spatial orientation data of each image to construct a three-dimensional structural model of the power supply.

[0116] In this embodiment, a camera or other image acquisition device is used to obtain multiple viewing angle images of the energy storage power supply to ensure that the viewing angle images can fully cover all sides and components of the energy storage power supply. Image processing and analysis are performed on each viewing angle image. Computer vision technology, such as feature extraction and feature matching, is used to find key feature points in the image. Based on the position and distribution of the key feature points, the spatial orientation of each image relative to the energy storage power supply, such as the rotation angle and translation distance, is inferred. The spatial orientation data of each image is recorded for subsequent three-dimensional reconstruction processing. Image processing and computer vision technology are used to identify and segment component nodes for each viewing angle image. Image segmentation algorithms, such as segmentation methods based on color, texture, or shape, can be used to separate component nodes from the image. The components are extracted from the image and each component node is marked for subsequent node spatial layout analysis and three-dimensional reconstruction processing. The positional relationship, connection relationship and spatial position relative to the energy storage power supply between the component nodes are analyzed. The spatial coordinates, relative position and connection information of the component nodes are recorded to generate component node spatial layout data. The spatial orientation data of each image and the component node spatial layout data are used for three-dimensional reconstruction processing. A three-dimensional reconstruction algorithm, such as stereo vision and structured light scanning, is used to convert the spatial position and connection relationship of each component node into three-dimensional coordinates. The three-dimensional coordinates of all component nodes are combined to construct a three-dimensional structural model of the energy storage power supply. The model can be presented using three-dimensional visualization technology so that users can observe and analyze the spatial structure of the energy storage power supply.

[0117] In this embodiment, step S35 includes the following steps:

[0118] Calculate the spatial pixel coordinates of the power supply component nodes based on the multi-view images of the energy storage power supply to obtain the pixel coordinates of the component nodes;

[0119] Perform node feature space registration on the power component nodes according to the spatial orientation data of each image to obtain node space matching association data;

[0120] Based on the node space matching association data, the three-dimensional coordinates of the component node pixel coordinates are reversely calculated to obtain the three-dimensional position coordinates of the component;

[0121] Based on the three-dimensional position coordinates of the components, point cloud modeling is performed on the spatial layout data of the component nodes to generate a preliminary power supply point cloud model;

[0122] Identify the point cloud normal distribution of the preliminary power point cloud model and extract the normal feature direction;

[0123] Based on the normal feature direction, the base surface is accurately divided to obtain multiple point cloud model base surfaces;

[0124] Based on multiple point cloud model base surfaces, a preliminary power point cloud model is subjected to three-dimensional reconstruction to obtain a power structure model;

[0125] The morphological surface deviation of the power supply structure model is optimized to construct a three-dimensional structure model of the power supply.

[0126] In this embodiment, image processing and analysis are performed on each viewing angle image of the energy storage power supply, and computer vision techniques such as edge detection and feature extraction are used to locate and extract the pixel positions of component nodes in the image, and the pixel coordinates of each component node in each image are recorded to obtain the pixel coordinate data of the component nodes. The spatial orientation data of each image are used to perform spatial registration of node features according to the pixel coordinates of the component nodes, and the pixel coordinates of the component nodes in different viewing angle images are converted into spatial coordinates relative to the energy storage power supply. According to the spatial coordinates of the node features, spatial matching association data between the nodes are established, and the node spatial matching association data are used to perform three-dimensional coordinate inverse calculation on the pixel coordinates of the component nodes. The three-dimensional coordinate inverse calculation algorithm is used to infer the three-dimensional position coordinates of the component nodes according to the spatial matching relationship between the nodes. dimensional position coordinates, convert the coordinates of each node into point cloud data, merge the point cloud data of all component nodes to generate a preliminary power supply point cloud model, calculate the point cloud normal of the preliminary power supply point cloud model, use the point cloud normal distribution recognition algorithm to extract the normal feature direction, and accurately divide the base surface of the preliminary power supply point cloud model according to the normal feature direction. The point cloud model is divided into multiple base surfaces, each base surface represents a component node or component part, and each point cloud model base surface is reconstructed in three dimensions. A three-dimensional reconstruction algorithm, such as point cloud registration and surface reconstruction, is used to convert the point cloud data of each base surface into a three-dimensional structural model, and the morphological surface deviation of the power supply structure model is optimized. The morphological surface deviation optimization algorithm is used to fine-tune and optimize the model to reduce the deviation between the morphological surfaces, and finally a three-dimensional structural model of the constructed power supply is obtained.

[0127] In this embodiment, step S4 includes the following steps:

[0128] Step S41: performing battery capacity decay analysis on the real-time energy storage power supply state parameters to generate battery capacity decay data;

[0129] Step S42: performing multi-time point power calculation on the real-time energy storage power supply state parameters, thereby obtaining a power supply time sequence power curve;

[0130] Step S43: performing a turnover efficiency response analysis on the power supply timing power curve to generate power supply turnover efficiency response data;

[0131] Step S44: Quantitative mining of power consumption performance is performed on the power turnover efficiency response data and the battery capacity attenuation data to generate power consumption performance evaluation data.

[0132] In this embodiment, the state parameter data of the real-time energy storage power supply, including battery voltage, current, temperature, etc., is collected, the collected battery voltage and current data are processed, the real-time capacity of the battery is calculated, and the capacity decay rate of the battery is calculated in combination with the initial capacity and real-time capacity of the battery. According to the capacity decay rate and the use time, the battery capacity decay data, including the capacity decay curve and the decay rate, is generated. The state parameter data of the real-time energy storage power supply, such as the battery voltage and current, is used to obtain the power data of multiple time points, the battery voltage and current at each time point are multiplied to obtain the power data of the corresponding time point, and the power is generated in combination with the timestamp information. The timing power curve represents the power changes of the power supply at different time points. The power supply timing power curve data is used to calculate the input power and output power of the power supply at different time points. According to the relationship between the input power and the output power, the turnover efficiency of the power supply at each time point is calculated to generate the power supply turnover efficiency response data, including the turnover efficiency curve and the efficiency response value. The power consumption performance is quantitatively analyzed by combining the power supply turnover efficiency response data and the battery capacity attenuation data. According to the turnover efficiency and capacity attenuation rate of the power supply under different capacity and power conditions, the power consumption performance of the power supply is evaluated to generate the power consumption performance evaluation data, including the power consumption curve and power consumption indicators.

[0133] In this embodiment, step S5 includes the following steps:

[0134] Step S51: performing temperature trend evolution processing on the power supply temperature distribution scene graph to generate temperature trend evolution data;

[0135] Step S52: performing temperature trend prediction on the power supply temperature distribution scene graph based on the temperature trend evolution data to obtain a temperature trend prediction scene graph;

[0136] Step S53: dynamically rendering the power supply three-dimensional structure model according to the temperature trend prediction scene graph to construct a power supply temperature trend rendering model.

[0137] In this embodiment, the scene graph is processed in time series, the temperature distribution data at different time points are extracted, the temperature distribution data at different time points are analyzed, and the temperature trend is calculated, such as the rate of temperature rise or fall. Based on the temperature trend, temperature trend evolution data is generated, including information such as the temperature change trend and rate. The temperature trend evolution data is used to predict and calculate the temperature trend. Based on the predicted temperature trend, the power supply temperature distribution scene graph is adjusted accordingly. The predicted temperature trend is applied to generate a temperature trend prediction scene graph to show the change of the power supply temperature in the future time period. The temperature data in the temperature trend prediction scene graph is mapped to the three-dimensional structural model of the power supply. Based on the change of the temperature data, the three-dimensional structural model of the power supply is dynamically rendered to show the change of the power supply temperature at different positions. Through dynamic rendering, a power supply temperature trend rendering model is generated to show the temperature change and spatial distribution of the power supply over time.

[0138] In this embodiment, step S6 includes the following steps:

[0139] Step S61: performing abnormal temperature trend analysis on the power supply temperature trend rendering model to generate abnormal temperature trend data;

[0140] Step S62: performing abnormal temperature region positioning and segmentation processing on the power supply temperature trend rendering model based on the abnormal temperature trend data to obtain an abnormal temperature region model;

[0141] Step S63: quantifying the overheat power consumption of the abnormal temperature area model using the power consumption performance evaluation data, and generating overheat power consumption data of the abnormal temperature area;

[0142] Step S64: Calculate the performance failure probability of the overheat power consumption data in the abnormal temperature area, thereby obtaining performance failure probability data;

[0143] Step S65: Perform fault test decision analysis on the performance fault probability data to construct a power supply performance fault test model.

[0144] In this embodiment, the temperature trend data is analyzed to identify abnormal temperature trends, such as abnormal temperature rise or fall rates. Based on the abnormal temperature trend, abnormal temperature trend data is generated to record the abnormal location, time and temperature trend characteristics. The abnormal temperature trend data is used to locate and segment the abnormal temperature area of ​​the power supply temperature trend rendering model. According to the abnormal location information recorded in the abnormal temperature trend data, the area at the corresponding position in the temperature trend rendering model is marked as an abnormal temperature area. Through the positioning and segmentation processing, an abnormal temperature area model is obtained for further analysis and processing. The power consumption information of each position in the abnormal temperature area model is obtained using the power supply power consumption performance evaluation data. For each position in the abnormal temperature area model, the corresponding overheating power consumption is calculated, that is, the additional power consumption caused by the temperature exceeding the normal range. The overheating power consumption data of the abnormal temperature area is generated, and the overheating power consumption of each abnormal temperature area position is recorded. According to the overheating power consumption and the performance characteristics of the power supply, the performance failure probability of each abnormal temperature area is inferred. The performance failure probability data is generated to record the performance failure probability of each abnormal temperature area position. Based on the performance failure probability data, a failure decision analysis is performed to determine the countermeasures for different performance failure probabilities. According to the results of fault decision analysis, a power supply performance fault decision model is constructed, including information such as fault levels, early warning strategies, and repair plans for different fault probabilities.

[0145] In this embodiment, a performance testing system for an energy storage power supply is provided, which is used to perform the performance testing method for the energy storage power supply as described above, including:

[0146] The time series temperature module obtains the real-time energy storage power supply status parameters and the energy storage power supply surface temperature image; quantifies the fluctuation trend of the energy storage power supply surface temperature image to obtain the power supply temperature distribution trend data;

[0147] The temperature distribution module performs temperature distribution space mapping processing on the surface temperature image of the energy storage power supply based on the power supply temperature distribution trend data, and constructs a power supply temperature distribution scene diagram;

[0148] The three-dimensional reconstruction module obtains multi-view images of the energy storage power supply; performs three-dimensional reconstruction processing on the multi-view images of the energy storage power supply to construct a three-dimensional structural model of the power supply;

[0149] The power consumption performance module conducts quantitative mining of power consumption performance of real-time energy storage power supply status parameters and generates power consumption performance evaluation data;

[0150] The temperature trend prediction module dynamically renders the power supply three-dimensional structure model according to the power supply temperature distribution scene diagram to build a power supply temperature trend rendering model;

[0151] The fault decision module locates and segments the abnormal temperature area and calculates the performance fault probability of the power supply temperature trend rendering model based on the power supply power consumption performance evaluation data, thereby obtaining the performance fault probability data; and constructs the power supply performance fault decision model based on the performance fault probability data.

[0152] The present invention can obtain the state information and surface temperature distribution of the power supply by acquiring the real-time energy storage power supply state parameters and the surface temperature image of the energy storage power supply, and provide necessary data for subsequent performance testing. By processing the surface temperature image of the energy storage power supply, the time-series change data of the power supply temperature can be obtained, and its fluctuation trend is quantified to obtain the trend data of the power supply temperature distribution, and the temperature change of the power supply can be further understood. By acquiring the multi-view image of the energy storage power supply and performing three-dimensional reconstruction processing, a three-dimensional structural model of the power supply can be constructed, providing the spatial information of the power supply, and providing a basis for subsequent performance testing and analysis. By analyzing the real-time energy storage power supply state parameters, battery capacity decay data and power supply turnover efficiency response data can be generated. Further power consumption performance analysis can be performed on these data to obtain power consumption performance evaluation data of the power supply, and the battery capacity decay and turnover efficiency of the power supply during use can be understood. By analyzing the real-time energy storage power supply state parameters, battery capacity decay data and power supply turnover efficiency response data can be generated. Further power consumption performance analysis can be performed on these data to obtain power consumption performance evaluation data of the power supply, and the battery capacity decay and turnover efficiency of the power supply during use can be understood. By processing the temperature trend model, the abnormal temperature area in the power supply can be located and segmented. Using performance failure probability data, a power supply performance failure decision model can be constructed to help determine and predict power supply performance failure situations.

[0153] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0154] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A performance test method for an energy storage power supply, characterized in that: The following steps are involved: Step S1: Acquire real-time energy storage power supply state parameters and energy storage power supply surface temperature image; Quantify the fluctuation trend of the surface temperature diagram of the energy storage power source to obtain the power source temperature distribution trend data; Step S2: Based on the power supply temperature distribution trend data, the surface temperature image of the energy storage power supply is subjected to temperature distribution space mapping processing to construct a power supply temperature distribution scene diagram; Step S3: Acquire multi-view images of the energy storage power source; Perform three-dimensional reconstruction on multi-view images of energy storage power sources to build a three-dimensional structural model of the power source; Step S4: Quantitatively mine the power consumption performance of the real-time energy storage power supply state parameters to generate power consumption performance evaluation data; the power consumption performance evaluation data includes a power consumption curve and a power consumption index; Step S5: dynamically rendering the power supply three-dimensional structure model according to the power supply temperature distribution scene diagram to construct a power supply temperature trend rendering model; Step S6: Based on the power consumption performance evaluation data, the power temperature trend rendering model is subjected to abnormal temperature area location segmentation processing and performance failure probability calculation, thereby obtaining performance failure probability data; Construct a power supply performance failure decision model based on performance failure probability data; The specific steps of step S5 are: Step S51: performing temperature trend evolution processing on the power supply temperature distribution scene graph to generate temperature trend evolution data; Step S52: performing temperature trend prediction on the power supply temperature distribution scene graph based on the temperature trend evolution data to obtain a temperature trend prediction scene graph; Step S53: Dynamically render the three-dimensional structure model of the power supply according to the temperature trend prediction scene graph to construct a power supply temperature trend rendering model: The dynamic rendering is specifically: according to the changes in temperature data, dynamically render the three-dimensional structure model of the power supply to present the changes in the power supply temperature at different positions, and generate a power supply temperature trend rendering model through dynamic rendering to show the temperature changes and spatial distribution of the power supply over time.

2. The performance testing method of the energy storage power supply according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: performing transient multi-frequency voltage excitation processing on the energy storage power supply to obtain real-time energy storage power supply state parameters, and performing power supply thermal imaging detection to extract the surface temperature image of the energy storage power supply; Step S12: performing temperature difference distribution recognition on the surface temperature image of the energy storage power source to generate surface temperature difference distribution data; Step S13: performing time-series temperature fluctuation analysis on the surface temperature difference distribution data to generate surface time-series temperature change data; Step S14: quantifying the fluctuation trend of the surface temporal temperature variation data to obtain power supply temperature distribution trend data.

3. The performance testing method of the energy storage power supply according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing power supply surface view recognition based on the energy storage power supply surface temperature image to construct a power supply surface coordinate system; Step S22: performing temperature distribution space mapping processing on the power supply surface coordinate system based on the power supply temperature distribution trend data to generate a power supply temperature distribution network; Step S23: performing interpolation smoothing optimization on the power supply temperature distribution network to obtain an optimized power supply temperature distribution network; Step S24: performing discrete voxel decomposition on the optimized power supply temperature distribution network to obtain a plurality of temperature segmentation units; Step S25: performing inter-unit temperature correlation characteristic analysis based on multiple temperature segmentation units to generate unit temperature correlation characteristic data; Step S26: performing global convolution feature activation processing on the optimized power supply temperature distribution network based on the unit temperature associated feature data to construct a power supply temperature distribution scene graph.

4. The performance testing method of the energy storage power supply according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: Acquire multi-view images of the energy storage power source; Step S32: performing image spatial orientation analysis on the multi-view images of the energy storage power source to obtain spatial orientation data of each image; Step S33: performing component node recognition on the multi-view image of the energy storage power source to mark the power source component nodes; Step S34: performing node space layout analysis on power supply component nodes to generate component node space layout data; Step S35: Perform three-dimensional reconstruction processing on the spatial layout data of the component nodes based on the spatial orientation data of each image to construct a three-dimensional structural model of the power supply.

5. The performance testing method of the energy storage power supply according to claim 4, characterized in that: The specific steps of step S35 are: Calculate the spatial pixel coordinates of the power supply component nodes based on the multi-view images of the energy storage power supply to obtain the pixel coordinates of the component nodes; Perform node feature space registration on the power component nodes according to the spatial orientation data of each image to obtain node space matching association data; Based on the node space matching association data, the three-dimensional coordinates of the component node pixel coordinates are reversely calculated to obtain the three-dimensional position coordinates of the component; Based on the three-dimensional position coordinates of the components, point cloud modeling is performed on the spatial layout data of the component nodes to generate a preliminary power supply point cloud model; Identify the point cloud normal distribution of the preliminary power point cloud model and extract the normal feature direction; Based on the normal feature direction, the base surface is accurately divided to obtain multiple point cloud model base surfaces; Based on multiple point cloud model base surfaces, a preliminary power point cloud model is subjected to three-dimensional reconstruction to obtain a power structure model; The morphological surface deviation of the power supply structure model is optimized to construct a three-dimensional structure model of the power supply.

6. The performance testing method of energy storage power supply according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing battery capacity decay analysis on the real-time energy storage power supply state parameters to generate battery capacity decay data; Step S42: performing multi-time point power calculation on the real-time energy storage power supply state parameters, thereby obtaining a power supply time sequence power curve; Step S43: performing a turnover efficiency response analysis on the power supply timing power curve to generate power supply turnover efficiency response data; Step S44: Quantitative mining of power consumption performance is performed on the power turnover efficiency response data and the battery capacity attenuation data to generate power consumption performance evaluation data.

7. The performance testing method of energy storage power supply according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing abnormal temperature trend analysis on the power supply temperature trend rendering model to generate abnormal temperature trend data; Step S62: performing abnormal temperature region positioning and segmentation processing on the power supply temperature trend rendering model based on the abnormal temperature trend data to obtain an abnormal temperature region model; Step S63: quantifying the overheat power consumption of the abnormal temperature area model using the power consumption performance evaluation data, and generating overheat power consumption data of the abnormal temperature area; Step S64: Calculate the performance failure probability of the overheat power consumption data in the abnormal temperature area, thereby obtaining performance failure probability data; Step S65: Perform fault test decision analysis on the performance fault probability data to construct a power supply performance fault test model.

8. A performance test system for an energy storage power supply, characterized in that: The method for performing the performance test of the energy storage power supply according to claim 1 comprises: The time series temperature module obtains the real-time energy storage power supply status parameters and the energy storage power supply surface temperature image; quantifies the fluctuation trend of the energy storage power supply surface temperature image to obtain the power supply temperature distribution trend data; The temperature distribution module performs temperature distribution space mapping processing on the surface temperature image of the energy storage power supply based on the power supply temperature distribution trend data, and constructs a power supply temperature distribution scene diagram; The three-dimensional reconstruction module obtains multi-view images of the energy storage power supply; performs three-dimensional reconstruction processing on the multi-view images of the energy storage power supply to construct a three-dimensional structural model of the power supply; The power consumption performance module conducts quantitative mining of power consumption performance of real-time energy storage power supply status parameters and generates power consumption performance evaluation data; The temperature trend prediction module dynamically renders the power supply three-dimensional structure model according to the power supply temperature distribution scene diagram to build a power supply temperature trend rendering model; The fault decision module locates and segments the abnormal temperature area and calculates the performance fault probability of the power supply temperature trend rendering model based on the power supply power consumption performance evaluation data, thereby obtaining the performance fault probability data; and constructs the power supply performance fault decision model based on the performance fault probability data.

Images