A visualization method, system and storage medium for an energy storage cabinet

Abstract

The present application relates to the technical field of visualization, and particularly relates to a visualization method and system for an energy storage cabinet and a storage medium. The method comprises the following steps: acquiring energy storage cabinet data, collecting image information based on the data, and determining the running visualization state of the energy storage cabinet; analyzing the stability gradient attenuation trend of the energy storage cabinet by using the visualization state data, predicting the abnormal interaction influence state of the energy storage cabinet battery, and evaluating the degradation condition of the battery; estimating the battery health degree, detecting the power supply imbalance condition, and evaluating the dynamic load overload degree of the transmission line; predicting the line loss growth trend of the power transmission line; estimating the heat effect accumulation condition of the energy storage cabinet based on the line loss condition, combining the heat effect and stress abnormal condition to predict the degradation trend of the energy storage cabinet, and realizing the estimation of the service life of the energy storage cabinet. The present application realizes more accurate fault identification of the energy storage cabinet through the visualization optimization of the energy storage cabinet.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of visualization technology, and in particular to a visualization method, system and storage medium for an energy storage cabinet. BACKGROUND

[0002] As a core component in the energy storage system, the energy storage cabinet undertakes the task of storing and releasing electric energy, and plays a crucial role in the stability of the power grid, the efficient use of energy and the safety of equipment. However, a series of structural and electrical faults may occur in the energy storage cabinet during long-term operation. If these faults are not discovered and repaired in time, the efficiency of the energy storage system will decrease, and even the equipment will be damaged or safety hazards will be caused. The traditional monitoring method of the energy storage cabinet relies on manual inspection or simple sensor data monitoring. This method is not only inefficient, but also difficult to discover potential risks in the early stage of failure. With the development of artificial intelligence, big data and image processing technologies, visualization-based monitoring methods have gradually become a new trend. However, the traditional visualization of the energy storage cabinet has the problems of inaccurate analysis of the service life of the energy storage cabinet and inaccurate analysis of the abnormal aging of the energy storage cabinet. SUMMARY

[0003] Therefore, it is necessary to provide a visualization method, system and storage medium for an energy storage cabinet to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, a visualization method for an energy storage cabinet comprises the following steps:

[0005] Step S1: acquiring energy storage cabinet data; collecting energy storage cabinet image data based on the energy storage cabinet data; determining the energy storage cabinet operation visualization state based on the energy storage cabinet image data;

[0006] Step S2: detecting the energy storage cabinet stability gradient attenuation trend according to the energy storage cabinet operation visualization state; predicting the energy storage cabinet battery abnormal interaction influence state according to the energy storage cabinet stability gradient attenuation trend; predicting the energy storage cabinet battery degradation condition according to the energy storage cabinet battery abnormal interaction influence state;

[0007] Step S3: estimating the energy storage cabinet battery health degree according to the energy storage cabinet battery degradation condition; detecting the energy storage cabinet power supply imbalance state according to the energy storage cabinet battery health degree; evaluating the transmission line dynamic load overload degree according to the energy storage cabinet power supply imbalance state; predicting the electric energy transmission line loss growth trend according to the transmission line dynamic load overload degree;

[0008] Step S4: According to the power transmission line loss growth trend and the transmission line dynamic load overload degree, the accumulation of the thermal effect of the energy storage cabinet is estimated; the degradation trend of the energy storage cabinet is predicted based on the accumulation of the thermal effect of the energy storage cabinet; the service life of the energy storage cabinet is estimated based on the degradation trend of the energy storage cabinet, and the service life data of the energy storage cabinet is obtained.

[0009] The present application comprehensively understands the running state of the energy storage cabinet by acquiring the energy storage cabinet data and collecting image data, providing a basis for subsequent visual analysis. The analysis of the image data of the energy storage cabinet can accurately determine the running state of the energy storage cabinet, so that the system can timely discover any abnormal changes. Further detecting the stability gradient attenuation trend of the energy storage cabinet can accurately evaluate whether the structure and battery of the energy storage cabinet are in a safe state, timely predict the abnormal interactive influence state of the battery, and effectively avoid potential safety risks. Through the prediction of the battery degradation condition, the system can comprehensively understand the health condition of the battery, providing a scientific basis for battery management and maintenance. Based on the evaluation of the battery health degree, the problem of power supply imbalance can be timely discovered, so as to timely adjust and optimize the power system of the energy storage cabinet, avoiding power waste or safety hazards caused by imbalance. According to the prediction of the dynamic load overload degree of the transmission line and the power transmission line loss, the system can identify the transmission problem in advance, avoid further aggravation of energy loss, and optimize the energy management of the energy storage cabinet. By analyzing the thermal effect accumulation and degradation trend of the energy storage cabinet, the system can accurately evaluate the performance degradation of the energy storage cabinet and predict the actual service life of the energy storage cabinet through life estimation. Therefore, the present application optimizes the traditional visualization for the energy storage cabinet, solves the problems of inaccurate analysis of the service life of the energy storage cabinet and inaccurate analysis of the abnormal aging of the energy storage cabinet in the traditional visualization method for the energy storage cabinet, and improves the accuracy of the analysis of the service life of the energy storage cabinet and the accuracy of the abnormal aging analysis of the energy storage cabinet.

[0010] The present application also provides a visualization system for an energy storage cabinet for executing the visualization method for the energy storage cabinet as described above, which comprises:

[0011] A visualization state determination module for acquiring energy storage cabinet data; collecting energy storage cabinet image data based on the energy storage cabinet data; determining the running visualization state of the energy storage cabinet based on the energy storage cabinet image data;

[0012] A battery degradation prediction module for detecting the stability gradient attenuation trend of the energy storage cabinet according to the running visualization state of the energy storage cabinet; predicting the abnormal interactive influence state of the battery of the energy storage cabinet according to the stability gradient attenuation trend of the energy storage cabinet; and predicting the degradation condition of the battery of the energy storage cabinet according to the abnormal interactive influence state of the battery of the energy storage cabinet;

[0013] The line loss growth trend prediction module is configured to estimate the state of health of the energy storage cabinet battery according to the energy storage cabinet battery degradation condition, detect the energy storage cabinet power supply imbalance state according to the state of health of the energy storage cabinet battery, estimate the dynamic load overload degree of the transmission line according to the energy storage cabinet power supply imbalance state, and predict the line loss growth trend of the power transmission line according to the dynamic load overload degree of the transmission line.

[0014] The energy storage cabinet service life estimation module is configured to estimate the thermal effect accumulation condition of the energy storage cabinet according to the line loss growth trend of the power transmission line and the dynamic load overload degree of the transmission line, predict the degradation trend of the energy storage cabinet based on the thermal effect accumulation condition of the energy storage cabinet, and estimate the service life of the energy storage cabinet based on the degradation trend of the energy storage cabinet to obtain the service life data of the energy storage cabinet.

[0015] A computer readable storage medium storing a computer program, wherein the computer program is configured to execute the visualization method for the energy storage cabinet. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 A step flowchart for a visualization method for an energy storage cabinet;

[0017] Figure 2 A detailed implementation step flowchart for step S3 in the method; Figure 1 A detailed implementation step flowchart for step S3 in the method;

[0018] Figure 3 A detailed implementation step flowchart for step S4 in the method; Figure 1 A detailed implementation step flowchart for step S4 in the method;

[0019] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0020] The technical method of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0021] In addition, the accompanying drawings are only schematic illustrations of the present application, and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated description thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0022] It should be understood that, although the terms "first", "second" or the like can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the example embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0023] To achieve the above object, please refer to Figures 1 to 3 A visualization method for an energy storage cabinet, comprising the following steps:

[0024] Step S1: acquiring energy storage cabinet data; collecting energy storage cabinet image data based on the energy storage cabinet data; determining the energy storage cabinet operation visualization state based on the energy storage cabinet image data;

[0025] In the embodiments of the present application, a variety of sensor devices built-in the energy storage cabinet are used to obtain the operation data of the energy storage cabinet, including temperature, humidity, current, voltage, load and other key parameters. The collection and real-time monitoring of these data are closely related. The data collection process involves the deployment of sensors, which are configured at different positions of the energy storage cabinet to comprehensively monitor the operation of the energy storage cabinet. The temperature sensor is mainly used to record the temperature changes inside and outside the energy storage cabinet in real time, the humidity sensor is used to detect the humidity state inside the energy storage cabinet, the current sensor and the voltage sensor monitor the current flow and voltage fluctuation of the energy storage cabinet respectively, and the load sensor monitors the load condition of the energy storage cabinet. These data are connected with the data acquisition module through the monitoring system of the energy storage cabinet and transmitted to the central processing platform. The central platform receives these information in real time through the data acquisition system and preliminarily evaluates the operation state of the energy storage cabinet. Specifically, these data not only include conventional parameters such as temperature, humidity, current and voltage, but also cover the mechanical structure of the energy storage cabinet, the temperature distribution of electronic components, and the health status of the battery pack, ensuring that the operation health condition of the energy storage cabinet can be fully understood. In addition, the image acquisition system is used to capture the appearance and heat distribution of the energy storage cabinet to further enhance the monitoring of the operation state of the energy storage cabinet. The visible light camera and the infrared imager configured outside the energy storage cabinet undertake the image acquisition task respectively. The visible light camera is set to 1920x1080 pixels and 30FPS for capturing the overall appearance image outside the energy storage cabinet, which can help subsequent analysis of the physical characteristics of the surface of the energy storage cabinet. The infrared imager is used to capture the temperature information of the energy storage cabinet, with the temperature measurement range of-20℃ to 300℃, the minimum temperature resolution of 0.05℃, and the image frame rate of 25Hz, which can accurately detect the heat distribution on the surface and inside of the energy storage cabinet, especially the high-precision capture of hot spot areas. The acquired visible light image and infrared imaging data will be transmitted to the specially designed image processing system as input information. The image processing system processes and analyzes these image data through image recognition algorithms, automatically detects and labels the visual state outside and inside the energy storage cabinet. The image recognition technology can identify whether there are abnormalities or potential problems in the energy storage cabinet by analyzing the surface features, temperature hot spots and important markers in the image. At the same time of image processing, the system also fuses the real-time data from the sensors, applies data fusion technology to combine image information with sensor data, and performs in-depth analysis on the overall state of the energy storage cabinet to form the operation visualization state of the energy storage cabinet.

[0026] Step S2: detecting the stability gradient attenuation trend of the energy storage cabinet according to the energy storage cabinet operation visualization state; predicting the energy storage cabinet battery abnormal interaction influence state according to the stability gradient attenuation trend of the energy storage cabinet; predicting the energy storage cabinet battery degradation condition according to the energy storage cabinet battery abnormal interaction influence state;

[0027] In the embodiment of the present application, based on the operation visual state information of the energy storage cabinet obtained in step S1, the system uses multiple analysis techniques to evaluate the stability gradient attenuation trend of the energy storage cabinet through thermal imaging images and mechanical state data. In specific operation, the system obtains the thermal imaging image of the energy storage cabinet, analyzes the temperature change of each part of the surface of the energy storage cabinet using thermal imaging technology, and further judges the structural stability of the energy storage cabinet in combination with the mechanical state information of the energy storage cabinet. The system uses a set of algorithms based on physical models to calculate the stress and deformation of the energy storage cabinet under different operating conditions by monitoring the overall structural deformation of the energy storage cabinet, and identifies risk points. For example, by analyzing the deformation of the energy storage cabinet during the load change process, the system can find that the deformation of some parts of the energy storage cabinet exceeds the normal range, prompting that these parts will have structural problems in the future. At the same time, the system also analyzes the heat accumulation in different regions in combination with the hot spot distribution data of the energy storage cabinet, so as to infer the stability change trend of the energy storage cabinet. If the temperature of some regions abnormally rises, the system will warn that the structural degradation or uneven load caused by thermal effects will further accelerate the stability attenuation of the energy storage cabinet. On this basis, the system continues to analyze the state of the battery pack in combination with the thermal characteristic data of the battery pack of the energy storage cabinet for further evaluation. Specifically, the system obtains real-time data of the surface temperature of the battery in combination with multiple parameters such as the temperature, voltage and current inside the battery, analyzes the interaction between the batteries inside the energy storage cabinet and its potential impact. For example, if the temperature of some batteries abnormally rises, the system can analyze whether the battery is in an overheated state, and in combination with the state of the surrounding batteries, judge whether there is mutual influence between the batteries, such as the heat conduction effect between the batteries causing the temperature of the adjacent batteries to rise, thereby causing short circuit, increased internal resistance and other faults. Through the analysis of these multi-dimensional data, the system can accurately infer the abnormal interaction state of the batteries inside the energy storage cabinet. Specifically, when it is detected that the temperature of some batteries exceeds the set safety threshold, in combination with the voltage and current fluctuation of the battery, the system can predict whether these batteries will enter an excessive degradation stage, and further infer the degradation trend of the overall battery of the energy storage cabinet based on the changes of the temperature and internal resistance. In particular, the degradation trend of the battery includes not only the loss of battery capacity, but also the increase of battery internal resistance and other factors. Through these data, the system can accurately predict the battery degradation degree of the energy storage cabinet.

[0028] Step S3: estimating the battery health degree of the energy storage cabinet according to the battery degradation condition of the energy storage cabinet; detecting the power supply imbalance state of the energy storage cabinet according to the battery health degree of the energy storage cabinet; evaluating the dynamic load overload degree of the transmission line according to the power supply imbalance state of the energy storage cabinet; predicting the loss growth trend of the power transmission line according to the dynamic load overload degree of the transmission line;

[0029] In the embodiment of the present application, according to the energy storage cabinet battery degradation data obtained in step S2, the system calculates the health degree of the energy storage cabinet battery. In this calculation process, the system comprehensively considers multiple key factors of the battery, including the actual capacity of the battery, the number of charge and discharge, the internal resistance, the working temperature, etc., and uses a special health degree evaluation algorithm to complete this evaluation. This algorithm is usually based on a battery life model, by analyzing the aging characteristics of the battery under different working conditions, combined with the actual use, to obtain a specific battery health degree index, usually expressed in the form of percentage. For example, if the capacity of the battery decreases to less than 80% of the original capacity, the internal resistance increases to twice the normal value, and the number of charge and discharge is far beyond the design value, the system will give a lower health degree evaluation result. Through this health degree evaluation, the system can fully understand the current condition of the battery and timely find potential problems. Next, the system further analyzes the power supply state of the energy storage cabinet based on the battery health degree data. If the battery health degree of the energy storage cabinet is low, it means that the battery cannot effectively support the work of the energy storage cabinet under high load state, which will lead to the occurrence of power supply imbalance. At this time, the system detects whether there is a power supply imbalance in the energy storage cabinet by real-time monitoring of the current, output voltage and load distribution of the energy storage cabinet battery. The system will judge whether the battery cannot provide enough power to support the load demand of the energy storage cabinet, whether there are problems such as unstable battery voltage, and affect the stable operation of the energy storage cabinet. If the power supply is imbalanced, the system will immediately trigger an alarm and provide relevant maintenance suggestions. Next, the system further evaluates the dynamic load overload degree of the power transmission line according to the power supply imbalance. For this purpose, the system real-time monitors the current and voltage fluctuation of the power transmission line, and uses load flow analysis technology to real-time calculate the load state of the power transmission line. In this way, the system can real-time evaluate the load level of the line and judge whether there is a risk of overload. If the current and voltage of the power transmission line are monitored to exceed the safe range, the system will further analyze the load to evaluate whether there is a phenomenon of line overload. Especially in the case of low battery health degree or high load, the system can accurately predict whether the load of the power transmission line will continue to increase, thereby causing the line loss to increase. The system can predict the future growth of line loss by analyzing the trend of current and temperature change. Specifically, in the case of continuous load increase, the resistance of the power transmission line will cause the energy loss to gradually rise, and the system can predict the future development of line loss according to the current load flow data combined with the temperature change trend of the line.

[0030] Step S4: According to the growth trend of the power transmission line loss and the dynamic load overload degree of the transmission line, the accumulation of the thermal effect of the energy storage cabinet is estimated; the degradation trend of the energy storage cabinet is predicted based on the accumulation of the thermal effect of the energy storage cabinet; the service life of the energy storage cabinet is estimated based on the degradation trend of the energy storage cabinet, and the service life data of the energy storage cabinet is obtained.

[0031] In the embodiments of the present application, based on the transmission line loss increase data and the load overload condition obtained in step S3, the system further evaluates the heat effect accumulation condition of the energy storage cabinet, and uses current, voltage and temperature data inside the energy storage cabinet to simulate and calculate the heat distribution of each component of the energy storage cabinet through a thermal analysis algorithm. The heat generated by the flow of current and the power consumption of the battery pack and elements inside the energy storage cabinet directly affect the temperature change of the energy storage cabinet. The system monitors the temperature of each component inside the energy storage cabinet in real time, especially the temperature of the battery, transmission line and power conversion equipment, to determine whether there is an overheating phenomenon. If the temperature of some components abnormally rises, it indicates that these components are subjected to a large thermal stress, exceeding the normal working range, thereby accelerating the aging process of the components. Based on this, the system calculates the speed of heat effect accumulation and identifies which components are damaged or performance degraded due to long-term overheating. Specifically, when the system detects that the surface temperature of the battery pack continuously exceeds the safety threshold, a local hot spot appears in a certain part of the energy storage cabinet, the system analyzes the impact of the accumulation of these heat on the structure of the energy storage cabinet, especially the negative impact on the chemical reaction process of the battery. As the temperature rises, the chemical reaction inside the battery will accelerate, leading to rapid capacity decay of the battery and causing battery safety problems. Then, the system analyzes the aging process of each part of the energy storage cabinet using a comprehensive degradation model. This degradation model takes into account temperature changes, mechanical stress, material aging, and battery degradation, etc. By monitoring the stress and thermal load of each component of the energy storage cabinet under different working environments for a long time, the system identifies the key components that fail. For example, the heat effect of the battery can cause the evaporation of the electrolyte inside the battery or the deterioration of the electrode material, and long-term overheating can cause damage to the internal battery cells. Based on this degradation trend, the system further determines which components are most likely to fail prematurely and gives the remaining service life of these components. In addition, the system also considers the performance change of the energy storage cabinet after a long time of use in combination with the degradation trend of the overall structure of the energy storage cabinet, and estimates the overall remaining service life of the energy storage cabinet using a life prediction model. The life prediction model calculates the expected remaining service life of the energy storage cabinet based on the usage, aging speed, and heat effect of each component inside the energy storage cabinet.

[0032] Preferably, step S1 comprises the following steps:

[0033] Step S11: set the resolution of the visible light camera to 1920x1080 pixels, the minimum light sensitivity to 0.01 lux, and the frame rate to 30 FPS;

[0034] In the embodiment of the present application, when setting the visible light camera, the resolution of the camera is determined to be 1920*1080 pixels to ensure that the collected image has sufficient clarity and can provide detailed features of the external surface of the energy storage cabinet. The minimum light sensitivity of the visible light camera is set to 0.01 lux to ensure that the changes on the surface of the energy storage cabinet can be clearly captured even in low light environments, ensuring the accuracy and integrity of the data. In actual application, the frame rate is set to 30FPS to ensure the smoothness of image acquisition, especially when monitoring the external of the energy storage cabinet dynamically, it can smoothly capture the details of rapid movement or change. The visible light camera transmits the collected image data to the central processing system through wired or wireless mode, and the system uses these image data to further analyze the external visualization state of the energy storage cabinet.

[0035] Step S12: setting the temperature measurement range of the infrared imager to-20℃ to 300℃, the minimum temperature resolution to 0.05℃, and the image frame rate to 25Hz;

[0036] In the embodiment of the present application, the configuration parameters of the infrared imager are set to a temperature measurement range from-20℃ to 300℃, ensuring that it can cover the working state of the energy storage cabinet at extremely low to extremely high temperatures, especially for monitoring the internal environment of the energy storage cabinet with large temperature fluctuations. The minimum temperature resolution is 0.05℃, which ensures that the infrared imager can accurately capture the temperature changes in the internal environment of the energy storage cabinet, especially the small temperature differences in the hot spot area. The image frame rate is set to 25Hz, so that the infrared imager can track the changes of the internal temperature of the energy storage cabinet in real time, and match these data with the image data collected by the visible light camera, to ensure the synchronous update of the temperature distribution information and the visualization information. In actual application, the infrared imager sends real-time temperature data to the central processing platform through a dedicated data transmission protocol, providing accurate basis for subsequent thermal effect analysis.

[0037] Step S13: acquiring energy storage cabinet data;

[0038] In the process of acquiring the energy storage cabinet data, a variety of sensor devices built-in the energy storage cabinet are used for data acquisition in the embodiment of the present application. These sensors can record the running state of the internal and external environment of the energy storage cabinet in real time, including temperature sensors, humidity sensors, current sensors, voltage sensors, load sensors, etc. All sensor data are transmitted to the data acquisition module through the monitoring system of the energy storage cabinet, and the module transmits the data to the central processing platform in wired or wireless mode. On the platform, these data are uniformly received and preliminarily processed and stored. The data content includes the environmental temperature, humidity, load current, voltage change and other information of the energy storage cabinet.

[0039] Step S14: using the visible light camera to collect energy storage cabinet image data;

[0040] In the embodiment of the present application, when the visible light camera is used to collect the data of the energy storage cabinet and the image data of the energy storage cabinet, the visible light camera is started and set to 1920*1080 pixel resolution to ensure high image definition. The camera captures the image outside the energy storage cabinet at a frame rate of 30 FPS per second. These images include the surface, structural features, wiring conditions and other key parts of the energy storage cabinet. The camera uploads the image data to the central processing system through the configured transmission interface. During the image collection process, the system will monitor the image quality in real time to ensure that there is no overexposure, blur or data loss during the collection process, and ensure that the quality of each frame of image meets the analysis standard.

[0041] Step S15: determining the running visual state of the energy storage cabinet by using the infrared imager and the image data of the energy storage cabinet.

[0042] In the embodiment of the present application, after obtaining the data of the visible light camera and the infrared imager, the system will analyze the running state of the energy storage cabinet by using the image processing algorithm. The system analyzes the images collected by the visible light camera to identify the surface features outside the energy storage cabinet, including the deformation of the mechanical structure, surface damage, etc. At the same time, the temperature distribution image provided by the infrared imager is used to analyze the heat distribution inside and outside the energy storage cabinet. Through the thermal imaging image, it is detected whether the energy storage cabinet has overheating phenomenon, especially the temperature change of the hot spot area. After the combination of the two data, by using the data fusion technology, the system can comprehensively evaluate the running visual state of the energy storage cabinet, identify the potential fault risk or abnormal behavior of the energy storage cabinet, and form the complete visual running state of the energy storage cabinet.

[0043] Preferably, step S15 comprises the following steps:

[0044] Step S151: performing energy storage cabinet image preprocessing on the energy storage cabinet image data to obtain energy storage cabinet image preprocessing data;

[0045] In the embodiment of the present application, the energy storage cabinet image data is preprocessed. The energy storage cabinet image data is collected by the visible light camera and the infrared imager and transmitted to the data processing system through the image transmission module. The image preprocessing includes denoising processing, brightness adjustment, contrast enhancement and edge detection operations. The denoising processing uses Gaussian blur or median filter algorithm to remove noise points in the image through smoothing processing to ensure image definition. Brightness adjustment is used to eliminate the phenomenon of uneven image brightness caused by light changes. Contrast enhancement helps to highlight the detailed features of the surface of the energy storage cabinet, making the subsequent image analysis more accurate. Finally, the structural edges in the image are extracted through edge detection (such as Canny operator) to clearly show the geometric structure outside and inside the energy storage cabinet. After these preprocessing, the obtained energy storage cabinet image preprocessing data provides clear and less noisy image input for subsequent three-dimensional point cloud feature extraction and surface feature analysis.

[0046] Step S152: Collecting three-dimensional point cloud features of the energy storage cabinet image according to the energy storage cabinet image preprocessing data;

[0047] In the embodiment of the present application, three-dimensional point cloud features of the energy storage cabinet image are collected according to the energy storage cabinet image preprocessing data. After image preprocessing, three-dimensional spatial information of the energy storage cabinet is extracted through computer vision algorithms combined with three-dimensional imaging technologies such as binocular stereo vision or LiDAR. The image data taken by two visible light cameras at different angles is used to calculate the distance between each point on the object surface by using the parallax method, thereby generating three-dimensional point cloud data of the energy storage cabinet image. Each point in the point cloud data represents a small area on the surface of the energy storage cabinet, and its coordinates contain information of three dimensions X, Y and Z. The collection of three-dimensional point cloud features is realized through high-precision visual calculation, which ensures accurate description of the spatial form of the external and internal structure of the energy storage cabinet. The obtained three-dimensional point cloud data provides detailed geometric information for subsequent surface feature extraction and structure analysis.

[0048] Step S153: Extracting surface features of the energy storage cabinet image according to the three-dimensional point cloud features of the energy storage cabinet image;

[0049] In the embodiment of the present application, surface features of the energy storage cabinet image are extracted according to the three-dimensional point cloud features of the energy storage cabinet image. In the extraction process, the spatial information in the point cloud data is used to model the surface of the energy storage cabinet by using three-dimensional reconstruction technology, and the point cloud data is processed by using surface normal estimation algorithm to calculate the normal direction of each point on the surface of the energy storage cabinet, and then determine the local form and structure of the surface. Then, the point cloud is segmented by using region growing algorithm and other technologies, and different parts of the surface of the energy storage cabinet are labeled and classified to analyze the features of different regions. Next, the surface model is optimized by using surface smoothing algorithm to remove noise points, making the geometric features of the surface of the energy storage cabinet more smooth and accurate. In this way, the external surface features of the energy storage cabinet are extracted from the three-dimensional point cloud, including structural damage, deformation or any abnormal changes.

[0050] Step S154: Detecting the structure condition of the energy storage cabinet based on the surface features of the energy storage cabinet image;

[0051] In the embodiments of the present application, the surface features of the energy storage cabinet are detected based on the energy storage cabinet image to detect the structural condition of the energy storage cabinet. After the surface features are extracted, the system analyzes the structural condition according to the surface geometric data of the energy storage cabinet. Specifically, whether the structure of the energy storage cabinet is stable is judged by detecting whether there is obvious deformation, crack, damage or irregular area on the surface of the energy storage cabinet. Shape matching and geometric deformation detection algorithm is used to detect the surface deformation of the energy storage cabinet. For example, the deviation of the surface features of the energy storage cabinet from the standard model is compared using the template matching based method, and the deformation degree of each part is calculated. If cracks or deformations are found on the surface of the energy storage cabinet, the system will automatically label and calculate the damage degree. Based on this information, the system further analyzes whether the structure of the energy storage cabinet is in a normal state to ensure that it can operate stably. If abnormalities are found, the system will give an alarm prompt through the analysis result to help maintenance personnel to further check and repair.

[0052] Step S155: Collecting the hot spot distribution of the energy storage cabinet by using an infrared imager;

[0053] In the embodiments of the present application, the hot spot distribution of the energy storage cabinet is collected by using an infrared imager. The task of the infrared imager in this process is to collect the temperature distribution data of the inside and surface of the energy storage cabinet in real time. The temperature measurement range of the infrared imager is from -20℃ to 300℃, and the minimum temperature resolution is 0.05℃, which can detect the hot spot area of the energy storage cabinet with high precision. Through infrared thermal imaging, the system accurately locates the hot spots on the surface and inside of the energy storage cabinet caused by overload, damage or battery abnormalities. These hot spots are caused by problems such as overheating of the batteries inside the energy storage cabinet, poor contact or excessive current. The collected temperature data is processed by thermal imaging algorithm to generate a thermal distribution map of the hot spots of the energy storage cabinet, showing the temperature change of different areas. The infrared imaging data will be combined with the data of the sensors of the energy storage cabinet to provide strong support for subsequent thermal effect analysis.

[0054] Step S156: Calculating the hot spot distribution balance of the energy storage cabinet according to the hot spot distribution of the energy storage cabinet;

[0055] In the embodiments of the present application, the hot spot distribution balance of the energy storage cabinet is calculated according to the hot spot distribution of the energy storage cabinet. According to the hot spot distribution data of the energy storage cabinet collected from the infrared imager, the system analyzes the uniformity of the temperature distribution. Specifically, the system evaluates the balance of the temperature distribution by calculating the temperature difference of different areas of the energy storage cabinet. If the temperature of a certain area is significantly higher than that of the area, it indicates that there is an abnormal overheating phenomenon in this area, which is caused by damage to the internal components of the energy storage cabinet or unbalanced load. When calculating the balance, the system also considers the load distribution of the energy storage cabinet and the changes of the operating environment, and analyzes the deviation degree of the temperature distribution by using statistical methods.

[0056] Step S157: Determine the energy storage cabinet operation visualization state according to the energy storage cabinet hotspot distribution balance and the energy storage cabinet structure condition.

[0057] In the embodiment of the present application, the energy storage cabinet operation visualization state is determined according to the energy storage cabinet hotspot distribution balance and the energy storage cabinet structure condition. The system combines the structure condition analysis result of the energy storage cabinet with the balance of the hotspot distribution to comprehensively evaluate the operation state of the energy storage cabinet. If the structure of the energy storage cabinet is severely deformed or damaged, and the hotspot distribution is uneven, the system determines that the operation state of the energy storage cabinet is abnormal, and marks it as a high-risk state. If the structure of the energy storage cabinet is stable and the hotspot distribution is balanced, the energy storage cabinet is in a normal operation state. This process uses decision tree, fuzzy logic or multi-dimensional data fusion technology to comprehensively analyze different data sources to obtain the overall visualization state of the energy storage cabinet.

[0058] Preferably, the energy storage cabinet stability gradient attenuation trend detection in step S2 comprises:

[0059] According to the energy storage cabinet operation visualization state, the structure defect condition of the energy storage cabinet is collected;

[0060] In the embodiment of the present application, the operation visualization state of the energy storage cabinet is obtained through a plurality of sensors, covering the temperature, humidity, current, voltage, load and other data of the energy storage cabinet, and at the same time, image data collected by a visible light camera and an infrared imager. After image preprocessing, three-dimensional point cloud feature extraction and surface feature analysis, the structure information of the energy storage cabinet is obtained, including the surface shape, cracks, deformation and defect areas. Based on these image data, the system detects the defects of the external and internal structure of the energy storage cabinet through computer vision algorithms. Through template matching, deformation detection and geometric feature analysis, the cracks, depressions, excessive wear and other defects on the surface and inside the structure of the energy storage cabinet are automatically identified. The defect information is marked in the form of coordinate points, size and shape, etc., to constitute the structure defect condition data of the energy storage cabinet.

[0061] The structure deformation degree of the energy storage cabinet is identified by using the structure defect condition of the energy storage cabinet;

[0062] In the embodiment of the present application, once the structure defect data of the energy storage cabinet is obtained, the system further analyzes the deformation degree of the energy storage cabinet. By comparing the geometric data of the external and internal structure of the energy storage cabinet, the deformation of the energy storage cabinet in the running process is detected. The deformation degree is quantified by calculating the displacement of each component and the change of the overall geometric shape. The commonly used method includes calculating the percentage of deformation by comparing the geometric difference between the initial model and the current model of the energy storage cabinet. If the deformation degree of the energy storage cabinet exceeds 0.5%, the system will mark it as abnormal and enter the next detection process. This calculation is realized by solving the elastic deformation equation of the object and combining the sensor data. The deformation degree of the energy storage cabinet structure is evaluated to determine whether it will affect the overall stability of the energy storage cabinet.

[0063] When the structural deformation degree of the energy storage cabinet exceeds 0.5%, and the local mechanical stress of the energy storage cabinet is calculated based on the structural defect condition of the energy storage cabinet;

[0064] In the embodiment of the present application, when the structural deformation degree of the energy storage cabinet exceeds 0.5%, the system will further analyze the change of the local mechanical stress of the energy storage cabinet in combination with the structural defect condition of the energy storage cabinet. The system performs mechanical simulation on each component of the energy storage cabinet based on finite element analysis (FEA). By inputting the current deformation degree and structural defect information of the energy storage cabinet, the system calculates the stress distribution of each region of the energy storage cabinet. In the local deformation region, the system will pay special attention to the abnormal growth trend of the mechanical stress, for example, whether the stress of some regions exceeds the normal value or there is a local stress concentration phenomenon. This process calculates by solving the stress-strain relationship and combining with external load data, which can identify whether there is a stress concentration area that leads to damage in the energy storage cabinet. If the local mechanical stress shows an abnormal growth trend, the system will mark these areas and prompt potential failure.

[0065] When the local mechanical stress growth trend exceeds 50MPa, and the surface crack degree of the energy storage cabinet is detected based on the structural deformation degree of the energy storage cabinet;

[0066] In the embodiment of the present application, when the local mechanical stress growth trend exceeds 50MPa, the system will further detect the surface crack of the energy storage cabinet under this high stress condition. The system collects thermal image data of the surface of the energy storage cabinet through an infrared imager. The infrared imager can accurately capture the temperature change caused by the crack. The crack usually causes uneven heat distribution on the surface of the energy storage cabinet. In the thermal imaging image, the temperature at the location of the crack will abnormally rise or fall, showing a clear temperature change area. The thermal image data is input into the image processing system, which preliminarily locates the position and distribution of the surface crack of the energy storage cabinet by analyzing the position and size of the temperature abnormal area. At the same time, the system also uses high-resolution visible light images to further analyze the surface of the energy storage cabinet. The visible light image accurately identifies the existence and morphological characteristics of the crack through advanced image processing algorithms (such as edge detection, shape analysis, etc.). By extracting the edge information of the crack, the system can accurately measure the length, width and depth of the crack. Combined with the mechanical stress data, the system evaluates the severity of the crack by comprehensively analyzing the geometric parameters of the crack and the local stress concentration. If the length of the crack exceeds 2cm, the system will judge the further damage degree caused by the crack according to the size of the crack and the local stress condition, and further predict its impact on the overall stability of the energy storage cabinet. If the crack threatens the stability of the energy storage cabinet structure, the system will issue an alarm to prompt that there is a high risk of damage in this area, which may lead to major failure or failure of the energy storage cabinet structure, thereby affecting the safe operation of the energy storage cabinet.

[0067] When the surface crack of the energy storage cabinet exceeds 2 cm, the damage of the support structure of the energy storage cabinet is evaluated based on the growth trend of the local mechanical stress of the energy storage cabinet;

[0068] In the embodiment of the present application, when the surface crack of the energy storage cabinet exceeds 2 cm, the system further evaluates the damage of the support structure of the energy storage cabinet through various analysis methods. The system monitors the expansion of the crack, combines the position and shape of the surface crack of the energy storage cabinet, and establishes a crack expansion model. This model is based on the classical mechanics theory of crack expansion, especially the relationship between stress intensity factor (K) and crack expansion rate, to analyze the expansion trend of the crack under different loads. The position of the crack is directly related to the mechanical stress distribution inside the energy storage cabinet. The system combines the local stress data of the energy storage cabinet to predict the potential path of crack expansion. On this basis, the system uses finite element analysis (FEA) for numerical simulation to calculate the influence of crack expansion on the support structure of the energy storage cabinet. Through the simulation, the system can identify whether the crack will expand to the key areas of the support structure, especially the parts of the structure that bear more stress, such as the connection points, support columns and load-bearing frames, etc. If the crack expands to these areas, the system will evaluate its impact on the strength of the support structure, use the mechanical properties and geometric characteristics of the material to judge whether the carrying capacity of the support structure has been threatened. At this time, the system further analyzes the changes in the overall mechanical response of the support structure caused by the crack through the established structural mechanics model, calculates the influence of the local stress concentration caused by the crack on the support structure, and then predicts whether it will lead to the failure or serious damage of the support structure. If the simulation results show that the stress concentration caused by the crack expansion leads to the failure of the support structure.

[0069] The stability gradient decay trend of the energy storage cabinet is detected based on the damage of the support structure of the energy storage cabinet.

[0070] In the embodiments of the present application, based on the damage condition of the energy storage cabinet support structure, the stability gradient attenuation trend of the energy storage cabinet is detected, and the state of the energy storage cabinet support structure needs to be analyzed in detail. The system monitors the operation of each key component of the energy storage cabinet in real time through various sensors, image acquisition devices and stress analysis models. When the support structure is damaged, the system will analyze the type, degree and impact of the damage in depth. For example, if a part of the support structure cracks, deforms locally or material fatigue occurs, the system will simulate the mechanics of the component through finite element analysis (FEA) to evaluate the impact of the damage on the overall stability. Specifically, by analyzing the stress concentration of the damaged area of the support structure, it can be determined whether the damage will lead to local failure or further expand to the component. The stress concentration area detection uses the stress-strain curve and the material mechanics characteristics to accurately calculate the stress distribution of the energy storage cabinet under certain load, find the weak points, and predict the damage caused by these weak points under continuous working load. At the same time, the deformation data of the energy storage cabinet components are also acquired in real time and compared with the damage condition of the support structure. In this way, it is determined whether the energy storage cabinet will locally stress concentrate to cause component deformation or damage, thereby affecting the overall stability. When it is found that the damage of the support structure has reached a certain degree, or the component has been damaged due to excessive stress, the system will automatically calculate the attenuation trend of the overall stability of the energy storage cabinet. By comparing the stress, deformation and damage data of each part of the energy storage cabinet, the system can predict the strength attenuation degree of the overall structure. If the calculation result shows that the damage of the support structure leads to rapid decline of the overall stability of the energy storage cabinet, the system will issue a warning signal to indicate that the energy storage cabinet is in a dangerous state.

[0071] Preferably, the energy storage cabinet battery abnormal interaction state prediction in step S2 comprises:

[0072] According to the energy storage cabinet stability gradient attenuation trend, the energy storage cabinet structure tilt probability is calculated.

[0073] In the embodiments of the present application, the energy storage cabinet structure tilt probability is calculated according to the energy storage cabinet stability gradient attenuation trend. The energy storage cabinet stability gradient attenuation trend data is obtained by real-time monitoring of various mechanical and structural parameters of the energy storage cabinet. These data include the deformation, stress distribution and external environmental factors of the energy storage cabinet. By inputting these data into the stability analysis algorithm, the system calculates the probability of structural tilt of the energy storage cabinet occurring during operation. Specifically, the system uses the mechanical model and stability theory to calculate the tilt of the energy storage cabinet through the distribution of internal stress and the change of external load, and outputs a tilt probability value.

[0074] Based on the energy storage cabinet structure tilt probability, the displacement degree of the internal elements of the energy storage cabinet is estimated.

[0075] In the embodiments of the present application, based on the structural tilt probability of the energy storage cabinet, the system further estimates the displacement degree of the internal elements of the energy storage cabinet. The internal elements of the energy storage cabinet, including battery packs, lines and structural elements, are displaced due to the influence of the structural tilt of the energy storage cabinet. The system uses the structural model of the energy storage cabinet and the displacement calculation formula to calculate the displacement range of each internal element according to the tilt probability. In the specific calculation, the tilt direction, angle, and the weight and relative position of the internal elements in the energy storage cabinet are considered. Through this process, the displacement degree of the internal elements of the energy storage cabinet under the condition of structural tilt is estimated.

[0076] The internal battery misplacement trend of the energy storage cabinet is predicted by using the displacement degree of the internal elements of the energy storage cabinet and the structural tilt probability of the energy storage cabinet.

[0077] In the embodiments of the present application, based on the displacement degree of the elements and the structural tilt probability, the system predicts the misplacement trend of the internal batteries of the energy storage cabinet. Battery misplacement can cause short circuit, poor contact or even damage between batteries. By predicting this trend, combining the installation position of the battery in the energy storage cabinet, the tilt angle and its physical characteristics (such as the weight, size and support method of the battery pack), the probability of battery misplacement is calculated. This prediction considers the relationship between the displacement amount of the battery caused by the structural tilt and the relative position change between the batteries, and further predicts the risk of battery misplacement.

[0078] The internal structural compression condition of the energy storage cabinet is calculated by using the internal battery misplacement trend of the energy storage cabinet and the displacement degree of the internal elements of the energy storage cabinet.

[0079] In the embodiments of the present application, according to the battery misplacement trend and the displacement degree of the elements, the structural compression condition inside the energy storage cabinet is calculated. When the battery is misplaced, mechanical compression occurs between the battery and the surrounding elements or between the batteries, thereby aggravating the damage of the battery or affecting the normal work of the battery. The system calculates the distance, contact point and pressure distribution between the battery and the elements to obtain the structural compression state inside the energy storage cabinet. This process involves complex mechanical models, especially the analysis of contact mechanics and compressive stress, to ensure accurate assessment of the stress state inside the energy storage cabinet.

[0080] The battery swelling trend of the energy storage cabinet is estimated according to the internal structural compression condition of the energy storage cabinet.

[0081] In the embodiments of the present application, after evaluating the compression status inside the energy storage cabinet, the system predicts the trend of battery swelling by combining various sensor data and mechanical analysis, as well as the temperature, charging and discharging data of the battery, and the degree of mechanical compression. Battery swelling is usually caused by multiple factors, among which the most common cause is abnormal internal chemical reaction, especially in the case of overcharging or over-discharging, the chemical substances in the battery react unbalancedly, generating gas or causing volume expansion. The mechanical compression state inside the energy storage cabinet further aggravates this phenomenon, and the system monitors the temperature data of the battery to determine whether the battery is in an abnormal temperature environment. The rise of battery temperature is often due to overcharging, over-discharging or excessive internal chemical reaction, which all lead to more gas generated inside the battery, thus causing swelling. If the temperature of the battery reaches a certain threshold, combined with the output data of the temperature sensor in the system, it is speculated that the chemical reaction inside the battery has been out of control, increasing the risk of swelling. Secondly, the system records and analyzes the charging and discharging data of the battery in real time, especially the fluctuation of charging current and voltage, to further evaluate the working status of the battery. Overcharging or over-discharging can cause uneven distribution of electrolyte inside the battery, which in turn triggers the swelling of the battery. Especially at high charging voltage, the electrolyte of the battery is easy to decompose, generate gas, increase internal pressure and cause swelling. If the system detects that the charging process of the battery exceeds the recommended voltage range, the depth of battery discharge is too large, the system will speculate that the probability of battery swelling increases. In addition to temperature and charging and discharging data, the system also monitors the mechanical compression status of the battery inside the energy storage cabinet in real time. Battery swelling is closely related to the space compression status inside the energy storage cabinet. Inside the energy storage cabinet, if the battery is compressed or affected by limited space, the space for battery swelling will be further compressed, causing greater internal stress in the battery and increasing the risk of swelling.

[0082] Detecting abnormal chemical substance distribution of the battery for the trend of battery swelling in the energy storage cabinet;

[0083] In the embodiment of the present application, when monitoring the expansion trend of the battery of the energy storage cabinet, the system analyzes the temperature, pressure sensor data, and current and voltage data of the battery comprehensively to monitor whether the chemical substance distribution inside the battery is abnormal in real time. The chemical substance distribution of the battery directly affects its performance and safety, especially during the expansion process, the chemical substance distribution inside the battery will change unevenly, causing the battery performance to decline or safety hazards to occur, the system obtains the temperature data inside the battery in real time through the temperature sensor. During the expansion process, due to the change of the pressure inside and outside the battery, the temperature of part of the area will abnormally rise, and the uneven change of the temperature usually indicates that the chemical reaction inside the battery is uneven, especially the activity degree of the battery chemical reaction. Next, the system analyzes the pressure change inside the battery in combination with the output of the pressure sensor. The battery expansion is often accompanied by the change of the pressure, especially during the expansion process of the battery, the pressure inside the battery increases unevenly, part of the area will bear higher pressure, causing the redistribution of the chemical substances inside the battery, thereby affecting the battery performance and service life. In addition to temperature and pressure, the system also monitors the running state of the battery by using the current and voltage data of the battery. The battery expansion often changes the flow path of the electrolyte inside the battery, or causes the uneven distribution of the current inside the battery, and the voltage fluctuation will be abnormal, reflecting the distribution problem of the battery chemical substances. For example, if the electrolyte of the battery concentrates in a certain part of the area during the expansion process, this will cause the chemical reaction in the area to be uneven, thereby affecting the charge and discharge efficiency and safety of the battery. The system analyzes the current and voltage data in combination with the temperature and pressure changes to identify the abnormal condition of the chemical substance distribution of the battery in time. Specifically, the system can monitor whether a part of the battery has excessive electrolyte concentration or a chemical reaction area due to expansion, and judge whether the battery has serious performance decline or safety hazards based on these data.

[0084] Detect the electrical connection fault condition of the energy storage cabinet according to the internal structure compression condition of the energy storage cabinet and the expansion trend of the battery of the energy storage cabinet;

[0085] In the embodiments of the present application, according to the compression condition of the internal structure of the energy storage cabinet and the expansion trend of the battery, the system will further monitor and detect whether the electrical connection of the energy storage cabinet fails. Battery expansion and internal compression are common causes of electrical connection problems. When the battery expands, the battery shell will be affected by internal and external pressure, causing the battery internal structure to deform. This deformation will affect the electrical contact between the batteries, causing poor contact or short circuits, which will affect the normal operation of the battery. The system monitors the battery in the energy storage cabinet in real time, obtains the current and voltage change data of the battery, and pays special attention to the electrical contact points between the batteries. Voltage fluctuation of the battery is one of the important indicators reflecting whether the electrical connection is normal. When the battery expands, the shape of the battery will change, causing the contact points between the batteries to shift or loosen, resulting in poor contact or short circuits of the contact points. The system collects the current and voltage data of the battery in real time, analyzes the voltage fluctuation changes between the batteries, especially the standard fluctuation range of the voltage and current between the batteries. Once the fluctuation is abnormal, it identifies potential failures of the electrical connection. If the electrical contact points between the batteries are poor or short-circuited due to expansion, the voltage of the battery will show unstable fluctuations, and the current will overload or mutate. The system not only captures abnormal fluctuations in the voltage and current of the battery in real time, but also predicts the development trend of the electrical connection failure between the batteries according to the expansion trend of the battery and the compression condition of the battery. If the battery electrical connection is found to be abnormal, the system will further analyze the change pattern of the current and voltage between the batteries to assess whether the failure will cause more serious electrical failure problems, such as unstable power supply of the battery group or overall operation failure of the energy storage cabinet, so as to timely issue a warning signal.

[0086] Predict the abnormal interaction state of the energy storage cabinet based on the electrical connection failure condition of the energy storage cabinet and the abnormal distribution of the battery chemical substances.

[0087] In the embodiment of the present application, based on the electrical connection fault condition and the abnormal chemical substance distribution condition of the energy storage cabinet, the system will combine multiple factors to perform complex prediction analysis, thereby comprehensively evaluating the abnormal interaction state of the batteries inside the energy storage cabinet. When the batteries are misaligned, swollen, have electrical connection faults, or have abnormal chemical substance distribution, the system will perform real-time monitoring based on the data of battery temperature, pressure, current, voltage, etc. collected by the sensors inside the energy storage cabinet. Misalignment of the batteries leads to poor contact between the batteries, affecting the electrical connection between the batteries, and further causing electrical short circuit or poor contact faults. Swelling of the batteries is usually caused by overcharging, over-discharging, or aging, etc. The swelling process causes uneven internal pressure of the battery, leading to damage to the battery surface or poor sealing, thereby affecting the chemical reaction efficiency of the battery, and even causing leakage or uneven distribution of internal chemical substances. When swelling and battery misalignment are combined, it exacerbates the expansion of cracks on the surface of the battery, increases the friction and mutual influence between the batteries, and causes the battery to fail faster. Electrical connection faults of the batteries are usually accompanied by unstable battery voltage, abnormal current fluctuation, etc., which can cause uneven current distribution between battery groups, causing overcharging or over-discharging of some batteries, and further affecting the performance and safety of the entire energy storage cabinet. Abnormal distribution of battery chemical substances, especially in the case of battery swelling, leads to uneven distribution of electrolyte, increases the instability of the chemical reaction inside the battery, and further negatively affects the capacity, life and safety of the battery. These abnormal phenomena not only cause the degradation of the performance of the battery itself, but also interfere with the battery management system (BMS) of the energy storage cabinet, affecting the monitoring and adjustment of the system on the state of the battery. By comprehensively analyzing factors such as battery misalignment, swelling, electrical connection faults, and abnormal chemical substance distribution, combined with the battery health state, environmental changes, and system load conditions, the algorithm model predicts the interaction and potential faults between the components of the battery. The system can discover abnormal interaction problems inside the battery of the energy storage cabinet in time through real-time monitoring and data analysis, and predict potential faults or safety risks.

[0088] Preferably, the energy storage cabinet battery degradation condition prediction in step S2 comprises:

[0089] According to the energy storage cabinet battery abnormal interaction state, the energy storage cabinet power transmission stability attenuation analysis is performed to obtain power transmission stability attenuation data;

[0090] In the embodiments of the present application, the power transmission stability decay of the energy storage cabinet is analyzed according to the abnormal interaction state of the battery. The system collects the battery state data of the energy storage cabinet, including the voltage, current, temperature and other information of the battery, and combines the internal chemical state, expansion degree, electrical connection state and other factors of the battery to analyze the abnormal interaction state of the battery. These data are input into the power transmission stability model, which evaluates the stability decay of power transmission based on the health status of the battery, the working environment of the energy storage cabinet and the load condition. These analysis results generate power transmission stability decay data, which are used to further judge the health degree of the battery system of the energy storage cabinet.

[0091] The power frequency fluctuation characteristics of the energy storage cabinet are detected based on the power transmission stability decay data;

[0092] In the embodiments of the present application, based on the power transmission stability decay data, the system continues to detect the power frequency fluctuation characteristics of the energy storage cabinet. The system collects the power output data of the energy storage cabinet, especially the voltage and current signals, to analyze the frequency fluctuation in the power transmission process. Through frequency domain analysis methods such as Fourier transform, the frequency fluctuation characteristics in the power transmission are extracted. The change of frequency fluctuation characteristics is usually an indication of battery performance degradation, especially when the battery has abnormal interaction, local poor electrical contact or uneven chemical reaction, the power transmission frequency often fluctuates obviously. Through this process, the system can identify the early signs of reduced stability of the power transmission system.

[0093] The growth of the overcurrent risk of the transmission power is predicted according to the power frequency fluctuation characteristics of the energy storage cabinet;

[0094] In the embodiments of the present application, after detecting the power frequency fluctuation characteristics, the system predicts the growth of the overcurrent risk of the transmission power according to these characteristics. Overcurrent risk is usually accompanied by battery wear, decreased charging and discharging efficiency, and electrical interference problems inside the battery. The system analyzes the relationship between power frequency fluctuation characteristics and current anomalies to evaluate the probability of current exceeding the standard, and then predicts the overcurrent condition of the energy storage cabinet under normal working conditions. The system combines historical data and real-time data to establish a model between current fluctuation and overcurrent risk, and accurately predicts the overcurrent risk occurring in the power transmission process.

[0095] The electrical interference condition of the battery of the energy storage cabinet is evaluated based on the growth of the overcurrent risk of the transmission power;

[0096] In the embodiment of the present application, the electrical interference of the battery of the energy storage cabinet is evaluated based on the growth of the overcurrent risk of the transmitted electric energy. During the transmission of electric energy, the battery may generate electrical interference due to factors such as poor electrical contact, oxidation of the contact point, damage to the transmission line or damage to the electrical components. These interferences usually manifest as abnormal fluctuations in the internal current or voltage of the battery, and may even cause the battery to overheat, reduce capacity, increase internal resistance, or degrade performance. The system can detect whether the battery is subjected to electrical interference in a timely manner by monitoring the current and voltage changes of the battery in real time, in combination with the working state of the battery (such as charging and discharging conditions, temperature changes, etc.). When the current and voltage of the battery fluctuate abnormally, the system will mark it as an electrical interference event. By analyzing the fluctuation of the voltage and current changes of the battery in detail, the system can evaluate whether there is electrical interference inside the battery. The electrical interference source usually causes irregular fluctuations in the voltage or current of the battery. For example, the sudden increase or decrease in current caused by poor electrical contact or loose wiring inside the battery usually manifests as obvious fluctuation in the current and voltage curves of the battery. The system will analyze the fluctuation amplitude, frequency and trend of the battery voltage and current. If the frequency of current and voltage fluctuations is too high and the amplitude is abnormal, the system will speculate that there is a problem of poor electrical contact or electrical components. The electrical interference of the battery is usually accompanied by temperature abnormalities, especially near the poor contact inside the battery or the damaged electrical components, and local overheating may occur when the current passes through. The system combines the temperature sensor data of the battery to further confirm the location of the electrical interference source and analyze whether the local overheating is caused by abnormal current. Through multi-point monitoring data, the system can identify whether the battery has overheated and determine the location of the electrical interference source through positioning technology. Through comprehensive analysis of the battery voltage, current and temperature, the system can accurately identify and locate the electrical interference source and evaluate the impact of the electrical interference on the battery.

[0097] The degree of wear of the battery of the energy storage cabinet is estimated according to the electrical interference of the battery of the energy storage cabinet and the growth of the overcurrent risk of the transmitted electric energy.

[0098] In the embodiments of the present application, the degree of loss of the energy storage cabinet battery is estimated according to the electrical interference of the energy storage cabinet battery and the increasing risk of overcurrent transmission of electric energy. The system continuously monitors the key electrical parameters of the battery such as voltage, current and temperature, and combines historical data such as the number of cycles and the depth of charge and discharge of the battery to perform comprehensive analysis and predict the loss of the battery. Electrical interference, especially electrical noise caused by factors such as current fluctuation, unstable voltage and poor contact, affects the electrochemical reaction inside the battery, thereby accelerating the aging process of the battery. The system monitors the voltage and current of the battery in real time, analyzes the fluctuation, identifies the existence of electrical interference, and evaluates the potential threat to the performance of the battery. In addition, current overload or overcurrent phenomenon also has a negative impact on the battery. Long-term overcurrent state not only causes the temperature inside the battery to rise, but also accelerates the chemical reaction process inside the battery, further exacerbating the loss. The system monitors the overcurrent risk of the transmission of electric energy, analyzes whether the battery is in an overcurrent state in combination with the electrical response of the battery, and calculates the loss impact of overcurrent on the battery. By comparing with the historical data of the battery, the system evaluates the degree of loss of the battery under specific working conditions. The number of cycles is an important indicator of battery loss. Each charge and discharge cycle will have some impact on the chemical performance of the battery. With the increase of the number of cycles, the capacity of the battery will gradually decrease, the internal resistance will rise, and the charge and discharge efficiency will decrease. At the same time, the depth of charge and discharge also affects the degree of loss of the battery. Deeper charge and discharge cycles will cause the battery to degrade faster. The system compares the real-time monitored data with the historical data to analyze the loss trend of the battery under the current use conditions.

[0099] The degree of loss of the energy storage cabinet battery is detected based on the degree of loss of the energy storage cabinet battery.

[0100] In the embodiments of the present application, the degree of decline of the charging and discharging efficiency of the energy storage cabinet is detected based on the degree of battery loss. The system continuously monitors the current and voltage changes of the battery during charging and discharging, combines the discharge capacity and charge capacity of the battery, and analyzes the efficiency decline of the battery in real time. The charging and discharging efficiency is a key indicator of battery performance, reflecting the efficiency level that the battery can achieve in the energy conversion process. During the use of the battery, as time goes by, the chemical reactions inside the battery will gradually cause loss, leading to an increase in the internal resistance of the battery and a decrease in the power output capacity of the battery, thereby affecting its charging and discharging efficiency. The system collects the current and voltage data of the battery in real time, combines the charge capacity and discharge capacity of the battery, calculates the charging and discharging efficiency, analyzes the use environment of the battery, and considers the influence of environmental temperature, humidity and other factors on the charging and discharging efficiency. As the battery loss increases, the charging and discharging efficiency of the battery will gradually decrease, and this process is usually accompanied by a decrease in the capacity of the battery and an increase in the internal resistance. By combining the charging and discharging data of the battery with the degree of battery loss, the system can more accurately evaluate the health status of the battery. When the degree of battery loss is large, the internal resistance of the battery increases, which will cause energy waste during the charging process and cannot effectively release electric energy during the discharging process, thereby causing a significant decrease in the charging and discharging efficiency.

[0101] The degree of decline of the charging and discharging efficiency of the energy storage cabinet is detected based on the degree of battery loss.

[0102] In the embodiments of the present application, the overall health condition of the battery is accurately evaluated through analysis of multiple data. The system detects the energy conversion efficiency of the battery during the charging and discharging process by monitoring the charging and discharging efficiency of the battery in the energy storage cabinet. As the use time of the battery increases, the chemical reaction inside the battery will gradually reduce the efficiency, resulting in a decrease in charging and discharging efficiency. The system collects real-time data such as charging current, voltage, and battery capacity of the battery, and combines factors such as the charging and discharging cycle of the battery, the use environment temperature, and the depth of discharge to evaluate the degradation of the charging and discharging efficiency of the battery. The charging and discharging efficiency of the battery is an important indicator of the health of the battery. When the charging and discharging efficiency is significantly lower than the predetermined standard, it indicates that the battery has signs of performance degradation, and the system will make predictions about the state of the battery based on these data. In addition to the charging and discharging efficiency, the system further evaluates the degradation of the battery in the energy storage cabinet by the degree of battery wear. Battery wear is usually manifested as a decrease in battery capacity and an increase in internal resistance, which directly affects the battery's power output capability and charging and discharging efficiency. The system collects data such as voltage, current, temperature, and depth of discharge of the battery during use, and combines the cycle life and historical operation data of the battery to evaluate the degree of battery wear. If the battery wear is too large, the output power of the battery will gradually decrease, resulting in complete failure of the battery. By monitoring these parameters, the system can accurately determine the degree of battery wear and predict the performance decline trend of the battery in the future. The system takes into account factors such as electrical interference and overcurrent risk for a more comprehensive analysis. During use, the battery will be affected by electrical interference and overcurrent, especially when the load fluctuation of the energy storage cabinet is large, the electrical interface of the battery will malfunction or have poor contact, causing the performance of the battery to further decline. By monitoring the voltage and current signals of the battery, the system can timely capture electrical interference or overcurrent events and analyze their potential impact on battery health. For example, overcurrent conditions can cause excessive heat inside the battery, thereby accelerating the aging process of the battery. The system combines the analysis of these electrical interference and overcurrent risks to further quantify the degradation of the battery.

[0103] Preferably, step S3 comprises the following steps:

[0104] Step S31: estimate the imbalance failure of the battery in the energy storage cabinet according to the degradation of the battery in the energy storage cabinet;

[0105] In the embodiment of the present application, the equalization failure of the energy storage cabinet battery is estimated according to the degradation state of the energy storage cabinet battery. In the long-term charging and discharging cycle, due to the gradual imbalance of the voltage, current, internal resistance and other parameters of each single battery, the equalization failure of the battery in the energy storage cabinet will occur. Equalization failure usually shows that the state of charge of some battery monomers deviates greatly, which leads to the performance reduction of the entire battery pack. In the implementation process, the system monitors the voltage, current, temperature and other parameters of each battery monomer in the energy storage cabinet in real time, as well as the charging and discharging history of the battery, analyzes the performance change trend of each battery monomer. When the system detects that the charging or discharging state of a single battery deviates from the predetermined standard, the system will estimate whether the battery pack of the energy storage cabinet exists the risk of equalization failure. By calculating the voltage difference of each battery monomer, combined with the degradation state of the battery, the system can predict the equalization failure of the battery pack, and evaluate the degree and range of failure through the model.

[0106] Step S32: evaluating the health degree of the energy storage cabinet battery based on the equalization failure of the energy storage cabinet battery and the degradation state of the energy storage cabinet battery;

[0107] In the embodiment of the present application, the health degree of the energy storage cabinet battery is evaluated based on the equalization failure of the energy storage cabinet battery and the degradation state of the energy storage cabinet battery. The battery health degree is an important indicator to evaluate the overall performance and remaining service life of the battery pack, which is usually evaluated by the change of the voltage, internal resistance, capacity and other parameters of the battery. When the equalization failure of the energy storage cabinet battery occurs, it usually leads to the decline of the battery health degree. In the implementation, the system analyzes the voltage change, internal resistance change and capacity degradation of each single battery of the energy storage cabinet battery combined with the degradation state of the energy storage cabinet battery. The system also compares the voltage difference between different battery monomers to determine whether the energy storage cabinet battery exists the condition of over-discharge or over-charge. By counting the health data of all battery monomers, the system comprehensively evaluates the overall health degree of the energy storage cabinet battery. The evaluation process also dynamically adjusts combined with the use environment (such as temperature, humidity) and operation history (such as charging frequency, discharge depth, etc.) of the battery, and outputs a value representing the battery health degree.

[0108] Step S33: detecting the output power fluctuation of the battery according to the health degree of the energy storage cabinet battery, and detecting the power supply imbalance state of the energy storage cabinet based on the output power fluctuation of the battery;

[0109] In the embodiment of the present application, the battery output power fluctuation is detected according to the battery health degree of the energy storage cabinet, and the power supply imbalance state of the energy storage cabinet is detected based on the battery output power fluctuation. The battery output power fluctuation generally reflects the change of the battery pack health condition. When the battery health degree decreases, the battery output power fluctuation occurs, and even the stable power supply cannot be maintained. The system analyzes whether the battery output power is stable by monitoring the output power change of the energy storage cabinet in real time. In the specific implementation, the system collects the output data of the energy storage cabinet through current, voltage and power sensors, and evaluates the fluctuation of the output power in combination with the battery health degree. If the fluctuation of the output power exceeds the preset threshold, the system marks the energy storage cabinet as a power supply imbalance state. The imbalance state indicates that the battery capacity cannot meet the load demand, or the battery has abnormal loss during operation.

[0110] Step S34: evaluating the dynamic load overload degree of the transmission line according to the power supply imbalance state of the energy storage cabinet;

[0111] In the embodiment of the present application, the dynamic load overload degree of the transmission line is evaluated according to the power supply imbalance state of the energy storage cabinet. The fluctuation of the battery output power directly affects the power supply situation of the energy storage cabinet, and the power supply imbalance state leads to the load overload of the power transmission line. The system analyzes the power supply imbalance state of the energy storage cabinet, and evaluates the dynamic load situation of the transmission line in combination with the current, voltage and load data of the transmission line. When the power output of the energy storage cabinet is unstable, the system models the load change of the power transmission line, and predicts whether the load exceeds the safety threshold in combination with the rated load, load type and transformer capacity of the line. If the load is too high, the system can identify the potential overload risk in time and give an alarm prompt.

[0112] Step S35: predicting the loss growth trend of the power transmission line according to the dynamic load overload degree of the transmission line.

[0113] In the embodiment of the present application, the loss growth trend of the power transmission line is predicted according to the dynamic load overload degree of the transmission line. The resistance, voltage drop and temperature parameters of the power transmission line will change abnormally in the overload operation state, and the long-term overload operation will gradually increase the loss of the line. In the implementation process, the system establishes a loss model under the dynamic load overload condition by combining the current and voltage data of the transmission line with the material characteristics and temperature sensor data of the line. The system evaluates the loss growth trend of the line within a certain time based on the load condition and the power loss prediction model of the transmission line. If the line load is continuously overloaded, the system can predict that the loss of the line will increase with time, leading to line failure or efficiency decrease.

[0114] Especially important is that step S35 includes the following steps:

[0115] Step S351: predicting the magnetic field growth trend around the transmission line according to the dynamic load overload degree of the transmission line;

[0116] In the embodiment of the present application, when the load of the transmission line increases, the current value in the line increases, according to the Biot-Savart law and the Ampere loop law, the magnetic field strength around the line is proportional to the current. Obtain the accurate magnetic field change trend, use the magnetic flux meter, Hall sensor or magnetic field detector to measure the magnetic field around the transmission line in different positions in real time, and record the change of magnetic induction intensity B. At the same time, combined with the rated current value of the transmission line, the instantaneous current change and the load curve of the line, the magnetic field growth trend data is obtained by using integral calculation method, and a time series prediction model is established to calculate the growth trend of the future magnetic field

[0117] Step S352: estimating the proximity effect characteristics according to the magnetic field growth trend around the transmission line;

[0118] In the embodiment of the present application, the proximity effect is caused by the redistribution of current in the adjacent conductor due to the change of magnetic field, which causes additional current loss. Accurately estimate the proximity effect, use the obtained magnetic field growth trend data to calculate the induced electromotive force between adjacent lines, analyze the mutual inductance change between lines according to Maxwell's equations and Faraday's law. Through the high-frequency current sensor, the induced current of the transmission line under different current load conditions is detected, the intensity and phase change of the induced current are measured, so as to evaluate the characteristics of the proximity effect. At the same time, use finite element electromagnetic simulation software (such as ANSYS Maxwell or COMSOL) to establish an electromagnetic field simulation model, simulate the influence of proximity effect under different load conditions, and extract the proximity effect characteristic parameters to form visual proximity effect characteristic data.

[0119] Step S353: detecting the attenuation of the line conductive cross-sectional area based on the proximity effect characteristics and the magnetic field growth trend around the transmission line;

[0120] In the embodiment of the present application, the proximity effect causes the current in the conductor to concentrate on the side close to the adjacent conductor, which reduces the effective conductive cross-sectional area and increases the equivalent resistance of the conductor. Detect the attenuation of the conductive cross-sectional area, use the alternating current impedance analyzer to measure the resistance of the line under different frequencies and load conditions, and combine the aforementioned proximity effect characteristic data to obtain the effective change value of the conductive cross-sectional area by analytical calculation. In addition, use the infrared thermal imager to measure the temperature distribution of the conductor surface, analyze the heating area caused by the current concentration effect, and further verify the attenuation of the conductive cross-sectional area to obtain the conductive cross-sectional area attenuation trend data.

[0121] Step S354: analyzing the equivalent resistance increasing trend according to the attenuation of the line conductive cross-sectional area;

[0122] In the embodiment of the present application, the increase of the equivalent resistance is mainly affected by the attenuation of the conductive cross-sectional area, and is also affected by factors such as temperature change and material aging. Precise analysis of the increasing trend of the equivalent resistance is based on the conductive cross-sectional area attenuation trend data, combined with the line resistance temperature coefficient, to establish a calculation model of the change of the equivalent resistance. The four-terminal method is used to measure the dynamic resistance change of the line, the resistance value under different load conditions is recorded, and the resistance change trend with time is analyzed. At the same time, the large current pulse test method is used to simulate the resistance change of the line under extreme load conditions, combined with the historical operation data of the line, to establish an equivalent resistance increasing trend prediction model, and output the equivalent resistance increasing trend data.

[0123] Step S355: predicting the power transmission line loss growth trend based on the equivalent resistance increasing trend and the conductive cross-sectional area attenuation of the line.

[0124] In the embodiment of the present application, the power loss is mainly caused by the equivalent resistance of the line, and the loss power is calculated by P=I 2 R. Accurate prediction of the loss growth trend of the power transmission line is based on the equivalent resistance increasing trend data, combined with the line current load change record, to calculate the loss change of the line at different time periods. At the same time, the thermal simulation analysis software is used to simulate the temperature rise of the line, to evaluate the additional loss of the conductor caused by heating, and combined with the thermal-electric coupling model to calculate the loss growth trend of the line, and output the calculated loss growth trend data.

[0125] Preferably, step S4 comprises the following steps:

[0126] Step S41: estimating the accumulation of thermal effects of the energy storage cabinet according to the power transmission line loss growth trend and the dynamic load overload degree of the transmission line;

[0127] In the embodiment of the present application, the accumulation of thermal effects of the energy storage cabinet is estimated according to the power transmission line loss growth trend and the dynamic load overload degree of the transmission line. The loss growth trend and the load overload degree of the power transmission line directly affect the thermal effects of the energy storage cabinet. High load and high loss cause the temperature of the working environment of the energy storage cabinet to rise, thereby affecting the performance and service life of the battery. In the implementation process, the system calculates the power loss of the line through the current, voltage and other transmission line parameters. Combined with the dynamic change of the load overload, the system evaluates the thermal effects caused by the line loss by using a heat conduction model (such as a heat transfer equation), and further calculates the temperature change of the energy storage cabinet. By monitoring the temperature sensor data (such as battery temperature, energy storage cabinet shell temperature, etc.) in the energy storage cabinet, the accumulation of the thermal effects inside the energy storage cabinet is estimated in real time. If the loss of the transmission line continues to increase or the load is overloaded for a long time, the system will predict the thermal accumulation degree of the energy storage cabinet and provide a warning for the temperature anomaly.

[0128] Step S42: detecting stress abnormal conditions in the energy storage cabinet according to the accumulation of thermal effects of the energy storage cabinet;

[0129] In the embodiment of the present application, the stress abnormal conditions in the energy storage cabinet are detected according to the accumulation of thermal effects of the energy storage cabinet. In the long-term use process of the energy storage cabinet, the accumulation of thermal effects causes thermal expansion of the internal materials of the energy storage cabinet, and further generates mechanical stress. If the temperature in the energy storage cabinet is too high, the thermal expansion of the components such as the battery and the support structure will cause stress concentration, and local damage or deformation will occur. In the implementation, the system combines the real-time data of the temperature sensor, the stress sensor and the deformation sensor in the energy storage cabinet to monitor the stress state in the energy storage cabinet. By analyzing the stress distribution of each component of the energy storage cabinet, the system can detect the abnormal stress conditions caused by the accumulation of thermal effects. If the stress in the energy storage cabinet exceeds the preset safety threshold, the system will automatically mark it as a stress abnormal state.

[0130] Step S43: predicting the degradation trend of the energy storage cabinet based on the stress abnormal conditions in the energy storage cabinet and the accumulation of thermal effects of the energy storage cabinet;

[0131] In the embodiment of the present application, the degradation trend of the energy storage cabinet is predicted based on the stress abnormal conditions in the energy storage cabinet and the accumulation of thermal effects of the energy storage cabinet. The accumulation of stress abnormality and thermal effects usually accelerates the degradation process of the components of the energy storage cabinet, especially the life and safety of the battery. In the implementation process, the system uses the stress distribution data and temperature change data in the energy storage cabinet, combined with the chemical reaction model of the battery, to predict the degradation trend of the components of the energy storage cabinet. The specific operation is that the system models the stress and temperature data of the energy storage cabinet by time series analysis method, simulates the degradation process of the energy storage cabinet under different working conditions, and predicts the performance degradation speed caused by thermal effects and stress abnormality. If the temperature in the energy storage cabinet continues to rise or the stress is long-term uneven, the system predicts that the battery performance of the energy storage cabinet will rapidly decrease, the discharge efficiency of the battery will decline, and the capacity of the battery will decrease.

[0132] Step S44: performing performance aging estimation of the energy storage cabinet based on the stress abnormal conditions in the energy storage cabinet and the degradation trend of the energy storage cabinet, to obtain performance aging data of the energy storage cabinet;

[0133] In the embodiment of the present application, the performance aging data of the energy storage cabinet is obtained by estimating the performance aging of the energy storage cabinet based on the stress abnormal condition and the degradation trend of the energy storage cabinet. The performance aging of the energy storage cabinet is closely related to the stress abnormality and the degradation trend. After long-term use, the charging and discharging efficiency, cycle life and battery capacity of the battery will be affected due to the accumulation of thermal effect and mechanical stress. In the implementation process, the system combines the degradation trend and stress abnormality of the energy storage cabinet, and uses an aging prediction method based on a physical model (such as the Arrhenius model or the battery degradation model) to calculate the performance aging of the energy storage cabinet. By simulating the charging and discharging cycle of the battery and the change of the temperature in the energy storage cabinet, the system obtains the performance aging data of the energy storage cabinet in the future period of time.

[0134] Step S45: estimating the service life of the energy storage cabinet based on the performance aging data of the energy storage cabinet and the degradation trend of the energy storage cabinet, and obtaining the service life data of the energy storage cabinet.

[0135] In the embodiment of the present application, the service life data of the energy storage cabinet is obtained by estimating the service life of the energy storage cabinet based on the performance aging data of the energy storage cabinet and the degradation trend of the energy storage cabinet. The service life of the energy storage cabinet is an evaluation result considering various factors such as performance degradation, aging, stress abnormality, etc. The system analyzes the performance aging data and the degradation trend of the energy storage cabinet, and combines the charging and discharging cycle, temperature, stress and other factors of the battery to estimate the service life of the energy storage cabinet. The prediction method of the service life is usually based on a linear regression model or an accelerated life test model, and the remaining service life of the energy storage cabinet is calculated by statistically analyzing the historical data, temperature and stress. The system will be updated in real time according to these parameters, and the remaining life of the energy storage cabinet will be continuously evaluated as the use time of the energy storage cabinet increases. If the performance aging of the energy storage cabinet reaches a set threshold, the system will issue a warning that the energy storage cabinet will soon enter a state requiring maintenance or replacement, and the system outputs the service life data of the energy storage cabinet.

[0136] Especially important is that step S43 comprises the following steps:

[0137] Step S431: estimating the thermal management failure condition of the energy storage cabinet based on the stress abnormal condition in the energy storage cabinet and the thermal effect accumulation condition of the energy storage cabinet;

[0138] In the embodiment of the present application, the thermal management failure of the energy storage cabinet is estimated based on the stress abnormality inside the energy storage cabinet and the accumulation of thermal effects. The stress abnormality inside the energy storage cabinet is mainly caused by the change of temperature gradient, and the accumulation of thermal effects leads to uneven internal temperature distribution, thereby affecting the heat dissipation efficiency of the thermal management system. The temperature data inside the energy storage cabinet is collected by using a temperature sensor, and the thermal distribution is obtained by using a thermal imaging device. By comparing the thermal conduction model under the normal operating state, the temperature abnormal points and heat loss are analyzed. Further, the mechanical stress inside the energy storage cabinet is measured by using a pressure sensor to determine whether the stress concentration area will affect the stability of the heat dissipation component. By inputting these data into the thermal management simulation system, the heat exchange efficiency and heat dissipation capacity of the energy storage cabinet are calculated, and the data of the thermal management failure of the energy storage cabinet is obtained.

[0139] Step S432: analyzing the stability degradation of the energy storage cabinet based on the thermal management failure of the energy storage cabinet;

[0140] In the embodiment of the present application, the stability degradation of the energy storage cabinet is analyzed based on the thermal management failure of the energy storage cabinet. The thermal management failure of the energy storage cabinet will cause local overheating, thereby affecting the stability of the battery module, the connecting component and the overall structure. The surface temperature distribution of the battery is detected by using an infrared thermal imager, and the abnormal fluctuation of the battery temperature is analyzed in combination with the data of the battery management system (BMS). The operating state of the heat dissipation fan and the electric cooling system of the energy storage cabinet is monitored, and the overall stability decline trend is calculated in combination with the temperature change rate and the distribution of the overheating area. The degree of mechanical deformation caused by thermal expansion is detected by using a vibration sensor, and the material fatigue degree is calculated in combination with the thermal expansion and contraction coefficient, thereby further analyzing whether the stability of the energy storage cabinet structure is degraded due to thermal runaway, and obtaining the stability degradation data of the energy storage cabinet.

[0141] Step S433: detecting the power grid fault of the energy storage cabinet according to the stability degradation of the energy storage cabinet;

[0142] In the embodiment of the present application, the power grid fault of the energy storage cabinet is detected according to the stability degradation of the energy storage cabinet. The stability degradation of the energy storage cabinet leads to problems such as loose electrical connection, power output fluctuation and short circuit, thereby affecting the interaction between the energy storage cabinet and the power grid. The output power parameters of the energy storage cabinet are monitored in real time by using high-precision voltage and current sensors, the voltage fluctuation rate and the current harmonic content are analyzed, and the quality of the output power of the energy storage cabinet is calculated in combination with the power factor. The energy storage cabinet power output spectrum is analyzed by using short-time Fourier transform (STFT), whether there is an abnormal harmonic is detected, and then whether the energy storage cabinet interferes with the power grid is judged. In addition, the overcurrent and short circuit of the connection point of the energy storage cabinet and the power grid are detected by using a relay protection device, and the data of the power grid fault of the energy storage cabinet is obtained.

[0143] Step S434: estimating the material aging degree of the energy storage cabinet based on the stress abnormality inside the energy storage cabinet;

[0144] In the embodiment of the present application, the material aging degree of the energy storage cabinet is estimated according to the stress abnormal condition in the energy storage cabinet. In the long-term operation process, the internal materials of the energy storage cabinet will appear aging phenomenon under the influence of temperature cycle, mechanical stress and current impact. The environmental temperature, operating current and mechanical stress data are collected by the internal sensor of the energy storage cabinet, and the life attenuation trend of the key components is analyzed combined with the fatigue life curve of the metal material. Secondly, the micro crack propagation of the energy storage cabinet shell and the internal connecting components is detected by X-ray computed tomography (CT), and the fatigue strength of the stress area is calculated combined with finite element analysis (FEA), so as to evaluate the aging degree of the material. Finally, the electrical performance of the insulation material is measured by dielectric loss test, whether the insulation layer appears leakage risk due to aging is judged, and the material aging degree data of the energy storage cabinet is obtained.

[0145] Step S435: predicting the degradation trend of the energy storage cabinet according to the material aging degree of the energy storage cabinet and the power grid fault condition of the energy storage cabinet.

[0146] In the embodiment of the present application, the degradation trend of the energy storage cabinet is predicted according to the material aging degree of the energy storage cabinet and the power grid fault condition of the energy storage cabinet. The material aging of the energy storage cabinet will reduce its mechanical strength, and the power grid fault will cause additional electrical impact. The two together will accelerate the overall degradation process of the energy storage cabinet. By comprehensively analyzing the material aging data of the energy storage cabinet, the power grid fault data and the historical operation condition, a time series analysis model is constructed to calculate the degradation rate. Further, by using the accelerated life test (ALT) method, the degradation rate curve of the energy storage cabinet under normal working conditions is calculated through accelerated temperature and electrical stress experiments, and combined with the existing operation data, the degradation trend of the future operation stage is extrapolated, and the degradation trend data of the energy storage cabinet is obtained.

[0147] The present application also provides a visualization system for an energy storage cabinet for executing the visualization method for an energy storage cabinet as described above, which comprises:

[0148] A visualization state determination module is configured to acquire energy storage cabinet data, collect energy storage cabinet image data based on the energy storage cabinet data, and determine an energy storage cabinet operation visualization state based on the energy storage cabinet image data.

[0149] A battery degradation prediction module is configured to detect an energy storage cabinet stability gradient attenuation trend according to the energy storage cabinet operation visualization state, predict an energy storage cabinet battery abnormal interaction influence state according to the energy storage cabinet stability gradient attenuation trend, and predict an energy storage cabinet battery degradation condition according to the energy storage cabinet battery abnormal interaction influence state.

[0150] The line loss growth trend prediction module is configured to estimate the state of health of the energy storage cabinet battery according to the energy storage cabinet battery degradation condition, detect an energy storage cabinet power supply imbalance state according to the state of health of the energy storage cabinet battery, estimate a transmission line dynamic load overload degree according to the energy storage cabinet power supply imbalance state, and predict a power transmission line loss growth trend according to the transmission line dynamic load overload degree.

[0151] The energy storage cabinet service life estimation module is configured to estimate an energy storage cabinet thermal effect accumulation condition according to the power transmission line loss growth trend and the transmission line dynamic load overload degree, predict an energy storage cabinet degradation trend based on the energy storage cabinet thermal effect accumulation condition, and estimate the service life of the energy storage cabinet based on the energy storage cabinet degradation trend to obtain energy storage cabinet service life data.

[0152] A computer readable storage medium storing a computer program, wherein the computer program is configured to execute the visual method for the energy storage cabinet.

[0153] The above description is merely a specific implementation of the present application, which enables those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A visualization method for an energy storage cabinet, characterized in that, The method comprises the following steps: Step S1: obtaining energy storage cabinet data; collecting energy storage cabinet image data based on the energy storage cabinet data; and determining an energy storage cabinet operation visualization state based on the energy storage cabinet image data; Step S2: detecting an energy storage cabinet stability gradient attenuation trend according to the energy storage cabinet operation visualization state; predicting an energy storage cabinet battery abnormal interaction state according to the energy storage cabinet stability gradient attenuation trend; and predicting an energy storage cabinet battery degradation condition according to the energy storage cabinet battery abnormal interaction state; Step S3: estimating an energy storage cabinet battery health degree according to the energy storage cabinet battery degradation condition; detecting an energy storage cabinet power supply imbalance state according to the energy storage cabinet battery health degree; evaluating a transmission line dynamic load overload degree according to the energy storage cabinet power supply imbalance state; and predicting an electric energy transmission line loss growth trend according to the transmission line dynamic load overload degree; Step S4: estimating an energy storage cabinet thermal effect accumulation situation according to the electric energy transmission line loss growth trend and the transmission line dynamic load overload degree; and predicting an energy storage cabinet degradation trend based on the energy storage cabinet thermal effect accumulation situation; Based on the energy storage cabinet degradation trend, the service life of the energy storage cabinet is estimated to obtain energy storage cabinet service life data, the energy storage cabinet stability gradient attenuation trend is detected based on the damage situation of the energy storage cabinet support structure, and the energy storage cabinet battery abnormal interaction state is predicted based on the energy storage cabinet electrical connection fault situation and the abnormal distribution of battery chemical substances.

2. The visualization method for an energy storage tank of claim 1, wherein, Step S1 comprises the following steps: Step S11: setting the resolution of the visible light camera to 1920x1080 pixels, the minimum light sensitivity to 0.01 lux, and the frame rate to 30 FPS; Step S12: setting the temperature measurement range of the infrared imager to -20°C to 300°C, the minimum temperature resolution to 0.05°C, and the image frame rate to 25 Hz; Step S13: obtaining energy storage cabinet data; Step S14: collecting energy storage cabinet image data using a visible light camera on the energy storage cabinet data; Step S15: determining an energy storage cabinet operation visualization state using an infrared imager and the energy storage cabinet image data.

3. The visualization method for an energy storage tank of claim 2, wherein, Step S15 comprises the following steps: Step S151: performing energy storage cabinet image preprocessing on the energy storage cabinet image data to obtain energy storage cabinet image preprocessing data; Step S152: collecting energy storage cabinet image three-dimensional point cloud features according to the energy storage cabinet image preprocessing data; Step S153: extracting energy storage cabinet image surface features according to the energy storage cabinet image three-dimensional point cloud features; Step S154: detecting an energy storage cabinet structure condition based on the energy storage cabinet image surface features; Step S155: collecting an energy storage cabinet hot spot distribution situation using an infrared imager; Step S156: calculating an energy storage cabinet hot spot distribution uniformity according to the energy storage cabinet hot spot distribution situation; Step S157: determining an energy storage cabinet operation visualization state according to the energy storage cabinet hot spot distribution uniformity and the energy storage cabinet structure condition.

4. The visualization method for an energy storage tank of claim 1, wherein, The energy storage cabinet stability gradient attenuation trend detection in Step S2 comprises: collecting an energy storage cabinet structure defect situation according to the energy storage cabinet operation visualization state; identifying an energy storage cabinet structure deformation degree using the energy storage cabinet structure defect situation; calculating an energy storage cabinet local mechanical stress abnormal growth trend when the energy storage cabinet structure deformation degree exceeds 0.5% and the energy storage cabinet structure defect situation; When the local mechanical stress growth trend of the energy storage cabinet exceeds 50 MPa, the surface crack degree of the energy storage cabinet is detected based on the structure deformation degree of the energy storage cabinet; When the surface crack degree of the energy storage cabinet exceeds 2 cm, the support structure damage of the energy storage cabinet is evaluated based on the local mechanical stress growth trend of the energy storage cabinet; The stability gradient attenuation trend of the energy storage cabinet is detected based on the support structure damage of the energy storage cabinet.

5. The visualization method for an energy storage tank of claim 1, wherein, The energy storage cabinet battery abnormal interaction state prediction in step S2 includes: The energy storage cabinet structure tilt probability is calculated according to the stability gradient attenuation trend of the energy storage cabinet; The internal element displacement degree of the energy storage cabinet is predicted based on the energy storage cabinet structure tilt probability; The internal battery misplacement trend of the energy storage cabinet is predicted by using the internal element displacement degree of the energy storage cabinet and the energy storage cabinet structure tilt probability; The internal structure compression condition of the energy storage cabinet is calculated by using the internal battery misplacement trend of the energy storage cabinet and the internal element displacement degree of the energy storage cabinet; The battery swelling trend of the energy storage cabinet is predicted according to the internal structure compression condition of the energy storage cabinet; The battery chemical substance distribution abnormality is detected according to the battery swelling trend of the energy storage cabinet; The electrical connection fault condition of the energy storage cabinet is detected according to the internal structure compression condition of the energy storage cabinet and the battery swelling trend of the energy storage cabinet; The energy storage cabinet battery abnormal interaction state is predicted based on the electrical connection fault condition of the energy storage cabinet and the battery chemical substance distribution abnormality.

6. The visualization method for an energy storage tank of claim 1, wherein, The energy storage cabinet battery degradation condition prediction in step S2 includes: The power transmission stability attenuation data is obtained by performing power transmission stability attenuation analysis on the energy storage cabinet battery abnormal interaction state; The energy storage cabinet power frequency fluctuation characteristics are detected based on the power transmission stability attenuation data; The transmission power overcurrent risk growth situation is predicted according to the energy storage cabinet power frequency fluctuation characteristics; The energy storage cabinet battery electrical interference condition is evaluated based on the transmission power overcurrent risk growth situation; The energy storage cabinet battery loss degree is predicted according to the energy storage cabinet battery electrical interference condition and the transmission power overcurrent risk growth situation; The energy storage cabinet charge and discharge efficiency degradation degree is detected based on the energy storage cabinet battery loss degree; The energy storage cabinet battery degradation condition is predicted based on the energy storage cabinet charge and discharge efficiency degradation degree and the energy storage cabinet battery loss degree.

7. The visualization method for an energy storage tank of claim 1, wherein, Step S3 includes the following steps: Step S31: The energy storage cabinet battery equalization failure condition is predicted according to the energy storage cabinet battery degradation condition; Step S32: The energy storage cabinet battery health degree is evaluated based on the energy storage cabinet battery equalization failure condition and the energy storage cabinet battery degradation condition; Step S33: The battery output power fluctuation situation is detected according to the energy storage cabinet battery health degree, and the energy storage cabinet power supply imbalance state is detected based on the battery output power fluctuation situation; Step S34: The transmission line dynamic load overload degree is predicted according to the energy storage cabinet power supply imbalance state; Step S35: The energy transmission line loss growth trend is predicted according to the transmission line dynamic load overload degree.

8. The visualization method for an energy storage tank of claim 1, wherein, Step S4 includes the following steps: Step S41: The energy storage cabinet thermal effect accumulation situation is predicted according to the energy transmission line loss growth trend and the transmission line dynamic load overload degree; Step S42: The energy storage cabinet internal stress abnormal condition is detected according to the energy storage cabinet thermal effect accumulation situation; Step S43: The energy storage cabinet degradation trend is predicted based on the energy storage cabinet internal stress abnormal condition and the energy storage cabinet thermal effect accumulation situation; Step S44: based on the stress abnormal condition in the energy storage cabinet and the energy storage cabinet degradation trend, the energy storage cabinet performance aging estimation is performed to obtain energy storage cabinet performance aging data; Step S45: based on the energy storage cabinet performance aging data and the energy storage cabinet degradation trend, the energy storage cabinet service life estimation is performed to obtain energy storage cabinet service life data.

9. A visualization system for an energy storage cabinet, comprising: The visualization system for the energy storage cabinet is used to perform the visualization method for the energy storage cabinet as claimed in claim 1, and the visualization system for the energy storage cabinet comprises: a visualization state determination module, configured to acquire energy storage cabinet data, collect energy storage cabinet image data based on the energy storage cabinet data, and determine an energy storage cabinet operation visualization state based on the energy storage cabinet image data; a battery degradation prediction module, configured to detect an energy storage cabinet stability gradient attenuation trend according to the energy storage cabinet operation visualization state, predict an energy storage cabinet battery abnormal interaction state according to the energy storage cabinet stability gradient attenuation trend, and predict an energy storage cabinet battery degradation condition according to the energy storage cabinet battery abnormal interaction state; a line loss growth trend prediction module, configured to estimate and evaluate an energy storage cabinet battery health degree according to the energy storage cabinet battery degradation condition, detect an energy storage cabinet power supply imbalance state according to the energy storage cabinet battery health degree, evaluate a transmission line dynamic load overload degree according to the energy storage cabinet power supply imbalance state, and predict an electric energy transmission line loss growth trend according to the transmission line dynamic load overload degree; an energy storage cabinet service life estimation module, configured to estimate an energy storage cabinet thermal effect accumulation condition according to the electric energy transmission line loss growth trend and the transmission line dynamic load overload degree, predict an energy storage cabinet degradation trend based on the energy storage cabinet thermal effect accumulation condition, and perform energy storage cabinet service life estimation based on the energy storage cabinet degradation trend to obtain energy storage cabinet service life data.

10. A computer readable storage medium storing a computer program, characterized in that, The computer program is executed to implement the visualization method for the energy storage cabinet as claimed in any one of claims 1 to 8. The computer program is executed to implement the visualization method for the energy storage cabinet as claimed in any one of claims 1 to 8.

Images