Energy storage power station lithium battery safety state estimation method, device, equipment and medium

Abstract

The application discloses a kind of energy storage power station lithium battery safety state estimation methods based on multi-dimension information fusion, process as follows: collection multi-dimension information;Analysis multi-dimension information, determine whether to send alarm, if not, continue event message listening, if send alarm, after determining alarm high, middle, low grade, send;When receiving alarm information, set while alarm length, four-level fusion alarm quantification index interval, the weight of basic alarm and the nonlinear weight of each dimension simultaneous alarm;According to the length determined whether to receive multiple dimensions alarm information simultaneously, if not, the original alarm information is displayed according to high, middle, low three levels basic alarm, if yes, alarm quantitative index is calculated according to the weight of set basic alarm and the nonlinear weight value of each dimension simultaneous alarm, according to alarm quantitative index, approve super-high, high, middle, low four-level fusion alarm, display fusion alarm level, display alarm quantitative index and associated basic alarm level simultaneously.

Description

Technical Field

[0001] This invention relates to the field of lithium battery energy storage equipment technology, specifically to a method, device, computer equipment, and storage medium for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion. Background Technology

[0002] In recent years, guided by the dual carbon targets, new energy industries such as photovoltaic and wind power have developed rapidly. Since new energy power plants are dependent on weather conditions and their output is highly volatile, the connection of a large number of new energy power plants to the grid has put great pressure on grid dispatch. Against this backdrop, lithium battery energy storage stations, as one of the main forces for grid peak shaving and frequency regulation, have also developed rapidly.

[0003] As a key component of power grid balancing and dispatching, the safety of lithium battery energy storage stations has received widespread attention. In recent years, safety issues at lithium battery energy storage stations have occurred frequently both domestically and internationally. As a common safety management method, a battery management system is typically deployed at lithium battery energy storage stations to collect data on the temperature, voltage, and current of the lithium battery terminals to estimate the internal state of the lithium battery. At the same time, the external environment of the lithium battery is monitored in real time, including external images, ambient temperature distribution, detection of combustible gases and smoke, etc., and alarms are displayed for abnormal conditions.

[0004] Current management methods do not make sufficient use of alarm information from various dimensions. They generally only display a few alarm levels for each dimension and do not make sufficient use of information from multiple dimensions that alarm simultaneously. They fail to fully explore and display the inherent risk indication meaning of alarm information and fail to provide quantitative indicators, making it difficult to intuitively display the actual operation and maintenance risks of energy storage power stations. Summary of the Invention

[0005] The purpose of this invention is to address the aforementioned deficiencies in the prior art and provide a method, apparatus, computer equipment, and storage medium for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion. This method for estimating the safety status of lithium batteries in energy storage power stations is a way to quantify and fuse alarm information indicators from multiple dimensions to facilitate a comprehensive assessment of the degree of risk.

[0006] The first objective of this invention is to provide a method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion, wherein the method includes:

[0007] S1. Data collection steps: Collect multi-dimensional information, including: lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring image, lithium battery module surrounding temperature distribution, lithium battery module surrounding combustible gas concentration and lithium battery module surrounding smoke concentration.

[0008] S2. Basic analysis steps: Analyze multi-dimensional information to determine whether to send an alarm. If not, continue to listen for event messages. If an alarm is sent, determine which level (high, medium, or low) the alarm belongs to before sending it.

[0009] S3. Fusion Analysis Steps: Upon receiving alarm information, set the simultaneous alarm duration, the quantitative index range of the four-level fusion alarm, the weight of the basic alarm, and the nonlinear weight of simultaneous alarms in each dimension; determine whether alarm information from multiple dimensions is received simultaneously based on the set duration. If not, proceed to step S4; if so, calculate the fusion alarm quantitative index based on the set weight of the basic alarm and the nonlinear weight value of simultaneous alarms in each dimension. Verify the four-level fusion alarm (ultra-high, high, medium, and low) based on the fusion alarm quantitative index to form the alarm level and quantitative index, and proceed to step S5.

[0010] S4. Basic alarm display steps: Display the original alarm information as low, medium and high basic alarms;

[0011] S5. Integrated Alarm Display Steps: Display alarm information in four levels: low, medium, high, and extra-high, and simultaneously show the warning quantification number and associated basic alarm information.

[0012] Furthermore, step S1 is performed as follows:

[0013] S11. The temperature, current, and voltage of the lithium battery terminals are collected using a lithium battery terminal temperature, current, and voltage acquisition instrument. The terminals have good thermal conductivity, which can largely characterize the internal temperature of the lithium battery. Based on a circuit model or electrochemical model, the remaining capacity of the lithium battery can be estimated using the terminal temperature, current, and voltage. By using the terminal temperature, current, voltage, and the real-time estimated remaining capacity, the internal working state of the lithium battery can be assessed in real time, and the level of risk can be determined.

[0014] S12. Collect images of the lithium battery module's appearance using a visible light acquisition instrument; When a lithium battery experiences a micro-short circuit, internal short circuit, excessive current, or excessively high ambient temperature, the electrolyte or positive electrode material inside the lithium battery may decompose, releasing gas. When the amount of gas inside the lithium battery module reaches a certain level, it can cause the lithium battery module to bulge. In severe cases, it can cause the pressure relief valve of a hard-shell lithium battery to open or the closed structure of a soft-pack lithium battery to crack. In even more severe cases, it may explode. By inspecting the appearance of the lithium battery module, the safety status of the lithium battery can be monitored and the degree of risk can be assessed.

[0015] S13. Collect the temperature distribution around the lithium battery module using an infrared light acquisition device; compared to the temperature of the lithium battery terminals, infrared light can collect a larger range of temperature distribution around the battery module, allowing for monitoring of the working environment temperature of the lithium battery on a larger scale and assessing the degree of risk.

[0016] S14. Collect the concentration of combustible gases around the lithium battery module using a combustible gas collector. When a lithium battery experiences a micro-short circuit, internal short circuit, excessive current, or excessively high operating temperature, the electrolyte or positive electrode material inside the lithium battery may decompose, releasing gases. Among these, the most hazardous and easily detectable combustible gases are H2 and CO. The released gases can easily leak out through the gaps in the hard-shell lithium battery module casing or the closed structure of the soft-pack lithium battery module. Depending on the severity, the amount of gas released per unit time varies. By detecting the concentration of combustible gases, the safety status of the lithium battery can be monitored and the degree of risk can be assessed.

[0017] S15. The smoke concentration around the lithium battery module is collected by a smoke collector. When the lithium battery experiences micro-short circuit, internal short circuit, excessive current, or excessively high operating temperature, it can cause the electrolyte or positive electrode material inside the lithium battery to decompose. In severe cases, the high temperature can cause some substances to undergo incomplete combustion, releasing smoke. The smoke leaks out through the gaps in the shell of the hard-shell lithium battery module or the sealed structure of the soft-pack lithium battery module. The amount of smoke released per unit time varies depending on the severity. By detecting the smoke concentration, the risk level of the lithium battery can be monitored.

[0018] Furthermore, step S2 is as follows:

[0019] S21. Analyze the temperature, current, and voltage of the lithium battery terminals; by comparing the differences between the lithium battery terminal temperature, current, voltage, and the real-time estimated remaining power and the rated operating range, the internal working status of the lithium battery can be monitored in real time, the risk level can be determined, and it can be determined whether to output an alarm. If not, the event message listening continues. If an alarm is sent, the alarm level is determined according to the proportion of each indicator exceeding the rated range, and then sent. Proceed to step S3.

[0020] S22. Analyze the video monitoring images of the lithium battery module; by real-time detection of whether the lithium battery module is bulging, whether the pressure relief valve of the hard-shell lithium battery module is open, whether the closed structure of the soft-pack lithium battery module is cracked, and whether an explosion has occurred, the risk level can be determined in real time, and it can be determined whether to output an alarm and the corresponding alarm level. If not, the event message is continuously monitored. If an alarm is sent, the alarm level is determined according to the proportion of each indicator exceeding the rated range, and then sent. Proceed to step S3.

[0021] S23. Analyze the temperature distribution around the lithium battery module; when the lithium battery has a micro short circuit, internal short circuit, or excessive current, the internal heat conduction of the battery is higher than the surface of the battery module, or when the air conditioner malfunctions and causes abnormal ambient temperature, by analyzing the temperature distribution around the lithium battery module, the risk level can be determined in real time, and it can be determined whether to output an alarm and the corresponding alarm level. If not, the event message will be continuously monitored. If an alarm is sent, the alarm level will be determined according to the proportion of each indicator exceeding the rated range, and then sent to step S3.

[0022] S24. Analyze the concentration of combustible gas around the lithium battery module; the high temperature inside the lithium battery causes the material to decompose and generate combustible gas, which leaks outward through the gaps in the shell of the hard-shell lithium battery module or the closed structure of the soft-pack lithium battery module. By analyzing the concentration of combustible gas around the lithium battery module, the risk level can be determined in real time, and it can be determined whether to output an alarm and the corresponding alarm level. If not, the event message is continuously monitored. If an alarm is sent, the alarm level is determined according to the proportion of each indicator exceeding the rated range. Then, the alarm is sent and proceeds to step S3.

[0023] S25. Analyze the smoke concentration around the lithium battery module; the high temperature inside the lithium battery causes some substances to burn incompletely, releasing smoke. The smoke leaks out through the gaps in the shell of the hard-shell lithium battery module or the sealed structure of the soft-pack lithium battery module. By analyzing the concentration of the smoke gas around the lithium battery module, the risk level can be determined in real time, and it can be determined whether to output an alarm and the corresponding alarm level. If not, the event message is continuously monitored. If an alarm is sent, the alarm level is determined according to the proportion of each indicator exceeding the rated range, and then sent to step S3.

[0024] Furthermore, step S3 is as follows:

[0025] S31. It receives alarm information for abnormal state inside the lithium battery, alarm information for abnormal shape of the lithium battery module, alarm information for abnormal temperature around the lithium battery module, alarm information for excessive concentration of combustible gas around the lithium battery module, and alarm information for excessive smoke concentration around the lithium battery module. It sets the duration of simultaneous alarms, the quantitative index range of four-level fusion alarms, the weight of basic alarms, and the nonlinear weight of simultaneous alarms in each dimension. It has the conditions to quantitatively display fusion alarms when multiple dimensions alarm simultaneously.

[0026] S32. Determine whether multiple alarm messages from multiple dimensions are received simultaneously based on the set duration of simultaneous alarms. If not, proceed to step S4. If so, calculate the alarm quantitative index based on the set basic alarm weight and the nonlinear weight value of simultaneous alarms in each dimension, and determine the quantified fusion alarm level based on the quantitative index range of the four-level fusion alarm. Proceed to step S5.

[0027] Further, step S31 is as follows:

[0028] S311. Set the duration for simultaneous alarms. The duration range for simultaneous alarms needs to be within a reasonable range. If the time is too long, the correlation between multiple alarm dimensions will be weak, and this feature will lose its significance. If the time is too short, it may not be able to capture effective correlated alarms. Based on experimental data of individual batteries, this patent initially sets it to 50 minutes, which means that alarms of multiple dimensions appearing within 50 minutes are considered simultaneous alarms. For different types of battery power stations, users can flexibly adjust it according to the operation and maintenance experience of the power station.

[0029] S312. Set the quantitative indicator range for the four-level fusion alarm, the weight of the basic alarm, and the non-linear weight of simultaneous alarms in each dimension, using the following scheme:

[0030] The four-level fusion alarm is divided into four levels: extra high, high, medium, and low. The quantitative index ranges for the four levels are set to [3, +∞), [2, 3), [1, 2), and [0, 1), respectively. The weights of the basic alarms for the high, medium, and low levels are set to 3, 2, and 1, respectively. When two dimensions alarm simultaneously, the non-linear weight index is set to 0.4; when three dimensions alarm simultaneously, the non-linear weight index is set to 0.8; when four dimensions alarm simultaneously, the non-linear weight index is set to 1.6; and when five dimensions alarm simultaneously, the non-linear weight index is set to 3.2.

[0031] Further, step S32 is as follows:

[0032] When two dimensions issue alerts simultaneously, the final quantitative indicator for the alert is calculated by multiplying the average weight of the alert levels for both dimensions by the non-linear weighting metric for simultaneous alerts, and then adding the weight of the higher-level alert. For example, if one dimension's alert is classified as medium-level and the other as high-level, the final quantitative indicator for the merged alert would be:

[0033] (Weight of intermediate alarm + weight of advanced alarm) / 2 * non-linear weight index when both dimensions alarm simultaneously + weight of advanced alarm = (2 + 3) / 2 * 0.4 + 3 = 3.6. Since 3.6 is greater than 3, the alarm belongs to the ultra-high-level fusion alarm category.

[0034] When all three dimensions trigger alarms simultaneously, the final quantitative indicator for the alarm is calculated by multiplying the average weight of the alarm levels for each of the three dimensions by the non-linear weighting index for simultaneous alarms in all three dimensions, and then adding the weight of the highest-level alarm among the three dimensions. For example, if all three alarms are at the intermediate level, the final quantitative indicator for the fused alarm would be:

[0035] (Weight of intermediate alarm + weight of intermediate alarm + weight of intermediate alarm) / 3 * non-linear weight index when three dimensions alarm simultaneously + weight of intermediate alarm = (2 + 2 + 2) / 3 * 0.8 + 2 = 3.6. Since 3.6 is greater than 3, the alarm belongs to the ultra-high level fusion alarm.

[0036] As can be seen, in the traditional model, when multiple dimensions issue alarms simultaneously, only the independent alarm levels of each dimension are determined because a quantitative mechanism for non-linear risk growth is not adopted. Furthermore, there are no specific quantitative indicators for the independent alarm levels, making it difficult to intuitively discover the hidden risks. By adopting this method, by setting non-linear weight values ​​for simultaneous alarms of multiple dimensions and setting quantitative indicator ranges for each alarm level, it provides the possibility to deeply explore the mutual influence mechanism between alarms of various dimensions and finally present the quantitative results.

[0037] Within the above framework, the specific values ​​of the quantitative indicator range and weight can be adjusted by the user based on their operational experience to adapt to different types of batteries and operating conditions.

[0038] The second objective of this invention is to provide a safety status estimation device for lithium batteries in energy storage power stations based on multi-dimensional information fusion, the safety status estimation device comprising:

[0039] The acquisition module is used to collect multi-dimensional information, including: lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring image, lithium battery module surrounding temperature distribution, lithium battery module surrounding combustible gas concentration and lithium battery module surrounding smoke concentration.

[0040] The basic analysis module is used to analyze multi-dimensional information and determine whether to send an alarm. If not, it continuously listens for event messages. If an alarm is sent, it determines which level of the alarm (high, medium, or low) it belongs to before sending it to the fusion analysis module.

[0041] The fusion analysis module is used to receive alarm information, set the simultaneous alarm duration, the quantitative index range of the four-level fusion alarm, the weight of the basic alarm, and the non-linear weight of simultaneous alarms in each dimension; it determines whether alarm information from multiple dimensions is received simultaneously based on the set duration. If not, it switches to the basic alarm display module; if so, it calculates the fusion alarm quantitative index based on the set weight of the basic alarm and the non-linear weight value of simultaneous alarms in each dimension. Based on the fusion alarm quantitative index, it verifies the four-level fusion alarm (ultra-high, high, medium, and low), forming the alarm level and quantitative index, and then switches to the fusion alarm display module.

[0042] The basic alarm display module is used to display the original alarm information in three levels: low, medium, and high basic alarms.

[0043] The integrated alarm display module is used to integrate alarm information into four levels: low, medium, high, and extremely high, and simultaneously display the warning quantification number and the associated basic alarm information.

[0044] A third objective of this invention is to provide a computer device, including a processor and a memory for storing processor-executable programs, wherein when the processor executes the program stored in the memory, it implements the above-mentioned method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion.

[0045] The fourth objective of this invention is to provide a storage medium storing a program that, when executed by a processor, implements the aforementioned method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion.

[0046] The present invention has the following advantages and effects compared with the prior art:

[0047] (1) This invention addresses the objective law that security risks will increase non-linearly when alarm information of different dimensions occurs simultaneously. By defining the quantitative index range of alarms at all levels and defining the non-linear weight index when multiple dimensions alarm simultaneously, the objective phenomenon of non-linear increase in security risks when multiple dimensions alarm simultaneously is quantified. This helps to monitor key issues in engineering applications such as micro short circuits in lithium batteries and other minor alarms that occur simultaneously. It also makes it easier for maintenance personnel to discover the inherent high risk and extremely high risk of multiple external low-risk alarms in a timely manner and to judge the severity of the situation.

[0048] (2) After quantitative calculation, the quantitative indicators for multiple dimensions alarming at the same time are more likely to be significantly greater than the quantitative indicators for only a single dimension or a few dimensions alarming at the same time, which makes it easier for managers to focus on the main risks, quickly judge the overall safety status, and formulate emergency plans.

[0049] (3) While displaying the integrated alarm level and quantitative indicators, the associated basic alarm information is also displayed, which makes it easier for managers to quickly understand the origin of the integrated alarm and to make adjustments according to different battery conditions in the production environment. For example, if it is found that a certain lithium battery alarms in three dimensions at the same time, its safety risk is significantly greater than that of the other three dimensions alarming at the same time. The risk weight value of the three dimensions alarming at the same time can be increased, making the technology application closer to actual needs.

[0050] (4) Analysis of energy storage station accidents revealed that most accidents originated from negligence by management personnel. Before serious accidents occurred, multiple alarm messages of varying degrees and dimensions appeared within a sufficient time window for management personnel to react. A major reason for this negligence is that traditional alarm models do not provide clear and intuitive warnings of risks. For energy storage stations with tens of thousands of batteries, minor alarms from a single battery in multiple dimensions can easily be buried among insignificant alarm messages from other batteries in single dimensions. Therefore, quantifying alarms based on their physical characteristics allows management personnel to quickly focus on key risks, make rapid judgments, and respond urgently. Attached Figure Description

[0051] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0052] Figure 1 This is a flowchart of a method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion, as disclosed in this invention.

[0053] Figure 2 This is a structural block diagram of a lithium battery safety status estimation device for energy storage power stations based on multi-dimensional information fusion disclosed in Embodiment 2 of the present invention;

[0054] Figure 3 This is a structural block diagram of the computer device in Embodiment 3 of the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] Example 1

[0057] Considering the main aspects that cause lithium battery safety risks, the five main aspects for estimating the safety of lithium batteries in energy storage stations are: collecting lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring images, lithium battery module surrounding temperature distribution, lithium battery module surrounding flammable gas concentration, and lithium battery module surrounding smoke concentration.

[0058] Due to the complex internal physicochemical changes, the operation of energy storage lithium batteries exhibits very strong nonlinear characteristics, and their safety risks also show strong nonlinear characteristics. For example, a slight alarm in a single dimension generally does not pose a significant risk, but when multiple slight alarms in multiple dimensions occur simultaneously, it may indicate a very serious risk. Before a serious accident occurs, multiple alarms in multiple dimensions often occur within a relatively short period of time. Experimental studies on thermal runaway of lithium batteries have found that within a short period of time from the onset of an anomaly to the occurrence of thermal runaway, lithium batteries will experience multiple alarm phenomena, such as the detection of combustible gas, the detection of a significant temperature rise, the detection of a significant voltage change, smoke, and combustion and fire.

[0059] Traditional alarm models lack clear and intuitive risk warnings. For energy storage power stations with tens of thousands of batteries, minor alarms from a single battery across multiple dimensions can easily be buried under insignificant alarms from other batteries. Current management methods underutilize alarm information across various dimensions, typically displaying only a few alarm levels for each dimension. They fail to adequately utilize information from multiple simultaneous alarms, failing to fully explore the inherent risk implications of alarms and lacking quantifiable metrics, thus hindering a clear understanding of the actual operational risks of energy storage power stations.

[0060] Therefore, this embodiment proposes a method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion. The alarms are quantitatively displayed according to their physical characteristics, allowing managers to quickly focus on the main risks and make rapid judgments and emergency responses.

[0061] This embodiment tests a hard-shell lithium iron phosphate energy storage battery module commonly used in energy storage power stations. The module consists of 32 individual cells arranged in 4 parallel and 8 series. The rated voltage of each cell is 3.2V, and the rated capacity is 86Ah. The rated voltage of the module is 25.6V, the rated capacity is 344Ah, and the rated energy is 8.8kWh.

[0062] Assuming the battery remaining capacity estimation fails, overcharging begins at t=0s. The hard-shell lithium iron phosphate battery module is charged with a constant current of 172A at 0.5 times the charging current. At t=1060s, the opening of the battery module's pressure relief valve and a combustible gas signal are detected. At t=1782s, a significant increase in the temperature around the battery module is detected. At t=1894s, a significant abnormal change in the battery voltage is detected. At t=2000s, smoke is detected around the battery module. At t=2964s, combustion of the battery module is detected.

[0063] The basic alarms are divided into three levels: high, medium, and low. Detecting an open battery module pressure relief valve, detecting flammable gas signals around the battery module, detecting a significant rise in temperature around the battery module, and detecting a significant change in battery voltage are all signals that indicate a clear risk, but are not enough to directly and quickly cause a loss of control. Classifying these basic alarms as medium alarms is more reasonable. Detecting smoke around the battery module is a signal of impending loss of control, and detecting combustion of the battery module is a signal that the battery module is already out of control. Classifying these two basic alarms as high alarms is more reasonable.

[0064] The method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion, as proposed in this embodiment, is as follows:

[0065] S1. Data collection steps: Collect multi-dimensional information, including: lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring image, lithium battery module surrounding temperature distribution, lithium battery module surrounding combustible gas concentration and lithium battery module surrounding smoke concentration.

[0066] S2. Basic analysis steps: Analyze multi-dimensional information to determine whether to send an alarm. If not, continue to listen for event messages. If an alarm is sent, determine which level (high, medium, or low) the alarm belongs to before sending it.

[0067] S3. Fusion Analysis Steps: Upon receiving alarm information, set the simultaneous alarm duration, the quantitative index range of the four-level fusion alarm, the weight of the basic alarm, and the nonlinear weight of simultaneous alarms in each dimension; determine whether alarm information from multiple dimensions is received simultaneously based on the set duration. If not, proceed to step S4; if so, calculate the fusion alarm quantitative index based on the set weight of the basic alarm and the nonlinear weight value of simultaneous alarms in each dimension. Verify the four-level fusion alarm (ultra-high, high, medium, and low) based on the fusion alarm quantitative index to form the alarm level and quantitative index, and proceed to step S5.

[0068] S4. Basic alarm display steps: Display the original alarm information as low, medium and high basic alarms;

[0069] S5. Integrated Alarm Display Steps: Display alarm information in four levels: low, medium, high, and extra-high, and simultaneously show the warning quantification number and associated basic alarm information.

[0070] The above alarm signals all occur within a 50-minute interval, constituting simultaneous alarms. Based on the weight settings for basic alarms, the non-linear weight index for multi-dimensional simultaneous alarms, and the range setting for fused alarm levels, the fused alarm levels and quantitative indicators displayed at each time point are calculated as shown in Table 1 below:

[0071] Table 1. Fusion alarm levels and quantitative indicators displayed at various time points in Example 1

[0072]

[0073]

[0074] As can be seen, at t=1060s, the alarm is displayed as an advanced fusion alarm with a quantification index of 2.8. At t=1728, the alarm is upgraded to an extra-advanced fusion alarm with a quantification index of 3.6. Subsequently, at t=1894, t=2000, and t=2964, while maintaining the extra-advanced fusion alarm status, the quantification index steadily increases to 10.68. Compared to the independent basic alarm levels for each dimension, the fusion alarm of this method has the ability to fully reflect the complex correlations between alarms of various dimensions, and can accurately, intuitively, and quickly display the risks of lithium batteries in energy storage power stations.

[0075] Example 2

[0076] This embodiment continues the experiment on the soft-pack lithium iron phosphate energy storage battery module commonly used in energy storage power stations. The battery module consists of 72 soft-pack individual cells in 6 parallel and 12 series configurations. The rated voltage of each individual cell is 3.2V and the rated capacity is 48Ah. The rated voltage of the module is 38.4V, the rated capacity is 288Ah, and the rated capacity is 11.1kWh.

[0077] Assuming the battery remaining capacity estimation fails, overcharging begins at t=0s. The soft-pack lithium iron phosphate battery module is charged with a constant current of 144A at 0.5 times the charging current. At t=705s, a significant increase in temperature around the battery module is detected. At t=1463s, an increase in the solubility of combustible gas around the battery module is detected, and the left side of the battery module's sealed structure cracks. At t=1741s, smoke is detected around the battery module. At t=2016s, an abnormal change in battery voltage is detected. At t=2319s, the battery module is detected to be burning.

[0078] The basic alarms are divided into three levels: high, medium, and low. Detecting an open battery module pressure relief valve, detecting flammable gas signals around the battery module, detecting a significant temperature rise around the battery module, and detecting a closed structure of the battery module are all signals that indicate a clear risk, but are not enough to directly and quickly cause a loss of control. Classifying these basic alarms as medium alarms is more reasonable. Detecting rapid changes in battery voltage and smoke around the battery module are signals that a loss of control is imminent, while detecting battery module combustion is a signal that the battery module has already lost control. Classifying these three basic alarms as high alarms is more reasonable.

[0079] According to the calculation method in this patent, the time intervals of the alarm signals mentioned above are all within 50 minutes, which constitutes simultaneous alarms. Based on the weight settings of the basic alarms, the nonlinear weight index for multi-dimensional simultaneous alarms, and the range settings of the fused alarm level, the fused alarm level and quantitative indicators displayed at each time point are calculated as follows:

[0080] Table 2. Fusion alarm levels and quantitative indicators displayed at various time points in Example 2

[0081]

[0082]

[0083] As can be seen, at t=1463s, the alarm is displayed as a high-level fusion alarm with a quantification index of 3.6. Subsequently, at t=1741, t=2016, and t=2319, while maintaining the high-level fusion alarm status, the quantification index steadily increases to 11.32. Compared to the independent basic alarm levels of each dimension, the fusion alarm of this method has the ability to fully reflect the complex correlation between alarms of various dimensions, and can accurately, intuitively, and quickly display the risks of lithium batteries in energy storage power stations.

[0084] Example 3

[0085] like Figure 2 As shown in the figure, this embodiment provides a lithium battery safety status estimation device for energy storage power stations. The device includes a data acquisition module 201, a basic analysis module 202, a fusion analysis module 203, a basic alarm display module 204, and a fusion alarm display module 205. The specific functions of each module are as follows:

[0086] The acquisition module 201 is used to acquire multi-dimensional information, including: lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring image, lithium battery module surrounding temperature distribution, lithium battery module surrounding combustible gas concentration and lithium battery module surrounding smoke concentration.

[0087] The basic analysis module 202 is used to analyze multi-dimensional information and determine whether to send an alarm. If not, it continuously listens for event messages. If an alarm is sent, it determines which level of the alarm (high, medium, or low) it belongs to before sending it to the fusion analysis module.

[0088] The fusion analysis module 203 is used to receive alarm information, set the simultaneous alarm duration, the quantitative index range of the four-level fusion alarm, the weight of the basic alarm, and the nonlinear weight of simultaneous alarms in each dimension; determine whether alarm information from multiple dimensions is received simultaneously based on the set duration; if not, transfer to the basic alarm display module; if so, calculate the fusion alarm quantitative index based on the set weight of the basic alarm and the nonlinear weight value of simultaneous alarms in each dimension; verify the four-level fusion alarm (ultra-high, high, medium, and low) based on the fusion alarm quantitative index, form the alarm level and quantitative index, and transfer to the fusion alarm display module.

[0089] The basic alarm display module 204 is used to display the original alarm information in three levels: low, medium and high basic alarms.

[0090] The integrated alarm display module 205 is used to integrate alarm information into four levels: low, medium, high, and extremely high, and simultaneously display the warning quantification number and the associated basic alarm information.

[0091] The specific implementation of each module in this embodiment can be found in Embodiment 1 above, and will not be repeated here. It should be noted that the device provided in this embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0092] Example 4

[0093] This embodiment provides a computer device, which can be a computer, such as... Figure 3 As shown, the system is connected via a system bus 301 to a processor 302, a memory, an input device 303, a display 304, and a network interface 305. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium 306 and internal memory 307. The non-volatile storage medium 306 stores the operating system, computer programs, and a database. The internal memory 307 provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. When the processor 302 executes the computer programs stored in the memory, it implements the method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion proposed in Embodiment 1 above. The process is as follows:

[0094] S1. Data collection steps: Collect multi-dimensional information, including: lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring image, lithium battery module surrounding temperature distribution, lithium battery module surrounding combustible gas concentration and lithium battery module surrounding smoke concentration.

[0095] S2. Basic analysis steps: Analyze multi-dimensional information to determine whether to send an alarm. If not, continue to listen for event messages. If an alarm is sent, determine which level (high, medium, or low) the alarm belongs to before sending it.

[0096] S3. Fusion Analysis Steps: Upon receiving alarm information, set the simultaneous alarm duration, the quantitative index range of the four-level fusion alarm, the weight of the basic alarm, and the nonlinear weight of simultaneous alarms in each dimension; determine whether alarm information from multiple dimensions is received simultaneously based on the set duration. If not, proceed to step S4; if so, calculate the fusion alarm quantitative index based on the set weight of the basic alarm and the nonlinear weight value of simultaneous alarms in each dimension. Verify the four-level fusion alarm (ultra-high, high, medium, and low) based on the fusion alarm quantitative index to form the alarm level and quantitative index, and proceed to step S5.

[0097] S4. Basic alarm display steps: Display the original alarm information as low, medium and high basic alarms;

[0098] S5. Integrated Alarm Display Steps: Display alarm information in four levels: low, medium, high, and extra-high, and simultaneously show the warning quantification number and associated basic alarm information.

[0099] Example 5

[0100] This embodiment provides a storage medium, which is a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion proposed in Embodiment 1 above. The process is as follows:

[0101] S1. Data collection steps: Collect multi-dimensional information, including: lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring image, lithium battery module surrounding temperature distribution, lithium battery module surrounding combustible gas concentration and lithium battery module surrounding smoke concentration.

[0102] S2. Basic analysis steps: Analyze multi-dimensional information to determine whether to send an alarm. If not, continue to listen for event messages. If an alarm is sent, determine which level (high, medium, or low) the alarm belongs to before sending it.

[0103] S3. Fusion Analysis Steps: Upon receiving alarm information, set the simultaneous alarm duration, the quantitative index range of the four-level fusion alarm, the weight of the basic alarm, and the nonlinear weight of simultaneous alarms in each dimension; determine whether alarm information from multiple dimensions is received simultaneously based on the set duration. If not, proceed to step S4; if so, calculate the fusion alarm quantitative index based on the set weight of the basic alarm and the nonlinear weight value of simultaneous alarms in each dimension. Verify the four-level fusion alarm (ultra-high, high, medium, and low) based on the fusion alarm quantitative index to form the alarm level and quantitative index, and proceed to step S5.

[0104] S4. Basic alarm display steps: Display the original alarm information as low, medium and high basic alarms;

[0105] S5. Integrated Alarm Display Steps: Display alarm information in four levels: low, medium, high, and extra-high, and simultaneously show the warning quantification number and associated basic alarm information.

[0106] The storage medium described in this embodiment can be a disk, optical disk, computer memory, random access memory (RAM), USB flash drive, portable hard drive, etc.

[0107] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

Claims

1. A method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion, characterized in that, The method for estimating the safety status of lithium batteries in the energy storage power station includes: S1. Data collection steps: Collect multi-dimensional information, including: lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring image, lithium battery module surrounding temperature distribution, lithium battery module surrounding combustible gas concentration and lithium battery module surrounding smoke concentration. S2. Basic analysis steps: Analyze multi-dimensional information to determine whether to send an alarm. If not, continue to listen for event messages. If an alarm is sent, determine which level (high, medium, or low) the alarm belongs to before sending it. S3. Fusion Analysis Steps: Upon receiving alarm information, set the simultaneous alarm duration, the quantitative index range for the four-level fusion alarm, the weight of the basic alarm, and the non-linear weight of simultaneous alarms in each dimension; determine whether alarm information from multiple dimensions is received simultaneously based on the set duration. If not, proceed to step S4; if so, calculate the fusion alarm quantitative index based on the set weight of the basic alarm and the non-linear weight values ​​of simultaneous alarms in each dimension. Verify the four-level fusion alarm (ultra-high, high, medium, and low) based on the fusion alarm quantitative index, forming the fusion alarm level and quantitative index, and proceed to step S5; the specific process is as follows: S31. Receive alarm information for abnormal state inside lithium battery, alarm information for abnormal shape of lithium battery module, alarm information for abnormal temperature around lithium battery module, alarm information for excessive concentration of combustible gas around lithium battery module, alarm information for excessive smoke concentration around lithium battery module, and set the duration of simultaneous alarms, the quantitative index range of four-level fusion alarms, the weight of basic alarms, and the nonlinear weight of simultaneous alarms in each dimension. S32. Determine whether multiple alarm messages from multiple dimensions are received simultaneously based on the set alarm duration. If not, proceed to step S4. If yes, that is, when two or more dimensions alarm simultaneously, multiply the average weight of the alarm levels of the two or more dimensions by the non-linear weight index when the corresponding dimensions alarm simultaneously, and add the weight of the higher-level alarm in each dimension alarm. The resulting number is used as the final quantitative index of the fused alarm. Proceed to step S5. S4. Basic alarm display steps: Display the original alarm information as low, medium and high basic alarms; S5. Integrated Alarm Display Steps: Display alarm information in four levels: low, medium, high, and extra-high, and simultaneously show the warning quantification number and associated basic alarm information.

2. The method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion according to claim 1, characterized in that, The process of step S1 is as follows: S11. Collect the temperature, current, and voltage of the lithium battery terminals using a lithium battery terminal temperature, current, and voltage acquisition instrument; S12. Acquire monitoring images of the lithium battery module's appearance using a visible light acquisition instrument; S13. Collect the temperature distribution around the lithium battery module using an infrared light collector; S14. Collect the concentration of combustible gas around the lithium battery module using a combustible gas collector; S15. Collect the smoke concentration around the lithium battery module using a smoke collector.

3. The method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion according to claim 1, characterized in that, The process of step S2 is as follows: S21. Analyze the temperature, current, and voltage of the lithium battery terminals to determine whether an alarm should be output. If not, continue listening for event messages. If an alarm is sent, determine which of the three levels (high, medium, or low) the alarm belongs to before sending it. S22. Analyze the appearance monitoring image of the lithium battery module to determine whether an alarm is output and the corresponding alarm level. If not, continue to listen for event messages. If an alarm is sent, determine which level of the three levels (high, medium, and low) the alarm belongs to before sending it. S23. Analyze the infrared temperature measurement data around the lithium battery module to determine whether to output an alarm and the corresponding alarm level. If not, continue to listen for event messages. If an alarm is sent, determine which of the three levels (high, medium, or low) the alarm belongs to before sending it. S24. Analyze the concentration of combustible gas around the lithium battery module to determine whether to output an alarm and the corresponding alarm level. If not, continue to listen for event messages. If an alarm is sent, determine which of the three levels (high, medium, or low) the alarm belongs to before sending it. S25. Analyze the smoke concentration around the lithium battery module to determine whether to output an alarm and the corresponding alarm level. If not, continue to listen for event messages. If an alarm is sent, determine which of the three levels (high, medium, or low) the alarm belongs to before sending it.

4. The method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion according to claim 1, characterized in that, The process of step S31 is as follows: S311. Set the duration of simultaneous alarms. The initial value is set to 50 minutes, and the user can adjust it flexibly according to the power plant's operation and maintenance experience. S312. Set the quantitative indicator range for the four-level fusion alarm, the weight of the basic alarm, and the non-linear weight of simultaneous alarms in each dimension, as follows: The fusion analysis sets up a four-level fusion alarm, divided into ultra-high, high, medium, and low levels. The quantitative index ranges for the four levels are set to [3, +∞), [2, 3), [1, 2), and [0, 1), respectively. The weights of the three basic alarm levels (high, medium, and low) are set to 3, 2, and 1, respectively. When two dimensions alarm simultaneously, the non-linear weight index is set to 0.4; when three dimensions alarm simultaneously, the non-linear weight index is set to 0.8; when four dimensions alarm simultaneously, the non-linear weight index is set to 1.6; and when five dimensions alarm simultaneously, the non-linear weight index is set to 3.

2.

5. A safety state estimation device based on the multi-dimensional information fusion-based safety state estimation method for lithium batteries in energy storage power stations as described in any one of claims 1 to 4, characterized in that, The security status estimation device includes: The acquisition module is used to collect multi-dimensional information, including: lithium battery terminal temperature, current, voltage, lithium battery module appearance monitoring image, lithium battery module surrounding temperature distribution, lithium battery module surrounding combustible gas concentration and lithium battery module surrounding smoke concentration. The basic analysis module is used to analyze multi-dimensional information and determine whether to send an alarm. If not, it continuously listens for event messages. If an alarm is sent, it determines which level of the alarm (high, medium, or low) it belongs to before sending it to the fusion analysis module. The fusion analysis module is used to receive alarm information, set the simultaneous alarm duration, the quantitative index range of the four-level fusion alarm, the weight of the basic alarm, and the non-linear weight of simultaneous alarms in each dimension; it determines whether alarm information from multiple dimensions is received simultaneously based on the set duration. If not, it switches to the basic alarm display module; if so, it calculates the fusion alarm quantitative index based on the set weight of the basic alarm and the non-linear weight value of simultaneous alarms in each dimension. Based on the fusion alarm quantitative index, it verifies the four-level fusion alarm (ultra-high, high, medium, and low), forming the alarm level and quantitative index, and then switches to the fusion alarm display module. The basic alarm display module is used to display the original alarm information in three levels: low, medium, and high basic alarms. The integrated alarm display module is used to integrate alarm information into four levels: low, medium, high, and extremely high, and simultaneously display the warning quantification number and the associated basic alarm information.

6. A computer device comprising a processor and a memory for storing a processor-executable program, characterized in that, When the processor executes the program stored in the memory, it implements the method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion as described in any one of claims 1-4.

7. A storage medium storing a program, characterized in that, When the program is executed by the processor, it implements the method for estimating the safety status of lithium batteries in energy storage power stations based on multi-dimensional information fusion as described in any one of claims 1-4.

Images