Battery pressure prediction method and device, electronic equipment, storage medium and product

Abstract

The embodiment of the invention discloses a battery pressure prediction method and device, electronic equipment, a storage medium and a product. The method comprises the following steps: acquiring operation condition data corresponding to a to-be-detected battery at a current moment; according to the operation condition data and an aggregation concentration prediction model, predicting an intrinsic gas aggregation concentration value of the to-be-detected battery at the current moment; and determining a battery pressure value of the to-be-detected battery at the current moment according to the corresponding intrinsic gas gathering concentration value of the to-be-detected battery at the current moment so as to perform valve opening risk assessment on the to-be-detected battery according to the battery pressure value. According to the technical scheme, the intrinsic gas gathering concentration value capable of representing the comprehensive effect of gas production and physical expansion of the battery can be accurately predicted only through the basic operation condition data of the battery without depending on special detection hardware, and then the effect of deducing the real pressure value in the battery is achieved.

Description

Technical Field

[0001] This disclosure relates to the field of battery thermal safety technology, and in particular to a battery pressure prediction method, apparatus, electronic device, storage medium, and product. Background Technology

[0002] Currently, batteries are widely used in energy storage and power fields. As the energy density of batteries gradually increases, the energy released after thermal runaway is also becoming increasingly scarce, which can easily lead to serious consequences.

[0003] In related technologies, the detection method for battery thermal runaway typically involves detecting the characteristic gases generated after thermal runaway to determine whether thermal runaway has occurred. However, batteries are often stored in relatively enclosed spaces, causing the characteristic gases to accumulate and their concentration to surge, easily exceeding the detector's range limit. This makes it impossible to effectively determine whether the battery thermal runaway will continue to worsen, and the decision to implement a thermal runaway early warning scheme can only be made based on empirical data. Consequently, the timeliness and accuracy of monitoring the battery thermal runaway state are poor, resulting in inaccurate thermal runaway early warning. Summary of the Invention

[0004] This invention provides a battery pressure prediction method, device, electronic device, storage medium, and product, which can accurately predict the intrinsic gas accumulation concentration value that characterizes the combined effect of battery gas production and physical expansion using only basic battery operating condition data without relying on dedicated detection hardware, and thus derive the true internal pressure value of the battery.

[0005] According to one aspect of the present invention, a battery pressure prediction method is provided, the method comprising: Acquire the operating condition data corresponding to the battery under test at the current moment; wherein, the operating condition data includes at least one of the following: current value, state of charge value, and battery temperature value; Based on the operating condition data and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment is predicted; wherein, the intrinsic gas accumulation concentration value is used to characterize the gas accumulation state inside the battery under test at the current moment; the gas accumulation state is determined by at least one of the gas generation reaction and physical expansion of the battery under test; Based on the intrinsic gas concentration value of the battery under test at the current time, the battery pressure value of the battery under test at the current time is determined, so as to conduct a valve opening risk assessment of the battery under test based on the battery pressure value.

[0006] According to another aspect of the present invention, a battery pressure prediction device is provided, the device comprising: The data acquisition module is used to acquire the operating condition data corresponding to the battery under test at the current moment; wherein, the operating condition data includes at least one of the following: current value, state of charge value, and battery temperature value; An accumulation concentration prediction module is used to predict the intrinsic gas accumulation concentration value of the battery under test at the current moment based on the operating condition data and the accumulation concentration prediction model; wherein, the intrinsic gas accumulation concentration value is used to characterize the gas accumulation state inside the battery under test at the current moment; the gas accumulation state is determined by at least one of the gas generation reaction and physical expansion of the battery under test. The battery pressure prediction module is used to determine the battery pressure value of the battery under test at the current time based on the intrinsic gas accumulation concentration value corresponding to the battery under test at the current time, so as to perform valve opening risk assessment on the battery under test based on the battery pressure value.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: One or more processors; Storage device for storing one or more programs. When one or more programs are executed by one or more processors, the one or more processors implement a battery pressure prediction method as described in any of the embodiments of this disclosure.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement any of the battery pressure prediction methods of the present invention.

[0009] According to another aspect of the present disclosure, a computer program product is provided, which, when executed by a processor, implements a battery pressure prediction method as described in any of the embodiments of the present disclosure.

[0010] The technical solution of this disclosure provides accurate and readily available input data for subsequent concentration and pressure prediction by acquiring the operating condition data of the battery under test at the current moment, eliminating the need for dedicated detection hardware and reducing implementation costs. Furthermore, by using the operating condition data and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment is predicted, accurately eliminating apparent interference and truly representing the essential state of gas accumulation resulting from the combined effects of battery gas production and physical expansion. Furthermore, by determining the battery pressure value of the battery under test at the current moment based on the intrinsic gas accumulation concentration value, the valve opening risk assessment of the battery under test is performed based on the battery pressure value, fundamentally avoiding pressure misjudgment, improving the accuracy and scientific nature of battery valve opening risk assessment, and ensuring battery safety. The technical solution of this disclosure solves the problems of poor timeliness and accuracy in monitoring battery thermal runaway and poor accuracy in thermal runaway early warning in related technologies. It realizes that it can accurately predict the intrinsic gas accumulation concentration value that can characterize the combined effect of battery gas production and physical expansion based solely on the battery's basic operating condition data without relying on dedicated detection hardware, and then derive the actual internal pressure value of the battery. This significantly improves the timeliness and accuracy of valve opening risk monitoring before battery thermal runaway, effectively improves the accuracy of thermal runaway early warning, and ensures battery safety.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A schematic flowchart illustrating a battery pressure prediction method provided in an embodiment of this disclosure; Figure 2 A schematic flowchart of another battery pressure prediction method provided in this embodiment of the disclosure; Figure 3 A schematic flowchart of another battery pressure prediction method provided in this embodiment of the disclosure; Figure 4 This is a schematic diagram of the structure of a battery pressure prediction device provided in an embodiment of the present disclosure; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0017] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0018] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0019] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0020] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0021] With the rapid development of the new energy industry, the safety of power batteries, as the core power source, has become a key issue for the industry's development. During normal operating conditions such as charging, discharging, and resting, power batteries are prone to generating gas due to electrolyte decomposition and electrode side reactions. Gas accumulation can lead to increased internal pressure and casing expansion. If this is not detected and warned of in a timely manner, it can easily trigger safety valve opening, battery bulging, or even thermal runaway, seriously threatening the safety of the entire vehicle and the user. In related technologies, monitoring technologies for gas generation pressure in power batteries mostly rely on the fusion of measured data from multiple types of sensors, including gas, pressure, temperature, and sound. This not only results in high hardware procurement and maintenance costs but also suffers from the problem that monitoring indicators are easily affected by factors such as ambient temperature and dynamic volume deformation of the battery, making it difficult to capture the essential state of gas generation. Furthermore, traditional technologies often focus on the real-time passive judgment of extreme thermal runaway faults, lacking the ability to accurately calculate and predict the trend of gas generation pressure accumulation under normal operating conditions. This makes it impossible to intervene in safety risks in advance, and the technologies have poor versatility for different types of power batteries, making it difficult to adapt to the actual application needs of automotive power batteries with high-frequency switching of operating conditions and complex and variable operating environments.

[0022] To address the aforementioned issues, the technical solution provided in this disclosure can be adopted. This involves collecting battery operating condition data to predict the intrinsic gas concentration within the battery, and then predicting the internal pressure based on the predicted intrinsic gas concentration. Furthermore, a valve opening risk assessment can be performed on the battery based on the predicted battery pressure. This achieves the goal of accurately predicting the intrinsic gas concentration, which characterizes the combined effects of gas generation and physical expansion, using only basic battery operating condition data, without relying on dedicated detection hardware. This allows for the derivation of the actual internal pressure of the battery, significantly improving the timeliness and accuracy of valve opening risk monitoring before thermal runaway, effectively enhancing the accuracy of thermal runaway early warning, and ensuring battery safety.

[0023] Figure 1 This is a flowchart illustrating a battery pressure prediction method provided in an embodiment of this disclosure. This embodiment is applicable to situations where battery pressure is predicted based on battery operating condition data. The method can be executed by a battery pressure prediction device, which can be implemented in hardware and / or software and can be configured in electronic devices such as computers or servers. Figure 1 As shown, the method in this embodiment includes: S110. Obtain the operating condition data corresponding to the battery under test at the current moment.

[0024] The battery under test can be a power battery whose gas production pressure and valve opening risk are being tested and evaluated. The battery under test can be used to power vehicles, such as automotive lithium-ion power batteries; or it can be used to power home smart devices, such as the lithium-ion cells inside a robotic vacuum cleaner; or it can be used to power power systems and communication energy storage. It can be understood that the battery under test can encompass power battery cells, battery modules, or battery packs in any operating state, such as charging / discharging or resting. The current time can be any specific point in time, serving as the time reference for collecting operating condition data, predicting intrinsic gas accumulation concentration, and determining battery pressure. The calculation / prediction results of each step are aligned to this time point to ensure the uniqueness and consistency of the timeline. Operating condition data can be understood as the physical parameters that characterize the actual operating state of the battery under test at the current time. That is, operating condition data can be used to characterize the operating state of the battery under test at the current time. Operating condition data can include various parameters characterizing the battery's operating state, optionally including at least one of current value, state of charge value, and battery temperature value. The current value can be the measured charging and discharging current of the battery under test at the current moment, usually in amperes. It can be understood that the current value serves as a criterion for distinguishing whether the battery under test is in a charging / discharging state (current value ≠ 0) or a static state (current value = 0), directly affecting the rate and increment of gas generation reactions. The State of Charge (SOC) value can be the percentage of the remaining charge of the battery under test relative to its rated capacity at the current moment (ranging from 0% to 100%), a parameter characterizing the battery's charge level. The SOC value directly affects the intensity of gas generation reactions such as electrolyte decomposition and electrode side reactions. The battery temperature value can be the measured temperature of the battery under test at the current moment, including physical quantities reflecting the actual operating temperature of the battery, such as the battery cell temperature and the ambient temperature of the battery pack. It is a core factor affecting the gas generation reaction rate and the fluctuation of the displayed pressure.

[0025] In one implementation, sensors for collecting operational data can be pre-configured for the battery under test. Furthermore, during the application of the battery under test, operational data can be collected according to a preset collection cycle. Thus, operational data of the battery under test at the current moment can be obtained.

[0026] S120. Based on the operating condition data and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment is predicted.

[0027] The accumulation concentration prediction model can be understood as a pre-constructed parameterized model used to predict the intrinsic gas accumulation concentration value of the battery under test. The accumulation concentration prediction model takes operating condition data as input, processes the operating condition data based on the physicochemical mechanism of gas production in the power battery and the operating condition time-series logic, and outputs the predicted intrinsic gas accumulation concentration value of the battery under test at the current moment. In other words, the accumulation concentration prediction model can be a parameterized calculation model constructed based on the physicochemical mechanism of gas production in the power battery and the operating condition time-series logic. The intrinsic gas accumulation concentration value can be understood as a predefined core state parameter, which refers to the amount of gaseous substance per unit volume inside the battery under test at the current moment. The intrinsic gas accumulation concentration value can be used to determine the gas accumulation state inside the battery under test at the current moment. The intrinsic gas accumulation concentration value can be jointly determined by the total amount of gas produced by the gas production reaction of the battery under test and the internal dynamic free volume change caused by the physical expansion of the battery under test. The gas accumulation state can be understood as the actual state of the battery under test under the combined effect of the gas production reaction and the physical expansion effect, and is a comprehensive characterization of the gas production results inside the battery under test. In other words, the intrinsic gas concentration value can be used to characterize the overall gas state inside the battery under test at the current moment, carrying dual information about the total amount of gas produced by the gas-generating reaction and the battery volume change due to physical expansion. The gas-generating reaction can be understood as the process by which the battery under test generates gas due to physicochemical changes such as electrolyte decomposition, electrode material side reactions, and electrolyte interface film rupture / regeneration under charge / discharge or resting conditions; it is the source of gas generation inside the battery. The reaction rate of the gas-generating reaction can be determined by operating parameters such as current value, state of charge value, and battery temperature value. Physical expansion can be understood as the dynamic automatic volume change inside the battery under test caused by lithium insertion / extraction from electrode materials, electrolyte volume changes, and micro-deformation of the battery casing during charge / discharge, temperature changes, and aging processes; it is the core physical factor affecting the degree of gas accumulation inside the battery. Physical expansion changes the gas distribution space inside the battery under test; even if the total amount of gas produced remains unchanged, physical expansion will directly lead to a change in the gas accumulation state.

[0028] It should be noted that the "intrinsic gas accumulation concentration" proposed in this embodiment is different from the "gas concentration" in the prior art. The intrinsic gas accumulation concentration can be an intrinsic state parameter derived from the ideal gas equation, not a sensor measurement value. Instead, it is a comprehensive quantitative index that integrates the battery gas generation reaction and the physical expansion effect. It can effectively isolate apparent interferences such as temperature and battery dynamic free volume changes, accurately characterize the essential state of gas accumulation inside the battery, without distinguishing the type of characteristic gas or relying on a gas sensor. In contrast, the gas concentration in the prior art is mostly the actual content value of specific characteristic gases such as VOC and CO inside the battery, which is an independent conventional monitoring physical quantity. It does not consider the influence of temperature and battery physical state changes, cannot reflect the true state of gas accumulation under the combined effect of gas generation and physical expansion, and requires dedicated gas detection hardware. It can only characterize the content of one or more characteristic gases and cannot reflect the overall level of gas generation inside the battery.

[0029] In practical applications, battery pressure testing typically relies on sensor-measured gas concentration and / or displayed pressure to determine the internal pressure. However, this method is susceptible to distortion due to factors such as battery temperature coupling and dynamic physical expansion. Furthermore, it requires specialized gas sensors, resulting in high hardware costs and significant complexity. Additionally, the apparent values ​​of gas concentration and displayed pressure measured by sensors are affected by external / internal factors like battery temperature and physical expansion. Relying solely on these values ​​fails to isolate the true state of gas production within the battery and accurately reflect its internal pressure level. For example, during charging and discharging, the battery undergoes physical expansion, increasing the space for gas. Even if the total gas production remains constant, the measured gas concentration will decrease due to the increased volume. This lower apparent gas concentration fails to reflect the underlying state of "unchanged total gas production."

[0030] To address the above issues, this embodiment predefines a state parameter, namely the intrinsic gas accumulation concentration, to characterize the gas accumulation concentration inside the battery under test under the combined effects of gas generation reaction and physical expansion. Furthermore, given the collected operating condition data of the battery under test at the current moment, an accumulation concentration prediction model is used to process the operating condition data to predict the intrinsic gas accumulation concentration value of the battery under test at the current moment. Moreover, using the intrinsic gas accumulation concentration value to predict the internal pressure of the battery can eliminate the interference of apparent values ​​such as temperature and dynamic physical expansion of the battery, accurately capturing the essential state of gas generation in the battery, thereby achieving accurate prediction of the true internal pressure of the battery. This provides a reliable basis for valve opening risk assessment, while eliminating the need for dedicated hardware such as gas sensors, reducing detection costs and implementation difficulty.

[0031] In one implementation, the acquired operating condition data of the battery under test at the current moment can be input into the accumulation concentration prediction model. The accumulation concentration prediction model can then directly process the operating condition data to obtain the output intrinsic gas accumulation concentration value.

[0032] In another implementation, the acquired operating condition data of the battery under test at the current moment can be input into the accumulation concentration prediction model, and the operating condition of the battery under test at the current moment can be determined based on the current value in the operating condition data. Further, based on the operating condition, the operating condition data, and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment can be determined.

[0033] S130. Based on the intrinsic gas concentration value of the battery under test at the current moment, determine the battery pressure value of the battery under test at the current moment, and conduct a valve opening risk assessment of the battery under test based on the battery pressure value.

[0034] The battery pressure value can be understood as the absolute internal pressure of the battery under test at the current moment. It is a core value that truly reflects the actual level of gas pressure inside the battery. Unlike the pressure value directly measured by the sensor, the battery pressure value in this embodiment is free from the interference of apparent factors such as battery temperature and dynamic physical expansion on the measured pressure. It can accurately and truly reflect the actual level of gas pressure inside the battery, providing an objective and reliable core basis for assessing the valve opening risk of the battery under test. This fundamentally avoids risk misjudgment (false alarm / missed alarm) caused by apparent pressure distortion, greatly improving the accuracy and scientific nature of valve opening risk assessment. At the same time, the battery pressure value is derived from the model, eliminating the need for additional correction to the sensor's measured pressure, thus simplifying the pressure calculation and risk assessment process.

[0035] In this embodiment, the battery pressure value of the battery under test at the current moment can be determined based on at least one of the following methods: processing the intrinsic gas accumulation concentration value using a battery pressure prediction model to obtain the battery pressure value of the battery under test at the current moment; or processing the intrinsic gas accumulation concentration value using a battery pressure calculation formula to obtain the battery pressure value of the battery under test at the current moment. One of these determination methods will be explained in detail below.

[0036] Optionally, the battery pressure value of the battery under test at the current moment is determined based on the intrinsic gas accumulation concentration value of the battery under test at the current moment, including: determining the product between the intrinsic gas accumulation concentration value, the battery temperature value, and a preset constant to obtain the battery pressure value of the battery under test at the current moment.

[0037] The preset constant can be understood as a fixed value predetermined based on the ideal gas law, specifically a universal gas constant. This constant is a universally recognized fixed value in the field of physics and does not change with different scenarios. The preset constant can serve as a quantitative bridge connecting the intrinsic gas concentration value and the battery pressure value, without needing to be adjusted according to changes in battery model or operating conditions.

[0038] In one embodiment, given the intrinsic gas concentration value of the battery under test at the current moment, the product of the intrinsic gas concentration value, the battery temperature value of the battery under test at the current moment, and a preset constant can be determined, and the obtained product can be determined as the battery pressure value of the battery under test at the current moment.

[0039] For example, the battery pressure value can be determined based on the following formula: ;in, Indicates the time of the battery under test. Battery pressure value; Indicates the time of the battery under test. The intrinsic gas concentration value is below; Indicates a preset constant; Indicates the time of the battery under test. Battery temperature value; Indicates multiplication.

[0040] In this embodiment, after obtaining the battery pressure value of the battery under test at the current moment, the battery pressure value can be compared with a preset valve opening pressure threshold. Furthermore, if the battery pressure value is not less than the preset valve opening pressure threshold, it can be determined that the battery under test has a valve opening risk. Further, a warning signal or intervention control strategy can be sent. Alternatively, if the battery pressure value of the battery under test at the current moment is less than the preset valve opening pressure threshold, it can be determined that the battery under test does not have a valve opening risk, and the battery under test continues to collect operating condition data, predict intrinsic gas concentration, and predict battery pressure value until a preset pressure prediction stop condition is reached. The pressure prediction stop condition may include at least one of the following: determining that the battery under test has a valve opening risk; reaching a preset pressure detection time for the battery under test; or reaching a preset SOD threshold (depleted charge) for the battery under test.

[0041] The technical solution of this disclosure provides accurate and readily available input data for subsequent concentration and pressure prediction by acquiring the operating condition data of the battery under test at the current moment, eliminating the need for dedicated detection hardware and reducing implementation costs. Furthermore, by using the operating condition data and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment is predicted, accurately eliminating apparent interference and truly representing the essential state of gas accumulation resulting from the combined effects of battery gas production and physical expansion. Furthermore, by determining the battery pressure value of the battery under test at the current moment based on the intrinsic gas accumulation concentration value, the valve opening risk assessment of the battery under test is performed based on the battery pressure value, fundamentally avoiding pressure misjudgment, improving the accuracy and scientific nature of battery valve opening risk assessment, and ensuring battery safety. The technical solution of this disclosure solves the problems of poor timeliness and accuracy in monitoring battery thermal runaway and poor accuracy in thermal runaway early warning in related technologies. It realizes that it can accurately predict the intrinsic gas accumulation concentration value that can characterize the combined effect of battery gas production and physical expansion based solely on the battery's basic operating condition data without relying on dedicated detection hardware, and then derive the actual internal pressure value of the battery. This significantly improves the timeliness and accuracy of valve opening risk monitoring before battery thermal runaway, effectively improves the accuracy of thermal runaway early warning, and ensures battery safety.

[0042] Figure 2 This is a schematic flowchart illustrating another battery pressure prediction method provided in this embodiment. The technical solution of this embodiment can be combined with other embodiments; for the same or related parts, they can be described in conjunction with the descriptions of other embodiments, and will not be repeated here. Figure 2 As shown, the method in this embodiment may specifically include: S210. Obtain the operating condition data corresponding to the battery under test at the current moment.

[0043] S220. Input the operating condition data into the accumulation concentration prediction model, determine the operating condition of the battery under test at the current moment based on the current value, and determine the intrinsic gas accumulation concentration value of the battery under test at the current moment based on the operating condition, operating condition data and accumulation concentration prediction model.

[0044] The operating condition can be understood as the type of working state of the battery under test at the current moment, which can be determined based on the current value. Optionally, the operating condition can include the charging / discharging condition (current value ≠ 0, the battery is in the charging / discharging state) and the idle condition (current value = 0, the battery is in the idle / standby state).

[0045] In one implementation, given the operating condition data of the battery under test at the current moment, this data can be input into a concentration prediction model. If the concentration prediction model determines that the current value in the operating condition data is not zero, the battery under test can be determined to be in a charge / discharge condition at the current moment. Further, the operating condition data can be processed using a prediction module in the concentration prediction model corresponding to the charge / discharge condition to obtain the intrinsic gas concentration value of the battery under test at the current moment. Alternatively, if the concentration prediction model determines that the current value in the operating condition data is zero, the battery under test can be determined to be in a static condition at the current moment. Further, the operating condition data can be processed using a prediction module in the concentration prediction model corresponding to the static condition to obtain the intrinsic gas concentration value of the battery under test at the current moment.

[0046] Optionally, the accumulation concentration prediction model includes a charge / discharge condition prediction module and a resting condition prediction module. Based on the operating conditions, operating condition data, and accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment is determined, including: when the battery under test is determined to be in a charge / discharge condition based on the current value, the intrinsic gas accumulation concentration value of the battery under test at the current moment is determined based on the current value, the state of charge value, the battery temperature value, and the charge / discharge condition prediction module; when the battery under test is determined to be in a resting condition based on the current value, the intrinsic gas accumulation concentration value of the battery under test at the current moment is determined based on the state of charge value, the battery temperature value, and the resting condition prediction module.

[0047] The charge / discharge condition prediction module can be understood as the charge / discharge condition calculation module in the accumulation concentration prediction model. This module integrates quantitative calculation logic based on the gas generation law during charge and discharge. Taking current, state of charge, and battery temperature as inputs, the charge / discharge condition prediction module accurately calculates the gas generation increment of the battery under test under charge / discharge conditions, ultimately outputting the intrinsic gas accumulation concentration value under that condition. The resting condition prediction module can be understood as the resting condition calculation module in the accumulation concentration prediction model. This module integrates quantitative calculation logic based on the gas generation law during resting. Since the current is zero under resting conditions, the resting condition prediction module takes state of charge and battery temperature as inputs, accurately calculates the gas generation increment of the battery under test under resting conditions, ultimately outputting the intrinsic gas accumulation concentration value under that condition.

[0048] In one implementation, when operating condition data is input into the accumulation concentration prediction model, the operating condition of the battery under test at the current moment can be determined based on the current value in the operating condition data. Further, if the current value is non-zero, the operating condition of the battery under test at the current moment can be determined to be a charge-discharge condition. Further, the current value, state of charge (SOC) value, and battery temperature value can be input into the charge-discharge condition prediction module. The charge-discharge condition prediction module processes the current value, SOC value, and battery temperature value to obtain the output intrinsic gas accumulation concentration value of the battery under test at the current moment. If the current value in the operating condition data received by the accumulation concentration prediction model is zero, the operating condition of the battery under test at the current moment can be determined to be a static condition. Further, the SOC value and battery temperature value can be input into the static condition prediction module. The static condition prediction module processes the SOC value and battery temperature value to obtain the output intrinsic gas accumulation concentration value of the battery under test at the current moment.

[0049] In this embodiment, the processing logic of processing the current value, state of charge value, and battery temperature value through the charge / discharge condition prediction module is basically the same as that of processing the state of charge value and battery temperature value through the static condition prediction module. The following will take one of the processing processes as an example for specific explanation.

[0050] Optionally, based on the current value, state of charge value, battery temperature value, and charge / discharge condition prediction module, the predicted gas concentration value of the battery under test at the current moment is determined, including: inputting the current value, state of charge value, and battery temperature value to the charge / discharge condition prediction module to obtain the accumulation concentration increment corresponding to the current moment; determining the accumulation concentration coupling increment corresponding to the current moment based on the cumulative accumulation concentration value of the battery under test at the previous moment; and determining the intrinsic gas accumulation concentration value of the battery under test at the current moment based on the accumulation concentration increment corresponding to the current moment and the accumulation concentration coupling increment corresponding to the current moment.

[0051] The accumulation concentration increment can be understood as the change in intrinsic gas accumulation concentration caused by real-time gas production directly triggered by the current current value, state of charge value, and battery temperature value under the current charge / discharge conditions of the battery under test. It is the newly added concentration value at the current moment calculated by the charge / discharge condition prediction module based on the gas production mechanism. The accumulation concentration increment can be used to reflect the instantaneous gas production effect of the battery under test under the current conditions and parameters. The cumulative accumulation concentration value under operating conditions can be understood as the total intrinsic gas accumulation concentration value calculated by the accumulation concentration prediction model at the previous continuous monitoring time point of the battery under test, which integrates the real-time gas production increment of the previous moment and the historical operating condition coupling increment. It is the complete time-series cumulative result of the battery's gas production state up to the previous moment. Its specific type can be divided into charge / discharge condition concentration cumulative value and / or resting condition concentration cumulative value according to the actual operating conditions of the previous moment. It is the core historical data basis for quantifying the current accumulation concentration coupling increment. Optionally, the cumulative accumulation concentration value under operating conditions corresponding to the previous moment can include charge / discharge condition concentration cumulative value and / or resting condition concentration cumulative value. The cumulative concentration value under charge / discharge conditions can be understood as the total cumulative intrinsic gas concentration up to the previous moment, calculated by the charge / discharge condition prediction module when the battery under test was in charge / discharge condition. It incorporates the real-time gas production increment under the previous moment's charge / discharge condition and the coupled increment from historical conditions at that moment. The predicted concentration value under resting conditions can be understood as the total cumulative intrinsic gas concentration up to the previous moment, calculated by the resting condition prediction module when the battery under test was in resting condition. It incorporates the real-time gas production increment under the previous moment's resting condition and the coupled increment from historical conditions at that moment. The coupled increment of the concentration can be understood as the additional change in gas production concentration caused by the interaction between the battery's historical operating conditions (including the operating conditions of the previous moment) and the current charge / discharge condition. The concentration coupling increment can quantify the gas production coupling effect across operating conditions and time (such as the SEI membrane regeneration state in the previous static operating condition, and its acceleration / deceleration effect on the current charge and discharge operating condition SEI membrane rupture gas production), making up for the deficiency that a single real-time increment cannot reflect the linkage effect of operating conditions.

[0052] In this embodiment, determining the aggregation concentration coupling increment corresponding to the current time based on the accumulated concentration value of the battery under test at the previous time under the current condition can include at least one of the following: determining the product between the accumulated concentration value under charge / discharge conditions, the accumulated concentration value under rest conditions, and the first coupling increment coefficient to obtain the aggregation concentration coupling increment corresponding to the current time; adding the accumulated concentration value under charge / discharge conditions, the accumulated concentration value under rest conditions, and the second coupling increment coefficient to obtain the aggregation concentration coupling increment corresponding to the current time; and calculating the accumulated concentration value under charge / discharge conditions and the accumulated concentration value under rest conditions through a weighted summation operation to obtain the aggregation concentration coupling increment corresponding to the current time.

[0053] In this embodiment, determining the intrinsic gas concentration value of the battery under test at the current time based on the accumulation concentration increment and the accumulation concentration coupling increment corresponding to the current time may include at least one of the following: determining the product between the accumulation concentration increment, the accumulation concentration coupling increment, and the first coupling coefficient to obtain the intrinsic gas accumulation concentration value corresponding to the current time; adding the accumulation concentration increment, the accumulation concentration coupling increment, and the second coupling coefficient to obtain the intrinsic gas accumulation concentration value corresponding to the current time; and calculating the accumulation concentration increment and the accumulation concentration coupling increment through a weighted summation operation to obtain the intrinsic gas accumulation concentration value corresponding to the current time.

[0054] In one implementation, if it is determined that the battery under test is currently in a charge / discharge state, the current value, state of charge value, and battery temperature value from the operating condition data can be input into the charge / discharge state prediction module. The gas generation increment calculation logic integrated in the charge / discharge state prediction module calculates the current value, state of charge value, and battery temperature value to obtain the accumulation concentration increment corresponding to the current moment. Further, the accumulated accumulation concentration value of the battery under test at the previous moment can be obtained. The obtained accumulated accumulation concentration value can include the accumulated concentration value of the charge / discharge state and the accumulated concentration value of the static state. Further, the product of the accumulated concentration value of the charge / discharge state, the accumulated concentration value of the static state, and the first coupling increment coefficient can be determined to obtain the accumulation concentration coupling increment corresponding to the current moment. Further, the product of the accumulation concentration increment at the current moment, the accumulation concentration coupling increment at the current moment, and the first coupling coefficient is determined to obtain the intrinsic gas accumulation concentration value corresponding to the current moment.

[0055] S230. Based on the intrinsic gas concentration value of the battery under test at the current moment, determine the battery pressure value of the battery under test at the current moment, and conduct a valve opening risk assessment of the battery under test based on the battery pressure value.

[0056] The technical solution of this disclosure, by inputting operating condition data into the accumulation concentration prediction model, determines the operating condition of the battery under test at the current moment based on the current value, and determines the intrinsic gas accumulation concentration value of the battery under test at the current moment based on the operating condition, operating condition data and accumulation concentration prediction model. This achieves a precise operating condition characterization of the essential state of gas accumulation under the combined effect of battery gas production and physical expansion, and improves the pertinence and accuracy of concentration prediction.

[0057] Figure 3This is a schematic flowchart illustrating another battery pressure prediction method provided in this embodiment. The technical solution of this embodiment can be combined with other embodiments; for the same or related parts, they can be described in conjunction with the descriptions of other embodiments, and will not be repeated here. Figure 3 As shown, the method in this embodiment may specifically include: S310. Obtain the first test sample dataset corresponding to the sample battery under charge-discharge test conditions and the second test sample dataset under static test conditions.

[0058] The sample battery can be understood as a power battery specimen used for charge / discharge and standby condition tests to collect training data and construct a test sample dataset. The sample battery can be a power battery of the same type and / or specification as the battery under test, such as a lithium-ion battery. The charge / discharge test condition can be a simulated actual charge / discharge test state set for the sample battery to collect model training data. The charge / discharge test condition can be distinguished from the charge / discharge conditions in actual battery applications; it is a standardized and repeatable test scenario used to obtain test data related to gas production and concentration under charge / discharge conditions. The first test sample dataset can be understood as a dedicated dataset for model training constructed from the sample battery under charge / discharge test conditions, consisting of test condition data corresponding to multiple test moments and a one-to-one correspondence between the intrinsic gas accumulation concentration and the actual value. The standby test condition can be a simulated actual standby or idle test state set for the sample battery to collect model training data. The standby test condition can be a standardized and repeatable test scenario used to obtain test data related to gas production and concentration under standby conditions. The second test sample dataset can be understood as a dedicated dataset for model training constructed from sample batteries under static testing conditions. It consists of test operation data corresponding to multiple test moments and the true values ​​of intrinsic gas accumulation concentration. Test moments can be preset time points used to collect test data during charge-discharge and / or static testing of the sample batteries. Test moments can be standardized time bases in the testing process, with test data at each test moment being independent and continuous, ensuring the temporal sequence of the dataset. Test operation data can be the core physical parameters characterizing the test condition state of the sample batteries collected by testing equipment at each test moment, consistent with the operating condition data in actual applications, and are the input feature data in the test sample dataset. The true values ​​of intrinsic gas accumulation concentration can be obtained from the sample batteries at each test moment using standardized testing methods (such as measured pressure values ​​and derivation of gas accumulation concentration calculation models), accurately reflecting the combined effects of internal gas production and physical expansion. These are the labeled output data in the test sample dataset, used for error calibration and parameter optimization during model training.

[0059] In this embodiment, the construction methods of the first test sample dataset and the second test sample dataset are consistent. The construction process of the test sample dataset can be further explained below using the first test sample dataset as an example.

[0060] Optionally, the construction of the first test sample dataset includes: performing matrix tests on the sample battery according to a pre-constructed charge-discharge test matrix to obtain test operation data and measured battery pressure values ​​corresponding to multiple test moments under charge-discharge conditions; the test operation data includes battery temperature values; for multiple test moments, processing the battery temperature values ​​and measured battery pressure values ​​corresponding to the test moments using a pre-defined gas accumulation concentration calculation model to obtain the true intrinsic gas accumulation concentration values ​​of the sample battery at the test moments; and constructing the first test sample dataset corresponding to the sample battery under charge-discharge test conditions based on the test operation data and the true intrinsic gas accumulation concentration values ​​corresponding to multiple test moments.

[0061] The charge / discharge condition test matrix can be a standardized test parameter matrix pre-built according to the core influencing parameters of power battery charging and discharging, for the systematic collection of model training data under charge / discharge test conditions. It includes different gradients and combinations of parameters such as current rate, state of charge, and battery temperature, covering typical operating states of charge / discharge conditions. It serves as the foundation for conducting standardized testing and ensuring data comprehensiveness. Matrix testing can be understood as a comprehensive and systematic charge / discharge test of the sample battery according to the parameter combinations / gradient settings in the charge / discharge condition test matrix. Matrix testing differs from fragmented testing of single parameters, efficiently collecting test data under different charge / discharge conditions, ensuring the integrity and representativeness of subsequent datasets. The measured battery pressure value can be understood as the apparent internal pressure value of the sample battery directly detected by pressure sensors and other testing equipment at each test moment during the charge / discharge test. The gas accumulation concentration calculation model can be a pre-built mechanistic calculation model for deriving the true value of intrinsic gas accumulation concentration. The gas accumulation concentration calculation model can be built based on the ideal gas law. It can take the battery temperature value and the measured battery pressure value at the test time as input, and complete the quantitative conversion after removing apparent interferences such as temperature. It is a key tool to connect the measured battery pressure value with the true value of intrinsic gas accumulation concentration.

[0062] In one implementation, when constructing the first test sample dataset required for the aggregation concentration prediction model, a charge-discharge condition test matrix is ​​first pre-built based on the core influencing factors of gas generation during the charging and discharging of the sample battery. This matrix includes different gradients and combinations of key parameters such as current rate, state of charge, and battery temperature. This matrix serves as the standardized testing basis for conducting comprehensive and systematic matrix testing on sample batteries of the same type and specifications as the actual battery under test. Furthermore, during the testing process, test operation condition data of the sample battery (including at least battery temperature values, and potentially also core parameters characterizing the battery test conditions such as current values ​​and state of charge values) is collected at multiple preset test times. Simultaneously, the measured battery pressure values ​​of the sample battery at each test time are acquired synchronously using dedicated testing equipment such as pressure sensors. Furthermore, after completing the raw data acquisition for multiple test moments, for each test moment, the corresponding measured battery temperature and pressure values ​​are input into a pre-constructed gas accumulation concentration calculation model based on the ideal gas law. The model calculations remove the interference of apparent factors such as temperature on the measured pressure values, and after quantitative conversion, the intrinsic gas accumulation concentration value that truly reflects the combined effect of gas generation reaction and physical expansion within the sample battery at that test moment is obtained. Finally, using each test moment as a data matching benchmark, the test operation condition data collected at each moment is integrated one-to-one with the intrinsic gas accumulation concentration value calculated by the model, forming the first test sample dataset, composed of multiple sets of "input feature-output label" data pairs, specifically used to train the charge / discharge condition prediction module in the accumulation concentration prediction model.

[0063] For example, based on the ideal gas law, a gas accumulation concentration calculation model is defined, and its corresponding formula can be expressed as: ;in, Indicates the first The true value of the intrinsic gas accumulation concentration at each test moment; Indicates the first The measured pressure values ​​corresponding to each test moment; Indicates standard atmospheric pressure; Indicates a preset constant; Indicates the first Battery temperature values ​​corresponding to each test moment; Indicates multiplication.

[0064] It should be noted that the reason for using the accumulation concentration prediction model to predict the intrinsic gas accumulation concentration of the battery under test at the current moment, rather than the gas accumulation concentration calculation model, in actual operating scenarios is as follows: The application of the gas accumulation concentration calculation model relies on the simultaneous acquisition of measured battery pressure and battery temperature values. In actual operating conditions, this not only requires equipping the battery under test with dedicated hardware such as pressure sensors, increasing equipment costs and subsequent maintenance difficulties, but also makes it difficult to quickly and accurately derive intrinsic values ​​because the measured pressure values ​​are easily affected by apparent factors such as dynamic physical expansion of the battery and complex environmental temperature fluctuations. In contrast, the accumulation concentration prediction model only requires the current value and state of charge value that can be directly acquired by the battery management system. Using basic operating condition data such as battery temperature as input, no additional dedicated detection hardware is required, making it suitable for engineering implementation needs under actual operating conditions. Furthermore, this model is built based on the gas generation mechanism of power batteries and incorporates core logics such as automatic operating condition identification and cross-operating condition coupling time-series accumulation. It can directly eliminate the interference of apparent factors and predict the intrinsic gas accumulation concentration value that reflects the essential state of battery gas generation in real time and accurately. This better meets the core needs of efficient, low-cost, and accurate monitoring of battery gas generation status in actual operating conditions. At the same time, it can achieve continuous time-series prediction, adapting to the high-frequency switching characteristics of charging and discharging and static operation conditions in actual battery operation conditions. In contrast, gas accumulation concentration calculation models can only perform static conversion based on single-point measured data and cannot meet the dynamic and continuous monitoring needs of actual operating conditions.

[0065] S320. Train the pre-built mathematical model based on the first test sample dataset and the second test sample dataset to obtain the aggregation concentration prediction model.

[0066] The pre-built mathematical model can be understood as a basic computational model framework built on the physical and chemical mechanism of gas production in power batteries before model training. It includes the core logical structure of working condition identification, concentration calculation under different working conditions, and cross-working condition coupling.

[0067] In one implementation, during the training of the aggregation concentration prediction model, firstly, standardized operating condition tests of charge-discharge and static conditions are conducted on sample batteries of the same type and specifications as the actual battery to be tested. Through a systematic matrix test and data acquisition and calculation process, a first test sample dataset corresponding to the charge-discharge test condition and a second test sample dataset corresponding to the static test condition are constructed. Both types of test sample datasets are based on multiple preset test moments of the sample battery during the test process, consisting of test operation condition data that characterizes the battery test condition state corresponding to each test moment, and test operation condition data that can truly reflect the internal gas generation and physical expansion of the battery calculated by a dedicated model. The intrinsic gas accumulation concentration is composed of the actual value of the effect. Then, the first and second test sample datasets are used as training data and input into the mathematical model based on the physicochemical mechanism of gas production in power batteries. Using the feature label pair of "test operation condition data - intrinsic gas accumulation concentration" in the two datasets, the mathematical model is optimized, calibrated, and trained iteratively under different operating conditions. The model learns and fits the quantitative correlation between battery operation condition data and intrinsic gas accumulation concentration under different charging, discharging, and static conditions. Finally, the training is completed to obtain an accumulation concentration prediction model that can accurately predict the intrinsic gas accumulation concentration under different battery operating conditions.

[0068] S330: Obtain the operating condition data corresponding to the battery under test at the current moment.

[0069] S340. Based on the operating condition data and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment is predicted.

[0070] S350. Based on the intrinsic gas concentration value of the battery under test at the current moment, determine the battery pressure value of the battery under test at the current moment, and conduct a valve opening risk assessment of the battery under test based on the battery pressure value.

[0071] The technical solution of this disclosure involves acquiring a first test sample dataset corresponding to the sample battery under charge-discharge test conditions and a second test sample dataset under static test conditions. Further, a pre-constructed mathematical model is trained based on the first and second test sample datasets to obtain an aggregation concentration prediction model. This achieves model adaptability training for different battery charge-discharge and static conditions, enabling the model to accurately learn the quantitative correlation between operating condition data and intrinsic gas aggregation concentration under different operating conditions, thereby improving the model's prediction accuracy and adaptability for intrinsic gas aggregation concentration values ​​under different operating conditions.

[0072] Figure 4 This is a schematic diagram of a battery pressure prediction device provided in an embodiment of this disclosure. Figure 4 As shown, the battery pressure prediction device includes: a data acquisition module 410, an accumulation concentration prediction module 420, and a battery pressure prediction module 430. The data acquisition module 410 is used to acquire operating condition data corresponding to the battery under test at the current moment; wherein the operating condition data includes at least one of current value, state of charge value, and battery temperature value. The accumulation concentration prediction module 420 is used to predict the intrinsic gas accumulation concentration value of the battery under test at the current moment based on the operating condition data and an accumulation concentration prediction model; wherein the intrinsic gas accumulation concentration value is used to characterize the gas accumulation state inside the battery under test at the current moment; the gas accumulation state is determined by at least one of the gas generation reaction and physical expansion of the battery under test. The battery pressure prediction module 430 is used to determine the battery pressure value of the battery under test at the current moment based on the intrinsic gas accumulation concentration value corresponding to the battery under test at the current moment, so as to perform a valve opening risk assessment on the battery under test based on the battery pressure value.

[0073] The technical solution of this disclosure provides accurate and readily available input data for subsequent concentration and pressure prediction by acquiring the operating condition data of the battery under test at the current moment, eliminating the need for dedicated detection hardware and reducing implementation costs. Furthermore, by using the operating condition data and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment is predicted, accurately eliminating apparent interference and truly representing the essential state of gas accumulation resulting from the combined effects of battery gas production and physical expansion. Furthermore, by determining the battery pressure value of the battery under test at the current moment based on the intrinsic gas accumulation concentration value, the valve opening risk assessment of the battery under test is performed based on the battery pressure value, fundamentally avoiding pressure misjudgment, improving the accuracy and scientific nature of battery valve opening risk assessment, and ensuring battery safety. The technical solution of this disclosure solves the problems of poor timeliness and accuracy in monitoring battery thermal runaway and poor accuracy in thermal runaway early warning in related technologies. It realizes that it can accurately predict the intrinsic gas accumulation concentration value that can characterize the combined effect of battery gas production and physical expansion based solely on the battery's basic operating condition data without relying on dedicated detection hardware, and then derive the actual internal pressure value of the battery. This significantly improves the timeliness and accuracy of valve opening risk monitoring before battery thermal runaway, effectively improves the accuracy of thermal runaway early warning, and ensures battery safety.

[0074] In some embodiments of this disclosure, optionally, the accumulation concentration prediction module 420 is specifically used to input the operating condition data into the accumulation concentration prediction model, determine the operating condition of the battery under test at the current time based on the current value, and determine the intrinsic gas accumulation concentration value of the battery under test at the current time based on the operating condition, the operating condition data and the accumulation concentration prediction model.

[0075] In some embodiments of this disclosure, the accumulation concentration prediction model includes a charge / discharge condition prediction module and a resting condition prediction module; the accumulation concentration prediction module 420 includes: a first gas concentration prediction unit and a second gas concentration prediction unit. The first gas concentration prediction unit is used to determine the intrinsic gas accumulation concentration value of the battery under test at the current moment, based on the current value, the state of charge value, the battery temperature value, and the charge / discharge condition prediction module, when the battery under test is determined to be in a charge / discharge condition based on the current value; the second gas concentration prediction unit is used to determine the intrinsic gas accumulation concentration value of the battery under test at the current moment, based on the state of charge value, the battery temperature value, and the resting condition prediction module, when the battery under test is determined to be in a resting condition based on the current value.

[0076] In some embodiments of this disclosure, optionally, the first gas concentration prediction unit includes: an accumulation concentration increment determination subunit, a coupling increment determination subunit, and a gas concentration prediction subunit. The accumulation concentration increment determination subunit is used to input the current value, the state of charge value, and the battery temperature value to the charge / discharge condition prediction module to obtain the accumulation concentration increment corresponding to the current moment; the coupling increment determination subunit is used to determine the accumulation concentration coupling increment corresponding to the current moment based on the accumulated accumulation concentration value of the battery under test at the previous moment; the gas concentration prediction subunit is used to determine the intrinsic gas accumulation concentration value of the battery under test at the current moment based on the accumulation concentration increment corresponding to the current moment and the accumulation concentration coupling increment corresponding to the current moment.

[0077] In some embodiments of this disclosure, optionally, the battery pressure prediction module 430 is specifically used to determine the product between the intrinsic gas accumulation concentration value, the battery temperature value, and a preset constant, so as to obtain the battery pressure value of the battery under test at the current moment.

[0078] In some embodiments of this disclosure, the apparatus may optionally further include: a test sample acquisition module and a model training module. The test sample acquisition module is used to acquire a first test sample dataset corresponding to the sample battery under charge-discharge test conditions and a second test sample dataset under static test conditions. The test sample dataset includes test operation data of the sample battery at multiple test times and the true value of intrinsic gas accumulation concentration. The model training module is used to train a pre-constructed mathematical model based on the first test sample dataset and the second test sample dataset to obtain an accumulation concentration prediction model.

[0079] Optionally, in some embodiments of this disclosure, the test sample acquisition module includes: a first test sample dataset construction unit, configured to perform matrix testing on the sample battery according to a pre-constructed charge-discharge condition test matrix to obtain test operation condition data and measured battery pressure values ​​corresponding to multiple test moments under the charge-discharge condition; the test operation condition data includes battery temperature values; for multiple test moments, a preset gas accumulation concentration calculation model is used to process the battery temperature values ​​and measured battery pressure values ​​corresponding to the test moments to obtain the true intrinsic gas accumulation concentration values ​​of the sample battery at the test moments; and a first test sample dataset corresponding to the sample battery under the charge-discharge test condition is constructed based on the test operation condition data and the true intrinsic gas accumulation concentration values ​​corresponding to the multiple test moments.

[0080] The battery pressure prediction device provided in this disclosure can execute the battery pressure prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0081] It is worth noting that the various units and modules included in the above-mentioned battery pressure prediction device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0082] Figure 5This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0083] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0084] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0085] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as battery pressure prediction methods.

[0086] In some embodiments, the battery pressure prediction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory (ROM) 12 and / or communication unit 19. When the computer program is loaded into random access memory (RAM) 13 and executed by processor 11, one or more steps of the battery pressure prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the battery pressure prediction method by any other suitable means (e.g., by means of firmware).

[0087] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0088] Computer programs used to implement the battery pressure prediction method of this disclosure can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0089] This disclosure provides a computer-readable storage medium storing computer instructions for causing a processor to execute a battery pressure prediction method, comprising: acquiring operating condition data corresponding to a battery under test at a current moment; wherein the operating condition data includes at least one of current value, state of charge value, and battery temperature value; predicting an intrinsic gas accumulation concentration value of the battery under test at the current moment based on the operating condition data and an accumulation concentration prediction model; wherein the intrinsic gas accumulation concentration value is used to characterize the gas accumulation state inside the battery under test at the current moment; the gas accumulation state is determined by at least one of gas generation reaction and physical expansion of the battery under test; and determining a battery pressure value of the battery under test at the current moment based on the intrinsic gas accumulation concentration value corresponding to the battery under test, so as to perform a valve opening risk assessment on the battery under test based on the battery pressure value.

[0090] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0091] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0092] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0093] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0094] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of embodiments of this disclosure.

[0095] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements a battery pressure prediction method according to any embodiment of this disclosure.

[0096] In implementing a computer program product, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0097] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0098] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for predicting battery pressure, characterized in that, include: Acquire the operating condition data corresponding to the battery under test at the current moment; wherein, the operating condition data includes at least one of the following: current value, state of charge value, and battery temperature value; Based on the operating condition data and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current moment is predicted; wherein, the intrinsic gas accumulation concentration value is used to characterize the gas accumulation state inside the battery under test at the current moment; the gas accumulation state is determined by at least one of the gas generation reaction and physical expansion of the battery under test; Based on the intrinsic gas concentration value of the battery under test at the current time, the battery pressure value of the battery under test at the current time is determined, so as to conduct a valve opening risk assessment of the battery under test based on the battery pressure value.

2. The battery pressure prediction method according to claim 1, characterized in that, The step of predicting the intrinsic gas concentration value of the battery under test at the current moment based on the operating condition data and the accumulation concentration prediction model includes: The operating condition data is input into the accumulation concentration prediction model. Based on the current value, the operating condition of the battery under test at the current time is determined. Based on the operating condition, the operating condition data, and the accumulation concentration prediction model, the intrinsic gas accumulation concentration value of the battery under test at the current time is determined.

3. The battery pressure prediction method according to claim 2, characterized in that, The accumulation concentration prediction model includes a charge / discharge condition prediction module and a static condition prediction module; based on the operating conditions, the operating condition data, and the accumulation concentration prediction model, it determines the intrinsic gas accumulation concentration value of the battery under test at the current moment, including: When the battery under test is determined to be in a charging / discharging state based on the current value, the intrinsic gas concentration value of the battery under test at the current moment is determined based on the current value, the state of charge value, the battery temperature value, and the charging / discharging state prediction module. If the battery under test is determined to be in a static condition based on the current value, the intrinsic gas concentration value of the battery under test at the current time is determined based on the state of charge value, the battery temperature value, and the static condition prediction module.

4. The battery pressure prediction method according to claim 3, characterized in that, The step of determining the intrinsic gas concentration value of the battery under test at the current moment based on the current value, the state of charge value, the battery temperature value, and the charge / discharge condition prediction module includes: The current value, the state of charge value, and the battery temperature value are input into the charge / discharge condition prediction module to obtain the accumulation concentration increment corresponding to the current moment; Based on the cumulative concentration value of the battery under test corresponding to the previous time of the current time, determine the coupling increment of the concentration corresponding to the current time. The intrinsic gas concentration value of the battery under test at the current time is determined based on the accumulation concentration increment corresponding to the current time and the accumulation concentration coupling increment corresponding to the current time.

5. The battery pressure prediction method according to claim 1, characterized in that, The step of determining the battery pressure value of the battery under test at the current moment based on the intrinsic gas concentration value of the battery under test at the current moment includes: The product of the intrinsic gas concentration value, the battery temperature value, and a preset constant is determined to obtain the battery pressure value of the battery under test at the current moment.

6. The battery pressure prediction method according to claim 1, characterized in that, Also includes: Obtain the first test sample dataset corresponding to the sample battery under charge and discharge test conditions and the second test sample dataset under static test conditions. The test sample dataset includes the test operation condition data and the true value of intrinsic gas accumulation concentration of the sample battery at multiple test times. The pre-built mathematical model is trained based on the first test sample dataset and the second test sample dataset to obtain the aggregation concentration prediction model.

7. The battery pressure prediction method according to claim 6, characterized in that, The first test sample dataset is constructed in the following ways: The sample battery is subjected to matrix testing according to a pre-constructed charge and discharge condition test matrix to obtain test operation condition data and measured battery pressure values ​​corresponding to multiple test moments under the charge and discharge conditions; the test operation condition data includes battery temperature values. For multiple test moments, a preset gas accumulation concentration calculation model is used to process the battery temperature value and the measured battery pressure value corresponding to the test moment to obtain the true value of the intrinsic gas accumulation concentration of the sample battery at the test moment. Based on the test operation data corresponding to multiple test times and the true value of the intrinsic gas accumulation concentration, a first test sample dataset corresponding to the sample battery under charge and discharge test conditions is constructed.

8. A battery pressure prediction device, characterized in that, include: The data acquisition module is used to acquire the operating condition data corresponding to the battery under test at the current moment; wherein, the operating condition data includes at least one of the following: current value, state of charge value, and battery temperature value; An accumulation concentration prediction module is used to predict the intrinsic gas accumulation concentration value of the battery under test at the current moment based on the operating condition data and the accumulation concentration prediction model; wherein, the intrinsic gas accumulation concentration value is used to characterize the gas accumulation state inside the battery under test at the current moment; the gas accumulation state is determined by at least one of the gas generation reaction and physical expansion of the battery under test. The battery pressure prediction module is used to determine the battery pressure value of the battery under test at the current time based on the intrinsic gas accumulation concentration value corresponding to the battery under test at the current time, so as to perform valve opening risk assessment on the battery under test based on the battery pressure value.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the battery pressure prediction method as described in any one of claims 1-7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the battery pressure prediction method according to any one of claims 1-7.

Images