Methods, apparatus and media for detecting potential risks and predicting lifespan of outdoor batteries

Abstract

This disclosure presents a method, apparatus, and medium for detecting potential risks and predicting the lifespan of outdoor batteries. One specific implementation of the method includes: acquiring relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and internal temperature information of a preset battery under outdoor low-temperature conditions; generating potential risk detection information for the battery; in response to determining that the potential risk detection information contains risk information indicating a risk of ion conduction breakage due to solidification in the preset battery, performing preheating protection treatment on the preset battery; in response to determining that the potential risk detection information contains risk information indicating a risk of lithium dendrites piercing the separator in the preset battery, performing load shedding protection treatment on the preset battery; generating battery lifespan prediction information; and performing battery replacement early warning processing. This implementation improves the stability and safety of battery use.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and more specifically to methods, apparatus, and media for detecting potential risks and predicting the lifespan of outdoor batteries. Background Technology

[0002] Equipment operating in low-temperature outdoor environments often lacks regular inspection, making it difficult to replace or maintain batteries promptly when they malfunction. Outdoor battery potential risk detection and lifespan prediction is a technology for detecting potential risks and predicting the lifespan of batteries in low-temperature outdoor environments. Currently, the common method for battery potential risk detection and lifespan prediction is to rely on monitoring battery status using voltage or current parameters.

[0003] However, when using the above methods to detect potential risks and predict the lifespan of batteries, the following technical problems often arise:

[0004] In low-temperature outdoor environments, battery electrolytes may solidify due to excessively low temperatures, leading to impaired or even broken ion conduction. Low temperatures also accelerate the growth of lithium dendrites, causing them to pierce the separator. However, these changes in physical state may not initially cause significant changes in voltage and current. Relying on battery voltage or current parameters to monitor battery status and perform potential risk detection and lifespan prediction typically only begins when the battery has already experienced significant performance degradation or failure (e.g., impaired or broken ion conduction or lithium dendrites piercing the separator). This has a significant lag, resulting in poor battery stability (e.g., a sharp decline in battery performance) and safety (e.g., lithium dendrite growth may pierce the internal separator, causing overheating, fire, or even explosion due to short circuits between the positive and negative electrodes).

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of this disclosure provide methods, apparatus, electronic devices, and computer-readable media for detecting potential risks and predicting the lifespan of outdoor batteries, in order to address one or more of the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of this disclosure provide a method for detecting potential risks and predicting the lifespan of outdoor batteries. The method includes: collecting relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and battery internal temperature information of a preset battery under outdoor low-temperature conditions; generating battery potential risk detection information based on the lithium dendrite growth thickness information and the battery internal temperature information; performing preheating protection processing on the preset battery in response to determining that the battery potential risk detection information contains risk detection information indicating that the preset battery has a risk of ion conduction breakage due to solidification; performing load shedding protection processing on the preset battery in response to determining that the battery potential risk detection information contains risk detection information indicating that the preset battery has a risk of lithium dendrite puncturing the separator; generating battery lifespan prediction information based on the relaxation voltage curve information, the impedance spectrum information, and a pre-trained battery lifespan prediction model in response to determining that the battery lifespan prediction information meets battery replacement warning conditions; and performing battery replacement warning processing in response to determining that the battery lifespan prediction information meets battery replacement warning conditions.

[0009] Secondly, some embodiments of this disclosure provide an outdoor battery potential risk detection and lifespan prediction device. The device includes: a data acquisition unit configured to acquire relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and battery internal temperature information of a preset battery under outdoor low-temperature conditions; a first generation unit configured to generate battery potential risk detection information based on the lithium dendrite growth thickness information and the battery internal temperature information; and a preheating protection processing unit configured to preheat the preset battery in response to determining that the battery potential risk detection information contains risk detection information indicating that the preset battery has a risk of ion conduction breakage due to solidification. The system includes a protection processing unit and a load cut-off protection processing unit, configured to perform load cut-off protection processing on the preset battery in response to determining that the battery potential risk detection information indicates that the preset battery has a risk of lithium dendrite piercing the separator. A second generation unit is configured to generate battery life prediction information based on the relaxation voltage curve information, the impedance spectrum information, and a pre-trained battery life prediction model in response to determining that the battery potential risk detection information indicates that the preset battery has no potential risk. An early warning unit is configured to perform battery replacement early warning processing in response to determining that the battery life prediction information meets the battery replacement early warning conditions.

[0010] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0012] The above-described embodiments of this disclosure have the following beneficial effects: the outdoor battery potential risk detection and lifespan prediction methods of some embodiments of this disclosure improve the stability of battery use and reduce safety hazards. Specifically, the reason for poor battery stability and safety is that in low-temperature outdoor environments, the battery electrolyte may solidify due to excessively low temperatures, leading to obstructed or even broken ion conduction. Low temperatures also accelerate the growth of lithium dendrites, causing them to pierce the separator. However, these changes in physical state may not cause significant changes in voltage and current initially. When relying on battery voltage or current parameters to monitor battery status and perform potential risk detection and lifespan prediction, potential risks are usually only detected when the battery has already experienced significant performance degradation or failure (e.g., obstructed or broken ion conduction or lithium dendrites piercing the separator). This has a significant lag, resulting in poor battery stability (e.g., a sharp decline in battery performance) and safety (e.g., the growth of lithium dendrites may pierce the separator inside the battery, causing overheating, fire, or even explosion due to short circuits between the positive and negative electrodes). Based on this, the outdoor battery potential risk detection and lifespan prediction method of some embodiments of this disclosure first collects relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and battery internal temperature information of a preset battery under outdoor low-temperature conditions. This allows the collection of these information under low-temperature outdoor conditions. Then, based on the lithium dendrite growth thickness information and the battery internal temperature information, battery potential risk detection information is generated. Thus, based on the lithium dendrite growth thickness information and the battery internal temperature information, potential risk detection information is generated to determine whether the battery has a risk of ion conduction breakage (i.e., electrolyte solidification) caused by low temperature and a risk of lithium dendrite puncturing the separator. Then, in response to determining that the battery potential risk detection information contains risk detection information indicating that the preset battery has a risk of ion conduction breakage due to solidification, preheating protection treatment is performed on the preset battery. Therefore, in the event of a risk of ion conduction breakage due to solidification, preheating protection can slow down electrolyte solidification, thereby improving the stability of outdoor battery use. Next, in response to the determination that the aforementioned potential battery risk detection information contains risk information indicating that the preset battery has a risk of lithium dendrites piercing the separator, a load shedding protection process is performed on the preset battery. This allows for automatic load shedding of the battery in the event of a lithium dendrite piercing risk, preventing overheating, fire, or explosion, and reducing safety hazards associated with outdoor battery use. Then, in response to the determination that the aforementioned potential battery risk detection information indicates that the preset battery does not have a potential risk, battery life prediction information is generated based on the aforementioned relaxation voltage curve information, the aforementioned impedance spectrum information, and the pre-trained battery life prediction model.Therefore, even if there are no potential risks to the outdoor battery, the remaining lifespan of the battery can still be predicted, allowing for replacement warnings. Finally, in response to the determination that the above battery lifespan prediction information meets the battery replacement warning conditions, battery replacement warning processing is performed. Furthermore, before predicting the lifespan of the outdoor battery, based on the lithium dendrite growth thickness information of the base battery and the aforementioned battery internal temperature information, potential battery risk detection information is generated to determine whether the battery has the risk of ion conduction disruption (i.e., electrolyte solidification) caused by low temperature and the risk of lithium dendrite puncturing the separator. Based on the detection information, preheating protection and / or load shedding protection are adopted when there is a risk of ion conduction disruption due to solidification and / or the risk of lithium dendrite puncturing the separator, respectively, improving the stability and safety of battery use. Attached Figure Description

[0013] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0014] Figure 1 This is a flowchart of some embodiments of the method for detecting potential risks and predicting the lifespan of outdoor batteries according to this disclosure;

[0015] Figure 2 This is a schematic diagram of the structure of some embodiments of the outdoor battery potential risk detection and lifespan prediction device according to the present disclosure;

[0016] Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0020] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0021] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0022] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] Figure 1 A flow 100 of some embodiments of the outdoor battery potential risk detection and lifespan prediction method according to this disclosure is shown. The outdoor battery potential risk detection and lifespan prediction method includes the following steps:

[0024] Step 101: Collect information on the relaxation voltage curve, impedance spectrum, lithium dendrite growth thickness, and internal temperature of the preset battery under outdoor low temperature conditions.

[0025] In some embodiments, the execution entity (e.g., a computing device) of the outdoor battery potential risk detection and lifespan prediction method can collect relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and battery internal temperature information of a preset battery under outdoor low-temperature conditions. The execution entity can be a BMS battery system. The outdoor low-temperature environment can be a winter environment or an environment in a cold geographical region, and can be an outdoor environment with a temperature range between 5°C and -40°C. The relaxation voltage curve information represents the relaxation voltage curve of the preset battery within a preset collection period (e.g., 3 hours) after a preset time period (e.g., 15 minutes) following a single charge-discharge cycle. The relaxation voltage curve information includes a voltage data point information sequence, where each voltage data point includes a voltage value and a time point. The voltage value can represent the voltage of the preset battery at the time point. The impedance spectrum information includes an impedance spectrum sequence, where each impedance spectrum corresponds to a corrected voltage data point in the corrected voltage data point information sequence. The acquisition time of the impedance spectrum is the same as the time point included in its corresponding corrected voltage data point information. The impedance spectrum is an electrochemical impedance spectroscopy. The aforementioned lithium dendrite growth thickness information can represent the lithium dendrite thickness collected after a preset time period following the charging and discharging of the aforementioned preset battery. The aforementioned battery internal temperature information can be the temperature collected by a temperature sensor embedded inside the preset battery after a preset time period following the charging and discharging of the aforementioned preset battery.

[0026] In some optional implementations of certain embodiments, the aforementioned execution entity may collect information on the relaxation voltage curve, impedance spectrum, lithium dendrite growth thickness, and internal temperature of a preset battery under outdoor low-temperature conditions through the following steps:

[0027] The first step involves collecting internal battery temperature information via a temperature sensor embedded within the battery after a preset time period following the battery's charging and discharging. In response to determining that the internal battery temperature meets a preset temperature condition, the following data collection steps are performed:

[0028] The first sub-step involves acquiring the relaxation voltage curve information of the preset battery within a preset acquisition time period using a voltage acquisition device connected to the preset battery. The temperature sensor can be an NTC temperature sensor. The preset temperature condition can be a temperature below or equal to a preset temperature threshold (e.g., 5 degrees Celsius).

[0029] The second sub-step involves acquiring the impedance spectrum information of the preset battery within the preset acquisition time period using an impedance spectrometer connected to the preset battery.

[0030] The third sub-step involves acquiring information on the lithium dendrite growth thickness of the pre-embedded battery using a fiber optic sensor embedded within the battery. This fiber optic sensor can be a fiber Bragg grating sensor.

[0031] Step 102: Based on the lithium dendrite growth thickness information and the battery internal temperature information, generate potential risk detection information for the battery.

[0032] In some embodiments, the aforementioned executing entity may generate potential risk detection information for the battery based on the aforementioned lithium dendrite growth thickness information and the aforementioned battery internal temperature information.

[0033] In some optional implementations of certain embodiments, the aforementioned execution entity may generate potential battery risk detection information based on the aforementioned lithium dendrite growth thickness information and the aforementioned battery internal temperature information through the following steps:

[0034] The first step is to obtain the temperature-electrolyte condensation mapping information of the aforementioned preset battery. This mapping information includes various mapping details, each of which includes a preset temperature range and a mapped condensation value. The preset battery temperature-electrolyte condensation mapping information can be a pre-created mapping table that records a one-to-one correspondence between temperature and electrolyte condensation. The mapped condensation value information can be the condensation value corresponding to the preset temperature information. For example, the mapping information could be "Preset temperature range: -10 degrees to -20 degrees, mapped condensation value: 0.95".

[0035] The second step involves retrieving the mapping information corresponding to the battery's internal temperature information from the aforementioned temperature-electrolyte solidification mapping information, using this as the target mapping information. In practice, the executing entity can determine the preset temperature range information included in each mapping information. Then, the preset temperature range information of the range represented by the battery's internal temperature information within each preset temperature range information is determined as the target preset temperature range information. Afterward, the executing entity can determine the mapping information containing the target preset temperature range information as the target mapping information.

[0036] The third step is to determine the mapped condensation information included in the above target mapping information as the target condensation information.

[0037] Fourth, in response to determining that the condensation degree represented by the aforementioned target condensation degree information is greater than or equal to a preset electrolyte condensation degree threshold, the information representing the risk of ion conduction interruption due to solidification in the preset battery is identified as risk detection information. Specifically, when the condensation degree is greater than or equal to the preset electrolyte condensation degree threshold (e.g., 0.7), it means that the solidification or high viscosity of the electrolyte may cause problems with ion conduction, thus posing a risk. The aforementioned information representing the risk of ion conduction interruption due to solidification in the preset battery can be text information; for example, the information representing the risk of ion conduction interruption due to solidification in the preset battery could be "Warning: Electrolyte has solidified, high risk of ion conduction interruption."

[0038] Fifth, in response to determining that the lithium dendrite growth thickness, as indicated by the aforementioned lithium dendrite growth thickness information, is greater than or equal to a preset generation thickness threshold, the information indicating a risk of lithium dendrites piercing the separator in the preset battery is identified as risk detection information. It should be noted that when the lithium dendrite growth thickness is greater than or equal to the preset generation thickness threshold, it means that the lithium dendrites may pierce the battery separator, posing an extremely high risk. The aforementioned information indicating a risk of lithium dendrites piercing the separator in the preset battery can be text information. For example, the information indicating a risk of lithium dendrites piercing the separator in the preset battery could be "Warning: May pierce the separator, posing a short circuit risk."

[0039] The sixth step is to identify at least one of the identified risk detection information as potential battery risk detection information.

[0040] Step 7: In response to determining that the condensation degree represented by the target condensation degree information is less than a preset electrolyte condensation degree threshold and the lithium dendrite growth thickness represented by the lithium dendrite growth thickness information is less than a preset generation thickness threshold, the information representing that the preset battery has no potential risk is determined as battery potential risk detection information. The information representing that the preset battery has no potential risk can be text information. For example, the information representing that the preset battery has no potential risk can be "No potential risk exists".

[0041] Step 103: In response to the presence of risk detection information in the battery potential risk detection information indicating that the preset battery has the risk of ion conduction breakage due to solidification, the preset battery is subjected to preheating protection treatment.

[0042] In some embodiments, the execution entity may perform preheating protection treatment on the preset battery in response to determining that the preset battery has risk detection information that indicates that the preset battery has a risk of ion conduction breakage due to solidification.

[0043] In some optional implementations of certain embodiments, the execution entity may perform preheating protection processing on the preset battery in response to determining that the preset battery has risk detection information indicating that the preset battery has a risk of ion conduction breakage due to solidification:

[0044] The first step involves, in response to the determination that the aforementioned potential risk detection information for the battery contains risk information indicating a risk of ion conduction disruption due to solidification, sending a preset preheating protection command to the preset battery to control the activation of the heating element built into the preset battery. This preset preheating protection command can be a control command to activate the heating element built into the preset battery. The heating element can be a heating element that raises the battery temperature through current heating (the heating element typically activates at low temperatures to prevent electrolyte solidification due to excessively low temperatures, thus affecting battery performance).

[0045] Step 104: In response to the presence of risk detection information in the battery potential risk detection information that indicates the risk of lithium dendrites piercing the separator in the preset battery, load cut-off protection processing is performed on the preset battery.

[0046] In some embodiments, the execution entity may perform load cut-off protection processing on the preset battery in response to determining that the preset battery has risk detection information that indicates the risk of lithium dendrites piercing the separator in the battery potential risk detection information.

[0047] In some optional implementations of certain embodiments, the execution entity may perform load cut-off protection processing on the preset battery in response to determining that the preset battery has risk detection information characterizing the risk of lithium dendrite puncturing the separator in the battery potential risk detection information:

[0048] The first step involves, in response to the determination that the aforementioned potential risk detection information for the battery contains risk information indicating a risk of lithium dendrites piercing the separator in the preset battery, sending preset load cut-off information to the control module of the load device associated with the preset battery to control the load device to disconnect from the preset battery. The load device can be a load device operating in low-temperature outdoor environments (e.g., a weather monitoring device operating in low-temperature outdoor environments). The control module can be an electronic system or device that controls the current flow between the battery and the load device. The preset load cut-off information can be an electrical signal or digital command that controls the disconnection of the load device from the preset battery.

[0049] Step 105: In response to determining that the battery potential risk detection information indicates that the preset battery does not have potential risks, battery life prediction information is generated based on the relaxation voltage curve information, impedance spectrum information and the pre-trained battery life prediction model.

[0050] In some embodiments, the execution entity may, in response to determining that the battery potential risk detection information indicates that the preset battery does not have potential risks, generate battery life prediction information based on the relaxation voltage curve information, the impedance spectrum information, and the pre-trained battery life prediction model.

[0051] In some optional implementations of certain embodiments, the execution entity can generate battery life prediction information based on the relaxation voltage curve information, the impedance spectrum information, and the pre-trained battery life prediction model through the following steps:

[0052] The first step is to perform the following temperature compensation correction process on each voltage data point in the voltage data point information sequence included in the above relaxation voltage curve information:

[0053] The first sub-step involves collecting the ambient temperature of the environment where the preset battery is located. In practice, the executing entity can use a digital temperature sensor on the load device to collect the ambient temperature as the ambient temperature of the environment where the preset battery is located.

[0054] The second sub-step involves generating temperature correction factor information based on the aforementioned ambient temperature and the preset linear correction model. The preset linear correction model can be a mathematical model (i.e., a mathematical formula) used to quantify the effect of temperature changes on battery voltage. As an example, the preset linear correction model can be:

[0055] f(T) = 1 + α(T - Tref)

[0056] Wherein, f(T) represents the temperature correction factor information at an ambient temperature of T. α can be a temperature coefficient, determined experimentally, representing the rate of change in battery voltage for every 1°C change in temperature. Tref represents the selected reference temperature (typically standard room temperature of 25°C). In practice, the ambient temperature and reference temperature can be input into a preset linear correction model to obtain the temperature correction factor information.

[0057] The third sub-step involves generating a corrected voltage value based on the voltage values ​​included in the aforementioned voltage data point information and the aforementioned temperature correction factor information. In practice, the executing entity can determine the corrected voltage value as the product of the voltage values ​​included in the voltage data point information and the values ​​represented by the temperature correction factor information.

[0058] The fourth sub-step involves deleting the voltage values ​​from the aforementioned voltage data point information and adding the corrected voltage values ​​to the aforementioned voltage data point information to update the aforementioned voltage data point information.

[0059] The fifth sub-step involves determining the updated voltage data point information as the corrected voltage data point information.

[0060] The second step is to arrange the determined corrected voltage data point information to obtain a corrected voltage data point information sequence. In practice, the aforementioned execution entity can sort the corrected voltage data point information according to the order of the corresponding voltage data point information in the voltage data point information sequence to obtain the corrected voltage data point information sequence.

[0061] The third step involves generating battery life prediction information based on the aforementioned ambient temperature, the aforementioned corrected voltage data point information sequence, the aforementioned impedance spectrum information, and the pre-trained battery life prediction model.

[0062] In the process of adopting technical solutions to address the problems mentioned in the background section, the following issues often arise:

[0063] The entire impedance spectrum information, ambient temperature, and corrected voltage data point sequence are directly input into the battery life prediction model to obtain battery life prediction information. However, directly inputting the entire impedance spectrum information into the battery life prediction model without separating the impedance spectrum, which contains multiple components, fails to directly capture the characteristics of electrolyte resistance and electrode polarization resistance that affect battery life, resulting in a significant deviation between the prediction results and the actual remaining life. Furthermore, without separating the impedance spectrum and performing low-temperature correction separately, directly inputting the entire impedance spectrum into the model makes it difficult for the model to accurately distinguish between resistance changes caused by temperature and those caused by battery aging, resulting in poor accuracy of the generated battery life prediction information. This leads to battery replacement warnings being issued too early or too late, and premature warnings waste battery resources. To address these technical problems, the inventors decided to adopt the following solution:

[0064] In some optional implementations of certain embodiments, the execution entity can generate battery life prediction information based on the ambient temperature, the modified voltage data point information sequence, the impedance spectrum information, and a pre-trained battery life prediction model through the following steps:

[0065] The first step, based on the impedance spectrum sequence included in the impedance spectrum information, is to perform the following separation steps:

[0066] The first sub-step involves performing resistance separation processing on the first impedance spectrum in the impedance spectrum sequence to obtain electrolyte resistance information and electrode polarization resistance information. In practice, the aforementioned execution entity can fit the impedance spectrum using an impedance model (such as the Randle circuit model) to extract the electrolyte resistance information and electrode polarization resistance information from the impedance spectrum. The electrolyte resistance information can be an electrolyte resistance sequence, and the electrode polarization resistance information can be an electrode polarization resistance sequence.

[0067] The second sub-step involves adding the electrolyte resistance information to the first preset queue to update the first preset queue.

[0068] The third sub-step involves adding the electrode polarization resistance information to the second preset queue to update the second preset queue.

[0069] The fourth sub-step involves removing the first impedance spectrum from the impedance spectrum sequence to update the impedance spectrum sequence.

[0070] The second step is to perform the separation step again based on the updated impedance spectrum sequence, in response to the determination that the updated impedance spectrum sequence is not empty.

[0071] Third, in response to the confirmation that the updated impedance spectrum sequence is not empty, the following generation steps are performed:

[0072] Sub-step one involves arranging the updated electrolyte resistance information in the first preset queue in sequence to obtain an electrolyte resistance information sequence. In practice, the aforementioned executing entity can arrange the electrolyte resistance information in the first preset queue according to the order of the electrolyte resistance information in the first preset queue to obtain the electrolyte resistance information sequence.

[0073] Sub-step two involves arranging the updated electrode polarization resistance information in the second preset queue in sequence to obtain the electrode polarization resistance information sequence.

[0074] The fourth step involves performing low-temperature correction processing on the aforementioned electrolyte resistance information sequence and electrode polarization resistance information sequence to obtain a low-temperature corrected electrolyte resistance information sequence and a low-temperature corrected electrode polarization resistance information sequence. In practice, for each electrolyte resistance included in the electrolyte resistance information sequence, the executing entity can correct the electrolyte resistance using the Arrhenius formula to obtain a corrected electrolyte group, and replace the corrected electrolyte resistance with the aforementioned electrolyte resistance to update the electrolyte resistance information sequence. Then, the executing entity can determine the updated electrolyte resistance information sequence as the low-temperature corrected electrolyte resistance information sequence. Similarly, the executing entity can correct each electrode polarization resistance included in the electrode polarization resistance information sequence using the Arrhenius formula to obtain a low-temperature corrected electrode polarization resistance information sequence.

[0075] The fifth step involves inputting the aforementioned corrected voltage data point information sequence, electrolyte resistance information sequence, and electrode polarization resistance information sequence into the time-series feature extraction layer of the battery life prediction model to obtain a hidden state feature information sequence. The battery life prediction model includes the aforementioned time-series feature extraction layer, an initial life prediction layer, and an optimized output layer. The aforementioned time-series feature extraction layer can be a GRU layer that takes the corrected voltage data point information sequence, electrolyte resistance information sequence, and electrode polarization resistance information sequence as input and the hidden state feature information sequence as output. The aforementioned hidden state feature information sequence is the hidden state feature information sequence obtained after inputting the corrected voltage data point information sequence, electrolyte resistance information sequence, and electrode polarization resistance information sequence into the time-series feature extraction layer (GRU layer) of the battery life prediction model. It represents the internal state of the GRU network at each time step during the processing of the input sequence. Each hidden state feature in the aforementioned hidden state feature information sequence represents a dynamic understanding of the input sequence (such as battery voltage, electrolyte resistance, electrode polarization resistance, etc.), that is, it represents the intrinsic representation of the current input (such as correction voltage, electrolyte resistance, electrode polarization resistance, etc.), and it integrates the input information of the current input and all previous time steps. The aforementioned hidden state feature information sequence can characterize the implicit state features of battery degradation.

[0076] Step 6: Input the aforementioned hidden state feature information sequence into the aforementioned initial lifespan prediction layer to obtain initial lifespan prediction information. The aforementioned initial lifespan prediction layer can be a fully connected layer that takes the hidden state feature information sequence as input and outputs the initial lifespan prediction information. The aforementioned initial lifespan prediction information can represent the predicted remaining lifespan of a preset battery (e.g., number of charging cycles or number of days of use).

[0077] Step 7: Input the initial lifespan prediction information and the ambient temperature to the optimization output layer. The optimization output layer then optimizes the initial lifespan prediction information based on preset lithium dendrite growth constraints to obtain battery lifespan prediction information. This battery lifespan prediction information can be the remaining battery usage time. Since lithium dendrite growth slows down at low temperatures, resulting in a relatively longer battery lifespan, the optimization output layer can use an ambient temperature as input, learning a correction factor corresponding to that temperature. This correction factor is then used to correct the initial lifespan prediction information to obtain the battery lifespan prediction information. The correction factor can be a correction value corresponding to the ambient temperature. For example, if the ambient temperature is -20℃, the corresponding correction factor is 1.2, and the initial lifespan prediction information is 10 days, then the battery lifespan prediction information can be 10 days × 1.2 = 12 days.

[0078] The above technical solution, combined with step 106 and related content, serves as an inventive point of this disclosure, solving the technical problem of "premature warnings wasting battery resources." Factors leading to premature warnings and wasted battery resources often include: directly inputting the entire impedance spectrum information, ambient temperature, and corrected voltage data point sequence into a battery life prediction model to obtain battery life prediction information. Directly inputting the entire impedance spectrum information into the battery life prediction model without separating the impedance spectrum (which contains multiple components) makes it impossible to directly capture the characteristics of electrolyte resistance and electrode polarization resistance that affect battery life, resulting in a significant deviation between the prediction result and the actual remaining life. Furthermore, without separating the impedance spectrum and performing low-temperature correction, directly inputting the entire impedance spectrum into the model makes it difficult for the model to accurately distinguish between resistance changes caused by temperature and resistance changes caused by battery aging, resulting in poor accuracy of the generated battery life prediction information. This leads to battery replacement warnings being issued too early or too late, and premature warnings waste battery resources. Solving these factors can reduce the waste of battery resources caused by premature warnings. To achieve this effect, firstly, based on the impedance spectrum sequence included in the impedance spectrum information, the following separation steps are performed: Step 1: Perform resistance separation processing on the first impedance spectrum in the impedance spectrum sequence to obtain electrolyte resistance information and electrode polarization resistance information. Step 2: Add the electrolyte resistance information to a first preset queue to update the first preset queue. Step 3: Add the electrode polarization resistance information to a second preset queue to update the second preset queue. Step 4: Delete the first impedance spectrum from the impedance spectrum sequence to update the impedance spectrum sequence. Step 5: In response to determining that the updated impedance spectrum sequence is not empty, perform the separation steps again based on the updated impedance spectrum sequence. Then, in response to determining that the updated impedance spectrum sequence is empty, perform the following generation steps: Step 1: Arrange each electrolyte resistance information in the updated first preset queue in order to obtain an electrolyte resistance information sequence. Step 2: Arrange each electrode polarization resistance information in the updated second preset queue in order to obtain an electrode polarization resistance information sequence. Therefore, through the separation and generation steps described above, electrolyte resistance and electrode polarization resistance information (i.e., electrolyte resistance information sequences and electrode polarization resistance information sequences) can be obtained separately, allowing subsequent models to more directly capture the impact characteristics of these two resistances on battery life. Subsequently, the electrolyte resistance information sequences and electrode polarization resistance information sequences are subjected to low-temperature correction processing to obtain low-temperature corrected electrolyte resistance information sequences and low-temperature corrected electrode polarization resistance information sequences. Temperature changes and battery aging have two distinct effects on resistance. Without low-temperature correction, the model may incorrectly confuse temperature-induced resistance changes with changes due to battery aging, leading to prediction bias.By performing low-temperature correction on the electrolyte resistance information sequence and the electrode polarization resistance information sequence, the influence of temperature-induced resistance changes can be eliminated, resulting in a low-temperature corrected electrolyte resistance information sequence and a low-temperature corrected electrode polarization resistance information sequence. Then, these corrected voltage data point information sequences, electrolyte resistance information sequences, and electrode polarization resistance information sequences are input into the time-series feature extraction layer of the battery life prediction model to obtain a hidden state feature information sequence. The battery life prediction model includes the time-series feature extraction layer, an initial lifespan prediction layer, and an optimized output layer. Thus, the time-series feature extraction layer can extract a hidden state feature information sequence reflecting battery degradation characteristics based on the corrected voltage data point information sequence, the electrolyte resistance information sequence, and the electrode polarization resistance information sequence. This hidden state feature information sequence is then input into the initial lifespan prediction layer to obtain initial lifespan prediction information. Next, the initial lifespan prediction information and the ambient temperature are input into the optimized output layer, which optimizes the initial lifespan prediction information based on preset lithium dendrite growth constraint information to obtain the final battery lifespan prediction information. The optimized output layer comprehensively considers the impact of ambient temperature on lithium dendrite growth. By optimizing the initial prediction using preset constraint information, the final battery life prediction information is made more consistent with reality, further improving prediction accuracy and yielding more accurate battery life prediction information. Furthermore, through the aforementioned separation and generation steps, electrolyte resistance and electrode polarization resistance can be separated separately, resulting in electrolyte resistance information sequences and electrode polarization resistance information sequences. This allows subsequent models to more directly capture the influence characteristics of these two resistances on battery life. Moreover, by performing low-temperature correction on the electrolyte resistance information sequences and electrode polarization resistance information sequences, the influence of temperature-induced resistance changes can be eliminated, resulting in low-temperature corrected electrolyte resistance information sequences and low-temperature corrected electrode polarization resistance information sequences. Inputting the corrected voltage data point information sequence, the low-temperature corrected electrolyte resistance information sequence, and the electrode polarization resistance information sequence into the battery life prediction model allows the model to comprehensively consider the temporal dependencies in these sequences and the characteristics of electrolyte resistance and electrode polarization resistance affecting battery life. Based on preset lithium dendrite growth constraint information, the initial life prediction information is optimized, generating more accurate battery life prediction information. Combined with step 106, this allows for battery replacement warnings to be issued based on more accurate battery lifespan prediction information, thereby reducing the occurrence of premature or late battery replacement warnings and thus minimizing the waste of battery resources caused by premature warnings.

[0079] Step 106: In response to determining that the battery life prediction information meets the battery replacement warning conditions, perform battery replacement warning processing.

[0080] In some embodiments, the executing entity may perform battery replacement warning processing in response to determining that the battery life prediction information meets the battery replacement warning conditions. The battery replacement warning conditions may be that the remaining battery life represented by the battery life prediction information is less than or equal to a preset duration (e.g., 1 day).

[0081] In some optional implementations of certain embodiments, the aforementioned execution entity may perform battery replacement warning processing in response to determining that the battery life prediction information meets the battery replacement warning conditions through the following steps:

[0082] The first step involves, in response to the determination that the battery life prediction information meets the battery replacement warning conditions, sending a battery replacement warning to a preset monitoring terminal and detecting whether there is a usable backup battery in the battery compartment where the preset battery is located, thus obtaining detection information. The preset monitoring terminal can be a maintenance personnel terminal (e.g., a mobile terminal (such as a mobile phone, tablet computer) or computer terminal used by maintenance personnel). The battery replacement warning information can be information indicating that the preset battery needs to be replaced. In practice, the voltage value of the backup battery can be detected by the battery management system (BMS) or battery monitoring circuit in the battery compartment. If the battery voltage is within the normal range (e.g., the voltage is higher than a preset voltage threshold), it indicates that the backup battery is usable, and the information indicating the existence of a usable backup battery is determined as the detection information. If the backup battery voltage is outside the normal range (e.g., the voltage is lower than or equal to the preset voltage threshold), the information indicating that there is no usable backup battery is determined as the detection information.

[0083] The second step is to control the battery compartment containing the preset battery to switch the backup battery to power the load device in response to the detection information indicating that there is a usable backup battery in the battery compartment.

[0084] The third step involves, in response to the determination that the aforementioned detection information indicates the absence of available spare batteries in the battery compartment, collecting the location information of the load device as the target point location information. In practice, the geographical location information of the load device can be collected using a GPS receiver built into the load device as the target point location information. The aforementioned load device is equipped with a corresponding battery replacement robot.

[0085] The fourth step is to obtain the location information of the battery-equipped robot corresponding to the aforementioned load device as the starting point location information. In practice, GPS positioning technology can be used to obtain the geographical location information of the battery-equipped robot corresponding to the load device. Then, the executing entity can convert the obtained geographical location information into the starting point node position in an outdoor two-dimensional grid map as the starting point location information. The upper left corner grid of the outdoor two-dimensional grid map can be the starting point grid corresponding to the starting point location information, and the location information of the starting point grid represents the starting node position (e.g., (0, 0)). The lower right corner grid of the outdoor two-dimensional grid map can be the ending point grid corresponding to the target point location information, and the location information of the ending point grid represents the position of the ending node in the outdoor two-dimensional grid map (e.g., (2, 2)). The aforementioned battery-equipped robot can be an outdoor robot that replaces the battery of the load device.

[0086] Fifth, based on the target point location information and the starting point location information, perform the following update scheduling process:

[0087] The first sub-step involves acquiring an outdoor 2D grid map. Each node in this map corresponds to either a feasibility marker or an obstacle marker. Each node represents a grid cell in the outdoor 2D grid map and has corresponding geographical location information. This outdoor 2D grid map can be a 2D grid map of the area where the payload device and its corresponding battery-equipped robot are located. The outdoor 2D grid map reflects the distribution of obstacles in the environment.

[0088] The second sub-step involves determining the node corresponding to the starting point location information in the outdoor two-dimensional grid map as the starting point node.

[0089] The third sub-step involves identifying target neighbor nodes that meet preset conditions among the neighbor nodes of the starting node in the outdoor 2D grid map, and generating the current node's location information based on the target point's location information and the outdoor 2D grid map. The preset conditions can include having feasible markers. In practice, for each target neighbor node, the executing entity can determine the path cost to that target neighbor node. This path cost can be represented by h, where h = g value + h value. The g value represents the actual cost from the node corresponding to the starting location information to the target neighbor node, typically the actual distance traveled along the grid path (note that the distance moved up, down, left, right, or diagonally each time can be set to 1). For example, if the first step is from the node corresponding to the starting location information to the target neighbor node, then the g value is 1. If the second step is from the node corresponding to the starting location information to the target neighbor node, then the g value is 2. The h value can be the estimated cost from the target neighbor node to the target node represented by the target point's location information, represented by the Manhattan distance, where the length of a cell in the outdoor 2D grid map is represented by 1. Then, the aforementioned executing entity can determine the path value with the smallest value among the determined path values ​​as the target path value. After that, the aforementioned executing entity can determine the position of the target neighbor node corresponding to the target path value in the aforementioned outdoor two-dimensional grid map as the current node position information (e.g., (2, 2)).

[0090] The fourth sub-step involves controlling the battery-equipped robot to move to the location represented by the current node's position information in the outdoor 2D grid map, in response to the determination that the location information of the endpoint grid corresponding to the target point's position information is different from that of the current node's position information. In practice, the aforementioned executing entity can determine the geographical location information corresponding to the node corresponding to the current node's position information as the moving position information. Afterward, the aforementioned executing entity can control the battery-equipped robot to move to the location represented by the moving position information.

[0091] The fifth sub-step is to update the current node's position information to the starting point's position information.

[0092] The sixth sub-step involves executing the update scheduling step again based on the updated starting point and target point location information.

[0093] Step 6: In response to the determination that the current node location information and the target point location information are the same in the outdoor two-dimensional grid map, the battery-equipped robot is dispatched to the location of the load device represented by the target point location information.

[0094] Step 7: Control the battery-equipped robot to remove a spare battery from the robot's spare battery compartment, and use a robotic arm to replace the removed spare battery with the aforementioned load device.

[0095] The above technical solution and its related content, as an inventive point of this disclosure, solve the technical problem of "increased scheduling resources". Factors leading to increased scheduling resources often include: a pre-planned fixed path from the starting point of the battery-equipped robot to the location of the load device, allowing the robot to move along this fixed path. Obstacles in the outdoor environment are constantly changing. If new obstacles appear along the way (such as fallen trees or temporarily stacked goods), the robot cannot continue along the original path and needs to be replanned. If a shorter, passable road appears during the scheduling process (obstacle removal, resulting in a shorter road), the scheduling resources increase because the battery-equipped robot can only move along the planned fixed path. Solving these factors can save scheduling resources. To achieve this effect, firstly, in response to determining that the battery life prediction information meets the battery replacement warning conditions, a battery replacement warning is sent to a preset monitoring terminal, and the presence of a usable spare battery in the battery compartment containing the preset battery is detected, obtaining detection information. Thus, the presence of a usable spare battery in the battery compartment can be detected. Then, in response to determining that the detection information indicates the presence of a usable spare battery in the battery compartment, the battery compartment containing the preset battery is controlled to switch to a spare battery to power the load device. In response to the determination that the above detection information indicates there are no available spare batteries in the battery compartment, the location information of the load device is collected as the target point location information. Thus, even when there are no available spare batteries in the battery compartment, the target point location information of the load device can be collected. Then, the location information of the battery-equipped robot corresponding to the load device is obtained as the starting point location information. Thus, the location information of the battery-equipped robot can be obtained. Then, based on the target point location information and the starting point location information, the following update scheduling process is performed: First, an outdoor two-dimensional grid map is obtained, where each node in the outdoor two-dimensional grid map corresponds to a feasible marker or an obstacle marker. Thus, an outdoor two-dimensional grid map showing the obstacle distribution in the current base environment can be obtained. Second, the node corresponding to the starting point location information in the outdoor two-dimensional grid map is determined as the starting point node. Third, each target neighbor node that meets preset conditions among the neighbor nodes of the starting point node in the outdoor two-dimensional grid map is determined, and the current node location information is generated based on the target point location information and the outdoor two-dimensional grid map. Thus, the node corresponding to the robot's starting point location and target point location can be determined in the outdoor two-dimensional grid map, and the feasible neighbor nodes of the starting point node are selected as target neighbor nodes. Fourth, in response to the determination that the current node position information and the target point position information are different from the corresponding endpoint grid position information, the battery-equipped robot is controlled to move to the position represented by the current node position information. Fifth, the current node position information is updated to the starting point position information to update the starting point position information.Step 6: Based on the updated starting point and target point locations, perform the update scheduling step again. Thus, through steps 4 to 6, the current node location information is updated to the starting point location information, and path planning is performed again based on the updated information. Step 7: In response to the determination that the current node location information and the target point location information correspond to the same endpoint grid location information, the battery-equipped robot is scheduled to the location of the load device represented by the target point location information. Thus, through the above update scheduling process, the robot updates its current node location information to the starting point location information every time it moves to a new location, and performs path planning again based on the updated information, enabling the robot to adapt to environmental changes in real time. If a closer passable path appears during the scheduling process (e.g., an obstacle is removed, and a closer path appears), the robot can adjust its path in time and choose a better route. This also effectively avoids situations where, when moving along a fixed path, new obstacles appear along the way (e.g., fallen trees, temporarily piled goods), preventing the robot from continuing along the original path, thereby saving scheduling resources during the movement of the battery-equipped robot. Finally, the battery delivery robot retrieves a spare battery from the robot's spare battery compartment and uses a robotic arm to replace the spare battery with the aforementioned load device. Thus, the battery delivery robot is deployed to the location of the load device to replace its battery.

[0096] The above-described embodiments of this disclosure have the following beneficial effects: the outdoor battery potential risk detection and lifespan prediction methods of some embodiments of this disclosure improve the stability of battery use and reduce safety hazards. Specifically, the reason for poor battery stability and safety is that in low-temperature outdoor environments, the battery electrolyte may solidify due to excessively low temperatures, leading to obstructed or even broken ion conduction. Low temperatures also accelerate the growth of lithium dendrites, causing them to pierce the separator. However, these changes in physical state may not cause significant changes in voltage and current initially. When relying on battery voltage or current parameters to monitor battery status and perform potential risk detection and lifespan prediction, potential risks are usually only detected when the battery has already experienced significant performance degradation or failure (e.g., obstructed or broken ion conduction or lithium dendrites piercing the separator). This has a significant lag, resulting in poor battery stability (e.g., a sharp decline in battery performance) and safety (e.g., the growth of lithium dendrites may pierce the separator inside the battery, causing overheating, fire, or even explosion due to short circuits between the positive and negative electrodes). Based on this, the outdoor battery potential risk detection and lifespan prediction method of some embodiments of this disclosure first collects relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and battery internal temperature information of a preset battery under outdoor low-temperature conditions. This allows the collection of these information under low-temperature outdoor conditions. Then, based on the lithium dendrite growth thickness information and the battery internal temperature information, battery potential risk detection information is generated. Thus, based on the lithium dendrite growth thickness information and the battery internal temperature information, potential risk detection information is generated to determine whether the battery has a risk of ion conduction breakage (i.e., electrolyte solidification) caused by low temperature and a risk of lithium dendrite puncturing the separator. Then, in response to determining that the battery potential risk detection information contains risk detection information indicating that the preset battery has a risk of ion conduction breakage due to solidification, preheating protection treatment is performed on the preset battery. Therefore, in the event of a risk of ion conduction breakage due to solidification, preheating protection can slow down electrolyte solidification, thereby improving the stability of outdoor battery use. Next, in response to the determination that the aforementioned potential battery risk detection information contains risk information indicating that the preset battery has a risk of lithium dendrites piercing the separator, a load shedding protection process is performed on the preset battery. This allows for automatic load shedding of the battery in the event of a lithium dendrite piercing risk, preventing overheating, fire, or explosion, and reducing safety hazards associated with outdoor battery use. Then, in response to the determination that the aforementioned potential battery risk detection information indicates that the preset battery does not have a potential risk, battery life prediction information is generated based on the aforementioned relaxation voltage curve information, the aforementioned impedance spectrum information, and the pre-trained battery life prediction model.Therefore, even if there are no potential risks to the outdoor battery, the remaining lifespan of the battery can still be predicted, allowing for replacement warnings. Finally, in response to the determination that the above battery lifespan prediction information meets the battery replacement warning conditions, battery replacement warning processing is performed. Furthermore, before predicting the lifespan of the outdoor battery, based on the lithium dendrite growth thickness information of the base battery and the aforementioned battery internal temperature information, potential battery risk detection information is generated to determine whether the battery has the risk of ion conduction disruption (i.e., electrolyte solidification) caused by low temperature and the risk of lithium dendrite puncturing the separator. Based on the detection information, preheating protection and / or load shedding protection are adopted when there is a risk of ion conduction disruption due to solidification and / or the risk of lithium dendrite puncturing the separator, respectively, improving the stability and safety of battery use.

[0097] Further reference Figure 2 As an implementation of the methods shown in the figures, this disclosure provides some embodiments of an outdoor battery potential risk detection and lifespan prediction device. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0098] like Figure 2 As shown, the outdoor battery potential risk detection and lifespan prediction device 200 in some embodiments includes: a data acquisition unit 201, a first generation unit 202, a preheating protection processing unit 203, a load cut-off protection processing unit 204, a second generation unit 205, and an early warning unit 206. The acquisition unit 201 is configured to acquire relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and battery internal temperature information of a preset battery under outdoor low-temperature conditions; the first generation unit 202 is configured to generate battery potential risk detection information based on the lithium dendrite growth thickness information and the battery internal temperature information; the preheating protection processing unit 203 is configured to perform preheating protection processing on the preset battery in response to determining that the battery potential risk detection information contains risk detection information indicating that the preset battery has a risk of ion conduction breakage due to solidification; the load shedding protection processing unit 204 is configured to perform load shedding protection processing on the preset battery in response to determining that the battery potential risk detection information contains risk detection information indicating that the preset battery has a risk of lithium dendrite piercing the separator; the second generation unit 205 is configured to generate battery life prediction information based on the relaxation voltage curve information, the impedance spectrum information, and a pre-trained battery life prediction model in response to determining that the battery potential risk detection information indicates that the preset battery has no potential risk; and the early warning unit 206 is configured to perform battery replacement early warning processing in response to determining that the battery life prediction information meets the battery replacement early warning conditions.

[0099] It is understandable that the units described in the device 200 are related to the reference. Figure 1 The steps in the method described above correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 200 and the units contained therein, and will not be repeated here.

[0100] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0101] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0102] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0103] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a 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 device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0104] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, 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 device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0105] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0106] The computer-readable medium may be included in an electronic device or may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and battery internal temperature information of a preset battery under outdoor low-temperature conditions; generate battery potential risk detection information based on the lithium dendrite growth thickness information and the battery internal temperature information; in response to determining that the battery potential risk detection information contains risk detection information indicating a risk of ion conduction breakage due to solidification in the preset battery, perform preheating protection processing on the preset battery; in response to determining that the battery potential risk detection information contains risk detection information indicating a risk of lithium dendrite puncturing the separator in the preset battery, perform load shedding protection processing on the preset battery; in response to determining that the battery potential risk detection information indicates that the preset battery has no potential risk, generate battery life prediction information based on the relaxation voltage curve information, the impedance spectrum information, and a pre-trained battery life prediction model; and in response to determining that the battery life prediction information meets the battery replacement warning conditions, perform battery replacement warning processing.

[0107] Computer program code for performing operations of some embodiments 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++—and conventional procedural programming languages—such as the "C" language or similar programming 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).

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0109] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a data acquisition unit, a first generation unit, a preheating protection processing unit, a load shedding protection processing unit, a second generation unit, and a warning unit. The names of these units do not necessarily limit the specific unit; for example, the first generation unit may also be described as "a unit that generates potential battery risk detection information based on the aforementioned lithium dendrite growth thickness information and the aforementioned battery internal temperature information."

[0110] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0111] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of technical features, but should also cover other technical solutions formed by arbitrary combinations of technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for detecting potential risks and predicting the lifespan of outdoor batteries, comprising: Collect information on the relaxation voltage curve, impedance spectrum, lithium dendrite growth thickness, and internal temperature of a preset battery under outdoor low-temperature conditions. Based on the lithium dendrite growth thickness information and the battery internal temperature information, potential risk detection information for the battery is generated. In response to the determination that the battery potential risk detection information contains risk detection information indicating that the preset battery has the risk of ion conduction breakage due to solidification, the preset battery is subjected to preheating protection treatment. In response to the determination that the battery potential risk detection information contains risk information characterizing the risk of lithium dendrites piercing the separator in the preset battery, the preset battery is subjected to load cut-off protection processing. In response to determining that the potential risk detection information of the battery indicates that the preset battery does not have potential risks, battery life prediction information is generated based on the relaxation voltage curve information, the impedance spectrum information and the pre-trained battery life prediction model. In response to determining that the battery life prediction information meets the battery replacement warning conditions, a battery replacement warning process is performed.

2. The method of claim 1, wherein, In response to determining that the battery potential risk detection information contains risk information indicating that the preset battery has a risk of ion conduction breakage due to solidification, the preset battery is subjected to a preheating protection process, including: In response to the determination that the potential risk detection information of the battery contains risk information indicating that the preset battery has a risk of ion conduction breakage due to solidification, a preset preheating protection command is sent to the preset battery to control the heating element built into the preset battery to start.

3. The method of claim 1, wherein, In response to determining that the battery potential risk detection information contains risk information characterizing the risk of lithium dendrites piercing the separator in the preset battery, the preset battery is subjected to load cut-off protection processing, including: In response to the determination that the potential risk detection information of the battery contains risk information indicating that the preset battery has the risk of lithium dendrite puncturing the separator, a preset load cut-off information is sent to the control module of the load device associated with the preset battery to control the load device to disconnect from the preset battery.

4. The method of claim 1, wherein, The acquisition of relaxation voltage curve information, impedance spectrum information, lithium dendrite growth thickness information, and battery internal temperature information of a preset battery under outdoor low-temperature conditions includes: After a preset time period following the charging and discharging of the preset battery, the internal temperature information of the battery is collected by a temperature sensor embedded inside the preset battery. In response to determining that the internal temperature information of the battery meets the preset temperature condition, the following data collection steps are performed: The relaxation voltage curve information of the preset battery within a preset acquisition time period is acquired by a voltage acquisition instrument connected to the preset battery, wherein the preset temperature condition is that the temperature represented is lower than or equal to a preset temperature threshold. The impedance spectrum information of the preset battery during the preset acquisition time period is collected by an impedance spectrometer connected to the preset battery. The lithium dendrite growth thickness information of the preset battery is collected by a fiber optic sensor pre-embedded inside the battery.

5. The method of claim 1, wherein, The generation of potential battery risk detection information based on the lithium dendrite growth thickness information and the battery internal temperature information includes: Obtain the temperature-electrolyte condensation mapping information of the preset battery, wherein the temperature-electrolyte condensation mapping information includes various mapping information, and each of the various mapping information includes preset temperature information and mapped condensation information; From each mapping information in the temperature-electrolyte solidification mapping information, query the mapping information corresponding to the internal temperature information of the battery as the target mapping information; The mapping condensation information included in the target mapping information is determined as the target condensation information; In response to determining that the condensation degree represented by the target condensation degree information is greater than or equal to a preset electrolyte condensation degree threshold, the information representing the risk of ion conduction interruption due to solidification in the preset battery is determined as risk detection information. In response to determining that the lithium dendrite growth thickness represented by the lithium dendrite growth thickness information is greater than or equal to a preset generation thickness threshold, the information representing the risk of lithium dendrite puncturing the separator in the preset battery is determined as risk detection information. At least one of the identified risk detection information is designated as potential battery risk detection information; In response to determining that the condensation degree represented by the target condensation degree information is less than a preset electrolyte condensation degree threshold and the lithium dendrite growth thickness represented by the lithium dendrite growth thickness information is less than a preset generation thickness threshold, the information representing that the preset battery does not have potential risks is determined as battery potential risk detection information.

6. The method of claim 1, wherein, The relaxation voltage curve information includes a sequence of voltage data points, each voltage data point in the sequence including a voltage value and a time point. The generation of battery life prediction information based on the relaxation voltage curve information, the impedance spectrum information, and a pre-trained battery life prediction model includes: For each voltage data point in the voltage data point information sequence included in the relaxation voltage curve information, the following temperature compensation correction process is performed: Collect the ambient temperature of the environment where the preset battery is located; Based on the ambient temperature and the preset linear correction model, temperature correction factor information is generated; Based on the voltage values ​​included in the voltage data point information and the temperature correction factor information, a corrected voltage value is generated; The voltage values ​​in the voltage data point information are deleted, and the corrected voltage values ​​are added to the voltage data point information to update the voltage data point information; The updated voltage data point information is identified as the corrected voltage data point information; Arrange the determined corrected voltage data point information to obtain the corrected voltage data point information sequence; Based on the ambient temperature, the sequence of corrected voltage data points, the impedance spectrum information, and the pre-trained battery life prediction model, battery life prediction information is generated.

7. A device for detecting potential risks and predicting the lifespan of outdoor batteries, comprising: The acquisition unit is configured to acquire information on the relaxation voltage curve, impedance spectrum, lithium dendrite growth thickness, and internal temperature of a preset battery under outdoor low-temperature conditions. The first generation unit is configured to generate potential risk detection information of the battery based on the lithium dendrite growth thickness information and the battery internal temperature information. The preheating protection processing unit is configured to perform preheating protection processing on the preset battery in response to determining that there is risk detection information in the battery potential risk detection information that indicates that the preset battery has a risk of ion conduction breakage due to solidification. The load cut-off protection processing unit is configured to perform load cut-off protection processing on the preset battery in response to determining that there is risk detection information in the battery potential risk detection information that characterizes the preset battery having the risk of lithium dendrite piercing the separator. The second generation unit is configured to generate battery life prediction information in response to determining that the battery potential risk detection information indicates that the preset battery does not have potential risks, based on the relaxation voltage curve information, the impedance spectrum information and the pre-trained battery life prediction model. The early warning unit is configured to perform battery replacement early warning processing in response to determining that the battery life prediction information meets the battery replacement early warning conditions.

8. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

9. A computer readable medium having stored thereon a computer program, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 6.

Images