A lithium iron phosphate battery safety early warning method and system based on multi-parameter fusion

Abstract

The application relates to the technical field of battery safety, in particular to a lithium iron phosphate battery safety early warning method and system based on multi-parameter fusion. The method comprises the following steps: obtaining a battery working condition data set, and analyzing a battery internal state information set based on the battery working condition data set; analyzing a microorganism corrosion representation information set based on the battery working condition data set; analyzing the coupling relationship between an external-to-internal corrosion path and an internal-to-external dendrite growth path in the battery failure process based on the battery internal state information set and the microorganism corrosion representation information set, and obtaining a failure path coupling situation information set; analyzing the composite stress intensity of multiple failure paths on the overall safety boundary of the battery based on the failure path coupling situation information set, generating a dynamically optimized risk mitigation early warning strategy, and outputting a battery safety state intervention process log. The stable operation of the lithium iron phosphate battery is guaranteed, and the task reliability of underwater operation equipment is improved.

Description

Technical Field

[0001] This application relates to the field of battery safety technology, and in particular to a method and system for safety early warning of lithium iron phosphate batteries based on multi-parameter fusion. Background Technology

[0002] Lithium iron phosphate batteries are widely used in underwater equipment due to their high safety, long lifespan, and environmental friendliness. They can also precisely meet the personalized off-grid energy needs of homes, RVs, yachts, and cabins, serving as an effective supplement to grid-connected scenarios. However, when underwater equipment performs missions in the deep sea, the batteries face complex internal and external challenges: the external deep-sea environment (high pressure, low temperature, barophilic microorganisms) causes chronic corrosion, while internal battery actions (such as profile cruise and emergency maneuvering) can lead to lithium deposition and thermal runaway risks. To address this, a safety early warning method based on multi-parameter fusion is designed. By real-time monitoring and fusion of multiple parameters, the battery safety status is dynamically assessed, and potential faults are promptly warned, ensuring the safety of underwater unmanned vehicles (UUVs) missions.

[0003] Existing methods cannot reveal the coupling relationship between the outside-to-inside corrosion path and the inside-to-outside dendrite growth path during battery failure, leading to delayed safety warnings and a high risk of false alarms or missed alarms. This lack of evaluation capability means that operation and maintenance adjustments are often based on incomplete information, which not only increases the safety hazards and operation and maintenance costs of batteries in underwater equipment, but also makes it difficult to adapt to the requirements of safe and stable battery operation in off-grid scenarios. Summary of the Invention

[0004] This application provides a safety early warning method and system for lithium iron phosphate batteries based on multi-parameter fusion to solve the above-mentioned problems.

[0005] In a first aspect, this application provides a safety early warning method for lithium iron phosphate batteries based on multi-parameter fusion, the method comprising:

[0006] A battery operating condition dataset is acquired. Based on this dataset, the interaction between temperature-pressure changes caused by different task actions and the internal electrochemical dynamics of the battery is analyzed to obtain a battery internal state information set. Based on this dataset, the impact of temperature-pressure changes on the metabolic activity and biofilm formation ability of barophilic microorganisms is analyzed to obtain a microbial erosion characterization information set. Based on this internal state information set, combined with the microbial erosion characterization information set, the coupling relationship between the external-to-inside corrosion path and the internal-to-outside dendrite growth path during battery failure is analyzed to obtain a failure path coupling situation information set. Based on this failure path coupling situation information set, the combined stress intensity of multiple failure paths on the overall battery safety boundary is analyzed, a dynamically optimized risk mitigation and early warning strategy is generated, and a battery safety status intervention process log is output.

[0007] Through the above technical solutions, and based on multi-parameter fusion analysis, key factors such as internal electrochemical changes, external temperature-pressure effects, and microbial erosion of the battery are comprehensively covered. The coupling relationship of failure paths is accurately revealed, effectively improving the comprehensiveness and accuracy of battery safety early warning. The dynamically optimized risk mitigation and early warning strategy can be adjusted in a timely manner according to the actual safety status of the battery, realizing proactive prevention and precise intervention of battery safety risks, significantly reducing the probability of battery failure. The output of the battery safety status intervention process log provides important data support for subsequent battery maintenance, fault tracing, and early warning method optimization, effectively ensuring the stable operation of lithium iron phosphate batteries, thereby improving the mission reliability and operational safety of the submersible.

[0008] Optionally, the battery operating condition dataset includes a mission action command sequence, battery compartment internal temperature, external hydrostatic pressure information set, battery operating voltage, and battery load current. Based on the mission action command sequence, the start and end time nodes of cruise, hovering, and acceleration actions are determined to obtain a mission phase division information set. Based on the mission phase division information set, combined with the battery compartment internal temperature and the external hydrostatic pressure information set, the hysteresis response relationship between the rate of temperature change and the rate of pressure change during the transient process of action switching is analyzed to obtain a temperature-pressure transient change information set characterizing the dynamic impact of the external marine environment on the battery compartment. Based on the temperature-pressure transient change information set, combined with the battery operating voltage and the battery load current, the coordinated fluctuation characteristics of ohmic polarization and concentration polarization inside the battery under external temperature-pressure change impact are analyzed to obtain a battery internal state information set.

[0009] Optionally, based on the temperature-pressure transient change information set, the action switching stages where temperature change precedes pressure change and pressure change precedes temperature change are analyzed to obtain a differentiated temperature-pressure dominant transient scenario information set; in the action switching stage where temperature change precedes pressure change, combined with the battery operating voltage, the ohmic resistance stepwise transition process caused by the thermal expansion and contraction of the active material layer inside the battery is analyzed to obtain a thermally induced ohmic polarization dominant information set; in the action switching stage where pressure change precedes temperature change, combined with the battery load current, the process of suppressed electrolyte ion migration rate caused by the gradient effect of the external hydrostatic pressure field is analyzed to obtain a pressure-induced concentration polarization dominant information set; based on the thermally induced ohmic polarization dominant information set and the pressure-induced concentration polarization dominant information set, the dynamic evolution path of the battery internal state, composed of alternating dominance of thermally induced ohmic polarization and pressure-induced concentration polarization, is analyzed during continuous task action switching to obtain a battery internal state information set.

[0010] Optionally, based on the task phase segmentation information set, combined with the battery compartment internal temperature and external hydrostatic pressure information set, the dynamic shaping process of the temperature-pressure parameter combination on the survival environment of barophilic microorganisms under different task phases is analyzed to obtain a microbial survival substrate condition information set strongly correlated with task actions; based on the microbial survival substrate condition information set, combined with the temperature-pressure transient change information set, the fluctuation law of the secretion of barophilic microbial metabolites under temperature-pressure change rate difference scenarios is analyzed to obtain a metabolic activity dynamic response information set characterizing the strength of microbial activity; based on the microbial survival substrate condition information set, combined with the task phase segmentation information set, the cumulative growth characteristics of the attachment area and thickness of barophilic microbial biofilm over time within the temperature-pressure stable range are analyzed to obtain a biofilm formation efficiency information set; based on the metabolic activity dynamic response information set, combined with the biofilm formation efficiency information set, the synergistic effect mechanism of the two under different temperature-pressure change modes is analyzed to obtain a microbial erosiveness characterization information set comprehensively reflecting the potential of microorganisms to erode the battery structure.

[0011] Optionally, based on the task phase segmentation information set, and combined with the battery compartment internal temperature and external hydrostatic pressure information set, the coordinated matching relationship of temperature and pressure change amplitudes during the cruise, hovering, and acceleration task phases is analyzed to obtain a temperature-pressure coordinated change pattern information set driven by task actions; based on the temperature-pressure coordinated change pattern information set, the adaptive adjustment process of barophilic microbial cell membrane fluidity and enzyme activity under temperature-pressure coordinated changes is analyzed to obtain a dynamic response information set of microbial physiological states; based on the dynamic response information set of microbial physiological states, and combined with the task phase segmentation information set, the dynamic changes of wettability and nutrient accessibility of microbial attachment surfaces under different task phases are analyzed to obtain a microbial survival substrate condition information set strongly correlated with task actions.

[0012] Optionally, based on the dynamic response information set of metabolic activity and combined with the information set of temperature-pressure synergistic change patterns, the phase and amplitude variation patterns of metabolic activity fluctuations under different temperature-pressure synergistic change patterns are analyzed to obtain a metabolic activity pattern matching information set; based on the biofilm formation efficiency information set and combined with the information set of temperature-pressure synergistic change patterns, the initiation delay and growth slope characteristics of biofilm formation efficiency under different temperature-pressure synergistic change patterns are analyzed to obtain a biofilm formation pattern matching information set; based on the metabolic activity pattern matching information set and combined with the biofilm formation pattern matching information set, the temporal coupling relationship and intensity correlation relationship between metabolic activity fluctuations and biofilm formation efficiency are analyzed to obtain a microbial erosion synergy information set; based on the microbial erosion synergy information set and combined with the task stage segmentation information set, the task action stage with the highest synergy is identified to obtain the microbial erosiveness characterization information set.

[0013] Optionally, based on the dominant information set of thermally induced ohmic polarization and combined with the dominant information set of pressure-induced concentration polarization, the local overheating phenomenon caused by the stepwise transition of ohmic internal resistance is analyzed during the action switching stage where temperature change precedes pressure change. This accelerates the fluctuation of metabolic product secretion by barophilic microorganisms during the task action stage with the highest degree of synergy, thus obtaining a thermal-microbial synergistic corrosion path information set. Based on the dominant information set of pressure-induced concentration polarization and combined with the dominant information set of thermally induced ohmic polarization, the inhibition of electrolyte ion migration rate is analyzed during the action switching stage where pressure change precedes temperature change. The resulting uneven lithium-ion deposition preferentially induces dendrite nucleation at local stress concentration points caused by the biofilm's adhesion area and thickness, resulting in a pressure-biofilm synergistic dendrite path information set. Based on the aforementioned thermal-microbial synergistic corrosion path information set, combined with the pressure-biofilm synergistic dendrite path information set, the spatiotemporal evolution of microcracks formed by the infiltration and corrosion of the battery shell by microbial metabolites from the outside to the inside, and microchannels formed by dendrites growing from the inside to the outside and piercing the separator, which connect in weak areas of the battery structure and form failure acceleration channels, is analyzed, resulting in the aforementioned failure path coupling situation information set.

[0014] Optionally, based on the thermal-microbial synergistic corrosion path information set and combined with the task phase segmentation information set, it is analyzed that during the action switching stage where temperature change precedes pressure change, local overheating caused by thermally induced ohmic polarization preferentially induces pitting corrosion in the biofilm-covered area, thereby guiding microcracks to propagate directionally along the biofilm edge, thus obtaining a microcrack bioguided propagation information set; based on the pressure-biofilm synergistic dendrite path information set and combined with the task phase segmentation information set, it is analyzed that during the action switching stage where pressure change precedes temperature change, local stress concentration caused by biofilm adhesion alters lithium ionization. The sub-flow field distribution guides the dendritic microchannels to preferentially grow towards the stress concentration region, resulting in a microchannel stress-guided growth information set. Based on the microcrack bio-guided expansion information set, combined with the microchannel stress-guided growth information set, the spatiotemporal competition and synergy between the outside-to-inside bio-guided cracks and the inside-to-outside stress-guided channels are analyzed: when the two evolve towards each other in the battery shell-separator interface region, the failure acceleration effect caused by path coupling is identified; when the two develop in a misaligned manner, the failure risk delayed by path separation is assessed, resulting in the failure path coupling situation information set.

[0015] Optionally, based on the failure path coupling situation information set and the task stage segmentation information set, the dynamic erosion rate caused to the battery safety boundary when the bio-guided cracks from the outside to the inside and the stress-guided channels from the inside to the outside evolve in opposite directions is analyzed to obtain a composite stress intensity information set; based on the composite stress intensity information set and the microbial erosion synergy information set, the task action stage where the composite stress intensity exceeds the safety threshold and the microbial erosion synergy reaches its peak is identified to obtain a key risk intervention window information set; based on the key risk intervention window information set, a risk mitigation and early warning strategy with the core of adjusting the task action sequence, activating active thermal compensation and electrolyte flow field optimization is generated, and the strategy-driven battery state regulation is executed, outputting a battery safety state intervention process log that records the regulation parameters and the evolution of the safety state.

[0016] Secondly, this application provides a safety early warning system for lithium iron phosphate batteries based on multi-parameter fusion, the system comprising:

[0017] The battery status analysis module acquires a battery operating condition dataset and, based on this dataset, analyzes the interaction between temperature-pressure changes caused by different task actions and the internal electrochemical dynamics of the battery, obtaining a battery internal status information set. The corrosion characterization module, based on the battery operating condition dataset, analyzes the impact of temperature-pressure changes on the metabolic activity and biofilm formation ability of barophilic microorganisms, obtaining a microbial erosiveness characterization information set. The coupling situation module, based on the battery internal status information set and the microbial erosiveness characterization information set, analyzes the coupling relationship between the external-to-inside corrosion path and the internal-to-outside dendrite growth path during battery failure, obtaining a failure path coupling situation information set. The early warning and intervention module, based on the failure path coupling situation information set, analyzes the combined stress intensity of multiple failure paths on the overall battery safety boundary, generates dynamically optimized risk mitigation and early warning strategies, and outputs a battery safety status intervention process log. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram illustrating an application scenario provided in one embodiment of this application;

[0020] Figure 2 A flowchart illustrating a safety early warning method for lithium iron phosphate batteries based on multi-parameter fusion, provided as an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of a safety early warning system for lithium iron phosphate batteries based on multi-parameter fusion, provided as an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0023] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0024] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0025] Existing technologies struggle to fully capture the multi-parameter dynamic coupling effects of batteries in complex marine environments. They lack correlation analysis between temperature-pressure transients and the internal state of the battery, resulting in insufficient identification of the dynamic evolution path of electrochemical processes. Furthermore, they neglect the assessment of the activity of barophilic microorganisms and their potential erosion of the battery structure. Due to the lack of integration of multi-source data, existing methods cannot reveal the coupling mechanism between the corrosion path from the outside to the inside and the dendrite growth from the inside to the outside. This leads to delayed safety warnings, a high risk of false alarms and missed alarms, and insufficient evaluation capabilities, resulting in reliance on incomplete information for operation and maintenance. This increases the safety hazards and operation and maintenance costs of battery systems.

[0026] Based on this, this application provides a method and system for safety early warning of lithium iron phosphate batteries based on multi-parameter fusion. Through multi-parameter analysis, the battery failure mechanism is accurately revealed, a dynamic early warning and active prevention and control mechanism is established, the failure probability is significantly reduced, and maintenance optimization is supported by log data, so as to ensure the safe and stable operation of the submarine battery and improve mission reliability.

[0027] Figure 1This application provides an illustration of an application scenario for lithium iron phosphate batteries used in unmanned underwater vehicles (UUVs) in a deep-sea environment. By applying the method provided in this application and fusing multi-source parameters, the comprehensive causes and coupling relationships of battery failure are accurately analyzed. Based on this, a dynamic adaptive early warning and active intervention mechanism is constructed, which significantly improves the accuracy of fault early warning and effectively reduces the risk of battery failure. At the same time, its detailed operation logs provide key data support for subsequent maintenance and strategy optimization, thereby comprehensively ensuring the safety of the UUV battery and the reliability of the mission.

[0028] Specifically, the method provided in this application can be applied to any server, where the server interacts with the battery status monitoring sensor to obtain the battery condition dataset provided by the battery status monitoring sensor. This accurately reveals the coupling relationship of the failure path, effectively improves the comprehensiveness and accuracy of battery safety early warning, and outputs a battery safety status intervention process log to the unmanned underwater vehicle safety personnel, thereby improving the mission reliability and operational safety of the underwater vehicle.

[0029] For specific implementation details, please refer to the following examples.

[0030] Figure 2 This is a flowchart illustrating a safety warning method for lithium iron phosphate batteries based on multi-parameter fusion, provided as an embodiment of this application. The method of this embodiment can be applied to servers in the above scenarios. Figure 2 As shown, the method includes:

[0031] S201. Obtain the battery operating condition dataset. Based on the battery operating condition dataset, analyze the interaction between the temperature-pressure changes caused by different task actions and the internal electrochemical dynamics of the battery to obtain the battery internal state information set.

[0032] A battery operating condition dataset can be a set of parameters reflecting the operating state of a lithium iron phosphate battery during operation, sourced from the battery status monitoring sensors mounted on the corresponding device. Temperature-pressure changes can be the fluctuations in temperature and pressure values ​​generated by the battery's environment and its own operation when the device carrying the battery performs different tasks. Internal electrochemical dynamics of the battery can be the changing state of the internal electrochemical processes. The battery internal state information set can be a collection of information on the battery's internal health status.

[0033] Specifically, the marine environment, especially the deep-sea environment, poses unique challenges to lithium iron phosphate batteries. Existing land-based or ordinary vehicle-mounted battery warning systems only focus on electro-thermal coupling, while seriously neglecting the key variable of hydrostatic pressure and the dynamic interaction between pressure and temperature. In submersibles, mission actions directly determine the application path of temperature and pressure loads. This dynamic change will profoundly affect the electrochemical dynamics inside the battery: for example, high pressure may compress the gaps between electrode materials and change the ion migration rate; drastic temperature changes will affect reaction kinetics and side reaction rates. Without accurate analysis of this chain interaction of "mission actions - temperature and pressure loads - electrochemical response", any warning will be detached from actual operating conditions and inaccurate.

[0034] S202. Based on the battery operating condition dataset, the effects of temperature-pressure changes on the metabolic activity and biofilm formation ability of barophilic microorganisms are analyzed to obtain a set of microbial erosiveness characterization information.

[0035] The metabolic activity of barophilic microorganisms can be defined as the degree of metabolic activity of barophilic microorganisms in the marine environment under different temperature and pressure conditions. Biofilm formation capability refers to characteristics such as the speed and thickness of biofilm formation by barophilic microorganisms on the battery surface. The microbial erosiveness characterization information set can be a collection of information reflecting the degree and manner of erosion of the battery by barophilic microorganisms.

[0036] Specifically, in the high-pressure environment of the deep sea, the metabolic activity and community behavior of barophilic microorganisms change significantly under specific temperature-pressure conditions. For example, some microorganisms exhibit enhanced metabolic activity and secrete more corrosive metabolites at certain pressure thresholds; while suitable temperatures may promote the formation of dense biofilms. These biofilms can not only locally alter the physicochemical properties of material surfaces but may also form closed cellular structures, accelerating localized corrosion. This outside-to-inside bio-erosion pathway is distinctly different from the electrochemical aging pathway within the battery, but ultimately they work together to lead to battery failure.

[0037] S203. Based on the battery internal state information set and combined with the microbial erosion characterization information set, analyze the coupling relationship between the corrosion path from the outside to the inside and the dendrite growth path from the inside to the outside in the battery failure process, and obtain the failure path coupling situation information set.

[0038] A corrosion path can be the propagation path of corrosion from the surface to the interior of a battery caused by external factors. A dendrite growth path can be the extension path of lithium-ion deposition inside the battery, forming dendrites that continue to grow. The failure path coupling state information set can be the set of state information on the interaction and mutual influence between the corrosion path and the dendrite growth path during the battery failure process.

[0039] Specifically, in deep-sea environments, battery failure is rarely the result of a single, independent path. For example, external microbial corrosion can lead to a decrease in the sealing performance of the battery casing, allowing moisture to infiltrate. This deteriorates the internal electrochemical environment and significantly accelerates the growth rate of lithium dendrites. Conversely, internal dendrite growth can cause internal short circuits, creating localized hotspots. This heat can alter the local microenvironment temperature of the battery compartment, stimulating the metabolic activity of barophilic microorganisms and accelerating external corrosion. This coupled relationship of "internal and external attacks, a vicious cycle" is the greatest threat to the safety of submersible batteries. Analyzing the internal state or external corrosion in isolation will not foresee this risk of accelerated failure.

[0040] S204. Based on the failure path coupling situation information set, analyze the combined stress intensity of multiple failure paths on the overall safety boundary of the battery, generate a dynamically optimized risk mitigation and early warning strategy, and output the battery safety status intervention process log.

[0041] Multiple failure paths can be multiple paths leading to battery failure, formed by corrosion paths and dendrite growth paths. The overall battery safety boundary can be the extreme range of parameters within which the battery can operate normally and safely. The combined stress intensity can be the degree of destructive pressure exerted on the overall battery safety boundary by multiple failure paths combined. Dynamically optimized risk mitigation and early warning strategies can be early warning and response plans that are dynamically adjusted based on the combined stress intensity to reduce battery safety risks. The battery safety state intervention process log can be a log of various operations and state changes recorded during battery safety state intervention.

[0042] Specifically, in the context of lithium iron phosphate batteries used in unmanned underwater vehicles (UUVs) in deep-sea environments, the analysis of combined stress intensity transforms complex coupled situations into a quantifiable and tiered management indicator. The early warning strategy generated based on this indicator must be dynamic and optimized, as fixed thresholds are rigid and ineffective in the face of complex coupled failures. For example, during critical mission phases, even with some risk, it may be necessary to maintain power; while during safety redundancy phases, a more conservative strategy is adopted. This dynamic optimization ensures the optimal balance between UUV mission execution and battery safety. Finally, outputting detailed intervention process logs is not only for post-event auditing and fault diagnosis, but also for continuously iterating and optimizing the early warning strategy itself using machine learning methods through data accumulation, forming a self-evolving safety system.

[0043] The method provided in this embodiment, based on multi-parameter fusion analysis, comprehensively covers key factors such as internal electrochemical changes in the battery, external temperature-pressure effects, and microbial erosion. It accurately reveals the coupling relationship of failure paths, effectively improving the comprehensiveness and accuracy of battery safety early warning. At the same time, the target application scenarios can accurately cover personalized off-grid energy needs such as homes, RVs, yachts, and cabins, effectively supplementing grid-connected scenarios. The dynamically optimized risk mitigation and early warning strategy can be adjusted in a timely manner according to the actual safety status of the battery, realizing proactive prevention and precise intervention of battery safety risks, significantly reducing the probability of battery failure. The output of the battery safety status intervention process log provides important data support for subsequent battery maintenance, fault tracing, and early warning method optimization, effectively ensuring the stable operation of lithium iron phosphate batteries, thereby improving the mission reliability and operational safety of the submersible.

[0044] In some embodiments, the battery operating condition dataset includes a sequence of mission action commands, internal temperature of the battery compartment, external hydrostatic pressure information, battery operating voltage, and battery load current. Based on the sequence of mission action commands, the start and end time points of cruise, hovering, and acceleration actions are determined to obtain a mission phase segmentation information set. Based on the mission phase segmentation information set, combined with the internal temperature of the battery compartment and the external hydrostatic pressure information set, the hysteresis response relationship between the rate of temperature change and the rate of pressure change during the transient process of action switching is analyzed to obtain a temperature-pressure transient change information set characterizing the dynamic impact of the external marine environment on the battery compartment. Based on the temperature-pressure transient change information set, combined with the battery operating voltage and battery load current, the coordinated fluctuation characteristics of ohmic polarization and concentration polarization inside the battery are analyzed under external temperature-pressure change impact to obtain a battery internal state information set.

[0045] The mission action command sequence can be a series of action commands executed by the submersible during a mission. The battery compartment internal temperature can be the temperature value inside the battery compartment. The external hydrostatic pressure information set can be a collection of hydrostatic pressure data at different depths in the marine environment. The battery operating voltage can be the terminal voltage of the battery in its operating state. The battery load current can be the current value output or input by the battery. The mission phase division information set can be a collection of information that divides the submersible's operation into different phases based on the mission action command sequence and by analyzing the start and end times of the actions. The temperature-pressure transient change information set can be a collection of data on the hysteresis response relationship between the rate of temperature change and the rate of pressure change during the transient process of action switching. Ohmic polarization can be the voltage drop caused by the ohmic internal resistance inside the battery. Concentration polarization can be the voltage drop caused by the difference in ion concentration inside the battery. Co-fluctuation characteristics can be the characteristics of the mutual influence and co-fluctuation of ohmic polarization and concentration polarization under the impact of external temperature-pressure changes.

[0046] Specifically, in complex operating environments, battery systems not only need to cope with the electrochemical stress brought about by high-load tasks, but also need to adapt to the dynamic influence of the external marine environment. The interaction between these external temperature and pressure changes and the internal electrochemical dynamics of the battery is a key factor leading to battery performance degradation and increased safety risks. Existing battery early warning methods often analyze environmental parameters or electrochemical parameters in isolation, ignoring the coupling effect between the two during transient action switching, resulting in early warning delays or false alarms, and failing to accurately capture the real-time evolution of the battery's internal state. This step addresses the aforementioned issues using the following methods: Based on the sequence of mission action commands, the start and end times of cruise, hovering, and acceleration actions are determined through time node analysis, thus obtaining a mission phase division information set. Combining the information sets of internal battery compartment temperature and external hydrostatic pressure, a hysteresis response analysis method is employed to analyze the hysteresis relationship between the rate of temperature change and the rate of pressure change during the transient process of action switching (for example, the rate of pressure change may lag behind the rate of temperature change as depth increases), obtaining a temperature-pressure transient change information set. Furthermore, using electrochemical dynamic modeling techniques, based on the temperature-pressure transient change information set and combined with the battery operating voltage and battery load current, the coordinated fluctuation characteristics of ohmic polarization and concentration polarization inside the battery under external temperature-pressure change shocks are analyzed. For example, by identifying the stepwise transition process of ohmic internal resistance (such as an increase in internal resistance due to a sudden temperature change) and the suppressed process of electrolyte ion migration rate (such as a slowdown in ion diffusion due to a pressure gradient), the battery internal state information set is finally obtained.

[0047] By analyzing the interaction between temperature-pressure changes and the internal electrochemical dynamics of the battery through the method provided in this embodiment, it is possible to monitor changes in the internal state of the battery in real time, thereby improving the accuracy and timeliness of safety warnings. It also helps to identify potential risk points of the battery in complex marine environments, providing data support for optimizing battery design and operation and maintenance strategies. At the same time, by integrating multi-parameter data, the robustness and adaptability of the battery warning system are enhanced, the battery life is extended, and the reliable operation of the battery is ensured. Furthermore, it can accurately cover personalized off-grid energy demand scenarios such as homes, RVs, yachts, and cabins, becoming an effective supplement to grid-connected scenarios.

[0048] In some embodiments, based on the temperature-pressure transient change information set, the action switching stages where temperature change precedes pressure change and pressure change precedes temperature change are analyzed to obtain differentiated temperature-pressure dominated transient scenario information sets. In the action switching stage where temperature change precedes pressure change, combined with the battery operating voltage, the ohmic resistance stepwise transition process caused by the thermal expansion and contraction of the active material layer inside the battery is analyzed to obtain the thermally induced ohmic polarization dominated information set. In the action switching stage where pressure change precedes temperature change, combined with the battery load current, the process of suppressed electrolyte ion migration rate caused by the gradient effect of the external hydrostatic pressure field is analyzed to obtain the pressure-induced concentration polarization dominated information set. Based on the thermally induced ohmic polarization dominated information set and the pressure-induced concentration polarization dominated information set, the dynamic evolution path of the battery internal state, which is dominated by alternating thermally induced ohmic polarization and pressure-induced concentration polarization, is analyzed during continuous task action switching to obtain the battery internal state information set.

[0049] The differentiated temperature-pressure dominant transient scenario information set can be an information set that distinguishes two different transient scenarios. A switching phase where temperature change precedes pressure change can be one type of differentiated temperature-pressure dominant transient scenario, referring to a specific stage where the internal temperature of the battery compartment begins to change earlier than the external hydrostatic pressure change during task switching of a battery-equipped device. A switching phase where pressure change precedes temperature change can be another type of differentiated temperature-pressure dominant transient scenario, referring to a specific stage where the external hydrostatic pressure begins to change earlier than the internal temperature change of the battery compartment during task switching. The internal active material layer of the battery can be the core structural layer involved in electrochemical energy conversion within a lithium iron phosphate battery. The ohmic resistance stepwise transition process can refer to a process where, under specific conditions, the battery's ohmic resistance does not change continuously and slowly, but rather exhibits a phased, leaping increase or decrease. The thermally induced ohmic polarization dominant information set can be an information set where, during the switching phase where temperature change precedes pressure change, temperature-induced ohmic polarization becomes the main form of polarization within the battery. The external hydrostatic pressure gradient can be the pressure change gradient formed by the difference in hydrostatic pressure at different depths in the sea area where the equipment is located. The process of inhibited electrolyte ion migration rate refers to the process in which the normal migration of electrolyte ions is hindered and the migration rate decreases under the influence of the external hydrostatic pressure gradient. The information set dominated by pressure-induced concentration polarization can be the set of information characterizing that, during the action switching phase where pressure change precedes temperature change, pressure-induced concentration polarization becomes the main form of polarization within the battery. Continuous task action switching refers to the process by which the equipment continuously switches from one task action to another during task execution. The dynamic evolution path of the battery's internal state can be the trajectory of the battery's internal state changing over time, characterized by the alternating dominance of thermal ohmic polarization and pressure-induced concentration polarization during continuous task action switching.

[0050] Specifically, in complex operating environments, batteries face dynamic temperature-pressure changes. These external conditions significantly affect the electrochemical processes inside the battery. However, existing early warning methods often overlook the synergistic effect of alternating dominance of temperature and pressure during transient temperature-pressure changes, leading to an incomplete assessment of the battery's internal state. For example, during task switching, temperature changes may precede pressure changes, or vice versa. This difference can trigger different dominant modes of ohmic polarization and concentration polarization inside the battery. If these modes cannot be accurately distinguished and quantified, the dynamic evolution path of the battery's internal state cannot be captured, thereby increasing the risk of battery failure. This step addresses the aforementioned issues using the following methods: Based on the temperature-pressure transient change information set, scene recognition techniques are employed to analyze the action switching phases where temperature changes precede pressure changes (e.g., during the cruise-to-hover transition, the temperature change rate may reach 0.5°C / s), and the action switching phases where pressure changes precede temperature changes (e.g., during the hover-to-acceleration transition, the pressure change rate may reach 0.1 MPa / s), thus obtaining a differentiated temperature-pressure dominant transient scene information set. In the temperature-preceding phase, combined with the battery operating voltage (e.g., 3.2V), electrochemical impedance spectroscopy is used to analyze the ohmic resistance caused by the prior thermal expansion and contraction of the active material layer inside the battery. The internal resistance step transition process (e.g., internal resistance transitioning from 10mΩ to 15mΩ) yields the thermally induced ohmic polarization dominant information set. During the pressure change leading stage, combined with the battery load current (e.g., 50A), the ion migration rate assessment method is used to analyze the process of the electrolyte ion migration rate being suppressed due to the effect of the external hydrostatic pressure field gradient, yielding the pressure-induced concentration polarization dominant information set. Based on the thermally induced ohmic polarization dominant information set and the pressure-induced concentration polarization dominant information set, dynamic path modeling is used to analyze the dynamic evolution path of the battery internal state, which is dominated by alternating thermally induced ohmic polarization and pressure-induced concentration polarization, during continuous task action switching, yielding the battery internal state information set.

[0051] The method provided in this embodiment can accurately identify the internal state changes of the battery under different temperature-pressure transient scenarios, reveal the synergistic fluctuation law of ohmic polarization and concentration polarization, thereby improving the early warning capability of battery safety risks, enhancing the operational stability and reliability of the equipment in complex marine environments, and accurately covering other personalized off-grid energy demand scenarios (such as homes, RVs, yachts, etc.).

[0052] In some embodiments, based on the task phase segmentation information set and combined with the battery compartment internal temperature and external hydrostatic pressure information set, the dynamic shaping process of the temperature-pressure parameter combination on the survival environment of barophilic microorganisms under different task phases is analyzed, resulting in a microbial survival substrate condition information set strongly correlated with task actions; based on the microbial survival substrate condition information set and combined with the temperature-pressure transient change information set, the fluctuation law of the secretion of barophilic microbial metabolites under temperature-pressure change rate difference scenarios is analyzed, resulting in a metabolic activity dynamic response information set characterizing the strength of microbial activity; based on the microbial survival substrate condition information set and combined with the task phase segmentation information set, the cumulative growth characteristics of the attachment area and thickness of barophilic microbial biofilm over time within the temperature-pressure stable range are analyzed, resulting in a biofilm formation efficiency information set; based on the metabolic activity dynamic response information set and combined with the biofilm formation efficiency information set, the synergistic effect mechanism of the two under different temperature-pressure change modes is analyzed, resulting in a microbial erosiveness characterization information set comprehensively reflecting the potential of microorganisms to erode the battery structure.

[0053] Temperature-pressure variation refers to the dynamic changes in internal battery compartment temperature and external hydrostatic pressure during mission transitions. Barotropic microorganisms are microbial species adapted to high-pressure environments. Metabolic activity refers to the rate of microbial metabolism under specific environmental conditions. Biofilm formation capability refers to the ability of microorganisms to attach to surfaces and form multicellular structures. Microbial erosiveness characterization information set is a data set on the potential for microbial erosion of the battery structure. Mission phase division information set is a set of time points for phases such as cruise, hovering, and acceleration, divided according to the sequence of mission commands. External hydrostatic pressure information set is hydrostatic pressure data at the depth of the submersible. Microbial survival substrate conditions information set is dynamic data describing the impact of temperature-pressure parameter combinations on the microbial survival environment under different mission phases. Temperature-pressure transient change information set is data characterizing the hysteretic response relationship between temperature and pressure change rates during mission transitions. Metabolic activity dynamic response information set is data on the fluctuation of metabolic product secretion under differences in temperature-pressure change rates. Biofilm formation efficiency information set is data on the cumulative growth characteristics of biofilm attachment area and thickness within the stable temperature-pressure range.

[0054] Specifically, lithium iron phosphate batteries, operating under high pressure in the deep sea, are not only affected by internal electrochemical dynamics but also face the threat of corrosion from barophilic microorganisms. This corrosion accelerates battery failure, but existing early warning methods often overlook microbial factors, leading to incomplete risk assessments. Barophilic microorganisms adjust their metabolic activity and biofilm formation under temperature-pressure changes, thus corroding the battery casing from the outside and coupling with internal dendrite growth to form a complex failure path. This step addresses the above problems through the following methods: By combining environmental simulation with biological experiments, a dynamic temperature-pressure control method is used to analyze the information set segmented by mission phase. Combined with the information set of internal battery compartment temperature and external hydrostatic pressure, a microbial incubator is used to simulate temperature-pressure parameter combinations under different mission actions (e.g., temperature 10°C, pressure 5MPa during the cruise phase). The attachment behavior of barophilic microorganisms is observed using an optical microscope to obtain the information set of microbial survival substrate conditions. Based on this, combined with the information set of transient temperature-pressure changes, metabolite detection methods (e.g., high-performance liquid chromatography) are used to analyze scenarios with different temperature-pressure change rates (e.g., temperature change rate 0.5°C / min, pressure change rate 0.1M). The fluctuation pattern of metabolic product secretion (Pa / min) was analyzed to obtain a dynamic response information set of metabolic activity. Simultaneously, based on the information set of microbial survival substrate conditions and task stage segmentation, surface roughness measurements were used to assess the cumulative growth characteristics of biofilm attachment area and thickness within the temperature-pressure stable range (e.g., hovering stage temperature 8°C, pressure 8MPa), resulting in a biofilm formation efficiency information set. Finally, the dynamic response information set of metabolic activity and the biofilm formation efficiency information set were integrated through a synergistic analysis model, and correlation analysis was used to assess the synergistic mechanism of the two under different temperature-pressure change modes (e.g., a positive correlation between metabolic activity and biofilm formation under high temperature and high pressure modes), resulting in a microbial erosiveness characterization information set.

[0055] The method provided in this embodiment can dynamically quantify the erosion potential of barophilic microorganisms under temperature-pressure changes, accurately identify high-risk task stages, thereby providing early warning of battery failure risks, enhancing the environmental adaptability and safety reliability of the battery system, and covering personalized off-grid energy needs such as homes, RVs, and yachts. As an effective supplement to grid-connected scenarios, it provides a scientific basis for optimizing task scheduling and maintenance strategies.

[0056] In some embodiments, based on the task phase segmentation information set and combined with the battery compartment internal temperature and external hydrostatic pressure information set, the coordinated matching relationship of temperature and pressure change amplitudes during cruise, hovering, and acceleration task phases is analyzed to obtain a temperature-pressure coordinated change pattern information set driven by task actions; based on the temperature-pressure coordinated change pattern information set, the adaptive adjustment process of barophilic microbial cell membrane fluidity and enzyme activity under temperature-pressure coordinated changes is analyzed to obtain a dynamic response information set of microbial physiological state; based on the dynamic response information set of microbial physiological state and combined with the task phase segmentation information set, the dynamic changes of wettability and nutrient accessibility of microbial attachment surfaces under different task phases are analyzed to obtain a microbial survival substrate condition information set strongly correlated with task actions.

[0057] Temperature-pressure parameter combinations can be numerical pairings of temperature and pressure at specific task stages. Temperature-pressure coordinated change pattern information sets can be pattern data describing the coordinated relationship between the amplitudes of temperature and pressure changes under task-driven actions. Microbial physiological state dynamic response information sets can be dynamic data characterizing the adaptive adjustment of cell membrane fluidity and enzyme activity of barophilic microorganisms under environmental changes. Microbial attachment surface wettability can be a characterization of the degree of liquid film coverage on microbial attachment surfaces. Nutrient accessibility can be the ease with which microorganisms obtain nutrients, influenced by environmental conditions.

[0058] Specifically, when equipment performs tasks in complex marine environments, the temperature-pressure environment of the battery compartment changes frequently with the mission's actions. These changes directly affect the survival and activity of barophilic microorganisms, and the erosive behavior of microorganisms is one of the key factors leading to battery failure. Existing technologies often overlook the dynamic shaping effect of mission actions on the temperature-pressure environment, and how this dynamic environment changes the microbial survival substrate conditions (such as surface wettability and nutrient accessibility) by affecting the physiological state of microorganisms (such as cell membrane fluidity and enzyme activity), resulting in the inability to accurately predict the risk of microbial erosion. This step addresses the aforementioned issues using the following methods: Utilizing multi-source data fusion and bio-environment interaction analysis, firstly, the task phase segmentation information set is used as a time reference. Combined with sensor-collected data on internal battery compartment temperature and external hydrostatic pressure, pattern recognition is employed to analyze the coordinated matching relationship between temperature and pressure change amplitudes during the cruise, hovering, and acceleration mission phases. For example, by calculating the correlation coefficient between temperature and pressure change rates, a coordinated pattern is identified where a small temperature increase (e.g., 2°C) and a significant pressure increase (e.g., 15 MPa) occur during the cruise phase, thus obtaining a set of temperature-pressure coordinated change pattern information driven by mission actions. Then, based on this pattern information set, principles of microbial physiology and ecology are applied to analyze the temperature-pressure coordinated... The adaptive adjustment process of cell membrane fluidity and enzyme activity of barotropic microorganisms under changing conditions was studied. For example, cell membrane permeability experiments under simulated high pressure were conducted to observe membrane lipid remodeling behavior, and the impact of pressure fluctuations on the activity of key metabolic enzymes was evaluated using enzyme kinetics methods, thus obtaining a dynamic response information set of microbial physiological state. Finally, combined with the information set divided by task stage, surface characteristic analysis was used to analyze the dynamic changes in wettability and nutrient accessibility of the microbial attachment surface under different task stages. For example, the evolution of surface wettability with task actions was evaluated using contact angle measurement technology, and the transport process of nutrients on the battery compartment surface was simulated using a fluid dynamics model, thus obtaining a microbial survival substrate condition information set strongly correlated with task actions.

[0059] The method provided in this embodiment analyzes the task phase segmentation information set, the internal temperature of the battery compartment and the external hydrostatic pressure information set to determine the temperature-pressure coordinated change pattern. Based on this, through the dynamic response of microbial physiological state and the analysis of survival substrate conditions, a microbial survival substrate condition information set that can map the dynamic correlation between task actions and microbial erosion potential is constructed. This information set can provide accurate environmental input for subsequent failure path coupling analysis, and at the same time enable the early warning strategy to intervene early in high-risk task phases, improve the overall safety and reliability of the battery system, and can also accurately cover personalized off-grid energy demand scenarios such as homes, RVs, yachts, and cabins, becoming an effective supplement to grid-connected scenarios.

[0060] In some embodiments, based on the dynamic response information set of metabolic activity and combined with the temperature-pressure synergistic change pattern information set, the phase and amplitude variation patterns of metabolic activity fluctuations under different temperature-pressure synergistic change patterns are analyzed to obtain a metabolic activity pattern matching information set; based on the biofilm formation efficiency information set and combined with the temperature-pressure synergistic change pattern information set, the initiation delay and growth slope characteristics of biofilm formation efficiency under different temperature-pressure synergistic change patterns are analyzed to obtain a biofilm formation pattern matching information set; based on the metabolic activity pattern matching information set and combined with the biofilm formation pattern matching information set, the temporal coupling relationship and intensity correlation relationship between metabolic activity fluctuations and biofilm formation efficiency are analyzed to obtain a microbial erosion synergy information set; based on the microbial erosion synergy information set and combined with the task stage segmentation information set, the task action stage with the highest synergy is identified to obtain a microbial erosiveness characterization information set.

[0061] The biofilm formation efficiency information set can be a collection of information on the cumulative growth characteristics of biofilm attachment area and thickness over time within the temperature-barotropic stable range for barotropic microorganisms. The microbial erosion synergy information set can be a collection of information on the temporal coupling and intensity correlation between metabolic activity fluctuations and biofilm formation efficiency. The temporal coupling relationship can be the pattern of mutual coordination and correlation between metabolic activity fluctuations and biofilm formation efficiency over time. The intensity correlation relationship can be the degree of mutual influence between the amplitude of metabolic activity fluctuations and the growth rate of biofilm formation efficiency. The task action phase with the highest synergy can be the specific task action phase in the task phase segmentation information set where the microbial erosion synergy reaches its peak.

[0062] Specifically, in the safety early warning system for lithium iron phosphate batteries, microbial erosion is a key external risk factor that distinguishes it from internal electrochemical failure. It's worth noting that lithium iron phosphate batteries are not only suitable for marine unmanned equipment but can also precisely cover personalized off-grid energy scenarios such as homes, RVs, yachts, and cabins, becoming an effective supplement to grid-connected scenarios. Furthermore, microbial erosion of batteries is not the result of a single independent action of "metabolic activity" or "biofilm formation," but rather a product of the synergistic effect of both under the unique temperature and pressure environment of the ocean. Therefore, analyzing metabolic activity or biofilm formation efficiency in isolation cannot comprehensively and accurately assess the actual erosion potential of microorganisms. This step addresses the aforementioned issues using the following methods: First, based on the dynamic response information set of metabolic activity and combined with the temperature-pressure co-variation pattern information set, pattern recognition techniques are employed to analyze the phase and amplitude variation patterns of metabolic activity fluctuations under different temperature-pressure co-variation patterns. For example, by calculating the phase difference and amplitude ratio, a metabolic activity pattern matching information set is obtained. Next, based on the biofilm formation efficiency information set and combined with the temperature-pressure co-variation pattern information set, trend analysis methods are used to analyze the initiation delay and growth slope characteristics of biofilm formation efficiency under different temperature-pressure co-variation patterns. For example, by fitting growth curves, delay time and slope values ​​are extracted. The process involves obtaining a biofilm formation pattern matching information set. Then, based on the metabolic activity pattern matching information set and the biofilm formation pattern matching information set, correlation analysis and temporal alignment techniques are used to analyze the temporal coupling and intensity correlation between metabolic activity fluctuations and biofilm formation efficiency. For example, by calculating correlation coefficients and synchronicity indices, a microbial erosion synergy information set is obtained. Finally, based on the microbial erosion synergy information set and combined with the task stage segmentation information set, peak detection methods are used to identify the task action stage with the highest synergy. For example, by finding the stage corresponding to the maximum synergy value, a microbial erosiveness characterization information set is obtained.

[0063] The method provided in this embodiment can comprehensively quantify the synergistic effect of microbial metabolic activity and biofilm formation under temperature-pressure change mode, accurately identify the task action stage with the highest potential for microbial erosion, thereby providing accurate input information for battery safety early warning, enhancing the ability to predict battery failure risks, effectively guiding the formulation of risk mitigation strategies, extending battery life, and improving the operational reliability of equipment.

[0064] In some embodiments, based on the dominant information set of thermally induced ohmic polarization and combined with the dominant information set of pressure-induced concentration polarization, the local overheating phenomenon caused by the stepwise transition of ohmic internal resistance is analyzed during the action switching stage where temperature change precedes pressure change. This accelerates the fluctuation of metabolite secretion by barophilic microorganisms during the task action stage with the highest degree of synergy, thus obtaining a thermal-microbial synergistic corrosion path information set. Based on the dominant information set of pressure-induced concentration polarization and combined with the dominant information set of thermally induced ohmic polarization, the inhibition of electrolyte ion migration rate during the action switching stage where pressure change precedes temperature change is analyzed. The uneven deposition of lithium ions caused by the biofilm preferentially induces dendrite nucleation at local stress concentration points caused by the biofilm's adhesion area and thickness, resulting in a pressure-biofilm synergistic dendrite path information set. Based on the heat-microorganism synergistic corrosion path information set, combined with the pressure-biofilm synergistic dendrite path information set, the spatiotemporal evolution of microcracks formed by the infiltration and corrosion of the battery shell by microbial metabolites from the outside to the inside, and microchannels formed by dendrites growing from the inside to the outside and piercing the separator, which are connected in the weak areas of the battery structure and form failure acceleration channels, is analyzed, resulting in a failure path coupling situation information set.

[0065] The thermal-microbial synergistic corrosion pathway information set can be a set of information reflecting the external corrosion process of the battery, formed during the action switching phase where temperature changes precede pressure changes, and the local overheating phenomenon caused by thermally induced ohmic polarization accelerates the fluctuation of the secretion of barophilic microbial metabolites under specific task stages. The pressure-biofilm synergistic dendrite pathway information set can be a set of information reflecting the internal dendrite growth process of the battery, formed during the action switching phase where pressure changes precede temperature changes, and the uneven deposition of lithium ions due to suppressed electrolyte ion migration rates preferentially forms dendrites at local stress concentration points caused by biofilm adhesion. Microbial metabolites can be various substances secreted by barophilic microorganisms during metabolism, which can have a penetrating corrosion effect on the battery casing. Microcracks can be tiny cracks formed on the surface of the battery casing after microbial metabolites penetrate and corrode it from the outside in. Dendrites can be dendritic crystals formed by uneven deposition of lithium ions inside the battery, which can puncture the separator and affect battery safety. Microchannels can be tiny channels formed on the separator after dendrites grow from the inside out and puncture it. Weak areas in battery structure refer to parts of the battery's internal structure that are low in strength and prone to failure, such as the battery casing-separator interface area. Accelerated failure pathways can be channels formed by microcracks and microchannels penetrating weak areas of the battery structure, accelerating the overall failure of the battery.

[0066] Specifically, the lithium iron phosphate batteries in underwater equipment operate in a unique environment. Their failure process is not caused by a single factor or a single path, but is the result of the interaction and synergistic effect of multiple failure paths under the combined action of internal electrochemical changes and external microbial erosion. When a submersible performs different missions, the dynamic changes in the temperature and pressure environment faced by the battery can trigger the alternating dominance of internal ohmic polarization and concentration polarization, and affect the metabolic activity and biofilm formation of barophilic microorganisms. This, in turn, fosters corrosion pathways from the outside in and dendrite growth pathways from the inside out. These two pathways do not evolve independently, but rather have a complex coupling relationship. This step addresses the above problems through the following methods: First, based on the information sets of thermally induced ohmic polarization and barophilic concentration polarization, thermodynamic analysis is used to identify the action switching stage (such as the cruise phase) in which temperature changes precede pressure changes. The local overheating phenomenon caused by the stepwise transition of ohmic internal resistance (such as the temperature rising to 50°C) is evaluated. Combined with the microbial erosiveness characterization information set, it is analyzed how this local overheating accelerates the fluctuation of the secretion of metabolites by barophilic microorganisms (such as the secretion increasing to 0.2 mg / L), thereby forming a thermo-microbial synergistic corrosion pathway. Simultaneously, electrochemical analysis is used to identify the action switching stage (such as the hovering stage) where pressure changes precede temperature changes. The uneven deposition of lithium ions caused by the suppressed migration rate of electrolyte ions is evaluated. Combined with the biofilm formation efficiency information set, the analysis is conducted on how local stress concentration points caused by biofilm adhesion (such as adhesion area up to 5 mm2) preferentially induce dendrite nucleation, thus forming a pressure-biofilm synergistic dendrite path. Then, using coupling analysis, the thermal-microbial synergistic corrosion path and the pressure-biofilm synergistic dendrite path are integrated. The analysis is conducted on the spatiotemporal evolution of microcracks (such as crack length up to 0.1 mm) formed by the infiltration and corrosion of the battery shell by microbial metabolites from the outside to the inside, and microchannels (such as channel diameter up to 0.05 mm) formed by dendrites growing from the inside to the outside and piercing the separator, which connect in weak areas of the battery structure (such as the shell-separator interface) and form failure acceleration channels, thus obtaining a failure path coupling situation information set.

[0067] The method provided in this embodiment can comprehensively analyze the multi-path coupling mechanism of battery failure, identify failure acceleration channels in advance, thereby enhancing the accuracy of early warning, providing data support for dynamically optimizing risk mitigation strategies, and effectively extending the service life of batteries in harsh marine environments.

[0068] In some embodiments, based on the thermal-microbial synergistic corrosion path information set and combined with the task phase segmentation information set, the analysis shows that during the action switching stage where temperature change precedes pressure change, local overheating caused by thermally induced ohmic polarization preferentially induces pitting corrosion in the biofilm-covered area, thereby guiding microcracks to propagate directionally along the biofilm edge, resulting in a microcrack bio-guided propagation information set; based on the pressure-biofilm synergistic dendrite path information set and combined with the task phase segmentation information set, the analysis shows that during the action switching stage where pressure change precedes temperature change, local stress concentration caused by biofilm adhesion alters the lithium-ion flow field distribution, thereby guiding dendritic microchannels to preferentially grow towards the stress concentration area, resulting in a microchannel stress-guided growth information set; based on the microcrack bio-guided propagation information set and combined with the microchannel stress-guided growth information set, the spatiotemporal competition and synergy between outside-to-inside bioguided cracks and inside-to-outside stress-guided channels are analyzed: when the two evolve towards each other in the battery shell-separator interface region, the failure acceleration effect caused by path coupling is identified; when the two develop in a misaligned manner, the failure risk delayed due to path separation is assessed, resulting in a failure path coupling situation information set.

[0069] Biofilm coverage areas can be specific regions on the battery surface where barophilic microorganisms form biofilms, the area and thickness of which dynamically change with the stage of the mission. Pitting corrosion can be a localized corrosion pitting phenomenon on the battery casing surface under the synergistic effect of thermally induced local overheating and biofilm, serving as the starting point for microcrack initiation. Bio-directed propagation can be the evolutionary characteristic of microcracks growing directionally along the edge of the biofilm, influenced by the synergistic effect of the biofilm and the corrosive environment. Local stress concentration can be a region of localized mechanical stress accumulation caused by uneven thickness of the biofilm after it adheres to the battery surface. Lithium-ion flow field distribution can be the spatial distribution of lithium-ion migration inside the battery, its uniformity being influenced by both external pressure and biofilm stress. Dendritic microchannels can be tiny channels formed by dendrite growth piercing the separator, their growth direction guided by stress concentration areas. Stress-directed growth can be the evolutionary characteristic of dendritic microchannels preferentially growing towards local stress concentration areas. The battery casing-separator interface region can be the transition region between the battery casing and the internal separator, and is one of the weak points in the battery structure. Accelerated failure can refer to the phenomenon where bio-directed cracks and stress-directed channels penetrate into weak areas, leading to a faster battery failure process. Delayed failure risk can refer to the state where battery failure time is prolonged when bio-directed cracks and stress-directed channels develop in a misaligned manner.

[0070] Specifically, in the failure process of lithium iron phosphate batteries, the analysis of a single failure path cannot fully reveal the evolution mechanism of battery safety hazards. Especially under complex operating conditions, battery failure is often the result of the combined effects of two pathways: external corrosion and internal dendrite growth. Previous analyses have identified the existence of the thermo-microbial synergistic corrosion pathway and the pressure-biofilm synergistic dendrite pathway, but have not delved into the interaction between these two pathways in the spatiotemporal dimensions. In fact, the microcracks formed by microbial corrosion and the microchannels formed by dendrite growth do not evolve independently; their interaction in the weak areas of the battery structure directly determines the speed and mode of battery failure. Without an understanding of this coupling relationship... Analysis alone cannot accurately determine the critical points of battery failure. This step addresses this issue using the following method: Through multiphysics coupling analysis and spatiotemporal evolution modeling, firstly, based on the information set of the thermal-microbial synergistic corrosion path and the information set divided by task stage, in the action switching stage where temperature change precedes pressure change (e.g., the rate of temperature change is 0.5°C / s faster than the rate of pressure change), local overheating induced by thermal ohmic polarization is utilized (e.g., the local battery temperature rises above 50°C). Combined with the pitting corrosion characteristics of the biofilm-covered area (e.g., the biofilm coverage area reaches 30% of the battery casing), microcrack propagation simulation is employed to guide microcrack propagation. Cracks propagate directionally along the edge of the biofilm (e.g., crack propagation rate of 0.01 mm / h), generating a microcrack bioguided propagation information set. Then, based on the pressure-biofilm synergistic dendrite path information set and the task stage segmentation information set, during the action switching stage where pressure change precedes temperature change (e.g., pressure change rate is 0.2 MPa / s higher than temperature change rate), local stress concentration caused by biofilm adhesion (e.g., stress concentration factor of 1.5) is utilized. Lithium-ion flow field perturbation analysis methods are applied to alter the lithium-ion migration distribution (e.g., lithium-ion migration rate decreases by 20%), and dendrite growth guidance technology is employed to guide the dendrite microchannels towards the stress concentration. Preferential growth in the central region (e.g., dendrite growth length of 5 μm) generates a microchannel stress-guided growth information set. Finally, based on the microcrack bio-guided propagation information set and the microchannel stress-guided growth information set, a path coupling assessment model and risk dynamic quantification method are used to analyze the spatiotemporal competition and synergy between bio-guided cracks and stress-guided channels in the battery shell-separator interface region (e.g., interface thickness of 0.05 mm). When the two evolve towards each other, the failure acceleration effect is identified (e.g., failure time is shortened by 30%), and when the two develop in a misaligned manner, the failure risk delay is assessed (e.g., failure risk is reduced by 20%), thereby obtaining a failure path coupling situation information set.

[0071] By analyzing the coupling state of failure paths through the method provided in this embodiment, it is possible to identify the failure acceleration channels of batteries in marine environments in advance, effectively prevent sudden battery failures caused by path coupling, and improve the accuracy and real-time performance of safety warnings. At the same time, by evaluating the risk delay in path separation scenarios, the battery maintenance strategy is optimized, the battery life is extended, and the reliability and continuity of the equipment in complex tasks are enhanced.

[0072] In some embodiments, based on the failure path coupling situation information set and the task stage segmentation information set, the dynamic erosion rate caused to the battery safety boundary when the bio-guided cracks from the outside to the inside and the stress-guided channels from the inside to the outside evolve in opposite directions is analyzed to obtain the composite stress intensity information set; based on the composite stress intensity information set and the microbial erosion synergy information set, the task action stage where the composite stress intensity exceeds the safety threshold and the microbial erosion synergy reaches its peak is identified to obtain the key risk intervention window information set; based on the key risk intervention window information set, a risk mitigation and early warning strategy with the core of adjusting the task action sequence, activating active thermal compensation and electrolyte flow field optimization is generated, and the strategy-driven battery state regulation is executed, outputting a battery safety state intervention process log that records the regulation parameters and the evolution of the safety state.

[0073] The composite stress intensity information set can be a quantitative information on the dynamic erosion rate caused by multiple failure paths to the overall battery safety boundary. The key risk intervention window information set can be a task action stage representing when the composite stress intensity exceeds the safety threshold (e.g., 0.5 units) and the microbial erosion synergy reaches its peak (e.g., 0.8 units), used to identify high-risk periods. The risk mitigation and early warning strategy can be a dynamic optimization strategy centered on adjusting the timing of task actions, activating active thermal compensation, and optimizing the electrolyte flow field, used to mitigate battery safety risks.

[0074] Specifically, in complex operating environments, lithium iron phosphate batteries face multiple challenges in safety early warning systems. On the one hand, the internal electrochemical dynamics of the battery are impacted by external temperature and pressure changes, easily triggering abnormal ohmic and concentration polarization, leading to local overheating or hindered ion migration. On the other hand, barophilic microorganisms exhibit enhanced metabolic activity and biofilm formation under temperature and pressure changes, corroding the battery structure from the outside and forming microcracks. Simultaneously, dendrite growth inside the battery preferentially nucleates at stress concentration points, forming microchannels. These corrosion paths from the outside in and dendrite growth paths from the inside out may couple during the failure process. For example, microcracks and microchannels may connect at the battery shell-separator interface, forming a failure acceleration channel that significantly shortens the battery safety boundary. Existing early warning methods often consider electrochemical or environmental factors in isolation, lacking dynamic analysis of the coupling relationship of multiple failure paths, resulting in delayed early warnings or overgeneralized strategies that cannot accurately address the complex stresses in marine environments. This step addresses the aforementioned issues using the following method: Based on the failure path coupling situation information set and combined with the task phase segmentation information set, dynamic erosion rate analysis is employed to assess the dynamic erosion rate (e.g., erosion depth increase of 0.1 micrometers per second) caused by the opposing evolution of bio-guided cracks from the outside to the inside and stress-guided channels from the inside to the outside, thus obtaining a composite stress intensity information set. Then, based on the composite stress intensity information set and combined with the microbial erosion synergy information set, threshold comparison and peak detection methods are used to identify task action phases (e.g., acceleration phases) where the composite stress intensity exceeds the safety threshold (e.g., 0.5 units) and the microbial erosion synergy reaches its peak value (e.g., 0.8 units). A key risk intervention window information set is obtained. Finally, based on the key risk intervention window information set, a strategy generation algorithm is used to generate a risk mitigation and early warning strategy with the core of adjusting the timing of task actions (such as delaying acceleration actions to the temperature-pressure stabilization stage), activating active thermal compensation (such as starting PTC heating elements to maintain the battery compartment temperature above 20°C), and optimizing the electrolyte flow field (such as adjusting the electrolyte flow rate to 0.2 mL / min through a micropump). The strategy-driven battery state regulation is executed, and a battery safety state intervention process log is output, which records the regulation parameters (such as temperature setpoint 25°C and flow rate 0.2 mL / min) and the evolution of the safety state (such as the improvement of dendrite growth inhibition rate).

[0075] The method provided in this embodiment can effectively address the multiple failure risks faced by lithium iron phosphate batteries, improve battery safety and reliability, extend battery life, reduce underwater vehicle mission interruptions caused by battery failure, and improve overall energy management efficiency.

[0076] Figure 3 A schematic diagram of a safety early warning system for lithium iron phosphate batteries based on multi-parameter fusion is provided as an embodiment of this application, as shown below. Figure 3As shown, a lithium iron phosphate battery safety early warning system 300 based on multi-parameter fusion in this embodiment includes: a state analysis module 301, an erosion characterization module 302, a coupled situation module 303, and an early warning intervention module 304.

[0077] The state analysis module 301 is used to acquire a battery operating condition dataset. Based on the battery operating condition dataset, it analyzes the interaction between temperature-pressure changes caused by different task actions and the internal electrochemical dynamics of the battery to obtain a battery internal state information set. The corrosion characterization module 302 is used to analyze the influence of temperature-pressure changes on the metabolic activity and biofilm formation ability of barophilic microorganisms based on the battery operating condition dataset to obtain a microbial erosiveness characterization information set. The coupling situation module 303 is used to analyze the coupling relationship between the corrosion path from the outside to the inside and the dendrite growth path from the inside to the outside in the battery failure process based on the battery internal state information set and the microbial erosiveness characterization information set to obtain a failure path coupling situation information set. The early warning intervention module 304 is used to analyze the combined stress intensity of multiple failure paths on the overall safety boundary of the battery based on the failure path coupling situation information set, generate a dynamically optimized risk mitigation early warning strategy, and output a battery safety state intervention process log.

[0078] Optionally, the state analysis module 301, when acquiring the battery operating condition dataset and analyzing the interaction between temperature-pressure changes caused by different task actions and the internal electrochemical dynamics of the battery based on the battery operating condition dataset to obtain the battery internal state information set, is specifically used for:

[0079] The battery operating condition dataset includes a sequence of mission action commands, internal temperature of the battery compartment, external hydrostatic pressure information, battery operating voltage, and battery load current. Based on the sequence of mission action commands, the start and end times of cruise, hovering, and acceleration actions are determined, resulting in a mission phase segmentation information set. Based on the mission phase segmentation information set, combined with the internal temperature of the battery compartment and the external hydrostatic pressure information set, the hysteresis response relationship between the rate of temperature change and the rate of pressure change during the transient process of action switching is analyzed, resulting in a temperature-pressure transient change information set characterizing the dynamic impact of the external marine environment on the battery compartment. Based on the temperature-pressure transient change information set, combined with the battery operating voltage and the battery load current, the coordinated fluctuation characteristics of ohmic polarization and concentration polarization inside the battery are analyzed under external temperature-pressure change impact, resulting in a battery internal state information set.

[0080] Optionally, the state analysis module 301, when analyzing the coordinated fluctuation characteristics of ohmic polarization and concentration polarization inside the battery under external temperature-pressure change shocks based on the temperature-pressure transient change information set, combined with the battery operating voltage and the battery load current, to obtain the battery internal state information set, is specifically used for:

[0081] Based on the temperature-pressure transient change information set, the action switching stages where temperature change precedes pressure change and pressure change precedes temperature change are analyzed, resulting in a differentiated temperature-pressure dominated transient scenario information set. In the action switching stage where temperature change precedes pressure change, combined with the battery operating voltage, the ohmic resistance stepwise transition process caused by the prior thermal expansion and contraction of the battery's internal active material layer is analyzed, resulting in a thermo-induced ohmic polarization dominated information set. In the action switching stage where pressure change precedes temperature change, combined with the battery load current, the process of suppressed electrolyte ion migration rate due to the external hydrostatic pressure field gradient is analyzed, resulting in a pressure-induced concentration polarization dominated information set. Based on the thermo-induced ohmic polarization dominated information set and the pressure-induced concentration polarization dominated information set, the dynamic evolution path of the battery's internal state, characterized by the alternating dominance of thermo-induced ohmic polarization and pressure-induced concentration polarization, is analyzed during continuous task action switching, resulting in a battery internal state information set.

[0082] Optionally, the erosion characterization module 302, when analyzing the effects of temperature-pressure changes on the metabolic activity and biofilm formation ability of barophilic microorganisms based on the battery operating condition dataset to obtain a microbial erosiveness characterization information set, is specifically used for:

[0083] Based on the task phase segmentation information set, combined with the battery compartment internal temperature and external hydrostatic pressure information set, the dynamic shaping process of the temperature-pressure parameter combination on the survival environment of barophilic microorganisms under different task phases is analyzed, resulting in a microbial survival substrate condition information set strongly correlated with task actions; based on the microbial survival substrate condition information set, combined with the temperature-pressure transient change information set, the fluctuation law of the secretion of barophilic microbial metabolites under temperature-pressure change rate difference scenarios is analyzed, resulting in a metabolic activity dynamic response information set characterizing the strength of microbial activity; based on the microbial survival substrate condition information set, combined with the task phase segmentation information set, the cumulative growth characteristics of the attachment area and thickness of barophilic microbial biofilm over time within the temperature-pressure stable range are analyzed, resulting in a biofilm formation efficiency information set; based on the metabolic activity dynamic response information set, combined with the biofilm formation efficiency information set, the synergistic effect mechanism of the two under different temperature-pressure change modes is analyzed, resulting in a microbial erosiveness characterization information set comprehensively reflecting the potential of microorganisms to erode the battery structure.

[0084] Optionally, the erosion characterization module 302, when analyzing the dynamic shaping process of the temperature-pressure parameter combination on the survival environment of barophilic microorganisms under different task stages by dividing the information set based on the task stage and combining the information set of the battery compartment internal temperature and the external hydrostatic pressure, and obtaining the information set of microbial survival substrate conditions strongly correlated with the task actions, is specifically used for:

[0085] Based on the task phase segmentation information set, combined with the battery compartment internal temperature and external hydrostatic pressure information set, the coordinated matching relationship of temperature and pressure change amplitudes during the cruise, hovering, and acceleration task phases is analyzed to obtain a temperature-pressure coordinated change pattern information set driven by task actions. Based on the temperature-pressure coordinated change pattern information set, the adaptive adjustment process of barophilic microbial cell membrane fluidity and enzyme activity under temperature-pressure coordinated changes is analyzed to obtain a dynamic response information set of microbial physiological states. Based on the dynamic response information set of microbial physiological states, combined with the task phase segmentation information set, the dynamic changes in the wettability and nutrient accessibility of microbial attachment surfaces under different task phases are analyzed to obtain a microbial survival substrate condition information set strongly correlated with task actions.

[0086] Optionally, the erosion characterization module 302, when analyzing the synergistic mechanism of the metabolic activity dynamic response information set and the biofilm formation efficiency information set under different temperature-pressure change modes to obtain a comprehensive microbial erosiveness characterization information set reflecting the potential of microorganisms to erode the battery structure, is specifically used for:

[0087] Based on the dynamic response information set of metabolic activity and the information set of temperature-pressure synergistic change patterns, the phase and amplitude variation patterns of metabolic activity fluctuations under different temperature-pressure synergistic change patterns are analyzed to obtain a metabolic activity pattern matching information set. Based on the biofilm formation efficiency information set and the information set of temperature-pressure synergistic change patterns, the initiation delay and growth slope characteristics of biofilm formation efficiency under different temperature-pressure synergistic change patterns are analyzed to obtain a biofilm formation pattern matching information set. Based on the metabolic activity pattern matching information set and the biofilm formation pattern matching information set, the temporal coupling relationship and intensity correlation between metabolic activity fluctuations and biofilm formation efficiency are analyzed to obtain a microbial erosion synergy information set. Based on the microbial erosion synergy information set and the task stage segmentation information set, the task action stage with the highest synergy is identified to obtain the microbial erosiveness characterization information set.

[0088] Optionally, the coupling situation module 303, when analyzing the coupling relationship between the corrosion path from the outside to the inside and the dendrite growth path from the inside to the outside during the battery failure process based on the battery internal state information set and the microbial erosiveness characterization information set, and obtaining the failure path coupling situation information set, is specifically used for:

[0089] Based on the dominant information set of thermally induced ohmic polarization and the dominant information set of pressure-induced concentration polarization, the local overheating phenomenon caused by the stepwise transition of ohmic resistance during the action switching phase where temperature change precedes pressure change is analyzed. This accelerates the fluctuation of metabolic product secretion by barophilic microorganisms during the task action phase with the highest degree of synergy, thus obtaining a thermal-microbial synergistic corrosion path information set. Based on the dominant information set of pressure-induced concentration polarization and the dominant information set of thermally induced ohmic polarization, the suppression of electrolyte ion migration rate during the action switching phase where pressure change precedes temperature change is analyzed. The uneven deposition of lithium ions preferentially induces dendrite nucleation at local stress concentration points caused by the biofilm adhesion area and thickness, resulting in a pressure-biofilm synergistic dendrite path information set. Based on the heat-microorganism synergistic corrosion path information set, combined with the pressure-biofilm synergistic dendrite path information set, the spatiotemporal evolution law of microcracks formed by the infiltration and corrosion of the battery shell by microbial metabolites from the outside to the inside, and microchannels formed by dendrites growing from the inside to the outside and piercing the separator, which are connected in the weak areas of the battery structure and form failure acceleration channels, is obtained, resulting in the failure path coupling situation information set.

[0090] Optionally, the coupling situation module 303, when analyzing the spatiotemporal evolution of microcracks formed by the infiltration and corrosion of the battery shell by microbial metabolites from the outside to the inside, and microchannels formed by dendrites growing from the inside to the outside and piercing the separator, based on the thermal-microbial synergistic corrosion path information set and combined with the pressure-biofilm synergistic dendrite path information set, and obtaining the failure path coupling situation information set, is specifically used for:

[0091] Based on the aforementioned thermo-microbial synergistic corrosion path information set, combined with the aforementioned task phase segmentation information set, it is analyzed that during the action switching phase where temperature change precedes pressure change, local overheating caused by thermally induced ohmic polarization preferentially induces pitting corrosion in the biofilm-covered area, thereby guiding microcracks to propagate directionally along the biofilm edge, thus obtaining a microcrack bioguided propagation information set; based on the aforementioned pressure-biofilm synergistic dendrite path information set, combined with the aforementioned task phase segmentation information set, it is analyzed that during the action switching phase where pressure change precedes temperature change, local stress concentration caused by biofilm adhesion alters lithium-ion flow. Field distribution guides dendritic microchannels to preferentially grow towards stress concentration regions, resulting in a microchannel stress-guided growth information set. Based on the microcrack bio-guided expansion information set, combined with the microchannel stress-guided growth information set, the spatiotemporal competition and synergy between the outside-to-inside bio-guided cracks and the inside-to-outside stress-guided channels are analyzed: when the two evolve towards each other in the battery shell-separator interface region, the failure acceleration effect caused by path coupling is identified; when the two develop in a misaligned manner, the failure risk delayed due to path separation is assessed, resulting in the failure path coupling situation information set.

[0092] Optionally, the early warning intervention module 304, when analyzing the combined stress intensity of multiple failure paths on the overall battery safety boundary based on the failure path coupling situation information set, generating a dynamically optimized risk mitigation early warning strategy, and outputting a battery safety status intervention process log, is specifically used for:

[0093] Based on the failure path coupling situation information set and the task stage segmentation information set, the dynamic erosion rate caused to the battery safety boundary when the bio-guided cracks from the outside to the inside and the stress-guided channels from the inside to the outside evolve in opposite directions is analyzed, resulting in a composite stress intensity information set. Based on the composite stress intensity information set and the microbial erosion synergy information set, the task action stage where the composite stress intensity exceeds the safety threshold and the microbial erosion synergy reaches its peak is identified, resulting in a key risk intervention window information set. Based on the key risk intervention window information set, a risk mitigation and early warning strategy is generated, which focuses on adjusting the task action sequence, activating active thermal compensation, and optimizing the electrolyte flow field. The strategy-driven battery state regulation is executed, and a battery safety state intervention process log recording the regulation parameters and the evolution of the safety state is output.

[0094] The system in this embodiment can be used to execute the methods of any of the above embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

Claims

1. A safety early warning method for lithium iron phosphate batteries based on multi-parameter fusion, characterized in that, include: Obtain a battery condition dataset, which includes a sequence of task action instructions, internal temperature of the battery compartment, external hydrostatic pressure information, battery operating voltage, and battery load current. Based on the sequence of mission action instructions, the start and end time points of cruise, hovering and acceleration actions are determined to obtain a set of mission phase division information. Based on the information set divided into mission phases, and combined with the information set of internal temperature of the battery compartment and external hydrostatic pressure, the hysteresis response relationship between the rate of temperature change and the rate of pressure change during the transient process of action switching is analyzed, and the information set of temperature-pressure transient changes characterizing the dynamic impact of the external marine environment on the battery compartment is obtained. Based on the temperature-pressure transient change information set, the action switching phase in which temperature change precedes pressure change and the action switching phase in which pressure change precedes temperature change are analyzed, resulting in a differentiated temperature-pressure dominant transient scenario information set. During the action switching phase where the temperature change precedes the pressure change, the ohmic resistance step transition process caused by the thermal expansion and contraction of the active material layer inside the battery is analyzed in conjunction with the battery operating voltage, and the thermally induced ohmic polarization dominant information set is obtained. During the action switching phase where the pressure change precedes the temperature change, the process of the electrolyte ion migration rate being suppressed due to the effect of the external hydrostatic pressure field gradient is analyzed in conjunction with the battery load current to obtain the pressure-induced concentration polarization dominant information set. Based on the thermally ohmic polarization-dominated information set and the compressive concentration polarization-dominated information set, the dynamic evolution path of the battery's internal state, which is alternately dominated by thermally ohmic polarization and compressive concentration polarization, is analyzed during continuous task action switching, and the battery's internal state information set is obtained. Based on the battery operating condition dataset, the effects of temperature-pressure changes on the metabolic activity and biofilm formation ability of barophilic microorganisms were analyzed, and a set of microbial erosiveness characterization information was obtained. Based on the thermally induced ohmic polarization dominant information set and the pressure-induced concentration polarization dominant information set, the local overheating phenomenon caused by the stepwise transition of ohmic internal resistance is analyzed in the action switching stage where temperature change precedes pressure change. This accelerates the fluctuation of the secretion of metabolites of barophilic microorganisms in the task action stage with the highest synergy in the microbial erosive characterization information set, thus obtaining the thermal-microbial synergistic corrosion path information set. Based on the pressure-induced concentration polarization dominant information set and the thermally induced ohmic polarization dominant information set, the analysis shows that during the action switching stage where pressure change precedes temperature change, the uneven deposition of lithium ions caused by the suppression of electrolyte ion migration rate preferentially induces dendrite nucleation at local stress concentration points caused by the biofilm attachment area and thickness, thus obtaining the pressure-biofilm synergistic dendrite path information set. Based on the thermal-microbial synergistic corrosion path information set and the pressure-biofilm synergistic dendrite path information set, the spatiotemporal evolution law of microcracks formed by the infiltration and corrosion of the battery shell by microbial metabolites from the outside to the inside, and microchannels formed by dendrites growing from the inside to the outside and piercing the membrane, which are connected in the weak area of ​​the battery structure and form failure acceleration channels, is analyzed to obtain the failure path coupling situation information set. Based on the failure path coupling situation information set, the combined stress intensity of multiple failure paths on the overall safety boundary of the battery is analyzed, a dynamically optimized risk mitigation and early warning strategy is generated, and a battery safety status intervention process log is output.

2. The method according to claim 1, characterized in that, Based on the battery operating condition dataset, the effects of temperature-pressure changes on the metabolic activity and biofilm formation ability of barophilic microorganisms are analyzed to obtain a microbial erosiveness characterization information set, including: Based on the information set divided by the task phase, and combined with the information set of the internal temperature of the battery compartment and the external hydrostatic pressure, the dynamic shaping process of the temperature-pressure parameter combination on the survival environment of barophilic microorganisms under different task phases is analyzed, and the information set of microbial survival base conditions strongly correlated with the task actions is obtained. Based on the microbial survival baseline condition information set and the temperature-pressure transient change information set, the fluctuation pattern of the secretion of metabolites of barophilic microorganisms under the scenario of temperature-pressure change rate difference is analyzed, and a dynamic response information set of metabolic activity characterizing the strength of microbial activity is obtained. Based on the microbial survival substrate condition information set and the task stage division information set, the cumulative growth characteristics of the attachment area and thickness of the barophilic microbial biofilm over time are analyzed within the temperature-pressure stability range, and a biofilm formation efficiency information set is obtained. Based on the dynamic response information set of metabolic activity and the information set of biofilm formation efficiency, the synergistic mechanism of the two under different temperature-pressure change modes is analyzed to obtain a microbial erosion characterization information set that comprehensively reflects the potential of microorganisms to erode battery structures.

3. The method according to claim 2, characterized in that, The information set based on the task phase, combined with the information sets of the internal temperature of the battery compartment and the external hydrostatic pressure, analyzes the dynamic shaping process of the survival environment of barophilic microorganisms by the combination of temperature and pressure parameters under different task phases, and obtains a set of microbial survival substrate conditions strongly correlated with task actions, including: Based on the information set divided into mission phases, and combined with the information set of internal temperature of the battery compartment and external hydrostatic pressure, the coordinated matching relationship of temperature and pressure change amplitudes in the cruise, hovering and acceleration mission phases is analyzed to obtain the information set of temperature-pressure coordinated change mode driven by mission actions. Based on the temperature-pressure coordinated change pattern information set, the adaptive adjustment process of cell membrane fluidity and enzyme activity of barophilic microorganisms under temperature-pressure coordinated change is analyzed, and a dynamic response information set of microbial physiological state is obtained. Based on the dynamic response information set of the microbial physiological state, combined with the information set of the task stage division, the dynamic changes in the wettability and nutrient accessibility of the microbial attachment surface under different task stages are analyzed to obtain the information set of microbial survival substrate conditions that are strongly correlated with the task actions.

4. The method according to claim 3, characterized in that, Based on the dynamic response information set of metabolic activity and the information set of biofilm formation efficiency, the synergistic mechanism of the two under different temperature-pressure change modes is analyzed to obtain a comprehensive microbial erosion characterization information set that reflects the potential of microorganisms to erode battery structures, including: Based on the dynamic response information set of metabolic activity and the information set of temperature-pressure coordinated change patterns, the phase and amplitude variation patterns of metabolic activity fluctuations under different temperature-pressure coordinated change patterns are analyzed to obtain the metabolic activity pattern matching information set. Based on the biofilm formation efficiency information set and the temperature-pressure coordinated change mode information set, the initiation delay and growth slope characteristics of biofilm formation efficiency under different temperature-pressure coordinated change modes are analyzed to obtain a biofilm formation mode matching information set. Based on the metabolic activity pattern matching information set and the biofilm formation pattern matching information set, the temporal coupling relationship and intensity correlation between metabolic activity fluctuations and biofilm formation efficiency are analyzed to obtain the microbial erosion synergy information set. Based on the microbial erosion synergy information set and combined with the task stage segmentation information set, the task action stage with the highest synergy is identified, and the microbial erosiveness characterization information set is obtained.

5. The method according to claim 4, characterized in that, Based on the thermal-microbial synergistic corrosion path information set and combined with the pressure-biofilm synergistic dendrite path information set, the spatiotemporal evolution of microcracks formed by the infiltration and corrosion of the battery shell by microbial metabolites from the outside to the inside, and microchannels formed by dendrites growing from the inside to the outside and puncturing the separator, which connect in weak areas of the battery structure and form accelerated failure channels, is analyzed to obtain the failure path coupling situation information set, including: Based on the thermal-microbial synergistic corrosion path information set and the task stage segmentation information set, it is analyzed that in the action switching stage where temperature change precedes pressure change, local overheating caused by thermal ohmic polarization preferentially induces pitting corrosion in the biofilm-covered area, thereby guiding microcracks to propagate directionally along the biofilm edge, thus obtaining the microcrack biological-guided propagation information set. Based on the pressure-biofilm synergistic dendrite path information set and the task stage division information set, the analysis shows that in the action switching stage where pressure change precedes temperature change, the local stress concentration caused by biofilm adhesion changes the lithium-ion flow field distribution, thereby guiding the dendrite microchannel to preferentially grow towards the stress concentration area, and thus obtaining the microchannel stress-guided growth information set. Based on the microcrack bio-guided extension information set and the microchannel stress-guided growth information set, the spatiotemporal competition and synergy between the outside-to-inside bio-guided cracks and the inside-to-outside stress-guided channels are analyzed: when the two evolve toward each other in the battery shell-separator interface region, the failure acceleration effect caused by path coupling is identified; when the two develop in a misaligned manner, the failure risk delayed by path separation is assessed, and the failure path coupling situation information set is obtained.

6. The method according to claim 5, characterized in that, Based on the failure path coupling situation information set, the combined stress intensity of multiple failure paths on the overall battery safety boundary is analyzed, a dynamically optimized risk mitigation and early warning strategy is generated, and a battery safety status intervention process log is output, including: Based on the failure path coupling situation information set and the task stage division information set, the dynamic erosion rate caused to the battery safety boundary when the biologically guided crack from the outside to the inside and the stress-guided channel from the inside to the outside evolve in opposite directions is analyzed, and the composite stress intensity information set is obtained. Based on the composite stress intensity information set and the microbial erosion synergy information set, the task action stage where the composite stress intensity exceeds the safety threshold and the microbial erosion synergy reaches its peak is identified, and the key risk intervention window information set is obtained. Based on the key risk intervention window information set, a risk mitigation and early warning strategy is generated, which focuses on adjusting the timing of task actions, activating active thermal compensation and optimizing the electrolyte flow field. The strategy-driven battery state regulation is executed, and a battery safety state intervention process log is output, which records the regulation parameters and the evolution of the safety state.

7. A safety early warning system for lithium iron phosphate batteries based on multi-parameter fusion, characterized in that, The method applied to any one of claims 1-6 includes: The state analysis module is used to acquire battery operating condition datasets. Based on the battery operating condition datasets, it analyzes the interaction between temperature-pressure changes caused by different task actions and the internal electrochemical dynamics of the battery to obtain a set of battery internal state information. The erosion characterization module is used to analyze the effects of temperature-pressure changes on the metabolic activity and biofilm formation ability of barophilic microorganisms based on the battery operating condition dataset, and to obtain a set of microbial erosion characterization information. The coupling situation module is used to analyze the coupling relationship between the corrosion path from the outside to the inside and the dendrite growth path from the inside to the outside during the battery failure process, based on the battery internal state information set and the microbial erosion characterization information set, and to obtain the failure path coupling situation information set. The early warning and intervention module is used to analyze the combined stress intensity of multiple failure paths on the overall safety boundary of the battery based on the failure path coupling situation information set, generate a dynamically optimized risk mitigation and early warning strategy, and output a battery safety status intervention process log.

Images