A water-based sodium-ion battery swap box dynamic monitoring system and method

Abstract

This invention relates to the field of monitoring technology for water-based sodium-ion battery swapping boxes. The invention discloses a dynamic monitoring system and method for water-based sodium-ion battery swapping boxes, wherein the monitoring method includes the following steps: S1, real-time identification of operating conditions; S2, dynamic correction of monitoring data; S3, multi-parameter fusion anomaly diagnosis; S4, operating condition adaptation and graded protection; S5, dynamic health assessment; S6, group collaborative monitoring and model iteration. The invention also discloses a dynamic monitoring system for water-based sodium-ion battery swapping boxes, which includes a local monitoring terminal, a swapping station edge computing platform, and a cloud platform management center. This invention quantitatively identifies the full-cycle operating conditions of the swapping box, and then retrieves a dedicated interference elimination algorithm and correction parameters based on the operating condition identifier to perform customized data processing for the core interference types of different operating conditions.

Description

Technical Field

[0001] This invention relates to the field of monitoring technology for water-based sodium-ion battery swapping, and in particular to a dynamic monitoring system and method for water-based sodium-ion battery swapping boxes. Background Technology

[0002] Aqueous sodium-ion batteries, due to their use of aqueous electrolytes, possess characteristics such as no risk of combustion or explosion, low raw material costs, and environmental friendliness, making them the preferred energy storage solution for low-speed new energy vehicles and shared battery swapping scenarios. As the core application carrier, the battery swapping box needs to be dynamically monitored throughout the entire process to ensure operational safety and service life.

[0003] Currently, the industry's monitoring technology for water-based sodium-ion battery swapping boxes largely adopts the fixed monitoring scheme of lithium-ion battery management systems (BMS). Because the monitoring strategy is a fixed mode throughout the entire process, there is no quantitative differentiation or adaptation design for the swapping box's full-cycle operating conditions. Under dynamic operating conditions, monitoring data is easily distorted by interference from vibration, electromagnetic fields, and contact jitter. Under static operating conditions, continuous high-frequency sampling results in excessively high standby power consumption of the swapping box. Ultimately, it becomes difficult to balance the validity of monitoring data with equipment power consumption, creating potential for misjudgments in subsequent anomaly diagnosis and protection actions.

[0004] Accordingly, this application proposes a dynamic monitoring system and method for water-based sodium-ion battery swapping boxes. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a dynamic monitoring system and method for water-based sodium-ion battery swapping boxes.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A method for dynamic monitoring of an aqueous sodium-ion battery swapping box includes the following steps:

[0008] S1. Real-time operating condition identification: Based on the door lock status of the battery swapping box, the on / off status of the battery swapping interface, the interaction signal between the vehicle and the charger, and the effective value of vibration, the battery swapping box is identified in real time through quantitative judgment rules. It is currently in four core operating conditions: waiting to swap batteries, battery swapping and plugging / unplugging transition, vehicle operation dynamics, and charging recovery, and the operating condition identifier is output.

[0009] S2. Dynamic correction of monitoring data: Based on the operating condition identifier output in step S1, the preset mapping relationship of operating condition, interference, and correction algorithm is invoked to perform filtering, baseline correction, and outlier removal processing on the collected raw monitoring data, and output the corrected valid monitoring data.

[0010] S3. Multi-parameter fusion anomaly diagnosis: Substitute the valid monitoring data output in step S2 into the multi-parameter cross-validation diagnosis rules specific to aqueous sodium-ion batteries to determine whether the anomaly triggering conditions are met. If they are met, identify the anomaly type and classify the risk levels as prompt level, early warning level, and first-level emergency level according to the degree of parameter deviation.

[0011] S4. Working Condition Adaptive Graded Protection: Based on the risk level divided in step S3 and combined with the current working condition in step S1, the preset risk, working condition, and protection action mapping strategy is invoked to issue corresponding control instructions to the execution module and perform differentiated protection handling.

[0012] S5. Dynamic Health Assessment: Based on the effective monitoring data from step S2, the SOH calculation model with the introduction of a side reaction compensation factor is substituted to calculate the health value of the battery swapping box in real time and synchronize it to the edge computing platform of the battery swapping station.

[0013] S6. Group Collaborative Monitoring and Model Iteration: The edge computing platform of the battery swapping station aggregates the risk, operating conditions, and SOH data of all battery swapping boxes, and performs batch anomaly identification and battery swapping scheduling optimization; the cloud platform optimizes diagnostic rules and model parameters based on full-area data and distributes them to local terminals to complete the iteration.

[0014] Preferably, the real-time identification of the working condition in step S1 is implemented as follows:

[0015] S101. Set the quantization judgment threshold: Vibration effective value threshold. Battery swapping and plugging-in operation duration threshold ;

[0016] S102. Acquire status signal: Door lock status Battery swapping interface on / off status Vehicle-charger interaction signals accelerometer vibration RMS value Charging and discharging current ;

[0017] S103, Perform quantitative judgment for each working condition:

[0018] like The condition was determined to be a static condition awaiting battery replacement.

[0019] If the door lock or interface status changes, the contact resistance signal is continuously collected, and the operating duration is... This is determined to be a battery swapping / plugging transition condition;

[0020] like Receive vehicle operation signal This is determined to be a dynamic operating condition for vehicle-mounted operation.

[0021] like Received charging command The condition is determined to be a charging recovery state;

[0022] S104. Output a unique operating condition identifier to the data correction module and the protection execution module.

[0023] Preferably, the dynamic correction of monitoring data in step S2 is implemented through the following steps:

[0024] S201 pre-built mapping table of operating conditions, interference, and correction algorithms, which contains the core interference types and dedicated correction algorithms corresponding to four types of operating conditions;

[0025] S202 receives the raw monitoring data and the operating condition identifier from step S1, and retrieves the corresponding correction algorithm and algorithm parameters from the mapping table;

[0026] S203 performs preprocessing on the raw data, removing invalid data that exceeds the sensor's measurement range;

[0027] S204 executes the retrieved correction algorithm to complete the filtering and baseline drift correction of the original data;

[0028] S205 performs outlier removal using the 3σ criterion on the corrected data and outputs valid monitoring data to the anomaly diagnosis module and the health assessment module; the 3σ criterion determination formula is: if... If x is an outlier, then x is determined to be an outlier, where x is a single sampled data point, μ is the mean of the data sequence, and σ is the standard deviation of the data sequence.

[0029] Preferably, the pre-constructed mapping table of operating conditions, interference, and correction algorithms in S201 is as follows:

[0030] Under the condition of waiting for battery swapping and stationary operation: low-frequency environmental drift interference is handled by a low-pass filter algorithm with a cutoff frequency of 0.1Hz;

[0031] Under the transitional condition of battery swapping and plugging in: the following algorithm is used to address contact jitter spike interference:

[0032] ;

[0033] ,in As the limiting threshold, the sliding window N=5. This is the original sampled data. This is the data after amplitude limiting and filtering. This is the final data after moving average filtering. This is the data index within the sliding window, with values ​​ranging from 0 to N-1. This refers to the original sampled data from the previous moment;

[0034] Under dynamic operating conditions on the vehicle: electromagnetic and vibration baseline drift interference is corrected using Kalman filtering and a first-order equivalent circuit baseline correction algorithm;

[0035] Under charging recovery conditions: Median filtering algorithm is used for pulse charging and discharging spike interference, with a filtering window M=7.

[0036] Preferably, the multi-parameter fusion anomaly diagnosis in step S3 is specifically implemented as follows:

[0037] S301. A pre-built multi-parameter cross-validation diagnostic rule library for specific anomalies of aqueous batteries. The rule library includes the triggering conditions for three types of anomalies: electrolyte leakage, water decomposition gas generation, and temperature and humidity coupled side reactions.

[0038] S302. Extract the feature parameters corresponding to various anomalies from the rule base from the effective monitoring data in step S2;

[0039] S303, Perform cross-validation for each anomaly: Determine whether the feature parameter simultaneously meets all the triggering conditions of the corresponding anomaly. If not, it is determined to be normal; if it is, the anomaly type is locked.

[0040] S304. For locked anomaly types, calculate the proportion of characteristic parameters deviating from their rated values. The calculation formula is: In the formula These are the measured values ​​of the characteristic parameters. These are the rated values ​​for characteristic parameters; risk levels are classified based on the deviation ratio. ≤10% is a warning level, 10% < ≤20% is the warning level. >20% is classified as Level 1 Emergency;

[0041] S305 will output the anomaly type and risk level results.

[0042] Preferably, the multi-parameter cross-validation diagnostic rule base in step S301 specifically comprises:

[0043] Electrolyte leakage anomaly: The rate of voltage drop in a single cell is ≥10% / 5min, and the humidity inside the chamber is ≥30%RH higher than the ambient humidity, and the resistance of the leakage electrode is ≤1kΩ;

[0044] Abnormal water decomposition gas production: The rate of pressure increase in the chamber is ≥2 kPa / h and the hydrogen concentration is ≥200 ppm and the total voltage deviates from the rated value by ≥5%;

[0045] Abnormal temperature and humidity coupling side reaction: The chamber temperature is ≥45℃, the relative humidity is ≥85%RH, and the charge / discharge coulombic efficiency η≤95%; the formula for calculating the charge / discharge coulombic efficiency is: , This represents the total charging capacity. This represents the total amount of electricity discharged.

[0046] Preferably, the working condition adaptation and graded protection in step S4 is implemented as follows:

[0047] S401 pre-built risk, operating condition, and protection action mapping strategy table, which contains exclusive protection actions after the combination of three risk levels and four operating conditions. The actions do not trigger a one-size-fits-all power outage across operating conditions.

[0048] S402 receives the operating condition identifier from step S1 and the abnormality type and risk level from step S3, and retrieves the corresponding protection action instruction from the strategy table.

[0049] S403 sends instructions to the graded protection execution module to execute the corresponding protection actions;

[0050] After the S404 protection action is executed, monitoring data is continuously collected to determine whether the abnormality has been resolved. If it has been resolved, normal operation is restored; otherwise, the protection action is upgraded.

[0051] A dynamic monitoring system for water-based sodium-ion battery swapping boxes is disclosed. The system includes a local monitoring terminal, a swapping station edge computing platform, and a cloud platform management center. The local monitoring terminal has a built-in operating condition identification unit, a data correction unit, an anomaly diagnosis unit, a graded protection unit, and a SOH assessment unit. The swapping station edge computing platform is communicatively connected to the local monitoring terminal, and the cloud platform management center is communicatively connected to the swapping station edge computing platform.

[0052] Preferably, the operating condition identification unit is used to perform the real-time operating condition identification step and output the operating condition identifier; the data correction unit is connected to the operating condition identification unit and is used to perform the dynamic correction step of monitoring data and output valid monitoring data; the anomaly diagnosis unit is connected to the data correction unit and is used to perform the anomaly diagnosis step and output the anomaly type and risk level; the graded protection unit is connected to the operating condition identification unit and the anomaly diagnosis unit respectively and is used to perform the operating condition adaptation graded protection step and perform protection actions; the SOH assessment unit is connected to the data correction unit and is used to perform the health dynamic assessment step and output the real-time SOH value.

[0053] The present invention has the following beneficial effects:

[0054] 1. By quantitatively identifying the full-cycle operating conditions of the battery swapping box, and then retrieving the exclusive interference cancellation algorithm and correction parameters based on the operating condition identifier, customized data processing is performed for the core interference types of different operating conditions. At the same time, differentiated sampling strategies can be matched to effectively eliminate interference such as vibration, electromagnetic interference, and contact jitter under dynamic operating conditions to ensure the validity of monitoring data. Under static operating conditions, the sampling frequency is reduced to reduce the standby power consumption of the battery swapping box, thereby achieving a balance between the validity of monitoring data and the power consumption of the equipment and eliminating the potential for misjudgment in abnormal diagnosis and protection actions.

[0055] 2. For the three types of specific safety risks of aqueous sodium-ion batteries, a multi-feature parameter and logic cross-validation rule is designed. An anomaly is only determined when all feature parameters meet the trigger conditions at the same time. This effectively eliminates false anomaly alarms caused by environmental fluctuations and single parameter drift. At the same time, it accurately identifies the specific safety risks of aqueous batteries, avoids missing real anomalies, and improves the accuracy and reliability of the safety protection of the battery swapping box. Attached Figure Description

[0056] Figure 1 This is a schematic diagram of the dynamic monitoring method for a water-based sodium-ion battery swapping box proposed in this invention.

[0057] Figure 2 This is a structural block diagram of a dynamic monitoring system for an aqueous sodium-ion battery swapping box proposed in this invention. Detailed Implementation

[0058] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0059] Reference Figure 1-2 A dynamic monitoring method for water-based sodium-ion battery swapping boxes includes the following steps:

[0060] S1. Real-time operating condition identification: Based on the door lock status of the battery swapping box, the on / off status of the battery swapping interface, the interaction signal between the vehicle and the charger, and the effective value of vibration, the battery swapping box is identified in real time through quantitative judgment rules. It is currently in four core operating conditions: waiting to swap batteries, battery swapping and plugging / unplugging transition, vehicle operation dynamics, and charging recovery, and the operating condition identifier is output.

[0061] The real-time identification of operating conditions in step S1 is implemented as follows:

[0062] S101. Set the quantization judgment threshold: Vibration effective value threshold. Battery swapping and plugging-in operation duration threshold ;

[0063] S102. Acquire status signal: Door lock status Battery swapping interface on / off status Vehicle-charger interaction signals accelerometer vibration RMS value Charging and discharging current ;

[0064] S103, Perform quantitative judgment for each working condition:

[0065] like The condition was determined to be a static condition awaiting battery replacement.

[0066] If the door lock or interface status changes, the contact resistance signal is continuously collected, and the operating duration is... This is determined to be a battery swapping / plugging transition condition;

[0067] like Receive vehicle operation signal This is determined to be a dynamic operating condition for vehicle-mounted operation.

[0068] like Received charging command The condition is determined to be a charging recovery state;

[0069] S104. Output a unique operating condition identifier to the data correction module and the protection execution module.

[0070] S2. Dynamic correction of monitoring data: Based on the operating condition identifier output in step S1, the preset mapping relationship of operating condition, interference, and correction algorithm is invoked to perform filtering, baseline correction, and outlier removal processing on the collected raw monitoring data, and output the corrected valid monitoring data.

[0071] The dynamic correction of monitoring data in step S2 is implemented as follows:

[0072] S201 pre-built mapping table of operating conditions, interference, and correction algorithms, which contains the core interference types and dedicated correction algorithms corresponding to four types of operating conditions;

[0073] The pre-built mapping table of operating conditions, interference, and correction algorithms is as follows:

[0074] Under the condition of waiting for battery swapping and stationary operation: low-frequency environmental drift interference is handled by a low-pass filter algorithm with a cutoff frequency of 0.1Hz;

[0075] Under the transitional condition of battery swapping and plugging in: the following algorithm is used to address contact jitter spike interference:

[0076] ;

[0077] ,in As the limiting threshold, the sliding window N=5. This is the original sampled data. This is the data after amplitude limiting and filtering. This is the final data after moving average filtering. This is the data index within the sliding window, with values ​​ranging from 0 to N-1. This is the original sampled data from the previous moment.

[0078] Under dynamic operating conditions on the vehicle: electromagnetic and vibration baseline drift interference is corrected using Kalman filtering and a first-order equivalent circuit baseline correction algorithm;

[0079] Under charging recovery conditions: Median filtering algorithm is used for pulse charging and discharging spike interference, with a filtering window M=7.

[0080] S202 receives the raw monitoring data and the operating condition identifier from step S1, and retrieves the corresponding correction algorithm and algorithm parameters from the mapping table;

[0081] S203 performs preprocessing on the raw data, removing invalid data that exceeds the sensor's measurement range;

[0082] S204 executes the retrieved correction algorithm to complete the filtering and baseline drift correction of the original data;

[0083] S205 performs outlier removal using the 3σ criterion on the corrected data and outputs valid monitoring data to the anomaly diagnosis module and the health assessment module; the 3σ criterion determination formula is: if... If x is an outlier, then x is determined to be an outlier, where x is a single sampled data point, μ is the mean of the data sequence, and σ is the standard deviation of the data sequence.

[0084] S3. Multi-parameter fusion anomaly diagnosis: Substitute the valid monitoring data output in step S2 into the multi-parameter cross-validation diagnosis rules specific to aqueous sodium-ion batteries to determine whether the anomaly triggering conditions are met. If they are met, identify the anomaly type and classify the risk levels as prompt level, early warning level, and first-level emergency level according to the degree of parameter deviation.

[0085] Step S3, multi-parameter fusion anomaly diagnosis, is implemented as follows:

[0086] S301. A pre-built multi-parameter cross-validation diagnostic rule library for specific anomalies of aqueous batteries. The rule library includes the triggering conditions for three types of anomalies: electrolyte leakage, water decomposition gas generation, and temperature and humidity coupled side reactions.

[0087] The multi-parameter cross-validation diagnostic rule base in step S301 is as follows:

[0088] Electrolyte leakage anomaly: The rate of voltage drop in a single cell is ≥10% / 5min, and the humidity inside the chamber is ≥30%RH higher than the ambient humidity, and the resistance of the leakage electrode is ≤1kΩ;

[0089] Abnormal water decomposition gas production: The rate of pressure increase in the chamber is ≥2 kPa / h and the hydrogen concentration is ≥200 ppm and the total voltage deviates from the rated value by ≥5%;

[0090] Abnormal temperature and humidity coupling side reaction: The chamber temperature is ≥45℃, the relative humidity is ≥85%RH, and the charge / discharge coulombic efficiency η≤95%; the formula for calculating the charge / discharge coulombic efficiency is: , This represents the total charging capacity. This represents the total amount of electricity discharged.

[0091] S302. Extract the feature parameters corresponding to various anomalies from the rule base from the effective monitoring data in step S2;

[0092] S303, Perform cross-validation for each anomaly: Determine whether the feature parameter simultaneously meets all the triggering conditions of the corresponding anomaly. If not, it is determined to be normal; if it is, the anomaly type is locked.

[0093] S304. For locked anomaly types, calculate the proportion of characteristic parameters deviating from their rated values. The calculation formula is: In the formula These are the measured values ​​of the characteristic parameters. These are the rated values ​​for characteristic parameters; risk levels are classified based on the deviation ratio. ≤10% is a warning level, 10% < ≤20% is the warning level. >20% is classified as Level 1 Emergency;

[0094] S305 will output the anomaly type and risk level results.

[0095] S4. Working Condition Adaptive Graded Protection: Based on the risk level divided in step S3 and combined with the current working condition in step S1, the preset risk, working condition, and protection action mapping strategy is invoked to issue corresponding control commands to the execution module and perform differentiated protection handling.

[0096] Step S4, the working condition adaptation and hierarchical protection, is implemented as follows:

[0097] S401 pre-built risk, operating condition, and protection action mapping strategy table, which contains exclusive protection actions after the combination of three risk levels and four operating conditions. The actions do not trigger a one-size-fits-all power outage across operating conditions.

[0098] S402 receives the operating condition identifier from step S1 and the abnormality type and risk level from step S3, and retrieves the corresponding protection action instruction from the strategy table.

[0099] S403 sends instructions to the graded protection execution module to execute the corresponding protection actions;

[0100] After the S404 protection action is executed, monitoring data is continuously collected to determine whether the abnormality has been resolved. If it has been resolved, normal operation is restored; otherwise, the protection action is upgraded.

[0101] S5. Dynamic Health Assessment: Based on the effective monitoring data from step S2, the SOH calculation model with the introduction of a side reaction compensation factor is substituted to calculate the health value of the battery swapping box in real time and synchronize it to the edge computing platform of the battery swapping station.

[0102] The SOH model, which incorporates a side reaction compensation factor, enables real-time calculation of health status. The model formula and specific implementation are as follows:

[0103] The SOH calculation model and fixed weight parameters are pre-defined, and the model formula is as follows:

[0104] ;

[0105] The weighting coefficients of each characteristic parameter are used to adjust the weighting of the effects of capacity, internal resistance, number of cycles, and side effects on health. Battery health, with a value ranging from 0 to 1. The closer the value is to 1, the better the battery health. This is the current measured capacity of the battery, estimated through charge-discharge tests or algorithms. The nominal capacity of the battery is the rated capacity of the battery design. The current DC internal resistance of the battery is obtained through testing. is the initial DC internal resistance of the battery, and is the reference value of the internal resistance of the battery in its brand new state; This represents the number of battery cycles; each complete charge and discharge cycle is counted as one cycle. The nominal cycle life of a battery refers to the number of cycles the battery is designed for. This is a side reaction compensation factor used to quantify the impact of side reactions on battery health, with a value ranging from 0 to 1.

[0106] From the valid monitoring data output in step S2, extract the core input parameters required by the model: the current measured capacity of the battery C, the current DC internal resistance of the battery R, ​​the number of charge-discharge cycles of the battery N, and the cumulative number of abnormal side reactions Nabn.

[0107] Through formula Calculate the side reaction compensation factor to quantify the impact of side reactions on the health of aqueous batteries; The cumulative number of abnormal events related to side reactions, i.e., the total number of abnormal events related to side reactions recorded during the monitoring process; The rated abnormal threshold for side reactions is the preset upper limit for the number of abnormal side reactions.

[0108] Substitute all input parameters into the SOH model to directly calculate the real-time SOH value, with a range of 0 ≤ SOH ≤ 1. The closer the value is to 1, the higher the battery health.

[0109] The SOH value is synchronized to the edge computing platform of the battery swapping station according to the preset cycle to provide data support for group collaborative scheduling.

[0110] S6. Group Collaborative Monitoring and Model Iteration: The edge computing platform of the battery swapping station aggregates the risk, operating conditions, and SOH data of all battery swapping boxes, and performs batch anomaly identification and battery swapping scheduling optimization; the cloud platform optimizes diagnostic rules and model parameters based on full-area data and distributes them to local terminals to complete the iteration.

[0111] A dynamic monitoring system for an aqueous sodium-ion battery swapping box includes a local monitoring terminal, a swapping station edge computing platform, and a cloud platform management center. The local monitoring terminal integrates a working condition identification unit, a data correction unit, an anomaly diagnosis unit, a graded protection unit, and a SOH (Sodium Oxide Hydrochloric) assessment unit. The swapping station edge computing platform is communicatively connected to the local monitoring terminal, and the cloud platform management center is also communicatively connected to the swapping station edge computing platform. The working condition identification unit performs real-time working condition identification and outputs a working condition identifier. The data correction unit, connected to the working condition identification unit, performs dynamic data correction and outputs valid monitoring data. The anomaly diagnosis unit, connected to the data correction unit, performs anomaly diagnosis and outputs the anomaly type and risk level. The graded protection unit, connected to both the working condition identification unit and the anomaly diagnosis unit, performs working condition-adaptive graded protection and executes protection actions. The SOH assessment unit, connected to the data correction unit, performs dynamic health assessment and outputs real-time SOH values.

[0112] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for dynamic monitoring of an aqueous sodium-ion battery swapping box, characterized in that, Includes the following steps: S1. Real-time operating condition identification: Based on the door lock status of the battery swapping box, the on / off status of the battery swapping interface, the interaction signal between the vehicle and the charger, and the effective value of vibration, the battery swapping box is identified in real time through quantitative judgment rules. It is currently in four core operating conditions: waiting to swap batteries, battery swapping and plugging / unplugging transition, vehicle operation dynamics, and charging recovery, and the operating condition identifier is output. S2. Dynamic correction of monitoring data: Based on the operating condition identifier output in step S1, the preset mapping relationship of operating condition, interference, and correction algorithm is invoked to perform filtering, baseline correction, and outlier removal processing on the collected raw monitoring data, and output the corrected valid monitoring data. S3. Multi-parameter fusion anomaly diagnosis: Substitute the valid monitoring data output in step S2 into the multi-parameter cross-validation diagnosis rules specific to aqueous sodium-ion batteries to determine whether the anomaly triggering conditions are met. If they are met, identify the anomaly type and classify the risk levels as prompt level, early warning level, and first-level emergency level according to the degree of parameter deviation. S4. Working Condition Adaptive Graded Protection: Based on the risk level divided in step S3 and combined with the current working condition in step S1, the preset risk, working condition, and protection action mapping strategy is invoked to issue corresponding control instructions to the execution module and perform differentiated protection handling. S5. Dynamic Health Assessment: Based on the effective monitoring data from step S2, the SOH calculation model with the introduction of a side reaction compensation factor is substituted to calculate the health value of the battery swapping box in real time and synchronize it to the edge computing platform of the battery swapping station. S6. Group Collaborative Monitoring and Model Iteration: The edge computing platform of the battery swapping station aggregates the risk, operating conditions, and SOH data of all battery swapping boxes, and performs batch anomaly identification and battery swapping scheduling optimization; the cloud platform optimizes diagnostic rules and model parameters based on full-area data and distributes them to local terminals to complete the iteration.

2. The dynamic monitoring method for an aqueous sodium-ion battery swapping box according to claim 1, characterized in that, The real-time identification of operating conditions in step S1 is implemented as follows: S101. Set the quantization judgment threshold: Vibration effective value threshold. Battery swapping and plugging-in operation duration threshold ; S102. Acquire status signal: Door lock status Battery swapping interface on / off status Vehicle-charger interaction signals accelerometer vibration RMS value Charging and discharging current ; S103, Perform quantitative judgment for each working condition: like The condition was determined to be a static condition awaiting battery replacement. If the door lock or interface status changes, the contact resistance signal is continuously collected, and the operating duration is... This is determined to be a battery swapping / plugging transition condition; like Receive vehicle operation signal This is determined to be a dynamic operating condition for vehicle-mounted operation. like Received charging command The condition is determined to be a charging recovery state; S104. Output a unique operating condition identifier to the data correction module and the protection execution module.

3. The dynamic monitoring method for an aqueous sodium-ion battery swapping box according to claim 1, characterized in that, The dynamic correction of monitoring data in step S2 is implemented as follows: S201 pre-built mapping table of operating conditions, interference, and correction algorithms, which contains the core interference types and dedicated correction algorithms corresponding to four types of operating conditions; S202 receives the raw monitoring data and the operating condition identifier from step S1, and retrieves the corresponding correction algorithm and algorithm parameters from the mapping table; S203 performs preprocessing on the raw data, removing invalid data that exceeds the sensor's measurement range; S204 executes the retrieved correction algorithm to complete the filtering and baseline drift correction of the original data; S205 performs outlier removal using the 3σ criterion on the corrected data and outputs valid monitoring data to the anomaly diagnosis module and the health assessment module; the 3σ criterion determination formula is: if... If x is an outlier, then x is determined to be an outlier, where x is a single sampled data point, μ is the mean of the data sequence, and σ is the standard deviation of the data sequence.

4. The dynamic monitoring method for an aqueous sodium-ion battery swapping box according to claim 2, characterized in that, The S201 pre-built working condition, interference, and correction algorithm mapping table is as follows: Under the condition of waiting for battery swapping and stationary operation: low-frequency environmental drift interference is handled by a low-pass filter algorithm with a cutoff frequency of 0.1Hz; Under the transitional condition of battery swapping and plugging in: the following algorithm is used to address contact jitter spike interference: ； ,in As the limiting threshold, the sliding window N=5. This is the original sampled data. This is the data after amplitude limiting and filtering. This is the final data after moving average filtering. This is the data index within the sliding window, with values ​​ranging from 0 to N-1. This refers to the original sampled data from the previous moment; Under dynamic operating conditions on the vehicle: electromagnetic and vibration baseline drift interference is corrected using Kalman filtering and a first-order equivalent circuit baseline correction algorithm; Under charging recovery conditions: Median filtering algorithm is used for pulse charging and discharging spike interference, with a filtering window M=7.

5. The dynamic monitoring method for an aqueous sodium-ion battery swapping box according to claim 1, characterized in that, Step S3, multi-parameter fusion anomaly diagnosis, is implemented as follows: S301. A pre-built multi-parameter cross-validation diagnostic rule library for specific anomalies of aqueous batteries. The rule library includes the triggering conditions for three types of anomalies: electrolyte leakage, water decomposition gas generation, and temperature and humidity coupled side reactions. S302. Extract the feature parameters corresponding to various anomalies from the rule base from the effective monitoring data in step S2; S303, Perform cross-validation for each anomaly: Determine whether the feature parameter simultaneously meets all the triggering conditions of the corresponding anomaly. If not, it is determined to be normal; if it is, the anomaly type is locked. S304. For locked anomaly types, calculate the proportion of characteristic parameters deviating from their rated values. The calculation formula is: In the formula These are the measured values ​​of the characteristic parameters. These are the rated values ​​for the characteristic parameters; Risk levels are classified based on the deviation ratio: ≤10% is a warning level, 10% < ≤20% is the warning level. >20% is classified as Level 1 Emergency; S305 will output the anomaly type and risk level results.

6. The dynamic monitoring method for an aqueous sodium-ion battery swapping box according to claim 1, characterized in that, The multi-parameter cross-validation diagnostic rule base in step S301 is as follows: Electrolyte leakage anomaly: The rate of voltage drop in a single cell is ≥10% / 5min, and the humidity inside the chamber is ≥30%RH higher than the ambient humidity, and the resistance of the leakage electrode is ≤1kΩ; Abnormal water decomposition gas production: The rate of pressure increase in the chamber is ≥2 kPa / h and the hydrogen concentration is ≥200 ppm and the total voltage deviates from the rated value by ≥5%; Abnormal temperature and humidity coupling side reaction: The chamber temperature is ≥45℃, the relative humidity is ≥85%RH, and the charge / discharge coulombic efficiency η≤95%; the formula for calculating the charge / discharge coulombic efficiency is: , This represents the total charging capacity. This represents the total amount of electricity discharged.

7. The dynamic monitoring method for an aqueous sodium-ion battery swapping box according to claim 1, characterized in that, Step S4, the working condition adaptation and hierarchical protection, is implemented as follows: S401 pre-built risk, operating condition, and protection action mapping strategy table, which contains exclusive protection actions after the combination of three risk levels and four operating conditions. The actions do not trigger a one-size-fits-all power outage across operating conditions. S402 receives the operating condition identifier from step S1 and the abnormality type and risk level from step S3, and retrieves the corresponding protection action instruction from the strategy table. S403 sends instructions to the graded protection execution module to execute the corresponding protection actions; After the S404 protection action is executed, monitoring data is continuously collected to determine whether the abnormality has been resolved. If it has been resolved, normal operation is restored; otherwise, the protection action is upgraded.

8. A dynamic monitoring system for an aqueous sodium-ion battery swapping box, used to implement the dynamic monitoring method for an aqueous sodium-ion battery swapping box as described in any one of claims 1-7, characterized in that, The system includes a local monitoring terminal, a battery swapping station edge computing platform, and a cloud platform management center. The local monitoring terminal has a built-in operating condition identification unit, data correction unit, anomaly diagnosis unit, graded protection unit, and SOH assessment unit. The battery swapping station edge computing platform is communicatively connected to the local monitoring terminal, and the cloud platform management center is communicatively connected to the battery swapping station edge computing platform.

9. A dynamic monitoring system for an aqueous sodium-ion battery swapping box according to claim 8, characterized in that, The operating condition identification unit performs real-time operating condition identification and outputs an operating condition identifier; the data correction unit is connected to the operating condition identification unit and performs dynamic correction of monitoring data and outputs valid monitoring data; the anomaly diagnosis unit is connected to the data correction unit and performs anomaly diagnosis and outputs anomaly type and risk level; the graded protection unit is connected to both the operating condition identification unit and the anomaly diagnosis unit and performs graded protection steps to adapt to operating conditions and execute protection actions; the SOH assessment unit is connected to the data correction unit and performs dynamic health assessment steps to output real-time SOH values.

Images