Method and system for detecting abnormal battery box of energy storage power station

Abstract

The invention relates to the technical field of battery box detection, in particular to a method and system for detecting an abnormal battery box of an energy storage power station. The method comprises the following steps: acquiring battery box data and operating environment data of the energy storage power station, evaluating the initial performance of a battery box, and generating operating state data of the energy storage power station according to the initial performance; on the basis of the operation state data, detecting a supporting configuration evolution unbalance condition, further identifying battery electrothermal coupling steady-state disintegration, and accordingly judging an electric energy quality abnormal trend; the power grid operation coordination attenuation trend is identified based on the power quality abnormal trend, the short-time harmonic surge condition is further detected, and finally the power grid stability attenuation level is determined; combining a power grid stability attenuation condition and a battery state change condition, identifying a power grid frequency instability degree, detecting an energy storage power station battery abnormal condition, and uploading abnormal information to a cloud platform to realize early warning response; according to the invention, through detection of the abnormity of the battery box, the abnormity identification of the battery box is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of battery box detection, and particularly to a method and system for detecting abnormal battery boxes in an energy storage power station. Background Art

[0002] Energy storage power stations generally use a battery system with lithium-ion batteries as the core for energy storage. As the basic operating unit, the battery box contains multiple battery cells, conductive connection structures, temperature control components, and electrical protection devices, and undertakes the tasks of energy charge and discharge conversion and multi-node parallel operation. However, during long-term operation, due to factors such as frequent charge and discharge cycles, aging of electrochemical materials, environmental temperature fluctuations, loose electrical connections, and external vibration impacts, the battery box is extremely prone to failure situations such as abnormal capacity attenuation, abnormal voltage and current fluctuations, overheating and out-of-control, swelling and leakage of battery cells, or internal short circuits. If such abnormalities cannot be detected and intervened in a timely manner, it will lead to a decline in system operation efficiency, increased energy loss, and even trigger a fire due to thermal runaway, seriously threatening the safe operation of the energy storage power station. However, traditional methods for detecting abnormalities in energy storage power stations have problems of inaccurate detection of abnormal trends in the power quality of the transmitted electric energy in the energy storage power station, and inaccurate detection of the attenuation status of the power grid stability in the energy storage power station. Summary of the Invention

[0003] Based on this, it is necessary to provide a method and system for detecting abnormal battery boxes in an energy storage power station to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for detecting abnormal battery boxes in an energy storage power station includes the following steps: Step S1: Obtain the data of the battery boxes in the energy storage power station; collect the operation environment data of the energy storage power station for the data of the battery boxes in the energy storage power station; evaluate the initial performance of the battery boxes in the energy storage power station based on the data of the battery boxes in the energy storage power station; evaluate the operation status data of the energy storage power station for the initial performance of the battery boxes in the energy storage power station according to the data of the battery boxes in the energy storage power station and the operation environment data of the energy storage power station; Step S2: Detect the imbalance status of the evolution of the support configuration in the energy storage power station according to the operation status data of the energy storage power station; detect the disintegration status of the steady state of the battery electro-thermal coupling according to the imbalance status of the evolution of the support configuration in the energy storage power station; detect the abnormal trend of the power quality of the transmitted electric energy in the energy storage power station based on the disintegration status of the steady state of the battery electro-thermal coupling; Step S3: Identify the attenuation trend of the grid operation coordination according to the abnormal trend of the power quality of the transmitted electric energy in the energy storage power station; detect the sudden increase in short-term harmonics in the transmission of the energy storage power station based on the attenuation trend of the grid operation coordination and the abnormal trend of the power quality of the transmitted electric energy in the energy storage power station; determine the attenuation status of the power grid stability in the energy storage power station based on the sudden increase in short-term harmonics in the transmission of the energy storage power station; Step S4: Detect the change of the energy storage power station battery state according to the attenuation of the power grid stability of the energy storage power station; identify the degree of instability of the power grid frequency according to the change of the energy storage power station battery state; detect the abnormal condition of the energy storage power station battery based on the degree of instability of the power grid frequency and the change of the energy storage power station battery state, and upload it to the cloud platform for early warning.

[0005] Through the layer-by-layer analysis from the basic performance of the battery box to the power quality transmission process of the system, the present invention realizes the accurate identification of the abnormal evolution of the battery state. Based on the acquisition of the energy storage battery box data and the operating environment data, through the initial performance modeling and the fusion evaluation of the operating state, the starting point of the analysis process is ensured to have high credibility; in the detection of the evolution of the support configuration and the electro-thermal coupling state, combined with the dual stability changes of the structure and the thermal coupling, the ability to identify complex physical interaction effects is enhanced; for the detection of the abnormal trend of power quality and the short-term harmonic surge during the transmission process, a logical chain from data perturbation response to stability quantification is constructed, effectively improving the dynamic tracking ability of the power grid stability attenuation; further, in the process of state change and frequency perturbation identification, a closed-loop analysis mechanism of the linkage response between the energy storage system and the power grid is established, and the abnormal condition of the battery is jointly detected by combining the frequency fluctuation and the battery state evolution, and reported through the cloud platform, constructing a complete early warning system driven by data and real-time perception. The overall solution has the characteristics of wide coverage, clear data link, and accurate anomaly traceability. Therefore, the present invention is an optimized treatment for the abnormal battery box of the traditional energy storage power station, solves the problems that the traditional abnormal battery box of the energy storage power station has inaccurate detection of the abnormal trend of the power quality transmitted by the energy storage power station and inaccurate detection of the attenuation of the power grid stability of the energy storage power station, and improves the accuracy of the detection of the abnormal trend of the power quality transmitted by the energy storage power station and the accuracy of the detection of the attenuation of the power grid stability of the energy storage power station.

[0006] The present invention also provides an abnormal battery box detection system for an energy storage power station, which is used to execute the abnormal battery box detection method for an energy storage power station as described above. The abnormal battery box detection system for an energy storage power station includes: An energy storage power station operating state evaluation module, which is used to obtain the energy storage power station battery box data; collect the energy storage power station operating environment data from the energy storage power station battery box data; evaluate the initial performance of the energy storage power station battery box based on the energy storage power station battery box data; evaluate the energy storage power station operating state data for the initial performance of the energy storage power station battery box according to the energy storage power station battery box data and the energy storage power station operating environment data; A transmission power quality abnormal detection module, which is used to detect the imbalance condition of the support configuration evolution of the energy storage power station according to the energy storage power station operating state data; detect the breakdown condition of the battery electro-thermal coupling steady state according to the imbalance condition of the support configuration evolution of the energy storage power station; detect the abnormal trend of the energy storage power station transmission power quality based on the breakdown condition of the battery electro-thermal coupling steady state; The power grid stability attenuation determination module is used to identify the attenuation trend of the power grid operation coordination according to the abnormal trend of the power quality transmitted by the energy storage power station; detect the short-term harmonic surge condition of the energy storage power station based on the attenuation trend of the power grid operation coordination and the abnormal trend of the power quality transmitted by the energy storage power station; determine the power grid stability attenuation condition of the energy storage power station based on the short-term harmonic surge condition of the energy storage power station. The energy storage power station battery abnormality detection module is used to detect the change of the energy storage power station battery state according to the power grid stability attenuation condition of the energy storage power station; identify the degree of power grid frequency instability according to the change of the energy storage power station battery state; detect the abnormal condition of the energy storage power station battery based on the degree of power grid frequency instability and the change of the energy storage power station battery state, and upload it to the cloud platform for early warning.

[0007] The abnormal battery box detection system of the energy storage power station of the present invention can implement any abnormal battery box detection method of the present invention, and is used as a medium for coordinating the operations and signal transmissions between each module to complete the abnormal battery box detection method of the energy storage power station. The internal modules of the system cooperate with each other to accurately identify and real-time warn the abnormal state of the battery box in the whole process of the energy storage power station operation, construct a chain diagnosis system driven by multi-source data, and improve the stability monitoring and risk response capabilities of the energy storage system. Brief Description of the Drawings

[0008] Figure 1 It is a schematic diagram of the step flow of an abnormal battery box detection method for an energy storage power station; Figure 2 It is Figure 1 a schematic diagram of the detailed implementation step flow of step S3 in Figure 3 It is Figure 1 a schematic diagram of the detailed implementation step flow of step S4 in The realization, functional characteristics and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the drawings. Detailed Embodiments

[0009] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0010] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0011] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0012] To achieve the above object, please refer to Figures 1 to 3 , a method for detecting an abnormal battery box of an energy storage power station, comprising the following steps: Step S1: Obtain the battery box data of the energy storage power station; collect the operation environment data of the energy storage power station for the battery box data; evaluate the initial performance of the battery box of the energy storage power station based on the battery box data of the energy storage power station; evaluate the operation status data of the energy storage power station for the initial performance of the battery box of the energy storage power station according to the battery box data of the energy storage power station and the operation environment data of the energy storage power station; In the embodiments of the present invention, data of battery boxes in an energy storage power station is obtained through a multi-channel battery state detection system deployed in the energy storage power station. The multi-channel battery state detection system includes: a multi-parameter synchronous acquisition device integrating a voltage acquisition module, a current induction module, a temperature monitoring module, and a state of charge sampling module. This device collects real-time temperature data at different positions in each battery box through a distributed optical fiber temperature measurement unit, obtains the instantaneous current values during the charging and discharging processes of each group of batteries using a time-sharing current sampling circuit, and collects the terminal voltage changes of the battery box using a high-frequency sampling ADC circuit. The state of charge sampling module is used to record the SOC change curve. After the data of the battery boxes is collected, environmental state perception devices deployed around the battery boxes are used to collect the operation environment data of the energy storage power station, including environmental temperature, relative humidity, external air pressure of the box body, dust concentration, and gas component concentration (such as H2, CO, CO2, etc.). This data is uploaded to the on-site edge computing device in real time by the integrated sensing unit to complete data preprocessing, including time synchronization, filtering and noise reduction, and outlier removal processing. Then, by calling the locally set performance evaluation threshold database, the obtained historical data of the battery boxes (such as temperature rise rate, voltage fluctuation range, capacity retention rate) is compared with the calibrated performance curve one by one to evaluate the initial performance level of each battery box in the current operation cycle. This evaluation is output in the form of quantitative data, such as voltage stability score, current fluctuation index, capacity consistency level, etc. Based on the corresponding relationship between the initial performance evaluation result and the environmental data (such as daily temperature difference, humidity fluctuation frequency), a battery state-environment stress influence map is constructed using a multi-dimensional data cross-correlation function, and then the operation state data of the energy storage power station is deduced. Such state data includes: the performance deterioration rate of the battery box per unit time, the voltage-temperature coupling reaction index, the environmental-induced abnormal growth trend index, etc., which are used as the direct input for the subsequent step of analyzing the state evolution of the support structure.

[0013] Step S2: Detect the imbalance condition of the support structure evolution of the energy storage power station according to the operation state data of the energy storage power station; detect the disintegration condition of the battery electro-thermal coupling steady state according to the imbalance condition of the support structure evolution of the energy storage power station; detect the abnormal trend of the power quality transmitted by the energy storage power station based on the disintegration condition of the battery electro-thermal coupling steady state; In the embodiment of the present invention, after receiving the operation status data output by step S1, based on the overall architecture topology diagram of the energy storage power station and the relationship model of the battery box deployment position, the detection of the imbalance of the support configuration evolution is carried out. In this process, the structural stress-temperature difference distribution comparison method is adopted. By deploying a stress sensor array at the key nodes of the support structure (such as the battery module bracket and the junction of the support beam), and combining with the historical data of the ambient temperature change, the thermal expansion and contraction influence curve of the support member is constructed to quantify the stress response change amplitude. The judgment logic of the support configuration imbalance is based on the following criteria: If the stress change rate of the three axes in a certain area exceeds the set threshold (such as ±15% / h) and is discontinuous with the stress of the adjacent support structure (the breakpoint is greater than ±10%) for more than two consecutive time windows (each window is 5 minutes), it is determined that there is an evolution imbalance trend in the support configuration of this area. On this basis, the thermoelectric dual-response sensing unit arranged on the surface of the battery box is used to monitor the coupling change of the thermal power density and the unit volume current density generated by the battery during operation. Through the response delay between the thermal response conduction time, the temperature rise slope and the current input, the stability of the electro-thermal coupling is judged. If the delay exceeds the preset response window or the thermal output power curve shows a significant non-linear mutation, it is defined as the disintegration of the electro-thermal coupling steady state. Subsequently, according to the degree of electro-thermal coupling disintegration, the transfer impedance, voltage consistency index and energy conversion efficiency between single cells are statistically analyzed and compared at the upper and lower boundaries of the preset power factor. If there are frequent oscillations in the bus voltage echo signal or the phase angle deviation exceeds 5 degrees, it is determined that there is an abnormal trend in the quality of the transmitted electric energy. This trend data is represented by the relative stability factor and the harmonic anomaly integral value and output for use in subsequent steps.

[0014] Step S3: Identify the attenuation trend of the grid operation coordination based on the abnormal trend of the transmitted electric energy quality of the energy storage power station; Detect the sudden increase in short-term harmonics of the energy storage power station based on the attenuation trend of the grid operation coordination and the abnormal trend of the transmitted electric energy quality of the energy storage power station; Determine the attenuation status of the grid stability of the energy storage power station based on the sudden increase in short-term harmonics of the energy storage power station; In the embodiments of the present invention, the abnormal power quality trend detected in step S2 is used as input data to identify the attenuation trend of the grid operation coordination. This identification process relies on the interactive boundary data acquisition device between the energy storage power station and the external power grid, records the active and reactive power change curves at the converter ports, and obtains the frequency, phase angle, and voltage transient change information of the interactive interface. Correlation analysis is performed based on the lag time between the fluctuation period of the energy storage unit's power output and the degree of deviation of the power grid main frequency. If the lag time exceeds 120 ms and there is a multi-peak oscillation phenomenon in the power grid response process (i.e., the feedback power curve is not monotonically decreasing), it is considered that there is an attenuation trend in the grid operation coordination. This trend is represented by quantization parameters such as the frequency disturbance duration and the grid load adjustment lag rate. After identifying the coordination attenuation, combined with the previously output abnormal power quality trend data, the wavelet decomposition algorithm is used to perform frequency-domain decomposition on the harmonic components within a short time window, and the energy density changes in the low-frequency band (50 Hz ± 5 Hz) and the high-frequency band (> 100 Hz) are compared. If the high-frequency harmonic energy surge rate exceeds the set value (such as 25% / min) within a certain time window, it is determined that there is a significant short-time harmonic surge in the energy storage power station during this time period. Based on the above detection results, the stability cooperation factor between the energy storage power station and the main power grid node is calculated (depending on the frequency synchronization error, voltage recovery rate, and phase angle recovery rate). If this factor continuously falls below the set critical value (such as 0.75), it is determined that there is an attenuation in the power grid stability. The judgment result outputs the stability attenuation level data, which is classified and described as states such as "slight fluctuation", "periodic oscillation", and "nonlinear misalignment", providing a basis for the next-step evaluation of the battery response change.

[0015] Step S4: Detect the change of the energy storage power station battery state according to the grid stability attenuation condition of the energy storage power station; identify the degree of grid frequency instability according to the change of the energy storage power station battery state; detect the abnormal condition of the energy storage power station battery based on the degree of grid frequency instability and the change of the energy storage power station battery state, and upload it to the cloud platform for early warning.

[0016] In the embodiment of the present invention, based on the power grid stability attenuation condition identified in step S3, the state change of the energy storage power station battery under abnormal power grid disturbances is further traced back in reverse. The multi-node multi-cycle comparison method is adopted to record the SOC change rate, internal resistance change trend and temperature change range of each battery box during the periods of harmonic surge and coordination disorder, and comparative analysis is carried out in combination with the existing health threshold library. If the SOC drop rate of a certain battery cell is greater than 3% / min within 90 seconds after the power grid disturbance, and the internal resistance growth rate exceeds 10% / min, it is determined that the battery state change is abnormal. This change is further used to calculate the degree of power grid frequency instability. The method is as follows: Fit the battery response lag time, voltage rebound amplitude with the power grid frequency fluctuation curve, and calculate the frequency fluctuation peak value, valley value and fluctuation period correspondingly to form a frequency instability index, which is marked as the product of the frequency deviation rate and the frequency recovery time. On this basis, combined with the current temperature distribution map, voltage consistency index and internal resistance abnormality index of the energy storage power station, it is comprehensively judged whether the battery is in an abnormal state. If there are simultaneous phenomena of rapid SOC drop, severe temperature rise and voltage jump in multiple battery boxes in the current cycle, it is determined that the battery group in this area is an abnormal unit. The identification result of the abnormal unit is marked in the form of an ID code, and is packaged together with its corresponding detection data, abnormal factors, determination timestamp and geographical location code, and uploaded to the cloud platform through the edge gateway device deployed at the station end. After receiving the data, the cloud platform automatically triggers the early warning mechanism according to the set abnormal battery response level standard, and generates a fault trend graph, a list of abnormal batteries and a warning notice, and sends them to the operation and maintenance platform to realize the closed-loop process of full-cycle detection of abnormal battery boxes for the actual operation state of the energy storage power station.

[0017] Preferably, step S1 includes the following steps: Step S11: Set the temperature measurement range of the temperature sensor to 0 - 200 °C, the minimum temperature change to 0.05 °C, and the temperature sampling frequency to 10 Hz; In the embodiment of the present invention, to ensure the measurement accuracy of temperature data and the consistency of subsequent battery box performance evaluation, the model of the temperature sensor used is set as the industrial-grade digital temperature sensor PT1000, and the temperature measurement range is set to 0 °C to 200 °C. By configuring a resistance bridge circuit and combining a 24-bit analog-to-digital converter (ADC), the minimum temperature change recognition accuracy of 0.05 °C is achieved. The sensor is installed on the inner walls of the top, middle and bottom of each battery box to capture the temperature distribution gradient in three-dimensional space. The sampling frequency is uniformly set to 10 Hz, and the central processing unit (using the high-performance microcontroller STM32F429) periodically reads the ADC value and calculates the temperature. All measured data are stored in the local edge data processing module (configured with 512MB DDR RAM and 4GB eMMC memory) in real time and marked with a timestamp for subsequent operating environment analysis and initial performance evaluation.

[0018] Step S12: Set the humidity measurement range of the humidity sensor to 0% to 100%RH, the minimum humidity change to 0.1%RH, and the humidity sampling frequency to 5Hz; In the embodiment of the present invention, the sensor selected for detecting the humidity change inside the battery box of the energy storage power station is a capacitive humidity sensor SHT35. This sensor has a humidity measurement range of 0%RH to 100%RH and can achieve a humidity change resolution of at least 0.1%RH. The sampling frequency is configured to 5Hz, and the timing data of temperature sampling is synchronously read by the same central control unit and transmitted via the I²C bus to ensure that the data synchronization accuracy is within the range of ±5ms. The sensor is arranged in the middle of the battery box and above the wiring area to capture environmental characteristics such as condensation risk and airtightness change. The collected data is also stored in the edge computing node and aligned with the temperature sensor sampling timestamp, serving as one of the input factors for subsequent battery initial performance evaluation.

[0019] Step S13: Obtain the data of the battery box of the energy storage power station; In the embodiment of the present invention, the process of obtaining the data of the battery box of the energy storage power station includes data channels in multiple dimensions: indicators such as voltage, current, SOC (State of Charge), SOH (State of Health), single-cell core temperature, number of charge and discharge cycles, and insulation resistance. The data real-time uploaded by the BMS (Battery Management System) is collected through the CAN bus interface. The single-cell voltage values (such as 3.65V ± 0.01V), corresponding current values (in the range of -100A to +100A), and core temperature (obtained from the built-in thermal element) of each series-connected core are read at a frequency of 10 frames per second. The read data is received and classified and stored by the main control system after CRC verification. The numbers, location numbers, and acquisition timestamps of all battery boxes correspond one by one, providing a data basis for environmental information matching and state evolution in subsequent steps.

[0020] Step S14: Use the humidity sensor and temperature sensor to collect the operation environment data of the energy storage power station for the data of the battery box of the energy storage power station; In the embodiments of the present invention, the temperature and humidity sensor devices deployed inside the battery box are utilized to synchronously collect the operation environment data. A dual-channel data docking module is set in the central control system to separately process the temperature and humidity channels. The ring buffer structure is adopted for real-time data caching, and the data in the buffer area is packaged and uploaded to the local environment data recording module every 10 seconds. For the cases of abnormal gradient change of temperature (exceeding 1.5 °C / minute) or sharp fluctuation of humidity (above 10%RH / minute), an alarm flag bit is set to indicate that the external environment has an impact on the battery performance. Such data is synchronized to the battery box data record item according to the time series to form a "running environment - performance performance" binding record, which is convenient for evaluating the environmental coupling impact in step S16.

[0021] Step S15: Based on the battery box data of the energy storage power station, collect the cumulative operation duration data of the energy storage power station; In the embodiments of the present invention, the cumulative operation duration data is statistically calculated based on the battery box activation record and the operation log. Each battery box has a unique number built in at the time of factory deployment. The first grid connection time record (accurate to seconds) is retrieved through the central platform and accumulated in combination with the working period data recorded in the operation log. The collection period is set to update the total duration once at 00:00 every day, and the current working state (idle, charging, discharging) is recorded in real time. For example, the battery box numbered "B01234567" has a cumulative operation time of 4867 hours since grid connection, and the current daily cumulative working time is 11.2 hours, which are both synchronously recorded in the database "battery_operation_log" as one of the reference bases for subsequent initial performance evaluation.

[0022] Step S16: Based on the battery box data of the energy storage power station, evaluate the initial performance of the battery box of the energy storage power station; In the embodiments of the present invention, the initial performance evaluation is carried out in a parallel manner of static parameter comparison and dynamic trend analysis. The benchmark reference values come from the standard performance parameter table in the technical specification provided by the manufacturer. Taking the single cell as the unit, indicators such as voltage deviation, temperature rise rate, current fluctuation, and SOC / SOH stability are calculated item by item. If the cell voltage fluctuates by more than 0.05V within 10 minutes and the SOC fluctuates by more than 5% per unit time, it is considered that there is an initial deviation in performance. Taking the battery box numbered "B01234567" as an example, the initial evaluation shows that 4 cells in it have over-temperature deviation (exceeding the specified threshold by 4 °C), and 2 cells have voltage drift phenomenon. These abnormal data are marked and recorded as the input variables for subsequent state analysis and are uniformly saved in the "initial_performance_record" database field.

[0023] Step S17: Evaluate the initial performance of the battery boxes of the energy storage power station based on the cumulative operation duration of the energy storage power station and the operation environment data of the energy storage power station to obtain the operation state data of the energy storage power station.

[0024] In the embodiment of the present invention, the evaluation of the operation state data is performed by joint analysis based on the multi-dimensional data set obtained in Steps S13 to S16. The environmental data (temperature, humidity) and the operation duration data are mapped into the time series linked list under the battery box number, and the missing data is linearly filled by using the equally spaced interpolation method. Subsequently, a number of evaluation index thresholds are set by using the rule engine, such as the cumulative time when the environmental temperature exceeds 45 °C for more than 100 hours, the humidity is long-term higher than 80%RH, etc., and a weighted score is combined with the operation duration to form the Environmental Stress Index (ESI). Then, this index is fused with indicators such as voltage volatility, current stability, and the range of SOC fluctuations to calculate the Operational Health Index (OHI), which is output in numerical form. For example, for the battery box numbered "B01234567", the ESI is 0.72 and the OHI is 0.86, and the system submits this state data to the "operation_state_database" for Step S2 to call to detect the imbalance of the support configuration evolution.

[0025] Preferably, Step S16 includes the following steps: Step S161: Extract the internal arrangement structure data of the battery box based on the battery box data of the energy storage power station; In the embodiment of the present invention, the battery box data of the energy storage power station includes the physical structure drawings recorded in the installation stage, the structure assembly coding record form, and the optical image acquisition data. Through a high-resolution industrial camera (such as a 12-megapixel CMOS camera) combined with a multi-angle robotic arm for internal structured light scanning, the arrangement image of the battery cell modules inside the battery box is obtained. During the scanning process, the scanning data at each angle needs to be geometrically distorted corrected by using the calibration correction software. Subsequently, the image segmentation algorithm is used to block and identify the positions of different battery cell modules, and the arrangement method is judged whether it is a regular matrix arrangement, a stacked arrangement, or an interleaved nested arrangement by the included angle distribution between the edge lines and the structure lines extracted from the image. The structure image is converted into a two-dimensional arrangement coordinate matrix and recorded in JSON structure. The extracted internal arrangement structure data of the battery box includes the minimum center distance between battery cells, the total number of rows and columns of the arrangement unit, the structure unit density, etc.

[0026] Step S162: Identify the internal conductive connection situation of the battery box based on the internal arrangement structure data of the battery box; In the embodiment of the present invention, based on the two-dimensional arrangement coordinate matrix extracted in step S161, the connection wire path and position are further obtained. The temperature rise image of each connection wire path during operation is collected under low-power energization conditions by combining a visible light image and an infrared thermal imager. The temperature rise area can accurately correspond to the position of the connection line segment. After superimposing the temperature rise image and the arrangement structure image, all wire path segments are extracted through an image matching algorithm. The OCR algorithm is used to extract the specification parameters (such as copper bus width, connector type code) printed on the surface of the connection component from the image, and it is confirmed whether they are standard specifications through a data comparison library. Finally, a topological matrix including the conductive connection methods between each battery cell and adjacent battery cells is established. The elements in the matrix are represented as parameters such as wire path length, cross-sectional area, and material code, constituting the complete internal conductive connection situation of the battery box.

[0027] Step S163: Evaluate the regularity of the busbar wiring in the battery box according to the internal conductive connection situation of the battery box and the internal arrangement structure data of the battery box; In the embodiment of the present invention, the arrangement structure of the battery box extracted in step S161 and the conductive connection topological matrix established in step S162 are jointly analyzed. For each conductive connection path, its path length, direction offset angle, and offset degree from the theoretical shortest path are calculated respectively; further analyze the distribution density of connection nodes, the uniformity of contact point spacing, and the frequency of repeated intersections. If the average offset angle of the unit wire is less than 3°, the repeated intersection rate is less than 10%, and the variance of the contact point density is less than 0.05, it is judged that the wire regularity is good, otherwise it is poor. After summarizing all the evaluation values, a wire regularity score value is constructed. This value is output in a percentage system, representing the neatness, regularity, and standard degree of the wire arrangement in the entire battery box, and generating a data table for the regularity of the busbar wiring in the battery box.

[0028] Step S164: Evaluate the internal heat dissipation capacity data of the battery box based on the regularity of the busbar wiring in the battery box and the internal arrangement structure data of the battery box; In the embodiment of the present invention, according to the busbar wiring regularity score result obtained in step S163 and the battery cell arrangement structure parameters in step S161, the smoothness of the heat dissipation channel and the integrity of the heat conduction path are comprehensively evaluated. A three-dimensional heat flow field simulation model is constructed using a CFD simulation tool (such as Ansys Fluent). In the simulation, the heat flux data of the battery cell and the connection conductor surface are input in an aerodynamic manner, and the thermal conductivity of the battery box housing material and the thermal resistance of the internal wire material are set. The temperature change process of the battery cell within 30 minutes under constant power operation is simulated, and the maximum inter-cell thermal gradient, the average air channel wind speed distribution, and the proportion of the local overheating area are extracted. Through statistical analysis of the simulation data, the average internal heat dissipation capacity value (unit: W / m²·K) and the heat dissipation non-uniformity index (defined based on the maximum temperature difference / average temperature difference) of the battery box are output, forming a data structure body for the internal heat dissipation capacity of the battery box.

[0029] Step S165: Calculate the initial voltage deviation of the energy storage power station battery based on the data of the energy storage power station battery box; In the embodiment of the present invention, the data of the energy storage power station battery box includes the voltage values of all cell monomers in the initial charging state, which are recorded once every 100 ms by the voltage acquisition module. All voltage values are composed into a voltage data vector, and the maximum value V_max, the minimum value V_min, and the average value V_avg are calculated. Further calculate the voltage deviation as ΔV = V_max - V_min, and the voltage standard deviation σ_v. The initial voltage deviation of the energy storage power station battery output consists of two parameters: the voltage difference ΔV (unit: mV) and the standard deviation σ_v (unit: mV). The larger the voltage deviation, the worse the consistency of the battery cells, which further reflects the risk of the initial balance stability of the battery pack.

[0030] Step S166: Determine the initial operation stability of the energy storage power station battery box based on the internal heat dissipation capacity data of the battery box and the initial voltage deviation of the energy storage power station battery; In the embodiment of the present invention, the internal heat dissipation capacity data of the battery box generated in step S164 and the voltage deviation data in step S165 are logically correlated and analyzed to determine whether there is local heat accumulation in the heat dissipation capacity data (i.e., the heat dissipation non-uniformity index > 1.5), and then determine whether the voltage deviation ΔV is greater than a set threshold (such as 50 mV). If there are both uneven heat dissipation and a large voltage difference, the initial operation stability level is determined to be low; if only one item is abnormal, it is medium; if both are normal, it is high. Based on the above judgment logic, an initial operation stability level value L_s (taking values of high, medium, and low) is constructed, and the boundary values of the stability level are corrected by combining the environmental temperature and humidity data to prevent misjudgment due to sensor drift, and the initial operation stability level and its corresponding heat dispersion factor and voltage fluctuation factor are output.

[0031] Step S167: Evaluate the initial performance of the energy storage power station battery box based on the initial operation stability of the energy storage battery box and the initial operation stability of the energy storage power station battery box.

[0032] In the embodiments of the present invention, the initial operation stability level of the battery box evaluated in step S166 is compared with the operation stability records of the entire battery box during the manufacturing and debugging phases, including data items such as the comparison record of cell swelling during historical operation, the time difference of battery balanced charge and discharge, and the internal impedance distribution of cells. The weighted evaluation of multiple indicators is carried out by using the decision rule tree method to determine the comprehensive score S_p. The scoring dimensions include heat dissipation capacity, structural consistency, voltage consistency, thermal stability level, etc. It is set that the score S_p > 80 is excellent performance, 60 - 80 is medium, and < 60 is poor. An initial performance evaluation result table of the energy storage power station battery box is generated, and a detailed result structure including the score value, grade classification, and contribution ratio of each indicator is output. This data serves as the initial reference data for the subsequent trend of the battery box state change and as a comparison reference for the subsequent anomaly detection data.

[0033] Preferably, step S17 includes the following steps: Step S171: Collect the abnormal fluctuation of the operating environment temperature and humidity according to the operating environment data of the energy storage power station; In the embodiments of the present invention, an industrial-grade temperature and humidity sensor module group is deployed in different directions of the environment where the energy storage power station battery box is located. The deployed sensor devices need to have the ability to continuously monitor for 24 hours, with the temperature measurement accuracy not less than ±0.1 °C and the humidity measurement accuracy not less than ±1.5%RH. The sensors are respectively installed near the top, bottom, left and right sides of the battery box and the external ventilation port area to achieve the collection of temperature and humidity data coverage of key parts such as local hot areas, enclosed areas, and ventilation areas. The sampling period of each sensor is fixed at 10 seconds, and the collected data is uniformly archived by the edge data acquisition unit (with A / D conversion and preliminary data caching functions). The collected temperature and humidity data is transmitted to the data preprocessing unit in the local controller for abnormal fluctuation identification processing. The identification rule is set as follows: within 60 consecutive minutes, when the temperature change amplitude exceeds ±3 °C, or the humidity change amplitude exceeds ±10%RH, it is marked as an "abnormal fluctuation point"; if the number of abnormal fluctuation points in a certain time period occupies more than 30% of the total number of points in this period, it is defined that there is an "abnormal fluctuation of the environmental temperature and humidity" in this period, and the generated result is an "abnormal fluctuation situation determination data table", including the time period number, abnormal fluctuation amplitude, frequency, and specific sensor location distribution.

[0034] Step S172: Determine the sudden change of the operating environment day and night temperature and humidity based on the abnormal fluctuation of the operating environment temperature and humidity; In the embodiment of the present invention, after completing the abnormal fluctuation determination data table in step S171, the data for each time period is extracted and divided into day-night cycles. The data is grouped according to the natural day time, and each group corresponds to two time periods of daytime (06:00–18:00) and night (18:00–06:00) within 24 hours. The average temperature value and humidity value within the two day-night time periods are compared, and the temperature difference ΔT = |T_day - T_night| and humidity difference ΔRH = |RH_day - RH_night| are calculated. The mutation determination threshold is set as: when ΔT exceeds 6°C and ΔRH exceeds 15%RH, it is determined as a day-night mutation. If in a certain natural day, at least one of ΔT and ΔRH exceeds the threshold and the continuous occurrence times exceed 3 consecutive days, it constitutes a "day-night temperature and humidity mutation situation". The analysis results are summarized to generate a "day-night mutation statistical table", and the content includes fields such as the mutation time range, mutation type (temperature, humidity, or both), continuous days, mutation amplitude range, etc.

[0035] Step S173: Based on the situation that the day-night temperature and humidity mutation in the operating environment exceeds 30%, identify the initial performance of the battery box of the energy storage power station and the oxidation trend of the energy storage power station structure; In the embodiment of the present invention, the proportion of mutation events in the total monitoring period is statistically calculated in the day-night mutation statistical table. If the proportion of mutation days exceeds 30%, the operation of identifying the oxidation trend of the structure is performed. Taking the high mutation period (a continuous period with a mutation proportion exceeding 30%) as the analysis window, the oxidation trend is estimated by combining the change in relative humidity in the ambient air and the parameters of the battery box shell material (such as aluminum alloy or steel structure). The specific method is: combining the relationship between environmental humidity and metal corrosion rate, the total oxidation trend level within the analysis window is obtained by accumulating the daily oxidation growth rate data, and it is normalized to a percentage value to generate structure oxidation trend data, such as 40%, 50%, 60%, etc., which are output as a "structure oxidation trend level evaluation table" for subsequent judgment on whether to enter the structure pressure-bearing test process.

[0036] Step S174: Test the pressure-bearing operation state of the energy storage power station when the cumulative operation duration of the energy storage power station exceeds 48h and the structure oxidation trend of the energy storage power station exceeds 50%; In the embodiment of the present invention, when the oxidation trend value in the evaluation result of the structural oxidation trend level exceeds 50% and the cumulative operation duration of the energy storage power station after startup exceeds 48 hours (the startup time is recorded by the operation time monitoring system and accumulated), the pressure-bearing operation state test is performed. A pressure measurement component is installed at the connection position between the battery box and the power station frame, including resistance strain gauges, vibration acceleration sensors, and thermal expansion displacement sensors installed at the force-bearing points of the box body (such as the bottom support seat and the top cover hinge point). After the data of each measurement point is collected in real time, it is transmitted to the control unit, and through the cross-comparison of the three parameters of stress, temperature, and deformation, the difference from the initial structural mechanics state data at the factory (stored in the equipment management system) is compared. If the strain value exceeds 80% of the designed elastic limit, the vibration intensity increases by more than 50%, and the thermal expansion amount exceeds 1.5 mm, it is determined that the pressure-bearing state approaches the critical state, and a "pressure-bearing operation state report" is generated, including the structural deformation level, stress distribution diagram, and warning classification index.

[0037] Step S175: Estimate the overload situation of the energy storage power station according to the load operation state of the energy storage power station; In the embodiment of the present invention, based on the pressure-bearing operation state report, the pressure-bearing level is mapped to the power and load level of the power station. Combining the current load data of the energy storage power station (the power load curve recorded every 10 seconds obtained from the power meter and current collector), a comparative analysis of the load trend and the pressure-bearing state is performed. Define the "overload threshold" as the load percentage corresponding to the structural strain limit. If the power corresponding to the strain critical value is 1000 kW and the current power exceeds this value, it is considered "operation overload". Compare the measured actual power load data with this threshold, calculate the overload ratio, and output the operation overload determination result.

[0038] Step S176: Evaluate the operation state data of the energy storage power station based on the overload situation of the energy storage power station and the structural oxidation trend of the energy storage power station for the initial performance of the battery box of the energy storage power station.

[0039] In the embodiment of the present invention, the structural oxidation tendency percentage value obtained in step S173 and the operation overload determination result generated in step S175 are used as dual variable inputs to evaluate the initial performance of the battery box of the energy storage power station. An operation status classification system is constructed, including: stable (oxidation trend <30%, no overload), mild warning (oxidation trend 30%-50%, mild overload), moderate risk (oxidation trend 50%-70%, mild or severe overload), high risk (oxidation trend >70%, severe overload). Using the above logical rules, the corresponding operation status level is output by judging the cross-combination result of the oxidation trend level and the overload situation. The evaluation results include the operation status level (e.g., moderate risk), influencing factors (structural oxidation trend and operation load ratio), and the corresponding recommended maintenance time period, which are summarized into an "operation status data report table" to support the subsequent monitoring, operation and maintenance, and early abnormality detection process of the battery box of the energy storage power station.

[0040] Preferably, the energy storage support configuration evolution imbalance detection in step S2 includes: Identify the degree of oxidation of the connection structure of the energy storage power station based on the operating status data of the energy storage power station; In the embodiment of the present invention, the operating status data of the energy storage power station includes but is not limited to: the real-time ambient humidity (unit: %RH) and temperature (unit: °C) obtained by the temperature and humidity acquisition unit in the station; and the electrical contact resistance measurement data (unit: mΩ) located on the surface of the energy storage connection terminal (including bolts, copper bars, etc.). By setting a four-wire resistance measurement module at each connection end, the resistance value is collected every 5 minutes, and uploaded to the local industrial control system together with the current and voltage records of the position. The multi-channel data synchronization acquisition module implemented by hardware is used to link this type of data with the temperature rise of the metal surface (acquired by the thermal imager) and the change of the infrared reflectivity of the metal (acquired by the infrared spectrometer). According to the increasing trend of the contact resistance of stainless steel or copper conductors during the oxidation process, a mapping table of the contact resistance time series increase and the oxidation level is established, and the oxidation level is divided into four categories: mild (ΔR<2mΩ), moderate (2–5mΩ), severe (>5mΩ) and extremely severe (>10mΩ). The system identifies the degree of oxidation of the connection structure by comparing the above table. This process does not rely on model inference, but is based on the measured physical resistance value and the trend of electrical property changes during the metal oxidation process.

[0041] Determine the loosening trend of the energy storage power station connection structure based on the oxidation degree of the energy storage power station connection structure; In the embodiments of the present invention, the triaxial acceleration sensor at the connection point is called again to collect the micro-vibration frequency (unit: Hz) and acceleration (unit: mg) generated during the operation of the joint. The acceleration sensor records the dynamic response data within each second at a frequency of 500 Hz. The abnormal resistance mutation and abnormal vibration frequency jointly constitute the loosening trend identification index. In implementation, the connection points with an oxidation level of "moderate" or above are taken as the key monitoring objects, and the situation where the number of resistance fluctuations exceeds 3 times and the acceleration amplitude fluctuation range exceeds ±25 mg within a unit time (1 hour) is analyzed. Such an electrical connection structure is determined to have a loosening trend. This operation logic is based on the co-variation characteristics of the measured resistance and the dynamic response signal rather than empirical rules, and uses a fixed hardware signal threshold judgment method. All judgment results are stored in the non-volatile memory of the local PLC control system for subsequent calls.

[0042] Estimate the micro-vibration condition at the connection of the energy storage power station based on the loosening trend of the connection structure of the energy storage power station; In the embodiments of the present invention, a high-sensitivity micro-vibration capture device (such as a combined module of a MEMS triaxial gyroscope and a high-frequency MEMS accelerometer) is arranged on the connection structure where the loosening trend has been identified, and the micro-vibration signal is collected at a sampling frequency of 1000 times per second. In the embodiment, the sensors used quantify the vibration intensity in each direction of the X, Y, and Z axes, with the unit of μg, and analyze the frequency-domain distribution of the vibration signal in combination with the FFT (Fast Fourier Transform) algorithm to extract the high-frequency vibration energy density (unit: dB / Hz) in the range of 1–100 Hz. This density index is used as the micro-vibration intensity characterization index, and the maximum value and the mean value are recorded. If the oxidation degree of the connection structure is above moderate and the vibration energy density exceeds the threshold (such as 20 dB / Hz), the estimated micro-vibration condition is "active level". This process does not involve model inference, and all data processing is completed using deterministic algorithms and measurement threshold judgments.

[0043] Measure the degree of mechanical stress growth of the energy storage power station structure based on the micro-vibration condition at the connection of the energy storage power station; In the embodiments of the present invention, in order to quantify the mechanical stress changes caused by micro-vibrations, a strain gauge array is deployed on the support structure and connection plate of the energy storage power station (with a set of bidirectional strain gauges deployed every 50 cm), and the full-bridge electrical strain measurement system is used to collect the stress responses generated at the corresponding positions under vibration excitation. The strain gauge module used amplifies the strain signal and converts it into stress units (unit: MPa), and the measurement accuracy is controlled within ±0.5%. The stress response waveform within each vibration cycle is collected and its maximum amplitude and average amplitude are obtained, and the stress growth rate is analyzed by data comparison, that is: dσ / dt (unit: MPa / h). If the stress response growth rate of the structural part under the corresponding vibration excitation exceeds the set threshold (such as 1.5 MPa / h), it is marked that there is a phenomenon of continuous mechanical stress growth in this structural part. The stress measurement system and the micro-vibration analysis subsystem are synchronously sampled in a unified time-stamp manner to ensure the accuracy of the analysis process.

[0044] Predict the micro-deformation status of the energy storage power station structure according to the mechanical stress growth degree of the energy storage power station structure and the micro-vibration conditions at the connections of the energy storage power station; In the embodiments of the present invention, using the obtained structural stress growth data and the micro-vibration parameters in step S23 as inputs, a structural displacement measurement unit (laser displacement meter or distributed fiber Bragg grating ranging system) is called to measure the micron-level displacement change of the structure per unit time. During the implementation process, each laser displacement meter records the maximum displacement values in the X and Y directions of a certain fixed support node, and a one-to-one mapping relationship is established between the displacement change amount (unit: μm), the stress growth rate, and the vibration frequency to determine whether micro-deformation characteristics appear. If the maximum displacement amplitude continuously exceeds 20 μm within a unit time (1 hour), combined with the known stress growth rate and vibration level, the system determines that there is a significant micro-deformation trend in this structure. All displacement data is completed by physical measurement devices and does not rely on algorithm estimation. The measurement devices are fixedly installed in the preset interfaces inside the structure housing, and the data is uploaded to the edge processing module and stored in the database through industrial Ethernet.

[0045] Detect the dynamic fatigue status of the energy storage power station structure according to the micro-deformation status of the energy storage power station structure and the mechanical stress growth degree of the energy storage power station structure; In the embodiments of the present invention, by combining the stress growth rate and the deformation amount, a stress-deformation amount history curve is constructed at the key nodes of the structure. The periodic cycle number statistical method is adopted to record the number of daily stress fluctuation cycles (each cycle is defined as a loading-unloading-reloading process) and the maximum stress amplitude. Based on the fatigue limit of the material (different steel grades correspond to different SN curves, which are determined in the design stage), the actual stress cycle loading times are compared with the fatigue limit cycle number threshold to judge the fatigue level: primary (<30% fatigue life), intermediate (30% - 60%), severe (more than 60%). The fatigue state is tagged in real time and updated to the structure state database. The data processing does not involve abstract model reasoning and is completed by directly comparing the standard curve of material mechanics with the measured data.

[0046] Detect the imbalance of the support configuration evolution of the energy storage power station based on the dynamic fatigue condition of the energy storage power station structure and the micro-deformation condition of the energy storage power station structure.

[0047] In the embodiments of the present invention, by comparing the fatigue level, the amplitude of the micro-deformation amount and its spatial distribution pattern of each structural support node, a bearing state distribution map of each unit of the support structure is constructed. If the fatigue level of any node in the support system is severe, and the corresponding displacement amplitude is not less than 50μm, and the average displacement difference of the 3 connecting nodes around this node exceeds 30μm, the system determines that the current support configuration has evolved out of balance. The structural support configuration is no longer the initial design state, showing stress concentration or uneven deformation distribution. The system records the number, spatial coordinates and deformation amount level of the support imbalance area to form a complete "report on the evolution imbalance of the support configuration" for the subsequent formulation of maintenance strategies and early fault warning. This conclusion is derived from physical data statistics, the structural distribution displacement map and the cross-validation of the fatigue curve, and does not involve any model algorithms or empirical rules.

[0048] Preferably, the detection of the battery electro-thermal coupling steady-state disintegration condition in step S2 includes: Identify the abnormal extrusion inside the battery according to the imbalance of the support configuration evolution of the energy storage power station; In the embodiments of the present invention, based on the monitoring data of the support structure configuration of the energy storage power station box, decoupled analysis of the configuration evolution trend is carried out. Strain gauge arrays and structural displacement gauges are installed at the key stress nodes at the bottom, side walls and brackets of the energy storage unit. Among them, high-precision foil resistance strain gauges are selected for the strain gauges, and the response time is less than 10 ms; laser triangulation displacement sensors are used for the displacement gauges, and the measurement accuracy reaches 0.05 mm. Through the structural strain field and displacement data at multiple moments during the dispatching period, the difference between the yield critical deformation amplitude and the current deformation of each support member is calculated, and the configuration evolution imbalance modes such as unilateral sinking, deformation distortion, and connection loosening of the support bracket are identified by using the strain concentration area. If it is identified that there is a sudden gradient displacement or abnormal gradient aggregation of strain in a local member in the support path, it can be confirmed that there is a local abnormal extrusion phenomenon induced by the redistribution of the support load inside the battery pack.

[0049] Measure the degree of imbalance in the lateral force on the battery cells according to the abnormal extrusion situation inside the battery; In the embodiments of the present invention, after it is confirmed that abnormal extrusion has occurred, the change in the lateral contact pressure of the battery cells is obtained through the MEMS micro pressure sensor array embedded in the side structure of the battery module. The spacing between the sensors is not greater than 10 mm to ensure that the accuracy covers a single battery cell unit. The measured pressure data is compared with the nominal arrangement mechanical equilibrium value of the battery cells, and the deviation degree of the lateral pressure difference between each battery cell and the standard pressure gradient is calculated. The sensor data arranged inside the battery module is converged to the edge processing unit in real time through the serial I²C protocol, and a lateral pressure distribution field is constructed through the multi-point spatial interpolation method (non-model type), and its gradient direction and amplitude interval are extracted. If the single-direction asymmetric area in the lateral pressure distribution exceeds 30%, and the maximum gradient exceeds 200 kPa / m, it is determined that the imbalance in the lateral force on the battery cells is serious.

[0050] Determine the horizontal displacement condition of the battery cells based on the degree of imbalance in the lateral force on the battery cells and the abnormal extrusion situation inside the battery; In the embodiments of the present invention, the identified extrusion position coordinates are superimposed on the force distribution gradient map measured in S22. After determining the main direction of the force and the stress concentration points, the laser displacement probe is started to measure the horizontal displacement of the corresponding battery cells. The probe is deployed along the width direction of the module, and the accuracy is not less than 0.01 mm. The actual horizontal offset of the battery cell surface relative to the fixed reference surface of the battery box is recorded. According to the measurement results, a displacement distribution curve of the battery cell sequence is established, and combined with the nominal arrangement spacing and the actual deviation interval of the battery cells, parameters such as the displacement peak value, deformation extension length, and concentrated offset area are extracted to form a "battery cell horizontal displacement parameter matrix". If the horizontal displacement of any single battery cell exceeds the design allowable offset upper limit (usually 1.5 mm), and more than three adjacent battery cells deviate in the same direction, it is confirmed that the battery cell sequence has undergone horizontal displacement.

[0051] Measure the imbalance of the insulation distance between battery cells according to the horizontal displacement condition of the battery cells; In an embodiment of the present invention, based on the obtained horizontal displacement parameter matrix of the battery cells, the ultrasonic pulse reflection module is deployed by an interval measurement method to perform a reflection time scan on the thickness of the insulating medium between the battery cells, and the ranging accuracy needs to reach 0.02 mm. Taking the three points in the middle, upper, and lower parts of each pair of adjacent battery cells as ranging sampling points, an insulation distance profile is constructed. Taking the standard insulation distance (such as 2 mm) as a reference, calculate the insulation distance compression ratio at different positions. Determine the boundary of the area where the compression ratio exceeds 30%. If the compression area is concentrated in a certain battery cell group and extends horizontally by more than four battery cells, it can be determined that an effective imbalance band is formed due to the imbalance of the insulation distance between the battery cells. After jointly analyzing all the measured distance data and the offset direction, an "insulation imbalance level determination map" is output.

[0052] Determine the degradation of the electrical connection performance of the energy storage power station according to the imbalance of the insulation distance between the battery cells; In an embodiment of the present invention, the insulation imbalance level determination map output in this step is matched with the positions of the conductive connection sheets between the corresponding battery cells. Use a laser conduction tester to measure the local conduction resistance of the connection sheets, and use the four-terminal method for precise measurement with an accuracy not lower than 1 μΩ. Compare the resistance of the connection sheets in the imbalance area with the nominal initial state resistance, extract its resistance growth rate curve, and simultaneously evaluate the transition impedance and abnormal contact heat value. If the resistance growth rate in a certain area exceeds 200% and overlaps with the area where the heat value rises (>15%), it is considered that the electrical connection performance has deteriorated significantly. A "connection performance degradation distribution map" is formed in the data, in which the spatial overlap rate of the high-resistance path concentration band and the insulation imbalance band is marked as the basis for subsequent thermal coupling instability deduction.

[0053] Measure the distortion of the heat dissipation path of the battery cells according to the imbalance of the insulation distance between the battery cells; In an embodiment of the present invention, an embedded infrared thermal imaging unit is used to perform a dynamic scan on the surface heat distribution of the battery module, with an image frame rate not lower than 25 Hz and a temperature resolution better than 0.1 °C. Combining with the insulation compression section obtained in S24, the extension direction and central offset of the heat diffusion area are extracted specifically. By constructing a heat flow path vector map (based on the first derivative of the temperature gradient) to invert the heat dissipation path morphology, and further using the heat flux density distribution and isotherm fitting to detect whether it has shifted, compressed, or broken. If the original linear heat flow direction deflects by more than 30° in the compression area, or the width of the isothermal zone of the heat dissipation path decreases by more than 40%, it is determined that the heat dissipation path of the battery cells has been severely distorted.

[0054] Detect the breakdown of the electro-thermal coupling steady state of the battery according to the distortion of the heat dissipation path of the battery cells and the degradation of the electrical connection performance of the energy storage power station.

[0055] In the embodiments of the present invention, a coupled steady-state risk assessment grid is constructed based on the spatially overlapping region where the heat dissipation path is blocked and the connection impedance increases. The integrated electro-thermal power consumption density (the superposition value of the heat power consumption and the conduction power consumption per unit area per unit time) is introduced as an index in this grid. If the electro-thermal power consumption density in a certain grid exceeds the threshold of 2 W / cm² and is accompanied by an increase in the conduction impedance, it is determined that the coupled steady-state structure in this region is unbalanced, and an "electro-thermal coupled steady-state disintegration map" is output. Then, by superimposing three-cycle data in time series, it is judged whether the disintegration state in this region is in a continuous deterioration trend, so as to identify whether a stability disintegration unit is formed, providing a basis for the downstream intelligent alarm system to call.

[0056] Preferably, the abnormal trend detection of the power quality transmitted by the energy storage power station in step S2 includes: Detecting the continuous growth of the internal resistance of the battery transmission current based on the electro-thermal coupled steady-state disintegration condition of the battery; In the embodiments of the present invention, by collecting the current, voltage, and temperature data of each battery cell in the energy storage power station in real time, the change in the voltage drop of the battery transmission current is obtained by using a high-precision power quality monitoring device, and combined with the detection result of the electro-thermal coupled steady-state disintegration condition of the battery, the dynamic internal resistance value of the battery is calculated. The specific operations include: arranging current sampling sensors and voltage sampling modules to collect the battery port current and terminal voltage signals respectively, and ensuring the time consistency of the data through synchronous sampling technology; further using digital filtering technology to eliminate noise interference and obtain stable voltage and current data. The internal resistance calculation is based on Ohm's law, and the internal resistance of the battery is derived by using the ratio of the measured voltage drop to the current value. Sampling continuously for multiple time periods to form an internal resistance change curve, and detecting whether the internal resistance shows a continuous growth trend through statistical analysis, using trend analysis algorithms to identify the change rate and persistence of the internal resistance, and outputting quantization parameters of the continuous growth of the battery internal resistance, such as the internal resistance growth rate and the growth time window. This step is connected to the next step, and the continuously growing internal resistance parameters are used as input data to support the determination of the imbalance condition of the subsequent transmission current shunt.

[0057] Determining the imbalance condition of the battery transmission current shunt according to the continuous growth of the internal resistance of the battery transmission current; In the embodiments of the present invention, based on the continuously increasing battery internal resistance parameter, current data of each parallel branch in the energy storage battery pack is further collected through a multi-point current distribution monitoring device. High-precision Hall effect current sensors are respectively installed on the transmission lines of each parallel branch of the battery pack to ensure real-time acquisition of the current change of each branch. According to the internal resistance change data, combined with the current sampling value, the current shunt balance degree is quantified by calculating the current ratio between branches. Specifically, the root mean square deviation (RMSD) index of current distribution is used to statistically analyze the deviation degree of each branch current and determine the degree of current shunt imbalance. Continuous increase in internal resistance will cause the current of some branches to decrease, thus leading to current shunt imbalance. Using time series analysis technology, the change trend of the current shunt index is tracked, and the current shunt imbalance level parameter is output. The output parameter of this step is used as the input condition for subsequent abnormal overcharge prediction to achieve step-by-step information transfer and in-depth analysis.

[0058] Predict the abnormal overcharge condition of the energy storage power station battery according to the current shunt imbalance condition of the battery transmission current; In the embodiments of the present invention, combined with the obtained current shunt imbalance parameter, abnormal detection technology is used to analyze the current and voltage characteristics during the battery charging stage. By setting up a dedicated battery charging monitor, the charging current curve and the battery voltage response signal are continuously collected to form a charging state database. By comparing with the standard charging curve, abnormal deviation phenomena are detected. The specific operations include calculating the peak value of the charging current, the charging time, and the stability index during the voltage plateau stage. The overcharge phenomenon of some battery cells caused by current shunt imbalance will be reflected in the charging current fluctuation and voltage abnormality. Using the statistical threshold method, abnormal current fluctuation points during the charging process are identified, combined with the current shunt imbalance level, the abnormal overcharge risk level is judged, and the abnormal overcharge probability parameter is quantified. This prediction result provides key input data for the next analysis of the degradation trend of the battery active material, completing the natural connection of the data stream.

[0059] Determine the degradation trend of the battery active material according to the abnormal overcharge condition of the energy storage power station battery; In the embodiments of the present invention, based on the predicted abnormal overcharge parameter, combined with the battery chemical property detection equipment, the state detection of the active material is implemented. The active material of the sampled battery cell is quantitatively characterized by a laser scanning confocal microscope or an X-ray diffractometer to obtain the change information of the material structure integrity and surface morphology. Further, combined with the cyclic charge and discharge historical data of the battery, the capacity loss rate and the degree of structural damage of the active material are determined by chemical analysis methods. The abnormal overcharge parameter is associated with the chemical analysis result to construct a degradation trend curve of the active material. This trend is measured by the percentage of material capacity loss, reflecting the deterioration speed and cumulative degree of the material. This data serves as the basis for the subsequent evaluation of the damage degree of the electrode interface cooperation mechanism, forming a complete technical chain from current abnormality to material degradation.

[0060] Testing the degree of damage to the battery electrode interface synergy mechanism based on the degradation trend of battery active materials; In the embodiments of the present invention, using the Electrochemical Impedance Spectroscopy (EIS) technology, for the degradation trend of the active materials determined in step S2-4, the synergy mechanism of the battery electrode interface is deeply detected. By applying alternating current signals with different frequencies, the impedance response data of the battery electrode interface are collected to obtain key parameters such as the interfacial charge transfer impedance and the electrolyte diffusion impedance. The impedance spectrum data are compared and analyzed with the degradation trend of the active materials to quantitatively describe the degree of damage to the electrode interface synergy mechanism. Specifically, the complex impedance diagram and the equivalent circuit model fitting method are used to separate the impedance contributions of each component of the interface, and calculate the reduction ratio of the interface activity and the degree of hindrance to ion migration. This degree of damage is expressed as the percentage increase in the interface impedance, providing important data support for the subsequent estimation of the limitation of the internal ion diffusion channel, and ensuring the technical closed-loop from material degradation to interface damage.

[0061] Estimating the limitation of the internal ion diffusion channel of the battery based on the degree of damage to the battery electrode interface synergy mechanism and the degradation trend of the battery active materials; In the embodiments of the present invention, combining the obtained electrode interface damage parameters and the material degradation trend data, a multi-parameter coupling analysis method is used to estimate the limitation of the internal ion diffusion channel of the battery. By comprehensively statistically analyzing the battery electrochemical test data, the physical structure change of the active materials, and the interface impedance change, the narrowness degree and the hindrance level of the ion diffusion path are determined. The specific steps include using the pulsed current method to measure the diffusion coefficient, observing the internal microstructure change by combining with the Scanning Electron Microscope (SEM), and quantitatively analyzing the change of the cross-sectional area and the smoothness rate of the ion channel. The numerical interpolation method is used to construct the distribution map of the limitation degree of the ion diffusion channel and output the ion diffusion hindrance index. This index is used as the direct input parameter for detecting the abnormal trend of the power transmission quality, realizing the effective correlation between the internal and external structure changes and the abnormal power quality.

[0062] Detecting the abnormal trend of the power transmission quality of the energy storage power station based on the limitation of the internal ion diffusion channel of the battery.

[0063] In the embodiments of the present invention, taking the obtained ion diffusion hindrance index as the core parameter, combining the data of the overall power quality monitoring system of the energy storage power station, the abnormal trend detection of the transmitted power quality is carried out. By monitoring the AC side voltage waveform, harmonic content, power factor and transient current change, and combining the internal parameter change of the energy storage battery pack, signal processing technology is used to extract abnormal features. Specifically, through Fourier transform and wavelet transform technologies, the frequency components and change trends in the voltage and current signals are analyzed to identify the decrease in energy conversion efficiency and the deterioration of power quality caused by restricted ion diffusion. Combining the ion diffusion hindrance index with power quality indicators, a multi-dimensional abnormal trend map is constructed to quantify the abnormal trend level and output the abnormal trend parameters of the transmitted power quality. This parameter provides an important reference for the overall abnormal detection system of the energy storage power station, realizing the technical closure from the internal physical changes of the battery to the abnormal power quality.

[0064] Preferably, step S3 includes the following steps: Step S31: Detect the distortion condition of the transmitted voltage of the energy storage power station according to the abnormal trend of the transmitted power quality of the energy storage power station; In the embodiments of the present invention, the detection of the distortion condition of the transmitted voltage of the energy storage power station is realized by real-time collection and spectrum analysis of the voltage signal at the output end of the energy storage power station. High-precision voltage sensors are arranged at the voltage output end of the energy storage power station to collect the time-domain data of the three-phase voltage in real time. The sampling frequency of the sensor is set to not less than 10 kHz to ensure the complete capture of high-frequency harmonic signals. The collected voltage signal is transmitted to the data acquisition system after analog-to-digital conversion. Subsequently, the fast Fourier transform (FFT) algorithm is used to decompose the spectrum of the collected voltage signal to obtain the amplitude and phase information of each frequency component of the voltage. Calculate the total harmonic distortion (THD) index of the voltage, which is defined as the ratio of the effective value of all harmonic components to the effective value of the fundamental wave. By setting the fundamental wave frequency (such as 50 Hz or 60 Hz) as a reference, the amplitude distribution of the high-order harmonics is decomposed to obtain the distortion degree of the voltage waveform. This process is completed relying on a digital signal processing chip or a dedicated power quality analyzer to ensure the accuracy and real-time performance of the calculation. Calculate the total harmonic distortion (THD) index of the voltage, which is defined as the ratio of the effective value of all harmonic components to the effective value of the fundamental wave. By setting the fundamental wave frequency (such as 50 Hz or 60 Hz) as a reference, the amplitude distribution of the high-order harmonics is decomposed to obtain the distortion degree of the voltage waveform. This process is completed relying on a digital signal processing chip or a dedicated power quality analyzer to ensure the accuracy and real-time performance of the calculation.

[0065] Step S32: Identify the attenuation trend of the grid operation coordination according to the distortion condition of the transmitted voltage of the energy storage power station; In the embodiments of the present invention, the identification of the attenuation trend of power grid operation coordination is further analyzed based on the energy storage power station transmission voltage distortion data obtained in step S31, and a mapping relationship between the voltage waveform distortion index and the physical parameters related to power grid coordination is constructed. The increase in voltage waveform distortion usually reflects unbalanced power grid load, resonance, or intensified voltage fluctuation, which in turn affects the synchronous and stable operation of the power grid. The time series analysis method is used to extract the trend change characteristics in the voltage distortion data, including the trend line slope, fluctuation amplitude, and periodic change characteristics. Combining with the historical operation data of the power grid, the correlation between the voltage distortion index and the power grid coordination index is calculated. The coordination index can include power grid frequency stability, phase difference change rate, synchronous machine speed deviation, etc., which are collected by the phasor measurement unit (PMU) deployed at the key nodes of the power grid. A power grid operation coordination attenuation trend curve is generated. This trend curve can reveal the continuous impact of voltage distortion on the power grid synchronization performance, and use numerical calculation methods to predict the coordination attenuation within a certain period in the future. Through this step, a quantitative description of the dynamic relationship between voltage distortion and power grid operation coordination is formed to support the subsequent assessment of power grid stability.

[0066] Step S33: Detect the short-term harmonic surge condition of the energy storage power station transmission based on the attenuation trend of power grid operation coordination and the voltage distortion condition of the energy storage power station transmission; In the embodiments of the present invention, detecting the short-term harmonic surge condition of the energy storage power station transmission requires comprehensive determination by combining the dual information of the power grid coordination attenuation trend and the voltage distortion condition. Using the voltage harmonic spectrum information obtained in step S31, the harmonic amplitude change rate is continuously calculated in a short time, and special attention is paid to the mutation values of high-order harmonics (such as the 11th, 13th, and higher orders). The short-term harmonic surge is manifested as a sharp rise in the harmonic amplitude on the time scale of milliseconds to seconds. Combining with the power grid coordination attenuation trend curve calculated in step S32, the power grid condition background of the harmonic surge event is analyzed. When the coordination attenuation intensifies, the system's ability to suppress harmonics decreases, and the harmonic amplitude is more likely to rise rapidly. By setting a multi-layer threshold mechanism, the starting point and peak duration of the harmonic surge are determined, and the threshold parameters are quantitatively obtained based on the historical operation data of the power grid over the years and the historical harmonic records of the energy storage power station. During the implementation process, the digital signal processing unit is used to perform sliding window FFT analysis on the real-time voltage signal. The window length is set to 100 ms, and the sliding step is 10 ms to ensure accurate capture of the harmonic dynamic changes. The harmonic surge data is transmitted to the central monitoring system through a high-speed data link. Combining with the coordination trend, statistical analysis methods are used to determine the severity and frequency of the short-term harmonic surge, and the time identification and amplitude parameters of the surge event are obtained.

[0067] Step S34: Determine the power grid stability attenuation condition of the energy storage power station based on the short-term harmonic surge condition of the energy storage power station transmission.

[0068] In the embodiments of the present invention, the determination of the grid stability attenuation status of the energy storage power station is based on the short-term harmonic surge parameters detected in step S33, and the key indicators of the short-term harmonic surge event are extracted, including the surge amplitude peak value, the surge duration, and the event occurrence frequency. Combining with the real-time operation data of the energy storage power station grid, such as the current harmonic content, the voltage fluctuation amplitude, and the frequency deviation, a comprehensive stability evaluation parameter is formed. The frequency domain analysis technology is used to match the harmonic surge frequency range with the grid oscillation mode, and judge the impact of the harmonic surge on the grid oscillation mode, especially paying attention to the interaction between low-frequency oscillation (in the range of 0.1 Hz to 2 Hz) and high-frequency harmonics. The high-precision power quality monitor is used to collect this data to ensure the accuracy of the parameters. The stability attenuation status is quantified by a set comprehensive index function, which combines the amplitude and frequency of the harmonic surge, the surge event density, and other grid operation indicators to obtain a stability score. This score value is used to reflect the degree of influence of the energy storage power station on the grid stability, and the stability attenuation status data is uploaded to the monitoring platform for subsequent grid dispatching and energy storage power station maintenance decision-making.

[0069] Especially importantly, step S32 includes the following steps: Step S321: Predict the damage situation of the grid waveform structure according to the distortion situation of the transmission voltage of the energy storage power station; In the embodiments of the present invention, the on-line power quality monitoring device deployed in the energy storage power station collects the high-frequency voltage waveform at the transmission bus port, the sampling frequency is set above 10 kHz, and the sampling time period is the whole point to whole point window within the continuous operation cycle. The obtained original voltage data is split into each harmonic component by Fourier transform, and the total voltage distortion rate (THDv) index is calculated. When the THDv exceeds the 5% threshold, the system further statistically analyzes the amplitude ratio of the 3rd, 5th, and 7th harmonics, and combines the fundamental frequency drift (based on 50 Hz) for multi-factor comprehensive analysis. Combining the data time series within 48 hours of continuous sampling, a sliding window correlation analysis is performed on the THDv, the change trend of each harmonic content, and the fundamental wave phase offset. If there are phenomena such as continuous increase of THDv, severe fluctuation of even harmonics, or fundamental wave phase drift of more than ±15°, it is judged that the current transmission voltage has caused damage to the grid waveform structure, and the damage degree is quantified and output by the multi-parameter weighted value W (composed of THDv, even / odd harmonic ratio, fundamental wave phase shift rate), and the value range is set to 0–1, where when W exceeds 0.65, it is judged as structural damage.

[0070] Step S322: Predict the growth trend of the line loss of the energy storage power station based on the damage situation of the grid waveform structure; In the embodiment of the present invention, based on the quantization value W of the power grid waveform structure damage obtained in step S321, combined with the three-phase output line resistance value of the energy storage power station (measured and calculated according to the in-station wiring length and the cross-sectional area of the copper wire), the power transmission loss calculation module is started. The module reads the measured current data of each line in different time periods (every 15 minutes), and calculates the active and reactive power losses respectively according to the loss coefficients of the resistive and non-resistive components under the distortion condition. In the specific formula, the I²R formula is used to calculate the active power loss under the distortion condition, and the additional loss caused by harmonics is adjusted by the harmonic loss multiplication factor recommended by IEC 61000. At the same time, the line loss rate in the same period of history is compared. If, on the premise that the structure damage coefficient W>0.65, the growth rate of the daily average line loss rate compared with the three-day moving average baseline exceeds 12%, it is marked as a line loss growth trend event, and the loss growth rate ΔL is output, with the unit of kWh / day, and a 24-hour loss growth trend graph curve is generated as the basis for further analysis.

[0071] Step S323: Detect the cumulative degree of the power grid error of the energy storage power station based on the line loss growth trend of the energy storage power station and the power grid waveform structure damage situation; In the embodiment of the present invention, on the basis of obtaining the loss growth rate ΔL calculated in step S322, the quantization value W of the power grid waveform structure damage obtained in step S321 is introduced at the same time. With these two key parameters as the input, combined with the load input and output power difference data in the operation log of the energy storage power station (using the difference between the actual charge and discharge power of the PCS and the power set by the EMS dispatch as the error source), the system conducts a retrospective detection of the error accumulation situation. Using the error integral analysis method, the real-time power deviations in each dispatch cycle are added and accumulated to form an error accumulation value Eacc (unit: kWh). Combining the change trend of ΔL and the fluctuation value of W, the growth rate of Eacc is analyzed. When ΔL is higher than 8 kWh / day and Eacc increases by more than 25% within 72 hours, the system marks it as an over-limit state of the error accumulation rate, outputs the total value of Eacc, and forms an error source influence factor matrix in combination with the position of the waveform distortion source (positioned according to the phase shift of the bus and branch monitoring points) as the input basis for the coordination evaluation.

[0072] Step S324: Identify the attenuation trend of the power grid operation coordination based on the cumulative degree of the power grid error of the energy storage power station.

[0073] In the embodiment of the present invention, the error accumulation value Eacc calculated in step S323 and the error source influence factor matrix are jointly input into the power grid coordination evaluation module. The evaluation module analyzes based on four technical indicators: regional dispatch plan, load response situation, two-way energy regulation history, and the achievement rate of energy storage charge and discharge targets. In this module, if Eacc exceeds the set threshold (such as 100 kWh), and there is a single node with the proportion of the error source influence factor exceeding 30%, it is determined as a local collapse of coordination. At the same time, the system retrieves the dispatch response delay (the time difference between the actual start of the response and the issuance time of the EMS command) and the feedback dispatch deviation rate within the last 96 hours, and uses the linear cumulative trend analysis method to extract the overall operation trend change. If the average response delay extension amplitude exceeds 20% of the original value, and the dispatch deviation rate is greater than 10%, it is further determined that the system coordination attenuation trend has an obvious manifestation, and the coordination attenuation index Cdeg is output, with the unit of percentage, which is used for the correlation analysis with the battery box working stability in the subsequent abnormal identification of energy storage batteries, forming an upstream and downstream logical closed loop.

[0074] Preferably, step S4 includes the following steps: Step S41: Evaluate the thermal runaway risk degree of the energy storage power station according to the grid stability attenuation condition of the energy storage power station; In the embodiment of the present invention, after determining the grid stability attenuation condition of the energy storage power station, it is necessary to evaluate the thermal runaway risk degree faced by the energy storage power station based on this attenuation data. In the specific operation process, indicators such as the frequency disturbance amplitude, voltage drop rate, short-time current reverse peak value, and power reverse fluctuation period during the stability attenuation process are obtained through multi-channel voltage and current synchronous sampling devices deployed at the grid connection nodes of the energy storage power station. These time-domain and frequency-domain indicators are respectively input into the hardware calculation unit established in the digital logic gate array, and the Fourier transform analysis component is used to synchronously calculate the frequency concentration degree of short-period disturbances and the power oscillation phase deviation degree. Subsequently, using the set critical parameter library, the overheat warning threshold associated with the stability attenuation is extracted (such as the current continuous rise rate exceeding 0.8 A / ms, the voltage stroboscopic amplitude exceeding 5% of the rated value, the temperature rise rate exceeding 2 °C / min, etc.), and combined with the cabin temperature rise trend output by the thermistor array in the battery cabin, the thermal runaway risk degree is comprehensively judged through Boolean logic relationships. Five risk levels are set in this process, graded from "very low" to "very high", and the current thermal runaway risk level of the energy storage power station is output as the third level (moderately high), and the value 3 is used for subsequent data transmission.

[0075] Step S42: Detect the battery state change of the energy storage power station based on the thermal runaway risk degree of the energy storage power station; In the embodiments of the present invention, after the level of the thermal runaway risk degree is determined, it is necessary to detect the state change of each battery box in the energy storage power station in real time according to this level. During the actual operation process, the system calls the three-dimensional multi-point temperature detection module (including the top plate, side wall and bottom sensors) installed inside each battery box, and jointly uses the infrared thermal imaging module to obtain the image of abnormal heat dissipation distribution outside the battery box. To ensure the integrity and timeliness of the detection data, a full-parameter acquisition and image update operation is performed every 10 seconds, and preliminary data preprocessing is carried out through the edge computing node, including outlier rejection, differential moving average denoising and block thermal gradient enhancement. Subsequently, based on the thermal runaway risk level value obtained in the previous step, the set threshold is adjusted dynamically. For example, when the risk level is 3, a battery temperature change rate exceeding 1.5°C / min will be marked as an abnormal state, and the distribution position of the abnormal points will be recorded. Further, in combination with the change trend of electrical parameters such as the change amplitude of the charge amplitude and the slope of the terminal voltage drop output by the SOC (state of charge) sensing module and the terminal voltage stability monitor, it is determined whether there are abnormal behaviors such as attenuation type, overcharge type or thermal coupling type in the battery, and the state of each battery box is divided into four types: "stable", "slightly fluctuating", "trend abnormal" and "critical abnormal", and the detection results of each battery box are recorded to form a sequence of state change results corresponding to a set of numbers.

[0076] Step S43: Identify the degree of instability of the grid frequency according to the change of the battery state in the energy storage power station; In the embodiments of the present invention, after the determination of the battery state change is completed, it is necessary to identify the degree of instability of the grid frequency where the energy storage power station is located according to its change trend. In the implementation operation, first, the "trend abnormal" and "critical abnormal" items in the battery state change result sequence are screened out, and the grid connection frequency record data during the working periods corresponding to these batteries are extracted. The frequency data is collected by a high-precision frequency measuring instrument located at the outlet port of the converter with an accuracy of 0.1Hz, and the frequency fluctuation is recorded once per second, continuously tracking the data change in the recent 30 minutes. By setting a frequency fluctuation window (such as ±0.3Hz) and applying the three-point central difference method to extract the frequency change rate, it can be judged whether there is a local frequency oscillation or frequency jump phenomenon. Then, in combination with the temperature rise change and the SOC imbalance amplitude of the corresponding battery box, according to the logical judgment conditions such as whether the measured frequency disturbance period coincides with the time window of the battery state change and whether the coincidence rate exceeds 60%, the influence intensity of this type of state change on the grid frequency is identified. Taking the number of times of frequency fluctuation exceeding the limit, the average fluctuation amplitude and the frequency change rate as the main evaluation factors, the grid frequency instability degree classification data is output after comprehensive calculation, and it is expressed in a five-level integer system. In this embodiment, the evaluation result is the 4th level (high frequency instability state).

[0077] Step S44: Detect the abnormal conditions of the energy storage power station battery based on the instability degree of the grid frequency and the change of the battery state of the energy storage power station, and upload them to the cloud platform for early warning.

[0078] In the embodiment of the present invention, after identifying the instability degree of the grid frequency, combined with the battery state change results detected previously, the comprehensive detection and early warning upload of the abnormal conditions of the energy storage power station battery are implemented. In the actual operation process, the battery state level and the frequency instability level are jointly analyzed through a preset logical combination rule. For example, when the battery state level is "critical abnormal" and the frequency instability level is 4 or above, the battery abnormal marking event is triggered. After the triggering condition is satisfied, the system immediately enables the multi-parameter verification module, and calls back the operation history of the battery box in the past 24 hours, including the continuous records of the terminal voltage, terminal current, SOC change rate, internal impedance change curve, and infrared thermal pattern. Whether it is a short-term disturbance or a continuous abnormal trend is identified through multi-index linkage. If it is the latter, the abnormality is confirmed, and the abnormal event number, location identifier (battery box number), abnormal start time, duration, abnormal type, and main associated parameters are encapsulated in the JSON structure format. Subsequently, the data is uploaded to the specified cloud platform by using the cellular communication module (such as NB-IoT or 5G module) deployed at the edge node of the control center. After the upload is completed, the cloud platform receives and triggers the backend early warning processing program, marks the abnormal battery box as a state that needs to be repaired, and displays the real-time abnormal information through the cloud management interface.

[0079] Especially importantly, step S41 includes the following steps: Step S411: Detect the increasing trend of grid frequency fluctuation according to the attenuation condition of the grid stability of the energy storage power station; In the embodiments of the present invention, during the operation of the energy storage power station, a grid frequency acquisition module disposed at the AC busbar is used to collect frequency change signals in real time. The module consists of a high-precision Phase-Locked Loop (PLL) unit, a voltage sampling circuit, and a digital signal processing unit. The sampling frequency is set to 2000 Hz. The filtering unit uses a 50 Hz band-pass filter. After extracting the main frequency fundamental wave signal, the grid frequency value per second is calculated by the zero-crossing method. The obtained frequency data f(t) is structured and stored in one-minute granularity. Using the grid stability evaluation module, data such as reactive voltage offset, power fluctuation frequency, discontinuous dispatching response failure records, and bus voltage asymmetry within the past 30 days are called to construct a grid stability attenuation factor sequence C_deg(t), and the current stability attenuation level is calculated based on this factor. If the current C_deg(t) is higher than the threshold of 0.35 (indicating a significant decline in grid stability), the grid frequency fluctuation growth trend identification process is started. The sliding time window T is selected to be 1 hour, the maximum frequency f_max and the minimum frequency f_min within this window are extracted, and the fluctuation amplitude Δf = f_max - f_min is calculated. The Δf of the most recent 12 hours is continuously collected to construct a time series Δf(t). A first-order difference calculation is performed on this sequence to analyze the change rate of Δf in the time dimension. If the Δf growth rate is positive three times in a row, and Δf exceeds 0.15 Hz and is also 1.5 times higher than the average value of the past seven days, it is determined that there is a current grid frequency fluctuation growth trend. This trend is represented by a level parameter Fv_tier, which is divided into four levels: 0 (no growth), 1 (slight growth), 2 (moderate growth), 3 (severe growth), and is used as the input for subsequent steps.

[0080] Step S412: Predict the frequent growth trend of the energy storage power station's response based on the grid frequency fluctuation growth trend; In the embodiment of the present invention, according to the frequency fluctuation level Fv_tier obtained in step S411, enter the analysis link of the dispatching response record of the energy storage power station. Call the dispatching log of the energy storage system, and count the number of start-stop regulations of the energy storage system due to responding to the grid frequency deviation in the most recent 24 hours. Let this number be N_resp. The response record includes the trigger timestamp, start power, end power, and response duration. Set the time segment at the hour level through the program to form the response number time series N_resp(t). Perform a difference calculation on N_resp(t) to obtain the change amount of the response number per hour ΔN_resp(t)=N_resp(t)−N_resp(t−1). If ΔN_resp(t) is greater than or equal to 2 in the most recent three hours, and the response number in the current hour increases by more than 50% compared with the average value in the same time period within a week, it is determined that the response frequency growth trend is obvious. Output the response frequent growth status parameter R_flag, with a value of 0 (no significant growth) or 1 (response frequently increases). In addition, draw the trend sequence of the response number as a trend curve R_trend(t), and its slope is used to measure the response growth rate, and it is jointly passed into the next step together with Fv_tier in step S411.

[0081] Step S413: Detect the continuous power conversion situation of the energy storage power station based on the grid frequency fluctuation growth trend; In the embodiment of the present invention, take Fv_tier and R_flag respectively obtained in steps S411 and S412 as the pre-judgment parameters. If Fv_tier≥2 and R_flag = 1, enter the power conversion behavior analysis process. Retrieve the output power value P(t) of the energy storage system recorded by the PCS control unit each time, obtain the power change record in the continuous time period, and extract the start power P_start, end power P_end, start time T_start, and end time T_end in each response operation. Calculate the duration of each power conversion operation ΔT=T_end−T_start, and the power change amplitude ΔP=|P_end−P_start|. After counting the response number N_resp(t) within each hour, calculate the average duration T_avg and average power amplitude P_avg within this hour respectively. If T_avg≥10 minutes, P_avg≥150kW, and the standard deviation of ΔP is less than 10%, it is determined that the current power conversion has the characteristics of continuity and strong stability. Set the power conversion trend level parameter Pw_conv_tier, and the levels are divided into four levels: 0 (no conversion), 1 (fluctuating conversion), 2 (medium-intensity stable conversion), 3 (high-intensity high-frequency continuous conversion). This parameter is used as the key input basis for the next thermal runaway risk assessment.

[0082] Step S414: Evaluate the thermal runaway risk level of the energy storage power station according to the continuous power conversion situation of the energy storage power station and the increasing trend of frequent response of the energy storage power station.

[0083] In the embodiment of the present invention, the thermal runaway risk of the energy storage battery box is judged by multi-parameter cross-judgment based on the frequent response growth flag R_flag in step S412 and the power conversion level Pw_conv_tier in step S413. The thermocouple temperature sensor installed on the surface of the battery module is called to collect the internal temperature T_in(t) and the shell temperature T_shell(t) of the battery box once every 30 seconds. By analyzing the temperature rise rate dT / dt of T_in(t), the temperature change trend is judged. When dT / dt≥0.5℃ / min for 10 consecutive minutes, and Pw_conv_tier≥2, R_flag = 1, further analyze whether the heat dissipation system is at the working limit. Call the fan speed rpm_fan in the cooling system and the refrigerant flow rate v_coolant in the heat exchange pipeline. If rpm_fan is lower than 80% of the rated speed and there is no obvious increase in the refrigerant flow rate, it is determined that the cooling response is lagging and the heat dissipation redundancy is insufficient. A comprehensive risk scoring function H_risk is constructed, and the weights include the temperature rise rate (weight 0.4), the power conversion level (weight 0.3), the response frequency (weight 0.2), and the cooling efficiency lag value (weight 0.1), and the thermal runaway risk index value is output, ranging from 0 to 1. When H_risk≥0.75, the system marks the current battery box as a high-risk state, numbers it into the "abnormal battery box risk list", and starts the remote alarm system to send a warning command to the maintenance platform through the SCADA system to achieve dynamic response processing.

[0084] The present invention also provides an abnormal battery box detection system for an energy storage power station, which is used to execute the abnormal battery box detection method for an energy storage power station as described above. The abnormal battery box detection system for an energy storage power station includes: An energy storage power station operation state evaluation module, which is used to obtain the battery box data of the energy storage power station; collect the operation environment data of the energy storage power station for the battery box data of the energy storage power station; evaluate the initial performance of the battery box of the energy storage power station based on the battery box data of the energy storage power station; evaluate the operation state data of the energy storage power station according to the battery box data of the energy storage power station and the operation environment data of the energy storage power station; A transmission power quality abnormal detection module, which is used to detect the imbalance state of the support configuration evolution of the energy storage power station according to the operation state data of the energy storage power station; detect the steady-state disintegration state of the battery electro-thermal coupling according to the imbalance state of the support configuration evolution of the energy storage power station; detect the abnormal trend of the transmission power quality of the energy storage power station based on the steady-state disintegration state of the battery electro-thermal coupling; The power grid stability attenuation determination module is used to identify the attenuation trend of the grid operation coordination according to the abnormal trend of the power quality transmitted by the energy storage power station; detect the short-term harmonic surge condition of the energy storage power station transmission based on the attenuation trend of the grid operation coordination and the abnormal trend of the power quality transmitted by the energy storage power station; determine the power grid stability attenuation condition of the energy storage power station based on the short-term harmonic surge condition of the energy storage power station transmission. The energy storage power station battery abnormality detection module is used to detect the change of the energy storage power station battery state according to the power grid stability attenuation condition of the energy storage power station; identify the degree of grid frequency instability according to the change of the energy storage power station battery state; detect the abnormality of the energy storage power station battery based on the degree of grid frequency instability and the change of the energy storage power station battery state, and upload it to the cloud platform for early warning.

[0085] The above are only the specific implementation manners of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A detection method for abnormal battery boxes in an energy storage power station, characterized in that, Including the following steps: Step S1: Obtain the data of the battery boxes in the energy storage power station; Collect the operation environment data of the energy storage power station based on the data of the battery boxes in the energy storage power station; Evaluate the initial performance of the battery boxes in the energy storage power station based on the data of the battery boxes in the energy storage power station; Evaluate the operation status data of the energy storage power station based on the data of the battery boxes in the energy storage power station and the operation environment data of the energy storage power station; Step S2: Detect the imbalance condition of the support configuration evolution of the energy storage power station according to the operation status data of the energy storage power station; Detect the breakdown condition of the battery electro-thermal coupling steady state according to the imbalance condition of the support configuration evolution of the energy storage power station; Detect the abnormal trend of the power quality transmitted by the energy storage power station based on the breakdown condition of the battery electro-thermal coupling steady state; Step S3: Identify the attenuation trend of the grid operation coordination according to the abnormal trend of the power quality transmitted by the energy storage power station; Detect the sudden increase condition of the short-term harmonics transmitted by the energy storage power station based on the attenuation trend of the grid operation coordination and the abnormal trend of the power quality transmitted by the energy storage power station; Determine the attenuation condition of the grid stability of the energy storage power station based on the sudden increase condition of the short-term harmonics transmitted by the energy storage power station; Step S4: Detect the change condition of the battery state in the energy storage power station according to the attenuation condition of the grid stability of the energy storage power station; Identify the unstable degree of the grid frequency according to the change condition of the battery state in the energy storage power station; Detect the abnormal condition of the battery in the energy storage power station based on the unstable degree of the grid frequency and the change condition of the battery state in the energy storage power station, and upload it to the cloud platform for early warning.

2. The abnormal battery box detection method for an energy storage power station according to claim 1, wherein Step S1 includes the following steps: Step S11: Set the temperature measurement range of the temperature sensor to 0 - 200 °C, the minimum temperature change to 0.05 °C, and the temperature sampling frequency to 10 Hz; Step S12: Set the humidity measurement range of the humidity sensor to 0% to 100% RH, the minimum humidity change to 0.1% RH, and the humidity sampling frequency to 5 Hz; Step S13: Obtain the data of the battery boxes in the energy storage power station; Step S14: Collect the operation environment data of the energy storage power station by using the humidity sensor and the temperature sensor based on the data of the battery boxes in the energy storage power station; Step S15: Collect the operation cumulative duration data of the energy storage power station based on the data of the battery boxes in the energy storage power station; Step S16: Evaluate the initial performance of the battery boxes in the energy storage power station based on the data of the battery boxes in the energy storage power station; Step S17: Evaluate the operation status data of the energy storage power station based on the initial performance of the battery boxes in the energy storage power station according to the operation cumulative duration and the operation environment data of the energy storage power station.

3. The abnormal battery box detection method for an energy storage power station according to claim 2, characterized in that Step S16 includes the following steps: Step S161: Extract the internal arrangement structure data of the battery box based on the data of the battery boxes in the energy storage power station; Step S162: Identify the internal conductive connection condition of the battery box based on the internal arrangement structure data of the battery box; Step S163: Evaluate the wiring regularity of the busbar in the battery box according to the internal conductive connection condition of the battery box and the internal arrangement structure data of the battery box; Step S164: Evaluate the internal heat dissipation capacity data of the battery box based on the wiring regularity of the busbar in the battery box and the internal arrangement structure data of the battery box; Step S165: Calculate the initial voltage deviation condition of the battery in the energy storage power station according to the data of the battery boxes in the energy storage power station; Step S166: Determine the initial operation stability of the battery boxes in the energy storage power station based on the internal heat dissipation capacity data of the battery box and the initial voltage deviation condition of the battery in the energy storage power station; Step S167: Evaluate the initial performance of the energy storage power station battery boxes based on the initial operation stability of the energy storage battery boxes and the initial operation stability of the energy storage power station battery boxes.

4. The abnormal battery box detection method for an energy storage power station according to claim 2, wherein Step S17 includes the following steps: Step S171: Collect the abnormal fluctuation of the operating environment temperature and humidity according to the operating environment data of the energy storage power station; Step S172: Determine the sudden change of the day-night temperature and humidity in the operating environment based on the abnormal fluctuation of the operating environment temperature and humidity; Step S173: Identify the oxidation trend of the energy storage power station structure for the initial performance of the energy storage power station battery boxes when the sudden change of the day-night temperature and humidity in the operating environment exceeds 30%; Step S174: Test the pressure-bearing operation state of the energy storage power station when the cumulative operation duration of the energy storage power station exceeds 48h and the oxidation trend of the energy storage power station structure exceeds 50%; Step S175: Estimate the overload condition of the energy storage power station operation according to the load-bearing operation state of the energy storage power station; Step S176: Evaluate the operation state data of the energy storage power station for the initial performance of the energy storage power station battery boxes based on the overload condition of the energy storage power station operation and the oxidation trend of the energy storage power station structure.

5. The abnormal battery box detection method for an energy storage power station according to claim 1, characterized in that, The detection of the unbalanced evolution of the energy storage support configuration state in Step S2 includes: Identify the oxidation degree of the connection structure of the energy storage power station according to the operation state data of the energy storage power station; Determine the loosening trend of the connection structure of the energy storage power station based on the oxidation degree of the connection structure of the energy storage power station; Estimate the micro-vibration condition at the connection of the energy storage power station based on the loosening trend of the connection structure of the energy storage power station; Measure the growth degree of the mechanical stress of the energy storage power station structure based on the micro-vibration condition at the connection of the energy storage power station; Predict the micro-deformation condition of the energy storage power station structure according to the growth degree of the mechanical stress of the energy storage power station structure and the micro-vibration condition at the connection of the energy storage power station; Detect the dynamic fatigue condition of the energy storage power station structure based on the micro-deformation condition of the energy storage power station structure and the growth degree of the mechanical stress of the energy storage power station structure; Detect the unbalanced evolution condition of the energy storage support configuration state based on the dynamic fatigue condition of the energy storage power station structure and the micro-deformation condition of the energy storage power station structure.

6. The abnormal battery box detection method for an energy storage power station according to claim 1, wherein The detection of the steady-state disintegration condition of the battery electro-thermal coupling in Step S2 includes: Identify the abnormal extrusion inside the battery according to the unbalanced evolution condition of the energy storage support configuration state; Measure the unbalanced degree of the lateral force on the battery cell according to the abnormal extrusion inside the battery; Determine the horizontal displacement condition of the battery cell based on the unbalanced degree of the lateral force on the battery cell and the abnormal extrusion inside the battery; Measure the unbalanced condition of the insulation distance between the battery cells according to the horizontal displacement condition of the battery cell; Determine the degradation of the electrical connection performance of the energy storage power station based on the unbalanced condition of the insulation distance between the battery cells; Measure the distortion condition of the heat dissipation path of the battery cell according to the unbalanced condition of the insulation distance between the battery cells; Detect the steady-state disintegration condition of the battery electro-thermal coupling according to the distortion condition of the heat dissipation path of the battery cell and the degradation of the electrical connection performance of the energy storage power station.

7. The abnormal battery box detection method for an energy storage power station according to claim 1, characterized in that The detection of the abnormal trend of the power quality transmitted by the energy storage power station in Step S2 includes: Detect the continuous increase of the internal resistance of the battery current transmitted based on the steady-state disintegration condition of the battery electro-thermal coupling; Determine the unbalanced condition of the current shunt of the battery current transmitted according to the continuous increase of the internal resistance of the battery current transmitted; Predict the abnormal overcharge condition of the energy storage power station battery according to the unbalanced condition of the current shunt of the battery current transmitted; Determine the trend of the loss of battery active materials based on the abnormal overcharge condition of the energy storage power station battery. Testing the degree of damage to the battery electrode interface synergy mechanism based on the trend of battery active material disintegration; Estimating the limitation of the internal ion diffusion channels in the battery based on the degree of damage to the battery electrode interface synergy mechanism and the trend of battery active material disintegration; Detecting the abnormal trend of the transmitted power quality of the energy storage power station based on the limitation of the internal ion diffusion channels in the battery.

8. The abnormal battery box detection method for an energy storage power station according to claim 1, wherein Step S3 includes the following steps: Step S31: Detecting the distortion of the transmitted voltage of the energy storage power station according to the abnormal trend of the transmitted power quality of the energy storage power station; Step S32: Identifying the decay trend of the grid operation coordination based on the distortion of the transmitted voltage of the energy storage power station; Step S33: Detecting the sudden increase in short-term harmonics in the transmission of the energy storage power station based on the decay trend of the grid operation coordination and the distortion of the transmitted voltage of the energy storage power station; Step S34: Determining the decay status of the grid stability of the energy storage power station based on the sudden increase in short-term harmonics in the transmission of the energy storage power station.

9. The abnormal battery box detection method for an energy storage power station according to claim 1, wherein Step S4 includes the following steps: Step S41: Evaluating the degree of thermal runaway risk of the energy storage power station according to the decay status of the grid stability of the energy storage power station; Step S42: Detecting the change in the battery state of the energy storage power station based on the degree of thermal runaway risk of the energy storage power station; Step S43: Identifying the degree of instability of the grid frequency according to the change in the battery state of the energy storage power station; Step S44: Detecting the abnormal conditions of the energy storage power station battery based on the degree of instability of the grid frequency and the change in the battery state of the energy storage power station, and uploading them to the cloud platform for early warning.

10. An abnormal battery box detection system for an energy storage power station, characterized in that, An energy storage power station abnormal battery box detection system for implementing the energy storage power station abnormal battery box detection method as claimed in claim 1, the energy storage power station abnormal battery box detection system includes: An energy storage power station operation state evaluation module, configured to obtain energy storage power station battery box data; collect energy storage power station operation environment data from the energy storage power station battery box data; evaluate the initial performance of the energy storage power station battery box based on the energy storage power station battery box data; evaluate the energy storage power station operation state data based on the energy storage power station battery box data and the energy storage power station operation environment data; A transmitted power quality abnormal detection module, configured to detect the imbalance in the evolution of the support configuration state of the energy storage power station according to the energy storage power station operation state data; detect the disintegration of the battery electro-thermal coupling steady state according to the imbalance in the evolution of the support configuration state of the energy storage power station; detect the abnormal trend of the transmitted power quality of the energy storage power station based on the disintegration of the battery electro-thermal coupling steady state; A grid stability decay determination module, configured to identify the decay trend of the grid operation coordination according to the abnormal trend of the transmitted power quality of the energy storage power station; detect the sudden increase in short-term harmonics in the transmission of the energy storage power station based on the decay trend of the grid operation coordination and the abnormal trend of the transmitted power quality of the energy storage power station; determine the decay status of the grid stability of the energy storage power station based on the sudden increase in short-term harmonics in the transmission of the energy storage power station; An energy storage power station battery abnormal detection module, configured to detect the change in the battery state of the energy storage power station according to the decay status of the grid stability of the energy storage power station; identify the degree of instability of the grid frequency according to the change in the battery state of the energy storage power station; detect the abnormal conditions of the energy storage power station battery based on the degree of instability of the grid frequency and the change in the battery state of the energy storage power station, and upload them to the cloud platform for early warning.

Images