Energy storage power station battery heat flow digital twinborn simulation and cooling capacity adaptive control method

Abstract

The invention discloses an energy storage power station battery heat flow digital twinborn simulation and cooling capacity adaptive control method, and relates to the technical field of battery heat flow data processing. The energy storage power station battery heat flow digital twinborn simulation and cooling capacity self-adaptive control method comprises the steps that S1, battery characteristic data and cooling characteristic data are collected and preprocessed, and a standardized heat state data set is constructed; s2, evaluating the overall heat flux density of the battery, and dynamically adjusting the rotating speed of a cooling pump and refrigerant flow distribution; s3, analyzing simulation precision, and correcting cooling boundary conditions in real time; s4, the cooling demand intensity is analyzed, and a graded adjusting instruction of the refrigerant flow and the pump speed is generated based on the demand analysis result; and S5, a cooling capacity distribution instruction is generated and verified, issuing execution is carried out, and preventive adjustment is carried out. The problems that most of current heat management systems lack heat flow multi-dimensional space perception and model coupling capacity, three-dimensional heat distribution cannot be mapped in real time, and fine regulation and control and early recognition of abnormal heat distribution are limited are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery heat flow data processing, in particular to a method for digital twin simulation of energy storage power station battery heat flow and adaptive control of cold energy. BACKGROUND

[0002] In the charging and discharging process of energy storage batteries, a large amount of electrical energy is converted into heat and rapidly accumulates inside the battery cluster. Therefore, thermal management technology is widely used in battery operation state perception, cooling loop regulation and system energy consumption optimization. At the same time, with the continuous improvement of the capacity and power level of battery clusters, digital twin technology has been gradually introduced into the field of thermal management. Through synchronous modeling and interactive simulation of battery geometric structure, operation signals and sensor data, a virtual model highly coupled with the actual battery pack is constructed to provide predictive support for cold energy distribution and operation strategy.

[0003] For example, the invention with the announcement number CN112818602B provides a battery digital twin control method and device based on big data analysis. The method includes: clustering processing according to vehicle information of multiple vehicles and battery information of batteries in each vehicle to obtain at least one vehicle classification and at least one battery classification. According to at least one vehicle classification, a target vehicle is selected from the multiple vehicles. According to at least one battery classification, a target battery is selected from the target vehicle. The battery parameters of the target battery corresponding to the target vehicle are obtained through a third-party device, or when the target vehicle is in a special working condition, the battery parameters of the target battery corresponding to the target vehicle are obtained. According to the battery parameters of the target battery corresponding to the target vehicle, the parameters of the refined multi-physical field model corresponding to the target battery are updated. By only establishing a refined multi-physical field model for a small number of batteries in a small number of vehicles, the problem of large consumption of cloud computing resources is solved.

[0004] For example, the invention with the announcement number CN114004168B discloses a fuel cell comprehensive management system and method based on digital twin. The system includes an entity battery pack: for generating dynamic performance parameters in operation; a digital twin model: for real-time simulation of dynamic performance parameters of the entity fuel cell pack; a data acquisition platform: for real-time acquisition of dynamic performance parameters of the entity fuel cell pack in operation, preprocessing and feature extraction of data, and transmission of extracted feature data to the digital twin model to drive the operation of the model; a fuel cell and lithium battery terminal management module: a human-computer interaction interface, for remotely and real-time visually presenting the operating state of the digital twin model, and controlling the adjustment parameters of the entity fuel cell pack and the digital twin model. The present application can remotely and real-time visually monitor the complex fuel cell system; according to the operation results of the digital twin model, the relevant physical quantities of the physical device are adjusted in time and accurately, so that the performance reaches the best state.

[0005] However, the existing thermal management means mostly rely on point temperature monitoring and single flow regulation, lack real-time perception and coupled modeling of three-dimensional heat flow distribution inside the battery cluster, and cannot identify local hot spots and temperature difference gradient in spatial scale. In the cooling control process, fixed threshold or single flow increase and decrease strategy is often used, ignoring the dynamic response characteristics of the refrigerant to thermal disturbance under different working conditions, which is easy to cause overcooling or insufficient cooling, and further affects the stability and energy efficiency of thermal management. At the same time, digital twinning has been applied in manufacturing and structural simulation, but in the field of thermal control of energy storage power station, there is still a lack of deep integration of battery geometry, operation signals and sensing data, which leads to deviation between the prediction model and the measured thermal field, and it is difficult to realize adaptive allocation of cooling capacity.

[0006] In view of the above problems, it is urgent to need a battery heat flow digital twinning simulation and cooling capacity adaptive control method for energy storage power station. SUMMARY

[0007] Technical problems solved In view of the deficiencies of the prior art, the present application provides a battery heat flow digital twinning simulation and cooling capacity adaptive control method for energy storage power station, which solves the problem that most of the current thermal management systems lack heat flow multi-dimensional spatial perception and model coupling ability, three-dimensional thermal distribution cannot be mapped in real time, which limits the fine regulation and early identification of thermal distribution abnormalities.

[0008] Technical scheme

[0009] To achieve the above purpose, the present application realizes the following technical scheme: a battery heat flow digital twinning simulation and cooling capacity adaptive control method for energy storage power station, comprising S1, collecting battery characteristic data and cooling characteristic data during battery operation, and preprocessing the collected battery characteristic data and cooling characteristic data to construct a standardized thermal state data set; S2, based on the standardized thermal state data set, evaluating the heat flow density of the battery as a whole, and dynamically adjusting the cooling pump speed and refrigerant flow distribution based on the heat flow evaluation result; S3, based on the standardized thermal state data set, analyzing the precision from the difference between the infrared thermal imaging measured temperature and the predicted temperature, and correcting the cooling boundary conditions in real time based on the precision analysis result; S4, taking the heat flow evaluation result and the precision analysis result as input, analyzing the cooling demand intensity, and generating graded regulation instructions of refrigerant flow and pump speed based on the demand analysis result; S5, generating and checking the cooling capacity allocation instructions in each cooling control period, issuing and executing the instructions, and combining real-time deviation feedback and short-term prediction for preventive adjustment.

[0010] Further, the specific steps of collecting battery characteristic data and cooling characteristic data during battery operation are as follows: collecting battery characteristic data during battery operation, the battery characteristic data including: single battery volume, battery heating power, battery surface maximum temperature, battery surface minimum temperature, infrared thermal imaging measured temperature, and simultaneously calculating and recording the temperature fluctuation standard deviation of the battery; collecting cooling characteristic data, the cooling characteristic data including: refrigerant flow, refrigerant inlet temperature and refrigerant outlet temperature, and simultaneously calculating and recording the average inlet and outlet temperature difference of the refrigerant.

[0011] Further, the specific steps of preprocessing the collected battery characteristic data and cooling characteristic data to construct a standardized thermal state data set are as follows: for battery characteristic data, the single battery volume is registered into the database as a geometric constant, the battery heating power is cross-verified and sliding average filtering is performed; the battery surface maximum temperature and minimum temperature are based on the edge value of the infrared thermal imaging measured temperature to extract the edge value and construct the battery temperature field; the infrared thermal imaging measured temperature is processed by Gaussian denoising, and the temperature fluctuation standard deviation of the battery is calculated simultaneously according to the sliding window mechanism; for cooling characteristic data, the refrigerant flow is subjected to time series smoothing and variation rate analysis to remove pulse interference, the instantaneous temperature difference is calculated after aligning the refrigerant inlet temperature and outlet temperature, and the average inlet and outlet temperature difference of the refrigerant is calculated; the normalized battery characteristic data and cooling characteristic data after standardization are normalized to construct a standardized thermal state data set.

[0012] Further, the specific steps of heat flow evaluation of the battery overall heat flow density based on the standardized thermal state data set are as follows: dividing the single battery volume by the battery heating power to obtain the volume heating intensity value; subtracting the battery surface minimum temperature from the battery surface maximum temperature and multiplying by the corresponding temperature weighting factor to obtain the surface temperature difference correction value; adding one to the refrigerant flow and dividing by the refrigerant flow and multiplying by the corresponding cooling weighting factor to obtain the cooling flow weighting value; adding the volume heating intensity value, the surface temperature difference correction value and the cooling flow weighting value to obtain the three-dimensional heat flow evaluation value.

[0013] Further, the dynamic adjustment of the cooling pump speed and the refrigerant flow distribution based on the heat flow evaluation results comprises the following specific steps: real-time comparison of the three-dimensional heat flow evaluation value and the heat flow threshold value; when the three-dimensional heat flow evaluation value is less than the heat flow threshold value, the cooling pump speed is kept unchanged, the refrigerant flow is maintained at the default value, and only the normal heat flow distribution is output in the battery twin model; when the heat flow evaluation value is equal to the heat flow threshold value, the cooling pump is adjusted to 25% to 40% of the rated value, the refrigerant flow rate is increased, the potential hot spot area is highlighted in the battery twin model in real time, and a cold distribution plan is generated in advance; when the three-dimensional heat flow evaluation value exceeds the heat flow threshold value, the cooling pump is adjusted to the highest speed, the refrigerant flow is increased to the highest, and a high-load operation instruction is immediately sent to the cold adjusting device, and the three-dimensional heat distribution in the battery twin model is updated in real time and the high-risk area is marked to trigger the operation and maintenance alarm.

[0014] Further, the precision analysis of the simulation accuracy based on the difference between the infrared thermal imaging measured temperature and the predicted temperature comprises the following specific steps: inputting the access data as training data, the access data including: the three-dimensional geometry of the battery based on the CAD refinement, the volume of the single battery, the refrigerant flow, the refrigerant inlet temperature and outlet temperature, and the battery temperature field extracted by the infrared thermal imaging; on the modeling side, the access data is solved by transient conjugate heat transfer on CFD to obtain high-fidelity temperature and heat flow distribution, and then a fast prediction model is constructed by principal component dimension reduction and thermal RC network equivalence method, and online calibration is performed by extended Kalman filter; the fast prediction model is associated with Simulink on the control side, and short-time domain rolling optimization is adopted to inversely solve the cooling capacity demand within the safety band under the constraint condition, and the predicted temperature and the predicted cooling flow are output in real time on the output side; the absolute value of the difference between the measured temperature and the predicted temperature of the battery is divided by the sum of the temperature fluctuation standard deviation and one, and then one is added to take the natural logarithm to obtain the temperature difference deviation correction value; the value of the predicted cooling flow plus one is divided by the value of the refrigerant flow minus the predicted cooling flow, and then one is added to obtain the cooling deviation correction value; the temperature difference deviation correction value and the cooling deviation correction value are multiplied to obtain the model deviation correction value.

[0015] Further, the cooling boundary condition is corrected in real time based on the accuracy analysis result, and the specific steps are as follows: when the calculation result of the model deviation correction value continuously increases for three times, it is determined that the deviation between the model prediction and the actual measurement is enlarged, the infrared thermal imaging measured temperature and the flow measured data are fed back to the battery twin model, the heat conduction coefficient and the boundary condition are dynamically corrected, and the cooling regulation device is triggered to enter the early warning; when the calculation result of the model deviation correction value fluctuates for three times and is less than the tolerance threshold, the battery twin model access data is continuously updated, the cooling pump speed is adjusted to 25% to 40% of the rated value, the cooling loop flow is kept stable, the deviation area is marked in the battery twin model, and monitoring is prompted; when the calculation result of the model deviation correction value continuously decreases for three times, the battery twin model parameters remain unchanged, the cooling pump speed is reduced, and the cooling loop enters the energy saving mode.

[0016] Further, the cooling demand intensity is analyzed based on the heat flow evaluation result and the accuracy analysis result, and the specific steps are as follows: the three-dimensional heat flow evaluation value is multiplied by the value obtained by adding 1 to the model deviation correction value, and then the square root is taken to obtain the heat flow deviation coupling value; the average inlet and outlet temperature difference of the refrigerant is added by 1, and then divided by the value obtained by subtracting the refrigerant outlet temperature from the refrigerant inlet temperature to obtain the cooling temperature difference ratio; the heat flow deviation coupling value and the cooling temperature difference ratio are added to obtain the cooling adaptive distribution value.

[0017] Further, the refrigerant flow and pump speed are adjusted based on the demand analysis result to generate a hierarchical regulation instruction, and the specific steps are as follows: the cooling adaptive distribution value is compared with the cooling distribution threshold in real time, the cooling distribution threshold includes a first cooling threshold and a second cooling threshold, the first cooling threshold is higher than the second cooling threshold: when the cooling adaptive distribution value is less than or equal to the second cooling threshold, the cooling pump is kept at the lowest speed, the cooling regulation device is controlled to output unchanged, the thermal imaging image enhancement is turned off, only the original value of the battery characteristic data is recorded, the simulation incremental calculation process is turned off, the three-dimensional heat distribution map is not refreshed, and only the central node temperature sequence is appended; when the cooling adaptive distribution value is greater than the second cooling threshold and less than or equal to the first cooling threshold, the cooling pump speed is increased, the image analysis algorithm is started to reconstruct the boundary of the hot spot area, the simple thermal map panel is generated and synchronized to the control interface, and the current cooling capacity distribution range information is updated; when the cooling adaptive distribution value is greater than the first cooling threshold, the cooling pump is immediately switched to the highest speed, the three-dimensional heat distribution map dynamic rendering and the hot spot migration trajectory tracking are continuously started, the full-cycle charging and discharging task data is loaded and a three-order time step prediction sequence is generated; the simulation engine starts the complete reconstruction path and synchronizes the real-time battery characteristic data and cooling characteristic data, and the current battery characteristic data and cooling characteristic data are recorded as high-frequency data snapshots.

[0018] Furthermore, the specific steps for generating and verifying the cooling capacity allocation command within each cooling control cycle, issuing and executing it, and combining real-time deviation feedback and short-term prediction for preventative adjustment are as follows: Within each cooling control cycle, a cooling capacity allocation command is generated based on the three-dimensional heat flow evaluation value and the model deviation correction value. The command covers the cooling pump speed and refrigerant flow rate. A shadow simulation is performed in the battery twin model. When the predicted temperature is equal to or greater than the safety threshold, the cooling capacity allocation command is rolled back and re-verified until the predicted temperature is less than the safety threshold before being issued to the execution component. During the execution phase of the cooling capacity allocation command, the average inlet and outlet temperature difference of the refrigerant is continuously collected and compared with the predicted temperature. At the same time, the deviation information between the average inlet and outlet temperature difference of the refrigerant and the twin predicted temperature is fed back to the battery twin model. Before the end of the cooling control cycle, a short-term prediction is performed based on the adaptive cooling capacity allocation value. When a local hot spot trend appears, the cooling pump speed is increased in advance, and the execution and readback results are recorded as baseline data.

[0019] Beneficial effects

[0020] The present invention has the following beneficial effects:

[0021] (1) The battery thermal flow digital twin simulation and cooling capacity adaptive control method of the energy storage power station achieves accurate characterization of the internal thermal distribution state of the battery by introducing a three-dimensional thermal flow evaluation mechanism based on battery geometric modeling and infrared measured data fusion.

[0022] (2) The battery thermal flow digital twin simulation and cooling capacity adaptive control method of the energy storage power station effectively eliminates the error accumulation between prediction and measurement by establishing model deviation correction value and introducing feedback closed loop, and enhances the stability of control response.

[0023] (3) The battery heat flow digital twin simulation and cooling capacity adaptive control method of the energy storage power station realizes the refined allocation and energy-saving management of cooling resources by dynamically calculating the cooling capacity adaptive allocation value and triggering the control strategy in stages.

[0024] (4) The battery thermal flow digital twin simulation and cooling capacity adaptive control method of the energy storage power station ensures that the cooling capacity command has a temperature safety zone prediction guarantee before execution by embedding shadow simulation and parameter verification mechanism in each control cycle.

[0025] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0026] Figure 1 This is a flowchart of the digital twin simulation of battery thermal flux and adaptive control of cooling capacity in the energy storage power station according to the present invention.

[0027] Figure 2 This is a line graph showing the adaptive allocation of cooling capacity involved in this invention.

[0028] Figure 3 Signal schematic involved in the present application;

[0029] Figure 4 Signal generation flowchart involved in the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0031] Please refer to Figures 1-4 The technical solution provided by the embodiments of the present application is a method for digital twin simulation of thermal flow of battery of energy storage power station and adaptive control of cold quantity, which comprises the following steps: S1, collecting battery characteristic data and cooling characteristic data in the battery operation process, and preprocessing the collected battery characteristic data and cooling characteristic data to construct a standardized thermal state data set; S2, based on the standardized thermal state data set, performing thermal flow evaluation on the overall thermal flow density of the battery, and dynamically adjusting the cooling pump speed and the refrigerant flow distribution based on the thermal flow evaluation result; S3, based on the standardized thermal state data set, performing precision analysis on the simulation precision from the difference between the infrared thermal imaging measured temperature and the predicted temperature, and real-time correcting the cooling boundary condition based on the precision analysis result; S4, taking the thermal flow evaluation result and the precision analysis result as inputs, performing demand analysis on the cooling demand intensity, and generating grading regulation instructions for refrigerant flow and pump speed based on the demand analysis result; S5, generating and checking the cold quantity distribution instructions in each cooling control period, issuing and executing the instructions, and combining real-time deviation feedback and short-term prediction for preventive regulation.

[0032] Specifically, the specific steps of collecting the battery characteristic data and the cooling characteristic data in the battery operation process are as follows: collecting the battery characteristic data in the battery operation process, the battery characteristic data including: battery volume, used to establish thermal flow density normalization benchmark; battery heating power, checked by multiplying bus voltage and current and combining controller power consumption, reflecting the intensity of internal heat source of the battery per unit time; battery surface maximum temperature and battery surface minimum temperature, respectively extracting regional extreme values from the infrared thermal imaging matrix to construct thermal distribution gradient characteristics; infrared thermal imaging measured temperature, obtained by using a high-frequency frame rate area array infrared sensor, as a direct input for dynamic thermal field reconstruction and simulation feedback; at the same time, the temperature fluctuation standard deviation of the battery is calculated and recorded, the temperature dispersion degree is counted by using a sliding time window, and the thermal state stability in the current period is reflected.

[0033] Collecting cooling characteristic data, including: refrigerant flow, continuously monitoring the main circuit and branch cooling medium by flow sensor, providing cold quantity adjustment strength basis; refrigerant inlet temperature and refrigerant outlet temperature, synchronously collecting by temperature sensing unit at inlet and outlet positions and aligning time stamp; at the same time, calculating and recording the average inlet and outlet temperature difference of refrigerant as a key index for measuring current heat exchange intensity and cooling efficiency, for driving the cold quantity adaptive distribution logic.

[0034] In the embodiment, the basic data system of supporting heat flow evaluation and cold quantity adjustment is constructed, the battery characteristic data and cooling characteristic data generated during the battery operation are collected and statistically processed in high precision and multi-dimension, and complete and dynamic updated data support is provided for subsequent three-dimensional thermal field modeling, heat intensity estimation, cooling capacity evaluation and adaptive control strategy. This step not only realizes the synchronous perception of the internal heat generation behavior of the battery and the external cooling response state, but also enhances the quantitative expression ability of the thermal stability and heat exchange efficiency through the calculation of key indexes such as temperature fluctuation standard deviation and average inlet and outlet temperature difference, which is a prerequisite link for realizing precise twin modeling and cold quantity closed-loop control.

[0035] Specifically, the collected battery characteristic data and cooling characteristic data are preprocessed, and a standardized thermal state data set is constructed. The specific steps are as follows: for the battery characteristic data, the volume of the single battery is registered into the database as a geometric constant, which is used for subsequent heat flux density normalization calculation and parameter binding of three-dimensional geometric modeling; the battery heating power is obtained through cross verification of direct current bus voltage and current and controller power consumption, and combined with sliding average filtering to remove transient peak noise, to obtain a smooth heat source intensity curve; the highest temperature and the lowest temperature of the battery surface are extracted based on the edge value of the infrared thermal imaging data, and further interpolated and fitted with the matrix temperature distribution to construct a dynamically updated battery surface temperature field; the infrared thermal imaging measured temperature is subjected to Gaussian denoising before entering the data platform, reducing the influence of sensor noise and environmental interference, and at the same time, the temperature fluctuation standard deviation of the battery is calculated by using the sliding time window mechanism, as a key index representing the current running stability.

[0036] For the cooling characteristic data, the refrigerant flow is processed by time series smoothing and variation rate analysis to eliminate the instability caused by mechanical pulse and transient disturbance, and a continuous flow sequence is generated; after aligning the time stamp, the instantaneous inlet and outlet temperature difference is calculated point by point, and the average inlet and outlet temperature difference of the refrigerant is obtained by statistical processing in multiple cycles, to reflect the continuous heat exchange capacity and overall performance level of the cooling link.

[0037] Finally, the battery characteristic data and the cooling characteristic data that have been standardized are unified, normalized, aligned at the same time resolution, and packaged to form a standardized thermal state dataset, providing a complete, reliable, and sustainable data basis for subsequent three-dimensional heat flow evaluation, deviation correction, and adaptive cooling allocation.

[0038] In this embodiment, the battery characteristic data and the cooling characteristic data are transformed from the original collection state into a unified standardized thermal state dataset through geometric constant registration, power curve smoothing, temperature field reconstruction, fluctuation feature extraction, flow time series correction, and temperature difference statistical processing means. This not only eliminates the uncertainty caused by sampling noise and environmental disturbance, but also ensures the alignment consistency of various data in the time dimension and physical scale. The dataset thus established can provide accurate, stable, and directly callable input basis for three-dimensional heat flow evaluation, model deviation correction, and adaptive cooling allocation, thereby supporting high-precision simulation and dynamic regulation of the digital twin model.

[0039] Specifically, based on the standardized thermal state dataset, the steps for heat flow evaluation of the overall battery are as follows: divide the volume of the single battery by the battery heat generation power to obtain a volume heat generation intensity value; subtract the battery surface minimum temperature from the battery surface maximum temperature, then multiply the result by the corresponding temperature weighting factor to obtain a surface temperature difference correction value; add one to the refrigerant flow rate, then divide the result by the refrigerant flow rate and multiply it by the corresponding cooling weighting factor to obtain a cooling flow weighting value; add the volume heat generation intensity value, the surface temperature difference correction value, and the cooling flow weighting value to obtain a three-dimensional heat flow evaluation value.

[0040] The calculation formula of the three-dimensional heat flow evaluation value is as follows:

[0041]

[0042] In the formula: represents the volume of the single battery, used for normalizing the heat flow density, and derived from the battery geometric modeling; represents the battery heat generation power, used to represent the instantaneous heat generated by charging and discharging, and derived from the DC bus voltage and current and controller power consumption calculation; represents the battery surface maximum temperature, used to depict the surface hot spots and gradients, and derived from the infrared thermal imager; represents the battery surface minimum temperature, used to depict the surface hot spots and gradients, and derived from the infrared thermal imager, represents the refrigerant flow rate, used to reflect the bottom convection intensity, and derived from the cooling circuit flow sensor; represents a temperature weighting factor, with a value range of 0.5 to 2, used to dynamically adjust the weight of the battery surface temperature difference in the three-dimensional heat flow evaluation, derived from the deviation between the temperature difference gradient characteristics of the current operating section of the battery and the historical steady-state temperature distribution, in the specific calculation, first, the highest temperature and the lowest temperature difference value of the infrared thermal imaging matrix in the current sliding time window are extracted, and the change rate and the duration are calculated to depict the dynamic evolution trend of the temperature difference; then the temperature difference benchmark sequence of the battery in the historical steady-state operation is called, including the long-term average temperature difference, the median fluctuation amplitude and the high temperature region persistence index, forming a temperature difference template; then the current temperature difference characteristics are compared with the benchmark template to obtain the amplitude difference rate, the duration offset value and the abnormal temperature rise section matching degree, and combined with the temperature distribution stability rating under different load conditions, the weighted aggregation is performed, and finally the temperature weighting factor is generated, when the battery surface temperature difference rapidly expands and deviates from the steady-state template, the temperature weighting factor increases, thereby enhancing the weight of the temperature difference term in the heat flow evaluation; when the temperature difference changes slowly and is highly consistent with the historical mode, the temperature weighting factor decreases to avoid over amplification of the smooth temperature distribution; represents a cooling weighting factor, with a value range of 1 to 3, used to adjust the contribution of the refrigerant flow in the three-dimensional heat flow evaluation, derived from the comparison and analysis between the current flow fluctuation and the heat exchange capacity stability of the cooling circuit. In the specific calculation, first, the instantaneous fluctuation sequence of the refrigerant flow in the current sliding time window is extracted, and the average value, the change slope and the fluctuation frequency are calculated to depict the flow stability; then the steady-state flow characteristics of the historical cooling circuit are extracted, including the rated flow value, the typical flow offset rate and the cooling capacity retention rate, to establish a flow benchmark model; then the current flow characteristics are aligned with the benchmark model, including the mean difference rate, the fluctuation frequency matching degree and the heat exchange efficiency retention rate, and combined with the stability rating of the cooling unit under different working conditions, the multi-dimensional weighted aggregation is performed to obtain the cooling weighting factor, when the refrigerant flow fluctuates violently and is significantly different from the benchmark, the cooling weighting factor increases, thereby enhancing the inhibitory regulation of the cooling flow term in the heat flow evaluation; on the contrary, when the flow is stable and the heat exchange efficiency is consistent with the historical mode, the cooling weighting factor decreases to maintain the balanced contribution of the cooling intensity term in the overall evaluation.

[0043] In this embodiment, the heat generation intensity, surface temperature difference characteristics and cooling flow state during battery operation are comprehensively quantified to generate a three-dimensional heat flow evaluation value H, thereby providing a unified quantitative index for battery heat flow distribution modeling and cooling capacity regulation. By normalizing the volume of single battery and the instantaneous heat generation power as the unit volume heat flux density, and combining the surface temperature difference term modified by the temperature weighting factor and the refrigerant flow correction term adjusted by the cooling weighting factor, the formula can reflect the coupling effect of battery internal heat source intensity, surface temperature gradient and external cooling capacity, form a dynamic evaluation benchmark for the overall thermal state of the battery, and provide core calculation support for subsequent twin simulation correction and cooling capacity adaptive allocation.

[0044] Specifically, and based on the heat flow evaluation results, the cooling pump speed and refrigerant flow distribution are dynamically adjusted according to the following specific steps: real-time comparison of the three-dimensional heat flow evaluation value and the heat flow threshold value, and execution of graded control measures according to different intervals:

[0045] When the three-dimensional heat flow evaluation value is less than the heat flow threshold value, the cooling pump is maintained in the current low-speed running state, and the refrigerant remains at the default flow rate, ensuring that the cooling circuit is in a basic maintenance mode; at the same time, only the conventional heat flow distribution image is output in the battery twin model, the basic evolution of the temperature field is recorded, and the data is archived as a control data, without triggering additional adjustment commands.

[0046] When the three-dimensional heat flow evaluation value is equal to the heat flow threshold value, the cooling pump running speed is automatically adjusted to 25% to 40% of the rated speed, and the refrigerant flow rate is moderately increased to enhance the cooling coverage of potential hot spots; the battery twin model starts the hot spot recognition function, and the surface and local temperature rise trend is highlighted in real time to form a visual warning area; at the same time, a cooling capacity distribution plan is generated in the background, including possible subsequent flow grading, pump speed adjustment and cooling capacity compensation strategies, so as to quickly switch when entering the next stage.

[0047] When the three-dimensional heat flow evaluation value exceeds the heat flow threshold value, the cooling pump is immediately switched to the highest speed operation, the refrigerant flow is quickly increased to the upper limit allowed by the equipment, and a high-load operation instruction is sent to the cooling capacity regulation device to drive the cooling unit into full-power working condition; in the battery twin model, the three-dimensional heat distribution map is updated and rendered in real time, and the hot spot migration track and high-risk area are automatically marked; the operation and maintenance alarm mechanism is triggered synchronously, the high-heat load state is pushed to the operation and maintenance monitoring terminal, and the key parameters are recorded for subsequent safety analysis and operation decision.

[0048] In this embodiment, by comparing the three-dimensional heat flow evaluation value with the heat flow threshold value in real time, a hierarchical cooling regulation mechanism is established, and layer-by-layer response from regular maintenance, early plan to full-load emergency is realized. Specifically, this step can maintain the basic cooling mode when the battery thermal load is low, avoiding unnecessary energy consumption; when the heat flow is close to the critical value, the cooling capacity is increased in advance and a cold distribution plan is generated, providing a buffer time for subsequent regulation; when the heat flow exceeds the threshold value, the highest intensity cooling and operation and maintenance alarm are triggered quickly, ensuring that the risk hotspots are identified and processed in real time, thereby providing a key execution link for digital twin simulation and cold adaptive control, and ensuring the safety and stability of the energy storage battery operation.

[0049] Specifically, based on the standardized thermal state data set, the difference between the infrared thermal imaging measured temperature and the predicted temperature is used to analyze the simulation accuracy. The specific steps are as follows: input the access data as training data, which includes: the three-dimensional geometric structure of the battery established based on CAD refinement and the volume of the single battery, which is used to define the spatial boundary conditions and heat normalization parameters of the battery; refrigerant flow, refrigerant inlet temperature and outlet temperature, which are collected by sensors in real time and used as cooling capacity constraint conditions; and the battery surface temperature field obtained by infrared thermal imaging and extraction, which is used to construct dynamic verification data of external temperature distribution. On the modeling side, based on the CFD platform, the above-mentioned multi-source input is solved by transient conjugate heat transfer to obtain a high-fidelity temperature field and heat flow distribution including battery body heat conduction, cooling liquid convection and boundary heat exchange. Then, the principal component analysis is introduced to reduce the dimension of the high-dimensional heat field data, and the main characteristic variables are extracted to reduce the calculation overhead; and the thermal RC network equivalent method is combined, that is, a fast thermal prediction model is established by resistance-capacitance equivalent network form to realize the simplified expression of complex thermal process. On this basis, the extended Kalman filter is used to calibrate the model online, and the measured sensor data and the model prediction results are fused to dynamically correct the key parameters of the heat conduction coefficient and the convection coefficient, so as to maintain the high consistency of the model to the real running state. On the control side, the fast prediction model is jointly simulated with the Simulink platform, and the cooling capacity demand curve that meets the temperature safety band requirements is inversely solved under the constraint condition through the short-time domain rolling optimization strategy, and the real-time adjustment signal is generated. On the output side, the predicted temperature and the predicted cooling flow are given in real time as the control basis for the cooling pump speed regulation and valve opening adjustment execution link, forming a closed-loop mechanism of prediction-calibration-control. The absolute value of the difference between the infrared thermal imaging measured temperature and the predicted temperature is divided by the sum of the temperature fluctuation standard deviation and one, and then one is added to take the natural logarithm to obtain the temperature difference deviation correction value; the value of the predicted cooling flow plus one is divided by the value of the refrigerant flow minus the predicted cooling flow, and then one is added to obtain the cooling deviation correction value; the temperature difference deviation correction value and the cooling deviation correction value are multiplied to obtain the model deviation correction value.

[0050] The model deviation correction value calculation formula is:

[0051] ;

[0052] In the formula: represents the infrared thermal imaging measured temperature, which is used to reflect the battery surface hot spot, and is derived from the infrared thermal imager; represents the model predicted temperature, which is used to compare the difference between simulation and measurement, and is derived from the digital twin model output; represents the temperature fluctuation standard deviation, which is used to smooth the abnormal fluctuation, and is derived from the sliding window calculation; represents the refrigerant flow rate, which is used to reflect the bottom convection intensity, and is derived from the cooling circuit flow sensor; represents the predicted cooling flow rate, which is used as a deviation comparison reference, and is derived from the twin model output.

[0053] In this embodiment, the difference between the digital twin prediction result and the actual monitoring data is quantified, and the model parameters are dynamically corrected on this basis. The formula normalizes the difference between the infrared thermal imaging measured temperature and the model predicted temperature, and combines the temperature fluctuation standard deviation to smooth the abnormal fluctuation, to obtain a stable temperature deviation factor; at the same time, the ratio of the measured refrigerant flow rate to the model predicted cooling flow rate is introduced to reflect the deviation of cooling capacity between simulation and actual. The product of the two is multiplied and logarithmically compressed to obtain the final correction value R, which can not only suppress the deviation amplification caused by sudden abnormalities, but also ensure that the cooling capacity difference is effectively mapped, thereby providing a reliable basis for online updating of the twin model, parameter calibration and cooling capacity adaptive allocation.

[0054] Specifically, and based on the accuracy analysis results, the cooling boundary conditions are corrected in real time as follows:

[0055] When the calculation results of the model deviation correction value for three consecutive times show a continuous increasing trend, it is determined that the difference between the digital twin prediction and the measured results is expanding, at which time the temperature matrix data collected by the infrared thermal imager and the flow measurement sequence obtained by the cooling circuit sensor are returned to the battery twin model in synchronization, triggering the dynamic parameter calibration process, which corrects the thermal conductivity, heat exchange boundary conditions and local cooling efficiency factor online; at the same time, a new set of boundary conditions is generated and written into the simulation kernel, and the cooling capacity regulating device automatically enters the warning state, pre-setting the acceleration instructions of the cooling pump, fan and valve group, to ensure the rapid response capability to deal with sudden heat risks.

[0056] When the fluctuation range of the calculation results of the model deviation correction value is less than the tolerance threshold for three consecutive times, it is determined that the twin prediction and the actual measurement remain within the allowable error interval, the real-time update of the model parameters and the collected data is maintained, and the cooling pump speed is adjusted to the interval of 25% to 40% of the rated value to ensure that the flow is in the stable operation interval; at the same time, the region with slight deviation is automatically marked in the three-dimensional thermal field of the battery twin model, and monitoring prompt information is generated and pushed to the operation and maintenance end for continuously tracking the potential evolution trend of the local hot spot.

[0057] When the calculation results of the model deviation correction value continue to decrease for three consecutive times, it is determined that the fitting degree of the twin prediction and the actual measurement is gradually improved, and the deviation gradually converges, so the current parameters of the battery twin model are maintained unchanged, and no additional boundary condition correction is performed; the cooling pump speed is automatically adjusted to the low gear operation, the refrigerant flow is reduced, the cooling circuit enters the energy-saving mode, and only low-frequency sampling and parameter recording are reserved in the background to reduce energy consumption and prolong the service life of the equipment.

[0058] In the embodiment, the consistency between the digital twin model and the actual measurement data is dynamically checked by continuously monitoring the change trend of the model deviation correction value, and a differentiated cooling regulation strategy is triggered accordingly. When the deviation continues to expand, the actual measurement data can be fed back in time to correct the model parameters; when the deviation is within the tolerance range, the stable update of the twin model and the medium operation of the cooling pump are maintained, and the deviation region is marked in the model for operation and maintenance monitoring; when the deviation gradually converges, the model parameters are kept unchanged and the cooling pump speed is reduced, so that the cooling circuit enters the energy-saving mode. Through this logic, closed-loop correction of prediction and actual measurement, graded execution of cooling regulation, and dynamic balance of energy consumption and safety are realized.

[0059] Specifically, the cooling demand intensity is analyzed by taking the heat flow evaluation result and the precision analysis result as inputs. The specific steps are as follows: multiply the three-dimensional heat flow evaluation value by the value obtained by adding one to the model deviation correction value, and then take the square root to obtain the heat flow deviation coupling value; divide the average inlet and outlet temperature difference of the refrigerant by the value obtained by subtracting the refrigerant outlet temperature from the current refrigerant inlet temperature after adding one to the average inlet and outlet temperature difference of the refrigerant to obtain the cooling temperature difference ratio; add the heat flow deviation coupling value and the cooling temperature difference ratio to obtain the cooling adaptive allocation value.

[0060] The cooling adaptive allocation value calculation formula is:

[0061] ;

[0062] In the formula: represents the three-dimensional heat flow evaluation value, which is used to depict the intensity of the internal heat distribution of the battery; represents the model deviation correction value, which is used to quantify the difference between simulation and actual measurement; represents the average inlet and outlet temperature difference, which is used to construct an adaptive reference and is derived from sliding window statistics; represents the refrigerant inlet temperature, used to characterize the instantaneous heat absorption capacity of the cooler, derived from the cooling loop temperature sensor; represents the refrigerant outlet temperature, used to characterize the instantaneous heat absorption capacity of the cooler, derived from the cooling loop temperature sensor.

[0063] In this embodiment, the three-dimensional heat flow evaluation value of Example One is set to 0.80, the model deviation correction value is set to 0.20, the average inlet and outlet temperature difference is set to 2.0, the refrigerant inlet temperature is set to 22.0, and the refrigerant outlet temperature is set to 27.0;

[0064] In this embodiment, the three-dimensional heat flow evaluation value of Example One is set to 0.80, the model deviation correction value is set to 0.20, the average inlet and outlet temperature difference is set to 2.0, the refrigerant inlet temperature is set to 22.0, and the refrigerant outlet temperature is set to 27.0;

[0065] In this embodiment, the three-dimensional heat flow evaluation value of Example One is set to 0.80, the model deviation correction value is set to 0.20, the average inlet and outlet temperature difference is set to 2.0, the refrigerant inlet temperature is set to 22.0, and the refrigerant outlet temperature is set to 27.0;

[0066] In this embodiment, the three-dimensional heat flow evaluation value of Example One is set to 0.80, the model deviation correction value is set to 0.20, the average inlet and outlet temperature difference is set to 2.0, the refrigerant inlet temperature is set to 22.0, and the refrigerant outlet temperature is set to 27.0;

[0067] In this embodiment, the three-dimensional heat flow evaluation value of Example One is set to 0.80, the model deviation correction value is set to 0.20, the average inlet and outlet temperature difference is set to 2.0, the refrigerant inlet temperature is set to 22.0, and the refrigerant outlet temperature is set to 27.0;

[0068] In this embodiment, the three-dimensional heat flow evaluation value of Example One is set to 0.80, the model deviation correction value is set to 0.20, the average inlet and outlet temperature difference is set to 2.0, the refrigerant inlet temperature is set to 22.0, and the refrigerant outlet temperature is set to 27.0;

[0069] In this embodiment, the three-dimensional heat flow evaluation value of Example One is set to 0.80, the model deviation correction value is set to 0.20, the average inlet and outlet temperature difference is set to 2.0, the refrigerant inlet temperature is set to 22.0, and the refrigerant outlet temperature is set to 27.0;

[0070] Table 1: Data table of cooling capacity adaptive allocation value

[0071]

[0072] As Figure 2The cold adaptive allocation value fold line chart provided by the present application is shown. As shown in Table 1 and Figure 2 It can be seen that the cold adaptive allocation value of example six is the highest, indicating that the three-dimensional heat flow evaluation value and the model deviation correction value are both at a high level, and the average inlet and outlet temperature difference is also the largest, reflecting that the thermal load is high, the model fitting error is obvious, and the cooling demand is urgent, and more cooling capacity needs to be allocated to cope with the transient thermal risk and realize the rapid recovery of temperature control stability; the cold adaptive allocation value of example three is the lowest, although the model deviation correction value is small and the actual cooling temperature difference is low, indicating that the thermal state changes smoothly and the energy consumption pressure is small under this working condition, so it is suitable to adopt a conservative cooling capacity allocation strategy to maintain energy efficiency balance and avoid resource waste; the fold line chart of the cold adaptive allocation value clearly shows the cooling resource response strength of each example under typical working conditions, and the higher the value, the more active cooling is needed, which is suitable for the priority ranking reference of dynamic thermal management strategy formulation and execution of twin driving.

[0073] Specifically, and based on the demand analysis results, the specific steps of generating the step adjustment instructions of the refrigerant flow and the pump speed are: comparing the cold adaptive allocation value with the cold capacity allocation threshold value in real time, the cold capacity allocation threshold value includes a first cold capacity threshold value and a second cold capacity threshold value, the first cold capacity threshold value is higher than the second cold capacity threshold value, and the first cold capacity threshold value is used to realize step response and resource allocation optimization in dynamic cooling regulation;

[0074] When the cold adaptive allocation value is less than or equal to the second cold capacity threshold value, it is identified that the current working condition is in a low thermal load interval, the cooling pump is maintained at the lowest speed, and the output power of the cooling capacity regulation device is kept unchanged; at this time, in order to reduce the calculation load, the infrared thermal imaging image enhancement function is automatically turned off, only the original measurement values of the battery feature data are collected and stored; the simulation module suspends the execution of the incremental calculation process, and does not refresh the three-dimensional heat distribution map in real time, only the central node temperature sequence is recorded in an append write mode, which is used for subsequent trend tracking and baseline comparison, and avoids waste of redundant operation resources;

[0075] When the cold adaptive allocation value is greater than the second cold capacity threshold value and less than or equal to the first cold capacity threshold value, it is determined that the current thermal load is in a medium fluctuation interval, the cooling pump speed is automatically increased to medium speed operation to ensure that the cooling flow rate responds within the safety band; at the same time, the image analysis algorithm is activated to reconstruct the boundary and extract the area of the hot spot region in the infrared image, and the high-temperature core region features are refined; the simulation module generates a simple heat map panel, marks the key attention area and synchronously displays the visualization results to the control interface, which is convenient for manual inspection and strategy fine-tuning; the spatial coverage information of the current cold capacity allocation range is updated synchronously, and is written into the cold capacity regulation log for retrieval;

[0076] When the cold adaptive allocation value is greater than the first cold threshold, it is judged that the current working condition is in a high heat load high risk state, and the cooling pump is immediately switched to the highest speed to realize the limit cold response; at the same time, the simulation module is triggered to enter the intensive operation mode, the dynamic rendering engine of the three-dimensional heat distribution map is continuously started, the global visual tracking of the temperature field change of the battery surface and the internal temperature field is carried out, and the hot spot migration trajectory is constructed in real time; the historical data and strategy model of the full cycle charging and discharging task are loaded, a short-term prediction sequence is constructed based on a three-order time step, which is used to simulate the heat load evolution trend in advance; the simulation path executes the complete reconstruction strategy, synchronously introduces the joint calculation of the real-time collected battery characteristic data and cooling characteristic data, and forms a high-frequency data snapshot of all key parameters at this moment, so as to facilitate the post-fault cause and traceability analysis.

[0077] In the embodiment, based on the real-time comparison between the cold adaptive allocation value and the cold allocation threshold, a hierarchical response mechanism is constructed to realize fine control of cooling resource scheduling and dynamic linkage adjustment of the simulation model. The core purpose is to flexibly adjust the cooling strategy and simulation calculation process under different heat load conditions, and to improve the overall operation efficiency and calculation resource utilization. When the cold demand is in a low load state, this step can effectively inhibit the redundant resource calling, and only record the key node data to maintain the basic monitoring; in the case of medium heat load, the cooling capacity and image analysis intensity are moderately strengthened, while ensuring the synchronization update of heat map data visualization and control interface; in the high heat load scene, the maximum cooling capacity is quickly released, and the simulation engine, control platform and data recording module are linked, and the response accuracy and prediction control ability of high risk working condition are fully strengthened, so as to build an intelligent cooling regulation closed loop with energy saving, real-time and safety.

[0078] Specifically, in each cooling control cycle, the cold allocation instruction is generated and verified, and the preventive adjustment is carried out in combination with real-time deviation feedback and short-term prediction. The specific steps are as follows:

[0079] In each cooling control cycle, based on the current battery thermal state data, the three-dimensional heat flow evaluation value and model deviation correction value are extracted in real time, and a group of cold allocation instructions are generated according to the three-dimensional heat flow evaluation value and model deviation correction value. The instruction clearly defines the target speed of the cooling pump and the dynamic flow rate distribution of the refrigerant to realize precise allocation of cooling resources. Before the instruction is issued, a shadow simulation process is started in the battery twin model, the heat diffusion process under the current instruction condition is fed forward and predicted, if the temperature of any node in the simulation process is equal to or higher than the safety threshold, the current cold allocation instruction is automatically rolled back, and the related parameters are adjusted and verified again until the predicted temperature is below the safety threshold. The cold allocation instruction is formally issued to the execution component to ensure that the control strategy has sufficient safety margin.

[0080] During the execution of the cold distribution instruction, the inlet and outlet temperatures of the refrigerant in the cooling loop are continuously collected, the average temperature difference is dynamically calculated, and the actual heat exchange capacity is compared and analyzed with the battery twin model prediction temperature result. The deviation information is extracted as a feedback parameter to update the thermal response state of the twin model in real time, and the model accurately maps the current cooling effect. Before the end of the cooling control period, a short-term trend prediction is performed in combination with the cold self-adaptive distribution value. If the heat accumulation trend of the local hot spot area is found to be significant, the cooling pump speed will be increased in advance to interrupt the development path of the hot spot, and the control execution value and the actual reading will be recorded as baseline data for subsequent period modeling and control strategy iteration, thereby gradually building a self-adaptive evolution cooling control mechanism.

[0081] As Figure 3 The signal schematic involved in the present application is shown, starting from the Internet of Things node, real-time collection of thermal state and environmental data by front-end sensing equipment, and after being summarized by the data collection module, it is transmitted to the data center for unified processing and management. In the data center, the infrared thermal imaging data flows into the modeling module to build a three-dimensional thermal behavior simulation model of the battery and the thermal sensitive component. After modeling, it enters the simulation module to predict the heat distribution and trend analysis of the current operating state. The simulation results are sent to the decision module to generate control instructions for cooling intensity adjustment, fluid distribution optimization and risk response. At the same time, the decision results are also fed back to the adjustment module to dynamically correct the operating parameters in the data center, such as the cooling pump speed and the valve opening, to realize the adaptive optimization of cold adjustment and thermal control. The whole process embodies the real-time coupling relationship among modeling, simulation and adjustment, supports continuous monitoring, rapid evaluation and precise intervention during operation, and is an important digital twin support structure for battery safety and heat dissipation efficiency optimization scenarios.

[0082] As Figure 4The signal generation flowchart related to the application is shown, starting from the collection of two types of data: one is the physical structure data of the battery, and the other is the dynamic state data of the battery in the charging and discharging process, including voltage, current, power and other electrical signal information. Based on these data, first, a three-dimensional model of the battery is constructed to restore its spatial structure characteristics; then, the charging and discharging electrical signal data is input into the model for dynamic simulation to deduce the heat distribution and change trend generated under different current conditions, thereby obtaining the heat source evolution process in the charging and discharging process. On this basis, by establishing a three-dimensional thermodynamic diffusion model, the above heat source data is further mapped to the heat propagation path and cold demand distribution area, providing quantitative support for the subsequent cooling control strategy. When the electrical signal input of detecting the start of discharging and the start of charging is detected, the thermal simulation process is automatically started, the required refrigerant flow is predicted in advance based on the current working condition evaluation result, the refrigeration capacity generation signal is output, and the pre-adjustment of the cooling device is realized. This simulation prediction method based on the generation and diffusion mechanism of heat sources helps to realize the intelligent and feedforward control of battery thermal management, and is a key step for building a digital twin thermal management.

[0083] In the embodiment, a cooling control closed-loop mechanism with feedforward verification, real-time feedback and adaptive adjustment capability is constructed, and the core goal is to ensure that the battery is always below the safe temperature threshold in the thermal management process and dynamically responds to the heat flow change trend to accurately allocate cold. Through three-dimensional heat flow evaluation and model deviation correction, cold distribution instructions are generated, and shadow simulation is performed in the battery twin model to judge potential overheating risks in advance, thereby avoiding thermal runaway caused by unreasonable instructions from the source; in the actual execution process, the refrigerant inlet and outlet temperature difference is collected and compared with the predicted result, so that the model prediction accuracy can be continuously corrected, and the reliability and accuracy of the cooling regulation can be improved; and based on the local heat spot short-term prediction of the cold adaptive allocation value at the end of the cycle, the proactive response capability to sudden heat accumulation is embodied, which helps to intervene in potential risk points in advance and ensures the stability and energy efficiency of the entire thermal management process. As a key execution unit of the cooling strategy, this step provides strong technical support for realizing battery thermal safety and energy efficiency optimization.

[0084] It should be noted that, in this document, relationship terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device.

[0085] The preferred embodiments of the application disclosed above are only to facilitate the elucidation of the application. The preferred embodiments do not describe all the details of the application and limit the application to the specific embodiments described. Obviously, many modifications and variations can be made in light of the teachings above. The description is chosen and described in order to best explain the principles of the application and its practical application to thereby enable others skilled in the art to best utilize the application and get the best results from the application. The application is only limited by the claims and their full scope and equivalents.

Claims

1. A method for thermal flow digital twin simulation and cold adaptive control of energy storage plant batteries, characterized in that: Comprise: S1, collect battery feature data and cooling feature data during battery operation, and pretreat the collected battery feature data and cooling feature data to construct a standardized thermal state data set; S2, based on the standardized thermal state data set, heat flow evaluation is performed on the overall heat flow density of the battery, and the cooling pump speed and refrigerant flow distribution are dynamically adjusted based on the heat flow evaluation result; S3, based on the standardized thermal state data set, precision analysis is performed on the simulation accuracy from the difference between the infrared thermal imaging measured temperature and the predicted temperature, and the cooling boundary condition is corrected in real time based on the precision analysis result; S4, taking the heat flow evaluation result and the precision analysis result as input, demand analysis is performed on the cooling demand intensity, and the graded regulation instruction of refrigerant flow and pump speed is generated based on the demand analysis result; S5, generate and verify the cooling capacity distribution instruction in each cooling control period, and issue the execution and combine the real-time deviation feedback and short-term prediction for preventive adjustment.

2. The energy storage plant battery thermal flow digital twin simulation and cold adaptive control method of claim 1, wherein: The specific steps of collecting battery feature data and cooling feature data during battery operation are: Collecting battery feature data during battery operation, the battery feature data includes: single battery volume, battery heating power, battery surface maximum temperature, battery surface minimum temperature, infrared thermal imaging measured temperature, and calculating and recording the temperature fluctuation standard deviation of the battery at the same time; Collecting cooling feature data, the cooling feature data includes: refrigerant flow, refrigerant inlet temperature and refrigerant outlet temperature, and calculating and recording the average inlet and outlet temperature difference of the refrigerant at the same time.

3. The energy storage plant battery thermal flow digital twin simulation and cold adaptive control method of claim 1, wherein: The specific steps of pretreating the collected battery feature data and cooling feature data to construct a standardized thermal state data set are: For battery feature data, single battery volume is registered as a geometric constant, battery heating power is cross-verified and sliding average filtering is performed; the maximum and minimum temperatures of the battery surface are based on the edge value of the infrared thermal imaging measured temperature and the battery temperature field is constructed; the infrared thermal imaging measured temperature is processed by Gaussian denoising, and the temperature fluctuation standard deviation of the battery is calculated according to the sliding window mechanism; For cooling feature data, refrigerant flow is subjected to time series smoothing and variation rate analysis to remove pulse interference, and after aligning the refrigerant inlet temperature and outlet temperature, the instantaneous temperature difference is calculated, and the average inlet and outlet temperature difference of the refrigerant is calculated; The normalized battery feature data and cooling feature data after standardization are normalized to construct a standardized thermal state data set.

4. The method of claim 1, wherein: The specific steps of heat flow evaluation on the overall heat flow density of the battery based on the standardized thermal state data set are: Divide the volume of the single battery by the battery heating power to obtain the volume heating intensity value; Subtract the maximum temperature of the battery surface from the minimum temperature of the battery surface, then multiply by the corresponding temperature weighting factor to obtain the surface temperature difference correction value; Add one to the refrigerant flow, then divide by the refrigerant flow and multiply by the corresponding cooling weighting factor to obtain the cooling flow weighting value; Add the volume heating intensity value, the surface temperature difference correction value and the cooling flow weighting value to obtain the three-dimensional heat flow evaluation value.

5. The energy storage plant battery thermal flow digital twin simulation and cold adaptive control method of claim 1, wherein: The specific steps of dynamically adjusting the cooling pump speed and refrigerant flow distribution based on the heat flow evaluation result are: Real-time comparison of three-dimensional heat flow evaluation value and heat flow threshold value: When the three-dimensional heat flow evaluation value is less than the heat flow threshold value, the cooling pump operating speed is kept unchanged, the refrigerant maintains the default flow rate, and only the normal heat flow distribution condition is output in the battery twin model; When the heat flow evaluation value is equal to the heat flow threshold value, the cooling pump is adjusted to 25% to 40% of the rated value, the refrigerant flow rate is increased, the potential hot spot area is highlighted in the battery twin model in real time, and a cold energy distribution plan is generated in advance; When the three-dimensional heat flow evaluation value exceeds the heat flow threshold value, the cooling pump is adjusted to the highest speed, the refrigerant flow rate is increased to the highest, a high-load operation instruction is immediately sent to the cold energy adjusting device, the three-dimensional heat distribution in the battery twin model is updated in real time, and a high-risk area is marked, triggering an operation and maintenance alarm.

6. The energy storage plant battery thermal flow digital twin simulation and cold adaptive control method of claim 1, wherein: The specific steps of performing precision analysis on the simulation accuracy based on the standardized heat state data set and the difference between the infrared thermal imaging measured temperature and the predicted temperature are as follows: The input access data is used as training data, and the access data includes: the battery three-dimensional geometry and single battery volume established based on CAD refinement, the refrigerant flow rate, the refrigerant inlet temperature and outlet temperature, and the battery temperature field extracted by infrared thermal imaging; On the modeling side, the access data is solved by transient conjugate heat transfer on CFD to obtain high-fidelity temperature and heat flow distribution, and a fast prediction model is constructed by principal component dimension reduction and thermal RC network equivalence method, and online calibration is performed by extended Kalman filter; On the control side, the fast prediction model is associated with Simulink, and the cold energy demand within the safety band is inversely solved under the constraint condition by short-time domain rolling optimization, and the predicted temperature and predicted cooling flow rate are output in real time on the output side; The absolute value of the difference between the infrared thermal imaging measured temperature and the predicted temperature of the battery is divided by the sum of one and the temperature fluctuation standard deviation, and then one is added to take the natural logarithm to obtain the temperature difference deviation correction value; The value of the predicted cooling flow rate plus one is divided by the value of the refrigerant flow rate minus the predicted cooling flow rate, and then one is added to obtain the cooling deviation correction value; The temperature difference deviation correction value and the cooling deviation correction value are multiplied to obtain the model deviation correction value.

7. The energy storage plant battery thermal flow digital twin simulation and cold adaptive control method of claim 1, wherein: The specific steps of real-time correction of the cooling boundary condition based on the precision analysis result are as follows: When the calculation results of the model deviation correction value for three consecutive times continue to increase, it is determined that the model prediction and measurement deviation is enlarged, the infrared thermal imaging measured temperature and the flow rate measured data are fed back to the battery twin model, the thermal conductivity coefficient and the boundary condition are dynamically corrected, and the cold energy adjusting device is triggered to enter the early warning state; When the calculation results of the model deviation correction value for three consecutive times fluctuate and are less than the tolerance threshold value, the access data of the battery twin model is kept updating, the cooling pump speed is adjusted to 25% to 40% of the rated value, the cooling loop flow rate is kept stable, the deviation area is marked in the battery twin model, and monitoring is prompted; When the calculation results of the model deviation correction value for three consecutive times continue to decrease, the parameters of the battery twin model are kept unchanged, the cooling pump speed is reduced, and the cooling loop enters the energy saving mode.

8. The energy storage plant battery thermal flow digital twin simulation and cold adaptive control method of claim 1, wherein: The specific steps of demand analysis on the cooling demand intensity by taking the heat flow evaluation result and the precision analysis result as inputs are as follows: The three-dimensional heat flow evaluation value and the value obtained by adding one to the model deviation correction value are multiplied and then the square root is taken to obtain the heat flow deviation coupling value; The cooling temperature difference ratio is obtained by dividing the average refrigerant inlet and outlet temperature difference plus one by the value of the current refrigerant inlet temperature minus the refrigerant outlet temperature; The cooling capacity adaptive allocation value is obtained by adding the heat flow deviation coupling value and the cooling temperature difference ratio.

9. The energy storage plant battery thermal flow digital twin simulation and cold adaptive control method of claim 1, wherein: The specific steps of generating the refrigerant flow and pump speed step adjustment instructions based on the demand analysis results are as follows: The cooling capacity adaptive allocation value is compared with the cooling capacity allocation threshold in real time, and the cooling capacity allocation threshold includes a first cooling capacity threshold and a second cooling capacity threshold, wherein the first cooling capacity threshold is higher than the second cooling capacity threshold: When the cooling capacity adaptive allocation value is less than or equal to the second cooling capacity threshold, the cooling pump is kept at the lowest speed, the cooling capacity adjustment device output is kept unchanged, the thermal imaging image enhancement is turned off, only the original value of the battery characteristic data is recorded, the simulation incremental calculation process is turned off, the three-dimensional heat distribution map is not refreshed, and only the central node temperature sequence is appended and written; When the cooling capacity adaptive allocation value is greater than the second cooling capacity threshold and less than or equal to the first cooling capacity threshold, the cooling pump speed is increased, the image analysis algorithm is started to reconstruct the boundary of the hot spot area, a simple heat map panel is generated and synchronized to the control interface, and the current cooling capacity allocation range information is updated; When the cooling capacity adaptive allocation value is greater than the first cooling capacity threshold, the cooling pump is immediately switched to the highest speed, the three-dimensional heat distribution map dynamic rendering and hot spot migration trajectory tracking are continuously started, the full-cycle charging and discharging task data is loaded and a three-order time step prediction sequence is generated; the simulation engine starts the complete reconstruction path and synchronizes the real-time battery characteristic data and cooling characteristic data, and the current battery characteristic data and cooling characteristic data are recorded as high-frequency data snapshots.

10. The energy storage plant battery thermal flow digital twin simulation and cold adaptive control method of claim 1, wherein: The specific steps of generating and verifying the cooling capacity allocation instructions in each cooling control cycle, issuing the execution and combining real-time deviation feedback and short-term prediction for preventive adjustment are as follows: In each cooling control cycle, the cooling capacity allocation instructions are generated according to the three-dimensional heat flow evaluation value and the model deviation correction value, and the instructions cover the cooling pump speed and the refrigerant flow rate; A shadow simulation is performed in the battery twin model, when the predicted temperature is equal to or greater than the safety threshold, the cooling capacity allocation instructions are rolled back and reverified until the predicted temperature is less than the safety threshold before being issued to the execution component; During the execution stage of the cooling capacity allocation instructions, the refrigerant average inlet and outlet temperature difference is continuously collected and compared with the predicted temperature, and the deviation information of the refrigerant average inlet and outlet temperature difference and the twin predicted temperature is fed back to the battery twin model; Before the end of the cooling control cycle, short-term prediction is performed in combination with the cooling capacity adaptive allocation value, and when a local hot spot trend occurs, the cooling pump speed is increased in advance, and the execution and read-back results are recorded as baseline data.

Images