Heat dissipation control method and device of single-phase immersed liquid cooling charging pile and medium

Abstract

The invention discloses a heat dissipation control method and device for a single-phase immersed liquid cooling charging pile and a medium, and relates to the technical field of battery thermal management, and the method comprises the steps: carrying out the high-precision scanning and dynamic feature extraction of a built-in fiber grating array of a cold plate according to a partition flow control signal, and obtaining a temperature field matrix and a dynamic thermal feature set; performing multi-dimensional fusion analysis and electrochemical coupling analysis on the temperature field matrix and the dynamic thermal feature set to generate a thermal coupling parameter set; performing real-time risk quantitative evaluation and risk topological mapping on the thermal coupling parameter set, and outputting a risk topological data set; and performing cooling intensity dynamic modulation according to the risk topology data set, and obtaining a partition flow redistribution instruction. According to the invention, fine monitoring of the cold plate-battery interface contact thermal resistance is realized through a high-precision pressure field reconstruction technology, the accuracy and reliability of pressure distribution detection are significantly improved, and the local overheating risk caused by an assembly gap is effectively eliminated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery thermal management, in particular to a heat dissipation control method, device and medium for a single-phase immersion liquid-cooled charging pile. BACKGROUND

[0002] In recent years, with the development of electric vehicle fast charging technology towards high power density, the charging pile heat dissipation system is facing severe challenges. The traditional heat dissipation schemes are mainly divided into two categories: air cooling and liquid cooling. The air cooling technology reduces the temperature through forced convection, and the liquid cooling technology improves the heat dissipation efficiency through cold plate or immersion design. In the liquid cooling system, the cold plate heat dissipation is in contact with the battery surface through the metal flow channel, and the immersion liquid cooling directly immerses the heat generating components in the insulating cooling liquid. However, these schemes still have significant limitations in dealing with the dynamic deformation and thermal runaway risk of the battery during fast charging.

[0003] The current technical problem is that the dynamic contact thermal resistance of the battery-cold plate interface cannot be compensated in real time. The periodic expansion of the battery during fast charging due to lithium ion intercalation / deintercalation causes the continuous change of the cold plate contact pressure distribution, which easily leads to the aggravation of temperature field inhomogeneity, triggering of BMS forced power reduction, imbalance of cooling liquid flow rate distribution, insufficient flow in low pressure area leading to boiling risk and other chain problems. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a heat dissipation control method for a single-phase immersion liquid-cooled charging pile to solve the problem of uneven heat dissipation and thermal runaway risk caused by battery deformation during fast charging.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a heat dissipation control method for a single-phase immersion liquid-cooled charging pile, which comprises,

[0008] Real-time acquisition of contact pressure data between the battery and the cold plate, and visual reconstruction to generate a pressure distribution matrix;

[0009] Constructing a flow decision model, intelligently mapping the pressure distribution matrix and dynamically optimizing the threshold value to generate a partitioned flow control signal;

[0010] According to the partitioned flow control signal, performing high-precision scanning and dynamic feature extraction on the cold plate built-in fiber grating array to obtain a temperature field matrix and a dynamic thermal feature set;

[0011] Multi-dimensional fusion analysis and electrochemical coupling analysis are performed on the temperature field matrix and the dynamic thermal feature set to generate a thermal coupling parameter set;

[0012] Real-time risk quantitative evaluation and risk topology mapping are performed on the thermal coupling parameter set, and a risk topology data set is output;

[0013] Cooling intensity dynamic modulation is performed according to the risk topology data set, and partition flow redistribution instructions are obtained.

[0014] As a preferred scheme of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile, the specific steps of generating the pressure distribution matrix are as follows,

[0015] Real-time acquisition of contact pressure data between the battery and the cold plate is performed, and signal conditioning and dynamic compensation are performed to generate a temperature-compensated pressure signal array;

[0016] Noise suppression and physical quantity calibration conversion are performed on the temperature-compensated pressure signal array to generate a physical pressure value array;

[0017] The physical pressure value array is subjected to spatial interpolation expansion and gradient continuity verification to generate a contact pressure characteristic field;

[0018] The contact pressure characteristic field is subjected to pressure threshold partition mapping and statistical feature integration to generate a pressure distribution matrix.

[0019] As a preferred scheme of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile, the specific steps of generating the pressure distribution matrix are as follows,

[0020] As a preferred scheme of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile, the specific steps of generating the pressure distribution matrix are as follows,

[0021] The sensor data layer extracts and vectorizes the multi-dimensional features of the pressure distribution matrix to generate a pressure feature vector;

[0022] The strategy reasoning layer performs intelligent strategy mapping and flow proportion allocation on the pressure feature vector to generate an initial flow proportion coefficient array;

[0023] The dynamic optimization layer performs multi-source feedback optimization and dynamic threshold control on the initial flow proportion coefficient array to generate a partition flow control signal.

[0024] As a preferred scheme of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile, the specific steps of generating the pressure distribution matrix are as follows,

[0025] Based on the partition flow control signal, fiber grating array synchronous scanning and spectrum-temperature conversion are performed to generate a preliminary temperature data array;

[0026] The high-resolution temperature field matrix is subjected to thermal field dynamic characteristic analysis to generate a dynamic thermal characteristic set.

[0027] The high-resolution temperature field matrix is subjected to thermal field dynamic characteristic analysis to generate a dynamic thermal characteristic set.

[0028] As a preferred scheme of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile, the generated thermal coupling parameter set has the following specific steps,

[0029] The dynamic thermal characteristic set is subjected to multi-source data space-time alignment and feature fusion to generate a space-time aligned data set.

[0030] The space-time aligned data set is subjected to thermal-electric characteristic correlation and parameter mapping to output an intermediate coupling parameter set.

[0031] Based on the intermediate coupling parameter set, the lithium extraction probability is calculated and the safety margin is evaluated to output the thermal coupling parameter set.

[0032] As a preferred scheme of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile, the generated thermal coupling parameter set has the following specific steps,

[0033] The thermal coupling parameter set is subjected to probability field reconstruction and risk area extraction to generate a risk probability field matrix.

[0034] The risk probability field matrix is subjected to regional continuity optimization and risk intensity calibration to output a comprehensive risk field matrix.

[0035] The comprehensive risk field matrix is subjected to risk area clustering analysis and hierarchical topology construction to output a risk topology data set.

[0036] As a preferred scheme of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile, the generated thermal coupling parameter set has the following specific steps,

[0037] The risk topology data set is subjected to hierarchical cooling intensity mapping and battery state dynamic constraint to output a cooling intensity modulation strategy table.

[0038] The cooling intensity modulation strategy table is subjected to actuator signal conversion and safety parameter packaging to output a partition flow redistribution instruction.

[0039] In a second aspect, the present application provides a computer device comprising a memory and a processor, the memory storing a computer program, wherein the computer program is executed by the processor to implement any step of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile according to the first aspect of the present application.

[0040] In a third aspect, the present application provides a computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements any step of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile according to the first aspect of the present application.

[0041] The present application has the advantages that: the fine monitoring of the cold plate-battery interface contact thermal resistance is realized through the high-precision pressure field reconstruction technology, the accuracy and reliability of the pressure distribution detection are significantly improved, and the local overheating risk caused by the assembly gap is effectively eliminated; the early prediction of lithium precipitation risk is realized through the electrochemical-thermal coupling risk modeling, the timeliness and accuracy of the identification of thermal runaway risks are greatly improved, and a full-link intelligent heat dissipation control system from the physical layer to the electrochemical layer is constructed. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] Figure 1 The flowchart of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile.

[0044] Figure 2 The flowchart of the pressure distribution matrix generation.

[0045] Figure 3 The flowchart of the thermal coupling parameter set generation.

[0046] Figure 4 The flowchart of the risk topology data set generation. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0048] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the scope of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0049] Second, the "one embodiment" or "an embodiment" referred to herein can include a particular feature, structure, or characteristic. The various embodiments appearing at different places in the specification are not necessarily all cumulative or mutually exclusive of each other.

[0050] Referring to Figures 1-4 For one embodiment of the present application, the embodiment provides a heat dissipation control method for a single-phase submerged liquid-cooled charging pile, comprising the following steps:

[0051] S1, real-time acquisition of contact pressure data between the battery and the cold plate, and visual reconstruction to generate a pressure distribution matrix; Specifically, as Figure 2 The steps are as follows:

[0052] S1.1, real-time acquisition of contact pressure data between the battery and the cold plate, and signal conditioning and dynamic compensation to generate a temperature-compensated pressure signal array;

[0053] It should be noted that the micro-piezoelectric film sensor array embedded on the surface of the cold plate continuously acquires the original analog voltage signal at a fixed sampling frequency, and the original analog voltage signal is converted into a digital signal by a 16-bit analog-to-digital converter; The temperature drift compensation processing is performed on the digital signal, and further, the internal temperature sensor data of the cold plate is read synchronously, the sensor output voltage and the standard pressure gauge value are recorded under different temperature conditions, and the temperature-voltage-pressure quantitative corresponding relationship table is fitted by the least squares method. The output voltage of each sensing channel is compensated in real time; the compensated digital voltage signal is further processed by a Butterworth low-pass filter to filter out high-frequency noise components caused by mechanical vibration and retain low-frequency pressure signals, and finally output the temperature-compensated pressure signal array.

[0054] S1.2, noise suppression and physical quantity calibration conversion are performed on the temperature-compensated pressure signal array to generate a physical pressure value array;

[0055] It should be noted that the waveform is smoothed by taking the arithmetic mean of a plurality of consecutive data points in the temperature-compensated pressure signal array, and further, a fixed-length sliding window is set, the window moves along the signal sequence point by point, and the average value of all data points in the window is calculated each time as the output value of the window center point, thereby eliminating high-frequency fluctuations and retaining signal trend components; Subsequently, a sensor calibration curve is applied, the sensor calibration curve is established through laboratory calibration test, the voltage value of each sensing unit is converted into the corresponding pressure physical quantity, and finally the physical pressure value array is output.

[0056] S1.3, spatial interpolation expansion and gradient continuity verification are performed on the physical pressure value array to generate a contact pressure characteristic field;

[0057] It should be pointed out that the adjacent four pressure sensing points in the physical pressure value array are divided into a rectangular unit, and a plurality of equidistant grid points are divided in each unit; according to the known pressure values of the four vertices of the unit, the linear interpolation is performed on each row of boundary points along the X direction to obtain the intermediate auxiliary point values, and then the quadratic interpolation is performed on the intermediate auxiliary point values along the Y direction to obtain the grid point pressure values; after processing all the sensor regions unit by unit, the discrete sensor point data is converted into a continuous spatial pressure distribution field; the gradient continuity of the continuous spatial pressure distribution field is checked, the absolute values of the pressure gradients between adjacent grid points are calculated, and the median replacement method is used to correct the abnormal jump points exceeding the pressure gradient threshold value; finally, the contact pressure characteristic field with spatial continuity and in accordance with the physical law is output.

[0058] It should be pointed out that the pressure gradient threshold value is set based on the shear stress limit value of the laminar boundary layer in fluid mechanics, and the example value range is 3-8 MPa / mm.

[0059] S1.4, the contact pressure characteristic field is subjected to pressure threshold partition mapping and statistical feature integration to generate a pressure distribution matrix.

[0060] It should be pointed out that each grid point pressure value in the contact pressure characteristic field is compared with a preset first pressure limit value and a second pressure limit value, the area with a pressure value lower than the first pressure limit value is marked as a low pressure area, the area with a pressure value between the first pressure limit value and the second pressure limit value is marked as a medium pressure area, and the area with a pressure value higher than the second pressure limit value is marked as a high pressure area; the area ratio of the low pressure area and the global pressure variance value are calculated synchronously, and the partition identification result and the statistical feature value are written into the matrix header file together, and finally the pressure distribution matrix containing the pressure partition information and the statistical features is output.

[0061] It should be pointed out that the first pressure limit value and the second pressure limit value are set based on the contact thermal resistance safety limit value of the cold plate-battery interface.

[0062] S2, a flow decision model is constructed, intelligent strategy mapping and dynamic threshold optimization are performed on the pressure distribution matrix, and a partition flow control signal is generated;

[0063] S2.1, a flow decision model is constructed based on the sensing data layer, the strategy reasoning layer and the dynamic optimization layer;

[0064] It should be pointed out that the flow decision model is constructed as follows: in the PyTorch framework, a one-dimensional convolutional network is called by adopting nn.Conv1d parameters, and the convolutional network is initialized, a spatial attention mechanism is connected after the convolutional layer, the key area feature response is enhanced through the self-attention mechanism, and the feature normalization is performed by using the LayerNorm layer, so as to complete the construction of the sensing data layer; the Transformer encoder architecture is called by applying nn.TransformerEncoder parameters, and the encoder is initialized; the process constraint rule is embedded for the encoder, the safety threshold is injected into the network as prior knowledge through the gating mechanism, and the residual connection is adopted to prevent gradient disappearance, so as to complete the construction of the policy inference layer; the long short-term memory network is called by applying nn.LSTM parameters, and the long short-term memory network is initialized; the real-time feedback regulator is embedded for the long short-term memory network, the flow coefficient is dynamically corrected through the time difference learning algorithm, the temperature-pressure coupling loss function is synchronously integrated for back propagation optimization, the dynamic optimization layer is constructed, and the flow decision model is obtained.

[0065] It should be pointed out that the safety threshold is set based on the battery thermal safety boundary and the pressure fluctuation tolerance, and the example value range is: the real-time temperature of the battery surface is 45-55℃, and the spatial variance of the contact pressure between the battery and the cold plate is 0.3-0.8MPa.

[0066] The pre-training process of the flow decision model is as follows: the supervised learning mode of the historical operation data set is adopted, the parameter training is completed by optimizing the comprehensive performance of temperature uniformity and energy consumption indicators, further, a training set containing a large number of pressure distribution matrix samples and partition flow control signals is constructed; the minimization of the maximum temperature difference of the battery surface and the reduction of the total power consumption are taken as the joint optimization objectives; five-fold cross-validation is adopted in the training to prevent overfitting, and finally when the loss decreases by less than the minimum convergence threshold for 5 consecutive times, the training is terminated, and the flow decision model is output.

[0067] It should be pointed out that the minimum convergence threshold is set based on the balance between overfitting risk and training efficiency, and the example value range is (0.1%, 0.5%).

[0068] S2.2, the sensing data layer extracts and vectorizes the pressure distribution matrix multidimensional features to generate a pressure feature vector;

[0069] It should be pointed out that the low-pressure area proportion and the global pressure variance values are read from the header file of the pressure distribution matrix, and the number and spatial distribution density of the connected regions of different pressure partition identifiers in the pressure distribution matrix are also counted; the low-pressure area proportion, the pressure variance, the high-pressure area proportion, the medium-pressure area proportion, the low-pressure area connectivity, the high-pressure area connectivity, the low-pressure area density and the high-pressure area density are combined into an eight-dimensional vector in a fixed order, and finally the pressure feature vector with a standardized structure is output.

[0070] S2.3, the policy inference layer performs intelligent policy mapping and flow proportion allocation on the pressure feature vector to generate an initial flow proportion coefficient array;

[0071] It should be noted that the pressure feature vector is input into the pre-constructed decision rule library, which contains a mapping relationship table of pressure features and flow coefficients. The basic flow coefficient is obtained by searching the mapping relationship table. Further, first, collect the pressure distribution matrix under different working conditions and the corresponding optimal flow control record to form a training data set; then use multivariate regression method to analyze the quantitative relationship between the pressure feature vector and the basic flow coefficient; then convert the correlation analysis result into a query table structure with pressure feature value as input index and optimal flow coefficient as output value; finally, through cross-validation, the mapping relationship of the decision rule library is iteratively optimized, and the basic flow coefficient and the optimal flow coefficient are controlled below the preset flow threshold. The mapping relationship table is generated by discretizing the pressure feature value by interval, obtaining the mode of the corresponding flow coefficient in each interval as the mapping output value; then according to the low pressure area density value in the pressure feature vector, adjust the corresponding partition coefficient according to the low pressure area density change amplitude (for example: adjust the rule that the corresponding partition coefficient is increased by zero point one for every ten percent increase in density); at the same time, combined with the pressure variance value, the high pressure area coefficient is corrected according to the pressure variance change degree (for example: the high pressure area coefficient is reduced by zero point zero five for every zero point five increase in variance); finally, the flow proportion coefficient of sixteen partitions is generated, forming the initial flow proportion coefficient array.

[0072] It should be noted that the preset flow threshold is set based on the thermal safety boundary of lithium ion battery, and the example value range is 0.08.

[0073] S2.4, the dynamic optimization layer performs multi-source feedback optimization and dynamic threshold control on the initial flow proportion coefficient array to generate partition flow control signals.

[0074] It should be noted that the initial flow proportion coefficient array receives real-time temperature data of the battery surface and the pressure variance value in the pressure distribution matrix; when the real-time temperature data of the battery surface exceeds the temperature control boundary value, all partition flow proportion coefficients are adjusted upward; when the pressure variance value exceeds the pressure control boundary value, the flow proportion coefficient of the high pressure area partition is corrected downward; the adjusted flow proportion coefficient is converted into a pulse width modulation duty cycle signal through a flow-control signal conversion relationship, and finally sixteen partition flow control signals are generated.

[0075] It should be noted that the temperature control boundary value is set based on the thermal safety boundary of lithium ion battery, and the pressure control boundary value is set based on the contact interface pressure fluctuation tolerance.

[0076] The flow-control signal conversion relationship establishment process is specifically as follows: under laboratory conditions, the flow of the cooling liquid of the electromagnetic valve under different control signal intensities is measured using a precision flowmeter, and the corresponding data of signal intensity and flow are recorded; a signal intensity-flow corresponding relationship table is established based on the measured data, and the flow control signal generation is realized through table lookup; finally, the relationship table is written into the non-volatile memory of the controller to form a fixed flow-control signal conversion relationship.

[0077] S3. According to the partition flow control signal, high-precision scanning and dynamic feature extraction are performed on the cold plate built-in fiber grating array to obtain a temperature field matrix and a dynamic thermal feature set.

[0078] S3.1. Based on the partition flow control signal, synchronous scanning of the fiber grating array and spectrum-temperature conversion are performed to generate a preliminary temperature data array.

[0079] It should be noted that the partition flow control signal triggers the wavelength demodulator to start, and the reflection spectrum of all fiber grating sensors built-in the cold plate is synchronously collected; the reflection spectrum is converted through a wavelength-temperature corresponding relationship table calibrated in the laboratory, the wavelength-temperature corresponding relationship table is constructed by measuring the center wavelength shift of the fiber grating sensor under different temperature environments and recording the corresponding data, and the center wavelength shift of each sensor is converted into a temperature value through the wavelength-temperature corresponding relationship table; the converted temperature value is processed by Kalman filtering to eliminate fluid pulsation interference, and finally a preliminary temperature data array containing the temperature values of all sensors is output.

[0080] S3.2. The preliminary temperature data array is subjected to spatial interpolation expansion and edge optimization processing to generate a high-resolution temperature field matrix.

[0081] It should be noted that the preliminary temperature data array is subjected to spatial interpolation expansion processing to realize grid refinement, taking a rectangular region composed of four adjacent temperature sensor points as a reference region, based on the known temperature values of the four vertices of the reference region, the temperature values of the interpolation points inside the unit are determined by linear weighting method, and the whole sensor region is processed cell by cell to form a continuous spatial temperature distribution; then the regularized temperature distribution matrix generated after the spatial interpolation expansion processing is subjected to edge optimization processing, the temperature difference value of each grid point and the directly adjacent point is calculated, and the abnormal points exceeding the temperature gradient abnormal threshold value are replaced by the temperature median of the surrounding points to eliminate the discontinuous mutation in the distribution field; finally, a high-resolution temperature field matrix with physical rationality and spatial continuity is output.

[0082] It should be noted that the temperature gradient abnormal threshold value is set based on the maximum temperature change rate allowed in the heat conduction theory, and the example value range is 1.5℃ / mm-3.0℃ / mm.

[0083] S3.3, thermal field dynamic characteristic analysis is performed on the high-resolution temperature field matrix to generate a dynamic thermal feature set.

[0084] It should be noted that the high-resolution temperature field matrix is calculated by calculating the temperature difference of adjacent grid points. When the temperature difference exceeds the maximum allowed temperature gradient in the lithium ion battery thermal safety specification to prevent local thermal runaway, it is marked as a high-risk area. The global temperature change rate value is obtained synchronously, combined with the high-risk area coordinate information to form a structured data set, and finally the dynamic thermal feature set is output.

[0085] S4, multi-dimensional fusion analysis and electrochemical coupling analysis are performed on the temperature field matrix and the dynamic thermal feature set to generate a thermal coupling parameter set; Specifically, as Figure 3 The steps are as follows:

[0086] S4.1, multi-source data space-time alignment and feature fusion are performed on the dynamic thermal feature set to generate a space-time alignment data set;

[0087] It should be noted that the temperature field matrix, high-risk area coordinate set and temperature change rate scalar included in the dynamic thermal feature set are synchronized with the voltage, current and SOC data provided by the battery management system through timestamp matching, with a timestamp accuracy of milliseconds. The synchronized temperature field matrix, voltage, current and SOC data are integrated in time sequence to form a space-time alignment data set containing temperature field, voltage, current and SOC parameters, ensuring that all data have a unified time base and spatial reference frame.

[0088] S4.2, thermal-electric characteristic correlation and parameter mapping are performed on the space-time alignment data set to output a coupling parameter intermediate set;

[0089] It should be noted that the temperature field matrix in the space-time alignment data set is aggregated into an average temperature value by region, and is combined with the voltage and current data of the same timestamp to form a time sequence triple. Then the sliding window method is used to analyze the synchronicity of temperature change trend and current change trend, and the consistency ratio of temperature rise / drop and current increase / decrease in the window is taken as the correlation index. Finally, the thermal-electric coupling coefficient is generated according to the correlation index. When the correlation degree of the high-voltage area is higher than the thermal-electric correlation degree judgment threshold, it is marked as a strong coupling area, and finally the coupling parameter intermediate set containing equivalent thermal impedance distribution, thermal-electric correlation scalar and coupling coefficient is output.

[0090] It should be noted that the thermal-electric correlation degree judgment threshold is set based on the thermal-electric change synchronicity in historical charging and discharging data, with an example value range of (0.75, 0.88).

[0091] S4.3, based on the coupling parameter intermediate set, the lithium extraction probability is calculated and the safety margin is evaluated, and the thermal coupling parameter set is output, expressed as,

[0092] ;

[0093] in, for The probability value of lithium plating at that location. for Temperature gradient value at that location, for The equivalent thermal resistance at that point.

[0094] It should be noted that the equivalent thermal impedance distribution and temperature gradient data in the intermediate set of coupling parameters are processed through a risk probability function to generate a lithium plating probability value for each grid point. At the same time, a linear correspondence is established between the lithium plating probability value and the safety margin number, specifically, the safety margin equals one minus the lithium plating probability value; when the lithium plating probability value is zero, the safety margin is 1.0; when the lithium plating probability value is 0.5, the safety margin is 0.5; and when the lithium plating probability value is 1.0, the safety margin is zero. The final output is a thermal coupling parameter set containing the lithium plating probability distribution, the safety margin index, and the original coupling parameters.

[0095] S5. Perform real-time risk quantification assessment and risk topology mapping on the thermally coupled parameter set, and output the risk topology dataset; Specifically, such as Figure 4 The steps are as follows:

[0096] S5.1 Perform probability field reconstruction and risk region extraction on the thermal coupling parameter set to generate a risk probability field matrix;

[0097] It should be noted that the lithium plating probability distribution in the thermal coupling parameter set is processed by Gaussian filtering to eliminate local noise interference and smooth the probability distribution field; continuous regions with probability values ​​exceeding the risk probability judgment threshold are extracted from the smoothed probability distribution field, marked as risk candidate regions, and their boundary coordinates are recorded; the final output is a risk probability field matrix containing the probability values ​​of all grid points and a list of risk candidate region boundaries.

[0098] It should be noted that the risk probability determination threshold is set based on the critical probability of lithium plating reaction occurring in lithium-ion batteries, with an example value range of (0.3, 0.5).

[0099] S5.2 Perform regional continuity optimization and risk intensity calibration on the risk probability field matrix, and output a comprehensive risk field matrix;

[0100] It should be pointed out that the risk probability field matrix improves the regional continuity in the lithium precipitation risk probability distribution through the morphological processing method, fills the incoherent area and connects the adjacent risk area. Further, the region where the lithium precipitation risk probability value reaches or exceeds the risk probability judgment threshold is subjected to inflation operation, which expands each risk point outward by one circle to fill the small gap between regions; then the eroded operation is performed on the inflated region to eliminate the redundant edge generated by expansion and retain the complete shape of the main risk area; finally, the adjacent risk areas are merged through neighborhood analysis to form a continuous risk belt and eliminate isolated points. The regional continuity in the lithium precipitation risk probability distribution is finally optimized; the processed lithium precipitation risk probability value is classified into risk levels according to the low probability interval and the high probability interval. The low probability interval refers to the region in the lithium precipitation risk probability field matrix where the lithium precipitation risk probability value is lower than the risk probability judgment threshold, the lithium precipitation risk is low, and the safe operation state is corresponding; the high probability interval refers to the region where the lithium precipitation risk probability value is equal to or higher than the risk probability judgment threshold, the lithium precipitation risk is large, and the high-risk state requiring intervention is corresponding. The low probability interval corresponds to the low-risk identification, and the high probability interval corresponds to the high-risk identification; finally, the comprehensive risk field matrix containing the risk intensity calibration result and the probability distribution information is output.

[0101] S5.3, risk region clustering analysis and hierarchical topology construction are performed on the comprehensive risk field matrix, and a risk topology data set is output.

[0102] It should be pointed out that the comprehensive risk field matrix is processed by a spatial clustering method, which classifies grid points with similar risk intensity values and adjacent positions into the same risk cluster; each risk cluster is divided into different levels according to the risk intensity value. The risk cluster with a risk intensity value lower than the risk probability judgment threshold is marked as the warning level (low risk), and the risk cluster with a risk intensity value equal to or higher than the risk probability judgment threshold is marked as the emergency level (high risk). The adjacency relationship table and the center point coordinate list are generated based on the spatial distribution of the risk cluster, and finally the risk topology data set containing the hierarchical risk region map, the adjacency relationship table and the risk center point coordinate list is output.

[0103] S6, cooling intensity dynamic modulation is performed according to the risk topology data set, and partition flow redistribution instructions are obtained.

[0104] S6.1, hierarchical cooling intensity mapping and battery state dynamic constraint are performed on the risk topology data set, and a cooling intensity modulation strategy table is output;

[0105] It should be pointed out that the emergency level risk area in the risk topology dataset is mapped to a high intensity cooling level, and the warning level risk area is mapped to a medium intensity cooling level; the cooling intensity mapping result is adjusted according to the battery state of charge and battery health state data, the cooling intensity coefficient of all regions is reduced in proportion when the battery state of charge value is low, and the cooling intensity increase of the emergency level risk area is reduced in proportion when the battery health state value is low; and finally a cooling intensity modulation strategy table containing the cooling intensity coefficient and adjustment parameters of each region is output.

[0106] S6.2, the cooling intensity modulation strategy table is executed to perform actuator signal conversion and safety parameter packaging, and a partition flow redistribution instruction is output.

[0107] It should be pointed out that the cooling intensity coefficient in the cooling intensity modulation strategy table is processed through the flow-control signal conversion relationship calibrated in the laboratory, the flow-control signal conversion relationship is obtained by precisely measuring the cooling liquid flow of the electromagnetic valve under different control signals and establishing a corresponding table, and the cooling intensity demand of each partition is converted into a corresponding control signal value; at the same time, the highest risk area coordinates, the global cooling intensity adjustment amplitude and the recommended charging power adjustment amplitude parameters in the cooling intensity modulation strategy table are extracted and packaged into a safety control parameter set; and finally a partition flow redistribution instruction containing the partition control signal and the safety control parameter set is output. The final output of the partition flow redistribution instruction controls the opening degree of each partition electromagnetic valve through pulse width modulation duty cycle, realizes dynamic flow distribution: higher flow (such as 300% of the reference flow) is allocated to high-risk areas, and the reference flow is maintained in low-risk areas, and the safety control parameter set is combined to dynamically limit the cooling intensity increase when the battery state is abnormal; by monitoring the temperature field change in real time and feeding back the optimized flow distribution, it is ensured that the temperature of each partition is stable within the target range.

[0108] The embodiment also provides a computer device suitable for the heat dissipation control method of the single-phase immersed liquid cooling charging pile, which comprises a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the heat dissipation control method of the single-phase immersed liquid cooling charging pile proposed in the above embodiment.

[0109] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, an operator network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0110] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the heat dissipation control method for single-phase immersion liquid-cooled charging piles proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk.

[0111] To sum up, the application achieves fine monitoring of the cold plate-battery interface contact thermal resistance by high-precision pressure field reconstruction technology, significantly improves the accuracy and reliability of pressure distribution detection, and effectively eliminates the risk of local overheating caused by assembly gaps; early prediction of lithium precipitation risk is achieved by electrochemical-thermal coupling risk modeling, which greatly improves the timeliness and accuracy of identifying thermal runaway risks, and builds a full-link intelligent heat dissipation control system from the physical layer to the electrochemical layer.

[0112] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A heat dissipation control method of a single-phase submerged liquid-cooled charging pile, characterized in that: The application relates to a battery cooling system and a cooling method thereof. Real-time acquisition of contact pressure data between the battery and the cold plate is performed, and a pressure distribution matrix is generated through visual reconstruction; A flow decision model is constructed to perform intelligent strategy mapping and dynamic threshold optimization on the pressure distribution matrix, and a partition flow control signal is generated; According to the partition flow control signal, high-precision scanning and dynamic feature extraction are performed on the built-in fiber grating array of the cold plate to obtain a temperature field matrix and a dynamic thermal feature set; The temperature field matrix and the dynamic thermal feature set are subjected to multi-dimensional fusion analysis and electrochemical coupling analysis to generate a thermal coupling parameter set; The thermal coupling parameter set is subjected to real-time risk quantification evaluation and risk topology mapping, and a risk topology data set is outputted; According to the risk topology data set, the cooling intensity is dynamically modulated to obtain a partition flow re-distribution instruction. 2.The single-phase immersion liquid-cooled charging pile heat dissipation control method of claim 1, wherein: The specific steps of generating the pressure distribution matrix are as follows, Real-time acquisition of contact pressure data between the battery and the cold plate is performed, and a temperature-compensated pressure signal array is generated through signal conditioning and dynamic compensation; Noise suppression and physical quantity calibration conversion are performed on the temperature-compensated pressure signal array to generate a physical pressure value array; The physical pressure value array is subjected to spatial interpolation expansion and gradient continuity verification to generate a contact pressure feature field; The contact pressure feature field is subjected to pressure threshold partition mapping and statistical feature integration to generate a pressure distribution matrix.

3. The single-phase immersion liquid cooling electric pile heat dissipation control method of claim 2, wherein: The flow decision model is constructed based on a sensing data layer, a strategy reasoning layer and a dynamic optimization layer.

4. The single-phase immersion liquid cooling electric pile heat dissipation control method of claim 3, wherein: The specific steps of generating the partition flow control signal are as follows, The sensing data layer extracts and vectorizes multi-dimensional features of the pressure distribution matrix to generate a pressure feature vector; The strategy reasoning layer performs intelligent strategy mapping and flow proportion distribution on the pressure feature vector to generate an initial flow proportion coefficient array; The dynamic optimization layer performs multi-source feedback optimization and dynamic threshold control on the initial flow proportion coefficient array to generate a partition flow control signal.

5. The single-phase immersion liquid cooling electric pile heat dissipation control method of claim 4, wherein: The specific steps of obtaining the temperature field matrix and the dynamic thermal feature set are as follows, Based on the partition flow control signal, synchronous scanning and spectrum-temperature conversion of the fiber grating array are performed to generate a preliminary temperature data array; The preliminary temperature data array is subjected to spatial interpolation expansion and edge optimization processing to generate a high-resolution temperature field matrix; The high-resolution temperature field matrix is subjected to thermal field dynamic characteristic analysis to generate a dynamic thermal feature set.

6. The single-phase immersion liquid-cooled charging pile heat dissipation control method of claim 5, wherein: The specific steps of generating the thermal coupling parameter set are as follows, Multi-source data space-time alignment and feature fusion are performed on the dynamic thermal feature set to generate a space-time aligned data set; Thermal-electric characteristic correlation and parameter mapping are performed on the space-time aligned data set to output a coupling parameter intermediate set; Based on the coupling parameter intermediate set, the lithium extraction probability is calculated and safety margin evaluation is performed to output a thermal coupling parameter set.

7. The single-phase immersion liquid cooling electric pile heat dissipation control method of claim 6, wherein: The specific steps of outputting the risk topology data set are as follows, The thermal coupling parameter set is subjected to probability field reconstruction and risk region extraction to generate a risk probability field matrix; The risk probability field matrix is subjected to region continuity optimization and risk intensity calibration to output a comprehensive risk field matrix; The comprehensive risk field matrix is subjected to risk region clustering analysis and hierarchical topology construction to output a risk topology data set. 8.The single-phase immersion liquid-cooled charging pile heat dissipation control method of claim 7, wherein: The specific steps of obtaining the partition flow re-distribution instruction are as follows, The risk topology dataset is subjected to graded cooling intensity mapping and battery state dynamic constraint, and a cooling intensity modulation strategy table is outputted; The cooling intensity modulation strategy table is subjected to actuator signal conversion and safety parameter packaging, and a partition flow redistribution instruction is outputted. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile according to any one of claims 1-8.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the heat dissipation control method of the single-phase immersed liquid-cooled charging pile according to any one of claims 1-8.

Images