Power battery thermal monitoring management method and system based on big data analysis

Abstract

The invention discloses a power battery thermal monitoring management method and system based on big data analysis, and particularly relates to the technical field of power battery thermal monitoring management. Multi-point temperature sensors are arranged on single power batteries, temperature distribution data of the whole power batteries are obtained in real time, and clustering analysis is carried out to calculate temperature distribution difference coefficients; the method comprises the following steps: accurately identifying the problem of abnormal temperature rise behaviors occurring in different areas of a power battery, and when the power battery has the abnormal temperature rise behaviors in the areas, obtaining fan rotating speed information of a heat dissipation control system, time sequence synchronization information between the heat dissipation control system and battery charging and discharging, and cooling liquid circulation information of the heat dissipation control system; and calculating a fan rotating speed abnormal coefficient, a time sequence synchronization coefficient and a cooling liquid circulation blocking coefficient, outputting a heat dissipation control system self-checking index, evaluating potential hidden dangers of the heat dissipation control system at the current stage, performing early warning management on the heat dissipation control system according to an evaluation result, and detecting potential faults of the heat dissipation system in time.

Description

Technical Field

[0001] The present invention relates to the technical field of power battery thermal monitoring management, and more specifically, to a power battery thermal monitoring management method and system based on big data analysis. Background Art

[0002] With the widespread use of electric vehicles and energy storage devices, the safety and performance of power batteries have become the focus of attention. Batteries generate a certain amount of heat during the charging and discharging process. Excessive temperature not only affects the cycle life of the battery, but may also cause safety accidents. Therefore, real-time monitoring and management of the temperature distribution and thermal behavior of power batteries, especially abnormal temperature increases in different areas, is the key to ensuring the safe operation of the battery system.

[0003] Existing power battery thermal monitoring and management systems mainly focus on overall battery temperature monitoring and uniform heat dissipation control. However, these systems usually have the following problems: First, the temperature distribution monitoring of different areas of the battery (such as battery cells, modules and different parts of the battery pack) is insufficient, making it difficult to identify abnormal temperature rise behavior that may exist in the power battery; second, existing heat dissipation control systems often rely on preset temperature thresholds for heat dissipation startup, but in actual operation, there is a lack of monitoring of the heat dissipation system's self-inspection and status feedback, making it difficult to promptly detect performance degradation or failure of the heat dissipation system. These problems may lead to heat dissipation failure, local overheating, and battery performance degradation, thus affecting the safety and service life of the battery. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a power battery thermal monitoring management method and system based on big data analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The power battery thermal monitoring management method based on big data analysis includes the following steps:

[0007] Step S1, by arranging multiple temperature sensors on the power battery cells, collecting temperature distribution data of the power battery in real time, and analyzing the regional abnormal temperature rise behavior of the temperature distribution data of the power battery;

[0008] Step S2, when there is abnormal temperature rise in a region of the power battery, obtain the fan speed information of the heat dissipation control system, and calculate the fan speed abnormality coefficient according to the fan speed information of the heat dissipation control system;

[0009] Step S3, when there is abnormal temperature rise in a region of the power battery, obtaining timing synchronization information between the heat dissipation control system and the battery charging and discharging, and calculating a timing synchronization coefficient according to the timing synchronization information between the heat dissipation control system and the battery charging and discharging;

[0010] Step S4, when there is abnormal temperature rise in a region of the power battery, obtain coolant flow information of the heat dissipation control system, and calculate the coolant flow blockage coefficient according to the coolant flow information of the heat dissipation control system;

[0011] Step S5, constructing a heat dissipation control system self-check model according to the fan speed abnormality coefficient, timing synchronization coefficient, and coolant flow blockage coefficient, outputting the heat dissipation control system self-check index, evaluating the potential hidden dangers of the heat dissipation control system at the current stage, and performing early warning management of the heat dissipation control system according to the evaluation results.

[0012] In a preferred embodiment, the temperature distribution data of the power battery includes temperature data of different sub-areas;

[0013] The abnormal temperature rise behavior of the region is identified based on the temperature distribution data of the power battery, as follows:

[0014] Step A1: Create a temperature clustering dataset {wd i}={wd1,wd2,...,wd I}, where wd i represents the temperature of the i-th sub-region, i∈{1,2,...,I};

[0015] Step A2, using the elbow rule to determine the number of initial clusters K, randomly selecting the temperatures of K sub-regions from the temperature clustering data set as initial clusters, and using the temperatures of the sub-regions as the cluster centers of the initial clusters;

[0016] Step A3, using the Euclidean distance calculation method to calculate the distance between the temperature of each sub-region in the temperature clustering data set and the cluster center of each cluster, and assigning it to the cluster with the smallest distance;

[0017] Step A4, calculating the average temperature of the sub-regions in each cluster, and using it as the cluster center of the cluster;

[0018] Step A4, repeating steps A3 and A4 until the cluster center no longer changes, then the clustering process ends and the final temperature distribution cluster is obtained;

[0019] Calculate the temperature distribution cluster JL separately n and temperature distribution cluster JL m mean and standard deviation of interior temperature;

[0020] Calculate the nth temperature distribution cluster JL n Cluster JL with the mth temperature distribution m The difference value CY nm , the expression is as follows where σC n Represents the nth temperature distribution cluster JL n Standard deviation of internal temperature, σC m Represents the mth temperature distribution cluster JL m Standard deviation of internal temperature, TC n Represents the nth temperature distribution cluster JL n The mean internal temperature, TC m Represents the mth temperature distribution cluster JL m The mean value of the internal temperature, ∈ represents the minimum constant factor to avoid the denominator being zero;

[0021] Calculate the temperature distribution difference coefficient Wdc, the expression is as follows Where n∈{1,2,...,N}, N is the total number of final temperature distribution clusters.

[0022] In a preferred embodiment, the temperature distribution difference coefficient is compared with a preset temperature distribution difference coefficient threshold to identify the abnormal temperature rise behavior of the region, as follows:

[0023] If the temperature distribution difference coefficient is greater than the temperature distribution difference coefficient threshold, a regional abnormal temperature rise behavior signal is generated; if the temperature distribution difference coefficient is less than or equal to the temperature distribution difference coefficient threshold, there is no need to generate a regional abnormal temperature rise behavior signal.

[0024] In a preferred embodiment, the abnormal degree of the fan speed of the heat dissipation control system is measured by acquiring the fan speed information of the heat dissipation control system, analyzing the abnormal degree of the fan speed of the heat dissipation control system, and acquiring the abnormal coefficient of the fan speed;

[0025] The logic for obtaining the fan speed abnormality coefficient is as follows:

[0026] The actual speed Ract of the fan is obtained through the real-time monitoring system, and the normal speed range [Rmin, Rmax] of the fan is obtained, where Rmin is the lowest speed of the fan under normal circumstances, and Rmax is the highest speed of the fan under normal circumstances; the expected average speed Ravg of the fan is calculated, and the expression is as follows Calculate the standard deviation of the actual fan speed σfan, the expression is as follows Ract j represents the actual speed of the fan at the jth sampling point, Indicates the average value of the actual fan speed. The calculation expression is as follows Where j∈{1,2,...,J}, J is the total number of sampling points; calculate the fan speed abnormality coefficient Fsyc, the expression is as follows Where ΔR represents the fan speed change rate, and θ is the sensitivity factor that controls the degree of influence of the fan speed change rate on the fan speed abnormality coefficient.

[0027] In a preferred embodiment, by acquiring the timing synchronization information between the heat dissipation control system and the battery charging and discharging, analyzing the timing synchronization between the heat dissipation control system and the battery charging and discharging, and acquiring the timing synchronization coefficient, the timing synchronization between the heat dissipation control system and the battery charging and discharging is measured;

[0028] The logic for obtaining the timing synchronization coefficient is as follows:

[0029] Obtain the response time Tcooling of the cooling system to start controlling the battery temperature and the generation time Theat of the regional abnormal temperature rise behavior signal, and calculate the cooling response delay ΔTresponse, which is expressed as follows: ΔTresponse = Tcooling - Theat;

[0030] Obtain the battery charging process duration ΔTcharge and the discharge process duration ΔTdischarge, and calculate the total charge and discharge time ΔT of the battery. The expression is as follows: ΔT = ΔTcharge + ΔTdischarge;

[0031] Calculate the timing synchronization coefficient Sxtb, the expression is as follows

[0032] In a preferred embodiment, the coolant circulation information of the heat dissipation control system is obtained, the smoothness of the coolant circulation is analyzed, and the coolant circulation blockage coefficient is obtained to measure the smoothness of the coolant circulation;

[0033] The logic for obtaining the coolant flow blockage coefficient is as follows:

[0034] The coolant density ρcool, coolant flow rate Vflow, pipe inner diameter Dpipe, and coolant viscosity μcoolant are obtained through the monitoring system, and the coolant Reynolds coefficient Re is calculated. The expression is as follows The coolant flow type is classified according to the coolant Reynolds coefficient as follows Calculate the coolant flow blockage coefficient Lque, the expression is as follows Transitional flow, where Lc is the length of the pipe, Qt is the volume flow rate of the coolant, fturbulent is the friction factor of turbulent flow, and flaminar is the friction factor of laminar flow.

[0035] In a preferred embodiment, a heat dissipation control system self-check model is constructed based on the fan speed abnormality coefficient, the timing synchronization coefficient, and the coolant flow blockage coefficient, and a heat dissipation control system self-check index CI is output. The model is based on the following formula: Where Wdc z It represents the temperature distribution difference coefficient corresponding to the generation of the regional abnormal temperature rise behavior signal, Fsyc, Sxtb, and Lque represent the fan speed abnormality coefficient, the timing synchronization coefficient, and the coolant circulation blockage coefficient, respectively, and a1, a2, and a3 represent the preset proportional coefficients of the fan speed abnormality coefficient, the timing synchronization coefficient, and the coolant circulation blockage coefficient, respectively, and a1, a2, and a3 are all greater than 0.

[0036] In a preferred embodiment, the heat dissipation control system self-check index is compared with a preset heat dissipation control system self-check index threshold, and early warning management of the heat dissipation control system is performed;

[0037] If the heat dissipation control system self-test index is greater than the heat dissipation control system self-test index threshold, a high-risk warning is immediately triggered; if the heat dissipation control system self-test index is less than or equal to the heat dissipation control system self-test index threshold, there is no need to trigger a high-risk warning.

[0038] In a preferred embodiment, the power battery thermal monitoring and management system based on big data analysis includes a regional abnormal temperature rise module, a fan abnormal speed module, a timing synchronization module, a coolant circulation module, and an early warning management module;

[0039] The regional abnormal temperature rise module is used to collect the temperature distribution data of the power battery in real time by arranging multiple temperature sensors on the power battery cells, and analyze the regional abnormal temperature rise behavior of the power battery temperature distribution data;

[0040] The fan abnormal speed module is used to obtain the fan speed information of the heat dissipation control system when there is abnormal temperature rise in a certain area of ​​the power battery, and calculate the fan speed abnormality coefficient according to the fan speed information of the heat dissipation control system;

[0041] A timing synchronization module is used to obtain timing synchronization information between the heat dissipation control system and the battery charging and discharging when there is abnormal temperature rise in a region of the power battery, and calculate the timing synchronization coefficient based on the timing synchronization information between the heat dissipation control system and the battery charging and discharging;

[0042] A coolant circulation module is used to obtain the coolant circulation information of the heat dissipation control system when there is an abnormal temperature rise behavior in a region of the power battery, and calculate the coolant circulation blockage coefficient according to the coolant circulation information of the heat dissipation control system;

[0043] The early warning management module is used to build a self-check model of the heat dissipation control system according to the fan speed abnormality coefficient, timing synchronization coefficient, and coolant circulation blockage coefficient, output the heat dissipation control system self-check index, evaluate the potential hidden dangers of the heat dissipation control system at the current stage, and perform early warning management of the heat dissipation control system based on the evaluation results.

[0044] Technical effects and advantages of the present invention:

[0045] 1. The present invention arranges multiple temperature sensors on the power battery cells to obtain the temperature distribution data of the entire power battery in real time, and calculates the temperature distribution difference coefficient by clustering the temperature distribution data, so as to accurately identify the abnormal temperature rise behavior between different regions of the power battery. When the power battery has regional abnormal temperature rise behavior, the fan speed information of the heat dissipation control system is obtained, and the fan speed abnormality coefficient is calculated according to the fan speed information of the heat dissipation control system, the timing synchronization information between the heat dissipation control system and the battery charging and discharging is obtained, and the timing synchronization coefficient is calculated according to the timing synchronization information between the heat dissipation control system and the battery charging and discharging, the coolant circulation information of the heat dissipation control system is obtained, and the coolant circulation information of the heat dissipation control system is calculated according to the coolant circulation information of the heat dissipation control system. The coolant circulation blockage coefficient builds a cooling control system self-check model based on the fan speed abnormality coefficient, timing synchronization coefficient, and coolant circulation blockage coefficient, outputs the cooling control system self-check index, evaluates the potential hidden dangers of the cooling control system at the current stage, and performs early warning management of the cooling control system based on the evaluation results, and promptly detects potential failures of the cooling system. It can also monitor the operating performance of the cooling system in real time, and promptly discover problems such as abnormal fan speed and poor coolant circulation, provide a scientific basis for early warning management of the cooling system, avoid cooling failure or system performance degradation, and prevent safety hazards caused by cooling system failure or performance degradation, thereby effectively improving the safety, reliability and service life of the power battery, and avoiding battery accidents and performance degradation caused by overheating. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0047] Figure 1 This is a flow chart of the method of embodiment 1 of the present invention;

[0048] Figure 2 This is a flow chart of the system of Example 2 of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Embodiment 1: Figure 1 The present invention provides a power battery thermal monitoring management method based on big data analysis, which includes the following steps:

[0051] Step S1, by arranging multiple temperature sensors on the power battery cells, collecting temperature distribution data of the power battery in real time, and analyzing the regional abnormal temperature rise behavior of the temperature distribution data of the power battery;

[0052] Step S2, when there is abnormal temperature rise in a region of the power battery, obtain the fan speed information of the heat dissipation control system, and calculate the fan speed abnormality coefficient according to the fan speed information of the heat dissipation control system;

[0053] Step S3, when there is abnormal temperature rise in a region of the power battery, obtaining timing synchronization information between the heat dissipation control system and the battery charging and discharging, and calculating a timing synchronization coefficient according to the timing synchronization information between the heat dissipation control system and the battery charging and discharging;

[0054] Step S4, when there is abnormal temperature rise in a region of the power battery, obtain coolant flow information of the heat dissipation control system, and calculate the coolant flow blockage coefficient according to the coolant flow information of the heat dissipation control system;

[0055] Step S5, constructing a heat dissipation control system self-check model according to the fan speed abnormality coefficient, the timing synchronization coefficient, and the coolant circulation blockage coefficient, outputting a heat dissipation control system self-check index, evaluating the potential hidden dangers of the heat dissipation control system at the current stage, and performing early warning management of the heat dissipation control system according to the evaluation results;

[0056] In step S1, multiple temperature sensors are arranged on the power battery cells to collect temperature distribution data of the power battery in real time, and the abnormal temperature rise behavior of the region is identified according to the temperature distribution data of the power battery;

[0057] By arranging multiple temperature sensors on the power battery cell, it is necessary to ensure that the arrangement of the temperature sensors should cover all areas of the entire power battery cell, and divide all areas of the power battery cell into multiple sub-areas according to the working coverage of each temperature sensor;

[0058] The temperature distribution data of the power battery includes temperature data of different sub-areas;

[0059] The abnormal temperature rise behavior of the region is identified based on the temperature distribution data of the power battery, as follows:

[0060] Step A1: Create a temperature clustering dataset {wd i}={wd1,wd2,...,wd I}, where wd i represents the temperature of the i-th sub-region, i∈{1,2,...,I};

[0061] Step A2, using the elbow rule to determine the number of initial clusters K, randomly selecting the temperatures of K sub-regions from the temperature clustering data set as initial clusters, and using the temperatures of the sub-regions as the cluster centers of the initial clusters;

[0062] Step A3, using the Euclidean distance calculation method to calculate the distance between the temperature of each sub-region in the temperature clustering data set and the cluster center of each cluster, and assigning it to the cluster with the smallest distance;

[0063] Step A4, calculating the average temperature of the sub-regions in each cluster, and using it as the cluster center of the cluster;

[0064] Step A4, repeating steps A3 and A4 until the cluster center no longer changes, then the clustering process ends and the final temperature distribution cluster is obtained;

[0065] It should be noted that, after the above cluster analysis, different sub-regions of the power battery are aggregated based on the similarity of temperature, and each temperature distribution cluster contains the temperatures of multiple sub-regions, which means that the temperatures of these sub-regions are similar;

[0066] Calculate the temperature distribution cluster JL separately n and temperature distribution cluster JL m mean and standard deviation of interior temperature;

[0067] Calculate the nth temperature distribution cluster JL n Cluster JL with the mth temperature distribution m The difference value CY nm , the expression is as follows where σC n Represents the nth temperature distribution cluster JL n Standard deviation of internal temperature, σC m Represents the mth temperature distribution cluster JL m Standard deviation of internal temperature, TC n Represents the nth temperature distribution cluster JL n The mean internal temperature, TC m Represents the mth temperature distribution cluster JL mThe mean value of the internal temperature, ε represents the minimum constant factor to avoid the denominator being zero;

[0068] Calculate the temperature distribution difference coefficient Wdc, the expression is as follows Where n∈{1,2,...,N}, N is the total number of final temperature distribution clusters;

[0069] The temperature distribution difference coefficient is compared with the preset temperature distribution difference coefficient threshold to identify the abnormal temperature rise behavior of the region, as follows:

[0070] If the temperature distribution difference coefficient is greater than the temperature distribution difference coefficient threshold, it means that not only the temperature difference between different temperature distribution clusters is large, but also the temperature fluctuation of each cluster is large, indicating that abnormal temperature rise behavior occurs between different regions of the power battery, and a regional abnormal temperature rise behavior signal is generated; if the temperature distribution difference coefficient is less than or equal to the temperature distribution difference coefficient threshold, it means that the temperature difference between different temperature distribution clusters is small, and the temperature fluctuation within the cluster is also small, and the temperature distribution of the power battery is relatively uniform, and there is no need to generate a regional abnormal temperature rise behavior signal;

[0071] Step S2, when there is abnormal temperature rise in a region of the power battery, obtain the fan speed information of the heat dissipation control system, and calculate the fan speed abnormality coefficient according to the fan speed information of the heat dissipation control system;

[0072] The fan speed abnormality coefficient is an indicator used to measure the degree of abnormal fan speed in the heat dissipation control system. It is used to evaluate whether the fan is operating normally and whether there is a heat dissipation problem caused by too low or too high fan speed. It can directly reflect the fan operation status of the heat dissipation control system. If the fan speed is abnormal, it may mean that there is a fault or insufficiency in the heat dissipation system, which in turn affects the heat dissipation efficiency of the battery, causing local temperature rise and increasing the risk of battery overheating. By calculating the fan speed abnormality coefficient, fan performance problems can be identified early, such as too low speed or too large fluctuations. These problems may be caused by fan failure, unstable power supply or control system problems. Secondly, the monitoring of the fan speed abnormality coefficient provides a basis for timely adjustment of the heat dissipation strategy. For example, when the fan speed abnormality coefficient exceeds the standard, the system can trigger an alarm mechanism to warn the operation and maintenance personnel in advance to inspect or adjust the fan or heat dissipation system to prevent battery overheating, performance degradation or safety hazards caused by insufficient heat dissipation. Through this active monitoring, equipment failures caused by unstable heat dissipation systems can be greatly reduced, thereby improving the overall safety and service life of batteries. In addition, the fan speed abnormality coefficient can also provide data support for subsequent heat dissipation optimization decisions. For example, when an abnormal fan speed is detected, a comprehensive analysis can be performed in combination with other parameters (such as temperature sensor data) to evaluate whether it is necessary to increase the number of fans, adjust the fan speed range, or optimize the design of the cooling system. By continuously tracking and analyzing the fan speed abnormality coefficient, dynamic adjustment of the cooling system can be achieved to ensure that the battery is always within a safe temperature control range, avoiding long-term performance degradation or unexpected failures caused by excessive temperature.

[0073] Therefore, by acquiring the fan speed information of the heat dissipation control system, analyzing the abnormal degree of the fan speed of the heat dissipation control system, and acquiring the fan speed abnormality coefficient, the abnormal degree of the fan speed of the heat dissipation control system is measured;

[0074] The logic for obtaining the fan speed abnormality coefficient is as follows:

[0075] The actual speed Ract of the fan is obtained through the real-time monitoring system, and the normal speed range [Rmin, Rmax] of the fan is obtained, where Rmin is the lowest speed of the fan under normal circumstances, and Rmax is the highest speed of the fan under normal circumstances; the expected average speed Ravg of the fan is calculated, and the expression is as follows Calculate the standard deviation of the actual fan speed σfan, the expression is as follows Ract j represents the actual speed of the fan at the jth sampling point, Indicates the average value of the actual fan speed. The calculation expression is as follows Where j∈{1,2,...,J}, J is the total number of sampling points; calculate the fan speed abnormality coefficient Fsyc, the expression is as follows Where ΔR represents the fan speed change rate, and θ is the sensitivity factor that controls the degree of influence of the fan speed change rate on the fan speed abnormality coefficient;

[0076] It should be noted that the fan speed change rate is the difference change of adjacent sampling points in unit time, which can be obtained by performing a ratio calculation based on the difference of the actual fan speeds of adjacent sampling points and the sampling time interval;

[0077] Step S3, when there is abnormal temperature rise in a region of the power battery, obtaining timing synchronization information between the heat dissipation control system and the battery charging and discharging, and calculating a timing synchronization coefficient according to the timing synchronization information between the heat dissipation control system and the battery charging and discharging;

[0078] The timing synchronization coefficient is an important indicator used to measure the timing synchronization between the heat dissipation control system and the battery charging and discharging process. It is used to describe the time difference between the battery heat generation and the heat dissipation system response during the charging and discharging process. If the heat dissipation control system lags behind the increase in battery temperature, or reacts too slowly, the battery temperature will be too high, increasing the risk of overheating and even affecting the safety and life of the battery. The purpose is to quantify how the heat dissipation control system matches the timing of the battery heat generation during the charging and discharging process. By calculating the timing synchronization coefficient, it can be found whether the heat dissipation system can respond to the battery's heat changes in a timely manner to ensure the temperature control of the battery during the charging and discharging process. It can effectively identify the problem of lagging response of the heat dissipation system, thereby predicting and avoiding possible overheating risks in advance. By quantifying the timing synchronization between the heat dissipation control system and the battery charging and discharging, it can be ensured that the heat dissipation system can respond quickly at the moment when the battery generates significant heat, avoiding excessive battery temperature due to response delay. If the timing synchronization coefficient is large, it indicates that the heat dissipation system fails to respond to the battery temperature change in time, and there is a potential hidden danger. At this time, the heat dissipation strategy can be adjusted or the charging and discharging process can be optimized to improve the response speed of the heat dissipation system, thereby effectively reducing the risk of overheating and ensuring the safety and stability of the battery. At the same time, by evaluating the timing synchronization coefficient, the efficiency of the cooling system can be improved, unnecessary energy waste can be avoided, more accurate temperature control management can be achieved, battery life can be extended, and the overall reliability of the system can be improved. This evaluation method based on the timing synchronization coefficient can not only improve the real-time monitoring capability of the battery management system, but also ensure that the system can maintain safe and stable operation under high load by early warning of potential risks;

[0079] Therefore, by acquiring the timing synchronization information between the heat dissipation control system and the battery charging and discharging, the timing synchronization between the heat dissipation control system and the battery charging and discharging is analyzed, and the timing synchronization coefficient is obtained to measure the timing synchronization between the heat dissipation control system and the battery charging and discharging;

[0080] The logic for obtaining the timing synchronization coefficient is as follows:

[0081] Obtain the response time Tcooling of the cooling system to start controlling the battery temperature and the generation time Theat of the regional abnormal temperature rise behavior signal, and calculate the cooling response delay ΔTresponse, which is expressed as follows: ΔTresponse = Tcooling - Theat;

[0082] Obtain the battery charging process duration ΔTcharge and the discharge process duration ΔTdischarge, and calculate the total charge and discharge time ΔT of the battery. The expression is as follows: ΔT = ΔTcharge + ΔTdischarge;

[0083] Calculate the timing synchronization coefficient Sxtb, the expression is as follows

[0084] Step S4, when there is abnormal temperature rise in a region of the power battery, obtain coolant flow information of the heat dissipation control system, and calculate the coolant flow blockage coefficient according to the coolant flow information of the heat dissipation control system;

[0085] The coolant flow blockage coefficient is used to measure the degree of smoothness of coolant flow in the heat dissipation control system, reflecting the possible flow resistance or flow obstacles in the heat dissipation control system. The coolant plays an important role in the heat dissipation process. If the flow is not smooth or blocked, the heat dissipation effect will be greatly reduced, thereby affecting the effect of battery temperature control and increasing the risk of overheating. Therefore, the calculation and evaluation of the coolant flow blockage coefficient is crucial to the healthy management of the heat dissipation system. The smaller the coolant flow blockage coefficient, the smaller the coolant flow resistance, the heat dissipation system can dissipate heat more smoothly, and the heat dissipation efficiency is good; the larger the coolant flow blockage coefficient, the coolant flow is blocked, and there may be problems such as blockage, pipe bending, and insufficient flow rate, resulting in poor heat dissipation effect and increased risk of temperature rise. Through the calculation and evaluation of the coolant flow blockage coefficient, the obstacles to the coolant flow in the heat dissipation control system can be discovered in time. If the coolant flow blockage coefficient is large, it may indicate that the coolant flow is blocked, resulting in inefficient heat dissipation system, and may even cause battery overheating, damage or safety accidents. Therefore, the coolant flow blockage coefficient can not only help monitor the health of the cooling system in real time, but also provide an early warning basis for preventing overheating and guide relevant personnel to perform necessary maintenance or optimization operations.

[0086] Therefore, by acquiring the coolant flow information of the heat dissipation control system, analyzing the smoothness of the coolant flow, and obtaining the coolant flow blockage coefficient, the smoothness of the coolant flow is measured;

[0087] The logic for obtaining the coolant flow blockage coefficient is as follows:

[0088] The coolant density ρcool, coolant flow rate Vflow, pipe inner diameter Dpipe, and coolant viscosity μcoolant are obtained through the monitoring system, and the coolant Reynolds coefficient Re is calculated. The expression is as follows The coolant flow type is classified according to the coolant Reynolds coefficient as follows Calculate the coolant flow blockage coefficient Lque, the expression is as follows Transitional flow, where Lc is the length of the pipe, Qt is the volume flow rate of the coolant, fturbulent is the friction factor of turbulent flow, and flaminar is the friction factor of laminar flow;

[0089] It should be noted that the friction factor of turbulent and laminar flow can be calculated by solving the Colebrook-White equation, which is as follows: Where τ is the relative roughness of the pipeline, and f represents the friction factor;

[0090] Step S5, constructing a heat dissipation control system self-check model according to the fan speed abnormality coefficient, the timing synchronization coefficient, and the coolant circulation blockage coefficient, outputting a heat dissipation control system self-check index, evaluating the potential hidden dangers of the heat dissipation control system at the current stage, and performing early warning management of the heat dissipation control system according to the evaluation results;

[0091] The heat dissipation control system self-check model is constructed based on the fan speed abnormality coefficient, timing synchronization coefficient, and coolant flow blockage coefficient, and the heat dissipation control system self-check index CI is output. The model is based on the following formula Where Wdc z represents the temperature distribution difference coefficient corresponding to the generation of the regional abnormal temperature rise behavior signal, Fsyc, Sxtb, Lque represent the fan speed abnormality coefficient, timing synchronization coefficient, coolant circulation blockage coefficient, a1, a2, a3 represent the preset proportional coefficients of the fan speed abnormality coefficient, timing synchronization coefficient, coolant circulation blockage coefficient, and a1, a2, a3 are all greater than 0;

[0092] It should be noted that before building the self-check model of the heat dissipation control system, it is necessary to ensure that the fan speed abnormality coefficient, timing synchronization coefficient, coolant flow blockage coefficient, and the temperature distribution difference coefficient corresponding to the generation of the regional abnormal temperature rise behavior signal are all normalized; a1, a2, and a3 are set according to the actual situation. For example, the expert empowerment method is adopted, that is, experts in related fields are invited to determine the preset proportional coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0093] It can be seen from the above calculation expression that the larger the fan speed abnormality coefficient, the larger the timing synchronization coefficient, the larger the coolant circulation blockage coefficient, the larger the temperature distribution difference coefficient corresponding to the generation of the regional abnormal temperature rise behavior signal, and the larger the heat dissipation control system self-check index, indicating that the current heat dissipation control system has the greater potential hidden dangers and may not be able to effectively deal with the abnormal temperature rise behavior problems occurring between different areas of the power battery. On the contrary, the smaller the fan speed abnormality coefficient, the smaller the timing synchronization coefficient, the smaller the coolant circulation blockage coefficient, the smaller the temperature distribution difference coefficient corresponding to the generation of the regional abnormal temperature rise behavior signal, and the smaller the heat dissipation control system self-check index, indicating that the current heat dissipation control system has the smaller potential hidden dangers and the current stage of the heat dissipation system can more effectively deal with the abnormal temperature rise behavior problems occurring between different areas of the power battery.

[0094] Compare the heat dissipation control system self-check index with a preset heat dissipation control system self-check index threshold to perform early warning management on the heat dissipation control system;

[0095] If the heat dissipation control system self-check index is greater than the heat dissipation control system self-check index threshold, a high-risk warning is immediately triggered. At this time, the warning information will be notified to the relevant operators or technical support team through the monitoring system, alarm system or maintenance platform; if the heat dissipation control system self-check index is less than or equal to the heat dissipation control system self-check index threshold, it means that the heat dissipation control system has no significant potential hidden dangers at the current stage, the system's heat dissipation performance and operating status are normal, and it can effectively deal with the abnormal temperature rise behavior problems between different areas of the power battery, and there is no need to trigger a high-risk warning;

[0096] The present invention arranges multiple temperature sensors on the power battery cells to obtain the temperature distribution data of the entire power battery in real time, and calculates the temperature distribution difference coefficient by clustering analysis on the temperature distribution data, so as to accurately identify the problem of abnormal temperature rise behavior between different areas of the power battery. When the power battery has regional abnormal temperature rise behavior, the fan speed information of the heat dissipation control system is obtained, and the fan speed abnormality coefficient is calculated according to the fan speed information of the heat dissipation control system, the timing synchronization information between the heat dissipation control system and the battery charging and discharging is obtained, and the timing synchronization coefficient is calculated according to the timing synchronization information between the heat dissipation control system and the battery charging and discharging, the coolant circulation information of the heat dissipation control system is obtained, and the coolant circulation information of the heat dissipation control system is calculated according to the coolant circulation information of the heat dissipation control system Coolant circulation blockage coefficient, build a cooling control system self-check model according to the fan speed abnormality coefficient, timing synchronization coefficient and coolant circulation blockage coefficient, output the cooling control system self-check index, evaluate the potential hidden dangers of the cooling control system at the current stage, and carry out early warning management of the cooling control system according to the evaluation results, timely detect potential failures of the cooling system, and monitor the operating performance of the cooling system in real time, and promptly discover problems such as abnormal fan speed and poor coolant circulation, provide a scientific basis for early warning management of the cooling system, avoid cooling failure or system performance degradation, and prevent safety hazards caused by cooling system failure or performance degradation, thereby effectively improving the safety, reliability and service life of the power battery, and avoiding battery accidents and performance degradation caused by overheating.

[0097] Example 2: This example is an introduction to a power battery thermal monitoring and management system based on big data analysis. Figure 2 As shown, it includes a regional abnormal temperature rise module, a fan abnormal speed module, a timing synchronization module, a coolant circulation module, and an early warning management module;

[0098] The regional abnormal temperature rise module is used to collect the temperature distribution data of the power battery in real time by arranging multiple temperature sensors on the power battery cells, and analyze the regional abnormal temperature rise behavior of the power battery temperature distribution data;

[0099] The fan abnormal speed module is used to obtain the fan speed information of the heat dissipation control system when there is abnormal temperature rise in a certain area of ​​the power battery, and calculate the fan speed abnormality coefficient according to the fan speed information of the heat dissipation control system;

[0100] A timing synchronization module is used to obtain timing synchronization information between the heat dissipation control system and the battery charging and discharging when there is abnormal temperature rise in a region of the power battery, and calculate the timing synchronization coefficient based on the timing synchronization information between the heat dissipation control system and the battery charging and discharging;

[0101] A coolant circulation module is used to obtain the coolant circulation information of the heat dissipation control system when there is an abnormal temperature rise behavior in a region of the power battery, and calculate the coolant circulation blockage coefficient according to the coolant circulation information of the heat dissipation control system;

[0102] The early warning management module is used to build a self-check model of the heat dissipation control system according to the fan speed abnormality coefficient, timing synchronization coefficient, and coolant circulation blockage coefficient, output the heat dissipation control system self-check index, evaluate the potential hidden dangers of the heat dissipation control system at the current stage, and perform early warning management of the heat dissipation control system based on the evaluation results.

[0103] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0104] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0105] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0106] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and method described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0107] In several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways.

[0108] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A power battery thermal monitoring management method based on big data analysis, characterized in that: The steps include: Step S1, by arranging multiple temperature sensors on the power battery cells, collecting temperature distribution data of the power battery in real time, and analyzing the regional abnormal temperature rise behavior of the temperature distribution data of the power battery; Step S2, when there is abnormal temperature rise in a region of the power battery, obtain the fan speed information of the heat dissipation control system, and calculate the fan speed abnormality coefficient according to the fan speed information of the heat dissipation control system; Step S3, when there is abnormal temperature rise in a region of the power battery, obtaining timing synchronization information between the heat dissipation control system and the battery charging and discharging, and calculating a timing synchronization coefficient according to the timing synchronization information between the heat dissipation control system and the battery charging and discharging; Step S4, when there is abnormal temperature rise in a region of the power battery, obtain coolant flow information of the heat dissipation control system, and calculate the coolant flow blockage coefficient according to the coolant flow information of the heat dissipation control system; Step S5, constructing a heat dissipation control system self-check model according to the fan speed abnormality coefficient, timing synchronization coefficient, and coolant flow blockage coefficient, outputting the heat dissipation control system self-check index, evaluating the potential hidden dangers of the heat dissipation control system at the current stage, and performing early warning management of the heat dissipation control system according to the evaluation results.

2. The power battery thermal monitoring management method based on big data analysis according to claim 1 is characterized in that: The temperature distribution data of the power battery includes temperature data of different sub-areas; The abnormal temperature rise behavior of the region is identified based on the temperature distribution data of the power battery, as follows: Step A1: Create a temperature clustering dataset {wd i }={wd1,wd2,...,wd I }, where wd i represents the temperature of the i-th sub-region, i∈{1,2,...,I}; Step A2, using the elbow rule to determine the number of initial clusters K, randomly selecting the temperatures of K sub-regions from the temperature clustering data set as initial clusters, and using the temperatures of the sub-regions as the cluster centers of the initial clusters; Step A3, using the Euclidean distance calculation method to calculate the distance between the temperature of each sub-region in the temperature clustering data set and the cluster center of each cluster, and assigning it to the cluster with the smallest distance; Step A4, calculating the average temperature of the sub-regions in each cluster, and using it as the cluster center of the cluster; Step A4, repeating steps A3 and A4 until the cluster center no longer changes, then the clustering process ends and the final temperature distribution cluster is obtained; Calculate the temperature distribution cluster JL separately n and temperature distribution cluster JL m mean and standard deviation of interior temperature; Calculate the nth temperature distribution cluster JL n Cluster JL with the mth temperature distribution m The difference value CY nm , the expression is as follows where σC n Represents the nth temperature distribution cluster JL n Standard deviation of internal temperature, σC m Represents the mth temperature distribution cluster JL m Standard deviation of internal temperature, TC n Represents the nth temperature distribution cluster JL n The mean internal temperature, TC m Represents the mth temperature distribution cluster JL m The mean value of the internal temperature, ∈ represents the minimum constant factor to avoid the denominator being zero; Calculate the temperature distribution difference coefficient Wdc, the expression is as follows Where n∈{1,2,...,N}, N is the total number of final temperature distribution clusters.

3. The power battery thermal monitoring management method based on big data analysis according to claim 2 is characterized in that: The temperature distribution difference coefficient is compared with the preset temperature distribution difference coefficient threshold to identify the abnormal temperature rise behavior of the region, as follows: If the temperature distribution difference coefficient is greater than the temperature distribution difference coefficient threshold, a regional abnormal temperature rise behavior signal is generated; if the temperature distribution difference coefficient is less than or equal to the temperature distribution difference coefficient threshold, there is no need to generate a regional abnormal temperature rise behavior signal.

4. The power battery thermal monitoring management method based on big data analysis according to claim 1 is characterized in that: By acquiring fan speed information of the heat dissipation control system, analyzing the abnormal degree of the fan speed of the heat dissipation control system, and acquiring the fan speed abnormality coefficient, the abnormal degree of the fan speed of the heat dissipation control system is measured; The logic for obtaining the fan speed abnormality coefficient is as follows: The actual speed Ract of the fan is obtained through the real-time monitoring system, and the normal speed range [Rmin, Rmax] of the fan is obtained, where Rmin is the lowest speed of the fan under normal circumstances, and Rmax is the highest speed of the fan under normal circumstances; the expected average speed Ravg of the fan is calculated, and the expression is as follows Calculate the standard deviation of the actual fan speed σfan, the expression is as follows Ract j represents the actual speed of the fan at the jth sampling point, Indicates the average value of the actual fan speed. The calculation expression is as follows Where j∈{1,2,...,J}, J is the total number of sampling points; calculate the fan speed abnormality coefficient Fsyc, the expression is as follows Where ΔR represents the fan speed change rate, and θ is the sensitivity factor that controls the degree of influence of the fan speed change rate on the fan speed abnormality coefficient.

5. The power battery thermal monitoring management method based on big data analysis according to claim 1 is characterized in that: By acquiring the timing synchronization information between the heat dissipation control system and the battery charging and discharging, the timing synchronization between the heat dissipation control system and the battery charging and discharging is analyzed, and the timing synchronization coefficient is obtained to measure the timing synchronization between the heat dissipation control system and the battery charging and discharging; The logic for obtaining the timing synchronization coefficient is as follows: Obtain the response time Tcooling of the cooling system to start controlling the battery temperature and the generation time Theat of the regional abnormal temperature rise behavior signal, and calculate the cooling response delay ΔTresponse, which is expressed as follows: ΔTresponse = Tcooling - Theat; Obtain the battery charging process duration ΔTcharge and the discharge process duration ΔTdischarge, and calculate the total charge and discharge time ΔT of the battery. The expression is as follows: ΔT = ΔTcharge + ΔTdischarge; Calculate the timing synchronization coefficient Sxtb, the expression is as follows 6. The power battery thermal monitoring management method based on big data analysis according to claim 1 is characterized in that: By acquiring the coolant flow information of the heat dissipation control system, analyzing the smoothness of the coolant flow, and obtaining the coolant flow blockage coefficient, the smoothness of the coolant flow is measured; The logic for obtaining the coolant flow blockage coefficient is as follows: The coolant density ρcool, coolant flow rate Vflow, pipe inner diameter Dpipe, and coolant viscosity μcoolant are obtained through the monitoring system, and the coolant Reynolds coefficient Re is calculated. The expression is as follows The coolant flow type is classified according to the coolant Reynolds coefficient as follows Calculate the coolant flow blockage coefficient Lque, the expression is as follows Transitional flow, where Lc is the length of the pipe, Qt is the volume flow rate of the coolant, fturbulent is the friction factor of turbulent flow, and flaminar is the friction factor of laminar flow.

7. The power battery thermal monitoring management method based on big data analysis according to claim 1 is characterized in that: The heat dissipation control system self-check model is constructed based on the fan speed abnormality coefficient, timing synchronization coefficient, and coolant flow blockage coefficient, and the heat dissipation control system self-check index CI is output. The model is based on the following formula Where Wdc z It represents the temperature distribution difference coefficient corresponding to the generation of the regional abnormal temperature rise behavior signal, Fsyc, Sxtb, and Lque represent the fan speed abnormality coefficient, the timing synchronization coefficient, and the coolant circulation blockage coefficient, respectively, and a1, a2, and a3 represent the preset proportional coefficients of the fan speed abnormality coefficient, the timing synchronization coefficient, and the coolant circulation blockage coefficient, respectively, and a1, a2, and a3 are all greater than 0.

8. The power battery thermal monitoring management method based on big data analysis according to claim 7 is characterized in that: Compare the heat dissipation control system self-check index with a preset heat dissipation control system self-check index threshold to perform early warning management on the heat dissipation control system; If the heat dissipation control system self-test index is greater than the heat dissipation control system self-test index threshold, a high-risk warning is immediately triggered; if the heat dissipation control system self-test index is less than or equal to the heat dissipation control system self-test index threshold, there is no need to trigger a high-risk warning.

9. A power battery thermal monitoring and management system based on big data analysis, used to implement the power battery thermal monitoring and management method based on big data analysis as claimed in any one of claims 1 to 8, characterized in that: It includes regional abnormal temperature rise module, fan abnormal speed module, timing synchronization module, coolant circulation module and early warning management module; The regional abnormal temperature rise module is used to collect the temperature distribution data of the power battery in real time by arranging multiple temperature sensors on the power battery cells, and analyze the regional abnormal temperature rise behavior of the power battery temperature distribution data; The fan abnormal speed module is used to obtain the fan speed information of the heat dissipation control system when there is abnormal temperature rise in a certain area of ​​the power battery, and calculate the fan speed abnormality coefficient according to the fan speed information of the heat dissipation control system; A timing synchronization module is used to obtain timing synchronization information between the heat dissipation control system and the battery charging and discharging when there is abnormal temperature rise in a region of the power battery, and calculate the timing synchronization coefficient based on the timing synchronization information between the heat dissipation control system and the battery charging and discharging; A coolant circulation module is used to obtain the coolant circulation information of the heat dissipation control system when there is an abnormal temperature rise behavior in a region of the power battery, and calculate the coolant circulation blockage coefficient according to the coolant circulation information of the heat dissipation control system; The early warning management module is used to build a self-check model of the heat dissipation control system according to the fan speed abnormality coefficient, timing synchronization coefficient, and coolant circulation blockage coefficient, output the heat dissipation control system self-check index, evaluate the potential hidden dangers of the heat dissipation control system at the current stage, and perform early warning management of the heat dissipation control system based on the evaluation results.

Images