Thermal management system diagnostic method, device and computer readable storage medium

Abstract

The present invention discloses a thermal management system diagnostic method, device and computer-readable storage medium, and relates to the field of vehicle diagnostic technology. The method comprises the following steps: obtaining the charging characteristic quantity of each charging cycle in the vehicle charging data; classifying each of the charging cycles according to the preset time and space categories, and performing clustering operations on the charging characteristic quantities of the collection of charging cycles under each of the preset time and space categories to obtain each charging condition under each of the preset time and space categories; obtaining the temperature change rate of the charging cycle corresponding to each of the charging conditions, and performing outlier analysis on the temperature change rate to obtain the outlier threshold of each of the charging conditions; obtaining the real-time charging data of the vehicle, and determining the faulty vehicle according to the outlier threshold of each of the charging conditions and the real-time charging data. The present invention improves the reliability and accuracy of the diagnostic results of faulty vehicles with thermal management anomalies.

Description

Technical Field

[0001] The present invention relates to the field of vehicle diagnosis technology, and in particular to a thermal management system diagnosis method, device and computer-readable storage medium. Background Art

[0002] With the rapid development of the electric vehicle industry in recent years, charging properties have become a key indicator that users are increasingly concerned about. The vehicle's thermal management strategy plays a decisive role in charging time and battery safety, so abnormal diagnosis measures for the vehicle's thermal management system are essential. However, the existing abnormal diagnosis methods for thermal management systems are easily affected by factors such as cities, seasons, driving conditions before charging, and charging pile equipment, resulting in low accuracy in abnormal diagnosis of vehicle thermal management systems.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a thermal management system diagnosis method, aiming to solve the technical problem of low accuracy in abnormal diagnosis of vehicle thermal management system.

[0005] To achieve the above object, the present invention provides a thermal management system diagnostic method, the thermal management system diagnostic method comprising the following steps: obtaining charging characteristic quantities of each charging cycle in vehicle charging data;

[0006] Classifying each of the charging cycles according to a preset time and space category, and performing clustering operations on the charging characteristic quantities of the set of charging cycles under each of the preset time and space categories to obtain each charging condition under each of the preset time and space categories;

[0007] Acquire the temperature change rate of the charging cycle corresponding to each of the charging conditions, and perform outlier analysis on the temperature change rate to obtain an outlier threshold value for each of the charging conditions;

[0008] Real-time charging data of the vehicle is obtained, and the faulty vehicle is determined according to the outlier threshold of each charging condition and the real-time charging data.

[0009] Optionally, the step of classifying each of the charging cycles according to preset spatiotemporal categories, performing clustering operations on charging feature quantities of a set of charging cycles under each of the preset spatiotemporal categories, and obtaining a charging condition corresponding to each of the preset spatiotemporal categories includes:

[0010] Obtaining the charging time and charging location of each charging cycle, determining the time segment in which the charging time is located, and the climate type of the charging location;

[0011] Determine, according to the time segment and the climate type, a preset time and space category corresponding to each of the charging cycles, and obtain a set of charging cycles under each of the preset time and space categories;

[0012] Based on a preset clustering algorithm, clustering operations are performed on the charging characteristic quantities of the sets of charging cycles under each of the preset time and space categories to obtain each charging condition under each of the preset time and space categories.

[0013] Optionally, the step of obtaining the temperature change rate of the charging cycle corresponding to each charging condition includes:

[0014] Acquiring a battery temperature of a charging cycle corresponding to each of the charging conditions, and performing a preset validity determination on the battery temperature to obtain an effective battery temperature that passes the preset validity determination;

[0015] The temperature change rate of each charging condition is determined according to the effective battery temperature.

[0016] Optionally, the step of determining the temperature change rate of each charging condition according to the effective battery temperature includes:

[0017] Determine, according to the effective battery temperature, a first maximum temperature at the start time of each charging cycle, a second maximum temperature at the end time, and a temperature change duration between the start time and the end time;

[0018] Obtaining a temperature change rate of each charging cycle according to a temperature difference between the first maximum temperature and the second maximum temperature and a temperature change duration;

[0019] The temperature change rate of the charging cycle corresponding to each of the charging conditions is used as the temperature change rate of each of the charging conditions.

[0020] Optionally, the step of performing outlier analysis on the temperature change rate to obtain an outlier threshold value for each charging condition includes:

[0021] Calculating the average value and standard deviation of the temperature change rate of each charging condition according to the temperature change rate of each charging condition;

[0022] Determine a concentrated interval of temperature change rate for each charging condition according to the three sigma criterion, the mean value and the standard deviation;

[0023] An outlier threshold value of each of the charging conditions is determined according to the type of the temperature change rate and the temperature change rate concentration interval.

[0024] Optionally, the real-time charging data includes real-time charging time, real-time charging location, real-time charging characteristic quantity and real-time temperature change rate, and the step of acquiring the real-time charging data of the vehicle and determining the faulty vehicle according to the outlier threshold of each charging condition and the real-time charging data includes:

[0025] According to the real-time charging time and the real-time charging location, a corresponding current time-space category is obtained;

[0026] According to the real-time charging characteristic quantity, each charging condition under the current time and space category is matched to obtain the real-time charging condition, and determine the real-time outlier threshold corresponding to the real-time charging condition;

[0027] Comparing the real-time temperature change rate with the real-time outlier threshold to obtain outlier information of the vehicle;

[0028] When the outlier information meets a preset outlier condition, the vehicle is determined to be a faulty vehicle.

[0029] Optionally, the step of obtaining the charging characteristic quantity of each charging cycle in the vehicle charging data includes:

[0030] Acquire vehicle data, and identify charging data of each charging cycle in the vehicle data according to the vehicle speed, charging state and vehicle current value in the vehicle data;

[0031] According to the preset charging characteristic type, the corresponding charging characteristic quantity is extracted from the charging data of each charging cycle.

[0032] Optionally, after the step of determining the faulty vehicle according to the outlier threshold of each charging condition, the step further includes:

[0033] Obtaining charging status information of the latest charging cycle of the faulty vehicle;

[0034] According to the charging status information, determining whether the coolant level is lower than a preset alarm level line;

[0035] If the coolant level is lower than a preset alarm level, a first prompt message is output to remind the vehicle owner that the coolant level is too low;

[0036] If the coolant level is not lower than the preset alarm level line, determining whether the water inlet temperature of the power battery in the charging status information is higher than the preset required temperature;

[0037] If the water inlet temperature is higher than the preset required temperature, a second prompt message is output to prompt the vehicle owner that there is a fault in the thermal management circuit of the vehicle;

[0038] If the water inlet temperature is not higher than the preset required temperature, a third prompt message is output to prompt the vehicle owner that there is a fault in the battery thermal management circuit.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also provides a thermal management system diagnostic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the computer program is executed by the processor, the steps of the method described in any one of the above items are implemented.

[0040] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium, on which a thermal management system diagnostic program is stored. When the thermal management system diagnostic program is executed by a processor, the steps of the thermal management system diagnostic method as described in any one of the above items are implemented.

[0041] The present invention proposes a thermal management system diagnostic method, which obtains the charging characteristic quantity of each charging cycle in the vehicle charging data, and then classifies each charging cycle according to the preset time and space category, and performs clustering operation on the charging characteristic quantity of the set of charging cycles under each preset time and space category, and obtains each charging condition under each preset time and space category, thereby realizing accurate classification of different charging conditions. Then, the temperature change rate of the charging cycle corresponding to each charging condition is obtained, and the temperature change rate is analyzed by outliers to obtain the outlier threshold of each charging condition. Finally, the real-time charging data of the vehicle is obtained, and the faulty vehicle is determined according to the outlier threshold of each charging condition and the real-time charging data. The present invention performs clustering and discrete analysis on a large amount of vehicle data, decouples factors such as the city, season, pre-charging driving condition, and charging pile equipment that affect the diagnosis result, and determines the discrete threshold of different charging conditions under the same time and space category. Then, based on the discrete threshold, the outlier faulty vehicle is determined, which effectively improves the reliability and accuracy of the diagnosis result of the faulty vehicle with thermal management abnormality. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a scenario of a thermal management system diagnostic method of the present invention;

[0043] Figure 2 A schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention;

[0044] Figure 3 It is a flow chart of the first embodiment of the thermal management system diagnostic method of the present invention;

[0045] Figure 4 A schematic diagram of a loss function of a preset clustering algorithm involved in the present invention;

[0046] Figure 5 A schematic diagram of the temperature change rate under a certain charging condition involved in the present invention;

[0047] Figure 6 It is a principle diagram of the 3σ criterion involved in the present invention;

[0048] Figure 7 It is a flow chart of the second embodiment of the thermal management system diagnostic method of the present invention;

[0049] Figure 8 It is a flowchart diagram of the third embodiment of the thermal management system diagnostic method of the present invention.

[0050] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0053] The terms "first" and "second" in the description and claims of the embodiments of the present application are used to distinguish different objects rather than to describe a specific order of objects. For example, a first target object and a second target object are used to distinguish different target objects rather than to describe a specific order of target objects.

[0054] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0055] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0056] With the rapid development of the electric vehicle industry in recent years, charging properties have become a key indicator that users are increasingly concerned about, among which charging time is particularly prominent. Currently on the market, there are a large number of customers complaining about charging power being limited due to battery temperature and long charging time, which has a negative impact. Therefore, the vehicle thermal management strategy plays a decisive role in charging time and battery safety, and abnormal diagnosis measures for the vehicle thermal management system are essential. At present, the commonly used thermal management system diagnostic methods are as follows:

[0057] Based on the temperature of vehicle components, it can be used to identify whether the thermal management system is abnormal, and an alarm will be issued when the temperature reaches a certain threshold. This method is simple and convenient, and is often used on the vehicle side, but it cannot distinguish whether the temperature abnormality is caused by sampling abnormality or vehicle thermal management system abnormality. In addition, the setting of thresholds often depends on experiments and the experience of developers, and the accuracy of the results is difficult to guarantee.

[0058] Alternatively, based on a certain charging cycle of a single vehicle and combined with the complex judgment logic of the vehicle's thermal management circuit, it is necessary to rely on a large number of signals and sensors to infer whether the thermal management system is abnormal. However, the charging condition is closely related to factors such as the battery status before charging begins, ambient temperature, charging power, charging current, and charging depth. It is difficult to decouple the influencing factors to determine that the thermal management system is abnormal, and the accuracy of the results is easily affected by the above factors.

[0059] Therefore, the existing abnormal diagnosis method of the thermal management system is easily affected by factors such as the city, season, driving conditions before charging, and charging pile equipment, resulting in low accuracy in the abnormal diagnosis of the vehicle thermal management system.

[0060] The thermal management system diagnostic method of the present invention is described below in conjunction with some embodiments:

[0061] Reference Figure 1 , Figure 1 This is a schematic diagram of a scenario of the thermal management system diagnostic method of the present invention. The execution subject of the thermal management system diagnostic method of the present invention can be the cloud.

[0062] The cloud collects the charging characteristics of each charging cycle from a large amount of vehicle charging data, and then classifies each charging cycle according to the preset time and space categories, and performs clustering operations on the charging characteristics of the collection of charging cycles under each preset time and space category to obtain each charging condition under each preset time and space category. Based on the massive amount of vehicle charging data, the cloud can solve the influence of factors such as city, season, driving conditions, and charging conditions through clustering operations, and is no longer limited to a certain vehicle or a certain charging cycle, thereby achieving accurate classification of different charging conditions.

[0063] After that, the temperature change rate of the charging cycle corresponding to each of the charging conditions is obtained, and the temperature change rate is subjected to outlier analysis to obtain the outlier threshold of each of the charging conditions. Then, the real-time charging data of the vehicle can be collected, and the faulty vehicle can be determined by comparing the outlier threshold of each of the charging conditions with the real-time charging data. The present invention performs clustering and discrete analysis on a large amount of vehicle data, decouples factors such as the city, season, pre-charging driving conditions, and charging pile equipment that affect the diagnosis results, and determines the discrete thresholds of different charging conditions under the same space-time category. Then, based on the discrete threshold, the outlier faulty vehicle is determined, which effectively improves the reliability and accuracy of the diagnosis results of faulty vehicles with thermal management anomalies.

[0064] like Figure 2 As shown, Figure 2 The figure is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention.

[0065] In this embodiment, the thermal management system diagnostic device may be a PC (Personal Computer), a tablet computer, a portable computer, a server or other device.

[0066] like Figure 2 As shown, the thermal management system diagnostic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0067] Those skilled in the art will understand that Figure 2 The device structure shown in the figure does not constitute a limitation on the thermal management system diagnostic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0068] like Figure 2As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a thermal management system diagnostic application.

[0069] exist Figure 2 In the device shown, the processor 1001 can be used to call the thermal management system diagnostic application stored in the memory 1005 and execute the operations of the thermal management system diagnostic method in the following embodiments.

[0070] Reference Figure 3 , Figure 3 FIG. 1 is a flow chart of a first embodiment of a thermal management system diagnostic method according to the present invention.

[0071] A first embodiment of the present invention provides a thermal management system diagnostic method, the thermal management system diagnostic method comprising the following steps:

[0072] Step S100, obtaining charging characteristic quantities of each charging cycle in vehicle charging data;

[0073] The cloud usually collects a large amount of vehicle data, and the vehicle data includes driving data, charging data, discharging data, parking data and other data generated during the use of the vehicle. In this embodiment, all charging cycles in the vehicle data can be identified by analyzing the vehicle after obtaining the vehicle data from the cloud. Then the charging characteristic quantities in each charging cycle are extracted, wherein the charging characteristic quantities include but are not limited to the maximum temperature of the battery cell before charging, the average charging current, the maximum charging current, the charging power, the charging mode (fast charging or slow charging), the thermal management request (heating request, cooling request or constant temperature request), the actual power of the PTC (Positive Temperature Coefficient, positive temperature coefficient element), the actual power of the compressor, the air conditioning temperature of the passenger compartment, the charging SOC (State Of Charge, battery state of charge) interval and the charging depth and other charging characteristic values. Further, in order to improve the validity and representativeness of the charging data in each charging cycle, the charging cycle whose charging time exceeds the preset screening time (such as 5min, 10min, 15min, etc.) can be selected as each charging cycle in the vehicle charging data.

[0074] It can be understood that since the data types of the above charging characteristics include different types such as interval scale variables, binary variables, nominal variables, etc., different types of charging characteristics can be combined in a single dissimilarity matrix, and all charging characteristics can be converted to a common value range interval to obtain the value of each charging characteristic (i.e., charging characteristic quantity).

[0075] Furthermore, step S100 includes the following steps:

[0076] Step S110, acquiring vehicle data, and identifying charging data of each charging cycle in the vehicle data according to the vehicle speed, charging state and vehicle current value in the vehicle data;

[0077] Step S111 : extracting corresponding charging characteristic quantities from the charging data of each charging cycle according to a preset charging characteristic type.

[0078] Specifically, after obtaining the vehicle data, the vehicle speed, charging state and vehicle current value in the vehicle data can be determined according to the preset charging cycle determination rule, so as to determine and identify the charging data of each charging cycle in the vehicle data. For example, the preset charging cycle determination rule is: (1) vehicle speed = 0 km / h; (2) charging start condition: charging state = parking charging, and the number of consecutive times of the vehicle current value I < 0A is greater than the first preset number threshold (such as 3 times, 5 times, etc.). Or the number of consecutive times of the vehicle current value I < 0A is greater than the second preset number threshold (such as 8 times, 10 times, etc.). The first preset number threshold is less than the second preset number threshold; (3) charging end condition: the number of consecutive times of the vehicle current value I ≥ 0A is greater than the third preset number threshold (such as 3 times, 5 times, etc.).

[0079] By means of the above-mentioned preset charging cycle determination rule, each charging cycle in the vehicle data can be effectively identified.

[0080] Furthermore, in terms of acquiring charging data for each charging cycle, during the charging process: the interval between two adjacent message frames is less than or equal to a first preset interval (such as 8 minutes, 10 minutes, 15 minutes, etc.). Then the two adjacent message frames are charging data for the same charging cycle. If the interval between two adjacent message frames exceeds the first preset interval, the message sending timeout may be due to an interruption in charging, and the two adjacent message frames are used as nodes to split the charging data into two charging cycles. Therefore, the accuracy of identifying each charging cycle can be further improved.

[0081] When the charging state = parking and charging, if there is charging completion data with the charging state being charging completed within the second preset interval (such as 5min, 6min, 7min, etc.), the charging completion data is retained in the charging data of the charging cycle. For example, if the charging state = charging completed exists within 6min, two frames of charging completion data are retained; if there is only one frame of charging completion data with the charging state = charging completed within 6min, this frame of charging completion data is retained. If there is no charging completion data with the charging state being charging completed within the second preset interval (such as 5min, 6min, 7min, etc.), the charging completion data does not need to be retained in the charging data of the charging cycle. This can avoid the situation where the charging data of the charging cycle is difficult to use as a reference in the case of short-term charging.

[0082] Step S200, classifying each of the charging cycles according to a preset time and space category, performing clustering operations on the charging characteristic quantities of the set of charging cycles under each of the preset time and space categories, and obtaining each charging condition under each of the preset time and space categories;

[0083] Since the battery charging condition is affected by factors such as the city where the vehicle is located, the ambient temperature affected by the season, the charging current, the charging depth, the charging time, the temperature of the battery cell and other factors, the charging condition needs to be distinguished for each charging cycle so that charging conditions of the same category can be compared with each other and be comparable.

[0084] The preset time and space categories can be divided according to time segments and climate types, such as season and climate, or month and climate. Taking the division according to season and climate as an example, China has four seasons, namely spring from February to April, summer from May to July, autumn from August to November, and winter from December to January, and there are five types of climate, namely tropical monsoon climate, subtropical monsoon climate, temperate monsoon climate, temperate continental climate, and high mountain plateau climate. The corresponding preset time and space categories have four seasons*five types of climate=4*5=20 types.

[0085] In this embodiment, by classifying each of the charging cycles according to the preset time and space categories, a collection of charging cycles under each of the preset time and space categories can be obtained to ensure that the collection of charging cycles under each of the preset time and space categories are all in a similar external environment. Then, clustering operations are performed on the charging feature quantities of the collection of charging cycles under each of the preset time and space categories to obtain the charging conditions under each of the preset time and space categories.

[0086] Further, step S200 includes the following steps:

[0087] Step S210, obtaining the charging time and charging location of each charging cycle, determining the time segment of the charging time and the climate type of the charging location;

[0088] Step S211, determining a preset time-space category corresponding to each of the charging cycles according to the time segment and the climate type, and obtaining a set of charging cycles under each of the preset time-space categories;

[0089] Step S212: Based on a preset clustering algorithm, clustering operations are performed on the charging characteristic quantities of the sets of charging cycles under each of the preset time and space categories to obtain each charging condition under each of the preset time and space categories.

[0090] By acquiring the charging time and charging location of each charging cycle, the time segment (such as season or month, etc.) in which the charging time is located and the climate type in which the charging location is located can be determined. Then, according to the time segment and the climate type, the preset time and space category corresponding to each charging cycle is determined, and a set of charging cycles under each preset time and space category is obtained.

[0091] This embodiment does not limit the selection of clustering algorithms, which can be selected according to specific needs. After obtaining the set of charging cycles under each of the preset time and space categories, the charging characteristic quantities of the set of charging cycles under each preset time and space category can be clustered based on the preset clustering algorithm to obtain each charging condition under each of the preset time and space categories. The preset clustering algorithm can be a K-Means clustering algorithm (k-means clustering algorithm, also known as k-means clustering algorithm), a density-based clustering algorithm, an expectation maximization clustering algorithm using a Gaussian mixture model, etc.

[0092] Taking the K-Means clustering algorithm as an example, the K-Means clustering algorithm is an iterative clustering analysis algorithm that randomly selects K objects as the initial cluster centers, then calculates the distance between each object and each seed cluster center, and assigns each object to the cluster center closest to it.

[0093] The steps are summarized as follows:

[0094] (1) Cluster allocation: K points (cluster centers) are randomly generated from the data, and the data are classified according to their distance from these K points (such as Euclidean distance: distance in multiple dimensions). Points close to a certain cluster (cluster center) are classified into this category.

[0095] (2) Moving the cluster center: Calculate the average value of all points classified into one category and move the cluster center to this average value to update the cluster center.

[0096] (3) New classifications are obtained by continuously calculating distances, assigning clusters, and moving cluster centers until the K cluster centers do not change.

[0097] (4) If a cluster center has no corresponding point, then the cluster center is randomly initialized.

[0098] The K-Means clustering algorithm takes minimizing the square error between samples and particles as the objective function. The sum of the square distance errors between the particles of each cluster and the sample points within the cluster is called the degree of distortion (i.e., the value of the loss function). So, for a cluster, the lower the degree of distortion, the closer the members in the cluster are, and the higher the degree of distortion, the looser the structure in the cluster. The degree of distortion will decrease with the increase of categories, but for data with a certain degree of differentiation, the degree of distortion will be greatly improved when it reaches a certain critical point, and then slowly decrease. This critical point can be considered as a point with better clustering performance. Figure 4 , Figure 4 FIG. 1 is a schematic diagram of the loss function of the preset clustering algorithm involved in the present invention. Figure 4 As shown, it can be clearly seen that when the category is 7, the degree of distortion is greatly improved, so it can be determined that the number of clusters is 7, that is, the type of charging conditions is 7.

[0099] Step S300, obtaining a temperature change rate of a charging cycle corresponding to each of the charging conditions, and performing an outlier analysis on the temperature change rate to obtain an outlier threshold value of each of the charging conditions;

[0100] Wherein, the temperature change rate may be a cooling rate or a heating rate. In this embodiment, the temperature value of the charging cycle corresponding to each of the charging conditions may be obtained, and then the corresponding temperature change rate may be calculated. Then, the temperature change rate of each of the charging conditions is subjected to outlier analysis, so as to determine the concentrated interval of the value of the temperature change rate of each charging condition. Wherein, the method for determining the concentrated interval may be the three sigma rule, the Dixon method, the Shawett method, the Grubbs method, the t-test method, the range method, etc. If the temperature change rate is the cooling rate, and the cooling rate is abnormally small, it means that the temperature is difficult to drop for a long time, and there is a fault in the thermal management system; if the cooling rate is abnormally large, it means that the temperature reduction rate is very fast, and the thermal management system is effective. Therefore, the temperature change rate is the cooling rate, and only the case where the temperature change rate is abnormally small can be judged, and the minimum value of the concentrated interval is used as the outlier threshold. If the temperature change rate is lower than the outlier threshold, it is judged as an outlier. It is understandable that when the temperature change rate is the heating rate, only the case where the temperature change rate is abnormally large can be judged, and the maximum value of the concentrated interval is used as the outlier threshold. If the temperature change rate is higher than the outlier threshold, it is judged as an outlier. Thus, the outlier thresholds of each charging condition under different time and space categories are obtained. Taking the preset time and space categories as divided into four seasons and five climate types, and each preset time and space category has 7 types of charging conditions as an example, a total of 4*5*7=140 outlier thresholds can be obtained.

[0101] The step of performing outlier analysis on the temperature change rate to obtain an outlier threshold value for each charging condition in step S300 includes:

[0102] Step S310, calculating an average value and a standard deviation of the temperature change rate of each charging condition according to the temperature change rate of each charging condition;

[0103] Step S311, determining a concentrated interval of the temperature change rate of each charging condition according to the three sigma criterion, the mean value and the standard deviation;

[0104] Step S312: determining an outlier threshold of each of the charging conditions according to the type of the temperature change rate and the temperature change rate concentration interval.

[0105] Reference Figure 5 , Figure 5 This is a schematic diagram of the temperature change rate under a certain charging condition involved in the present invention, in which the k value is the value of the temperature change rate. It can be seen that the temperature change rate basically obeys the normal distribution, so the temperature change rate of each charging condition can be analyzed based on the 3σ criterion (i.e., the three sigma criterion). First, according to the temperature change rate of each charging condition, the average value μ and standard deviation σ of the temperature change rate of each charging condition are calculated. Figure 6 , Figure 6 The schematic diagram of the 3σ criterion involved in the present invention is shown in FIG. 1 , where the horizontal axis is the value and the vertical axis is the frequency. The 3σ criterion is:

[0106] The probability that the value is distributed in (μ-σ, μ+σ) is 68.27%;

[0107] The probability that the value is distributed in (μ-2σ, μ+2σ) is 95.45%;

[0108] The probability that the value is distributed in (μ-3σ, μ+3σ) is 99.73%;

[0109] μ (i.e., mean value) is the location parameter of the normal distribution, which describes the central tendency position of the normal distribution. The probability law is that the probability of taking a value close to μ is large, and the probability of taking a value farther away from μ is small. σ (i.e., standard deviation) describes the degree of dispersion of the data distribution. The larger σ is, the more dispersed the data distribution is, and the smaller σ is, the more concentrated the data distribution is. σ is also called the shape parameter of the normal distribution. The larger σ is, the flatter the curve is. Conversely, the smaller σ is, the taller the curve is.

[0110] According to the three sigma criterion, the mean value and the standard deviation, the temperature change rate concentration interval of each charging condition is determined, and then the outlier threshold of each charging condition is determined according to the type of the temperature change rate and the temperature change rate concentration interval. The types of temperature change rates include cooling rate and heating rate. For example, μ = 0.24, μ-3σ = 0.1, μ + 3σ = 0.4, then the corresponding temperature change rate concentration interval is 0.1 to 0.4. If the type of the temperature change rate is cooling rate, the charging outlier threshold k < 0.1 ° C / min is obtained.

[0111] Step S400, acquiring real-time charging data of the vehicle, and determining the faulty vehicle according to the outlier threshold of each charging condition and the real-time charging data.

[0112] Specifically, the real-time charging data of the vehicle can be obtained to match the corresponding real-time charging condition, and then the real-time outlier threshold of the real-time condition can be determined. The real-time temperature change rate in the real-time charging data can be judged by the real-time outlier threshold to obtain the outlier information of the real-time charging data of the vehicle. When the outlier information meets the preset outlier condition, the vehicle is determined to be a faulty vehicle.

[0113] Furthermore, the real-time charging data includes real-time charging time, real-time charging location, real-time charging characteristic quantity and real-time temperature change rate. Step S400 further includes the following steps:

[0114] Step S410, obtaining a corresponding current time-space category according to the real-time charging time and the real-time charging location;

[0115] Step S420, matching the real-time charging characteristic quantity with each charging condition under the current spatiotemporal category to obtain the real-time charging condition, and determining a real-time outlier threshold corresponding to the real-time charging condition;

[0116] Step S430, comparing the real-time temperature change rate with the real-time outlier threshold to obtain outlier information of the vehicle;

[0117] Step S440: When the outlier information satisfies a preset outlier condition, the vehicle is determined to be a faulty vehicle.

[0118] The real-time charging data includes but is not limited to real-time charging time, real-time charging location, real-time charging characteristic quantity and real-time temperature change rate. According to the real-time charging time and real-time charging location in the real-time charging data, the current time segment of the real-time charging time and the current climate type of the real-time charging location are determined, and then according to the current time segment and the current climate type, the corresponding current time-space category is obtained. For example, if the real-time charging time is June xx and the real-time charging location is Hangzhou, the corresponding time segment is summer and the corresponding climate type is subtropical monsoon climate, so that the corresponding current time-space category is determined to be the summer subtropical monsoon climate category in the preset time-space category.

[0119] After determining the current spatiotemporal category corresponding to the real-time charging data of the vehicle, a real-time charging feature quantity can be extracted from the real-time charging data, and then the real-time charging feature quantity is matched with each charging condition under the current spatiotemporal category to obtain the real-time charging condition, and the real-time outlier threshold corresponding to the real-time charging condition is determined. The real-time charging feature quantity can be matched with each charging condition under the current spatiotemporal category by calculating the Euclidean distance between the real-time charging feature quantity and the cluster center of each charging condition, so that the charging condition corresponding to the cluster center with the smallest Euclidean distance is used as the real-time charging condition corresponding to the real-time charging feature quantity.

[0120] After obtaining the real-time outlier threshold, the real-time temperature change rate in the real-time charging data is compared with the real-time outlier threshold to obtain the outlier information of the vehicle. The outlier information may include information such as the number of outliers, the outlier time, and the charging cycle corresponding to the outlier. When the outlier information meets the preset outlier condition, the vehicle is determined to be a faulty vehicle. The preset outlier condition is a determination condition for determining whether the thermal management system of the vehicle is abnormal. The preset outlier condition may be that the number of outliers in the most recent preset number of charging cycles exceeds the preset abnormal threshold, for example, the number of outliers exceeds 5 times in 10 charging cycles; or it may be that the charging cycles with a preset number of abnormalities are all determined to be outliers, for example, 5 consecutive charging cycles are all determined to be outliers. It can be understood that the preset outlier condition can be set according to specific needs, and this embodiment does not limit this.

[0121] In the first embodiment of the present invention, by obtaining the charging characteristic quantity of each charging cycle in the vehicle charging data, and then classifying each charging cycle according to the preset time and space category, the charging characteristic quantity of the set of charging cycles under each preset time and space category is clustered respectively, and each charging condition under each preset time and space category is obtained, thereby achieving accurate classification of different charging conditions. Then, the temperature change rate of the charging cycle corresponding to each charging condition is obtained, and the temperature change rate is analyzed by outliers to obtain the outlier threshold of each charging condition. Finally, the real-time charging data of the vehicle is obtained, and the faulty vehicle is determined according to the outlier threshold of each charging condition and the real-time charging data. This embodiment performs clustering and discrete analysis on a large amount of vehicle data, decouples factors such as the city, season, pre-charging driving condition, and charging pile equipment that affect the diagnosis result, and determines the discrete threshold of different charging conditions under the same time and space category. Then, based on the discrete threshold, the outlier faulty vehicle is determined, which effectively improves the reliability and accuracy of the diagnosis result of the faulty vehicle with thermal management abnormality.

[0122] Further, refer to Figure 7 The second embodiment of the present invention provides a thermal management system diagnostic method based on the above Figure 3 In the embodiment shown, the step of obtaining the temperature change rate of the charging cycle corresponding to each charging condition in step S300 includes:

[0123] Step S320, obtaining the battery temperature of the charging cycle corresponding to each of the charging conditions, and performing a preset validity determination on the battery temperature to obtain an effective battery temperature that passes the preset validity determination;

[0124] Step S330: determining the temperature change rate of each charging condition according to the effective battery temperature.

[0125] Before calculating the temperature change rate, the validity of the battery temperature can be judged to prevent misjudgment of thermal management system abnormalities due to temperature sampling or communication abnormalities. This embodiment obtains the battery temperature of the charging cycle corresponding to each charging condition and performs a preset validity judgment on the battery temperature to obtain a valid battery temperature that passes the preset validity judgment, thereby improving the validity of the battery temperature.

[0126] The determination method of the preset effective determination may include: judging that the battery temperature is within the preset temperature range (such as -35≤T≤65℃), and removing the battery temperature that is not within the preset temperature range as an invalid battery temperature; and / or taking two adjacent ones as a probe group, calculating the temperature difference △T=|T1-T2| of each battery temperature measured by the same probe group, where T1 and T2 are two battery temperatures measured by the same probe group. When the temperature difference △T exceeds the preset temperature difference threshold (such as 7℃, 8℃, 9℃, etc.), it means that there is a temperature failure point. The median of the existing valid battery temperatures can be calculated. If the number of valid values ​​is an even number, the average of the two middle ones is taken as the median. Then, the two battery temperatures measured by the same probe group are compared with the median respectively, and the battery temperature with a larger difference from the median is determined to be an invalid battery temperature. If the difference with the median is equal, the battery temperature with a higher value is determined to be an invalid battery temperature and removed. In addition, two or more adjacent temperature probes may be used as a probe group, and battery temperatures with abnormal standard deviations may be removed as invalid battery temperatures based on the standard deviations of the battery temperatures measured by the same probe group.

[0127] After obtaining the effective battery temperature of the charging cycle corresponding to each of the charging conditions, the temperature change rate of each of the charging conditions is determined according to the effective battery temperature, wherein the types of the temperature change rate include a heating rate and a cooling rate. The corresponding heating rate can be determined by a temperature change curve from the lowest temperature at the beginning of the charging cycle to the highest temperature during the charging process, or the corresponding cooling rate can be determined by a slope from the highest temperature point at the beginning of the charging cycle to the highest temperature point at the end of the charging cycle.

[0128] In this embodiment, the battery temperature of the charging cycle corresponding to each charging condition is obtained, and the battery temperature is subjected to a preset validity determination to obtain an effective battery temperature that passes the preset validity determination, and then the temperature change rate of each charging condition is determined based on the effective battery temperature. This ensures the accuracy of the obtained temperature change rate of each charging condition, thereby improving the accuracy of the discrete threshold determined based on the temperature change rate.

[0129] Further, step S330 includes the following steps:

[0130] Step S331, determining the first maximum temperature at the start time of each charging cycle, the second maximum temperature at the end time, and the temperature change duration between the start time and the end time according to the effective battery temperature;

[0131] Step S332, obtaining a temperature change rate of each charging cycle according to a temperature difference between the first maximum temperature and the second maximum temperature and a temperature change duration;

[0132] Step S333: taking the temperature change rate of the charging cycle corresponding to each of the charging conditions as the temperature change rate of each of the charging conditions.

[0133] Specifically, after obtaining the effective battery temperature of the charging cycle corresponding to each of the charging conditions, the first maximum temperature at the start time of each of the charging cycles, the second maximum temperature at the end time, and the temperature change duration between the start time and the end time can be determined according to the effective battery temperature. Among them, the start time of the charging cycle can be selected as the moment when the charging state changes to parking charging. Of course, since the battery temperature may be low at the beginning of charging, the moment when the battery temperature is the highest within the time period when the charging current is less than or equal to the preset charging rate (such as 0.2C, 0.25C, 0.33C, C is the rate used to indicate the battery charging capacity) can also be selected as the start time to avoid misjudgment of the vehicle's thermal management system. The end time is the actual end time of the charging of the charging cycle, and the temperature change duration is the time difference between the start time and the end time.

[0134] In this embodiment, the first maximum temperature is subtracted from the second maximum temperature to obtain the corresponding temperature difference, and then the temperature difference is divided by the temperature change duration to obtain the temperature change rate of each charging cycle. The temperature change rate is the cooling rate, which can better reflect the heat dissipation capacity of the vehicle's thermal management system than the heating rate. The temperature change rate is then divided according to the different charging conditions corresponding to each charging cycle, and the temperature change rate of the charging cycle corresponding to each charging condition is used as the temperature change rate of each charging condition.

[0135] Further, refer to Figure 8 The third embodiment of the present invention provides a thermal management system diagnostic method based on the above Figure 3 In the embodiment shown, after step S400, the following steps are further included:

[0136] Step S500, obtaining charging status information of the latest charging cycle of the faulty vehicle;

[0137] Step S510, judging whether the coolant level is lower than a preset alarm level line according to the charging status information;

[0138] Step S511, if the coolant level is lower than a preset alarm level line, output a first prompt message to prompt the owner that the coolant level is too low;

[0139] Step S520, if the coolant level is not lower than the preset alarm level line, determining whether the water inlet temperature of the power battery in the charging status information is higher than the preset required temperature;

[0140] Step S521, if the water inlet temperature is higher than the preset required temperature, output a second prompt message to prompt the vehicle owner that there is a fault in the vehicle thermal management circuit;

[0141] Step S522: If the water inlet temperature is not higher than the preset required temperature, a third prompt message is output to prompt the owner that there is a fault in the battery thermal management circuit.

[0142] After locating a faulty vehicle with an abnormal thermal management system, the charging status information of the latest charging cycle of the faulty vehicle can be obtained, wherein the charging status information includes but is not limited to the coolant level and the water inlet temperature of the power battery.

[0143] In this embodiment, by judging whether the coolant level is lower than the preset alarm level line, it is determined whether the abnormality of the thermal management system of the faulty vehicle is caused by the low coolant level. If the coolant level is lower than the preset alarm level line, a first prompt message can be output to the owner's mobile terminal or the display screen of the vehicle to prompt the owner that the coolant level is too low, and the owner can replenish the coolant in time.

[0144] If the coolant level is not lower than the preset alarm level line, it means that the thermal management system abnormality of the faulty vehicle is not caused by the low coolant level. It can be determined whether the thermal management system abnormality of the faulty vehicle is caused by the abnormality of the battery thermal management circuit or the abnormality of the vehicle thermal management circuit by judging whether the water inlet temperature of the power battery in the charging status information is higher than the preset required temperature.

[0145] If the water inlet temperature is higher than the preset required temperature, it means that there is a fault in the thermal management circuit of the whole vehicle and cannot meet the cooling requirement of the power battery. Then a second prompt message is output to remind the owner that there is a fault in the thermal management circuit of the whole vehicle and the thermal management circuit, compressor, pump, valve, etc. of the whole vehicle need to be checked.

[0146] If the water inlet temperature is not higher than the preset required temperature, it means that the thermal management circuit of the whole vehicle can meet the cooling requirement of the power battery, and then a third prompt message is output to prompt the owner that there is a fault in the battery thermal management circuit and the liquid cooling plate, pump, valve, etc. of the power battery need to be checked.

[0147] In this embodiment, the coolant level of the latest charging cycle of the faulty vehicle and the water inlet temperature of the power battery are used for judgment, so that the faulty component causing the abnormality of the thermal management system of the faulty vehicle can be quickly located, thereby improving the accuracy of the thermal management system diagnosis.

[0148] In addition, an embodiment of the present invention further proposes a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the operations in the thermal management system diagnostic method provided in the above embodiment are implemented, and the specific steps are not repeated here.

[0149] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such actual relationship or order between these entities / operations / objects; the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0150] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. The device embodiment described above is only illustrative, and the units described as separate components may or may not be physically separated. Some or all of the modules in the selection can be selected according to actual needs to achieve the purpose of the scheme of the present invention. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0151] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0152] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, including a number of instructions for a terminal device (which can be a mobile phone, computer, server, vehicle, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0153] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A thermal management system diagnostic method, characterized in that: The thermal management system diagnostic method comprises the following steps: Obtaining charging characteristic quantities of each charging cycle in vehicle charging data; Classifying each of the charging cycles according to preset time and space categories, and performing clustering operations on the charging characteristic quantities of the sets of charging cycles under each of the preset time and space categories to obtain each charging condition under each of the preset time and space categories, wherein the preset time and space categories are obtained by dividing according to time segments and climate types; Acquire the temperature change rate of the charging cycle corresponding to each of the charging conditions, and perform outlier analysis on the temperature change rate to obtain an outlier threshold value for each of the charging conditions; Acquire real-time charging data of the vehicle, and determine the faulty vehicle according to the outlier threshold of each charging condition and the real-time charging data; The real-time charging data includes real-time charging time, real-time charging location, real-time charging characteristic quantity and real-time temperature change rate. The step of acquiring the real-time charging data of the vehicle and determining the faulty vehicle according to the outlier threshold of each charging condition and the real-time charging data includes: According to the real-time charging time and the real-time charging location, a corresponding current time-space category is obtained; According to the real-time charging characteristic quantity, each charging condition under the current time and space category is matched to obtain the real-time charging condition, and determine the real-time outlier threshold corresponding to the real-time charging condition; Comparing the real-time temperature change rate with the real-time outlier threshold to obtain outlier information of the vehicle; When the outlier information meets a preset outlier condition, the vehicle is determined to be a faulty vehicle.

2. The thermal management system diagnostic method according to claim 1, characterized in that: The step of classifying each of the charging cycles according to the preset time and space categories, performing clustering operations on the charging feature quantities of the sets of charging cycles under each of the preset time and space categories, and obtaining the charging conditions corresponding to each of the preset time and space categories includes: Obtaining the charging time and charging location of each charging cycle, determining the time segment in which the charging time is located, and the climate type of the charging location; Determine, according to the time segment and the climate type, a preset time and space category corresponding to each of the charging cycles, and obtain a set of charging cycles under each of the preset time and space categories; Based on a preset clustering algorithm, clustering operations are performed on the charging characteristic quantities of the sets of charging cycles under each of the preset time and space categories to obtain each charging condition under each of the preset time and space categories.

3. The thermal management system diagnostic method according to claim 1, characterized in that: The step of obtaining the temperature change rate of the charging cycle corresponding to each charging condition includes: Acquiring a battery temperature of a charging cycle corresponding to each of the charging conditions, and performing a preset validity determination on the battery temperature to obtain an effective battery temperature that passes the preset validity determination; The temperature change rate of each charging condition is determined according to the effective battery temperature.

4. The thermal management system diagnostic method according to claim 3, characterized in that: The step of determining the temperature change rate of each charging condition according to the effective battery temperature includes: Determine, according to the effective battery temperature, a first maximum temperature at the start time of each charging cycle, a second maximum temperature at the end time, and a temperature change duration between the start time and the end time; Obtaining a temperature change rate of each charging cycle according to a temperature difference between the first maximum temperature and the second maximum temperature and a temperature change duration; The temperature change rate of the charging cycle corresponding to each of the charging conditions is used as the temperature change rate of each of the charging conditions.

5. The thermal management system diagnostic method according to claim 1, characterized in that: The step of performing outlier analysis on the temperature change rate to obtain an outlier threshold value for each charging condition includes: Calculating the average value and standard deviation of the temperature change rate of each charging condition according to the temperature change rate of each charging condition; Determine a concentrated interval of temperature change rate for each charging condition according to the three sigma criterion, the mean value and the standard deviation; An outlier threshold value of each of the charging conditions is determined according to the type of the temperature change rate and the temperature change rate concentration interval.

6. The thermal management system diagnostic method according to claim 1, characterized in that: The step of obtaining the charging characteristic quantity of each charging cycle in the vehicle charging data includes: Acquire vehicle data, and identify charging data of each charging cycle in the vehicle data according to the vehicle speed, charging state and vehicle current value in the vehicle data; According to the preset charging characteristic type, the corresponding charging characteristic quantity is extracted from the charging data of each charging cycle.

7. The thermal management system diagnostic method according to any one of claims 1 to 6, characterized in that: After the step of determining the faulty vehicle according to the outlier threshold of each charging condition, the method further includes: Obtaining charging status information of the latest charging cycle of the faulty vehicle; According to the charging status information, determining whether the coolant level is lower than a preset alarm level line; If the coolant level is lower than a preset alarm level, a first prompt message is output to remind the vehicle owner that the coolant level is too low; If the coolant level is not lower than the preset alarm level line, determining whether the water inlet temperature of the power battery in the charging status information is higher than the preset required temperature; If the water inlet temperature is higher than the preset required temperature, a second prompt message is output to prompt the vehicle owner that there is a fault in the thermal management circuit of the vehicle; If the water inlet temperature is not higher than the preset required temperature, a third prompt message is output to prompt the vehicle owner that there is a fault in the battery thermal management circuit.

8. A thermal management system diagnostic device, characterized in that: The thermal management system diagnostic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 7 when executed by the processor.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a thermal management system diagnostic program, which, when executed by a processor, implements the steps of the thermal management system diagnostic method according to any one of claims 1 to 7.

Images