A Charging and Discharging Safety Monitoring System and Method for a New Energy Vehicle Battery

Abstract

The present invention provides a charging and discharging safety monitoring system and method for a new energy vehicle battery. The charging and discharging safety monitoring system includes a cloud server for providing charging and discharging safety monitoring services for the new energy vehicle battery, and a number of new energy vehicles communicatively connected to the cloud server. The new energy vehicles upload real-time charging and discharging data to the cloud server, so that the cloud server performs charging and discharging safety monitoring on the new energy vehicles based on the charging and discharging data. The cloud server is configured to perform clustering analysis on a cluster of new energy vehicles connected thereto that have the same or similar internal charging and discharging attributes and the same or similar external charging and discharging environmental conditions, so as to identify safety anomalies in the charging and discharging processes of the new energy vehicles according to the clustering analysis results, and can timely and accurately predict charging and discharging anomalies of the new energy vehicle battery, thereby fully and effectively guaranteeing the personal and property safety of people.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicles, and particularly relates to a charging and discharging safety monitoring system and method for a new energy vehicle battery. Background Art

[0002] With the increasing popularity of new energy vehicles, the safety issues of using new energy vehicles have gradually become one of the important issues that people are concerned about. Compared with traditional fuel vehicles, the power battery of a new energy vehicle, as a "new" component of the vehicle, is the key object of people's attention regarding the safety issues of new energy vehicles. The main reason is that the thermal stability of the power battery itself has a certain threshold. During the charging and discharging process of a new energy vehicle, the temperature of the power battery will continuously rise. If effective heat dissipation measures are not taken, it is very easy to cause thermal runaway of the battery, resulting in situations such as fire or even explosion. Moreover, the monitoring of the charging and discharging state of the battery during the charging and discharging process of a new energy vehicle is also very important. The power battery is usually a battery pack composed of a large number of single cells. Current technical means are difficult to accurately monitor the charging and discharging states of each single cell simultaneously. Once the charging and discharging current or voltage of any one of the single cells exceeds the critical value and is not detected in time, very serious safety accidents may occur. Currently, the common method for monitoring the safety of a new energy vehicle battery is to measure the charging and discharging current and voltage of the power battery of the new energy vehicle in real time and compare them with the configured safety current and safety voltage in real time, so as to stop charging or limit the discharge power when the current or voltage exceeds the safety critical value during the charging and discharging process. However, on the one hand, since the critical values of the charging and discharging parameters themselves are not fixed values that remain unchanged, they will change due to the characteristics of the battery itself and environmental influences. On the other hand, since the charging and discharging parameters of the power battery are also unstable due to environmental factors, simply judging whether they exceed the critical value cannot accurately identify the abnormal charging and discharging of new energy vehicles. Summary of the Invention

[0003] Based on the above problems, the present invention proposes a charging and discharging safety monitoring system and method for a new energy vehicle battery, which can timely and accurately predict the abnormal charging and discharging conditions of the new energy vehicle battery, thereby fully and effectively protecting people's personal and property safety.

[0004] In view of this, a first aspect of the present invention provides a charging and discharging safety monitoring system for a new energy vehicle battery, including a cloud server for providing charging and discharging safety monitoring services for the new energy vehicle battery, and a number of new energy vehicles communicatively connected to the cloud server. The new energy vehicles upload real-time charging and discharging data to the cloud server, so that the cloud server performs charging and discharging safety monitoring on the new energy vehicles based on the charging and discharging data. The cloud server is configured to perform clustering analysis on a cluster of new energy vehicles connected to it with the same or similar internal charging and discharging attributes and the same or similar external charging and discharging environmental conditions, so as to identify safety anomalies in the charging and discharging processes of the new energy vehicles according to the clustering analysis results.

[0005] A second aspect of the present invention provides a method for monitoring the charging and discharging safety of a new energy vehicle battery, including:

[0006] Determine the new energy vehicle to be monitored as the monitoring object, where the monitoring object is a new energy vehicle that is undergoing rapid charging or rapid discharging;

[0007] Obtain the real-time charging and discharging parameters of the monitoring object, where the charging and discharging parameters include one or more of the charging and discharging current, charging and discharging voltage, and charging and discharging power of the power battery of the monitoring object;

[0008] Determine the clustering object cluster of the monitoring object in the new energy vehicle list, where each new energy vehicle in the clustering object cluster has the same or similar internal charging and discharging attributes and the same or similar external charging and discharging environmental conditions as the monitoring object;

[0009] Obtain the charging and discharging parameters of each new energy vehicle in the clustering object cluster, where the charging and discharging parameters are the charging and discharging parameters of the most recent charging and discharging behavior of the new energy vehicles in the clustering object cluster;

[0010] Cluster the associated charging and discharging parameters of the new energy vehicles in the clustering object cluster;

[0011] Identify safety anomalies in the charging and discharging process of the monitoring object according to the clustering results.

[0012] Further, the step of determining the clustering object cluster of the monitoring object in the new energy vehicle list specifically includes:

[0013] Configure an upper bound and a lower bound for the number of clustering objects used to limit the number of clustering objects in the clustering object cluster;

[0014] Obtain the vehicle model, geographical location, and charging and discharging time of the monitoring object;

[0015] Sequentially screen the new energy vehicle list with the vehicle model, geographical location, and charging and discharging time of the monitored object as screening conditions to obtain the cluster object cluster, so that the number of new energy vehicles in the cluster object cluster falls within the cluster object number range formed by the upper bound of the cluster object number and the lower bound of the cluster object number.

[0016] Further, the step of sequentially screening the new energy vehicle list with the vehicle model, geographical location, and charging and discharging time of the monitored object as screening conditions to obtain the cluster object cluster specifically includes:

[0017] Screen the new energy vehicle list with the vehicle model of the monitored object as the screening condition to obtain the first candidate object list;

[0018] Judge whether the number of new energy vehicles in the first candidate object list falls within the cluster object number range formed by the upper bound of the cluster object number and the lower bound of the cluster object number;

[0019] When the number of new energy vehicles in the first candidate object list is greater than the upper bound of the cluster object number, screen the first candidate object list with the geographical location of the monitored object as the screening condition to obtain the second candidate object list;

[0020] Judge whether the number of new energy vehicles in the second candidate object list falls within the cluster object number range formed by the upper bound of the cluster object number and the lower bound of the cluster object number;

[0021] When the number of new energy vehicles in the second candidate object list is greater than the upper bound of the cluster object number, screen to obtain a cluster object cluster that falls within the cluster object number range formed by the upper bound of the cluster object number and the lower bound of the cluster object number based on the deviation between the last charging and discharging time of the new energy vehicles in the second candidate object list and the current time.

[0022] Further, the step of screening to obtain a cluster object cluster that falls within the cluster object number range formed by the upper bound of the cluster object number and the lower bound of the cluster object number based on the deviation between the last charging and discharging time of the new energy vehicles in the second candidate object list and the current time specifically includes:

[0023] Determine a target cluster object number between the upper bound of the cluster object number and the lower bound of the cluster object number;

[0024] Calculate the deviation between the last charging and discharging time of the new energy vehicles in the second candidate object list and the current time;

[0025] Sort the new energy vehicles in the second candidate object list in ascending order of the deviation between the most recent charge and discharge time of the new energy vehicle and the current time;

[0026] Intercept the new energy vehicles with the same quantity as the number of target clustering objects from the re-sorted second candidate object list to construct the clustering object cluster.

[0027] Further, before the step of clustering the charge and discharge parameters of the new energy vehicles in the clustering object cluster, it also includes:

[0028] Determine the key time nodes of the entire charge and discharge process of the new energy vehicle, and the key time nodes include the two end nodes of the charge and discharge process;

[0029] Scale and align the charge and discharge parameters in the charge and discharge process of the new energy vehicles in the clustering cluster based on the key time nodes;

[0030] Regenerate the time data in the time data sequence of the new energy vehicle.

[0031] Further, the step of scaling and aligning the charge and discharge parameters in the charge and discharge process of the new energy vehicles in the clustering cluster based on the key time nodes specifically includes:

[0032] The charge and discharge parameters already uploaded by the monitoring object during the current charge and discharge process;

[0033] Predict the next key time node of the monitoring object;

[0034] Based on the known key time nodes of the charge and discharge parameters already uploaded by the monitoring object and the predicted next key time node, scale and align the charge and discharge parameters of the monitoring object with the charge and discharge parameters in the charge and discharge process of the new energy vehicles in the clustering cluster.

[0035] Further, the step of clustering the charge and discharge parameters of the new energy vehicles in the clustering object cluster specifically includes:

[0036] Obtain the pre-configured clustering analysis period;

[0037] Construct a clustering analysis data set of the clustering object cluster in each clustering analysis period;

[0038] Map the charge and discharge parameters in the clustering analysis data set to the vector space;

[0039] Perform clustering analysis on the charge and discharge parameters in the clustering analysis data set in the vector space.

[0040] Further, the steps of constructing the clustering analysis data set of the clustering object cluster in each clustering analysis cycle specifically include:

[0041] In each clustering analysis cycle, determine a clustering analysis time point to perform the following steps:

[0042] Obtain the first charge and discharge parameter of the monitored object at the clustering analysis time point;

[0043] Map the clustering analysis time point to the time data after scaling and alignment of the monitored object to determine a standardized analysis time point;

[0044] Determine the relative positional relationship between the standardized analysis time point and the front and back key time nodes in the time data after scaling and alignment of the monitored object;

[0045] According to the relative positional relationship, obtain the second charge and discharge parameter of other new energy vehicles in the clustering object cluster corresponding to the standardized analysis time point except the monitored object;

[0046] Merge the first charge and discharge parameter and the second charge and discharge parameter into a clustering analysis data set.

[0047] Further, the steps of performing safety anomaly identification on the charge and discharge process of the monitored object according to the clustering result specifically include:

[0048] Determine the vector mapped to the vector space from the first charge and discharge parameter as the target vector;

[0049] Judge whether the target vector is a discrete point after clustering in the vector space, or whether the number of other vectors included in the cluster to which the target vector belongs is less than a preset value;

[0050] When the target vector is a discrete point after clustering in the vector space, or the number of other vectors included in the cluster to which the target vector belongs is less than a preset value, determine that a safety anomaly occurs in the charge and discharge process of the monitored object.

[0051] The present invention provides a charge and discharge safety monitoring system and method for a new energy vehicle battery. The charge and discharge safety monitoring system includes a cloud server for providing charge and discharge safety monitoring services for the new energy vehicle battery, and a plurality of new energy vehicles communicatively connected to the cloud server. The new energy vehicles upload real-time charge and discharge data to the cloud server, so that the cloud server performs charge and discharge safety monitoring on the new energy vehicles based on the charge and discharge data. The cloud server is configured to perform cluster analysis on a cluster of new energy vehicles connected to it that have the same or similar internal charge and discharge attributes and the same or similar external charge and discharge environmental conditions, so as to identify safety anomalies in the charge and discharge processes of the new energy vehicles according to the results of the cluster analysis, and can accurately predict in a timely manner the charge and discharge anomalies of the new energy vehicle battery, thereby fully and effectively protecting people's personal and property safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a schematic diagram of a charge and discharge safety monitoring system for a new energy vehicle battery provided by an embodiment of the present invention;

[0053] Figure 2 is a flowchart of a charge and discharge safety monitoring method for a new energy vehicle battery provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.

[0055] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention may be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0056] In the description of the present invention, the term "a plurality of" refers to two or more, unless otherwise clearly defined. The orientation or positional relationship indicated by terms such as "upper", "lower", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. Terms such as "connection", "installation", "fixation", etc. should all be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In addition, terms such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", etc. may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0057] In the description of this specification, the description of terms such as "an embodiment", "some embodiments", "specific embodiments", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or instance. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0058] Next, a charge and discharge safety monitoring system and method for a new energy vehicle battery according to some embodiments of the present invention will be described with reference to the drawings.

[0059] As Figure 1 shown, in the first aspect of the present invention, a charge and discharge safety monitoring system for a new energy vehicle battery is proposed, including a cloud server for providing charge and discharge safety monitoring services for the new energy vehicle battery, and a number of new energy vehicles communicatively connected to the cloud server. The new energy vehicles upload real-time charge and discharge data to the cloud server, so that the cloud server performs charge and discharge safety monitoring on the new energy vehicles based on the charge and discharge data. The cloud server is configured to perform clustering analysis on a cluster of new energy vehicles connected to it with the same or similar internal charge and discharge attributes and the same or similar external charge and discharge environmental conditions, so as to identify safety anomalies in the charge and discharge process of the new energy vehicles according to the clustering analysis results.

[0060] Specifically, the cloud server is a server device that provides cloud services for the Internet. A charging and discharging safety monitoring service program is running on the cloud server to provide charging and discharging safety monitoring services for the connected new energy vehicles. The new energy vehicle accesses the Internet through 5G or other Internet of Things communication networks to establish a communication connection with the cloud server.

[0061] In the technical solutions of some embodiments of the present invention, after the new energy vehicle establishes a communication connection with the cloud server, it registers in the charging and discharging safety monitoring service program to obtain an identity identifier assigned by the cloud server for uniquely representing the new energy vehicle.

[0062] In the technical solutions of other embodiments of the present invention, the identity identifier is a unique identity identifier pre-configured in the storage module of the new energy vehicle before leaving the factory. The new energy vehicle interacts with the charging and discharging safety monitoring service program in the cloud server based on the unique identity identifier, without the need for registration, assignment, and binding after leaving the factory.

[0063] The internal charging and discharging attributes are internal attributes related to the charging and discharging of the new energy vehicle battery, including but not limited to one or more of the rated capacity, rated power, and rated voltage of the new energy vehicle battery. When we say that two new energy vehicles have the same internal charging and discharging attributes, it means that all the internal charging and discharging attributes of these two new energy vehicles are the same. When we say that two new energy vehicles have similar internal charging and discharging attributes, it means that some of the internal charging and discharging attributes of these two new energy vehicles are the same, and the difference between the different internal charging and discharging attributes is less than a preset threshold.

[0064] The external charging and discharging environmental conditions are external environmental conditions related to the charging and discharging of the new energy vehicle, including but not limited to one or more of geographical location, environmental temperature, and air humidity. The geographical location is used to reflect the grid state, charging equipment state, and other external environmental conditions related to charging and discharging that are difficult to detect and quantify at the location where the new energy vehicle is located. Similarly, when we say that two new energy vehicles have the same external charging and discharging environmental conditions, it means that all the external charging and discharging environmental conditions of these two new energy vehicles are the same. When we say that two new energy vehicles have similar external charging and discharging environmental conditions, it means that some of the external charging and discharging environmental conditions of these two new energy vehicles are the same, and the difference between the different external charging and discharging environmental conditions is less than a preset threshold.

[0065] In the technical solution of the above embodiment, when the monitored object is a new energy vehicle undergoing rapid charging, the most recent charge-discharge behavior of the new energy vehicle refers to the most recent rapid charging behavior of the new energy vehicle. Similarly, when the monitored object is a new energy vehicle undergoing rapid discharging, the most recent charge-discharge behavior of the new energy vehicle refers to the most recent rapid discharging behavior of the new energy vehicle.

[0066] Further, the cloud server in the charge-discharge safety monitoring system of the new energy vehicle battery is configured to implement the charge-discharge safety monitoring method for the new energy vehicle battery provided in the second aspect of the present invention.

[0067] As Figure 2 shown, the second aspect of the present invention proposes a charge-discharge safety monitoring method for a new energy vehicle battery, including:

[0068] Determine the new energy vehicle to be monitored as the monitored object, where the monitored object is a new energy vehicle undergoing rapid charging or rapid discharging;

[0069] Obtain the real-time charge-discharge parameters of the monitored object, where the charge-discharge parameters include one or more of the charge-discharge current, charge-discharge voltage, and charge-discharge power of the power battery of the monitored object;

[0070] Determine the clustering object cluster of the monitored object in the new energy vehicle list, where each new energy vehicle in the clustering object cluster has the same or similar internal charge-discharge attributes and the same or similar external charge-discharge environmental conditions as the monitored object;

[0071] Obtain the charge-discharge parameters of each new energy vehicle in the clustering object cluster, where the charge-discharge parameters are the charge-discharge parameters of the most recent charge-discharge behavior of the new energy vehicle in the clustering object cluster;

[0072] Cluster the associated charge-discharge parameters of the new energy vehicles in the clustering object cluster;

[0073] Identify safety anomalies in the charge-discharge process of the monitored object according to the clustering results.

[0074] Specifically, during the charging and discharging processes, the new energy vehicle uploads the charging and discharging data to the cloud server in real time. The cloud server determines whether the new energy vehicle is undergoing rapid charging or rapid discharging based on the charging and discharging data. Here, rapid charging of the new energy vehicle means that the new energy vehicle uses a fast charging mode for charging, that is, the process of rapid charging with a large charging current through a high-power charging pile. Rapid discharging of the new energy vehicle means that the new energy vehicle discharges with a large output power in order to obtain greater output power. The so-called high power, large charging current, and large output power, etc. are all judged using pre-configured empirical values.

[0075] In the technical solution of the above embodiment, since the risk coefficient of low-power charging or low-power discharging is relatively low and the safety monitoring system of the new energy vehicle itself is sufficient to handle it, the cloud server only performs safety monitoring on the rapid charging and rapid discharging of the new energy vehicle.

[0076] Preferably, the charging and discharging parameters include, but are not limited to, one or more of the charging and discharging current, charging and discharging voltage, and charging and discharging power of each single battery in the power battery of the new energy vehicle.

[0077] Further, the steps of obtaining the real-time charging and discharging parameters of the monitoring object specifically include:

[0078] Determine the current charging and discharging behavior of the monitoring object, where the charging and discharging behavior includes rapid charging behavior and rapid discharging behavior;

[0079] Obtain the charging and discharging data of the current charging and discharging behavior of the monitoring object, where the charging and discharging data includes the charging and discharging parameters of the charging and discharging behavior and their corresponding sampling times;

[0080] Construct the charging and discharging data of the monitoring object into a time data sequence composed of discrete charging and discharging parameters and their sampling times.

[0081] The new energy vehicle list is a collection of new energy vehicles bound to the cloud server and assigned unique identity identifiers. The new energy vehicles in the new energy vehicle list achieve charging and discharging safety monitoring through the charging and discharging safety monitoring service program running in the cloud server. The clustering object cluster is a cluster of new energy vehicles including the monitoring object, and the clustering object cluster is a subset of the new energy vehicle list.

[0082] Further, the steps of determining the clustering object cluster of the monitoring object in the new energy vehicle list specifically include:

[0083] Configure an upper bound and a lower bound for the number of clustering objects that limit the number of clustering objects in the clustering object cluster;

[0084] Obtain the vehicle model, geographical location, and charge and discharge time of the monitored object;

[0085] Sequentially use the vehicle model, geographical location, and charge and discharge time of the monitored object as screening conditions to screen out the cluster object cluster from the new energy vehicle list, so that the number of new energy vehicles in the cluster object cluster falls within the cluster object number range composed of the upper bound of the cluster object number and the lower bound of the cluster object number.

[0086] Specifically, the upper bound of the cluster object number and the lower bound of the cluster object number together form a cluster object number range including the upper bound of the cluster object number and the lower bound of the cluster object number, and the number of new energy vehicles in the cluster object cluster falls within the cluster object number range.

[0087] Further, the steps of sequentially using the vehicle model, geographical location, and charge and discharge time of the monitored object as screening conditions to screen out the cluster object cluster from the new energy vehicle list specifically include:

[0088] Use the vehicle model of the monitored object as the screening condition to screen out the first candidate object list from the new energy vehicle list;

[0089] Judge whether the number of new energy vehicles in the first candidate object list falls within the cluster object number range composed of the upper bound of the cluster object number and the lower bound of the cluster object number;

[0090] When the number of new energy vehicles in the first candidate object list is greater than the upper bound of the cluster object number, use the geographical location of the monitored object as the screening condition to screen out the second candidate object list from the first candidate object list;

[0091] Judge whether the number of new energy vehicles in the second candidate object list falls within the cluster object number range composed of the upper bound of the cluster object number and the lower bound of the cluster object number;

[0092] When the number of new energy vehicles in the second candidate object list is greater than the upper bound of the cluster object number, screen out a cluster object cluster that falls within the cluster object number range composed of the upper bound of the cluster object number and the lower bound of the cluster object number based on the deviation between the most recent charge and discharge time of the new energy vehicles in the second candidate object list and the current time.

[0093] In the technical solution of the above embodiment, the new energy vehicles in the first candidate object list are new energy vehicles with the same vehicle model as the monitored object.

[0094] Further, after the step of determining whether the number of new energy vehicles in the first candidate object list falls within the clustering object number range formed by the upper bound of the clustering object number and the lower bound of the clustering object number, the following steps are further included:

[0095] When the number of new energy vehicles in the first candidate object list is less than the lower bound of the clustering object number, it is determined that the monitoring object does not meet the conditions for identifying safety anomalies in its charging and discharging process through clustering analysis.

[0096] In the technical solutions of some other embodiments of the present invention, when the number of new energy vehicles in the first candidate object list is less than the lower bound of the clustering object number, new energy vehicles with the same model power battery as the monitoring object can be determined in the new energy vehicle list and supplemented into the first candidate object list. However, in addition to the power battery itself, other components of new energy vehicles such as the electrical system and the power system also constitute internal factors affecting their charging and discharging safety. Therefore, when using new energy vehicles with the same model power battery as the monitoring object to supplement the first candidate object list and then performing clustering analysis, the reliability of the analysis results for identifying safety anomalies in the charging and discharging process of new energy vehicles is relatively low.

[0097] Further, after the step of determining whether the number of new energy vehicles in the second candidate object list falls within the clustering object number range formed by the upper bound of the clustering object number and the lower bound of the clustering object number, the following steps are further included:

[0098] When the number of new energy vehicles in the second candidate object list is less than the lower bound of the clustering object number, a clustering object cluster that falls within the clustering object number range formed by the upper bound of the clustering object number and the lower bound of the clustering object number is screened based on the deviation between the most recent charging and discharging time of the new energy vehicles in the first candidate object list and the current time.

[0099] In the technical solutions of the above embodiments, when the monitoring object is a new energy vehicle undergoing rapid charging, the most recent charging and discharging time of the new energy vehicle refers to the time of the most recent rapid charging of the new energy vehicle. Similarly, when the monitoring object is a new energy vehicle undergoing rapid discharging, the most recent charging and discharging time of the new energy vehicle refers to the time of the most recent rapid discharging of the new energy vehicle.

[0100] Further, the step of screening a clustering object cluster that falls within the clustering object number range formed by the upper bound of the clustering object number and the lower bound of the clustering object number based on the deviation between the most recent charging and discharging time of the new energy vehicles in the first candidate object list and the current time specifically includes:

[0101] Determine a target number of clustering objects between the upper bound and the lower bound of the number of clustering objects;

[0102] Calculate the difference between the target number of clustering objects and the number of new energy vehicles in the second candidate object list;

[0103] Use the new energy vehicles in the first candidate object list that are not included in the second candidate object list to construct a third candidate object list;

[0104] Based on the deviation between the last charge and discharge time of the new energy vehicles in the third candidate object list and the current time, screen out the same number of new energy vehicles as the difference to construct a fourth candidate object list;

[0105] Merge the fourth candidate object list with the new energy vehicles in the second candidate object list into the clustering object cluster.

[0106] Preferably, the target number of clustering objects is the average of the upper bound and the lower bound of the number of clustering objects.

[0107] Further, the step of screening out the same number of new energy vehicles as the difference based on the deviation between the last charge and discharge time of the new energy vehicles in the third candidate object list and the current time to construct a fourth candidate object list specifically includes:

[0108] Calculate the deviation between the last charge and discharge time of the new energy vehicles in the third candidate object list and the current time;

[0109] Sort the new energy vehicles in the third candidate object list in ascending order according to the deviation between the last charge and discharge time and the current time;

[0110] Intercept the same number of new energy vehicles as the difference from the re-sorted third candidate object list to construct the fourth candidate object list.

[0111] Further, the step of screening out a clustering object cluster that falls within the range of the number of clustering objects formed by the upper bound and the lower bound of the number of clustering objects based on the deviation between the last charge and discharge time of the new energy vehicles in the second candidate object list and the current time specifically includes:

[0112] Determine a target number of clustering objects between the upper bound and the lower bound of the number of clustering objects;

[0113] Calculate the deviation between the last charge and discharge time of the new energy vehicle in the second candidate object list and the current time;

[0114] Sort the new energy vehicles in the second candidate object list in ascending order of the deviation between the last charge and discharge time of the new energy vehicle in the second candidate object list and the current time;

[0115] Intercept the new energy vehicles with the same number as the target clustering object number from the re - sorted second candidate object list to construct the clustering object cluster.

[0116] Further, the steps of obtaining the charge - discharge parameters of each new energy vehicle in the clustering object cluster specifically include:

[0117] Determine the current charge - discharge behavior of the monitoring object, and the charge - discharge behavior includes fast charging behavior and fast discharging behavior;

[0118] Traverse each new energy vehicle in the clustering object cluster to perform the following steps:

[0119] Determine the current traversed new energy vehicle as the target new energy vehicle;

[0120] Obtain the charge - discharge data of the charge - discharge behavior of the target new energy vehicle that is the same as the current charge - discharge behavior of the monitoring object, and the charge - discharge data includes the charge - discharge parameters of the charge - discharge behavior and its corresponding sampling time;

[0121] Construct the charge - discharge data of the target new energy vehicle into a time data sequence composed of discrete charge - discharge parameters and their sampling times.

[0122] Specifically, the real - time charge - discharge data reported by the new energy vehicle to the cloud server during the charge - discharge process includes the numerical value of its charge - discharge parameters and the sampling time corresponding to each data. In the technical solution of the above - mentioned embodiment, the steps of obtaining the charge - discharge data of the charge - discharge behavior of the target new energy vehicle that is the same as the current charge - discharge behavior of the monitoring object specifically include obtaining the charge - discharge parameters of the target new energy vehicle corresponding to the charge - discharge behavior, and the sampling time corresponding to each numerical value in the charge - discharge parameters.

[0123] The time data sequence is composed of a number of data elements, and each data element consists of a discrete charge-discharge parameter value and its corresponding sampling time. Exemplarily, during a rapid discharge process of the target new energy vehicle, a total of n discrete discharge power values are collected, and there are n corresponding sampling times. Therefore, the time data sequence corresponding to this rapid discharge process of the target new energy vehicle is composed of n data elements, and each data element includes a key-value pair consisting of a discharge power value and its sampling time.

[0124] Further, before the step of clustering the charge-discharge parameters of the new energy vehicles in the clustering object cluster, it further includes:

[0125] Determine the key time nodes of the entire charge-discharge process of the new energy vehicle, and the key time nodes include two end nodes of the charge-discharge process;

[0126] Scale and align the charge-discharge parameters in the charge-discharge process of the new energy vehicles in the clustering cluster based on the key time nodes;

[0127] Regenerate the time data in the time data sequence of the new energy vehicle.

[0128] Specifically, when the charge-discharge process is a rapid charging process, it has several fixed key time nodes, including the constant current charging start node for switching from pre-charging to constant current charging, the constant voltage charging start node for switching from constant current charging to constant voltage charging, the floating charge start node for switching from constant voltage charging to floating charge, etc. At the same time, it also includes the charging start node and the charging end node during the entire charging process. Since during the discharge process, its discharge parameters usually do not have a fixed change pattern, when the charge-discharge process is a rapid discharge process, it only includes two fixed key time nodes, namely the discharge start node and the discharge end node of the entire discharge process.

[0129] Further, the step of scaling and aligning the charge-discharge parameters in the charge-discharge process of the new energy vehicles in the clustering cluster based on the key time nodes specifically includes:

[0130] Determine the fixed key time nodes in the charge-discharge process;

[0131] Respectively scale the charge parameters between two adjacent fixed time nodes to align the key time nodes in the charge-discharge process of the new energy vehicles in the clustering cluster.

[0132] Before scaling alignment, the time data in the time data sequence corresponding to the charging and discharging parameters of new energy vehicles is the sampling time corresponding to each charging and discharging parameter value, that is, it is a natural time with information such as year, month, day, hour, minute, and second. Of course, according to different accuracy requirements, it can be accurate to milliseconds or other time units.

[0133] After scaling alignment, the regenerated time data in the time data sequence of new energy vehicles is the time data after standardization processing. It can be in milliseconds and is a time sequence starting from 0. After scaling alignment, the time data in the charging and discharging parameters of all new energy vehicles in the cluster of clustering objects has the same start time and end time. When the charging and discharging process is a fast charging process, the times corresponding to several fixed key time nodes in the middle are also the same.

[0134] Further, the steps of scaling and aligning the charging and discharging parameters in the charging and discharging process of new energy vehicles in the clustering cluster based on the key time nodes specifically include:

[0135] The charging and discharging parameters already uploaded by the monitoring object during the current charging and discharging process;

[0136] Predict the next key time node of the monitoring object;

[0137] Based on the known key time nodes of the charging and discharging parameters already uploaded by the monitoring object and the predicted next key time node, scale and align the charging and discharging parameters of the monitoring object with the charging and discharging parameters in the charging and discharging process of new energy vehicles in the clustering cluster.

[0138] Further, in the step of predicting the next key time node of the monitoring object, an artificial intelligence model based on deep learning is used to predict the charging and discharging parameters of the monitoring object, so as to determine the next key time node of the monitoring object according to the predicted charging and discharging parameters. More specifically, the historical charging and discharging data of the monitoring object or other new energy vehicles can be used as sample data, and an artificial intelligence prediction model for predicting charging and discharging parameters can be trained through deep learning technology.

[0139] In the technical solution of the above embodiment, the known key time node is the key time node included in the charging and discharging parameters already uploaded by the monitoring object to the cloud server. The next key time node is the key time node that is not included in the charging and discharging parameters already uploaded by the monitoring object to the cloud server after the last key time node in the known key time nodes, and it can be identified from the charging and discharging parameters predicted by using the artificial intelligence model.

[0140] Further, the steps of clustering the charging and discharging parameters of the new energy vehicles in the cluster of clustering objects specifically include:

[0141] Obtain a pre-configured clustering analysis period;

[0142] Construct a clustering analysis data set of the cluster of clustering objects in each clustering analysis period;

[0143] Map the charging and discharging parameters in the clustering analysis data set to a vector space;

[0144] Perform clustering analysis on the charging and discharging parameters in the clustering analysis data set in the vector space.

[0145] In the technical solution of the above embodiment, according to specific implementation requirements, considering factors such as the number of monitored new energy vehicles, the probability of abnormal charging and discharging of new energy vehicles, and the performance and load pressure of the cloud server, the clustering analysis period can be configured as a time period of an appropriate length.

[0146] The clustering analysis data set is a data collection composed of the charging and discharging parameters of each new energy vehicle in the cluster of clustering objects at a specific time point within a clustering analysis period.

[0147] The vector space is a multi-dimensional vector space, and the number of its dimensions is related to the number of charging and discharging parameters collected during the charging and discharging process. Taking the example that during the fast charging process, the charging and discharging parameters are composed of three parameters: charging power, charging voltage, and charging current, then the vector space is a three-dimensional vector space composed of three dimensions: charging power dimension, charging voltage dimension, and charging current dimension.

[0148] Further, the steps of constructing the clustering analysis data set of the cluster of clustering objects in each clustering analysis period specifically include:

[0149] Determine a clustering analysis time point in each clustering analysis period to perform the following steps:

[0150] Obtain the first charging and discharging parameters of the monitored object at the clustering analysis time point;

[0151] Map the clustering analysis time point to the time data after scaling and alignment of the monitored object to determine a standardized analysis time point;

[0152] Determine the relative positional relationship between the standardized analysis time point and the front and rear key time nodes in the time data after scaling and alignment of the monitored object;

[0153] Obtain the second charge and discharge parameters corresponding to new energy vehicles other than the monitored object in the cluster of clustering objects according to the relative position relationship at the standardized analysis time point;

[0154] Combine the first charge and discharge parameters and the second charge and discharge parameters into a clustering analysis data set.

[0155] Specifically, the clustering analysis time point can be any time point during a clustering analysis period. Usually, the starting time point of each clustering analysis period can be used as the clustering analysis time point. Similarly, the clustering analysis time point is a natural time, and the standardized analysis time point is the corresponding time point in the standardized time data after the clustering analysis time point is mapped after scaling the object.

[0156] Further, in the step of determining the relative position relationship between the standardized analysis time point and the key time nodes before and after in the time data after scaling and aligning the monitored object, the relative position relationship can be the ratio of the absolute value of the difference between the standardized analysis time point and the key time nodes before and after.

[0157] Further, the steps of performing safety anomaly identification on the charge and discharge process of the monitored object according to the clustering result specifically include:

[0158] Determine the vector mapped from the first charge and discharge parameter to the vector in the vector space as the target vector;

[0159] Judge whether the target vector is a discrete point after clustering in the vector space, or whether the number of other vectors included in the cluster to which the target vector belongs is less than a preset value;

[0160] When the target vector is a discrete point after clustering in the vector space, or the number of other vectors included in the cluster to which the target vector belongs is less than a preset value, it is determined that a safety anomaly occurs in the charge and discharge process of the monitored object.

[0161] Specifically, when the target vector cannot be classified into the same family as the vector mapped from the second charge and discharge parameter of any new energy vehicle in the cluster of clustering objects in the vector space, the target vector is regarded as a discrete point.

[0162] The other vectors mentioned in the above embodiments refer to the vectors mapped from the second charge and discharge parameters of new energy vehicles other than the monitored object in the cluster of clustering objects in the vector space.

[0163] It should be noted that, in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0164] As described above with reference to the embodiments of the present invention, these embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the above description. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can make good use of the present invention and its modifications based on the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A method for monitoring the charging and discharging safety of a new energy vehicle battery, characterized in that, Including: Determine a new energy vehicle to be monitored as a monitoring object, where the monitoring object is a new energy vehicle undergoing rapid charging or rapid discharging; Obtain real-time charge and discharge parameters of the monitoring object, where the charge and discharge parameters include one or more of the charge and discharge current, charge and discharge voltage, and charge and discharge power of the power battery of the monitoring object; Determine a cluster of clustering objects of the monitoring object in the new energy vehicle list, where each new energy vehicle in the cluster of clustering objects has the same or similar inherent charge and discharge attributes and the same or similar external charge and discharge environmental conditions as the monitoring object; Obtain the charge and discharge parameters of each new energy vehicle in the cluster of clustering objects, where the charge and discharge parameters are the charge and discharge parameters of the most recent charge and discharge behavior of the new energy vehicles in the cluster of clustering objects; Cluster the associated charge and discharge parameters of the new energy vehicles in the cluster of clustering objects; Identify safety anomalies in the charge and discharge process of the monitoring object according to the clustering results; The step of determining the cluster of clustering objects of the monitoring object in the new energy vehicle list specifically includes: Configure an upper bound and a lower bound of the number of clustering objects for restricting the number of clustering objects in the cluster of clustering objects; Obtain the vehicle type, geographical location, and charge and discharge time of the monitoring object; Sequentially use the vehicle type, geographical location, and charge and discharge time of the monitoring object as screening conditions to screen out the cluster of clustering objects in the new energy vehicle list, so that the number of new energy vehicles in the cluster of clustering objects falls within the range of the number of clustering objects formed by the upper bound and the lower bound of the number of clustering objects; The step of sequentially using the vehicle type, geographical location, and charge and discharge time of the monitoring object as screening conditions to screen out the cluster of clustering objects in the new energy vehicle list specifically includes: Use the vehicle type of the monitoring object as a screening condition to screen out a first candidate object list in the new energy vehicle list; Judge whether the number of new energy vehicles in the first candidate object list falls within the range of the number of clustering objects formed by the upper bound and the lower bound of the number of clustering objects; When the number of new energy vehicles in the first candidate object list is greater than the upper bound of the number of clustering objects, use the geographical location of the monitoring object as a screening condition to screen out a second candidate object list in the first candidate object list; Judge whether the number of new energy vehicles in the second candidate object list falls within the range of the number of clustering objects formed by the upper bound and the lower bound of the number of clustering objects; When the number of new energy vehicles in the second candidate object list is greater than the upper bound of the number of clustering objects, screen out a cluster of clustering objects that falls within the range of the number of clustering objects formed by the upper bound and the lower bound of the number of clustering objects based on the deviation between the most recent charge and discharge time of the new energy vehicles in the second candidate object list and the current time.

2. The method for charging and discharging safety monitoring of a new energy vehicle battery according to claim 1, wherein The step of screening to obtain a cluster object cluster that falls within the range of the upper bound and the lower bound of the number of cluster objects based on the deviation between the last charge-discharge time of the new energy vehicle in the second candidate object list and the current time specifically includes: Determine a target number of cluster objects between the upper bound and the lower bound of the number of cluster objects; Calculate the deviation between the last charge-discharge time of the new energy vehicle in the second candidate object list and the current time; Sort the new energy vehicles in the second candidate object list in ascending order of the deviation between the last charge-discharge time of the new energy vehicle in the second candidate object list and the current time; Intercept the new energy vehicles with the same number as the target number of cluster objects from the re-sorted second candidate object list to construct the cluster object cluster.

3. The charging and discharging safety monitoring method for the new energy vehicle battery according to claim 1, characterized in that, Before the step of clustering the charge-discharge parameters of the new energy vehicles in the cluster object cluster, it further includes: Determine the key time nodes of the entire charge-discharge process of the new energy vehicle, and the key time nodes include two end nodes of the charge-discharge process; Scale-align the charge-discharge parameters in the charge-discharge process of the new energy vehicles in the cluster cluster based on the key time nodes; Regenerate the time data in the time data sequence of the new energy vehicle.

4. The charging and discharging safety monitoring method for the new energy vehicle battery according to claim 3, characterized in that, The step of scale-aligning the charge-discharge parameters in the charge-discharge process of the new energy vehicles in the cluster cluster based on the key time nodes specifically includes: The charge-discharge parameters already uploaded by the monitoring object in the current charge-discharge process; Predict the next key time node of the monitoring object; Based on the known key time nodes of the charge-discharge parameters already uploaded by the monitoring object and the predicted next key time node, scale-align the charge-discharge parameters of the monitoring object with the charge-discharge parameters in the charge-discharge process of the new energy vehicles in the cluster cluster.

5. The charging and discharging safety monitoring method for the new energy vehicle battery according to claim 4, wherein The step of clustering the charge-discharge parameters of the new energy vehicles in the cluster object cluster specifically includes: Obtain the pre-configured clustering analysis period; Construct a clustering analysis data set of the cluster object cluster in each clustering analysis period; Map the charge-discharge parameters in the clustering analysis data set to the vector space; Perform clustering analysis on the charge-discharge parameters in the clustering analysis data set in the vector space.

6. The method for charging and discharging safety monitoring of a new energy vehicle battery according to claim 5, characterized in that, The step of constructing a clustering analysis data set of the cluster object cluster in each clustering analysis period specifically includes: Determine a clustering analysis time point in each clustering analysis period to perform the following steps: Obtain the first charge-discharge parameter of the monitoring object at the clustering analysis time point; Map the clustering analysis time point to the time data after the monitoring object is scale-aligned to determine a standardized analysis time point; Determine the relative position relationship between the standardized analysis time point and the front and back key time nodes in the time data after the monitoring object is scale-aligned; Obtain the second charge-discharge parameters corresponding to other new energy vehicles except the monitored object in the cluster object cluster according to the relative position relationship for the standardized analysis time point; Merge the first charge-discharge parameter and the second charge-discharge parameter into a clustering analysis data set.

7. The method for charging and discharging safety monitoring of a new energy vehicle battery according to claim 6, wherein, The steps of performing safety anomaly identification on the charge-discharge process of the monitored object according to the clustering result specifically include: Determine the vector obtained by mapping the first charge-discharge parameter to the vector in the vector space as the target vector; Judge whether the target vector is a discrete point after clustering in the vector space, or whether the number of other vectors included in the cluster to which the target vector belongs is less than a preset value; When the target vector is a discrete point after clustering in the vector space, or the number of other vectors included in the cluster to which the target vector belongs is less than a preset value, determine that a safety anomaly occurs in the charge-discharge process of the monitored object.

Images