Aging detection method, aging detection device, and computer-readable storage medium

Abstract

The application provides an aging detection method, an aging detection device and a computer readable storage medium for an electric drive system, wherein the electric drive system comprises a motor, a motor control device and a cooling mechanism for the motor and the motor control device, and the method comprises the following steps: S100, judging whether a vehicle is in a preset working condition based on a vehicle state parameter; S200, in response to the vehicle being in the preset working condition, judging an overall aging degree of the electric drive system based on monitoring data of the cooling mechanism within a preset time, wherein the monitoring data comprises an inlet temperature and an outlet temperature of a cooling medium at the motor control device, an inlet temperature and an outlet temperature of the cooling medium at the motor and a cooling medium flow; and S300, in response to the overall aging degree reaching a preset aging level, determining an aging type according to an aging root cause positioning model, wherein the aging type represents position information of the aging about each subcomponent of the motor and the motor control device.

Description

Technical Field

[0001] The present invention relates to an aging detection method for an electric drive system, as well as an aging detection apparatus and a computer-readable storage medium for performing the method. Background Technology

[0002] The electric drive system is a key component used for drive control that converts high-voltage electrical energy into mechanical energy, as well as feedback control that converts mechanical energy into high-voltage electrical energy. During its operation, critical components within the electric drive system (such as power modules, busbars, capacitors, and shaft gears) bear loads of high voltage, alternating high current, high speed, high torque, or high heat. These are weak points in new energy vehicles that are prone to fatigue failure.

[0003] Currently, the diagnosis of abnormal conditions or aging of key components in electric drive systems is either lacking or relies on indirect methods such as torque monitoring or abnormality diagnosis using sensors like temperature sensors, current sensors, and resolvers. This results in insufficient degraded operating time before a vehicle stops due to a malfunction, and drivers lack sufficient warning time to take emergency evasive action. If a vehicle malfunctions at high speed, a sudden loss of power or an unexpected increase in power is extremely dangerous. Furthermore, if a malfunction is only diagnosed after it has occurred, the damage is often more extensive, and repair costs are higher.

[0004] If the health status or abnormalities of components can be accurately detected, and early warnings or maintenance can be carried out when the health status of a component falls below a certain value or when an abnormality is detected, it will help improve the reliability of the product throughout its entire life cycle.

[0005] Currently, fault detection methods for electric drive systems include checking the entire system, especially its cooling system, for overheating. If the result is positive, the electric drive system is considered faulty. However, this method has limitations. First, it cannot pinpoint the exact location of the fault within the electric drive system. Second, the impact of a single component failure on the overall temperature rise of the cooling system is relatively insignificant, thus failing to achieve optimal fault detection results. Summary of the Invention

[0006] Depending on the specific aspects, the object of the present invention is to provide an improved method for aging detection of an electric drive system, as well as an aging detection device and a computer-readable storage medium, wherein the detection method can locate the aging position with less expense.

[0007] Furthermore, the present invention aims to solve or alleviate other technical problems existing in the prior art.

[0008] This invention addresses the aforementioned problems by providing an aging detection method. Specifically, the electric drive system includes a motor, a motor control device, and a cooling mechanism for the motor and the motor control device, comprising the following steps:

[0009] S100: Based on vehicle status parameters, determine whether the vehicle is in a preset operating condition;

[0010] S200: In response to the vehicle being in the preset operating condition, the overall aging degree of the electric drive system is determined based on monitoring data from the cooling mechanism over a preset time period. The monitoring data includes the inlet and outlet temperatures of the cooling medium at the motor control device, the inlet and outlet temperatures of the cooling medium at the motor, and the cooling medium flow rate; and

[0011] S300: In response to the overall aging degree reaching a preset aging level, determine the aging type according to the aging root cause localization model, wherein the aging type characterizes the aging with respect to the location information of each sub-component of the motor and motor control device.

[0012] According to an aspect of the aging detection method proposed by the present invention, in step S100, it is determined whether the vehicle is in the preset operating condition based on a KNN clustering model that has been trained in advance with multiple sets of training data including the vehicle state parameters and corresponding labels. The vehicle state parameters include at least one of motor output torque value, motor speed value, current value, voltage value, and cooling medium flow rate; the labels characterize the preset operating condition type.

[0013] According to an aspect of the aging detection method of the present invention, step S200 includes the following sub-steps:

[0014] S210: Acquire monitoring data of the cooling mechanism within a preset time and input the monitoring data into the trained preliminary diagnostic model. The trained preliminary diagnostic model is constructed based on health history data under the preset working conditions using a multivariate statistical analysis method.

[0015] S220: Based on the trained preliminary diagnostic model, obtain the deviation statistics of the monitoring data and compare them with a preset threshold; and

[0016] S230: In response to the deviation statistical value exceeding the preset threshold, the overall aging degree of the electric drive system is determined.

[0017] According to an aspect of the aging detection method of the present invention, step S300 includes the following sub-steps:

[0018] S310: In response to the overall aging level of the electric drive system reaching a preset aging level, acquire the monitored temperature parameters of each sub-component within a preset time and / or the monitored cooling temperature parameters of the cooling mechanism at each sub-component; the monitored cooling temperature parameters are the inlet temperature and outlet temperature of the cooling medium at each sub-component; and

[0019] S320: Using the aging root cause model, determine the aging type based on the monitoring temperature parameter and / or monitoring cooling temperature parameter, wherein the aging root cause model is constructed based on multiple sets of training data containing health monitoring temperature parameters and / or health monitoring cooling temperature parameters using a multivariate statistical analysis method.

[0020] According to an aspect of the aging detection method of the present invention, in sub-step S310, the monitoring cooling temperature parameters of the cooling mechanism at each sub-component are obtained based on the thermal resistance of the cooling medium contained in the cooling mechanism, the thermal resistance of each sub-component, and the monitoring temperature parameters of each sub-component.

[0021] According to an aspect of the aging detection method of the present invention, sub-step S320 includes the following steps:

[0022] S321: Based on the aging root cause model, obtain the monitoring contribution rate of the monitored temperature parameter and / or monitored cooling temperature parameter, and the deviation between the monitored contribution rate and the theoretical contribution rate, wherein the theoretical contribution rate is obtained based on the corresponding health monitoring temperature parameter and / or health monitoring cooling temperature parameter under preset operating conditions; and

[0023] S322: Obtain the maximum value of the deviation between the monitored contribution rate and the theoretical contribution rate, and determine the sub-component to which the maximum value belongs as the aging location information.

[0024] According to one aspect of the aging detection method proposed by the present invention, the sub-components belonging to the motor control device include busbars, capacitors, power modules, on-board chargers, converters, and high-voltage junction boxes; the sub-components belonging to the motor include motor stators.

[0025] According to another aspect of the present invention, an aging detection device for an electric drive system is provided, the electric drive system including a motor, a motor control device, and a cooling mechanism for the motor and the motor control device, comprising:

[0026] Memory;

[0027] processor;

[0028] A computer program stored in the memory and executable on the processor, the execution of which causes the aging test method described above to be performed, the aging test method comprising the following steps:

[0029] S100: Based on vehicle status parameters, determine whether the vehicle is in a preset operating condition;

[0030] S200: In response to the vehicle being in the preset operating condition, the overall aging degree of the electric drive system is determined based on monitoring data from the cooling mechanism over a preset time period. The monitoring data includes the inlet and outlet temperatures of the cooling medium at the motor control device, the inlet and outlet temperatures of the cooling medium at the motor, and the cooling medium flow rate; and

[0031] S300: In response to the overall aging degree reaching a preset aging level, determine the aging type according to the aging root cause localization model, wherein the aging type characterizes the aging with respect to the location information of each sub-component of the motor and motor control device.

[0032] According to another aspect of the present invention, the aging detection device, when performing step S100, determines whether the vehicle is in the preset operating condition based on a KNN clustering model that has been trained in advance with multiple sets of training data including the vehicle state parameters and corresponding labels. The vehicle state parameters include at least one of motor output torque value, motor speed value, current value, voltage value, and cooling medium flow rate; the labels characterize the preset operating condition type.

[0033] According to another aspect of the present invention, the aging detection device performs the following sub-steps during step S200:

[0034] S210: Acquire monitoring data of the cooling mechanism within a preset time and input the monitoring data into the trained preliminary diagnostic model. The trained preliminary diagnostic model is constructed based on health history data under the preset working conditions using a multivariate statistical analysis method.

[0035] S220: Based on the trained preliminary diagnostic model, obtain the deviation statistics of the monitoring data and compare them with a preset threshold; and

[0036] S230: In response to the deviation statistical value exceeding the preset threshold, the overall aging degree of the electric drive system is determined.

[0037] According to another aspect of the present invention, the aging detection device, when performing step S300, performs the following sub-steps:

[0038] S310: In response to the overall aging level of the electric drive system reaching a preset aging level, acquire the monitored temperature parameters of each sub-component within a preset time and / or the monitored cooling temperature parameters of the cooling mechanism at each sub-component; the monitored cooling temperature parameters are the inlet temperature and outlet temperature of the cooling medium at each sub-component; and

[0039] S320: Using the aging root cause model, determine the aging type based on the monitoring temperature parameter and / or monitoring cooling temperature parameter, wherein the aging root cause model is constructed based on multiple sets of training data containing health monitoring temperature parameters and / or health monitoring cooling temperature parameters using a multivariate statistical analysis method.

[0040] According to another aspect of the present invention, the aging detection device, when performing sub-step S310, obtains the monitoring cooling temperature parameters of the cooling mechanism at each sub-component based on the thermal resistance of the cooling medium contained in the cooling mechanism, the thermal resistance of each sub-component, and the monitoring temperature parameters of each sub-component.

[0041] According to another aspect of the present invention, the aging detection apparatus, when performing sub-step S320, causes the following steps to be performed:

[0042] S321: Based on the aging root cause model, obtain the monitoring contribution rate of the monitored temperature parameter and / or monitored cooling temperature parameter, and the deviation between the monitored contribution rate and the theoretical contribution rate, wherein the theoretical contribution rate is obtained based on the corresponding health monitoring temperature parameter and / or health monitoring cooling temperature parameter under preset operating conditions; and

[0043] S322: Obtain the maximum value of the deviation between the monitored contribution rate and the theoretical contribution rate, and determine the sub-component to which the maximum value belongs as the aging location information.

[0044] According to another aspect of the present invention, the aging detection device includes sub-components of the motor control device such as busbars, capacitors, power modules, on-board chargers, converters, and high-voltage junction boxes; and sub-components of the motor such as motor stators.

[0045] According to another aspect of the invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, enables an aging detection method for an electric drive system.

[0046] By combining a rough preliminary diagnosis with specific root cause localization under defined preset operating conditions, the aging detection method according to the present invention can identify aging components of an electric drive system with less computation and greater accuracy. Attached Figure Description

[0047] Referring to the accompanying drawings, the above and other features of the present invention will become apparent, wherein,

[0048] Figure 1 The structure of a common electric drive system is shown in a block diagram;

[0049] Figure 2 The main steps of the aging detection method according to the present invention are illustrated schematically;

[0050] Figure 3 The main sub-steps of the condition judgment step in the aging detection method according to the present invention are illustrated schematically.

[0051] Figure 4 The main sub-steps of the preliminary diagnostic steps of the aging detection method according to the present invention are illustrated schematically;

[0052] Figure 5 The sub-steps of the aging root cause determination step in the aging detection method according to the present invention are illustrated schematically.

[0053] Figure 6 It schematically shows the origin of Figure 4 The relevant sub-steps of the aging root cause determination process;

[0054] Figure 7 An aging detection device according to the present invention is illustrated schematically. Detailed Implementation

[0055] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0056] The directional terms such as up, down, left, right, front, back, front, back, top, and bottom mentioned or possibly used in this specification are defined relative to the structures shown in the accompanying drawings. These are relative concepts and may therefore vary depending on their location and usage. Therefore, these or other directional terms should not be interpreted as restrictive. Furthermore, the terms "first," "second," "third," and similar expressions are used for descriptive and distinguishing purposes only and should not be construed as indicating or implying the relative importance of the corresponding components.

[0057] First, a brief explanation of the structure of the electric drive system in new energy vehicles will be given. (Reference) Figure 1This illustrates an embodiment of a common electric drive system 100, which generally includes a motor 110, a motor control unit 120, a gearbox 130, and a cooling mechanism associated therewith. The motor control unit comprises a motor controller in the conventional sense and additional control elements. The motor controller includes a busbar / capacitor 121 and a power module 122; the additional control elements involve an on-board charger 123, a converter 124 (e.g., a DC / DC converter), and a high-voltage junction box 125. The listed additional control elements can be integrated within the housing of the motor controller, as shown in... Figure 1 As shown; or the listed additional control elements can be arranged outside the housing of the motor controller (in this case, corresponding to the motor control device), that is, arranged separately from the motor controller. Generally, the sub-components within the motor control device 120 are arranged in series, such that the cooling medium of the cooling mechanism flows sequentially through each of the sub-components.

[0058] Here, the cooling medium contained in the cooling mechanism can involve coolant (e.g., water, oil), air cooling, or natural cooling. For clarity, the flow of the cooling medium or the exemplary cooling sequence of each sub-component is shown only by straight lines with arrows in the accompanying drawings, which can be extended to mean the cooling mechanism. For example, for a motor controller including busbar / capacitor 121 and power module 122, its cooling mechanism can be implemented as a cooling plate with cooling pipes containing the cooling medium arranged on the cooling plate. The cooling mechanisms for motor control device 120 and motor 110 can be constructed identically, for example, their cooling pipes are connected or involve the same cooling medium; however, it is also possible for the two cooling mechanisms to be relatively independent or to involve different cooling media, for example, one involving water cooling and the other involving oil cooling.

[0059] In another feasible embodiment, not shown, a heat exchanger may also be provided along the direction of the cooling pipe, which will not be described in detail here.

[0060] It should be noted that the arrangement of the components of the electric drive system, especially the sub-components of the motor control device, is not limited to the example shown in the accompanying drawings, and can be arranged in any order depending on the available vehicle space. Furthermore, gearbox aging or failure mainly manifests as mechanical wear of the teeth or bearings, and the aging detection process can be carried out with reference to the method according to this disclosure, or it can be performed in other ways.

[0061] For the above-mentioned type of electric drive system, the aging detection method according to the present invention is as follows: Figure 2 As shown, the main steps include the following:

[0062] S100 (i.e., operating condition judgment step): Based on vehicle status parameters, determine whether the vehicle is in a preset operating condition;

[0063] S200 (Preliminary Diagnostic Step): In response to the vehicle being in the preset operating condition, the overall aging degree of the electric drive system is determined based on monitoring data from the cooling mechanism over a preset time period. The monitoring data includes the inlet and outlet temperatures of the cooling medium at the motor control unit, the inlet and outlet temperatures of the cooling medium at the motor, and the cooling medium flow rate; and

[0064] S300 (i.e., aging root cause localization step): In response to the overall aging degree reaching a preset aging level, the aging type is determined according to the aging root cause localization model, wherein the aging type characterizes the aging location information of each sub-component of the motor and motor control device.

[0065] It should be noted that the step names mentioned above (and below) are only used to distinguish between steps and facilitate their reference, and do not represent the order of the steps. The flowcharts in the accompanying diagrams are merely examples of how this method is executed. Unless there is a clear conflict, the steps can be executed in various orders or simultaneously.

[0066] In the operating condition judgment step S100, the aging test of the electric drive system is only performed when the vehicle is under a preset operating condition. Considering that different driving conditions of the vehicle will cause differences in the temperature rise of the electric drive system, especially the cooling mechanism associated with it, the differences between driving conditions may be reflected in the differences in motor torque, motor speed, current, voltage, and cooling conditions, such as the flow rate of the cooling medium. By purposefully triggering the aging test, interference factors caused by problems not of the electric drive system itself can be eliminated, thereby improving the accuracy of the aging test.

[0067] Furthermore, aging tests on individual sub-components are only triggered when the preliminary diagnostic steps determine that the electric drive system has reached a certain aging level, i.e., the overall aging level has reached a preset aging level. This reduces the computational load on the vehicle controller to some extent compared to performing aging tests on all sub-components in real time. On the other hand, the combination of the preliminary diagnostic steps and the aging root cause localization steps enables a comprehensive aging diagnosis of the electric drive system with less computation.

[0068] Optionally, the operating condition determination step is implemented based on a KNN clustering model. Specifically, during vehicle operation, relevant vehicle state parameters are input into the trained KNN clustering model, which directly determines whether the vehicle is in a preset operating condition. This trained KNN clustering model is pre-trained with multiple sets of training data including relevant vehicle state parameters and corresponding labels. The vehicle state parameters are selected from the following group: motor output torque value, motor speed value, current value, voltage value, and cooling medium flow rate. Labels are used to indicate the type of preset operating condition.

[0069] refer to Figure 3 This illustrates the specific flow of the model construction process in the working condition judgment step S100. Specifically, it includes the following sub-steps:

[0070] Sub-step S110: Determine vehicle state parameters that can be used to characterize different operating conditions;

[0071] Sub-step S120: Collect vehicle status parameters under all operating conditions;

[0072] Sub-step S130: Determine the preset operating conditions that can be used for aging detection of the electric drive system and assign corresponding labels to the preset operating conditions;

[0073] Sub-step S140: Construct a KNN clustering model based on the collected vehicle state parameters and corresponding labels.

[0074] Here, in sub-step S110, one or more of the following parameters are selected, for example, to distinguish the operating conditions: motor torque value, current value, voltage value (e.g., DC bus voltage value measured by the motor controller), motor speed, and cooling medium flow rate. These parameters can be read or retrieved directly from the CAN line.

[0075] In sub-step S130, one or more typical operating conditions suitable for aging detection across the entire operating range are identified as preset operating conditions. These may include common urban operating conditions (e.g., motor speed of 4800 r / min, motor torque of 100 Nm), common high-speed operating conditions (e.g., motor speed of 7500 r / min, motor torque of 50 Nm), and common high-speed coasting operating conditions (e.g., motor speed of 7500 r / min, motor torque of 0 Nm). With n preset operating conditions, data corresponding to these n preset operating conditions are assigned labels 1 to n, and data that does not conform to these preset operating conditions are assigned label (n+1). This process can also be referred to as tagging.

[0076] During vehicle operation, relevant vehicle parameters, such as those directly collected from the CAN bus, are transmitted to the KNN clustering model trained through the aforementioned sub-steps, and based on this, it is determined whether the vehicle is in a preset operating condition. If the determination result is positive, preliminary aging diagnosis and subsequent determination of the specific aging type are performed.

[0077] The preliminary diagnostic steps of the aging detection method according to the present invention can be implemented, for example, based on a multivariate statistical analysis model, which may involve, but is not limited to, principal component analysis (PCA) models and independent component analysis (ICA) models. Hereinafter, the PCA model will be used for illustration. Specifically, the preliminary diagnostic steps are as follows: Figure 4 As shown, it includes the following sub-steps:

[0078] S210: Acquire monitoring data of the cooling mechanism within a preset time and input it into the trained preliminary diagnostic model, wherein the trained preliminary diagnostic model is constructed based on health history data under the preset working conditions using a multivariate analysis method.

[0079] S220: Based on the trained preliminary diagnostic model, obtain the deviation statistics of the monitoring data and compare them with a preset threshold; and

[0080] S230: In response to the deviation statistical value exceeding the preset threshold, the overall aging degree of the electric drive system is determined.

[0081] When constructing a preliminary diagnostic model based on the PCA model, the first step is to acquire the relevant health history data of a new vehicle or an electric drive system that has not yet undergone aging. The parameters included in this health history data are the same types as those collected during the aging detection process. For example, the health history data and corresponding detection data can involve, but are not limited to, the inlet and outlet temperatures of the cooling medium in the motor control unit, the inlet and outlet temperatures of the cooling medium in the motor, and the flow rate of the cooling medium under healthy conditions (i.e., when the electric drive system has not undergone aging). The location information of these temperatures is... Figure 1 The information is marked with a diamond symbol, and the temperature and flow rate of the cooling medium can be retrieved from the controller of the pump used to control the cooling medium. If the motor controller and additional control elements are not arranged in an integrated manner, the monitoring data and health history data may relate to the inlet and outlet temperatures of the cooling medium at the motor controller, additional control elements, and motor as a whole.

[0082] The following example, using the vehicle driving under the first preset operating condition, will be used to illustrate the preliminary diagnostic process in more detail.

[0083] When constructing the preliminary diagnostic model, firstly, a vehicle (or a new vehicle) in a healthy state is run for a preset time under a first preset operating condition, and relevant monitoring data is collected within that preset time as health history data. Secondly, data derivation is performed on the acquired health history data, and a PCA model is constructed based on the derived and directly collected health history data. After constructing the PCA model, the health history data needs to be statistically evaluated, i.e., its deviation statistical value is obtained and a corresponding preset threshold is set. Here, the deviation statistical value may involve T. 2 The deviation statistic is obtained by calculating the Mahalanobis distance of the principal component's score vector in space. Of course, this deviation statistic can also involve the Q-statistic, which will not be discussed further here.

[0084] If it is determined that the vehicle has been driven under preset operating conditions for a preset time, then the monitoring data within that preset time is retrieved, and the PCA model is used to obtain the aforementioned predefined deviation statistics (for clarity, these are referred to as actual deviation statistics). If the actual deviation statistics exceed a preset threshold, the electric drive system is determined to have reached a certain aging level, and the subsequent aging root cause determination step is activated. For the data input into the model, it is also feasible to perform data derivation on the monitoring data and input it into the PCA model along with the original monitoring data. Here, on the one hand, it is feasible to determine only the overall aging degree of the electric drive system as a whole based on the PCA model; on the other hand, it is feasible to directly determine the overall aging degree of a component of the electric drive system, such as the motor controller or the motor, based on the PCA model. Both approaches can be achieved by changing the model calculation method.

[0085] If the sub-components of the electric drive system have not aged, then under fixed driving conditions, the temperature rise of each sub-component and the temperature rise of the cooling medium in each sub-component will exhibit definite trends. Based on this, the aforementioned root cause determination step can be implemented using the trained model based on relevant temperature parameters. In an optional embodiment, the root cause determination step can also be implemented using a multivariate analysis method. Specifically, as... Figure 5 As shown, the aging root cause determination step S300 includes the following sub-steps:

[0086] S310: In response to the overall aging level of the electric drive system reaching a preset aging level, acquire the monitored temperature parameters of each sub-component within a preset time and / or the monitored cooling temperature parameters of the cooling mechanism at each sub-component; the monitored cooling temperature parameters are the inlet temperature and outlet temperature of the cooling medium at each sub-component; and

[0087] S320: Using an aging root cause model, determine the aging type based on the monitored temperature parameters and / or monitored cooling temperature parameters, wherein the aging root cause model is constructed based on multiple sets of training data containing health monitoring temperature parameters and / or health monitoring cooling temperature parameters using a multivariate analysis method.

[0088] Here, the concept of "aging type" refers to the names of various sub-components of the electric drive system; for example, this aging type can be represented as converter aging, power module aging, etc. "Monitored temperature parameters" and "Monitored cooling temperature parameters" refer to the actual parameters of the electric drive system under preset operating conditions and within a slightly earlier preset time period; in contrast, "health monitoring temperature parameters" and "health monitoring cooling temperature parameters" refer to the relevant parameters of a non-aged electric drive system or a new vehicle under the same operating conditions. Here, the measurement points involved in the monitoring cooling temperature parameters of the cooling medium are... Figure 1 It is shown in a circle.

[0089] In sub-step S310, relevant temperature parameters can be measured using a temperature sensor already equipped in the electric drive system, such as an NTC temperature sensor, and the corresponding detected temperature parameters can optionally be input into the aging root cause model via a CAN line. However, considering the difficulty in measuring the temperature of the cooling medium at each sub-component, the detected cooling temperature parameter can be calculated based on the temperature of the associated sub-component itself (i.e., the monitored temperature parameter) and the temperature of the cooling mechanism at another sub-component upstream of that sub-component. Below, in the appendix... Figure 1 In the arrangement shown, taking the busbar / capacitor as an example, the outlet temperature of the cooling medium at the busbar / capacitor is calculated according to the following formula:

[0090]

[0091] Among them, T Cap The temperature of the busbar / capacitor itself;

[0092] T Coolant_Cap_In This refers to the inlet temperature of the cooling medium at the busbar / capacitor.

[0093] P Cap This refers to the power loss of the busbar / capacitor.

[0094] R Cap The equivalent thermal resistance of the busbar / capacitor;

[0095] T Coolant_Cap_Out This refers to the outlet temperature of the cooling medium at the busbar / capacitor.

[0096] R Coolant It is the equivalent thermal resistance of the cooling medium.

[0097] Here, inFigure 1 In the arrangement shown, the cooling medium first flows through the busbar / capacitor, and the inlet temperature T of the cooling medium at the busbar / capacitor is... Coolant_Cap_In This can be directly obtained from the vehicle controller and can be considered known. The temperature of the busbar / capacitor itself can be directly obtained from the existing temperature sensor on it. The calculated outlet temperature of the cooling medium at the busbar / capacitor can be regarded as the detected cooling temperature parameter (i.e., the inlet temperature of the cooling medium at the power module) associated with the power module located directly downstream.

[0098] The formula above is used to calculate the outlet temperature of the cooling medium in each sub-component, ensuring the accuracy of aging tests in a cost-effective manner. It should be noted that the calculation of the inlet and outlet temperatures of the cooling medium in other sub-components can be referenced accordingly from the description above regarding busbars / capacitors, and will not be repeated here.

[0099] Temperature parameters for power modules can be measured using one or more NTC temperature sensors, which may be arranged on the power module's substrate. In the case of multiple such temperature sensors, the temperature parameters input into the root cause localization model are the average or maximum value of the detected temperatures. Correspondingly, temperature parameters for on-board chargers may involve the temperatures of their critical chips, current transformer modules, or MOSFETs. Furthermore, temperature parameters for converters may involve the temperatures of their critical chips, transformer modules, or MOSFETs. For motors or motor stators, their temperatures can be obtained using NTC temperature sensors arranged on the stator.

[0100] For sub-step S320, it is as follows Figure 6 As shown, the steps include:

[0101] S321: Based on the aging root cause model, obtain the monitoring contribution rate of the monitored temperature parameter and / or monitored cooling temperature parameter, and the deviation between the monitored contribution rate and the theoretical contribution rate, wherein the theoretical contribution rate is obtained based on the corresponding health monitoring temperature parameter and / or health monitoring cooling temperature parameter under preset operating conditions; and

[0102] S322: Obtain the maximum value of the deviation between the monitored contribution rate and the theoretical contribution rate, and determine the sub-component to which the maximum value belongs as the aging location information.

[0103] The following describes the root cause determination process in more detail, which can be divided into a preliminary model building process and a subsequent location process. First, based on the health parameters of the unaged electric drive system or new vehicle (including health monitoring temperature parameters of each sub-component and health monitoring cooling temperature parameters of the cooling medium) and their corresponding derived data, an aging root cause model is constructed, and the theoretical contribution rate of each parameter in a healthy state is calculated. Second, the constructed aging root cause model can be deployed in the cloud and / or on the vehicle. During vehicle operation, if the aging root cause determination step is activated, the relevant parameters described above are collected and input into the aging root cause model. The actual contribution rate of each parameter in the current state is calculated using the aging root cause model. Then, the theoretical contribution rate and the actual contribution rate are compared, and the sub-component to which the parameter with the largest deviation between the two belongs is determined as the aging location. Here, the names of aging components can be directly transmitted to the vehicle controller as signals, so that the vehicle controller can then make torque redistribution, downgrade operations, or instrument display warnings based on the degree of aging of each sub-component, so that maintenance personnel can carry out targeted maintenance on the electric drive system.

[0104] It should be noted that the above is merely an exemplary implementation for determining the root cause of aging, and it can also be implemented in any other way. For example, it is also possible to simply compare the difference between the inlet and outlet temperatures of the cooling medium in each sub-component and compare this difference with the theoretical difference under the same preset operating conditions. If the deviation between the two is too large, it can be determined that the sub-component has malfunctioned.

[0105] In summary, by combining a rough preliminary diagnosis with specific root cause localization under defined preset operating conditions, the aging detection method according to the present invention can identify aging components of an electric drive system with less computation and greater accuracy. In an optional embodiment, the efficiency of aging detection can be significantly improved by using a multivariate analysis model to perform the above steps. In another optional embodiment, for the temperature of the cooling medium in each sub-component, the aging detection method according to the present invention provides a simple and easily implemented calculation method instead of direct measurement, which is technically difficult to achieve.

[0106] refer to Figure 6The diagram illustrates an aging detection apparatus 200 according to another aspect of the present invention, comprising a memory 210 (e.g., a non-volatile memory such as flash memory, ROM, hard disk drive, magnetic disk, optical disk, etc.), a processor 220, and a computer program 230 stored on the memory 210 and executable on the processor 220, the execution of which implements an aging detection method for an electric drive system according to one or more embodiments of the present invention. A description of the apparatus is given above in relation to the aging detection method, and will not be repeated here.

[0107] Optionally, the aging detection device 200 can be a cloud computing device. For example, the memory 210 and processor 220, as cloud computing resources, can reside not only within the same physical device (e.g., the same server), but also on different physical devices (e.g., different servers). Furthermore, the aging detection device can also be integrated into or form part of the vehicle controller; or it can also be integrated into or form part of the motor controller.

[0108] Furthermore, the present invention relates to a computer-readable storage medium for implementing an aging detection method for an electric drive system according to one or more embodiments of the present invention. The computer-readable storage medium referred to herein includes various types of computer storage media, and can be any available medium accessible by a general-purpose or special-purpose computer. For example, a computer-readable storage medium may include RAM, ROM, EPROM, E2PROM, registers, hard disk, removable disk, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage device, or any other temporary or non-temporary medium capable of carrying or storing desired program code units having the form of instructions or data structures and accessible by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. A description of the computer-readable storage medium according to the present invention can be found in the explanation of the method according to the present invention, and will not be repeated here.

[0109] It should be understood that all the above preferred embodiments are exemplary and not restrictive, and various modifications or variations made by those skilled in the art to the specific embodiments described above under the concept of the present invention should be within the legal protection scope of the present invention.

Claims

1. An aging detection method for an electric drive system, the electric drive system comprising a motor, a motor control device, and a cooling mechanism for the motor and the motor control device, characterized in that, Includes the following steps: S100: Based on vehicle status parameters, determine whether the vehicle is in a preset operating condition; S200: In response to the vehicle being in the preset operating condition, the overall aging degree of the electric drive system is determined based on the monitoring data of the cooling mechanism within a preset time. The monitoring data includes the inlet and outlet temperatures of the cooling medium at the motor control device, the inlet and outlet temperatures of the cooling medium at the motor, and the flow rate of the cooling medium. as well as S300: In response to the overall aging degree reaching a preset aging level, determine the aging type according to the aging root cause localization model, wherein the aging type characterizes the aging with respect to the location information of each sub-component of the motor and motor control device.

2. The aging detection method according to claim 1, characterized in that, In step S100, based on a KNN clustering model that has been trained in advance with multiple sets of training data including the vehicle state parameters and corresponding labels, it is determined whether the vehicle is in the preset operating condition. The vehicle state parameters include at least one of the following: motor output torque value, motor speed value, current value, voltage value, and cooling medium flow rate. The labels represent the preset operating condition type.

3. The aging detection method according to claim 2, characterized in that, Step S200 includes the following sub-steps: S210: Acquire monitoring data of the cooling mechanism within a preset time and input the monitoring data into the trained preliminary diagnostic model. The trained preliminary diagnostic model is constructed based on health history data under the preset working conditions using a multivariate statistical analysis method. S220: Based on the trained preliminary diagnostic model, obtain the deviation statistics of the monitoring data and compare them with a preset threshold; and S230: In response to the deviation statistical value exceeding the preset threshold, the overall aging degree of the electric drive system is determined.

4. The aging detection method according to any one of claims 1 to 3, characterized in that, Step S300 includes the following sub-steps: S310: In response to the overall aging degree of the electric drive system reaching a preset aging level, acquire the monitoring temperature parameters of each sub-component within a preset time and / or the monitoring cooling temperature parameters of the cooling mechanism at each sub-component; the monitoring cooling temperature parameters are the inlet temperature and outlet temperature of the cooling medium at each sub-component respectively; as well as S320: Using the aging root cause model, determine the aging type based on the monitoring temperature parameter and / or monitoring cooling temperature parameter, wherein the aging root cause model is constructed based on multiple sets of training data containing health monitoring temperature parameters and / or health monitoring cooling temperature parameters using a multivariate statistical analysis method.

5. The aging detection method according to claim 4, characterized in that, In sub-step S310, the monitored cooling temperature parameters of the cooling mechanism at each sub-component are obtained based on the thermal resistance of the cooling medium contained in the cooling mechanism, the thermal resistance of each sub-component, and the monitored temperature parameters of each sub-component.

6. The aging detection method according to claim 5, characterized in that, Sub-step S320 includes the following steps: S321: Based on the aging root cause model, obtain the monitoring contribution rate of the monitored temperature parameter and / or monitored cooling temperature parameter, and the deviation between the monitored contribution rate and the theoretical contribution rate, wherein the theoretical contribution rate is obtained based on the corresponding health monitoring temperature parameter and / or health monitoring cooling temperature parameter under preset operating conditions; and S322: Obtain the maximum value of the deviation between the monitored contribution rate and the theoretical contribution rate, and determine the sub-component to which the maximum value belongs as the aging location information.

7. The aging detection method according to claim 1, characterized in that, The sub-components belonging to the motor control device include busbars, capacitors, power modules, on-board chargers, converters, and high-voltage junction boxes; the sub-components belonging to the motor include the motor stator.

8. An aging detection device for an electric drive system, the electric drive system comprising a motor, a motor control device, and a cooling mechanism for the motor and the motor control device, characterized in that, include: Memory; processor; A computer program stored in the memory and executable on the processor, the execution of the computer program causing the aging detection method according to any one of claims 1 to 7 to be performed, the aging detection method comprising the following steps: S100: determining whether the vehicle is in a preset working condition based on vehicle state parameters; S200: In response to the vehicle being in the preset operating condition, the overall aging degree of the electric drive system is determined based on the monitoring data of the cooling mechanism within a preset time. The monitoring data includes the inlet and outlet temperatures of the cooling medium at the motor control device, the inlet and outlet temperatures of the cooling medium at the motor, and the flow rate of the cooling medium. as well as S300: In response to the overall aging degree reaching a preset aging level, determine the aging type according to the aging root cause localization model, wherein the aging type characterizes the aging with respect to the location information of each sub-component of the motor and motor control device.

9. The aging detection device according to claim 8, characterized in that, When performing step S100, the vehicle is determined to be in the preset operating condition based on a KNN clustering model that has been trained in advance with multiple sets of training data including the vehicle state parameters and corresponding labels. The vehicle state parameters include at least one of the following: motor output torque value, motor speed value, current value, voltage value, and cooling medium flow rate. The labels represent the preset operating condition type.

10. The aging detection device according to claim 9, characterized in that, The following sub-steps are executed during step S200: S210: Acquire monitoring data of the cooling mechanism within a preset time and input the monitoring data into the trained preliminary diagnostic model. The trained preliminary diagnostic model is constructed based on health history data under the preset working conditions using a multivariate statistical analysis method. S220: Based on the trained preliminary diagnostic model, obtain the deviation statistics of the monitoring data and compare them with a preset threshold; and S230: In response to the deviation statistical value exceeding the preset threshold, the overall aging degree of the electric drive system is determined.

11. The aging detection device according to any one of claims 8 to 10, characterized in that, When step S300 is executed, the following sub-steps are performed: S310: In response to the overall aging degree of the electric drive system reaching a preset aging level, acquire the monitoring temperature parameters of each sub-component within a preset time and / or the monitoring cooling temperature parameters of the cooling mechanism at each sub-component; the monitoring cooling temperature parameters are the inlet temperature and outlet temperature of the cooling medium at each sub-component respectively; as well as S320: Using the aging root cause model, determine the aging type based on the monitoring temperature parameter and / or monitoring cooling temperature parameter, wherein the aging root cause model is constructed based on multiple sets of training data containing health monitoring temperature parameters and / or health monitoring cooling temperature parameters using a multivariate statistical analysis method.

12. The aging detection device according to claim 11, characterized in that, When performing sub-step S310, the monitored cooling temperature parameters of the cooling mechanism at each sub-component are obtained based on the thermal resistance of the cooling medium contained in the cooling mechanism, the thermal resistance of each sub-component, and the monitored temperature parameters of each sub-component.

13. The aging detection device according to claim 12, characterized in that, When executing sub-step S320, the following steps are performed: S321: Based on the aging root cause model, obtain the monitoring contribution rate of the monitored temperature parameter and / or monitored cooling temperature parameter, and the deviation between the monitored contribution rate and the theoretical contribution rate, wherein the theoretical contribution rate is obtained based on the corresponding health monitoring temperature parameter and / or health monitoring cooling temperature parameter under preset operating conditions; and S322: Obtain the maximum value of the deviation between the monitored contribution rate and the theoretical contribution rate, and determine the sub-component to which the maximum value belongs as the aging location information.

14. The aging detection device according to claim 8, characterized in that, The sub-components belonging to the motor control device include busbars, capacitors, power modules, on-board chargers, converters, and high-voltage junction boxes; the sub-components belonging to the motor include the motor stator.

15. A computer-readable storage medium on which a computer program is stored, characterized in that, When the computer program is executed by the processor, it implements the aging detection method for an electric drive system according to any one of claims 1 to 7.

Images