Vehicle motor water pump fault monitoring method and device, vehicle and medium

Abstract

The invention discloses a vehicle motor water pump fault monitoring method and device, a vehicle and a medium, and relates to the technical field of vehicles. The method comprises the following steps: acquiring and analyzing a motor water pump communication state signal in real time, and when it is monitored that communication loss continuously reaches a first preset duration, automatically extracting multi-dimensional features including a communication feature, an associated system feature and a time sequence environment feature instead of depending on a single signal for judgment; and inputting into a pre-trained motor water pump fault probability prediction model, outputting a quantized fault probability value, and further accurately judging the fault type according to the probability. Thus, the technical problems that an existing monitoring mechanism based on a fixed threshold value and a single signal is poor in adaptability and high in false alarm rate are effectively solved, through fusion of multi-source information and the intelligent prediction model, accurate distinguishing of motor water pump communication loss event roots is achieved, the accuracy and working condition adaptability of fault diagnosis are remarkably improved, and the fault diagnosis efficiency is improved. And meanwhile, false alarms caused by instantaneous interference are reduced.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle motor and water pump fault monitoring method, a vehicle motor and water pump fault monitoring device, a computer-readable storage medium, and a vehicle. Background Technology

[0002] In the distributed control system of new energy vehicles, the motor and water pump controller communicates with the vehicle network via the Controller Area Network (CAN bus). Currently, the status monitoring of this controller node mainly adopts a periodic signal monitoring mechanism based on the CAN bus. That is, the gateway periodically scans and parses the status signals reported by the water pump controller on the bus, and sets a diagnostic fault code when the signal is abnormal for more than a preset fixed number of cycles.

[0003] However, the periodic signal monitoring mechanism based on the CAN bus has obvious defects: First, its judgment basis is singular, relying only on the duration of a single lost communication signal, and it cannot distinguish whether the abnormal signal is due to a real hardware failure of the controller or a momentary interference such as a momentary low voltage of the vehicle power supply or electromagnetic interference of the bus, resulting in a high false alarm rate; Second, it uses a fixed time judgment threshold and lacks the ability to adapt to the actual driving conditions and environment of the vehicle (such as areas with harsh electromagnetic environments or high-speed, high-load cooling scenarios), and cannot achieve a dynamic trade-off between avoiding false alarms and timely fault detection. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in related technologies. To this end, the first objective of this application is to propose a method for monitoring vehicle motor-water pump faults. The method includes: acquiring a motor-water pump communication status signal; determining communication characteristics, associated system characteristics, and temporal environment characteristics when the motor-water pump is in a communication loss state for a sustained first preset duration based on the communication status signal; inputting the communication characteristics, associated system characteristics, and temporal environment characteristics into a preset motor-water pump fault probability prediction model to output a motor-water pump fault probability; and determining the fault type of the motor-water pump based on the fault probability. This application, by acquiring and analyzing the motor-water pump communication status signal in real time, no longer relies on a single signal for judgment when communication loss is detected to have lasted for a sustained first preset duration. Instead, it automatically extracts multi-dimensional features, including communication characteristics, associated system characteristics, and temporal environment characteristics, and inputs them into a pre-trained motor-water pump fault probability prediction model, outputting a quantified fault probability value, and then accurately determining the fault type based on this probability. In this way, the technical problems of poor adaptability and high false alarm rate of existing fixed threshold and single signal monitoring mechanisms are effectively overcome. By integrating multi-source information and intelligent prediction models, the root cause of communication loss events of motors and water pumps can be accurately distinguished, which significantly improves the accuracy of fault diagnosis and adaptability to operating conditions, while reducing false alarms caused by instantaneous interference.

[0005] The second objective of this application is to provide a vehicle motor water pump fault monitoring device.

[0006] The third objective of this application is to provide a computer-readable storage medium.

[0007] The fourth objective of this application is to propose a vehicle.

[0008] To achieve the above objectives, the first aspect of this application proposes a method for monitoring vehicle motor-water pump faults. The method includes: acquiring a motor-water pump communication status signal; determining communication characteristics, associated system characteristics, and temporal environment characteristics when the motor-water pump is determined to be in a communication loss state for a first preset duration based on the motor-water pump communication status signal; inputting the communication characteristics, associated system characteristics, and temporal environment characteristics into a preset motor-water pump fault probability prediction model to output a motor-water pump fault probability; and determining the fault type of the motor-water pump based on the motor-water pump fault probability.

[0009] According to one embodiment of this application, determining the fault type of a motor-pump based on the motor-pump fault probability includes: determining that the motor-pump has a deterministic fault when the motor-pump fault probability is greater than or equal to a first preset fault probability threshold; determining that the motor-pump communication is in an unstable state when the motor-pump fault probability is greater than or equal to a second preset fault probability threshold and less than the first preset fault probability threshold; and determining that the motor-pump communication is subject to transient interference when the motor-pump fault probability is less than the second preset fault probability threshold.

[0010] According to one embodiment of this application, the communication characteristics include the frequency and percentage loss of the motor-pump communication status signal. Determining the communication characteristics includes: determining the frequency of the motor-pump communication status signal loss as the number of times the motor-pump changes from a normal communication state to a communication loss state within a second preset time period; determining the percentage loss of the motor-pump communication status signal based on the ratio between the cumulative duration of the motor-pump communication status being in a communication loss state within the second preset time period and the second preset time period; wherein the second preset time period is longer than the first preset time period.

[0011] According to one embodiment of this application, the associated system features include the standard deviation of vehicle power supply voltage and the rate of change of motor coolant temperature. Determining the associated system features includes: determining the standard deviation of vehicle power supply voltage based on the vehicle power supply voltage at multiple time points within a third preset time period; performing linear regression analysis on the motor coolant temperature at multiple time points within a fourth preset time period to obtain a regression line, and determining the slope of the regression line as the rate of change of motor coolant temperature; wherein, both the third preset time period and the fourth preset time period are greater than the first preset time period.

[0012] According to one embodiment of this application, the timing environment features include the time interval for the loss of communication status signals of the motor and water pump and runtime segment feature information. Determining the timing environment features includes: determining the starting time point when the motor and water pump enter the current communication loss state and the transition time point when the motor and water pump last transitioned from the communication loss state to the communication normal state, and determining the time interval for the loss of communication status signals of the motor and water pump based on the difference between the transition time point and the starting time point; and determining the runtime segment feature information based on the time interval in which the starting time point is located.

[0013] According to one embodiment of this application, the above method further includes: constructing a model training set for a preset motor and water pump failure probability prediction model based on multiple historical communication features, multiple historical associated system features, multiple historical time-series environmental features, and corresponding motor and water pump failure types; training the preset motor and water pump failure probability prediction model based on the model training set to construct a preset motor and water pump failure probability prediction model for predicting motor and water pump failure probabilities.

[0014] According to one embodiment of this application, training a preset motor-pump failure probability prediction model based on a model training set includes: inputting any input data from the model training set into the initial motor-pump failure probability prediction model to obtain the predicted motor-pump failure probability; inputting the predicted motor-pump failure probability and the motor-pump failure type corresponding to the input data into a binary cross-entropy loss function to calculate the discriminant loss to obtain the calculation result; updating the model parameters of the initial motor-pump failure probability prediction model using the calculation result until the updated initial motor-pump failure probability prediction model meets the preset convergence condition to obtain the preset motor-pump failure probability prediction model.

[0015] To achieve the above objectives, a second aspect of this application provides a vehicle motor-water pump fault monitoring device. The device includes: an acquisition module for acquiring a motor-water pump communication status signal; a first determination module for determining communication characteristics, associated system characteristics, and temporal environment characteristics when the motor-water pump is determined to be in a communication loss state for a first preset duration based on the motor-water pump communication status signal; an output module for pre-setting the communication characteristics, associated system characteristics, and temporal environment characteristics into a motor-water pump fault probability prediction model to output a motor-water pump fault probability; and a second determination module for determining the fault type of the motor-water pump based on the motor-water pump fault probability.

[0016] To achieve the above objectives, a third aspect of this application provides a computer-readable storage medium storing a vehicle motor water pump fault monitoring program thereon, which, when executed by a processor, implements the aforementioned vehicle motor water pump fault monitoring method.

[0017] To achieve the above objectives, a fourth aspect of this application provides a vehicle including a memory, a processor, and a vehicle motor and water pump fault monitoring program stored in the memory and executable on the processor. When the processor executes the vehicle motor and water pump fault monitoring program, it implements the aforementioned vehicle motor and water pump fault monitoring method.

[0018] According to the vehicle motor-water pump fault monitoring method, device, vehicle, and medium of this application, the communication status signal of the motor-water pump is acquired; when it is determined from the communication status signal that the motor-water pump is in a communication loss state for a continuous first preset duration, communication characteristics, associated system characteristics, and temporal environment characteristics are determined; the communication characteristics, associated system characteristics, and temporal environment characteristics are input into a preset motor-water pump fault probability prediction model to output the motor-water pump fault probability; and the fault type of the motor-water pump is determined based on the motor-water pump fault probability. This application, by acquiring and analyzing the motor-water pump communication status signal in real time, no longer relies on a single signal for judgment when communication loss is detected to have lasted for a continuous first preset duration. Instead, it automatically extracts multi-dimensional features, including communication characteristics, associated system characteristics, and temporal environment characteristics, and inputs them into a pre-trained motor-water pump fault probability prediction model, outputting a quantified fault probability value, and then accurately determining the fault type based on this probability. In this way, the technical problems of poor adaptability and high false alarm rate of existing fixed threshold and single signal monitoring mechanisms are effectively overcome. By integrating multi-source information and intelligent prediction models, the root cause of communication loss events of motors and water pumps can be accurately distinguished, which significantly improves the accuracy of fault diagnosis and adaptability to operating conditions, while reducing false alarms caused by instantaneous interference. Attached Figure Description

[0019] Figure 1 The flowchart below shows a vehicle motor water pump fault monitoring method according to some embodiments of this application. Figure 2 This is a schematic diagram of the structure of a vehicle motor water pump fault monitoring system according to some embodiments of this application; Figure 3 This is a block diagram of a vehicle motor and water pump fault monitoring device according to some embodiments of this application; Figure 4 This is a block diagram of a vehicle according to some embodiments of this application. Detailed Implementation

[0020] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0021] The following describes in detail, with reference to the accompanying drawings, the vehicle motor and water pump fault monitoring method, device, vehicle, and medium according to embodiments of this application.

[0022] Figure 1 This is a flowchart of a vehicle motor water pump fault monitoring method according to some embodiments of this application. (Refer to...) Figure 1 The vehicle motor water pump fault monitoring method of this application embodiment may include the following steps: S110, acquire the communication status signal of the motor and water pump.

[0023] Specifically, the communication status signal of the motor and water pump can be acquired by periodically monitoring the CAN bus. This signal can be either 0 or 1. In the following explanation, we will use the example where a 0 signal indicates normal communication and a 1 signal indicates communication loss. No further specific limitations are imposed here.

[0024] S120: If it is determined from the motor-pump communication status signal that the motor-pump is in a communication loss state for a continuous first preset duration, then the communication characteristics, associated system characteristics, and timing environment characteristics are determined. The first preset duration can be specified according to actual conditions; for example, it could be 40 seconds. No specific limitation is imposed here.

[0025] Specifically, when the motor-water pump communication status signal changes from 0 to 1 (determining the motor-water pump is in a communication loss state), the current event time is stored in a status variable, and a timer is registered to trigger after a first preset duration. When the motor-water pump communication status signal changes from 1 to 0 within the first preset duration (determining the motor-water pump is in a normal communication state), the timer is immediately deleted and the status variable is cleared. If the motor-water pump communication status signal remains at 1 within the first preset duration, the communication characteristics, associated system characteristics, and timing environment characteristics are determined by using various signals recorded before the start time of the current communication loss state of the motor-water pump (such as vehicle power supply voltage signal, motor coolant temperature, and motor-water pump communication status signal). For example, communication characteristics include the frequency and percentage of loss of motor-water pump communication status signals, meaning that communication characteristics can be determined through motor-water pump communication status signals; associated system characteristics include the standard deviation of vehicle power supply voltage and the rate of change of motor coolant temperature, meaning that associated system characteristics can be determined through vehicle power supply voltage signals and motor coolant temperature; and temporal environment characteristics include the time interval of loss of motor-water pump communication status signals and runtime characteristic information, meaning that temporal environment characteristics can also be determined through motor-water pump communication status signals.

[0026] To further illustrate the above embodiments, in this application embodiment, the communication characteristics include the frequency and percentage loss of the motor-pump communication status signal. Determining the communication characteristics includes: determining the frequency of communication status signal loss of the motor-pump by measuring the number of times the motor-pump changes from a normal communication state to a communication loss state within a second preset time period; determining the percentage loss of the motor-pump communication status signal based on the ratio between the cumulative duration of the motor-pump communication status being in a communication loss state within the second preset time period and the second preset time period itself; wherein, the second preset time period is longer than the first preset time period. The second preset time period can be determined according to actual conditions, for example, it can be determined according to actual conditions, and no specific limitation is made here.

[0027] Specifically, the communication characteristics include the frequency and percentage of communication status signal loss for the motor and water pump. Starting from the initial moment when the motor and water pump enter the current communication loss state, a statistical window of a second preset duration is traced backwards. The number of times the motor and water pump's communication status transitions from normal to loss within this window is counted, and this number is determined as the frequency of communication status signal loss. Simultaneously, the ratio between the cumulative duration of the motor and water pump's communication status in the communication loss state within this window and the second preset duration is calculated to determine the percentage of communication status signal loss.

[0028] To further illustrate the above embodiments, in this application embodiment, the associated system features include the standard deviation of the vehicle power supply voltage and the rate of change of the motor coolant temperature. Determining the associated system features includes: determining the standard deviation of the vehicle power supply voltage based on the vehicle power supply voltage at multiple time points within a third preset time period; performing linear regression analysis on the motor coolant temperature at multiple time points within a fourth preset time period to obtain a regression line, and determining the slope of the regression line as the rate of change of the motor coolant temperature; wherein, both the third preset time period and the fourth preset time period are greater than the first preset time period. The third preset time period and the fourth preset time period can be calibrated according to actual conditions; for example, the third preset time period can be 5 minutes and the fourth preset time period can be 10 minutes, without specific limitations.

[0029] Specifically, the associated system characteristics include the standard deviation of the vehicle power supply voltage and the rate of change of the motor coolant temperature. Starting from the moment the motor water pump enters the current communication loss state, a statistical window of a third preset duration is traced backwards. The vehicle power supply voltage at multiple time points within this window is statistically analyzed, and the standard deviation of the vehicle power supply voltage is determined based on these multiple time points. For example, the standard deviation of the vehicle power supply voltage can be calculated by inputting the vehicle power supply voltage at multiple time points into the following formula: ; in, Indicates the standard deviation of the vehicle's power supply voltage; This indicates the number of vehicle power supply voltage sampling points within the statistics window; This represents the vehicle power supply voltage corresponding to the i-th sampling point; This represents the average power supply voltage of vehicles within the statistical window.

[0030] Starting from the moment the motor-water pump enters the current communication loss state, a statistical window of a fourth preset duration is traced backward. The motor coolant temperature at multiple time points within this window is statistically analyzed, and a linear regression analysis is performed on the motor coolant temperature at these multiple time points to obtain a regression line. The slope of the regression line is determined as the rate of change of the motor coolant temperature. For example, assuming the motor coolant temperature sampling time points are t1 and t2... ,tn, the motor coolant temperature corresponding to each sampling time point is T1, T2, Tn. A linear model is fitted using the least squares method. The formula for calculating the slope b is as follows: Where b represents the rate of change of motor coolant temperature; n is the number of motor coolant temperature sampling points within the statistical window; This represents the i-th sampling point; This represents the motor coolant temperature corresponding to the i-th sampling point.

[0031] To further illustrate the above embodiments, in this application embodiment, the timing environment features include the time interval of communication status signal loss for the motor and water pump and runtime segment feature information. Determining the timing environment features includes: determining the starting time point when the motor and water pump enter the current communication loss state and the transition time point when the motor and water pump last transitioned from the communication loss state to the communication normal state, and determining the time interval of communication status signal loss for the motor and water pump based on the difference between the transition time point and the starting time point; and determining the runtime segment feature information based on the time interval in which the starting time point is located.

[0032] Specifically, the temporal environmental characteristics include the communication status signal loss time interval of the motor and water pump and runtime characteristic information. First, the starting time point when the motor and water pump enter the current communication loss state is recorded. Then, the transition time point from the communication loss state to the normal communication state before that starting time point is traced and obtained. Finally, the difference between the two time points is calculated to obtain the communication status signal loss time interval of the motor and water pump. The communication status signal loss time interval of the motor and water pump is used to characterize the recurrence cycle of the communication loss event or the persistence of system stability recovery, serving as an important temporal characteristic for assessing whether the fault exhibits periodic or trend-like deterioration.

[0033] The time intervals include weekday morning peak hours and weekday evening peak hours, with the morning peak hours being 7-9 AM and the evening peak hours being 5-7 PM. The system determines whether the start time of the motor / water pump entering the current communication loss state falls within these time intervals. If the start time is between 7-9 AM or 5-7 PM, the operating period is determined to be during peak hours; otherwise, it is determined to be outside of peak hours.

[0034] S130: Input the communication characteristics, associated system characteristics and temporal environment characteristics into the preset motor and water pump failure probability prediction model to output the motor and water pump failure probability.

[0035] Specifically, after determining the communication characteristics, associated system characteristics, and temporal environment characteristics, these characteristics are input into a preset motor-pump failure probability prediction model to output the motor-pump failure probability. The preset motor-pump failure probability prediction model is trained based on a pre-built model training set.

[0036] To further illustrate the above embodiments, in this application embodiment, a model training set for a preset motor and water pump failure probability prediction model is constructed based on multiple historical communication features, multiple historical associated system features, multiple historical time-series environmental features, and corresponding motor and water pump failure types; the preset motor and water pump failure probability prediction model is trained based on the model training set to construct a preset motor and water pump failure probability prediction model for predicting motor and water pump failure probabilities.

[0037] Specifically, multiple historical communication features, multiple historical associated system features, and multiple historical time-series environmental features are collected and organized. Historical communication features include communication loss frequency and loss rate; historical associated system features include the standard deviation of vehicle power supply voltage and the rate of change of motor coolant temperature; and historical time-series environmental features include communication loss time intervals and operating period identifiers. Simultaneously, each historical sample is labeled with a corresponding motor-water pump fault type as a supervisory label. Fault types are categorized as deterministic faults, unstable motor-water pump communication, and transient interference. Finally, the features and labels are combined to form a model training set, which is used to train a preset motor-water pump fault probability prediction model. This model can output a predicted probability value of deterministic motor-water pump faults based on real-time extracted multi-dimensional features, thereby achieving intelligent mapping and prediction from multi-dimensional time-series data to fault probabilities.

[0038] To further illustrate the above embodiments, in this application embodiment, training a preset motor-pump failure probability prediction model based on a model training set includes: inputting any input data from the model training set into the initial motor-pump failure probability prediction model to obtain the predicted motor-pump failure probability; inputting the predicted motor-pump failure probability and the motor-pump failure type corresponding to the input data into a binary cross-entropy loss function to calculate the discriminant loss to obtain the calculation result; and updating the model parameters of the initial motor-pump failure probability prediction model using the calculation result until the updated initial motor-pump failure probability prediction model meets the preset convergence condition to obtain the preset motor-pump failure probability prediction model.

[0039] For example, firstly, any feature vector from the training set is input into the initial motor-pump failure probability prediction model (e.g., the LightGBM model). The model outputs a predicted motor-pump failure probability between 0 and 1. Then, this predicted probability and the corresponding real motor-pump failure type label are input into the binary cross-entropy loss function to calculate the discriminant loss between the prediction result and the real label. Next, the backpropagation algorithm is used to calculate the gradient based on the loss value and update the parameters of the initial model. By iteratively executing the above steps, multiple rounds of training are performed on all training samples until the model's loss on the validation set no longer decreases significantly or reaches the preset number of iterations, i.e., the convergence condition is met. Finally, a pre-trained motor-pump failure probability prediction model with high discriminant accuracy is obtained.

[0040] S140, determine the fault type of the motor and water pump based on the failure probability of the motor and water pump.

[0041] Specifically, after determining the probability of motor and water pump failure, the type of motor and water pump failure can be determined by judging the probability range in which the motor and water pump failure probability falls. The types of motor and water pump failure include deterministic failure of motor and water pump, unstable communication of motor and water pump, and instantaneous interference to motor and water pump communication.

[0042] To further illustrate the above embodiments, in this application embodiment, determining the fault type of the motor and water pump based on the motor and water pump fault probability includes: determining that the motor and water pump has experienced a deterministic fault when the motor and water pump fault probability is greater than or equal to a first preset fault probability threshold; determining that the motor and water pump communication is in an unstable state when the motor and water pump fault probability is greater than or equal to a second preset fault probability threshold and less than the first preset fault probability threshold; and determining that the motor and water pump communication is subject to transient interference when the motor and water pump fault probability is less than the second preset fault probability threshold. The first and second preset fault probability thresholds can be calibrated according to actual conditions; for example, the first preset fault probability threshold can be 0.75, and the second preset fault probability threshold can be 0.5. No specific limitations are imposed here.

[0043] It should be noted that the vehicle-mounted device can collect the motor-water pump communication status signal, vehicle power supply voltage signal, and motor coolant temperature. Based on these signals, it determines communication characteristics, associated system characteristics, and temporal environmental characteristics. These characteristics are then input into a preset motor-water pump fault probability prediction model to output the motor-water pump fault probability. The fault type of the motor-water pump is determined based on this probability. Alternatively, the vehicle-mounted device can also upload the collected motor-water pump communication status signal, vehicle power supply voltage signal, and motor coolant temperature to the cloud. The cloud then uses these signals to determine the same communication characteristics, associated system characteristics, and temporal environmental characteristics, inputting these same characteristics into the preset motor-water pump fault probability prediction model to output the motor-water pump fault probability. The fault type of the motor-water pump is then determined based on this probability.

[0044] As a concrete example, refer to Figure 2 The vehicle motor and water pump fault monitoring system 1 of this application includes a data acquisition module 11, a Flink real-time processing module 12, a decision module 13, a warning module 14, and a feature database 15. The Flink real-time processing module includes a status tracking unit 121 and a feature calculation unit 122.

[0045] The data acquisition module 11 is used to acquire the motor-water pump communication status signal, the motor coolant temperature, and the motor-water pump communication status signal.

[0046] The Flink real-time processing module 12 includes a state tracking unit 121 and a feature calculation unit 122. The state tracking unit 121 is used to determine whether the motor and water pump are in a communication loss state for a first preset duration based on the motor and water pump communication status signal. The feature calculation unit 122 is used to determine communication features, associated system features, and timing environment features based on the collected motor and water pump communication status signal, motor coolant temperature, and motor and water pump communication status signal.

[0047] The decision module 13 is used to input communication characteristics, associated system characteristics and temporal environment characteristics into a preset motor pump failure probability prediction model when it is determined that the motor pump is in a communication loss state for a first preset time, so as to output the motor pump failure probability and determine the failure type of the motor pump based on the motor pump failure probability.

[0048] Warning module 14 is used to control the vehicle to issue an alarm based on the type of motor and water pump failure.

[0049] Feature database 15 is used to store communication features, associated system features, and time-series environment features, as well as the motor and water pump fault types corresponding to these features.

[0050] In summary, this application acquires and analyzes the communication status signals of the motor and water pump in real time. When communication loss is detected to last for a first preset duration, it no longer relies on a single signal for judgment. Instead, it automatically extracts multi-dimensional features, including communication features, related system features, and time-series environmental features, and inputs them into a pre-trained motor and water pump fault probability prediction model. The model outputs a quantified fault probability value, and then accurately identifies the fault type based on this probability. This effectively overcomes the technical problems of poor adaptability and high false alarm rate of existing monitoring mechanisms based on fixed thresholds and single signals. By integrating multi-source information with an intelligent prediction model, it achieves accurate differentiation of the root causes of motor and water pump communication loss events, significantly improving the accuracy and adaptability of fault diagnosis, while reducing false alarms caused by transient interference.

[0051] Corresponding to the above embodiments, this application also proposes a vehicle motor water pump fault monitoring device.

[0052] Reference Figure 3 The vehicle motor and water pump fault monitoring device 300 includes: an acquisition module 310, a first determination module 320, an output module 330, and a second determination module 340.

[0053] The acquisition module 310 is used to acquire the communication status signal of the motor-pump. The first determination module 320 is used to determine communication characteristics, associated system characteristics, and temporal environment characteristics when it is determined from the motor-pump communication status signal that the motor-pump is in a communication loss state for a first preset duration. The output module 330 is used to preset the communication characteristics, associated system characteristics, and temporal environment characteristics into a motor-pump failure probability prediction model to output the motor-pump failure probability. The second determination module 340 is used to determine the failure type of the motor-pump based on the motor-pump failure probability.

[0054] According to one embodiment of this application, the second determining module 340 is specifically used to: determine that the motor and water pump have a deterministic failure when the motor and water pump failure probability is greater than or equal to a first preset failure probability threshold; determine that the motor and water pump communication is in an unstable state when the motor and water pump failure probability is greater than or equal to a second preset failure probability threshold and less than a first preset failure probability threshold; and determine that the motor and water pump communication is subject to momentary interference when the motor and water pump failure probability is less than a second preset failure probability threshold.

[0055] According to one embodiment of this application, the communication features include the frequency and percentage loss of the motor-pump communication status signal. The first determining module 320 is specifically used to determine the frequency of the motor-pump communication status signal loss as the number of times the motor-pump changes from a normal communication state to a communication loss state within a second preset time period; and to determine the percentage loss of the motor-pump communication status signal based on the ratio between the cumulative duration of the motor-pump communication status being in a communication loss state within the second preset time period and the second preset time period; wherein the second preset time period is longer than the first preset time period.

[0056] According to one embodiment of this application, the associated system features include the standard deviation of vehicle power supply voltage and the rate of change of motor coolant temperature. The first determining module 320 is specifically used to: determine the standard deviation of vehicle power supply voltage based on the vehicle power supply voltage at multiple time points within a third preset time period; perform linear regression analysis on the motor coolant temperature at multiple time points within a fourth preset time period to obtain a regression line, and determine the slope of the regression line as the rate of change of motor coolant temperature; wherein, both the third preset time period and the fourth preset time period are greater than the first preset time period.

[0057] According to one embodiment of this application, the timing environment features include the time interval of communication status signal loss for the motor and water pump and runtime segment feature information. The first determining module 320 is specifically used to determine the starting time point when the motor and water pump enter the current communication loss state and the transition time point when the motor and water pump last transitioned from the communication loss state to the communication normal state, and to determine the time interval of communication status signal loss for the motor and water pump based on the difference between the transition time point and the starting time point; and to determine the runtime segment feature information based on the time interval in which the starting time point is located.

[0058] According to one embodiment of this application, a model training set for a preset motor and water pump failure probability prediction model is constructed based on multiple historical communication features, multiple historical associated system features, multiple historical time-series environmental features, and corresponding motor and water pump failure types; the preset motor and water pump failure probability prediction model is trained based on the model training set to construct a preset motor and water pump failure probability prediction model for predicting motor and water pump failure probabilities.

[0059] According to one embodiment of this application, any input data from the model training set is input into an initial motor-pump failure probability prediction model to obtain a predicted motor-pump failure probability; the predicted motor-pump failure probability and the motor-pump failure type corresponding to the input data are input into a binary cross-entropy loss function to calculate the discriminant loss to obtain a calculation result; the model parameters of the initial motor-pump failure probability prediction model are updated using the calculation result until the updated initial motor-pump failure probability prediction model meets a preset convergence condition to obtain a preset motor-pump failure probability prediction model.

[0060] It should be noted that the above explanation of the embodiments and beneficial effects of the vehicle motor water pump fault monitoring method also applies to the vehicle motor water pump fault monitoring method of this application. To avoid redundancy, it will not be elaborated in detail here.

[0061] Corresponding to the above embodiments, this application also proposes a computer-readable storage medium.

[0062] The computer-readable storage medium of this application stores a vehicle motor and water pump fault monitoring program thereon, which, when executed by a processor, implements the aforementioned vehicle motor and water pump fault monitoring method.

[0063] It should be noted that the above explanation of the embodiments and beneficial effects of the vehicle motor water pump fault monitoring method also applies to the computer-readable storage medium of the embodiments of this application. To avoid redundancy, it will not be elaborated in detail here.

[0064] Corresponding to the above embodiments, this application also proposes a vehicle.

[0065] See Figure 4 As shown, the vehicle 400 of this application includes a memory 410, a processor 420, and a vehicle motor water pump fault monitoring program stored in the memory 410 and capable of running on the processor 420. When the processor executes the vehicle motor water pump fault monitoring program, it implements the aforementioned vehicle motor water pump fault monitoring method.

[0066] It should be noted that the above explanation of the embodiments and beneficial effects of the vehicle motor water pump fault monitoring method also applies to the vehicles in the embodiments of this application. To avoid redundancy, they will not be elaborated in detail here.

[0067] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0068] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0069] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0070] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0071] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0072] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for monitoring vehicle motor water pump faults, characterized in that, The method includes: Obtain the communication status signal of the motor and water pump; If it is determined from the motor-pump communication status signal that the motor-pump is in a communication loss state for a first preset duration, then the communication characteristics, associated system characteristics, and temporal environment characteristics are determined. The communication features, the associated system features, and the time-series environment features are input into a preset motor-pump failure probability prediction model to output the motor-pump failure probability. The fault type of the motor and water pump is determined based on the failure probability of the motor and water pump.

2. The vehicle motor water pump fault monitoring method according to claim 1, characterized in that, The fault type of the motor and water pump is determined based on the fault probability of the motor and water pump, including: If the failure probability of the motor and water pump is greater than or equal to the first preset failure probability threshold, it is determined that the motor and water pump has experienced a deterministic failure. If the failure probability of the motor and water pump is greater than or equal to the second preset failure probability threshold and less than the first preset failure probability threshold, it is determined that the communication of the motor and water pump is in an unstable state. If the probability of motor-pump failure is less than the second preset failure probability threshold, it is determined that the motor-pump communication is subject to momentary interference.

3. The vehicle motor water pump fault monitoring method according to claim 1, characterized in that, The communication characteristics include the frequency and percentage of loss of motor and water pump communication status signals. Determining the communication characteristics includes: The number of times the motor-pump changes from a normal communication state to a communication loss state within a second preset time period is determined as the loss frequency of the motor-pump communication status signal. The percentage of lost communication signals of the motor and water pump is determined by the ratio between the cumulative duration of communication loss of the motor and water pump within the second preset duration and the second preset duration. Wherein, the second preset duration is longer than the first preset duration.

4. The vehicle motor water pump fault monitoring method according to claim 1, characterized in that, The associated system characteristics include the standard deviation of the vehicle power supply voltage and the rate of change of the motor coolant temperature. Determining the associated system characteristics includes: The standard deviation of the vehicle power supply voltage is determined based on the vehicle power supply voltage at multiple time points within a third preset time period. Linear regression analysis was performed on the motor coolant temperature at multiple time points within a fourth preset time period to obtain a regression line, and the slope of the regression line was determined as the rate of change of the motor coolant temperature. The third preset duration and the fourth preset duration are both greater than the first preset duration.

5. The vehicle motor water pump fault monitoring method according to claim 1, characterized in that, Timing environment characteristics include the time interval of communication status signal loss for the motor and water pump and runtime segment characteristic information. Determining these timing environment characteristics includes: The starting time point when the motor-pump enters the current communication loss state and the transition time point when the motor-pump last changed from the communication loss state to the communication normal state are determined, and the communication status signal loss time interval of the motor-pump is determined based on the difference between the transition time point and the starting time point. The runtime segment feature information is determined based on the time interval in which the starting time point is located.

6. The vehicle motor water pump fault monitoring method according to claim 1, characterized in that, The method further includes: The model training set of the preset motor and water pump failure probability prediction model is constructed based on multiple historical communication features, multiple historical associated system features, multiple historical time-series environmental features, and corresponding motor and water pump failure types. The preset motor-pump failure probability prediction model is trained based on the model training set to construct a preset motor-pump failure probability prediction model for predicting motor-pump failure probabilities.

7. The vehicle motor water pump fault monitoring method according to claim 6, characterized in that, Training the preset motor-pump failure probability prediction model based on the model training set includes: Input any input data from the model training set into the initial motor-pump failure probability prediction model to obtain the predicted motor-pump failure probability. The predicted motor-pump failure probability and the motor-pump failure type corresponding to the input data are input into the binary cross-entropy loss function to calculate the discrimination loss and obtain the calculation result. The model parameters of the initial motor-pump failure probability prediction model are updated using the calculation results until the updated initial motor-pump failure probability prediction model meets the preset convergence condition, thus obtaining the preset motor-pump failure probability prediction model.

8. A vehicle motor water pump fault monitoring device, characterized in that, The device includes: The acquisition module is used to acquire the communication status signals of the motor and water pump; The first determining module is used to determine communication characteristics, associated system characteristics, and temporal environment characteristics when it is determined from the motor-pump communication status signal that the motor-pump is in a communication loss state for a first preset duration. The output module is used to preset the communication features, the associated system features, and the temporal environment features into a motor and water pump failure probability prediction model, so as to output the motor and water pump failure probability. The second determining module is used to determine the fault type of the motor and water pump based on the fault probability of the motor and water pump.

9. A computer-readable storage medium, characterized in that, It stores a vehicle motor and water pump fault monitoring program, which, when executed by the processor, implements the vehicle motor and water pump fault monitoring method according to any one of claims 1-7.

10. A vehicle, characterized in that, The system includes a memory, a processor, and a vehicle motor water pump fault monitoring program stored in the memory and executable on the processor. When the processor executes the vehicle motor water pump fault monitoring program, it implements the vehicle motor water pump fault monitoring method according to any one of claims 1-7.

Images