Vibration reduction method and system for vehicle motor and vehicle

Abstract

The embodiment of the invention relates to the technical field of vehicle vibration control, in particular to a vibration reduction method and system for a vehicle motor and a vehicle. The method mainly comprises the following steps: determining a predicted vibration acceleration of the motor in a future time period based on real-time operation data of the motor in a historical time period; and generating a corresponding vibration reduction control signal according to the predicted vibration acceleration. And controlling a magneto-rheological damper preset on the motor based on the vibration damping control signal to drive the magneto-rheological damper to adjust the damping force so as to perform vibration damping on the motor. Predicted vibration acceleration in a future time period is predicted through historical operation data, and vibration suppression in advance is achieved. Moreover, by utilizing the characteristic that the damping force of the magnetorheological damper can be electrically controlled and adjusted, the damping system can carry out accurate and quantifiable damping output according to a prediction result, and the inherent defects that a passive damping scheme is fixed in damping parameter and cannot adapt to complex and changeable working conditions are overcome.

Description

Technical Field

[0001] This application relates to the field of vehicle vibration control technology, and in particular to a method, system and vehicle for vibration reduction of a vehicle motor. Background Technology

[0002] As the core power source of new energy vehicles, the vibration generated by the electric motor during operation is one of the key factors affecting the driving experience and the lifespan of the motor.

[0003] Currently, passive vibration reduction technology is widely used in the industry to suppress motor vibration. For example, rubber shock absorbers are installed between the motor and the frame to absorb and disperse vibration energy using the elasticity and damping properties of rubber materials; or hydraulic shock absorbers are used to dissipate vibration energy through the flow damping of hydraulic oil.

[0004] However, the damping characteristics of the aforementioned passive damping technologies are usually fixed and cannot be adjusted in real time according to the vehicle's driving conditions. This results in limited damping effect in complex and ever-changing actual use environments, and may lead to contradictions such as insufficient damping under some conditions and excessive damping under others. Summary of the Invention

[0005] Therefore, it is necessary to provide a vibration reduction method, system, and vehicle for a vehicle motor to address at least one of the aforementioned technical problems.

[0006] In a first aspect, embodiments of this application provide a vibration reduction method for a vehicle motor, the method comprising: Based on the real-time operating data of the motor in historical periods, the predicted vibration acceleration of the motor in future periods is determined; the historical period is the first time range ending at the current time, and the future period is the second time range starting at the current time.

[0007] Based on the predicted vibration acceleration, a corresponding vibration reduction control signal is generated.

[0008] The vibration reduction control signal controls the magnetorheological vibration damper pre-installed on the motor to drive the magnetorheological vibration damper to adjust the damping force and reduce the vibration of the motor.

[0009] In some embodiments, when determining the predicted vibration acceleration of the motor in a future period based on real-time operating data of the motor over a historical period, the vibration reduction method for the vehicle motor further includes: Real-time operating data is used as input features and fed into a pre-trained vibration intensity prediction model to obtain the predicted vibration acceleration in future time periods; the vibration intensity prediction model is a recurrent neural network model trained based on the historical operating data of the motor.

[0010] In some embodiments, the vibration reduction method for the vehicle motor further includes: If the actual vibration acceleration of the motor is not less than the predicted vibration acceleration after vibration reduction, the vibration intensity prediction model is updated and trained based on the actual operating data.

[0011] In some embodiments, if the vibration reduction control signal is a current control signal, then when generating the corresponding vibration reduction control signal based on the predicted vibration acceleration, the vibration reduction method of the vehicle motor further includes: Determine the target damping force required for the magnetorheological vibration damper based on the predicted vibration acceleration; Based on the preset mapping relationship between damping force and current, the target current corresponding to the target damping force is determined, and the corresponding current control signal is generated based on the target current.

[0012] In some embodiments, when generating a corresponding current control signal based on a target current, the vibration reduction method for the vehicle motor further includes: Based on the target current, the duty cycle of the pulse width modulation signal is adjusted to generate a current control signal.

[0013] In some embodiments, the vibration reduction method for the vehicle motor further includes: Based on the predicted vibration acceleration, the health status of the motor is determined, and an early warning message is output when the determination result indicates an abnormality.

[0014] In some embodiments, real-time operating data includes, but is not limited to: motor vibration acceleration, vibration displacement, vibration velocity, rotational speed, torque, or stator temperature.

[0015] In a second aspect, embodiments of this application provide a vibration damping system for a vehicle motor, the system comprising: Data sensors are used to acquire real-time operating data of the motor within a historical time period; the historical time period is the first time range ending at the current moment.

[0016] The processor is used to perform the following steps: Based on the real-time operating data of the motor in historical time periods, the predicted vibration acceleration of the motor in future time periods is determined; the future time period is the second time range starting from the current moment. Based on the predicted vibration acceleration, a corresponding vibration reduction control signal is generated; The vibration damping control signal controls the magnetorheological vibration damper pre-installed on the motor; Magnetorheological dampers are used to receive damping control signals and adjust the damping force based on the damping control signals to dampen the motor.

[0017] In a third aspect, embodiments of this application provide a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the vibration reduction method for a vehicle motor provided in any embodiment of the first aspect of this application.

[0018] In a fourth aspect, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vibration reduction method for a vehicle motor provided in any embodiment of the first aspect of this application.

[0019] The aforementioned vibration reduction method, system, and vehicle for vehicle motors predict future vibration acceleration based on historical operating data, transforming vibration control from a passive response to active intervention. This solves the problem of poor vibration reduction performance under abrupt changes in operating conditions caused by response lag in traditional vibration reduction systems, achieving early vibration suppression. Furthermore, by utilizing the electrically adjustable damping force of magnetorheological dampers, the vibration reduction system can provide precise and quantifiable damping output based on the prediction results, overcoming the inherent shortcomings of passive vibration reduction schemes, such as fixed damping parameters and inability to adapt to complex and variable operating conditions. Attached Figure Description

[0020] Figure 1 This is an application environment diagram of the vibration reduction method for vehicle motors in some embodiments; Figure 2 This is a flowchart illustrating the vibration reduction method for a vehicle motor in some embodiments; Figure 3 This is a flowchart illustrating the step of generating a current control signal in some embodiments; Figure 4 This is a structural block diagram of the vibration damping system for the vehicle motor in some embodiments; Figure 5 This is a schematic diagram of the drive circuit of the magnetorheological vibration damper in some embodiments; Figure 6 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation

[0021] To make the technical solutions and advantages of this application clearer, the embodiments and related technical content of this application will be further described in detail below with reference to the accompanying drawings and text description. It should be understood that the embodiments described below are only used to explain the technical solutions of the embodiments of this application and are not intended to limit more possible implementations of this application.

[0022] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0023] It should be noted that relational terms such as "first" and "second" appearing in this document are used only to distinguish things, states, or actions, and do not necessarily indicate or imply relative importance or order. The terms "including," "comprising," or any other variations thereof are used to indicate non-exclusive inclusion, and the included objects may not be limited to those listed in this document. The terms "multiple" or other variations are used to indicate that the number of objects is two or more.

[0024] For ease of understanding, Figure 1 An application environment is illustrated, in which a controller 101 is built into a vehicle 102 to execute the steps of a vibration reduction method for the vehicle motor. During execution, the controller 101 can communicate with other devices or modules of the vehicle 102 via a network to obtain real-time operating data of the motor sent by other devices or modules of the vehicle 102. The controller 101 can be implemented using a standalone controller or a controller cluster consisting of multiple controllers.

[0025] The controller can be implemented using at least one of the following hardware forms: programmable logic array (PLA), field-programmable gate array (FPGA), digital signal processor (DSP), application-specific integrated circuit (ASIC), general-purpose processor, or other programmable logic device.

[0026] Of course, the vibration reduction method for vehicle motors provided in this application embodiment can also be applied to more scenarios not shown.

[0027] In a first aspect, embodiments of this application provide a vibration reduction method for a vehicle motor, which can be applied to... Figure 1 In the application environment shown, it can be applied to Figure 1 Taking controller 101 as an example, in some embodiments, such as Figure 2 As shown, the vibration reduction method for the vehicle motor includes steps S201, S202, and S203 that can be executed by the controller 101. Each step is described in detail below.

[0028] Step S201: Based on the real-time operating data of the motor in historical periods, determine the predicted vibration acceleration of the motor in future periods.

[0029] Historical time periods can be the first time range of the past, ending at the current moment or at some past moment, while future time periods can be the second time range of the future, starting at the current moment or at some future moment.

[0030] Historical time periods can also refer to a retrospective time window for predictive analysis. The length of a historical time period should be moderate; too short a period may fail to capture complete dynamic characteristics, while too long a period will introduce redundant information and increase the computational burden. The historical time period ends at the current moment, ensuring that the real-time operational data used is the most up-to-date and closely follows the motor's current state. The most relevant data sequence can accurately reflect the dynamic evolution of motor vibration from the past to the present moment. The current moment can be included within the historical time period.

[0031] For example, the specific length of the historical period can be 5 minutes, and the real-time operation data of the historical period can be the vibration acceleration, vibration displacement, vibration velocity, and other data corresponding to each second within the 5 minutes.

[0032] The future timeframe can also refer to the upcoming time range that the system attempts to anticipate and exert influence on. Starting from the current moment, the future timeframe directly links the predicted objective with the urgency of execution, clarifying that the vibration reduction system's intervention is aimed at a period immediately following the current moment.

[0033] The first and second duration ranges can be set as needed and are not specifically restricted here. Furthermore, the durations corresponding to the first and second duration ranges can be the same or different; this application does not impose any restrictions on this.

[0034] Real-time operating data refers to physical quantities or parameters that reflect the current operating status of a motor, directly acquired through sensors or a CAN (Controller Area Network) bus. In this application, real-time operating data specifically refers to dynamic data strongly correlated with the motor's vibration characteristics, and its core function is to provide accurate and timely input information for vibration intensity prediction models.

[0035] Specifically, real-time operating data includes, but is not limited to, the motor's vibration acceleration, vibration displacement, vibration velocity, rotational speed, torque, or stator temperature. In some specific implementations, vibration acceleration, vibration displacement, and vibration velocity can be used as core prediction features, collected at a sampling frequency of 100 Hz to ensure temporal continuity; rotational speed, torque, and stator temperature can be used as auxiliary prediction features to improve prediction accuracy.

[0036] The predicted vibration acceleration is a forward-looking judgment derived from the in-depth mining and analysis of the temporal correlation characteristics of real-time operational data within a future period, based on real-time operational data and algorithms.

[0037] Step S202: Generate the corresponding vibration reduction control signal based on the predicted vibration acceleration.

[0038] Step S203: Control the magnetorheological damper preset on the motor based on the vibration reduction control signal to drive the magnetorheological damper to adjust the damping force and reduce the vibration of the motor.

[0039] A magnetorheological damper is an intelligent fluid vibration damping device. Its core working principle utilizes the characteristic that magnetorheological fluid undergoes millisecond-level reversible viscosity changes under the influence of a magnetic field. The basic structure of a magnetorheological damper includes a cylinder filled with magnetorheological fluid, a piston, and an electromagnetic coil. Pre-installed on a motor, the damper changes the viscosity of the magnetorheological fluid upon receiving a vibration damping control signal, thereby providing a corresponding damping force to suppress motor vibration.

[0040] In one specific implementation, a vibration acceleration sensor mounted on the motor housing and a sensor integrated into the motor controller continuously collect vibration acceleration, speed, and torque data of the motor over the past 300 seconds (i.e., the historical period, the first time range). This data constitutes real-time operating data. After receiving the real-time operating data, the processor runs a built-in prediction algorithm to calculate the predicted vibration acceleration of the motor over the next 300 seconds (i.e., the future period, the second time range). Subsequently, the processor generates a vibration damping control signal with specific parameters based on the predicted vibration acceleration. The vibration damping control signal is transmitted to the magnetorheological damper mounted on the motor through a drive circuit. Upon receiving the vibration damping control signal, the electromagnetic coil inside the magnetorheological damper generates a magnetic field of corresponding strength, instantaneously changing the flow characteristics of the magnetorheological fluid, thereby adjusting the damping force of the magnetorheological damper to the target value to actively counteract and suppress the predicted motor vibration.

[0041] By predicting future vibration acceleration using historical operating data, vibration control shifts from passive response to active intervention. This solves the problem of poor vibration reduction performance under abrupt changes due to response lag in traditional vibration reduction systems, achieving proactive vibration suppression. Furthermore, by utilizing the electrically adjustable damping force of magnetorheological dampers, the vibration reduction system can provide precise and quantifiable damping output based on the prediction results, overcoming the inherent limitations of passive vibration reduction schemes with fixed damping parameters that cannot adapt to complex and variable operating conditions.

[0042] In some embodiments, the controller may further include the following steps when performing step S201: inputting real-time running data as input features into a pre-trained vibration intensity prediction model to obtain the predicted vibration acceleration in future time periods.

[0043] The vibration intensity prediction model is a recurrent neural network model trained based on the historical operating data of the motor.

[0044] Specifically, input features are obtained by preprocessing real-time running data. Data preprocessing operations include, but are not limited to, missing value handling, noise removal, or data normalization.

[0045] For example, linear interpolation is used to fill in missing data to avoid data breaks; moving average filtering is used to eliminate vibration data noise caused by electromagnetic interference during motor operation; and the mapmin-max function (a MATLAB function for data normalization, often used to map each row of a matrix to a specified range) is used to map all data (vibration acceleration, motor speed, etc.) to the [0,1] interval to avoid large values ​​masking the influence of small values ​​on the prediction results.

[0046] Recurrent neural networks (RNNs) are a type of neural network specifically designed for processing sequential data. They can apply information from previous data to the current output, making them suitable for analyzing dynamic temporal characteristics in time series data. In this application, a RNN is used to learn the temporal correlation features in historical motor operating data, enabling it to capture the time lag relationship between parameters such as motor speed or torque and vibration acceleration, thereby accurately predicting the future vibration trend of the motor.

[0047] During the model training phase, a large amount of historical motor operating data covering various working conditions is collected. This historical operating data can be divided into training, validation, and test sets in a 7:2:1 ratio. The validation set is used for model training and parameter tuning during training to avoid overfitting; the test set is used to verify the model's accuracy.

[0048] During model training, the training parameters are set to epochs=60 and batch_size=40 (i.e., 40 samples are used to update the parameters each time, for a total of 60 training epochs). The loss value on the validation set is observed during training. If the loss value increases for 5 consecutive epochs during training, an early stopping strategy is adopted to stop training and save the optimal model.

[0049] In the model accuracy evaluation phase, the input data from the test set is input into the trained model to obtain predicted values. Then, through inverse normalization, the predicted values ​​are restored to actual physical units (i.e., acceleration mm / s²). 2Regression prediction is used to calculate the mean square error of the predicted value for index evaluation. The smaller the value, the smaller the deviation between the predicted value and the actual value.

[0050] After the model is trained, it is converted into a lightweight format and deployed to the vehicle computing device to receive real-time operating data of the motor and output predicted vibration acceleration.

[0051] By employing a recurrent neural network model, the system is able to deeply mine and utilize the temporal dependencies in motor operation data, overcoming the shortcomings of simple regression or static models in capturing the dynamic changes in vibration, thereby significantly improving the accuracy of vibration prediction.

[0052] In some embodiments, the vibration reduction method for a vehicle motor may further include the following steps: after the motor is vibration reduced, if the actual vibration acceleration of the motor is not less than the predicted vibration acceleration, the vibration intensity prediction model is updated and trained based on the actual operating data; the new real-time operating data is used as input features and input into the updated and trained vibration intensity prediction model to obtain the predicted vibration acceleration for the new future time period.

[0053] Actual vibration acceleration refers to a physical quantity that characterizes the intensity of motor vibration, obtained directly by an accelerometer. It is objective data reflecting the true vibration state of the motor. Specifically, by installing a piezoelectric ceramic accelerometer on the motor housing, the actual vibration acceleration of the motor can be collected.

[0054] Update training refers to the process of readjusting or optimizing the parameters of a trained model using new data. It aims to enable the model to adapt to changes in data distribution or improve its performance in specific scenarios, and is an important means of ensuring the long-term effectiveness of the model.

[0055] In this application, after generating a vibration reduction control signal based on the predicted vibration acceleration and reducing the vibration of the motor each time, if the actual vibration acceleration is reduced relative to the predicted vibration acceleration, it indicates that there is a vibration reduction effect; otherwise, it indicates that the model's predictive ability is weak in actual working conditions. The trained vibration intensity prediction model is retrained using newly collected actual operating data, so that the model can learn the vibration characteristics of the motor performance as it ages over time or as new working conditions appear.

[0056] For example, the system predicts a vibration acceleration of 5 mm / s² within the next 0.1 seconds based on real-time operational data. 2 Based on this, the magnetorheological vibration damper was controlled to reduce vibration. After 0.1 seconds, the system read the measurement value from the vibration sensor and obtained the actual vibration acceleration as 6 mm / s². 2If this value is not less than the predicted vibration acceleration, the system triggers the model optimization process, storing the real-time running data and prediction results that caused the prediction deviation into a specific dataset. When the vehicle is idle (such as charging or parking), the data stored in the dataset is used to update and train the original vibration intensity prediction model, fine-tuning its network parameters, thereby improving the prediction accuracy of the model in similar working conditions in the future.

[0057] By using actual vibration acceleration as a feedback parameter during model usage, the system has the ability to self-verify and monitor the performance degradation of the vibration intensity prediction model in real time. This avoids the problem of decreased prediction accuracy caused by motor aging, component wear, or environmental changes after the deployment of pre-trained models, and solves the limitation of static models in adapting to dynamic changes throughout the vehicle's entire life cycle.

[0058] In some embodiments, the damping control signal is a current control signal, such as... Figure 3 As shown, when the controller executes step S202, it may also include steps S2021 and S2022.

[0059] Step S2021: Determine the target damping force required for the magnetorheological damper based on the predicted vibration acceleration.

[0060] The target damping force refers to a specific force value that the vibration damper needs to output in order to achieve the ideal vibration reduction effect. In this application, the target damping force specifically refers to the ideal damping force that the magnetorheological vibration damper needs to generate in order to effectively suppress the vibration energy corresponding to the predicted vibration acceleration. It is a theoretical set value that is dynamically calculated based on the predicted vibration results.

[0061] Step S2022: Based on the preset mapping relationship between damping force and current, determine the target current corresponding to the target damping force, and generate the corresponding current control signal based on the target current.

[0062] In the control of magnetorheological dampers, the relationship between damping force and electromagnetic coil current is typically established through experimental calibration. The relationship between damping force and current is not a simple linear proportional relationship; therefore, a pre-calibrated mapping table or fitting function is needed to describe their correspondence. In the practical application of this application, the mapping relationship refers to a pre-obtained correspondence obtained through bench testing and stored in the system memory. It can be a two-dimensional lookup table or an empirical formula. Its core function is to convert the calculated, abstract target damping force into a specific, executable target current command, thereby achieving precise control of the magnetorheological damper's output force.

[0063] For example, the vibration intensity prediction model outputs a predicted vibration acceleration of 8 mm / s² at a future moment. The target damping force required from the magnetorheological damper is determined to be 50 N by calculation or table lookup (e.g., the greater the vibration acceleration, the greater the required damping force). Based on a preset mapping relationship between damping force and current stored in memory (e.g., a calibration data table: 50 N damping force corresponds to 1.2 A current; 60 N corresponds to 1.5 A current, etc.), the target current required to achieve the 50 N damping force is determined to be 1.2 A by table lookup or interpolation. Finally, the system generates a current control signal designed to drive the electromagnetic coil of the magnetorheological damper to produce a current of 1.2 A.

[0064] By using the target damping force as an intermediate physical quantity, problems such as unclear logic and difficulty in parameter adjustment that may exist when directly mapping the predicted vibration acceleration to a current control signal can be avoided. Through a preset mapping relationship, the theoretically calculated target damping force is accurately converted into an operable electrical control quantity, which solves the problem of inaccurate control and large deviation between the output force and the expected value caused by the nonlinear characteristics of the magnetorheological damper, and realizes high-precision conversion from control command to damping force output.

[0065] In some embodiments, the vibration reduction method for a vehicle motor may further include the following steps: adjusting the duty cycle of a pulse width modulation signal based on a target current to generate a current control signal.

[0066] In the field of power electronics and control, pulse width modulation (PWM) signals are square wave signals that achieve different average voltage or current levels by adjusting the duty cycle of the pulse. In the practical application of this application, this feature specifically refers to a signal used to control the current flowing through the electromagnetic coil of a magnetorheological damper.

[0067] Duty cycle is a key parameter of pulse width modulation (PWM) signals, defined as the ratio of pulse duration to the total period within a signal cycle. Typically, the duty cycle is proportional to the average voltage or current across the load. By dynamically and precisely adjusting the duty cycle, the average current output to the electromagnetic coil can be smoothly and continuously controlled, thereby adjusting the damping force of the magnetorheological damper.

[0068] For example, assume the target current is determined to be 1.2A based on the predicted vibration acceleration. A pulse width modulation (PWM) signal generator with a peak voltage of 5V is pre-installed in the system. Based on stored calibration data, it is determined that an average current of 1.2A requires a 60% duty cycle. This generates a PWM signal with a fixed frequency of 1kHz and a 60% duty cycle, meaning that within one cycle, there are 0.6 milliseconds of high level (5V) and 0.4 milliseconds of low level (0V). The PWM signal is fed into a switching drive circuit, which converts it into a power signal capable of driving a large current. After smoothing, a current with an average value of 1.2A is stably supplied to the electromagnetic coil of the magnetorheological damper, thereby enabling the damper to accurately generate the desired damping force.

[0069] Continuous current control is achieved by adjusting the duty cycle as a single parameter. This method is simple, reliable, and easy to dynamically adjust in software. It solves the problems of parameter drift and difficulty in control in complex analog circuits, and enhances the flexibility and accuracy of control.

[0070] In some embodiments, the vibration reduction method for a vehicle motor may further include the following steps: determining the health status of the motor based on the predicted vibration acceleration, and outputting a warning message when the determination result indicates an abnormality.

[0071] Health status is a comprehensive evaluation index of the degree to which the current performance status of a device deviates from its initial or normal state. It is usually assessed indirectly by monitoring and analyzing the device's operating parameters.

[0072] In this application, the health status of the motor specifically refers to the overall mechanical integrity of the motor structure and the reliability of its fixed connections. By analyzing and predicting the key parameter of vibration acceleration, it is possible to determine whether the motor is in an abnormal state caused by faults such as bearing wear, rotor dynamic imbalance, or loose fasteners.

[0073] Under normal circumstances, the abnormality of the motor's health status can be determined by predicting that the value of vibration acceleration continuously or significantly exceeds the safety threshold preset according to the normal operating conditions of the motor.

[0074] Early warning information can be output synchronously through the vibration intensity prediction model in the form of abnormal probability values, thereby reminding the driver to pay attention or prompting maintenance personnel to intervene in advance, thus transforming passive maintenance into proactive maintenance.

[0075] In some specific embodiments, if the predicted vibration acceleration values ​​continuously exceed the corresponding threshold by more than 30% at a certain stable speed, and this phenomenon lasts for 5 seconds, the motor health status is judged to be abnormal. The system sends a command to the instrument cluster via the vehicle CAN bus to display the abnormal probability value of the motor in the next 8 hours on the instrument panel. At the same time, the warning information can also be uploaded to the cloud server via the vehicle T-Box to notify the corresponding maintenance team.

[0076] By utilizing predicted vibration acceleration data for motor health status analysis, the reuse of sensor data and computing resources is achieved. Fault warning based on predicted values ​​has a shorter reaction time compared to diagnosis based on actual vibration values, and can provide early warnings before the fault fully manifests or causes secondary damage, solving the problem of delayed warnings in traditional diagnostic systems and improving the active safety and reliability of vehicles.

[0077] It should be understood that, although Figure 2 and Figure 3 The steps in the flowchart are shown sequentially according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Figure 2 and Figure 3 Unless otherwise expressly stated herein, the steps illustrated and other steps involved in the embodiments are not subject to strict order restrictions and may be performed in other orders. Furthermore, at least some steps in the foregoing embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0078] In a second aspect, embodiments of this application provide a vibration damping system for a vehicle motor, such as... Figure 4 As shown, the vibration reduction system 400 specifically includes: a data sensor 401, a processor 402, and a magnetorheological vibration damper 403.

[0079] Data sensor 401 is used to acquire real-time operating data of the motor during historical periods.

[0080] Processor 402 is configured to perform the following steps: determining the predicted vibration acceleration of the motor in a future period based on real-time operating data of the motor during a historical period; generating a corresponding vibration damping control signal based on the predicted vibration acceleration; and controlling a magnetorheological vibration damper pre-installed on the motor based on the vibration damping control signal.

[0081] The magnetorheological damper 403 is used to receive the damping control signal and adjust the damping force based on the damping control signal to dampen the motor.

[0082] Among them, data sensors are basic components used to detect physical phenomena and convert them into electrical signals. There are many types of data sensors, and the selection needs to be based on the physical quantity being measured.

[0083] The data sensor in this application is a collective concept, specifically referring to a group of sensors configured to acquire real-time operating data, including but not limited to: piezoelectric ceramic accelerometers for acquiring vibration acceleration, rotary transformers or encoders for acquiring motor speed, and thermistors for acquiring temperature, etc.

[0084] A processor is the core computing unit that performs arithmetic and logical operations and controls the flow of instructions. It can be a microcontroller, microprocessor, or digital signal processor, etc. In the practical application of this application, the processor is specifically defined as the hardware carrier that executes the vibration reduction method for a vehicle motor. It receives signals from data sensors, runs built-in prediction algorithms and control logic, and ultimately outputs control instructions.

[0085] In some specific embodiments, the data sensor includes a piezoelectric ceramic accelerometer (for acquiring vibration acceleration) mounted on the motor housing and a CAN bus interface for communicating with the motor controller (for acquiring operating data such as speed and torque). The processor is a high-performance microprocessor in the vehicle domain controller, which internally stores a pre-trained vibration intensity prediction model and control program. The processor periodically reads the sensor data, executes the vehicle motor vibration reduction method as provided in the first aspect of this application, and calculates the required vibration reduction control signal. The vibration reduction control signal is sent to the magnetorheological damper through a dedicated wiring harness. The magnetorheological damper is mechanically fixed between the motor and the vehicle frame through its mounting bracket. Its internal electromagnetic coil changes the magnetic field according to the received signal, thereby adjusting the damping force in real time to achieve active suppression of motor vibration.

[0086] In some embodiments, the processor in the vibration damping system of the vehicle motor is integrated into the on-board computing unit, and the magnetorheological damper is electrically connected to the on-board computing unit through a drive circuit.

[0087] An onboard computing unit (OCU) is an electronic control unit inside a vehicle responsible for performing complex computational tasks. It possesses sufficient computing power to run vibration intensity prediction models and execute complex control algorithms in real time.

[0088] In practical applications of this application, the drive circuit specifically refers to a power electronic circuit located between the on-board computing unit and the magnetorheological damper. Its core function is to safely and reliably convert the microamp or milliamp level digital control signals (such as pulse width modulation signals) issued by the processor into a stable current, possibly reaching the ampere level, required to drive the electromagnetic coil of the magnetorheological damper.

[0089] In some specific embodiments, the processor runs within the vehicle's power domain controller (i.e., the onboard computing unit). The power domain controller outputs a 5V pulse-width modulated (PWM) signal with an adjustable duty cycle via its general purpose input / output (GPIO) interface. This PWM signal is transmitted to a separate drive circuit via a shielded wiring harness. This drive circuit board is typically mounted near the magnetorheological damper and contains a MOS power switch at its core. The drive circuit amplifies the received 5V PWM signal, outputting a controlled current with an amplitude of 12V and a maximum current of 2A. This high-current conductor is then electrically connected directly to the electromagnetic coil terminals of the magnetorheological damper, thereby achieving precise control of the damper's damping force.

[0090] like Figure 5 As shown, the power input and output of the drive circuit are both +5V. The input signal is the predicted vibration acceleration, which is converted into different duty cycles from 0V to 5V by software. An NPN transistor Q12 and a MOSFET Q1 are used for the switching design. When the input to Q12 is low, Q12 is not conducting, and Q1's Vgs = 0, so Q1 is not conducting. When the input to Q12 is high, Q12 conducts, and MOSFET Q1's Vgs > Vth, so Q1 conducts. Thus, MOSFET Q1 is controlled by a pulse width modulation signal to output an adjustable and stable DC power supply to control the electromagnetic coil of the magnetorheological damper.

[0091] By setting up a dedicated drive circuit, a safe and efficient buffer and conversion link is established between the low-power control unit and the high-power actuator. This solves the problems of insufficient drive capability of the on-board computing unit's input / output interface, which is easily damaged, and the electromagnetic interference of power signals on digital signals, thereby improving the reliability and electromagnetic compatibility of the entire system.

[0092] In a third aspect, embodiments of this application provide a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the vibration reduction method for a vehicle motor provided in any embodiment of the first aspect of this application.

[0093] In some embodiments, the computer device may be a controller, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores motor operating data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements the vehicle motor vibration reduction method in any embodiment of this document.

[0094] Those skilled in the art will understand that Figure 6 The structures shown are merely block diagrams of some structures related to the embodiments of this application and do not constitute a limitation on the computer devices on which the embodiments of this application are applied. Specific computer devices may include more or fewer components than those shown in the figures, or combine certain components, or have different component arrangements.

[0095] In a fourth aspect, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vibration reduction method for a vehicle motor provided in any embodiment of the first aspect of this application.

[0096] The computer-readable storage medium may be Figure 6 The computer-readable storage medium in the computer device shown.

[0097] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The aforementioned computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments of this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0098] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0099] The above embodiments merely illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of protection of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for vibration reduction of a vehicle motor, characterized in that, The method includes: Based on the real-time operating data of the motor in a historical period, the predicted vibration acceleration of the motor in a future period is determined; the historical period is a first time range ending at the current time, and the future period is a second time range starting at the current time. Based on the predicted vibration acceleration, a corresponding vibration reduction control signal is generated; The vibration reduction control signal controls the magnetorheological vibration damper preset on the motor to drive the magnetorheological vibration damper to adjust the damping force and reduce the vibration of the motor.

2. The method according to claim 1, characterized in that, The step of determining the predicted vibration acceleration of the motor in a future period based on the motor's real-time operating data over a historical period includes: The real-time operating data is used as input features and fed into a pre-trained vibration intensity prediction model to obtain the predicted vibration acceleration for the future time period; wherein, the vibration intensity prediction model is a recurrent neural network model trained based on the historical operating data of the motor.

3. The method according to claim 2, characterized in that, The method further includes: After the motor is subjected to vibration reduction, if the actual vibration acceleration of the motor is not less than the predicted vibration acceleration, the vibration intensity prediction model is updated and trained based on the real-time operating data.

4. The method according to claim 1, characterized in that, The vibration reduction control signal is a current control signal; The step of generating a corresponding vibration reduction control signal based on the predicted vibration acceleration includes: Based on the predicted vibration acceleration, determine the target damping force required for the magnetorheological vibration damper; Based on the preset mapping relationship between damping force and current, the target current corresponding to the target damping force is determined, and a corresponding current control signal is generated based on the target current.

5. The method according to claim 4, characterized in that, The generation of the corresponding current control signal based on the target current includes: Based on the target current, the duty cycle of the pulse width modulation signal is adjusted to generate the current control signal.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Based on the predicted vibration acceleration, the health status of the motor is determined, and an early warning message is output when the determination result indicates an abnormality.

7. The method according to any one of claims 1 to 5, characterized in that, The real-time operating data includes, but is not limited to: the vibration acceleration, vibration displacement, vibration velocity, rotational speed, torque, or stator temperature of the motor.

8. A vibration damping system for a vehicle motor, characterized in that, The system includes: Data sensors are used to acquire real-time operating data of the motor within a historical time period; the historical time period is a first duration range ending at the current moment. The processor is used to perform the following steps: Based on the real-time operating data of the motor in the historical period, the predicted vibration acceleration of the motor in the future period is determined; the future period is a second time range starting from the current moment. Based on the predicted vibration acceleration, a corresponding vibration reduction control signal is generated; The vibration reduction control signal controls the magnetorheological vibration damper pre-installed on the motor; A magnetorheological damper is used to receive the damping control signal and adjust the damping force based on the damping control signal to dampen the motor.

9. The system according to claim 8, characterized in that, The processor is integrated into the vehicle computing unit; the magnetorheological damper is electrically connected to the vehicle computing unit through a drive circuit.

10. A vehicle, characterized in that, The vehicle includes a vibration damping system for the vehicle motor as described in any one of claims 8 or 9.

Images