Driving shaft assembly and automobile

Abstract

The invention discloses a driving shaft assembly and an automobile, and relates to the field of automobile parts, the driving shaft assembly comprises a driving shaft, a cooling circulation assembly and a controller, the driving shaft is connected with a motor shaft and a hub, and a flow channel is formed in the driving shaft; the cooling circulation assembly is communicated with the flow channel to form a cooling circulation loop; the controller is connected with the cooling circulation assembly and is configured to obtain the current temperature, the current rotating speed, the current torque and the current environment temperature of the driving shaft; and according to the current temperature, the current rotating speed, the current torque and the current environment temperature of the driving shaft, a preset neural network model is adopted to calculate the target flow of cooling liquid in a cooling circulation loop, and the cooling circulation assembly is controlled according to the target flow of the cooling liquid. The temperature of the driving shaft can be prevented from being too high, the problem of accelerated aging of the driving shaft caused by insufficient heat dissipation of the driving shaft is effectively solved, the service life of the driving shaft and related parts is prolonged, and the performance stability of the driving shaft is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of automobile parts, and in particular to a drive shaft assembly and an automobile. Background Art

[0002] Distributed electric vehicles are an innovative achievement in the field of new energy vehicles. They use multiple motors to drive each wheel independently. This layout optimizes vehicle space and eliminates components such as the traditional central drive shaft. Drive shafts are located near each wheel, tightly connecting the motors to the wheel hubs. For example, a common four-wheel distributed drive electric vehicle has each wheel equipped with an independent drive shaft and motor.

[0003] While the vehicle is running, the drive shaft may also heat up due to some reasons, such as: 1. During the power transmission process from the motor to the wheels, the drive shaft struggles to achieve zero-loss energy transmission. For one thing, the drive shaft has a certain amount of rotational inertia, which must be overcome during startup, acceleration, and deceleration. This energy consumption is converted into heat. Furthermore, various connectors in the power transmission process, such as universal joints, generate power losses during operation to accommodate different transmission angles. This lost energy is ultimately dissipated as heat.

[0004] 2. The drive shaft is closely connected to the motor. Electromagnetic induction during motor operation can affect the drive shaft. The alternating magnetic field within the motor generates induced currents in metal components such as the drive shaft. According to Joule's law, these induced currents cause components to heat up. Electromagnetic induction heating is particularly pronounced during high-power, high-speed operation.

[0005] The drive shaft generates heat when in use. If the local temperature is too high, it will accelerate the aging of the drive shaft and affect the performance and life of the drive shaft. Summary of the Invention

[0006] An embodiment of the present invention provides a drive shaft assembly and an automobile to solve the technical problem in the related art that the drive shaft between the existing automobile motor and the wheel hub generates heat during actual use. When the local temperature is too high, it will accelerate the aging of the drive shaft and affect the performance and life of the drive shaft.

[0007] In a first aspect, a drive shaft assembly is provided, comprising: A drive shaft, which is used to connect the motor shaft and the wheel hub, and a flow channel is provided inside the drive shaft; a cooling circulation component, which is in communication with the flow channel to form a cooling circulation loop; A controller, connected to the cooling cycle component, is configured to: Obtaining the current temperature, current speed, current torque and current ambient temperature of the drive shaft; Based on the current temperature, current speed, current torque and current ambient temperature of the drive shaft, a preset neural network model is used to calculate the target flow rate of the coolant in the cooling circulation loop, and the cooling circulation component is controlled according to the target flow rate of the coolant.

[0008] In some embodiments, the cooling circulation assembly includes a coolant tank, a circulation pump, a flow control valve, a liquid inlet pipe, a liquid outlet pipe, and two slip rings; The two slip rings are arranged at both ends of the driving shaft, and each slip ring is provided with an interface; The coolant tank, circulation pump, flow control valve, liquid inlet pipe, liquid outlet pipe are connected to the interfaces of the two slip rings and then connected to the flow channel to form a cooling circulation loop; The circulation pump and the flow control valve are connected to the controller.

[0009] In some embodiments, the cooling cycle assembly further includes a flow sensor, which is disposed on the liquid inlet pipe and connected to the controller.

[0010] In some embodiments, each of the slip rings includes a stator and a rotor that are rotatably connected, the rotor is connected to the drive shaft, and the interface is provided on the stator.

[0011] In some embodiments, the flow channel is spirally arranged in the drive shaft.

[0012] In some embodiments, the steps of constructing the preset neural network model are as follows: A BP neural network model was established; the four nodes in the input layer corresponded to the temperature, speed, torque, and ambient temperature of the drive shaft; the hidden layer was set to have N nodes, where N is a positive integer; and one node in the output layer was the coolant flow rate. With the drive shaft temperature reaching the preset range as the goal, the drive shaft temperature, speed, torque, ambient temperature, and actual coolant flow rate under different vehicle test conditions are obtained to form a test data set; The BP neural network model is trained, verified and tested using the test data set to obtain the preset neural network model.

[0013] In some embodiments, the method of using the test data set to train the BP neural network model to obtain a preset neural network model includes: Divide the test data set into training set, validation set, and test set; Use the training set to train the BP neural network model; Use the validation set to determine whether the BP neural network model in training is overfitting or underfitting; The test set is used to perform performance testing on the trained BP neural network model.

[0014] In some embodiments, the controller is further configured to: Obtain the temperature, speed, torque, ambient temperature of the drive shaft at intervals of preset mileage or preset days under different vehicle application conditions, as well as the coolant flow rate under the corresponding vehicle application conditions to form an application data set; The application data set is merged with the test data set, and the BP neural network model is trained, verified and tested using the merged data set to update the preset neural network model.

[0015] In some embodiments, the controller is further configured to perform noise reduction processing on the formed test data set and the formed application data set.

[0016] In a second aspect, a vehicle is provided, comprising the aforementioned drive shaft assembly.

[0017] The beneficial effects brought about by the technical solution provided by the present invention include: An embodiment of the present invention provides a drive shaft assembly and a vehicle. The drive shaft assembly comprises a drive shaft, a cooling circuit component, and a controller. A flow channel is provided within the drive shaft, and the cooling circuit component is connected to the flow channel to form a cooling circuit. In practical applications, the controller uses a preset neural network model to control the cooling circuit component in real time based on the current temperature, speed, torque, and ambient temperature of the drive shaft. This ensures that the coolant in the cooling circuit flows at a target flow rate, preventing the drive shaft from overheating. This effectively addresses the issue of accelerated drive shaft aging caused by insufficient heat dissipation, significantly extends the service life of the drive shaft and related components, and ensures the stability of the drive shaft's performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic structural diagram of a drive shaft assembly provided by an embodiment of the present invention; Figure 2 A schematic diagram of a process for constructing a preset neural network model provided by an embodiment of the present invention; Figure 3 The embodiment of the present invention provides Figure 2 Schematic diagram of the process of implementing step S30; Figure 4 The embodiment of the present invention provides Figure 1 Schematic diagram of the process of updating the preset neural network model; Reference numerals: 1. Drive shaft; 11. Flow channel; 2. Cooling circulation assembly; 21. Coolant tank; 22. Circulating pump; 23. Flow control valve; 24. Liquid inlet pipe; 25. Liquid outlet pipe; 26. Slip ring; 261. Stator; 2611. Interface; 262. Rotor; 27. Flow sensor; 3. Controller. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0021] An embodiment of the present invention provides a drive shaft assembly that can solve the technical problem that the drive shaft between the existing automobile motor and the wheel hub generates heat during actual use, and when the local temperature is too high, it accelerates the aging of the drive shaft and affects the performance and life of the drive shaft.

[0022] See also Figure 1 As shown, an embodiment of the present invention provides a drive shaft assembly, including: a drive shaft 1, a cooling cycle component 2 and a controller 3.

[0023] The drive shaft 1 is used to connect the motor shaft and the wheel hub of the automobile. A flow channel 11 is provided inside the drive shaft 1 .

[0024] The cooling circulation component 2 is connected to the flow channel 11 to form a cooling circulation loop.

[0025] The controller 3 is connected to the cooling cycle component 2 and is configured to: The current temperature, current speed, current torque, and current ambient temperature of the drive shaft 1 are obtained. Specifically, a temperature sensor can be provided on the drive shaft 1 to collect the current temperature of the drive shaft 1 and transmit it to the controller 3. The current speed and current torque of the drive shaft 1 can be collected by corresponding sensors and transmitted to the controller 3. Alternatively, the current speed and current torque of the drive shaft 1 can be obtained indirectly through the motor and reducer. The current ambient temperature can be collected by other temperature sensors and transmitted to the controller 3.

[0026] According to the current temperature, current speed, current torque and current ambient temperature of the drive shaft 1, a preset neural network model is used to calculate the target flow rate of the coolant in the cooling circulation loop, and the cooling circulation component 2 is controlled according to the target flow rate of the coolant.

[0027] For example, when the drive shaft 1 is operating in a high-heating condition, a preset neural network model will be used to calculate the high target flow rate requirement of the coolant in the corresponding cooling circulation loop. The controller 3 increases the coolant flow rate in the cooling circulation loop according to the high target flow rate, removes heat in time, and avoids the drive shaft 1 from overheating. This effectively solves the problem of accelerated aging of the drive shaft due to insufficient heat dissipation, significantly extends the service life of the drive shaft and related components, and ensures the performance stability of the drive shaft. Similarly, when the drive shaft 1 is operating in a low-heating condition, a preset neural network model will be used to calculate the low target flow rate requirement of the coolant in the corresponding cooling circulation loop. The controller 3 reduces the coolant flow rate in the cooling circulation loop according to the low target flow rate, effectively reducing the vehicle's energy consumption and improving the vehicle's overall energy efficiency.

[0028] In summary, the drive shaft assembly in the embodiment of the present invention includes a drive shaft, a cooling circulation component, and a controller. A flow channel is provided within the drive shaft, and the cooling circulation component is connected to the flow channel to form a cooling circulation loop. In actual application, the controller uses a preset neural network model to control the cooling circulation component in real time based on the current temperature, speed, torque, and ambient temperature of the drive shaft, ensuring that the coolant in the cooling circulation loop flows at a target flow rate, preventing the drive shaft from overheating. This effectively solves the problem of accelerated aging of the drive shaft due to insufficient heat dissipation, significantly extends the service life of the drive shaft and related components, and ensures the performance stability of the drive shaft.

[0029] As an optional implementation, in one embodiment of the invention, participating Figure 1 As shown, the cooling circulation assembly 2 includes a coolant tank 21 , a circulation pump 22 , a flow control valve 23 , a liquid inlet pipe 24 , a liquid outlet pipe 25 and two slip rings 26 .

[0030] The two slip rings 26 are provided at both ends of the driving shaft 1 , and each slip ring 26 is provided with an interface 2611 .

[0031] The coolant tank 21, the circulation pump 22, the flow control valve 23, the liquid inlet pipe 24, the liquid outlet pipe 25 are connected to the interfaces 2611 of the two slip rings 26 and then communicated with the flow channel 11 to form a cooling circulation loop.

[0032] The circulation pump 22 and the flow control valve 23 are connected to the controller 3 .

[0033] Specifically, the circulation pump 22 receives the control signal of the controller 3 to operate. When the controller 3 calculates the target flow rate of the coolant in the corresponding cooling circulation loop based on the current temperature, current speed, current torque and current ambient temperature of the drive shaft 1 using a preset neural network model, the controller 3 outputs a control signal to adjust the valve opening of the flow control valve 23 so that the coolant in the cooling circulation loop reaches the target flow rate. The system structure is simple and easy to control.

[0034] Furthermore, the cooling cycle component 2 also includes a flow sensor 27, which is arranged on the liquid inlet pipe 24 and connected to the controller 3. The flow sensor 27 can provide real-time feedback of the real-time flow of the coolant in the cooling cycle to the controller 3, thereby ensuring the control accuracy of the flow control valve 23 by the controller 3, and further ensuring that the coolant in the cooling cycle accurately reaches the target flow.

[0035] As an optional implementation, in one embodiment of the invention, participating Figure 1 As shown, each slip ring 26 includes a stator 261 and a rotor 262 that are rotatably connected. The rotor 262 is connected to the drive shaft 1, and the interface 2611 is provided on the stator 261. Coolant enters through the interface 2611 on the surface of one of the stators 261, enters the flow channel 11 inside the drive shaft 1 through the liquid inlet provided on the drive shaft 1, flows out through the liquid outlet of the drive shaft 1, and then flows out through the interface 2611 on the surface of the other stator 261, thereby completing the flow of coolant inside the drive shaft 1 and absorbing heat from the drive shaft 1. The two rotors 262 ensure that the rotation of the drive shaft 1 is not affected.

[0036] As an optional implementation, in one embodiment of the invention, participating Figure 1 As shown, the flow channel 11 is spirally arranged in the drive shaft 1. The spirally arranged flow channel 11 can increase the flow time of the coolant in the drive shaft 1 and improve the heat dissipation efficiency of the drive shaft 1.

[0037] As an optional implementation, in one embodiment of the invention, see Figure 2 As shown, the steps for constructing the preset neural network model are as follows: Step S10: Establish a BP neural network model. The input layer nodes correspond to the drive shaft temperature, speed, torque, and ambient temperature. The hidden layer consists of N nodes, where N is a positive integer. The output layer nodes represent the coolant flow rate. N can be set to 10 based on experience, and a sigmoid activation function is used to enhance the model's nonlinear fitting capabilities. The 10 nodes in the hidden layer do not directly correspond to specific physical quantities; rather, they serve as key units for feature learning and data processing. During model training, these nodes automatically extract the complex feature combinations and inherent relationships of the input data (drive shaft temperature, drive shaft speed, drive shaft torque, and ambient temperature), thereby establishing a nonlinear mapping between the input and output (coolant flow rate).

[0038] In step S20, with the temperature of the drive shaft reaching a preset range as the goal, the temperature, speed, torque, ambient temperature of the drive shaft under different vehicle test conditions and the actual flow rate of the coolant under the corresponding vehicle test conditions are obtained to form a test data set.

[0039] Specifically, the entire vehicle is tested under different vehicle test conditions. The goal is to achieve a drive shaft temperature within a predetermined range (generally between 60°C and 80°C). The coolant flow rate in the cooling loop is controlled, and data on the drive shaft's temperature, speed, torque, and ambient temperature under these conditions is collected, along with actual coolant flow rate data for the corresponding vehicle test conditions. Vehicle test conditions include acceleration, deceleration, constant speed driving, climbing, and driving on flat roads. Drive shaft temperature data is collected by installing temperature sensors on the drive shaft (covering stress concentration points and areas prone to heat accumulation). Simultaneously, flow sensors are used to collect actual coolant flow rate data for the corresponding vehicle test conditions.

[0040] Step S30: Use the test data set to train, verify and test the BP neural network model to obtain a preset neural network model.

[0041] Specifically, see Figure 3 As shown, the BP neural network model is trained using the test data set to obtain a preset neural network model, including: Step S301: Divide the test data set into a training set, a validation set, and a test set. Specifically, the test data set can be divided into a training set, a validation set, and a test set in a ratio of 70%, 15%, and 15%.

[0042] Step S302: Use the training set to train the BP neural network model. Specifically, the stochastic gradient descent method can be used to train the BP neural network model, and the initial learning rate can be set to 0.01.

[0043] Step S303: Use the validation set to determine whether the BP neural network model being trained is overfitting or underfitting. Specifically, if the validation set is used to determine whether the BP neural network model being trained is overfitting or underfitting during the training process, the learning rate of the BP neural network model is adjusted. For example, if the validation set loss does not decrease after five consecutive iterations, the learning rate is halved.

[0044] Step S304: Use the test set to perform a performance test on the trained BP neural network model. The target coolant flow rate calculated based on the BP neural network model is compared with the actual coolant flow rate recorded in the test set. The mean absolute error, root mean square error, and coefficient of determination are calculated. If the mean absolute error is greater than 0.2 L / min, the root mean square error is greater than 0.3 L / min, or the coefficient of determination is less than 0.9, the BP neural network model is adjusted and retrained.

[0045] As an optional implementation, in one embodiment of the invention, see Figure 4 As shown, the controller is also used for: Step S40 : Acquire the drive shaft temperature, speed, torque, ambient temperature, and coolant flow rate at preset mileage intervals or preset days under different vehicle application conditions to form an application dataset. The preset mileage interval can be set to 1000 kilometers, and the preset days interval can be set to 30 days.

[0046] Step S50: Merge the application data set and the test data set, and use the merged data set to train, verify and test the BP neural network model again, thereby updating the preset neural network model.

[0047] By retraining, verifying and testing the model and updating the preset neural network model, it can be ensured that the neural network model adapts to factors such as aging of vehicle components and environmental changes, ensuring the real-time reliability of control accuracy.

[0048] As an optional implementation manner, in one embodiment of the invention, the controller is further configured to: perform noise reduction processing on the formed test data set and the formed application data set.

[0049] Noise reduction can remove outliers and ensure data accuracy. In addition, Z-score standardization can be used to standardize data such as temperature and flow to make different parameters comparable.

[0050] An embodiment of the present invention further provides an automobile, comprising the aforementioned drive shaft assembly.

[0051] In an embodiment of the present invention, the drive shaft assembly of an automobile comprises a drive shaft, a cooling circuit component, and a controller. A flow channel is provided within the drive shaft, connecting the cooling circuit component to the flow channel to form a cooling circuit. In practical applications, the controller uses a preset neural network model to control the cooling circuit component in real time based on the current drive shaft temperature, speed, torque, and ambient temperature, ensuring that the coolant in the cooling circuit flows at a target flow rate, preventing the drive shaft from overheating. This effectively addresses the issue of accelerated drive shaft aging caused by insufficient heat dissipation, significantly extending the service life of the drive shaft and related components, and ensuring the stability of the drive shaft's performance.

[0052] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper" and "lower" is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be internal communication between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0053] It should be noted that, in the present invention, relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0054] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features of the present invention.

Claims

1. A drive shaft assembly, characterized in that: include: A drive shaft (1) for connecting the motor shaft and the wheel hub, wherein a flow channel (11) is provided inside the drive shaft (1); A cooling circulation component (2) is connected to the flow channel (11) to form a cooling circulation loop; The controller (3), which is connected to the cooling cycle component (2), is configured to: Obtaining the current temperature, current speed, current torque and current ambient temperature of the drive shaft (1); According to the current temperature, current rotational speed, current torque and current ambient temperature of the drive shaft (1), a preset neural network model is used to calculate the target flow rate of the coolant in the cooling circulation loop, and the cooling circulation component (2) is controlled according to the target flow rate of the coolant.

2. The drive shaft assembly according to claim 1, characterized in that: The cooling circulation assembly (2) includes a coolant tank (21), a circulation pump (22), a flow control valve (23), a liquid inlet pipe (24), a liquid outlet pipe (25) and two slip rings (26); The two slip rings (26) are provided at both ends of the drive shaft (1), and each slip ring (26) is provided with an interface (2611); The coolant tank (21), the circulation pump (22), the flow control valve (23), the liquid inlet pipe (24), the liquid outlet pipe (25) are connected to the interfaces (2611) of the two slip rings (26) and then connected to the flow channel (11) to form a cooling circulation loop; The circulation pump (22) and the flow control valve (23) are connected to the controller (3).

3. The drive shaft assembly according to claim 2, characterized in that: The cooling circulation component (2) further includes a flow sensor (27), which is arranged on the liquid inlet pipe (24) and connected to the controller (3).

4. The drive shaft assembly according to claim 2, characterized in that: Each slip ring (26) includes a stator (261) and a rotor (262) that are rotatably connected, the rotor (262) is connected to the drive shaft (1), and the interface (2611) is provided on the stator (261).

5. The drive shaft assembly according to claim 1, characterized in that: The flow channel (11) is spirally shaped inside the drive shaft (1).

6. The drive shaft assembly according to claim 1, characterized in that: The steps for constructing the preset neural network model are as follows: A BP neural network model was established; the four nodes in the input layer corresponded to the temperature, speed, torque, and ambient temperature of the drive shaft; the hidden layer was set to have N nodes, where N is a positive integer; and one node in the output layer was the coolant flow rate. With the drive shaft temperature reaching the preset range as the goal, the drive shaft temperature, speed, torque, ambient temperature, and actual coolant flow rate under different vehicle test conditions are obtained to form a test data set; The BP neural network model is trained, verified and tested using the test data set to obtain the preset neural network model.

7. The drive shaft assembly according to claim 6, characterized in that: The method of using the test data set to train the BP neural network model to obtain a preset neural network model includes: Divide the test data set into training set, validation set, and test set; Use the training set to train the BP neural network model; Use the validation set to determine whether the BP neural network model in training is overfitting or underfitting; The test set is used to perform performance testing on the trained BP neural network model.

8. The drive shaft assembly according to claim 6, characterized in that: The controller is also used to: Obtain the temperature, speed, torque, ambient temperature of the drive shaft at intervals of preset mileage or preset days under different vehicle application conditions, as well as the coolant flow rate under the corresponding vehicle application conditions, to form an application data set; The application data set is merged with the test data set, and the BP neural network model is trained, verified and tested using the merged data set to update the preset neural network model.

9. The drive shaft assembly according to claim 8, characterized in that: The controller is further configured to perform noise reduction processing on the formed test data set and the formed application data set.

10. An automobile, characterized in that: Comprising the drive shaft assembly according to any one of claims 1-9.

Images