A rigid body modeling analysis system based on agricultural drive shaft processing

Abstract

The application relates to the technical field of rigid body modeling analysis, and discloses a rigid body modeling analysis system based on agricultural transmission shaft processing, which comprises the following steps: dividing a transmission shaft into M subsegments along a central axis based on segmentation constraints, and obtaining structure data of each subsegment, including an outer diameter, an inner diameter, a length and a material density; taking a central origin of the central axis of the transmission shaft as an X axis, taking two transverse directions perpendicular to the central axis as Y and Z axes, and taking the central axis as a coordinate system; combining and processing X-axis rotational inertia, Y-axis rotational inertia and Z-axis rotational inertia to form a rotational inertia tensor of the transmission shaft; inputting the rotational inertia tensor, an external load torque sequence and a load torque sequence of the transmission shaft under a target working condition into a pre-trained dynamics neural network model to obtain a predicted angular velocity sequence and a predicted rotation angle sequence; and performing check processing on the maximum shear stress of the transmission shaft based on the predicted angular velocity sequence and the predicted rotation angle sequence.

Description

Technical Field

[0001] This invention relates to the field of rigid body modeling and analysis technology, and more specifically, to a rigid body modeling and analysis system based on the machining of agricultural drive shafts. Background Technology

[0002] The core of the rigid body modeling and analysis system based on transmission shaft machining lies in the numerical integration method such as the Longkuta method (RK4) to iteratively solve the dynamic response of angular velocity and rotation angle step by step.

[0003] However, existing technologies have the following problems:

[0004] 1. The traditional Runkuta method requires iterative calculations for each time step, and the computational load increases linearly with the number of time steps, resulting in long offline modeling time and difficulty in quickly responding to parameter adjustments.

[0005] 2. In online monitoring or real-time control scenarios, stepwise integration cannot meet the requirements of high-frequency dynamic response output, limiting the rapid assessment of the real-time operating status of the drive shaft.

[0006] 3. When the moment of inertia changes, the entire process integration calculation needs to be re-performed, which lacks efficient generalization ability for dynamic parameters, and is particularly inefficient in large-scale batch analysis or multi-condition simulation. Summary of the Invention

[0007] This invention provides a rigid body modeling and analysis system based on the machining of agricultural drive shafts, which solves the technical problems mentioned in the background art.

[0008] This invention provides a rigid body modeling and analysis system based on the machining of agricultural drive shafts, comprising:

[0009] The data acquisition module is used to divide the drive shaft into M sub-segments along the central axis based on the segmentation constraint, and to acquire the structural data of each sub-segment, including: outer diameter, inner diameter, length and material density;

[0010] The segmentation constraints include: the outer diameter, inner diameter, and material density of each segment are equal everywhere;

[0011] The first processing module is used to construct a coordinate system based on the center origin of the central axis of the drive shaft, with the central axis as the X-axis and the two lateral directions perpendicular to the central axis as the Y-axis and Z-axis;

[0012] The second processing module is used to calculate the volume, mass, and centroid of the m-th sub-segment based on the structural data of each sub-segment, where 1 ≤ m ≤ M and m is a positive integer;

[0013] Based on the mass and centroid of the M sub-segments, the mass and centroid of the drive shaft are determined sequentially.

[0014] Based on the structural data, mass, and center of mass of the M sub-segments, as well as the center of mass of the transmission shaft, determine the rotational inertia of the X-axis, Y-axis, and Z-axis respectively.

[0015] The rotational inertia of the X-axis, Y-axis, and Z-axis are combined and processed to form the rotational inertia tensor of the transmission shaft.

[0016] The third processing module is used to input the moment of inertia tensor, as well as the external load torque sequence and load torque sequence of the drive shaft under the target working condition, into the pre-trained dynamic neural network model to obtain the predicted angular velocity sequence and the predicted rotation angle sequence.

[0017] The modeling and analysis module is used to verify the maximum shear stress of the drive shaft based on the predicted angular velocity sequence and the predicted rotation angle sequence.

[0018] Furthermore, based on the structural data of each segment, the volume, mass, and centroid of the m-th segment are calculated, including:

[0019] Determine the volume of the m-th sub-segment for: ,in, This represents the outer diameter of the m-th sub-segment. This represents the inner diameter of the m-th sub-segment. This represents the length of the m-th sub-segment;

[0020] Determine the quality of the m-th sub-segment for: , This represents the material density of the m-th sub-segment;

[0021] Determine the centroid of the m-th sub-segment for: , This represents the coordinates of the starting point of the m-th sub-segment on the X-axis.

[0022] Furthermore, based on the mass and center of mass of the M sub-segments, the mass and center of mass of the drive shaft are determined sequentially, including:

[0023] The sum of the masses of the M sub-segments is taken as the mass of the drive shaft;

[0024] Based on the centroids of M sub-segments, the centroid of the drive shaft is determined by a mass-weighted average, as follows:

[0025] ;

[0026] in, Indicates the center of mass of the drive shaft. This indicates the mass of the drive shaft.

[0027] Furthermore, based on the structural data, mass, and center of mass of the M sub-segments, as well as the center of mass of the transmission shaft, the moments of inertia of rotation along the X-axis, Y-axis, and Z-axis are determined, including:

[0028] Determine the moment of inertia of the X-axis for: ;

[0029] Determine the moment of inertia along the Y-axis for: ;

[0030] Determine the moment of inertia along the Z-axis and Y-axis moment of inertia equal.

[0031] Furthermore, the rotational inertia of the X-axis, Y-axis, and Z-axis are combined and processed to form the rotational inertia tensor of the transmission shaft, including:

[0032] Initialize the rotational inertia tensor ,in, , and , , and Both represent the product of moment of inertia;

[0033] If the drive shaft is a symmetrical rigid body about the X-axis, then the product of inertia is 0.

[0034] The final moment of inertia tensor .

[0035] Furthermore, the pre-trained dynamic neural network model includes:

[0036] The following is a labeled dataset for a dynamic neural network model:

[0037] Determine the external loading torque and load torque under typical operating conditions, and combine them with the moment of inertia tensor. The angular velocity and rotation angle are obtained using the fourth-order Runge-Kutta method.

[0038] The external applied torque, load torque, and moment of inertia tensor The sample data is spliced ​​together to form the labeled dataset;

[0039] The angular velocity and rotation angle obtained by the fourth-order Runge-Kutta method are used as sample labels for the labeled dataset;

[0040] A dynamic neural network model is obtained by pre-training based on a labeled dataset.

[0041] Furthermore, the hidden layers of the dynamic neural network model include:

[0042] The hidden layers of the dynamic neural network model are constructed based on the PINN neural network;

[0043] The physical constraints of the PINN neural network are constructed based on rotation equations, as follows:

[0044] ;

[0045] in, This represents the first derivative of the angular velocity obtained by the fourth-order Runge-Kutta method. This represents the externally applied torque obtained by the fourth-order Runge-Kutta method. This represents the angle obtained by the fourth-order Rungekuta method.

[0046] Furthermore, the loss function for the dynamic neural network model is as follows:

[0047] ;

[0048] in, This represents the loss function value of the dynamic neural network model. This represents the predicted value from the dynamic neural network model. This represents the sample label corresponding to the predicted value. and These represent the first loss weight and the second loss weight, respectively. This represents the square of the L2 norm.

[0049] Furthermore, based on the predicted angular velocity sequence and predicted rotation angle sequence, the maximum shear stress of the drive shaft is verified, including:

[0050] The maximum value of the externally loaded torque under typical working conditions is obtained as the characteristic torque;

[0051] Based on the structural parameters of the drive shaft, determine the polar moment of inertia of the drive shaft. , ,in, This represents the average outer diameter of the M sub-segments. This represents the average inner diameter of the M sub-segments;

[0052] The maximum shear stress is calculated based on the characteristic torque, polar moment of inertia, and average outer diameter, including:

[0053] ;

[0054] in, This indicates the maximum shear stress of the drive shaft. Indicates characteristic torque;

[0055] If the maximum shear stress is greater than or equal to the allowable shear stress of the drive shaft, the verification fails; otherwise, the verification passes.

[0056] The beneficial effects of this invention are as follows: by segmenting the drive shaft into segments and calculating the physical parameters of each segment, constructing the moment of inertia tensor, and combining it with a PINN neural network embedded with physical constraints of the rotation equation, efficient prediction of angular velocity and rotation sequence is achieved, significantly shortening offline modeling time and meeting the requirements of online real-time dynamic response. At the same time, the maximum shear stress verification ensures the strength safety of the drive shaft, significantly improving the generalization ability to different working conditions and structural parameters, and providing a rigid body modeling and analysis scheme with both high precision and high real-time performance for the processing of agricultural drive shafts. Attached Figure Description

[0057] Figure 1 This is a module diagram of a rigid body modeling and analysis system based on the machining of agricultural drive shafts according to the present invention. Detailed Implementation

[0058] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and implement the subject matter described herein, and changes may be made to the function and arrangement of the elements discussed without departing from the scope of this specification. Various processes or components may be omitted, substituted, or added as needed in the examples. Furthermore, features described in some examples may be combined in other examples.

[0059] like Figure 1 As shown, a rigid body modeling and analysis system based on the machining of agricultural drive shafts includes:

[0060] The data acquisition module is used to divide the drive shaft into M sub-segments along the central axis based on the segmentation constraint, and to acquire the structural data of each sub-segment, including: outer diameter, inner diameter, length and material density;

[0061] The segmentation constraints include: the outer diameter, inner diameter, and material density of each segment are equal everywhere;

[0062] The first processing module is used to construct a coordinate system based on the center origin of the central axis of the drive shaft, with the central axis as the X-axis and the two lateral directions perpendicular to the central axis as the Y-axis and Z-axis;

[0063] The second processing module is used to calculate the volume, mass, and centroid of the m-th sub-segment based on the structural data of each sub-segment, where 1 ≤ m ≤ M and m is a positive integer;

[0064] Based on the mass and centroid of the M sub-segments, the mass and centroid of the drive shaft are determined sequentially.

[0065] Based on the structural data, mass, and center of mass of the M sub-segments, as well as the center of mass of the transmission shaft, determine the rotational inertia of the X-axis, Y-axis, and Z-axis respectively.

[0066] The rotational inertia of the X-axis, Y-axis, and Z-axis are combined and processed to form the rotational inertia tensor of the transmission shaft.

[0067] The third processing module is used to input the moment of inertia tensor, as well as the external load torque sequence and load torque sequence of the drive shaft under the target working condition, into the pre-trained dynamic neural network model to obtain the predicted angular velocity sequence and the predicted rotation angle sequence.

[0068] The modeling and analysis module is used to verify the maximum shear stress of the drive shaft based on the predicted angular velocity sequence and the predicted rotation angle sequence.

[0069] In one embodiment of the present invention, based on the structural data of each sub-segment, the volume, mass, and centroid of the m-th sub-segment are calculated, including:

[0070] Determine the volume of the m-th sub-segment for: ,in, This represents the outer diameter of the m-th sub-segment. This represents the inner diameter of the m-th sub-segment. This represents the length of the m-th sub-segment;

[0071] Determine the quality of the m-th sub-segment for: , This represents the material density of the m-th sub-segment;

[0072] Determine the centroid of the m-th sub-segment for: , This represents the coordinates of the starting point of the m-th sub-segment on the X-axis.

[0073] It should be noted that by calculating the volume, mass, and center of mass in segments, the complex driveshaft is decomposed into uniform sub-segments. This simplifies calculations while ensuring the accuracy of parameters for each sub-segment, laying the foundation for subsequent analysis of moment of inertia, total center of mass, and dynamics, and improving the overall modeling accuracy. Precise mass and center of mass data make calculations of moment of inertia and total mass more reliable, thereby ensuring the accuracy of driveshaft dynamic behavior analysis (such as angular velocity and torque response). Ultimately, this improves the efficiency and reliability of dynamic performance evaluation of the driveshaft, ensuring its stability and safety in practical applications.

[0074] In one embodiment of the present invention, the mass and centroid of the transmission shaft are determined sequentially based on the mass and centroid of the M sub-segments, including:

[0075] The sum of the masses of the M sub-segments is taken as the mass of the drive shaft;

[0076] Based on the centroids of M sub-segments, the centroid of the drive shaft is determined by a mass-weighted average, as follows:

[0077] ;

[0078] in, Indicates the center of mass of the drive shaft. This indicates the mass of the drive shaft.

[0079] It should be noted that the center of mass reflects the central location of the mass distribution of an object. The center of mass and mass of each segment together determine its contribution to the overall center of mass of the drive shaft. By using a mass-weighted average, the segments with larger masses have a greater impact on the position of the overall center of mass, which conforms to the laws of physics and can accurately locate the center of the mass distribution of the drive shaft.

[0080] Total mass is a fundamental parameter describing the inertial characteristics of a drive shaft and is widely used in dynamic equations (such as the application of Newton's second law in rotational or translational motion). Accurate total mass ensures that subsequent analysis conforms to physical reality and avoids analytical deviations caused by incorrect mass parameters.

[0081] The total center of mass determined by the mass-weighted average method accurately reflects the influence of the mass distribution of each segment on the overall center of mass. When calculating the moment of inertia, the position of the center of mass is crucial for applying the parallel axis theorem; in analyzing the motion of a transmission shaft (such as vibration and rotation), an accurate center of mass can more realistically describe its dynamic behavior, improving the accuracy and reliability of dynamic analyses (such as angular velocity and torque response).

[0082] In one embodiment of the present invention, the X-axis moment of inertia, Y-axis moment of inertia, and Z-axis moment of inertia are determined based on the structural data, mass, and center of mass of the M sub-segments, and the center of mass of the transmission shaft, including:

[0083] Determine the moment of inertia of the X-axis for: ;

[0084] Determine the moment of inertia along the Y-axis for: ;

[0085] Determine the moment of inertia along the Z-axis and Y-axis moment of inertia equal.

[0086] It should be noted that moment of inertia is the core parameter describing the rotational inertia of an object. It is indispensable in dynamic analysis (such as torque, angular velocity relationship, vibration characteristics). Calculating the moment of inertia of three axes can comprehensively characterize the rotational characteristics of the drive shaft.

[0087] By segmented calculation and accumulation, the contribution of each segment to the overall rotational inertia of the drive shaft is accurately reflected, so that the rotational inertia of the X, Y, and Z axes are precisely matched with the actual structure and mass distribution.

[0088] Moment of inertia helps in the in-depth analysis of the dynamic response of the drive shaft under different operating conditions (such as angular velocity changes and rotational stability under torque), optimize the drive shaft design (such as reducing weight and increasing strength), and avoid design defects caused by deviations in rotational characteristic analysis.

[0089] In one embodiment of the present invention, the rotational inertia of the X-axis, Y-axis, and Z-axis is combined and processed to form the rotational inertia tensor of the transmission shaft, including:

[0090] Initialize the rotational inertia tensor ,in, , and , , and Both represent the product of moment of inertia;

[0091] If the drive shaft is a symmetrical rigid body about the X-axis, then the product of inertia is 0.

[0092] The final moment of inertia tensor .

[0093] It should be noted that the moment of inertia tensor is the core tool for describing the rotational inertia of a rigid body, and can comprehensively reflect the rotational characteristics of a rigid body in different axial directions. The initialization of the moment of inertia tensor adopts a standard form, which includes the moment of inertia and the product of inertia, and is a universal expression of the rotational inertia of a rigid body.

[0094] As a rigid body symmetrical about the X-axis, the drive shaft's mass distribution is symmetrical about the X-axis, and its inertia product (reflecting the coupling effect of the mass distribution on different axes) must be zero. By simplifying the tensor, the physical properties of the drive shaft can be matched more accurately, avoiding redundant calculations.

[0095] By eliminating the inertia product, the physical characteristics of the drive shaft being symmetrical about the X-axis are accurately reflected, avoiding model errors caused by retaining redundant inertia products, improving the accuracy of dynamic analysis (such as angular velocity and torque response), and making the results more consistent with actual working conditions.

[0096] In one embodiment of the present invention, the pre-trained dynamic neural network model includes:

[0097] The following is a labeled dataset for a dynamic neural network model:

[0098] Determine the external loading torque and load torque under typical operating conditions, and combine them with the moment of inertia tensor. The angular velocity and rotation angle are obtained using the fourth-order Runge-Kutta method.

[0099] The external applied torque, load torque, and moment of inertia tensor The sample data is spliced ​​together to form the labeled dataset;

[0100] The angular velocity and rotation angle obtained by the fourth-order Runge-Kutta method are used as sample labels for the labeled dataset;

[0101] A dynamic neural network model is obtained by pre-training based on a labeled dataset.

[0102] It should be noted that the fourth-order Runge-Kutta method is a high-precision numerical method for solving dynamic differential equations. Using this method, combined with the external loading torque T, load torque, and moment of inertia tensor under typical working conditions, angular velocity and rotation angle can be accurately calculated, providing sample labels for labeled datasets.

[0103] By concatenating the external load torque, load torque, and moment of inertia tensor into sample data, and labeling the corresponding angular velocity and rotation angle samples, the input-output relationship of the neural network model is clarified, enabling the model to learn the mapping law between these physical quantities, thereby having the ability to predict the dynamic response of the drive shaft.

[0104] The pre-trained dynamic neural network model can directly and quickly predict angular velocity and rotation angle based on the input torque and moment of inertia tensor, avoiding the high time consumption problem of iterative calculation by time step using the fourth-order Runge-Kutta method, and greatly improving the efficiency of dynamic analysis.

[0105] Neural networks possess powerful nonlinear fitting capabilities, enabling them to capture complex nonlinear relationships between externally applied torque, load torque, moment of inertia, angular velocity, and rotation angle. Compared to traditional analytical or numerical methods, they are more flexible and can adapt to diverse working conditions and changes in drive shaft structure.

[0106] In one embodiment of the present invention, the hidden layer of the dynamic neural network model includes:

[0107] The hidden layers of the dynamic neural network model are constructed based on the PINN neural network;

[0108] The physical constraints of the PINN neural network are constructed based on rotation equations, as follows:

[0109] ;

[0110] in, This represents the first derivative of the angular velocity obtained by the fourth-order Runge-Kutta method. This represents the externally applied torque obtained by the fourth-order Runge-Kutta method. This represents the angle obtained by the fourth-order Rungekuta method.

[0111] The rotation equation is the core physical law describing the dynamic behavior of a drive shaft. By constructing a hidden layer based on PINN (Physical Information Neural Network) and embedding this equation as a physical constraint, the model's prediction results can be forced to conform to physical laws, avoiding the physical irrationality that may occur when traditional neural networks rely solely on data fitting (such as incorrect predictions due to data noise or insufficient data).

[0112] By simultaneously fitting data (such as angular velocity and torque generated by the fourth-order Runge-Kutta method) and satisfying physical constraints (rotation equations), the model can more accurately capture the dynamic characteristics of the drive shaft, reduce prediction errors, and make the predicted results such as angular velocity and torque response closer to the actual physical behavior.

[0113] In one embodiment of the present invention, the loss function of the dynamic neural network model is as follows:

[0114] ;

[0115] in, This represents the loss function value of the dynamic neural network model. This represents the predicted value from the dynamic neural network model. This represents the sample label corresponding to the predicted value. and These represent the first loss weight and the second loss weight, respectively. This represents the square of the L2 norm.

[0116] It should be noted that the data fitting term By minimizing the model's predicted values With sample labels The differences (such as the angular velocity and rotation angle calculated by the fourth-order Runge-Kutta method) enable the model to learn the mapping relationship between external load torque, load torque, rotational inertia tensor and dynamic response (angular velocity and rotation angle), and use the information from labeled data to drive model training.

[0117] Physical constraints Based on the rotation equation, the model's predictions are forced to conform to physical laws. Even when the data is incomplete or noisy, physical constraints can guide the model to output results that conform to the principles of dynamics, avoiding physical inconsistencies caused by purely data-driven approaches.

[0118] In one embodiment of the present invention, the maximum shear stress of the drive shaft is verified based on the predicted angular velocity sequence and the predicted rotation angle sequence, including:

[0119] The maximum value of the externally loaded torque under typical working conditions is obtained as the characteristic torque;

[0120] Based on the structural parameters of the drive shaft, determine the polar moment of inertia of the drive shaft. , ,in, This represents the average outer diameter of the M sub-segments. This represents the average inner diameter of the M sub-segments;

[0121] The maximum shear stress is calculated based on the characteristic torque, polar moment of inertia, and average outer diameter, including:

[0122] ;

[0123] in, This indicates the maximum shear stress of the drive shaft. Indicates characteristic torque;

[0124] If the maximum shear stress is greater than or equal to the allowable shear stress of the drive shaft, the verification fails; otherwise, the verification passes.

[0125] It should be noted that the maximum value of the externally applied torque under typical working conditions represents the most severe torsional load that the drive shaft bears during operation. Using this as a characteristic torque, the strength of the drive shaft under extreme conditions can be specifically verified to ensure its safety in actual use.

[0126] Polar moment of inertia is a key parameter describing the ability of a drive shaft cross section to resist torsion. It is calculated based on the average outer diameter and average inner diameter and reflects the mechanical characteristics of the overall structure of the drive shaft torsion.

[0127] According to the torsional shear stress formula in mechanics of materials, the maximum shear stress occurs on the outer surface of the shaft. This formula quantitatively assesses the maximum shear stress of the drive shaft under the ultimate torque using characteristic torque, polar moment of inertia, and average outer diameter, which conforms to the principles of physics and mechanics. The allowable shear stress is the upper limit of stress for safe operation of a material. By comparing the allowable shear stress with the maximum shear stress, it is possible to directly determine whether the drive shaft will experience strength failure under extreme operating conditions, ensuring its operational reliability.

[0128] The embodiments of this example have been described above. However, this example is not limited to the specific implementation methods described above. The specific implementation methods described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms based on the guidance of this example, and all of them are within the protection scope of this example.

Claims

1. A rigid body modeling and analysis system based on the machining of agricultural drive shafts, characterized in that, include: The data acquisition module is used to divide the drive shaft into M sub-segments along the central axis based on the segmentation constraint, and to acquire the structural data of each sub-segment, including: outer diameter, inner diameter, length and material density; The segmentation constraints include: the outer diameter, inner diameter, and material density of each segment are equal everywhere; The first processing module is used to construct a coordinate system based on the center origin of the central axis of the drive shaft, with the central axis as the X-axis and the two lateral directions perpendicular to the central axis as the Y-axis and Z-axis; The second processing module is used to calculate the volume, mass, and centroid of the m-th sub-segment based on the structural data of each sub-segment, where 1 ≤ m ≤ M and m is a positive integer; Based on the mass and centroid of the M sub-segments, the mass and centroid of the drive shaft are determined sequentially. Based on the structural data, mass, and center of mass of the M sub-segments, as well as the center of mass of the transmission shaft, determine the rotational inertia of the X-axis, Y-axis, and Z-axis respectively. The rotational inertia of the X-axis, Y-axis, and Z-axis are combined and processed to form the rotational inertia tensor of the transmission shaft. The third processing module is used to input the moment of inertia tensor, as well as the external load torque sequence and load torque sequence of the drive shaft under the target working condition, into the pre-trained dynamic neural network model to obtain the predicted angular velocity sequence and the predicted rotation angle sequence. The modeling and analysis module is used to verify the maximum shear stress of the drive shaft based on the predicted angular velocity sequence and the predicted rotation angle sequence.

2. The rigid body modeling and analysis system based on the machining of agricultural drive shafts according to claim 1, characterized in that, Based on the structural data of each sub-segment, calculate the volume, mass, and centroid of the m-th sub-segment, including: Determine the volume of the m-th sub-segment for: ,in, This represents the outer diameter of the m-th sub-segment. This represents the inner diameter of the m-th sub-segment. This represents the length of the m-th sub-segment; Determine the quality of the m-th sub-segment for: , This represents the material density of the m-th sub-segment; Determine the centroid of the m-th sub-segment for: , This represents the coordinates of the starting point of the m-th sub-segment on the X-axis.

3. The rigid body modeling and analysis system based on the machining of agricultural drive shafts according to claim 2, characterized in that, Based on the mass and center of mass of the M sub-segments, determine the mass and center of mass of the drive shaft sequentially, including: The sum of the masses of the M sub-segments is taken as the mass of the drive shaft; Based on the centroids of M sub-segments, the centroid of the drive shaft is determined by a mass-weighted average, as follows: ； in, Indicates the center of mass of the drive shaft. This indicates the mass of the drive shaft.

4. The rigid body modeling and analysis system based on the machining of agricultural drive shafts according to claim 3, characterized in that, Based on the structural data, mass, and center of mass of the M sub-segments, as well as the center of mass of the transmission shaft, determine the rotational inertia of the X-axis, Y-axis, and Z-axis, including: Determine the moment of inertia of the X-axis for: ; Determine the moment of inertia along the Y-axis for: ; Determine the moment of inertia along the Z-axis and Y-axis moment of inertia equal.

5. The rigid body modeling and analysis system based on the machining of agricultural drive shafts according to claim 4, characterized in that, The rotational inertia of the X-axis, Y-axis, and Z-axis are combined and processed to form the rotational inertia tensor of the transmission shaft, including: Initialize the rotational inertia tensor ,in, , and , , and Both represent the product of moment of inertia; If the drive shaft is a symmetrical rigid body about the X-axis, then the product of inertia is 0. The final moment of inertia tensor .

6. The rigid body modeling and analysis system based on the machining of agricultural drive shafts according to claim 4, characterized in that, The pre-trained dynamic neural network model includes: The following is a labeled dataset for a dynamic neural network model: Determine the external loading torque and load torque under typical operating conditions, and combine them with the moment of inertia tensor. The angular velocity and rotation angle are obtained using the fourth-order Runge-Kutta method. The external applied torque, load torque, and moment of inertia tensor The sample data is spliced ​​together to form the labeled dataset; The angular velocity and rotation angle obtained by the fourth-order Runge-Kutta method are used as sample labels for the labeled dataset; A dynamic neural network model is obtained by pre-training based on a labeled dataset.

7. The rigid body modeling and analysis system based on the machining of agricultural drive shafts according to claim 5, characterized in that, The hidden layers of a dynamic neural network model include: The hidden layers of the dynamic neural network model are constructed based on the PINN neural network; The physical constraints of the PINN neural network are constructed based on rotation equations, as follows: ； in, This represents the first derivative of the angular velocity obtained by the fourth-order Runge-Kutta method. This represents the externally applied torque obtained by the fourth-order Runge-Kutta method. This represents the angle obtained by the fourth-order Rungekuta method.

8. The rigid body modeling and analysis system based on the machining of agricultural drive shafts according to claim 6, characterized in that, The loss function for the dynamic neural network model is as follows: ； in, This represents the loss function value of the dynamic neural network model. This represents the predicted value from the dynamic neural network model. This represents the sample label corresponding to the predicted value. and These represent the first loss weight and the second loss weight, respectively. This represents the square of the L2 norm.

9. A rigid body modeling and analysis system based on the machining of agricultural drive shafts according to claim 7, characterized in that, The maximum shear stress of the drive shaft is verified based on the predicted angular velocity sequence and the predicted rotation angle sequence, including: The maximum value of the externally loaded torque under typical working conditions is obtained as the characteristic torque; Based on the structural parameters of the drive shaft, determine the polar moment of inertia of the drive shaft. , ,in, This represents the average outer diameter of the M sub-segments. This represents the average inner diameter of the M sub-segments; The maximum shear stress is calculated based on the characteristic torque, polar moment of inertia, and average outer diameter, including: ； in, This indicates the maximum shear stress of the drive shaft. Indicates characteristic torque; If the maximum shear stress is greater than or equal to the allowable shear stress of the drive shaft, the verification fails; otherwise, the verification passes.

Images