Methods, apparatus, and systems for determining bearing parameters

Abstract

This application provides a method, apparatus, and system for determining the parameters of a bearing bush. The method includes obtaining design parameters for the bearing bush, wherein the design parameters include at least one or more of the following: radius of curvature, oil film thickness of lubricating oil, oil film pressure, and viscosity of lubricating oil; obtaining the wear amount of the bearing bush, wherein the wear amount is the material loss of the bearing bush due to friction; and using a target optimization algorithm to optimize and adjust the design parameters until the wear amount reaches a minimum value, obtaining updated design parameters, wherein the updated design parameters are used to construct the bearing bush. This method solves the problem of poor wear resistance in existing bearing bushes.

Description

Technical Field

[0001] This application relates to the field of bearing engineering, and more specifically, to a method, device, and system for determining the parameters of a bearing bush. Background Technology

[0002] As a key component of internal combustion engines and other rotating machinery, bearing bushes play a crucial role in supporting and guiding the rotating shaft, while also reducing friction and wear between the shaft and bearing through the formation of an oil film. Traditional bearing bush profile designs largely rely on engineers' experience. While these methods could meet past technical requirements to some extent, they prove inadequate when facing the challenges of modern high-power-density internal combustion engines.

[0003] With the development of internal combustion engine technology, especially in pursuit of higher efficiency and lower emissions, engines are becoming increasingly more powerful. This results in bearings experiencing more severe loads and wear during operation, placing unprecedented demands on their wear resistance and reliability. Currently, the profile design of bearings is severely inadequate in terms of wear resistance, especially under the extreme operating conditions of modern high-performance diesel engines, which seriously affects the reliability of bearing operation. Summary of the Invention

[0004] The main objective of this application is to provide a method, device, and system for determining the parameters of bearing bushes, so as to at least solve the problem of poor wear resistance of bearing bushes in the prior art.

[0005] To achieve the above objectives, according to one aspect of this application, a method for determining the parameters of a bearing bush is provided, comprising: obtaining design parameters of the bearing bush, wherein the design parameters include at least one or more of the following: radius of curvature, oil film thickness of lubricating oil, oil film pressure, and viscosity of the lubricating oil; obtaining the wear amount of the bearing bush, wherein the wear amount is the amount of material loss of the bearing bush due to friction; and performing optimization using a target optimization algorithm to adjust the design parameters until the wear amount reaches a minimum value, thereby obtaining updated design parameters, wherein the updated design parameters are used to construct the bearing bush.

[0006] Optionally, the wear amount of the bearing bush is determined by: obtaining a wear coefficient, contact pressure, and relative velocity, wherein the wear coefficient is a predefined coefficient of the bearing bush material's resistance to wear, the contact pressure is the pressure value at the contact position between the bearing bush and the journal, and the relative velocity is the relative velocity between the bearing bush and the journal; calculating the product of the wear coefficient and the contact pressure to obtain a first value; calculating the derivative of the relative velocity to obtain a second value; and calculating the product of the first value and the second value to obtain the wear amount.

[0007] Optionally, obtaining the contact pressure includes: obtaining a prediction model, wherein the prediction model is a model for numerical prediction; forming a first training set by combining historical design parameters and corresponding pressure labels, training the prediction model using the first training set to obtain a pressure prediction model, wherein the pressure labels are historical pressure values ​​of the historical contact positions of the bearing bush and the journal in the first training set; and inputting the design parameters into the pressure prediction model to obtain the contact pressure corresponding to the design parameters.

[0008] Optionally, obtaining relative speed includes: obtaining speed-related information, wherein the speed-related information includes one or more of the journal rotation speed, the bearing length, the bearing width, and the shaft eccentricity; combining the design parameters and the speed-related information to obtain a speed dataset; forming a second training set by combining the historical speed dataset and the corresponding speed labels, and training the prediction model using the second training set to obtain a speed prediction model, wherein the speed labels are the relative historical speeds of the bearing and the journal in the second training set; and inputting the speed dataset into the speed prediction model to obtain the relative speed corresponding to the speed dataset.

[0009] Optionally, after obtaining the wear amount of the bearing bush, the method further includes: obtaining the profile of the bearing bush, wherein the profile is the geometry of the inner surface of the bearing bush; updating the profile according to the wear amount to obtain an updated profile, wherein the wear amount and the change in the profile are positively correlated; and performing optimization again using a target optimization algorithm based on the updated profile to obtain optimized design parameters, wherein the optimized design parameters are used to construct the bearing bush.

[0010] Optionally, obtaining the wear amount of the bearing bush includes: forming a third training set by combining the historical design parameters and the corresponding wear labels; training the prediction model using the third training set to obtain a wear prediction model, wherein the wear labels are the historical wear amounts of the bearing bush in the third training set; and inputting the design parameters into the wear prediction model to obtain the wear amount corresponding to the design parameters.

[0011] Optionally, after inputting the design parameters into the wear prediction model to obtain the wear amount corresponding to the design parameters, the method further includes: obtaining the actual wear amount, wherein the actual wear amount is the actual material loss of the bearing due to friction; calculating the difference between the actual wear amount and the wear amount; optimizing the wear prediction model if the difference is greater than or equal to a preset difference threshold to obtain an optimized wear prediction model, wherein the optimization method includes one or more of adjusting weights, adjusting biases, adjusting model structure, feature selection, and regularization; training the optimized wear prediction model using the third training set to obtain an updated wear prediction model; and inputting the design parameters into the updated wear prediction model to obtain the wear amount corresponding to the design parameters.

[0012] Optionally, a target optimization algorithm is used to optimize the design parameters until the wear amount reaches the minimum wear amount, thereby obtaining the updated design parameters. This includes: using the target optimization algorithm to adjust the design parameters as variables multiple times, and obtaining the wear amount after each adjustment; extracting the minimum value among the multiple wear amounts after adjusting the design parameters, and extracting the adjusted design parameters corresponding to the minimum wear amount, thereby obtaining the updated design parameters.

[0013] According to another aspect of this application, a bearing bush parameter determination device is provided, comprising: a first acquisition unit for acquiring design parameters of the bearing bush, wherein the design parameters include at least one or more of the following: radius of curvature, oil film thickness of lubricating oil, oil film pressure, and viscosity of the lubricating oil; a second acquisition unit for acquiring the wear amount of the bearing bush, wherein the wear amount is the amount of material loss of the bearing bush due to friction; and a first determination unit for performing optimization using a target optimization algorithm to adjust the design parameters until the wear amount reaches a minimum value, thereby obtaining updated design parameters, wherein the updated design parameters are used to construct the bearing bush.

[0014] According to another aspect of this application, a bearing parameter determination system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any of the bearing parameter determination methods described above.

[0015] By applying the technical solution of this application, the design parameters and wear amount of the bearing bush are obtained. The design parameters of the bearing bush affect the contact condition between the bearing bush and the journal, the formation of the lubricating film, and the wear rate. The wear amount is the minimum wear condition of the bearing bush caused by friction. The design parameters are used as adjustable optimization variables, and the wear amount is used as the objective function. An objective optimization algorithm is used to find the optimal balance between the wear and lubrication performance of the bearing bush by continuously adjusting the design parameters. This can significantly reduce the wear amount of the bearing bush while ensuring lubrication performance, thereby effectively extending the service life of the bearing bush and improving its wear resistance. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for performing a bearing parameter determination method according to an embodiment of this application is shown.

[0018] Figure 2 A flowchart illustrating a method for determining the parameters of a bearing bush according to an embodiment of this application is shown.

[0019] Figure 3 A schematic diagram of the bearing profile design process is shown;

[0020] Figure 4 A schematic diagram of the bearing structure is shown;

[0021] Figure 5 A schematic diagram showing the bench verification results of errors in traditional bearing profile design is presented;

[0022] Figure 6 A schematic diagram showing the bench verification results of the bearing profile design error of this scheme is presented;

[0023] Figure 7 A structural block diagram of a bearing parameter determination device provided according to an embodiment of this application is shown.

[0024] The above figures include the following reference numerals:

[0025] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Bearing bushes are generally designed to improve wear resistance and extend service life through profile optimization. However, traditional design methods neglect the redistribution characteristics of the bearing bush-journal system under dynamic loads and the geometric parameter shifts caused by cumulative wear. This results in serious deficiencies in wear resistance due to profile design, particularly under the extreme operating conditions of modern high-performance diesel engines, severely impacting the reliability of bearing bush operation. Therefore, a more rational bearing bush profile design method is urgently needed to address this issue.

[0030] As described in the background section, the wear resistance of existing bearing bushes is poor. To solve the above problems, embodiments of this application provide a method for determining bearing bush parameters, a device for determining bearing bush parameters, and a system for determining bearing bush parameters.

[0031] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0032] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of determining bearing parameters according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the bearing parameter determination method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] This embodiment provides a method for determining the parameters of a bearing that operates on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] Figure 2 This is a flowchart illustrating a method for determining bearing parameters according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0036] Step S201: Obtain the design parameters of the bearing bush, wherein the design parameters include at least one or more of the radius of curvature, the oil film thickness of the lubricating oil, the oil film pressure, and the viscosity of the lubricating oil.

[0037] Specifically, obtaining the bearing design parameters is fundamental to optimized design. These parameters, such as radius of curvature, oil film thickness, oil film pressure, and lubricating oil viscosity, directly affect the wear and lubrication effect of the bearing during operation and are key inputs for subsequent optimization calculations. This embodiment, by accurately obtaining the design parameters, provides the necessary basic data for subsequent wear calculations and optimization algorithms. This is a prerequisite for optimizing the bearing profile, reducing wear, and improving lubrication performance.

[0038] Bearing shells are key components in internal combustion engines. They are mainly used to support rotating parts such as crankshafts and connecting rods, reduce friction and wear, and withstand the high loads generated during combustion.

[0039] In this scheme, the bearing profile can be decomposed into multiple segments. The radius of curvature of each segment is extracted as the profile feature of that segment, and each profile can generate a set of features (R1, R2, ..., Rn).

[0040] The radius of curvature, oil film thickness, oil film pressure, and viscosity of the lubricating oil all affect the amount of wear. The radius of curvature affects the contact area and shape between the bearing and the journal. A smaller radius of curvature leads to increased contact pressure and exacerbates wear; conversely, a larger radius of curvature reduces contact pressure and decreases wear. Oil film thickness relates to the lubrication state between the bearing and the journal. A thicker oil film reduces the direct contact between the bearing and the journal, resulting in lower wear. A thinner oil film reduces lubrication effectiveness, leading to increased contact pressure and accelerated wear. Oil film pressure is related to the oil film's load-bearing capacity. Higher oil film pressure allows the oil film to withstand a greater load, reducing wear. The viscosity of the lubricating oil determines the fluidity of the oil film. High-viscosity lubricating oil helps form a thick oil film under low-speed conditions, reducing wear.

[0041] In addition to the parameters mentioned above that affect wear, the hardness and toughness of the bearing and journal materials also influence the wear rate. Generally, materials with higher hardness are more wear-resistant, while materials with good toughness are less prone to cracking under impact loads, thus reducing the risk of wear. Furthermore, the heat generated during friction also affects wear. High temperatures accelerate material oxidation and decomposition, reduce material strength, and alter the viscosity of the lubricating oil, thereby affecting oil film formation and leading to increased wear.

[0042] Step S202: Obtain the wear amount of the bearing bush, wherein the wear amount is the amount of material loss of the bearing bush due to friction.

[0043] Specifically, obtaining the wear amount is the core of evaluating bearing performance. The wear amount directly reflects the degree of wear of the bearing during use and is a key indicator for measuring the effectiveness of design parameters. Through this embodiment, after determining the wear amount, the optimization algorithm has a clear objective: to reduce material loss, thereby extending the service life of the bearing and enhancing the reliability of the internal combustion engine.

[0044] Wear refers to the amount of material lost during friction due to the removal or deformation of surface material. It is an important indicator for evaluating the degree of wear of friction pairs (such as bearings and journals) in mechanical equipment under specific operating conditions. For larger wear amounts, millimeters are usually used as the unit, generally suitable for assessing wear through direct measurement. For precision mechanical parts or minor wear, micrometers are used as the unit for greater accuracy, suitable for measuring wear of minute dimensions. When wear is measured by volumetric loss, volume units such as cubic millimeters (mm³) or cubic centimeters (cm³) can be used. When wear is expressed as a loss of material weight, it is usually obtained by directly weighing the worn material in a wear test, such as in milligrams (mg) or grams (g).

[0045] Step S203: The target optimization algorithm is used to optimize the above design parameters until the wear amount reaches the minimum wear amount, and the updated design parameters are obtained. The updated design parameters are used to construct the above bearing.

[0046] Specifically, a target optimization algorithm (such as a multi-objective optimization algorithm) is used to adjust the design parameters, with the aim of finding a set of design parameters that minimizes the wear of the bearing bush. This process is achieved through iterative calculations, model predictions, and optimization of the objective function. This embodiment allows for fine-tuning of design parameters, significantly reducing bearing bush wear while ensuring good lubrication performance.

[0047] This scheme employs a lubrication-wear bidirectional coupled iterative approach, which refers to a numerical simulation method that considers the interaction between the hydrodynamic effect of lubrication and the surface wear morphology. By updating lubrication parameters and wear amounts, a dynamic coupled analysis is achieved. Optimal profile characteristic parameters can be obtained through multi-objective optimization design, leading to an optimized bearing profile scheme. In the multi-objective optimization design, the bearing profile characteristic values ​​(R1, R2, ..., Rn) are used as optimization variables, and the maximum or minimum wear amount of the bearing is used as the objective function. Through bidirectional coupling iterative calculation of lubrication and wear, the bearing wear condition under steady-state conditions is finally obtained, and the maximum or minimum wear amount of the bearing is extracted.

[0048] In the optimization problem of bearing profile design, NSGA-II (Non-dominated Sorting Genetic Algorithm II with elitist strategy) or MOEA / D (Multiobjective Optimization using Decomposition) algorithms are typically chosen. These algorithms can find the optimal solution among multiple objectives such as design parameters, wear rate, and lubrication performance, thus obtaining a set of bearing design schemes that balance performance across multiple indicators. NSGA-II is an evolutionary multiobjective optimization algorithm that balances the trade-offs between different objectives through non-dominated sorting and crowding distance selection. The MOEA / D algorithm decomposes the global multiobjective optimization problem into a series of single-objective optimization subproblems, then optimizes each sub-objective in parallel, and finally integrates them to obtain the frontier.

[0049] In constructing bearing bushes based on updated design parameters such as radius of curvature, oil film thickness, oil film pressure, and lubricating oil viscosity obtained from optimization algorithms, these parameters are first input into an established parametric design model of the bearing bush. Using computer-aided design software (e.g., CAD), the 3D model of the bearing bush is redrawn based on the new parameters. Subsequently, the manufacturing process of the bearing bush is adjusted in conjunction with the updated design parameters. After the adjustment is completed, a prototype bearing bush is fabricated based on the new parameters, and bench tests or actual tests are conducted to verify the actual effect of the optimized design in reducing wear, ensuring that the design parameters are translated into key performance improvements.

[0050] This embodiment obtains the design parameters and wear amount of the bearing bush. The design parameters affect the contact condition between the bearing bush and the journal, the formation of the lubricating film, and the wear rate. The wear amount is the minimum wear condition of the bearing bush caused by friction. The design parameters are used as adjustable optimization variables, and the wear amount is used as the objective function. An objective optimization algorithm is used to find the optimal balance between the wear and lubrication performance of the bearing bush by continuously adjusting the design parameters. This can significantly reduce the wear amount of the bearing bush while ensuring lubrication performance, thereby effectively extending the service life of the bearing bush and improving its wear resistance.

[0051] This invention establishes a lubrication dynamics model (i.e., the subsequent pressure prediction model and velocity prediction model, hereinafter referred to as the lubrication dynamics model) and a wear calculation model (i.e., the wear prediction model). It breaks through the traditional simulation framework by using bidirectional coupling iteration to achieve real-time coupled solution of lubrication and wear. Furthermore, by combining it with multi-objective optimization technology, it breaks through the traditional bearing profile design paradigm, innovatively constructing a bearing profile design system based on bidirectional coupling iteration. This invention constructs a parametric profile optimization scheme. By inversely inputting the wear prediction results into the design system and segmenting the bearing profile, the radius of curvature (R1, R2, ..., Rn) of each segment becomes the key design variable. Multi-objective optimization is achieved by combining the optimization algorithm. By introducing wear depth as the optimization objective, a more reasonable variable curvature composite profile is ultimately formed. Bench tests verify that the optimized bearing can significantly improve lubrication conditions, reduce friction loss, and increase the bearing's load-bearing capacity, thereby effectively extending the bearing's service life and providing strong support for the long-term stable operation of the internal combustion engine. Compared with traditional profile bearings, the bearings optimized based on this technology show a significant reduction in friction loss. The successful application of this technology provides a brand-new solution for the reliability design of high power density internal combustion engines.

[0052] The bearing bush parameter determination method proposed in this application is a bearing bush profile design method based on bidirectional coupling iteration. By combining lubrication-wear bidirectional coupling iteration and multi-objective optimization design methods, an optimal profile design scheme that meets the requirements of wear and reliability is established. The bearing bush profile design process is as follows: Figure 3 As shown in the diagram, after the process starts from "Start", the profile feature is extracted first. This feature is then input into a lubrication dynamics model that includes a lubrication model (i.e., the subsequent pressure prediction model) and a dynamics model (i.e., the subsequent speed prediction model) to obtain the rough contact pressure and relative slip. The results are then input into the bearing wear calculation model (i.e., the subsequent wear prediction model). After calculation, it is determined whether the profile has been updated. If not, the process returns to the profile feature extraction stage and repeats. If it has been updated, the maximum wear of the bearing is obtained and used as a training sample to construct a bearing wear calculation proxy model (i.e., the subsequent optimized wear prediction model). The accuracy is verified to meet the requirements. If not, the model is optimized. If it meets the requirements, multi-objective optimization design is carried out to form an optimized bearing profile scheme. Finally, the bearing profile design scheme is determined after durability testing, and the process ends.

[0053] The conventional structure of bearing bushes is as follows Figure 4 As shown, the bearing profile is arranged on the inner surface of the bearing. Under normal circumstances, a reasonable bearing profile is of great significance for reducing wear and improving bearing reliability. This paper breaks through the empirical paradigm of traditional bearing profile design and provides a bearing profile design method based on bidirectional coupling iteration to overcome the shortcomings of existing technologies.

[0054] In the specific implementation process, obtaining the wear amount of the aforementioned bearing bush includes: obtaining the wear coefficient, contact pressure, and relative velocity, wherein the wear coefficient is a predefined coefficient of the wear resistance of the bearing bush material, the contact pressure is the pressure value at the contact position between the bearing bush and the journal, and the relative velocity is the relative velocity between the bearing bush and the journal; calculating the product of the wear coefficient and the contact pressure to obtain a first value; calculating the derivative of the relative velocity to obtain a second value; and calculating the product of the first value and the second value to obtain the wear amount.

[0055] In this solution, the wear calculation method improves prediction accuracy. This embodiment not only considers wear assessment under static conditions but also incorporates the influence of dynamic operating conditions in the differential calculation of relative velocity, capturing the transient impact of velocity changes on wear and enhancing adaptability to actual operating conditions. More accurate wear prediction can effectively guide the optimized design of the bearing profile, avoiding under- or over-optimization due to prediction errors, and ensuring better reliability of the bearing under long-term operating conditions.

[0056] In the above embodiments, accurate prediction of wear amount stems from an understanding of the inherent properties of the material and a comprehensive consideration of dynamic factors of the operating conditions. The wear coefficient, as a quantitative indicator of a material's resistance to wear, multiplied by the contact pressure, reflects the material's wear tendency under a certain load, which is the basis of static wear assessment. By differentiating the relative velocity, the transient effect of velocity changes is captured, which is often ignored in traditional wear calculations. Therefore, this method can more closely approximate actual operating conditions, thereby improving the accuracy of wear prediction. In the process of calculating wear amount, the first value (wear coefficient × contact pressure) is combined with the second value (differentiation of relative velocity), comprehensively considering the interactive effects of material properties, load, and dynamic motion on wear amount. This method is more comprehensive than single-parameter assessment, ensuring the scientific and rational design of the bearing bush.

[0057] To accurately determine the wear of the bearing bush, the wear coefficient of the bearing bush material should be determined. This coefficient is preset and reflects the material's resistance to wear; it is determined by the material's hardness, toughness, and chemical composition. Secondly, the contact pressure at the contact point between the bearing bush and the journal should be measured. This is a crucial parameter under dynamic operating conditions and directly affects the degree of wear. Simultaneously, the relative velocity between the bearing bush and the journal should be recorded, as it influences the dynamic characteristics of the wear process.

[0058] Subsequently, the product of the wear coefficient and the contact pressure is calculated to obtain the first value, which reflects the influence of material properties and contact pressure on wear under static conditions. Next, the relative velocity is differentiated to obtain the second value; this step considers the instantaneous impact of velocity changes on the wear rate. Finally, the first and second values ​​are multiplied to obtain the wear amount. This calculation method fully considers material properties, operating loads, and dynamic factors, making the prediction of wear amount more accurate.

[0059] The wear coefficient needs to be set taking into account the properties of the bearing material. Assuming the bearing material is tin bronze, the wear coefficient can be 2 × 10⁻⁶. -16 m 2 / N, the contact pressure at the contact point between the bearing bush and the journal is 100MPa (i.e., 1×10). 8 The relative speed between the bearing bush and the journal is 10 m / s (N / m²).

[0060] Bearing wear is calculated using a wear calculation formula. The formula used for bearing wear calculation is as follows:

[0061] ,in, inner surface of the bearing i Wear amount within one work cycle on a node. Indicates the wear coefficient. The time of one work cycle, express i Rough contact pressure at the node at any given moment. express i At the node t The relative speed between the bearing bush and the journal at any given time.

[0062] In some embodiments, obtaining contact pressure includes: obtaining a prediction model, wherein the prediction model is a model for numerical prediction; forming a first training set by combining historical design parameters and corresponding pressure labels, training the prediction model using the first training set to obtain a pressure prediction model, wherein the pressure labels are historical pressure values ​​of the historical contact positions of the bearing bush and the journal in the first training set; and inputting the design parameters into the pressure prediction model to obtain the contact pressure corresponding to the design parameters.

[0063] In this scheme, the pressure prediction model learns from a large amount of historical data and can identify the subtle effects of changes in design parameters on contact pressure. It can make accurate predictions even under complex dynamic working conditions and obtain accurate predicted contact pressure.

[0064] In the above embodiments, accurate prediction of contact pressure is based on learning from historical data and building a predictive model. First, historical contact pressure data covering a wide range of design parameters and operating conditions is collected, providing a rich and diverse set of training samples for the model. Then, machine learning algorithms are used to train the pressure prediction model. Through repeated learning and adjustments, the model learns to map design parameters to actual contact pressure. When new design parameters are input, the model outputs a predicted contact pressure based on its learned knowledge, demonstrating generalization and adaptability. This enables it to cope with complex and changing actual operating conditions, significantly improving the accuracy of contact pressure prediction and providing a decision-making basis for the optimized design of bearing bushes.

[0065] To obtain the contact pressure at the contact point between the bearing bush and the journal, firstly, a suitable prediction model for numerical prediction is selected, such as a neural network, support vector machine, or random forest. Then, historical design parameters are combined with corresponding historical contact pressure values ​​(i.e., pressure labels) to form the first training set. By training the prediction model using this first training set, a pressure prediction model is obtained. This model can learn and understand the complex relationship between design parameters and contact pressure. During this process, the model continuously adjusts its internal parameters to minimize the difference between the predicted results and the actual pressure labels, ultimately achieving high prediction accuracy. Finally, the current design parameters are input into the aforementioned pressure prediction model to obtain the predicted contact pressure value.

[0066] In practical applications, the choice of prediction model depends on the characteristics of the data, the requirements of the prediction task, and the availability of computing resources. If the historical dataset contains a large number of design parameter combinations and the output contact pressure has a complex nonlinear relationship, then a neural network model (NN) can be chosen. This is an algorithm that mimics the structure of neurons in the human brain and can learn the complex nonlinear relationship between inputs and outputs. Neural network models are well-suited for handling multi-input, multi-output problems and can extract features from large amounts of historical data through deep learning to make highly accurate predictions. If the dataset is small, or if the uncertainty of the predicted output value needs to be addressed, Gaussian Process Regression (GPR) may be more suitable. GPR is a probability-based model that can provide confidence intervals for predicted values ​​and is suitable for small sample datasets and noisy data. GPR can handle the uncertainty between design parameters and contact pressure in contact pressure prediction, providing more reliable prediction results.

[0067] In the above embodiments, the lubrication dynamics model mainly refers to a model based on both a lubrication model and a dynamics model. The lubrication model is the pressure prediction model, and the dynamics model is the subsequent speed prediction model. This model analyzes the lubrication characteristics and dynamic response of the bearing. The lubrication model uses the Reynolds equation for calculation, as follows:

[0068] ,

[0069] in, These are the local coordinates of the lubrication zone of the bearing friction pair; and These are the lubricating oil film thickness and the oil film pressure, respectively. It is the relative sliding speed between the journal and the bearing bush; It is the combined surface roughness of the journal and bearing bush; It is the dynamic viscosity of the lubricating oil; , , and They are respectively Directional pressure flow factor The directional pressure flow factor, shear flow factor, and contact factor.

[0070] In the specific implementation process, obtaining relative speed includes: obtaining speed-related information, wherein the speed-related information includes one or more of the rotational speed of the journal, the length of the bearing shell, the width of the bearing shell, and the eccentricity of the shaft; combining the design parameters and the speed-related information to obtain a speed dataset; forming a second training set by combining the historical speed dataset and the corresponding speed labels, and training the prediction model using the second training set to obtain a speed prediction model, wherein the speed labels are the relative historical speeds of the bearing shell and the journal in the second training set; and inputting the speed dataset into the speed prediction model to obtain the relative speed corresponding to the speed dataset.

[0071] This solution employs a data-driven predictive model, which captures operational details that traditional theoretical models struggle to reflect, such as the impact of rotational speed changes on relative velocity, and the adjustment effect of bearing dimensions and shaft eccentricity on the velocity field distribution. Accurate relative velocity prediction ensures the accuracy of wear calculations, thereby resulting in better wear resistance of the bearings.

[0072] In the above embodiments, the accuracy of relative velocity prediction directly affects the calculation result of bearing wear. By collecting a large amount of historical data, including the relative velocity between the bearing and journal under different design parameters and operating conditions, an efficient prediction model can be trained. The model learns how to predict relative velocity from given design parameters and velocity information by studying the statistical regularities and physical correlations in the dataset. It can quickly and accurately output the predicted value of relative velocity based on the input information. Because the model is trained based on real historical data, it can handle nonlinear and uncertain problems, improving the reliability and accuracy of the prediction.

[0073] In practical applications, the first step is to collect speed-related information, including parameters such as journal rotational speed, bearing length, bearing width, and shaft eccentricity. These design parameters are then combined with the speed-related information to form a speed dataset. Next, a prediction model is trained using historical data, which includes the relative speed values ​​between the bearing and journal under different design parameters (serving as speed labels). Finally, the speed dataset of the current design is input into the speed prediction model to obtain the predicted relative speed values ​​under the current design parameters.

[0074] The dynamic model, also known as the velocity prediction model, is a numerical simulation method used to study the dynamic response and interaction of multiple interconnected moving parts under force and motion constraints. Based on the lubrication model (i.e., the pressure prediction model) and the multibody dynamic model (i.e., the velocity prediction model), a lubrication dynamic model for the bearing is established. The profile is then substituted into the model to solve for the corresponding rough contact pressure and relative slip of the bearing bush.

[0075] In some embodiments, after obtaining the wear amount of the bearing bush, the method further includes: obtaining the profile of the bearing bush, wherein the profile is the geometry of the inner surface of the bearing bush; updating the profile according to the wear amount to obtain an updated profile, wherein the wear amount and the change in the profile are positively correlated; and optimizing again using a target optimization algorithm based on the updated profile to obtain re-optimized design parameters, wherein the re-optimized design parameters are used to construct the bearing bush.

[0076] This solution introduces a wear feedback mechanism. Through dynamic adjustment of the profile, the bearing bush can adapt to the actual wear conditions. Even if wear occurs during operation, it can be compensated and adjusted by updating the profile, ensuring good performance stability of the bearing bush throughout its entire lifespan.

[0077] In the above embodiments, the core of the closed-loop optimization mechanism is the feedback of wear amount. This allows the design process to be adjusted based on actual wear predictions, avoiding performance deviations that might result from profile designs based on static assumptions. Through multiple iterative optimizations, each updated profile gets closer to the optimal solution, thereby improving the accuracy and efficiency of the bearing design. Assuming the bearing with the initial profile has a predicted wear amount of 0.01 mm under specific operating conditions... 3 By analyzing the wear distribution, areas with more severe wear were identified. The radius of curvature (i.e., profile change) of the bearing in these areas was then adjusted, reducing the wear to 0.008 mm. 3 This change is determined by the amount of wear; the greater the wear, the greater the change in profile. Then, the design was optimized again, and the optimized design parameters further reduced the wear to 0.005mm. 3 The entire process utilizes a closed-loop optimization mechanism to continuously reduce wear, thereby improving the service life and operational stability of the bearing.

[0078] After obtaining the wear amount of the bearing bush, the initial profile of the bearing bush is determined. The profile is then updated based on the wear amount, a process achieved by adjusting the radius of curvature of each segment of the bearing bush. Specifically, areas with significant wear will cause a change in the radius of curvature of the corresponding profile segment (i.e., a change in the profile) to compensate for the geometric deviation of the profile caused by wear. Wear amount and profile change are positively correlated; the greater the wear, the greater the profile change. This adjustment of the bearing bush profile reduces wear during subsequent operation. Finally, a target optimization algorithm is used again for optimization. Based on the updated profile, a new optimization design is performed to ensure that the bearing bush's performance indicators (such as load-bearing capacity, friction loss, and wear amount) reach their optimal levels. This process may require multiple iterations until the optimized design parameters that minimize bearing bush wear while satisfying other design constraints are found.

[0079] In bearing design, the profile refers to a set of designs and parameters, including but not limited to variations in the radius of curvature, the length and width of the bearing, and specific geometric features. The profile design of the inner surface of the bearing is to optimize lubrication conditions, reduce wear, improve load-bearing capacity, and enhance heat exchange efficiency.

[0080] During the process of updating the bearing bush profile based on wear, the wear distribution of the bearing bush under specific working conditions is obtained through numerical simulation or experimental testing. Then, the wear distribution is analyzed to identify areas with more severe wear. Areas with large wear are usually where the profile design needs to be adjusted significantly. Based on the magnitude of the wear, key parameters of the bearing bush profile, primarily the radius of curvature, are adjusted. Larger wear indicates that the profile may require a larger radius of curvature to distribute the load and reduce pressure per unit area. Conversely, if the wear is small, significant adjustments may not be necessary, or even the radius of curvature may need to be reduced to optimize lubrication conditions. Based on the adjusted radius of curvature and other design parameters, the inner profile of the bearing bush is reconstructed.

[0081] In the above embodiment, the bearing profile was updated based on wear feedback. Then, a target optimization algorithm was used to further optimize the updated profile. Based on the new profile, the design parameters were re-evaluated to ensure that the bearing's performance indicators were not only optimal in the initial design but also remained at their best after the profile update. Target optimization algorithms typically consider multiple objective functions, such as minimizing wear, reducing friction loss, and improving load-bearing capacity, thereby finding a balance between multiple performance indicators.

[0082] By substituting the rough contact pressure and relative slip into the wear calculation model, the wear condition of the bearing bush can be obtained. This information can then be imported into the mating clearance between the bearing bush and the journal to update the profile, thereby achieving real-time updating of the bearing bush profile and realizing bidirectional coupling iteration of lubrication and wear.

[0083] In the specific implementation process, obtaining the wear amount of the aforementioned bearing bush includes: forming a third training set by combining the aforementioned historical design parameters and the corresponding wear labels; training the aforementioned prediction model using the aforementioned third training set to obtain a wear prediction model, wherein the aforementioned wear labels are the historical wear amounts of the aforementioned bearing bush in the aforementioned third training set; and inputting the aforementioned design parameters into the aforementioned wear prediction model to obtain the aforementioned wear amounts corresponding to the aforementioned design parameters.

[0084] In this scheme, the wear prediction model is based on historical wear data and uses machine learning to accurately predict future wear conditions. It can handle complex operating conditions and nonlinear relationships, making the prediction results more consistent with reality. Accurate wear prediction provides a reliable basis for the optimized design of bearing profiles.

[0085] In the above embodiments, traditional wear prediction often relies on empirical formulas or simplified models. While these can estimate wear trends to some extent, they fall short when dealing with complex wear phenomena under dynamic operating conditions. Machine learning prediction models based on historical data, by learning historical wear patterns, can capture the subtle relationship between design parameters and wear amount, including nonlinear effects and coupling effects, thus providing more comprehensive data support for prediction. If there are 1000 sets of historical wear data, covering different profile designs with curvature radii from 10mm to 20mm, operating conditions ranging from 1000rpm to 2500rpm, and various bearing sizes from 40mm to 60mm, a wear prediction model can be constructed through deep neural network training. The average error between the predicted wear amount and the actual wear amount is less than 5%. That is, when a new type of bearing is designed with design parameters of a curvature radius of 15mm, a journal speed of 2000rpm, and a bearing size of 50mm×30mm, inputting it into the wear prediction model can accurately predict the wear amount as 0.007mm. 3 This prediction will be used to guide profile optimization and redesign to ensure that the bearing bushes can achieve the expected low wear rate in actual working conditions.

[0086] In the specific implementation process, historical design parameters and corresponding wear amounts are first collected. These historical design parameters cover all key aspects of the bearing design. Then, a third training set is constructed, combining the historical design parameters with corresponding actual wear amounts (wear labels). This third training set is used to train a prediction model. An appropriate machine learning algorithm is selected, and through training, the model learns to predict the bearing wear amount from the input parameters, thus forming a wear prediction model. Finally, the design parameters are input into the wear prediction model, and the trained model predicts the corresponding wear amount based on the current design parameters. This prediction result is used for profile updates and further design optimization to ensure that the bearing design achieves minimal wear under actual operating conditions, thereby improving its service life and reliability.

[0087] By using multiple sets of input profile features, the corresponding maximum wear values ​​of the bearing bush can be obtained. These are used as training samples to establish a proxy model for bearing bush wear calculation, thereby obtaining the bearing bush profile feature parameters (R1, R2, ..., R...). n The mapping relationship between bearing wear and bearing wear needs to be determined. If the accuracy of the proxy model is insufficient, additional feature sample data is required.

[0088] In some embodiments, after inputting the design parameters into the wear prediction model to obtain the wear amount corresponding to the design parameters, the method further includes: obtaining the actual wear amount, wherein the actual wear amount is the actual material loss of the bearing due to friction; calculating the difference between the actual wear amount and the wear amount; optimizing the wear prediction model if the difference is greater than or equal to a preset difference threshold to obtain an optimized wear prediction model, wherein the optimization method includes one or more of adjusting weights, adjusting biases, adjusting model structure, feature selection, and regularization; training the optimized wear prediction model using the third training set to obtain an updated wear prediction model; and inputting the design parameters into the updated wear prediction model to obtain the wear amount corresponding to the design parameters.

[0089] In this solution, accurate wear prediction is the cornerstone for guiding the updating and optimization of bearing profiles, ensuring the high performance and long service life of the designed bearings under actual working conditions. The accuracy of the wear prediction model is significantly improved, thereby enhancing the precision and reliability of the bearing profile optimization design.

[0090] In the above embodiments, by comparing the model's predicted results with the actual wear amount, prediction deviations can be detected in a timely manner. Targeted optimization of the model effectively improves its prediction accuracy. The model optimization triggered by a preset difference threshold forms a closed-loop mechanism, enabling the design process to self-verify and self-correct, ensuring continuous optimization of the bearing profile design. Assume that in a bearing design process, the initial model predicts a wear amount of 0.012 mm under a certain design parameter. 3 However, actual durability tests revealed that the actual wear amount under the same parameters was 0.016 mm. 3 The calculated difference between the two is 0.004 mm. 3 If the preset difference threshold is 0.003mm 3 Due to 0.004mm 3 >0.003mm 3 This triggered the model optimization process. Through feature selection and regularization, the model's structure and parameters were adjusted, resulting in the optimized model predicting a wear rate of 0.015 mm under those parameters. 3 The difference was reassessed and found to be 0.001 mm. 3 This indicates that the prediction error of the optimized model has been significantly reduced, achieving a more accurate wear prediction target, thereby improving the accuracy of the bearing profile optimization design.

[0091] In machine learning and deep learning, adjusting weights, adjusting biases, adjusting model structure, feature selection, and regularization are several common techniques for optimizing models. Weight adjustment is a fundamental model optimization method that changes the proportion of various parameters in the model to better fit the training data. In neural networks, weights connect nodes in the input layer and hidden layers, and hidden layers and output layers, and are continuously updated through the learning process of forward and backward propagation. Bias adjustment involves the bias parameters of each node in the model, allowing the model to have a non-zero output even when the input is zero. Bias adjustment helps the model cover the data offset, making the model output better reflect the true distribution of the training data. Adjusting the model structure involves changing the number of layers, nodes, activation function types, etc., in the neural network to find a model more suitable for the current dataset and problem complexity. Adjusting the model structure can significantly improve the model's predictive ability. Feature selection refers to selecting the most useful features for the prediction target from a large number of original input features before model training, removing irrelevant or redundant features to simplify the model and improve efficiency and predictive performance. Regularization is a strategy to prevent model overfitting. By adding a regularization term to the loss function, the model complexity is limited to avoid the model overfitting the noise in the training data, thereby enabling the model to have better generalization ability on unseen data.

[0092] This solution can also construct a proxy model for bearing wear calculation. The construction and training process of the proxy model for bearing wear calculation is the same as that of the wear prediction model, and will not be repeated here. The proxy model for bearing wear calculation is a fast bearing wear calculation model built through data-driven methods, which is used to replace complex simulations and evaluate the amount of bearing wear.

[0093] In the specific implementation process, a target optimization algorithm is used to find the best design parameters and adjust them until the wear amount reaches the minimum wear amount, thus obtaining the updated design parameters. This includes: using the target optimization algorithm to adjust the design parameters as variables multiple times and obtaining the wear amount after each adjustment; extracting the minimum value among the multiple wear amounts after adjusting the design parameters, and extracting the adjusted design parameters corresponding to the minimum wear amount to obtain the updated design parameters.

[0094] In this scheme, the design scheme with minimum wear ensures the reliability and durability of the bearing bush under long-term operation. The bearing bush design can quickly locate the optimal solution with minimum wear among multiple design parameters, thereby improving the wear resistance performance of the bearing bush.

[0095] In the above embodiments, the target optimization algorithm can automatically explore the design space and evaluate the performance of different parameter combinations, greatly improving the efficiency of optimization compared to manual trial and error. By adjusting the design parameters multiple times and calculating the wear amount after each adjustment, the algorithm can perform detailed comparisons across multiple dimensions of the design parameters, ensuring that the true minimum value is found.

[0096] The above embodiments include two key steps: parameter adjustment and wear measurement acquisition, and minimum value extraction and parameter updating. Parameter adjustment and wear measurement acquisition emphasize the dynamic adjustment of design parameters and the real-time feedback of wear. When designing the bearing profile, design parameters (such as radius of curvature, bearing size, journal speed, etc.) are considered as variable variables in the algorithm. Objective optimization algorithms (such as genetic algorithms, particle swarm optimization, gradient descent, etc.) intelligently adjust these parameters multiple times as variables. After each adjustment, the new wear measurement is calculated in real time to evaluate the effect of the parameter adjustment. After obtaining the wear measurement information after multiple parameter adjustments, the next step is to find the parameter combination corresponding to the minimum wear measurement and use it as the updated design parameters.

[0097] To achieve the above steps, a set of initial design parameters is first determined, such as a five-segment composite profile with a curvature radius distribution of (12mm, 14mm, 16mm, 18mm, 20mm), a journal rotation speed of 2000rpm, and a bearing size of 50mm × 30mm. Then, these parameters are automatically adjusted multiple times using a target optimization algorithm, with each adjusted parameter combination representing a candidate design. After adjusting the design parameters, the new parameter combination is immediately input into the wear prediction model to obtain the predicted wear amount. If the model predicts that the curvature radius distribution is adjusted to (13mm, 14mm, 17mm, 19mm, 21mm), the wear amount is 0.007mm. 3 Therefore, the wear amount of this parameter combination becomes part of the evaluation. After obtaining wear information after multiple parameter adjustments, the next step is to find the parameter combination corresponding to the minimum wear amount and use it as the updated design parameter. After multiple adjustments, dozens or even hundreds of design parameter combinations and corresponding wear amounts may be obtained. From this data, the minimum wear amount and the parameter combination corresponding to the minimum wear amount are extracted. Suppose that in a series of adjustments, it is found that when the radius of curvature distribution is (11mm, 13mm, 15mm, 17mm, 19mm), the wear amount of the bearing bush is reduced to the minimum, 0.006mm. 3 Therefore, this combination of parameters becomes the updated design parameters, namely the optimal profile design scheme for the bearing bush.

[0098] Multi-objective optimization design is a method that weighs multiple conflicting objectives and obtains the optimal solution through collaborative algorithm optimization.

[0099] This plan also includes a durability test, which is an experimental method that simulates actual working conditions to test the wear performance of the bearing under long-term alternating loads and evaluate its service life and reliability.

[0100] Based on endurance testing, the obtained bearing profile of the large-bore engine was bench-tested to verify the effectiveness of the optimization method. The results of the 500-hour endurance test are as follows: Figure 5 and Figure 6 As shown, by Figure 5 and Figure 6 It is evident that the bearing profile design based on bidirectional coupling iteration successfully solves the problem of high wear and low reliability of high-strength diesel engine bearings.

[0101] Traditional bearing profile design methods often rely on empirical approaches or conventional wear calculations. However, traditional multi-cylinder internal combustion engine bearing wear prediction suffers from several problems: models based on static boundary conditions struggle to update wear boundaries in real-time under dynamic operating conditions, failing to fully represent the wear evolution throughout the entire lifecycle. This directly leads to the following key technical constraints: a lack of dynamic correlation between wear accumulation and bearing profile, and a lack of reasonable theoretical support for profile optimization. These issues have become the core bottleneck restricting the improvement of bearing design accuracy, directly causing abnormal wear and bearing failure. Scientific modeling of profile optimization has become a crucial breakthrough in overcoming the empiricism of traditional bearing design.

[0102] This invention aims to propose a bearing profile optimization design method based on bidirectional coupling iteration, thereby breaking through the empirical paradigm of traditional bearing profile design, creating a more reliable profile optimization system, and providing a brand-new solution for the reliability design of high power density internal combustion engines.

[0103] The main advantages of this scheme are as follows: It designs a more reasonable bearing profile design method, improves the wear life of the bearing, and solves the problem of high bearing friction loss under the background of continuously increasing power density. By using a segmented feature optimization method, combined with lubrication-wear bidirectional coupling iteration and multi-objective optimization design methods, it breaks through the current empirical paradigm of bearing profile design.

[0104] This application also provides a bearing parameter determination device. It should be noted that the bearing parameter determination device of this application can be used to execute the bearing parameter determination method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0105] The parameter determination device for bearing bushes provided in the embodiments of this application is described below.

[0106] Figure 7 This is a structural block diagram of a bearing parameter determination device according to an embodiment of this application. Figure 7 As shown, the device includes:

[0107] The first acquisition unit 10 is used to acquire the design parameters of the bearing bush, wherein the design parameters include at least one or more of the radius of curvature, the oil film thickness of the lubricating oil, the oil film pressure, and the viscosity of the lubricating oil.

[0108] The second acquisition unit 20 is used to acquire the wear amount of the bearing bush, wherein the wear amount is the amount of material loss of the bearing bush due to friction.

[0109] The first determining unit 30 is used to perform optimization using a target optimization algorithm to adjust the above design parameters until the wear amount reaches the minimum wear amount, and obtain the updated design parameters, wherein the updated design parameters are used to construct the above bearing bush.

[0110] This embodiment obtains the design parameters and wear amount of the bearing bush. The design parameters affect the contact condition between the bearing bush and the journal, the formation of the lubricating film, and the wear rate. The wear amount is the minimum wear condition of the bearing bush caused by friction. The design parameters are used as adjustable optimization variables, and the wear amount is used as the objective function. An objective optimization algorithm is used to find the optimal balance between the wear and lubrication performance of the bearing bush by continuously adjusting the design parameters. This can significantly reduce the wear amount of the bearing bush while ensuring lubrication performance, thereby effectively extending the service life of the bearing bush and improving its wear resistance.

[0111] In the specific implementation process, the second acquisition unit includes an acquisition module, a first calculation module, a second calculation module, and a third calculation module. The acquisition module is used to acquire the wear coefficient, contact pressure, and relative velocity. The wear coefficient is a predefined coefficient of the wear resistance of the bearing material, the contact pressure is the pressure value at the contact position between the bearing and the journal, and the relative velocity is the relative velocity between the bearing and the journal. The first calculation module is used to calculate the product of the wear coefficient and the contact pressure to obtain a first value. The second calculation module is used to calculate the derivative of the relative velocity to obtain a second value. The third calculation module is used to calculate the product of the first value and the second value to obtain the wear amount.

[0112] In this solution, the wear calculation method improves prediction accuracy. This embodiment not only considers wear assessment under static conditions but also incorporates the influence of dynamic operating conditions in the differential calculation of relative velocity, capturing the transient impact of velocity changes on wear and enhancing adaptability to actual operating conditions. More accurate wear prediction can effectively guide the optimized design of the bearing profile, avoiding under- or over-optimization due to prediction errors, and ensuring better reliability of the bearing under long-term operating conditions.

[0113] In some embodiments, the acquisition module includes a first acquisition submodule, a first training submodule, and a first processing submodule. The first acquisition submodule is used to acquire a prediction model, wherein the prediction model is a model for numerical prediction. The first training submodule is used to form a first training set by combining historical design parameters and corresponding pressure labels, and to train the prediction model using the first training set to obtain a pressure prediction model. The pressure labels are the historical pressure values ​​of the historical contact positions of the bearing bush and the journal in the first training set. The first processing submodule is used to input the design parameters into the pressure prediction model to obtain the contact pressure corresponding to the design parameters.

[0114] In this scheme, the force prediction model learns from a large amount of historical data and can identify the subtle effects of changes in design parameters on contact pressure. It can make accurate predictions even under complex dynamic working conditions and obtain accurate predicted contact pressure.

[0115] In the specific implementation process, the acquisition module includes a second acquisition submodule, a combination submodule, a second training submodule, and a second processing submodule. The second acquisition submodule is used to acquire speed-related information, which includes one or more of the rotational speed of the journal, the length of the bearing shell, the width of the bearing shell, and the eccentricity of the shaft. The combination submodule is used to combine the design parameters and the speed-related information to obtain a speed dataset. The second training submodule is used to combine the historical speed dataset and the corresponding speed labels to form a second training set, and uses the second training set to train the prediction model to obtain a speed prediction model. The speed labels are the relative historical speeds of the bearing shell and the journal in the second training set. The second processing submodule is used to input the speed dataset into the speed prediction model to obtain the relative speed corresponding to the speed dataset.

[0116] This solution employs a data-driven predictive model, which captures operational details that traditional theoretical models struggle to reflect, such as the impact of rotational speed changes on relative velocity, and the adjustment effect of bearing dimensions and shaft eccentricity on the velocity field distribution. Accurate relative velocity prediction ensures the accuracy of wear calculations, thereby resulting in better wear resistance of the bearings.

[0117] In some embodiments, the above-described apparatus further includes a third acquisition unit, an update unit, and a second determination unit. The third acquisition unit is used to acquire the profile of the bearing bush after acquiring the wear amount, wherein the profile is the geometry of the inner surface of the bearing bush. The update unit is used to update the profile according to the wear amount to obtain an updated profile, wherein the wear amount and the change in the profile are positively correlated. The second determination unit is used to perform target optimization algorithm optimization again according to the updated profile to obtain the re-optimized design parameters, wherein the re-optimized design parameters are used to construct the bearing bush.

[0118] This solution introduces a wear feedback mechanism. Through dynamic adjustment of the profile, the bearing bush can adapt to the actual wear conditions. Even if wear occurs during operation, it can be compensated and adjusted by updating the profile, ensuring good performance stability of the bearing bush throughout its entire lifespan.

[0119] In the specific implementation process, the second acquisition unit includes a training module and a processing module. The training module is used to form a third training set by combining the above-mentioned historical design parameters and the corresponding wear labels, and to train the above-mentioned prediction model using the above-mentioned third training set to obtain the wear prediction model. The wear labels are the historical wear amounts of the above-mentioned bearings in the above-mentioned third training set. The processing module is used to input the above-mentioned design parameters into the above-mentioned wear prediction model to obtain the wear amounts corresponding to the above-mentioned design parameters.

[0120] In this scheme, the wear prediction model is based on historical wear data and uses machine learning to accurately predict future wear conditions. It can handle complex operating conditions and nonlinear relationships, making the prediction results more consistent with reality. Accurate wear prediction provides a reliable basis for the optimized design of bearing profiles.

[0121] In some embodiments, the above-described apparatus further includes a fourth acquisition unit, a calculation unit, an optimization unit, and a training unit. The fourth acquisition unit is used to acquire the actual wear amount after inputting the design parameters into the wear prediction model and obtaining the wear amount corresponding to the design parameters, wherein the actual wear amount is the actual material loss of the bearing bush due to friction. The calculation unit is used to calculate the difference between the actual wear amount and the wear amount. The optimization unit is used to optimize the wear prediction model when the difference is greater than or equal to a preset difference threshold to obtain an optimized wear prediction model, wherein the optimization method includes one or more of adjusting weights, adjusting biases, adjusting model structure, feature selection, and regularization. The training unit is used to train the optimized wear prediction model using the third training set to obtain an updated wear prediction model, and input the design parameters into the updated wear prediction model to obtain the wear amount corresponding to the design parameters.

[0122] In this solution, accurate wear prediction is the cornerstone for guiding the updating and optimization of bearing profiles, ensuring the high performance and long service life of the designed bearings under actual working conditions. The accuracy of the wear prediction model is significantly improved, thereby enhancing the precision and reliability of the bearing profile optimization design.

[0123] In the specific implementation process, the first determining unit includes an adjustment module and an extraction module. The adjustment module is used to use a target optimization algorithm to adjust the above design parameters as variables multiple times and obtain the above wear amount after each adjustment of the above design parameters. The extraction module is used to extract the minimum value among the above wear amounts after multiple adjustments of the above design parameters, and extract the adjusted above design parameters corresponding to the minimum value among the above wear amounts to obtain the above updated design parameters.

[0124] In this scheme, the design scheme with minimum wear ensures the reliability and durability of the bearing bush under long-term operation. The bearing bush design can quickly locate the optimal solution with minimum wear among multiple design parameters, thereby improving the wear resistance performance of the bearing bush.

[0125] The aforementioned bearing parameter determination device includes a processor and a memory. The first acquisition unit, the second acquisition unit, and the first determination unit are all stored as program units in the memory. The processor executes these program units stored in the memory to achieve their respective functions. All of the aforementioned modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0126] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and adjusting kernel parameters can address the poor wear resistance of bearing bushes in existing technologies.

[0127] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0128] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the bearing parameter determination method.

[0129] This invention provides a processor for running a program, wherein the program executes the method for determining the parameters of the bearing bush.

[0130] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements at least the method steps for determining the parameters of the bearing. The device described herein can be a server, PC, PAD, mobile phone, etc.

[0131] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform a program that initializes a method for determining parameters of at least bearings.

[0132] This application also provides a bearing parameter determination system, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for determining the parameters of any of the aforementioned bearings.

[0133] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0134] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0136] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0137] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0138] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0139] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0140] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0141] 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 specification.

[0142] It should also be noted that 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. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0143] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining the parameters of a bearing bush, characterized in that, include: Obtain the design parameters of the bearing bush, wherein the design parameters include at least one or more of the radius of curvature, the oil film thickness of the lubricating oil, the oil film pressure, and the viscosity of the lubricating oil; The wear amount of the bearing bush is obtained, wherein the wear amount is the amount of material loss of the bearing bush due to friction. An objective optimization algorithm is used to optimize the design parameters until the wear amount reaches the minimum value, resulting in updated design parameters. These updated design parameters are used to construct the bearing bush. Obtaining the wear amount of the bearing bush includes: obtaining a wear coefficient, contact pressure, and relative velocity, wherein the wear coefficient is a predefined coefficient of the bearing bush material's resistance to wear, the contact pressure is the pressure value at the contact position between the bearing bush and the journal, and the relative velocity is the relative velocity between the bearing bush and the journal; calculating the product of the wear coefficient and the contact pressure to obtain a first value; calculating the derivative of the relative velocity to obtain a second value; and calculating the product of the first value and the second value to obtain the wear amount.

2. The method according to claim 1, characterized in that, Obtaining contact pressure includes: Obtain a prediction model, wherein the prediction model is a model used for numerical prediction; The historical design parameters and corresponding pressure labels are combined into a first training set. The prediction model is trained using the first training set to obtain a pressure prediction model. The pressure label is the historical pressure value of the historical contact position of the bearing and the journal in the first training set. The design parameters are input into the pressure prediction model to obtain the contact pressure corresponding to the design parameters.

3. The method according to claim 2, characterized in that, To obtain relative velocity, including: Obtain speed-related information, wherein the speed-related information includes one or more of the journal rotation speed, the bearing length, the bearing width, and the shaft eccentricity; The design parameters and the speed-related information are combined to obtain a speed dataset; The historical speed dataset and the corresponding speed labels are combined to form a second training set. The prediction model is trained using the second training set to obtain a speed prediction model. The speed labels are the relative historical speeds of the bearing and the journal in the second training set. The speed dataset is input into the speed prediction model to obtain the relative speed corresponding to the speed dataset.

4. The method according to claim 2, characterized in that, After obtaining the wear amount of the bearing bush, the method further includes: Obtain the profile of the bearing bush, wherein the profile is the geometry of the inner surface of the bearing bush; The profile is updated based on the wear amount to obtain the updated profile, wherein the wear amount and the change in the profile are positively correlated. Based on the updated profile, the target optimization algorithm is used again to optimize and obtain the optimized design parameters, which are used to construct the bearing bush.

5. The method according to claim 2, characterized in that, Obtaining the wear amount of the bearing bush includes: The historical design parameters and corresponding wear labels are combined into a third training set. The prediction model is trained using the third training set to obtain the wear prediction model. The wear label is the historical wear amount of the bearing in the third training set. The design parameters are input into the wear prediction model to obtain the wear amount corresponding to the design parameters.

6. The method according to claim 5, characterized in that, After inputting the design parameters into the wear prediction model to obtain the wear amount corresponding to the design parameters, the method further includes: Obtain the actual wear amount, wherein the actual wear amount is the actual material loss of the bearing bush due to friction; Calculate the difference between the actual wear amount and the wear amount; If the difference is greater than or equal to a preset difference threshold, the wear prediction model is optimized to obtain an optimized wear prediction model. The optimization method includes one or more of the following: adjusting weights, adjusting biases, adjusting model structure, feature selection, and regularization. The optimized wear prediction model is trained using the third training set to obtain an updated wear prediction model. The design parameters are then input into the updated wear prediction model to obtain the wear amount corresponding to the design parameters.

7. The method according to any one of claims 1 to 6, characterized in that, An objective optimization algorithm is used to optimize the design parameters until the wear amount reaches its minimum value, resulting in updated design parameters, including: The design parameters are adjusted multiple times using a target optimization algorithm, and the wear amount is obtained after each adjustment of the design parameters. Extract the minimum value among multiple wear amounts after adjusting the design parameters, and extract the adjusted design parameters corresponding to the minimum wear amount to obtain the updated design parameters.

8. A device for determining the parameters of a bearing bush, characterized in that, include: The first acquisition unit is used to acquire the design parameters of the bearing bush, wherein the design parameters include at least one or more of the radius of curvature, the oil film thickness of the lubricating oil, the oil film pressure, and the viscosity of the lubricating oil; The second acquisition unit is used to acquire the wear amount of the bearing bush, wherein the wear amount is the amount of material loss of the bearing bush due to friction. The first determining unit is used to perform optimization using a target optimization algorithm to adjust the design parameters until the wear amount reaches the minimum wear amount, and obtain updated design parameters, wherein the updated design parameters are used to construct the bearing bush; The second acquisition unit includes an acquisition module, a first calculation module, a second calculation module, and a third calculation module. The acquisition module is used to acquire the wear coefficient, contact pressure, and relative velocity, wherein the wear coefficient is a predefined coefficient of the wear resistance of the bearing material, the contact pressure is the pressure value at the contact position between the bearing and the journal, and the relative velocity is the relative velocity between the bearing and the journal. The first calculation module is used to calculate the product of the wear coefficient and the contact pressure to obtain a first value. The second calculation module is used to calculate the derivative of the relative velocity to obtain a second value. The third calculation module is used to calculate the product of the first value and the second value to obtain the wear amount.

9. A parameter determination system for bearing bushes, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a method for performing a bearing parameter determination method according to any one of claims 1 to 7.

Images