Rotor assembly process axial thrust control method and system based on digital twinning

Abstract

This application discloses an axial thrust control method and system for rotor assembly processes based on digital twins, relating to the field of rotor assembly technology. The method includes: constructing a target simulation model based on the geometric parameters and process parameter set corresponding to the rotor assembly interface; inputting the acquired assembly process parameters into the target simulation model to obtain first simulation data; performing dimensionality reduction processing on the target simulation model based on the first simulation data to obtain a target reduced-order model; determining the axial friction force between the impeller and the main shaft based on the target reduced-order model and the temperature distribution of the impeller outer ring obtained from the rotor assembly production line; determining the axial thrust of the impeller based on the axial friction force; and performing rotor assembly operations according to the axial thrust of the impeller. This application embodiment can achieve precise control of the impeller axial thrust, thereby reducing the occurrence of axial clearance between the impeller and the positioning spacer.

Description

Technical Field

[0001] This application relates to the field of rotor assembly technology, and in particular to an axial thrust control method and system for rotor assembly process based on digital twins. Background Technology

[0002] Rotor assembly, as a core and key process in the manufacturing of heavy rotating machinery, involves heating the impeller inside the rotor to a predetermined temperature, causing the inner hole of the impeller to expand, and then fitting it onto the main shaft and tightly fitting it with the positioning spacer sleeve fitted on the main shaft. After the impeller cools and shrinks naturally, the radial clamping force generated achieves a tight connection with the main shaft.

[0003] However, during the cooling and shrinking process of the impeller, both the radial and axial dimensions of the impeller will decrease, resulting in the impeller shrinking back along the axial direction. This will cause an axial gap between the impeller and the positioning spacer, which in turn will affect the critical speed and operating stability of the rotor. Summary of the Invention

[0004] In view of this, the embodiments of this application provide an axial thrust control method and system for rotor assembly process based on digital twin, which can achieve precise control of impeller axial thrust, reduce axial clearance between impeller and positioning spacer, and improve rotor critical speed and operational stability.

[0005] In a first aspect, this application provides an axial thrust control method for a rotor assembly process based on digital twins, comprising: The temperature distribution of the outer ring of the inner impeller of the rotor is obtained from the rotor assembly line; Based on the temperature distribution of the impeller outer ring and the target reduced-order model, the axial friction force between the impeller and the inner main shaft of the rotor is determined; whereby the target reduced-order model is obtained by dimensionality reduction of the target simulation model, and the target simulation model is constructed based on the set of process parameters and the geometric parameters corresponding to the rotor assembly interface; The axial thrust of the impeller is determined based on the axial friction force, and the rotor assembly operation is carried out according to the axial thrust of the impeller.

[0006] Secondly, this application provides an axial thrust control system, including: the axial thrust control system includes a friction calculation module, a thrust calculation module, and a rotor assembly module; The friction calculation module is used to determine the axial friction force between the impeller and the rotor's inner main shaft based on the target reduced-order model and the temperature distribution of the outer ring of the impeller obtained from the rotor assembly line. The target reduced-order model is obtained by reducing the dimensionality of the target simulation model, which is constructed based on the set of process parameters and the geometric parameters corresponding to the rotor assembly interface. The thrust calculation module is used to determine the axial thrust of the impeller based on the axial friction force. The rotor assembly module is used to perform rotor assembly operations according to the axial thrust of the impeller.

[0007] By employing the above technical solutions, this application provides an axial thrust control method and system for rotor assembly processes based on digital twins. When the temperature distribution of the outer ring of the impeller is obtained from the rotor assembly line, the axial friction force between the impeller and the rotor's inner main shaft can be determined based on this temperature distribution and a target reduced-order model. The axial thrust of the impeller is then determined using this axial friction force, and rotor assembly operations are performed based on this axial thrust. This allows for accurate calculation of the axial thrust based on the temperature distribution under actual assembly conditions, providing a scientific and precise quantitative basis for rotor assembly operations. This significantly improves the accuracy and rationality of rotor assembly, reduces axial clearance between the impeller and the positioning spacer, and enhances the rotor's critical speed and operational stability.

[0008] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0009] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This paper shows a schematic diagram of the structure of an axial thrust control system provided in an embodiment of this application; Figure 2 The diagram shows a flowchart of an axial thrust control method for a rotor assembly process based on digital twins, as provided in an embodiment of this application. Detailed Implementation

[0010] To facilitate the explanation of the embodiments of this application, some technical terms and technical means related to the embodiments of this application, as well as the application scenarios of the embodiments of this application, will be introduced first below.

[0011] As the core component of various rotating machinery, the rotor's assembly precision directly determines the equipment's operational stability, transmission efficiency, operating noise, and service life. The selection and control of assembly parameters are key factors affecting rotor assembly precision. However, in the manufacturing of rotors for heavy rotating machinery such as large compressors and blowers, the connection between the rotor's internal impeller and the main shaft commonly employs a hot-fit interference fit process. This process heats the impeller to a predetermined temperature, causing the impeller's inner bore to expand. It is then fitted onto the main shaft and tightly fitted with a positioning spacer. After the impeller naturally cools and contracts, the resulting radial clamping force achieves a secure connection with the main shaft.

[0012] However, during the impeller's cooling and shrinking process, not only does the impeller's radial dimension decrease, generating a clamping force, but its axial dimension also decreases simultaneously. This means that even if the heated impeller is tightly fitted against the positioning sleeve on the main shaft, axial retraction can still occur during cooling and shrinking, resulting in an axial gap between the impeller and the positioning sleeve. Furthermore, altering this axial gap compromises the rotor's rigid structure, potentially causing fretting wear, dynamic imbalance, and other abnormalities during high-speed rotation. This negatively impacts the rotor's critical speed and operational stability, ultimately reducing the quality of heavy-duty rotating machinery.

[0013] In some cases, to reduce the possibility of axial clearance between the impeller and the locating sleeve, an empirical impeller over-pushing method is often used. This involves applying an estimated additional axial force during rotor assembly to compensate for cooling contraction. However, this impeller over-pushing method has low assembly accuracy and relies heavily on the operator's assembly experience. If the additional axial force is too small, the axial clearance may not be eliminated, potentially damaging the rotor's rigid structure. If the additional axial force is too large, it may cause localized plastic deformation of the impeller or main shaft, or even damage the equipment.

[0014] Therefore, in order to achieve precise control of the impeller axial thrust and reduce axial clearance between the impeller and the positioning spacer, thereby improving the rotor's critical speed and operational stability, this application provides an axial thrust control method for the rotor assembly process based on digital twins, applicable to rotor assembly scenarios of any heavy rotating machinery. In this method, the temperature distribution of the outer ring of the impeller inside the rotor is obtained from the rotor assembly production line. Then, based on the temperature distribution of the impeller outer ring and the target reduced-order model, the axial friction force between the impeller and the rotor's inner main shaft is determined. The target reduced-order model is obtained by dimensionality reduction of the target simulation model, which is constructed based on a set of process parameters and the geometric parameters corresponding to the rotor assembly interface. Finally, based on the axial friction force, the axial thrust of the impeller is determined, and the rotor assembly operation is performed according to the impeller's axial thrust.

[0015] In this embodiment, when the temperature distribution of the outer ring of the impeller is obtained from the rotor assembly line, the axial friction force between the impeller and the inner main shaft of the rotor can be determined based on the temperature distribution of the outer ring and the target reduced-order model. The axial thrust of the impeller can then be determined using this axial friction force, and the rotor assembly operation can be carried out based on this axial thrust. This allows for accurate calculation of the axial thrust based on the temperature distribution under actual assembly conditions, providing a scientific and precise quantitative basis for the rotor assembly operation. This significantly improves the accuracy and rationality of rotor assembly, reduces axial clearance between the impeller and the positioning spacer, and enhances the rotor's critical speed and operational stability.

[0016] Furthermore, since the axial friction force between the impeller and the inner shaft of the rotor is based on the temperature distribution of the impeller's outer ring and a target reduced-order model, which is obtained by dimensionality reduction of the target simulation model, this approach simultaneously balances the efficiency of axial friction force calculation with the accuracy of simulation analysis. This aligns with the high-efficiency requirements of actual assembly on the production line, reduces assembly errors and equipment failures caused by unreasonable assembly thrust, and improves the overall quality of rotor assembly and production line efficiency.

[0017] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0018] like Figure 1 As shown in the figure, this application provides an axial thrust control system 100, including: a model building module 110, a friction calculation module 120, a thrust calculation module 130, and a rotor assembly module 140. The axial thrust control system 100 is built based on digital twin technology. This digital twin technology constructs a dynamic digital mirror of a physical entity in virtual space, and through real-time data synchronization, simulation analysis, and closed-loop control, achieves perception, prediction, and optimization of the physical entity throughout its entire lifecycle.

[0019] The aforementioned model building module 110 is used to construct the target simulation model. This target simulation model is a thermo-mechanical multi-physics coupled simulation model including the impeller, main shaft, and positioning spacer. In other words, it is a multi-physics coupled model encompassing heat conduction and structural mechanics, capable of simulating the entire rotor assembly process from impeller heating, impeller assembly, impeller force application, to impeller cooling. Furthermore, this target simulation model is constructed based on the geometric parameters and process parameters corresponding to the rotor assembly interface. This rotor assembly interface is used to connect the impeller and main shaft within the rotor. Geometric parameters may include the interface diameter and / or interface length. For example, the interface diameter may be 800 millimeters (mm), and the interface length may be 600 mm. The set of process parameters may include multiple sets of experimental process parameters. Each set of experimental process parameters may include at least the friction coefficient, initial assembly temperature, and assembly speed.

[0020] In some cases, the aforementioned model building module 110 is also used to perform dimensionality reduction processing on the target simulation model based on the first simulation data output by the target simulation model, thereby obtaining a target reduced-order model. That is to say, the target reduced-order model is the model obtained after dimensionality reduction processing of the target simulation model, which is used to determine the axial friction force between the impeller and the main shaft.

[0021] The aforementioned friction calculation module 120 is used to determine the axial friction force between the impeller and the rotor inner main shaft based on the target reduced-order model and the temperature distribution of the outer ring of the rotor inner impeller obtained from the rotor assembly line.

[0022] The aforementioned thrust calculation module 130 is used to determine the axial thrust of the impeller based on the axial friction force.

[0023] The rotor assembly module 140 described above is used for rotor assembly operations according to the axial thrust of the impeller. The rotor assembly module 140 may include a servo actuator and a thrust control unit. The servo actuator can be a servo electric cylinder or a hydraulic servo system, which is used to apply axial thrust to the impeller. The thrust control unit is used to adjust the axial thrust of the impeller based on the measured axial thrust of the impeller collected by the thrust sensor.

[0024] In some cases, the rotor assembly module 140 may further include a controller 141 and an industrial computer 142. The controller 141 can be a programmable logic controller (PLC) or an industrial controller, used to receive rotor assembly instructions sent by the industrial computer 142, and apply axial thrust to the impeller via a servo execution unit according to the rotor assembly instructions, thereby mounting the impeller onto the main shaft. The industrial computer 142 is used to receive the axial thrust of the impeller sent by the thrust calculation module 130, and execute assembly control decisions based on the axial thrust of the impeller, thereby generating rotor assembly instructions. In some embodiments of this application, the controller operates at a frequency of 1 kHz, and the industrial computer operates at a frequency of 10-200 Hz.

[0025] In some cases, the rotor assembly module 140 may also include multiple temperature sensors. These temperature sensors may be high-precision infrared temperature sensors. That is, the rotor assembly module 140 is also used to send the temperature distribution of the impeller outer ring collected by the temperature sensors to the friction calculation module 120, so that the friction calculation module 120 can calculate the axial friction force between the impeller and the inner main shaft of the rotor.

[0026] In one implementation, such as Figure 1 As shown, the axial thrust control system 100 can trigger the model building module 110 to perform dimensionality reduction processing on the target simulation model based on the first simulation data output by the target simulation model, thereby obtaining a target reduced-order model. Afterwards, the model building module 110 can execute step a, sending the target reduced-order model to the friction calculation module 120.

[0027] Simultaneously, the axial thrust control system 100 can trigger the temperature sensor included in the rotor assembly module 140 to collect temperature values, thereby obtaining the temperature distribution of the impeller outer ring. Then, the rotor assembly module 140 can execute step b, sending the temperature distribution of the impeller outer ring to the friction calculation module 120. Subsequently, upon receiving the target reduced-order model sent by the model building module 110 and the temperature distribution of the impeller outer ring sent by the rotor assembly module 140, the friction calculation module 120 determines the axial friction force between the impeller and the inner main shaft of the rotor based on the target reduced-order model and the temperature distribution of the outer ring.

[0028] Next, the friction calculation module 120 can execute step c, sending the axial friction force to the thrust calculation module 130. Then, upon receiving the axial friction force from the friction calculation module 120, the thrust calculation module 130 determines the axial thrust of the impeller based on that axial friction force. Next, the thrust calculation module 130 can execute step d, sending the axial thrust of the impeller to the industrial computer 142 included in the rotor assembly module 140. Then, upon receiving the axial thrust of the impeller from the thrust calculation module 130, the industrial computer 142 executes assembly control decisions based on the axial thrust of the impeller, generating rotor assembly instructions. Then, the industrial computer 142 can execute step e, sending the rotor assembly instructions to the controller 141 included in the rotor assembly module 140. Then, upon receiving the rotor assembly instructions from the industrial computer 142, the controller 141 applies axial thrust to the impeller via a servo execution unit to mount the impeller onto the main shaft.

[0029] Furthermore, an axial thrust control method for a rotor assembly process based on digital twins is provided in the embodiments, such as... Figure 2 As shown, the method includes: S201, obtain the temperature distribution of the outer ring of the inner impeller of the rotor from the rotor assembly line.

[0030] It is understood that the rotor assembly line is equipped with multiple temperature sensors, all located circumferentially on the outer ring of the impeller. These temperature sensors can be high-precision infrared temperature sensors. In other words, the temperature distribution around the impeller's outer ring can be determined by the temperature values ​​collected from these sensors.

[0031] S202, based on the temperature distribution of the impeller outer ring and the target reduced-order model, determine the axial friction force between the impeller and the inner main shaft of the rotor.

[0032] Specifically, after obtaining the temperature distribution of the impeller outer ring, the axial friction force between the impeller and the main shaft can be determined based on this temperature distribution and the target reduced-order model. Thus, calculating the axial friction force using the target reduced-order model significantly reduces the solution cost of high-order simulation models while ensuring rotor assembly accuracy, achieving millisecond-level rapid solution of the field distribution, and providing a foundation for subsequent rapid adjustment of the axial thrust.

[0033] In one implementation, the process of determining the aforementioned target reduced-order model may specifically include: acquiring assembly process parameters. These assembly process parameters include at least the friction coefficient, initial assembly temperature, and assembly speed. Then, these assembly process parameters are input into the target simulation model to obtain first simulation data. This first simulation data may include the impeller outer ring temperature, the contact area between the impeller inner diameter and the main shaft outer diameter, and the axial friction force between the impeller and the main shaft.

[0034] In some cases, the aforementioned first simulation data may also include the temperature distribution of the impeller inner ring, the deformation field of the impeller during thermal expansion, the deformation field of the impeller during cooling and contraction, and the contact pressure field between the impeller inner diameter and the main shaft outer diameter.

[0035] The aforementioned target simulation model is constructed based on a set of process parameters and the corresponding geometric parameters of the rotor assembly interface. This set of process parameters may include multiple sets of experimental process parameters. Each set of experimental process parameters includes at least the friction coefficient, initial assembly temperature, and assembly speed. The rotor assembly interface is used to connect the impeller and the main shaft. The geometric parameters may include the interface diameter and / or interface length. For example, the interface diameter may be 800 mm, and the interface length may be 600 mm.

[0036] Specifically, the training process of the aforementioned target simulation model may include: acquiring a set of process parameters; then, for each set of experimental process parameters included in the process parameter set, inputting the experimental process parameters into the initial simulation model to obtain the second simulation data. The initial simulation model is a finite element simulation model constructed based on the geometric parameters corresponding to the rotor assembly interface. The second simulation data may include the contact area between the impeller inner diameter and the main shaft outer diameter, impeller temperature change, main shaft temperature change, impeller deformation, and main shaft deformation. Finally, if the root mean square error (RMSE) of the second simulation data is less than a preset error, the target simulation model is obtained.

[0037] Furthermore, after obtaining the aforementioned first simulation data, the target simulation model can be dimensionality-reduced based on this data to obtain a target reduced-order model. In other words, the target reduced-order model is obtained by dimensionality reduction of the target simulation model.

[0038] Specifically, the dimensionality reduction process of the aforementioned target simulation model may include: encoding the first simulation data using a time-series encoder to obtain the target simulation data; then training a pre-constructed neural operator based on the target simulation data to obtain the target neural operator. This neural operator can learn the mapping relationship of physical fields and can be a DeepONet, a Fourier Neural Operator (FNO), etc. Finally, based on the target neural operator, the target simulation model is dimensionality reduced to obtain an initial reduced-order model.

[0039] Subsequently, using impeller temperature data obtained from the rotor assembly line, the initial reduced-order model was modified to obtain the target reduced-order model. In other words, this target reduced-order model replaced the time-consuming finite element simulation model, realizing a digital twin of the physical process. This not only reduces the computational complexity of the model, enabling a response speed at the millisecond or micrometer level, providing the necessary conditions for rapid determination of axial thrust, but also allows the model to accurately match actual working conditions, improving its predictive ability and providing the necessary conditions for accurate determination of axial thrust.

[0040] Specifically, after obtaining the target reduced-order model, the temperature distribution of the impeller outer ring can be input into the target reduced-order model to obtain the contact pressure field between the impeller inner diameter and the main shaft outer diameter. Then, based on this contact pressure field and the friction coefficient included in the assembly process parameters, the axial friction force between the impeller and the main shaft is obtained.

[0041] S203, determine the axial thrust of the impeller based on the axial friction force, and perform rotor assembly operation according to the axial thrust of the impeller.

[0042] Specifically, after obtaining the axial frictional force between the impeller and the main shaft, the axial thrust of the impeller can be determined based on this axial frictional force.

[0043] In one implementation, the axial thrust of the impeller described above can be calculated using the following expression: Expression 1; in, The axial thrust of the impeller Axial friction force The preset thrust margin can be set in advance according to actual conditions. In some embodiments of this application, the preset thrust margin can be 0. In other embodiments, the preset thrust margin can also be other values, and there is no specific limitation.

[0044] In some cases, before determining the axial thrust of the impeller, it can be determined whether the axial friction force is less than the target axial thrust. This target axial thrust is the maximum axial thrust that the servo actuator can apply. The axial thrust of the impeller is only determined based on the axial friction force if it is less than the target axial thrust. If the axial friction force is greater than or equal to the target axial thrust, the target axial thrust is used as the impeller's axial thrust, and the rotor assembly operation continues according to this target axial thrust. This effectively avoids problems such as thrust determination failure and abnormal execution due to axial friction exceeding the thrust limit of the servo actuator, ensuring the rationality and feasibility of the impeller axial thrust determination process. It also ensures that subsequent operations based on this axial thrust match the performance of the servo actuator, improving the stability and reliability of the rotor assembly process.

[0045] Furthermore, after determining the axial thrust of the impeller, the rotor assembly operation can be performed according to the axial thrust of the impeller. The rotor assembly operation involves fitting the impeller onto the main shaft.

[0046] During rotor assembly based on the impeller's axial thrust, the measured axial thrust of the impeller can be obtained from the rotor assembly line. This line is equipped with a thrust sensor to collect the measured thrust value. In other words, the measured axial thrust of the impeller can be determined from the thrust value collected by the sensor. Then, based on the measured axial thrust, the impeller's axial thrust is adjusted, and the rotor assembly is performed according to the adjusted thrust. This allows for dynamic adjustment of the axial thrust, ensuring that the impeller remains in close contact with the positioning sleeve during cooling and contraction, reducing the possibility of axial clearance between the impeller and the positioning sleeve, and improving rotor assembly quality and rotor stiffness.

[0047] This application also provides a computer device, specifically a personal computer, server, network device, etc. The computer device includes a bus, processor, memory, and communication interface, and may also include input / output interfaces and a display device. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores location information. The network interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the various method embodiments.

[0048] Those skilled in the art will understand that the structure of the computer device described above is only a partial structure related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. A specific computer device may include more or fewer components, or combine certain components, or have different component arrangements.

[0049] In one embodiment, a computer-readable storage medium is provided, which may be non-volatile or volatile, having stored thereon a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0050] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0051] It should be noted that the user personal information involved in the embodiments of this application is all authorized (with the knowledge and consent) by the relevant parties or fully authorized by all parties, and the executing entity can obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with the relevant laws and regulations of the relevant countries and regions, and do not violate public order and good morals. It should be noted that if any software tools or components other than those of this company appear in the embodiments of this application, they are merely illustrative examples and do not represent actual use.

[0052] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0053] 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.

[0054] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An axial thrust control method for rotor assembly process based on digital twin, characterized in that, include: The temperature distribution of the outer ring of the inner impeller of the rotor is obtained from the rotor assembly line; Based on the temperature distribution of the outer ring of the impeller and the target reduced-order model, the axial friction force between the impeller and the inner main shaft of the rotor is determined; wherein, the target reduced-order model is obtained by dimensionality reduction of the target simulation model, and the target simulation model is constructed based on the set of process parameters and the geometric parameters corresponding to the rotor assembly interface; The axial thrust of the impeller is determined based on the axial friction force, and the rotor assembly operation is performed according to the axial thrust of the impeller.

2. The method according to claim 1, characterized in that, The axial thrust of the impeller is calculated using the following expression: Expression 1; Among them, the The axial thrust of the impeller, the The axial friction force, the This is the preset thrust margin.

3. The method according to claim 1, characterized in that, The method further includes: The assembly process parameters are obtained and input into the target simulation model to obtain the first simulation data; wherein, the first simulation data includes the impeller outer ring temperature, the contact area between the impeller inner diameter and the main shaft outer diameter, and the axial friction force between the impeller and the main shaft; Based on the first simulation data, the target simulation model is subjected to dimensionality reduction processing to obtain the target reduced-order model.

4. The method according to claim 3, characterized in that, The step of performing dimensionality reduction processing on the target simulation model based on the first simulation data to obtain the target reduced-order model includes: The first simulation data is encoded using a timing encoder to obtain the target simulation data; Based on the target simulation data, the pre-constructed neural operator is trained to obtain the target neural operator; Based on the target neural operator, the target simulation model is subjected to dimensionality reduction processing to obtain an initial reduced-order model; The initial reduced-order model is corrected using the impeller temperature data obtained from the rotor assembly line to obtain the target reduced-order model.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Obtain a set of process parameters; wherein, the set of process parameters includes multiple sets of experimental process parameters, and the experimental process parameters include at least the friction coefficient, the initial assembly temperature, and the assembly speed; For each set of experimental process parameters, the experimental process parameters are input into the initial simulation model to obtain the second simulation data; wherein, the initial simulation model is constructed based on the geometric parameters corresponding to the rotor assembly interface; The target simulation model is obtained when the root mean square error of the second simulation data is less than the preset error.

6. The method according to any one of claims 1-4, characterized in that, The step of determining the axial thrust of the impeller based on the axial friction force and performing rotor assembly operations according to the axial thrust of the impeller includes: Determine whether the axial friction force is less than the target axial thrust; When the axial friction force is less than the target axial thrust, the axial thrust of the impeller is determined based on the axial friction force, and the rotor assembly operation is performed according to the axial thrust of the impeller.

7. The method according to claim 6, characterized in that, The method further includes: When the axial friction force is greater than or equal to the target axial thrust, the target axial thrust is used as the axial thrust of the impeller, and the rotor assembly operation is performed according to the axial thrust of the impeller.

8. The method according to any one of claims 1-4, characterized in that, The method further includes: The measured axial thrust of the impeller is obtained from the rotor assembly line. Based on the measured axial thrust of the impeller, the axial thrust of the impeller is adjusted, and the rotor assembly operation is performed according to the adjusted axial thrust.

9. An axial thrust control system, characterized in that, The axial thrust control system includes a friction calculation module, a thrust calculation module, and a rotor assembly module; The friction force calculation module is used to determine the axial friction force between the impeller and the main shaft of the rotor based on the target reduced-order model and the temperature distribution of the outer ring of the impeller inside the rotor obtained from the rotor assembly line; wherein, the target reduced-order model is obtained by dimensionality reduction of the target simulation model, and the target simulation model is constructed based on the set of process parameters and the geometric parameters corresponding to the rotor assembly interface; The thrust calculation module is used to determine the axial thrust of the impeller based on the axial friction force. The rotor assembly module is used to perform rotor assembly operations according to the axial thrust of the impeller.

10. The system according to claim 9, characterized in that, The axial thrust control system also includes a model building module; The model building module is used to perform dimensionality reduction processing on the target simulation model based on the first simulation data output by the target simulation model, thereby obtaining the target reduced-dimensional model.

Images