Compressor rotor hot-charging system and method based on online monitoring of multi-source data

Abstract

This application discloses a compressor rotor hot-fitting system and method based on multi-source data online monitoring, relating to the fields of precision mechanical assembly and intelligent manufacturing technology. The system includes: a multi-source heterogeneous sensor network, a data processing unit, and a digital twin controller. The multi-source heterogeneous sensor network is used to acquire multi-source acquisition data corresponding to the compressor rotor using different sensors configured on the compressor rotor. The data processing unit is used to identify the hot-fitting process stage of the compressor rotor based on the multi-source acquisition data, generate acquisition control commands corresponding to the hot-fitting process stage, acquire rotor monitoring data corresponding to the acquisition control commands, and send the rotor monitoring data to the digital twin controller. The digital twin controller is used to map the rotor assembly panorama of the compressor rotor throughout the entire hot-fitting process based on the rotor monitoring data, and adjust the compressor rotor hot-fitting process based on the rotor assembly panorama.

Description

Technical Field

[0001] This application relates to the field of precision mechanical assembly and intelligent manufacturing technology, and in particular to a compressor rotor hot mounting system and method based on online monitoring of multi-source data. Background Technology

[0002] The compressor rotor is the core high-speed rotating component of various compressors, including centrifugal and screw compressors. The quality of the connection between the rotor and the main shaft, formed by the interference fit, is one of the most critical factors determining the vibration, noise, efficiency, and long-term operational reliability of the entire machine. Hot fitting is a common assembly process for achieving high-precision, high-strength interference fits. Specifically, the rotor is precisely heated, causing a predetermined amount of thermal expansion in its inner bore. The room-temperature main shaft is then installed, and after the rotor cools and contracts, an interference fit connection with enormous clamping force is formed. The physical mechanism of the compressor rotor hot fitting process is complex, involving the strong coupling and dynamic evolution of multiple physical quantities, including transient non-uniform temperature fields, the resulting thermal stress / strain fields, precision axial displacement, and pressing force. Some key parameters affecting assembly quality cannot be directly measured.

[0003] Currently, the relevant technologies mainly rely on the operator's experience and destructive or non-destructive testing after assembly to control the hot assembly process of the compressor rotor, such as ultrasonic testing and coordinate measuring machine. However, the assembly quality achieved in this way cannot be guaranteed, which seriously affects the service performance of the compressor. Summary of the Invention

[0004] In view of this, this application provides a compressor rotor hot-fitting system and method based on online monitoring of multi-source data. It is mainly used to solve the technical problem that related technologies mainly rely on the experience of operators and destructive or non-destructive testing after assembly to control the compressor rotor hot-fitting process, which makes it impossible to guarantee the assembly quality and thus seriously affects the service performance of the compressor.

[0005] According to a first aspect of this application, a compressor rotor hot-fitting system based on multi-source data online monitoring is provided, comprising: a multi-source heterogeneous sensor network, a data processing unit, and a digital twin controller; A multi-source heterogeneous sensor network is used to acquire multi-source data corresponding to the compressor rotor by utilizing different sensors configured on the compressor rotor. The data processing unit is used to identify the hot-loading process stage of the compressor rotor based on multi-source acquired data, generate acquisition control commands corresponding to the hot-loading process stage, acquire rotor monitoring data corresponding to the acquisition control commands, and send the rotor monitoring data to the digital twin controller; the acquisition control commands are used to control the acquisition strategies of different sensors in the multi-source heterogeneous sensor network. The digital twin controller is used to map the entire rotor assembly panorama of the compressor rotor during the hot-loading process based on rotor monitoring data, and adjust the hot-loading process of the compressor rotor based on the rotor assembly panorama.

[0006] According to a second aspect of this application, a method for hot-fitting a compressor rotor based on online monitoring of multi-source data is provided. The method is applied to the aforementioned compressor rotor hot-fitting system based on online monitoring of multi-source data, and includes: By utilizing different sensors configured on the compressor rotor, multi-source acquisition data corresponding to the compressor rotor is obtained; Based on multi-source acquired data, the hot-fitting process stage of the compressor rotor is identified, and acquisition control commands corresponding to the hot-fitting process stage are generated. The acquisition control commands are used to control the acquisition strategies of different sensors in the multi-source heterogeneous sensor network. Acquire rotor monitoring data corresponding to the acquisition control commands; Based on rotor monitoring data, the rotor assembly panorama of the compressor rotor is mapped throughout the entire hot-loading process, and the hot-loading process of the compressor rotor is adjusted based on the rotor assembly panorama.

[0007] According to a third aspect of this application, a compressor rotor heat-fitting device based on multi-source data online monitoring is provided, comprising: The acquisition module is used to acquire multi-source data corresponding to the compressor rotor using different sensors configured on the compressor rotor; based on the multi-source data, it identifies the hot-fitting process stage of the compressor rotor, generates acquisition control commands corresponding to the hot-fitting process stage, and uses the acquisition control commands to control the acquisition strategies of different sensors in the multi-source heterogeneous sensor network; and acquires the rotor monitoring data corresponding to the acquisition control commands. The adjustment module is used to map the rotor assembly panorama of the compressor rotor throughout the entire hot-loading process based on rotor monitoring data, and adjust the hot-loading process of the compressor rotor based on the rotor assembly panorama.

[0008] According to a fourth aspect of this application, a storage medium is provided on which a computer program is stored, which, when executed by a processor, implements the above-described method for hot mounting of a compressor rotor based on online monitoring of multi-source data.

[0009] According to a fifth aspect of this application, an electronic device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-described method for hot mounting of a compressor rotor based on online monitoring of multi-source data.

[0010] Using the above technical solution, this application provides a compressor rotor hot-fitting system and method based on multi-source data online monitoring. The system includes a multi-source heterogeneous sensor network for acquiring multi-source data corresponding to the compressor rotor using different sensors configured on the compressor rotor; a data processing unit for identifying the hot-fitting process stage of the compressor rotor based on the multi-source data, generating acquisition control commands corresponding to the hot-fitting process stage, acquiring rotor monitoring data corresponding to the acquisition control commands, and sending the rotor monitoring data to a digital twin controller; the acquisition control commands are used to control the acquisition strategies of different sensors in the multi-source heterogeneous sensor network; and the digital twin controller is used to map the entire rotor assembly panorama of the compressor rotor throughout the hot-fitting process based on the rotor monitoring data, and adjust the compressor rotor hot-fitting process based on the rotor assembly panorama. This application can identify multi-source acquisition data corresponding to the compressor rotor collected in real time by a multi-source heterogeneous sensor network, determine the current compressor rotor hot-fitting process stage, and adaptively adjust the acquisition strategies of different sensors in the multi-source heterogeneous sensor network according to the acquisition control commands corresponding to the hot-fitting process stage. This allows for data acquisition in conjunction with the hot-fitting process stage. Finally, based on the adaptively acquired rotor monitoring data, more key parameters affecting assembly quality are collected, and the entire rotor assembly panorama of the compressor rotor during the hot-fitting process is mapped. The hot-fitting process of the compressor rotor is adjusted in real time, realizing real-time rotor detection and process adjustment during the execution of the hot-fitting process. This eliminates the need to rely on operator experience for inspection after assembly, thus ensuring assembly quality and, consequently, the service performance of the compressor.

[0011] 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

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This illustration shows a structural schematic diagram of a compressor rotor hot-fitting system based on online monitoring of multi-source data, according to an embodiment of this application. Figure 2This illustration shows a schematic diagram of an example of a hot-charging process stage provided in an embodiment of this application; Figure 3 This illustration shows a schematic diagram of an example distributed thermocouple array arrangement provided in an embodiment of this application; Figure 4 This illustration shows a schematic diagram of an example of an online monitoring process for multi-source data provided in an embodiment of this application; Figure 5 A schematic flowchart of a compressor rotor thermal mounting method based on online monitoring of multi-source data provided in an embodiment of this application is shown. Figure 6 A schematic diagram of a compressor rotor heat-fitting device based on online monitoring of multi-source data is shown in an embodiment of this application. Detailed Implementation

[0015] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0016] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0017] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0018] To better understand the above-mentioned objectives, features, and advantages of this application, the solution of this application will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0019] To address the current industry practice where controlling the hot-fitting process of compressor rotors relies primarily on operator experience and subsequent destructive or non-destructive testing, assembly quality cannot be guaranteed, thus severely impacting compressor performance. This application provides a compressor rotor hot-fitting system and method based on multi-source data online monitoring.

[0020] like Figure 1 As shown, an embodiment of this application provides a compressor rotor hot-fitting system based on multi-source data online monitoring. The system includes: a multi-source heterogeneous sensor network 11, a data processing unit 12, and a digital twin controller 13. The multi-source heterogeneous sensor network 11 is used to acquire multi-source acquisition data corresponding to the compressor rotor using different sensors configured on the compressor rotor. The data processing unit 12 is used to identify the hot-fitting process stage of the compressor rotor based on the multi-source acquisition data, generate acquisition control commands corresponding to the hot-fitting process stage, acquire rotor monitoring data corresponding to the acquisition control commands, and send the rotor monitoring data to the digital twin controller 13. The acquisition control commands are used to control the acquisition strategies of different sensors in the multi-source heterogeneous sensor network 11. The digital twin controller 13 is used to map the rotor assembly panorama of the compressor rotor throughout the entire hot-fitting process based on the rotor monitoring data, and adjust the compressor rotor hot-fitting process based on the rotor assembly panorama.

[0021] In some embodiments, the multi-source heterogeneous sensor network 11 can be a data acquisition network composed of various types and operating modes of sensors configured on the compressor rotor to detect full-dimensional data of the rotor thermal assembly, such as sensors used to measure temperature, pressure, displacement, etc. The sensor types, communication methods, sampling frequencies, and data formats (such as analog signals and digital pulses) can be different. The various sensors in the multi-source heterogeneous sensor network 11 can be networked through an industrial bus or hardware interface to be uniformly scheduled and synchronously acquire multi-source acquisition data of the compressor rotor.

[0022] Correspondingly, the data processing unit 12 can be used to identify the multi-source data initially collected by the multi-source heterogeneous sensor network 11, determine the current hot-fitting process stage of the rotor, such as initial heating, uniform temperature preservation, and press assembly, and adopt different acquisition strategies for different hot-fitting process stages. It can generate acquisition control commands corresponding to the hot-fitting process stage to control different sensors in the multi-source heterogeneous sensor network 11 to adaptively adjust and collect data according to the acquisition strategy corresponding to the acquisition control command. This allows different sensors to collect data specifically at different process stages, reducing the possibility of missing key data affecting assembly quality and thus ensuring assembly quality. For example, after the data processing unit 12 determines that the hot-fitting process stage has changed, it can generate acquisition control commands corresponding to the hot-fitting process stage. Different sensors can synchronously receive the acquisition control commands and then adjust their acquisition strategies according to the commands to re-collect rotor monitoring data.

[0023] Specifically, in the compressor rotor hot-fitting process, the data processing unit 12 analyzes initial temperature data in real time according to a preset process schedule, such as temperature rise rate and uniformity, and automatically identifies the current hot-fitting process stage. Based on the characteristics of different hot-fitting process stages, it dynamically issues acquisition control commands. Different sensors adaptively adjust according to these commands at different stages. Compared to a fixed-frequency data acquisition method, this embodiment can adapt to the differentiated requirements of data density and type at different hot-fitting process stages. For example, as... Figure 2 As shown, the hot-charging process stages and corresponding data acquisition and control commands are as follows: Heating stage: Increase the sampling rate of infrared thermal imager and all temperature sensors, such as to 500Hz, and focus on the temperature rise trend and gradient. High-frequency sampling can capture the temperature distribution and local hot spots of the rotor in real time, detect uneven heating or local overheating in time, avoid thermal shock deformation, and prepare for the uniform temperature and heat preservation stage. During the heat preservation stage: reduce the temperature sampling rate, such as to 10Hz. By monitoring temperature changes, the stress and shape changes of the impeller are mapped using digital twin control technology. When the temperature stabilizes, high-frequency sampling is no longer necessary. Reducing the sampling rate saves system resources while continuously monitoring temperature uniformity to ensure consistent temperature inside and outside the rotor, as well as top and bottom. During the press-fit assembly stage: A high-speed acquisition mode is triggered, such as a sampling rate of 1kHz, maximizing the sampling rates of the laser displacement sensor and piezoelectric sensor to simultaneously record the displacement-force curve; the infrared thermal imager can switch to a rapid scanning mode focusing on the press-fit contact area. The press-fit assembly stage is the critical moment when the rotor heat sleeve is pressed into the spindle, requiring microsecond-level synchronous acquisition of transient data such as temperature, pressing force, displacement, and thermal field of the contact area to determine assembly quality and support digital twin mapping. Cooling stage: The sampling rate can be adjusted to a medium frequency, such as 200Hz. Based on digital twin control technology, the displacement of the impeller during the contraction process is mapped. Medium frequency sampling can effectively monitor the temperature gradient and contraction rate during the cooling process, avoid residual stress or assembly deviation caused by uneven cooling, and balance the amount of data and system load.

[0024] In some embodiments, the digital twin controller 13 can be a digital twin software system running on an industrial computer or server, used to receive rotor monitoring data collected at different stages of the hot-fitting process, reconstruct the entire hot-fitting process of the rotor in virtual space, obtain a panoramic view of rotor assembly, and construct a digital twin data body of the entire process. By analyzing abnormal data in the panoramic view of rotor assembly, such as temperature unevenness and sudden changes in pressing force, the key control parameters of the compressor rotor, such as inner ring temperature gradient, thermal deformation compensation, contact stress assessment, heating temperature, holding time, and pressing speed, can be adjusted in real time. Process optimization instructions corresponding to the key control parameters can be generated, so that the compressor rotor is optimized according to the process optimization instructions. By comparing the real-time synchronous data of the physical rotor and the virtual rotor, the physical hot-fitting process can be optimized in real time to ensure the quality of rotor assembly.

[0025] Compared with related technologies, this embodiment can identify the multi-source acquisition data corresponding to the compressor rotor collected in real time by the multi-source heterogeneous sensor network 11, determine the current hot-fitting process stage of the compressor rotor, and adaptively adjust the acquisition strategies of different sensors in the multi-source heterogeneous sensor network 11 according to the acquisition control commands corresponding to the hot-fitting process stage. This allows for data acquisition in conjunction with the hot-fitting process stage. Finally, based on the adaptively acquired rotor monitoring data, more key parameters affecting assembly quality are collected, and the entire rotor assembly panorama of the compressor rotor during the hot-fitting process is mapped. The hot-fitting process of the compressor rotor is adjusted in real time, realizing real-time rotor detection and process adjustment during the execution of the hot-fitting process. This eliminates the need to rely on operator experience for detection after assembly, ensuring assembly quality and thus guaranteeing the service performance of the compressor. It can provide highly reliable, highly synchronous, and multi-dimensional perception of the entire hot-fitting process, enabling online evaluation and real-time intervention of the compressor rotor assembly quality, thereby ensuring the assembly quality pass rate.

[0026] Optionally, the multi-source heterogeneous sensor network 11 includes a pressure sensor, a laser displacement sensor, a distributed thermocouple array, and an infrared thermal imager. The pressure sensor is arranged at the contact position between the tooling platform and the impeller of the compressor rotor to measure the indentation force of the compressor rotor. The laser displacement sensor is arranged near the tooling platform of the compressor rotor, aligned with the rotor end face or the main shaft end face, to measure the axial indentation displacement of the compressor rotor. The distributed thermocouple array is arranged at the key parts of the impeller of the compressor rotor to measure the temperature of the key parts of the impeller, including the axial and radial parts of the impeller. The infrared thermal imager is arranged on the impeller of the compressor rotor to switch scanning modes according to the acquisition control command and detect the rotor thermal field data of the compressor rotor.

[0027] For example, the multi-source heterogeneous sensor network 11 may include: The temperature sensing section includes an infrared thermal imager for two-dimensional / three-dimensional temperature field monitoring, and a distributed thermocouple array located at key rotor positions (such as end faces and flanges) to monitor the two-dimensional / three-dimensional distribution of the temperature field within the rotor's internal bore or overall structure. Specifically, the distributed thermocouple array corresponds to multiple temperature measurement points such as... Figure 3 As shown, K-type thermocouples, surface mount platinum resistance thermometers, and other devices can be arranged at key locations on the front and back sides of the impeller, respectively. Displacement sensing section: A high-precision laser displacement sensor can be used near the tooling platform, aligned with the rotor end face or the spindle end face, to measure the axial indentation displacement; Force sensing component: Includes a high-precision pressure sensor (piezoelectric sensor) integrated at the front end of the tooling platform spindle, at the contact position between the tooling platform and the impeller corresponding to the compressor rotor, used to measure the indentation force.

[0028] Optionally, the distributed thermocouple array includes K-type thermocouples and patch platinum resistance thermometers. The K-type thermocouples and patch platinum resistance thermometers are arranged at the same measurement point on the rotor target assembly surface of the compressor rotor, forming a redundant sensing pair. The distance between the K-type thermocouples and the heat source is smaller than the distance between the patch platinum resistance thermometers and the heat source. The redundant sensing pair is used to perform redundant sensing measurements on the temperature of the rotor target assembly surface, detecting redundant data of the rotor target assembly surface at the same time. The redundant data includes the temperature measured by the K-type thermocouples and the temperature measured by the patch platinum resistance thermometers.

[0029] In some embodiments, redundant sensing can be used to measure key measurement points. For example, for the temperature of the rotor target assembly surface, a K-type thermocouple and a patch-type platinum resistance thermometer, or two force sensors of different manufacturers and models can be arranged at the key measurement points of the rotor target assembly surface to collect redundant data corresponding to the rotor target assembly surface, and then the collected redundant data is uploaded to the data processing unit 12.

[0030] Optionally, the data processing unit 12 can also be used to store the limit temperature difference of the acquisition points corresponding to redundant data in different hot-fitting process stages; to judge the validity of redundant data at different times in different hot-fitting process stages according to preset data invalidity conditions; if the redundant data is detected as invalid, it is re-acquired using redundant sensors; if the redundant data is detected as valid, the average value of the redundant data is determined as the effective temperature value of the rotor target assembly surface; the preset data invalidity conditions include at least one of the following: the temperature measured by the K-type thermocouple is lower than the temperature measured by the patch platinum resistance thermometer, and the difference in redundant data is greater than the limit temperature difference of the acquisition point.

[0031] Among them, the extreme temperature difference of the collection point is the maximum difference of redundant data corresponding to different collection points in different hot-filling process stages. It is used to judge the validity of the redundant data collected in real time, so as to meet the collection requirements of different hot-filling process stages and thus ensure the quality of hot-filling.

[0032] In some embodiments, the K-type thermocouple is closer to the heat source than the patch-type platinum resistance thermometer, so the temperature measured by the K-type thermocouple needs to be higher than the temperature measured by the platinum resistance thermometer. For example, if the temperature measured by the K-type thermocouple is detected to be lower than the temperature measured by the platinum resistance thermometer at a certain moment, or if the difference between the redundant data collected by the redundant sensors at a certain moment is greater than the limit temperature difference of the corresponding collection point at that moment, then the redundant data corresponding to that moment is determined to be invalid.

[0033] Correspondingly, once the redundant data is determined to be invalid, a re-acquisition command can be initiated in a very short time. If the redundant data still meets the preset invalid data conditions after re-acquisition, the redundant sensor pair is determined to be invalid, a fault alarm is generated, and it is downweighted or removed in subsequent data fusion. At the same time, soft compensation can be performed by relying on other related data.

[0034] Optionally, the preset invalid data condition may also include that the data change trend of redundant data does not conform to the preset change trend corresponding to the current hot-loading process stage; the data processing unit 12 may also be used to store the preset change trends of redundant data corresponding to different hot-loading process stages; determine the data change trend of redundant data based on the redundant data corresponding to multiple consecutive acquisition times; if the data change trend conforms to the preset change trend corresponding to the current hot-loading process stage, it can be determined as valid redundant data; if the data change trend does not conform to the preset change trend corresponding to the current hot-loading process stage, it will be determined as invalid redundant data.

[0035] Optionally, the system may also include a data acquisition unit 14; the data acquisition unit 14 is used to issue a global hardware trigger signal according to the hardware trigger logic, and send the global hardware trigger signal to the trigger ports of different sensors simultaneously, triggering different sensors to start acquiring data at the same physical moment. The global hardware trigger signal includes a Low Voltage Transistor-Transistor Logic (LVTTL) pulse signal; the data acquisition unit 14 includes a Field Programmable Gate Array (FPGA), which is responsible for executing high-speed, parallel deterministic tasks and generating the global hardware trigger signal; it receives and buffers the rotor monitoring data corresponding to different sensors, injects a high-precision timestamp into the rotor monitoring data, and stores it in the FPGA's First In First Out (FIFO) storage unit.

[0036] In some embodiments, the FPGA can also be used to manage the reading and writing of independent FIFO buffers for each channel.

[0037] Correspondingly, the output of the multi-source heterogeneous sensor network 11 can be connected to the input of the data acquisition unit 14, and the output of the data acquisition unit 14 can be connected to the input of the data processing unit 12. The multi-source heterogeneous sensor network 11 can uniformly use hardware rising edge triggering to start operation of all sensors at the same microsecond time point, ensuring the consistency of the timing of the entire system, thereby unifying the data timestamps of each sensor, aligning temperature, displacement and other data at strictly the same time, so as to accurately reproduce and analyze the dynamic process of multi-physics coupling.

[0038] For example, synchronous acquisition can be triggered by the rising edge of the LVTTL global hardware trigger pulse generated by the FPGA (a level transition from 0V to 3.3V).

[0039] Optionally, the system may also include a virtual sensor 15; the data processing unit 12 may include a system-on-chip (SoC); the SoC and FPGA are connected via a high-speed bus to read rotor monitoring data; the SoC communicates with the virtual sensor 15 and the digital twin controller 13 via an Ethernet interface to synchronously send rotor monitoring data to the virtual sensor 15 and the digital twin controller 13; the SoC is used to deploy a high-precision synchronous clock source to generate pulses per second (PPS), record clock offset and drift, provide a unified microsecond-level time reference for the data acquisition unit 14 and different sensors, and store rotor monitoring data according to the channel identifiers corresponding to different sensors.

[0040] The data processing unit 12 is responsible for complex algorithms and scheduling, running process stage identification software, and providing human-machine interaction and network communication interfaces. Its core can be a precision clock module supporting the IEEE 1588 protocol, generating PPS (Power, Speed, and Power) and synchronously transmitting rotor monitoring data to the virtual sensor 15 and the digital twin controller 13. Specifically, the data processing unit 12 can establish a high-precision synchronous clock reference based on a timing model and synchronization method, synchronously triggering the data acquisition unit 14 to acquire data from all sensors. After timestamp alignment and fusion of the multi-source acquired data, it is input into the virtual sensor 15 to calculate key control parameters.

[0041] For example, the SoC can activate a high-precision synchronous clock source, outputting 1 PPS per second, measuring and recording clock offset and drift in real time, and issuing a unified microsecond-level timestamp to all sensors and data acquisition units 14. It utilizes the FPGA to acquire multiple data streams in parallel and stores them in an independent FIFO. The SoC reads rotor monitoring data from the FPGA via the Advanced eXtensible Interface (AXI) high-speed bus and categorizes and stores data such as temperature, pressure, and displacement according to channel identifiers for subsequent traceability and analysis. The SoC can also assign a unique channel identifier to each sensor to categorize and store data from different sensors, such as: CH1 for end face thermocouples, CH2 for flange thermocouples, CH3 for pressure-fitting force sensors, and CH4 for axial displacement sensors.

[0042] This embodiment can ensure strict consistency of data in the time domain by using a parallel acquisition method that simultaneously collects multi-dimensional physical information such as impeller axial and radial temperature, hot mounting platform displacement, and pressure.

[0043] Optionally, the virtual sensor 15 is used to output key control parameters corresponding to the hot-fitting process based on rotor monitoring data and a verifiable error boundary reduction model, and send the key control parameters to the digital twin controller 13. The key control parameters include the inner loop temperature gradient, thermal deformation compensation amount, and contact stress evaluation value.

[0044] Optionally, the input terminal of the virtual sensor 15 can be connected to the first output terminal of the data processing unit 12; the output terminal of the virtual sensor 15 can be connected to the first input terminal of the digital twin controller 13.

[0045] In some embodiments, the virtual sensor 15 can be an algorithm model in software or an industrial control computer. Based on the rotor monitoring data of the physical sensor, it uses a proven error bound reduction model to calculate key control parameters that cannot be directly measured by the physical sensor, such as rotor thermal expansion, interference fit, temperature gradient, and coaxiality estimation. The key control parameters are then sent to the digital twin controller 13 to support process adjustment.

[0046] Among them, the provable error bound reduction model can be a simulation algorithm model constructed for the rotor hot fitting process. By reducing the cost, the core factors affecting the hot fitting quality are retained, while irrelevant factors are removed, to simulate the real physical process of rotor hot fitting. The inner ring temperature gradient is the rate of temperature change along the radial / axial direction of the rotor's inner hole, which directly reflects whether the rotor heating is uniform. Only when the inner ring temperature gradient is within a reasonable range (e.g., ≤2℃ / mm) can uniform expansion and accurate assembly be guaranteed. However, physical sensors can only measure surface temperature and cannot monitor the rate of temperature change. After the rotor is heated, it will undergo thermal deformation (expansion). To ensure assembly accuracy, it is necessary to pre-calculate the thermal deformation compensation amount to correct and control the pressing displacement and heating temperature, and avoid assembly deviations. After the rotor is press-fitted onto the spindle, the stress (unit: MPa) on the contact surface between the rotor and the spindle is the core parameter for judging whether the interference fit is qualified. If the contact stress is too small, the clamping force will be insufficient and slippage will occur during high-speed rotation. If the stress is too large, the inner hole of the rotor will crack and the spindle will deform. Therefore, the contact stress evaluation value can be calculated by the virtual sensor 15. The digital twin controller 13 can compare the contact stress evaluation value with the preset stress threshold (e.g., 500-800 MPa) to judge the assembly quality. If it is not qualified, the process will be adjusted.

[0047] Optionally, the digital twin controller 13 is also used to acquire rotor monitoring data through the data processing unit 12 and determine key control parameters based on the rotor monitoring data when the virtual sensor 15 fails.

[0048] Correspondingly, the second input terminal of the digital twin controller 13 can be connected to the second output terminal of the data processing unit 12. The output terminal of the virtual sensor 15 can be connected to the first terminal of the digital twin controller 13.

[0049] For example, if the virtual sensor 15 malfunctions, the digital twin controller 13 can directly receive the rotor monitoring data sent by the data processing unit 12, perform key control parameter calculations, and improve system reliability.

[0050] As one possible implementation method, such as Figure 4 As shown, the overall system execution flow may include the following steps: Sensor deployment: K-type thermocouples, pressure sensors, laser displacement sensors, infrared thermal imagers, etc. are deployed at key locations such as rotors and tooling platforms to construct a multi-source heterogeneous sensor network 11 to acquire multi-source data and provide a hardware foundation for data acquisition. System initialization and global spatiotemporal reference establishment: A high-precision synchronous clock source is deployed through the SoC to generate PPS second pulses, establish a unified microsecond-level time reference, ensure that the timestamps of all sensor data are aligned, and avoid timing errors; Adaptive acquisition task scheduling based on process status identification: The data processing unit 12 analyzes multi-source acquisition data in real time, identifies the current hot-charging process stage, dynamically adjusts the acquisition frequency and triggering conditions of each sensor, acquires rotor monitoring data, realizes stage-by-stage acquisition, and avoids resource waste. Synchronous trigger acquisition and differential redundancy verification of multi-source data: The LVTTL global hardware trigger pulse generated by the FPGA is used as a unified signal to synchronously trigger the acquisition of all sensors; redundancy verification is performed by comparing redundant data to eliminate abnormal data and ensure data accuracy. Multi-source data storage and transmission: The SoC classifies and stores rotor monitoring data according to channel identifiers, and transmits it through high-speed bus (FPGA-SoC) and Ethernet (SoC - Virtual Sensor 15 / Digital Twin Controller 13) to achieve orderly management and efficient flow of data; Edge layer output: The verified and processed rotor monitoring data and key control parameters calculated by the virtual sensor 15 are output to the digital twin controller 13 to construct a complete rotor assembly overview, adjust the hot fitting process in real time, and ultimately ensure assembly quality. The edge layer may include a multi-source heterogeneous sensor network 11, a data acquisition unit 14, a data processing unit 12, and a virtual sensor 15.

[0051] The modular design and flexible hardware platform based on FPGA+SoC of this embodiment enable it to be easily adapted to the hot-fitting requirements of compressor rotors of different models and sizes. It can be quickly ported by configuring different sensor combinations and process model parameters, realizing multi-dimensional panoramic real-time perception of the hot-fitting process. It provides data support for online quality assessment and real-time optimization of process parameters, significantly improving the consistency of assembly quality and first-pass yield. It has high real-time performance and strong scalability, and has broad application prospects.

[0052] Compared with related technologies, in this embodiment, the virtual sensor 15 can calculate key control parameters that cannot be directly measured by physical sensors using a proven error bound reduced-order model, and then send the key control parameters to the digital twin controller 13 to support process adjustments. When the virtual sensor 15 fails, the digital twin controller 13 can directly receive rotor monitoring data sent by the data processing unit 12, perform key control parameter calculations, and improve system reliability.

[0053] like Figure 5 As shown, embodiments of this application provide a method for hot-fitting a compressor rotor based on online monitoring of multi-source data. This method can be applied to the aforementioned compressor rotor hot-fitting system based on online monitoring of multi-source data. The method for hot-fitting a compressor rotor based on online monitoring of multi-source data may include: Step 101: Use different sensors configured on the compressor rotor to acquire multi-source acquisition data corresponding to the compressor rotor.

[0054] In some embodiments, the different sensors configured on the compressor rotor may include various types of sensors arranged at key locations such as the rotor and tooling platform to comprehensively monitor the rotor hot-fitting process. Based on these sensors, a multi-source heterogeneous sensor network can be constructed and uniformly scheduled through a data acquisition unit to collect multi-source data in real time, reflecting different dimensions of the rotor hot-fitting process. Through multi-dimensional and full-process perception, data support is provided for intelligent control and quality assessment of the hot-fitting process.

[0055] For example, temperature sensors can be placed at key axial and radial locations of the impeller to measure the temperature values ​​at these key locations and monitor key parameters (displacement, pressure, etc.) of the assembly platform in real time. This enables hardware-level synchronous parallel acquisition of multi-dimensional data such as temperature field, displacement, and pressure. By utilizing digital twin technology, a panoramic, high-fidelity digital mapping of the entire hot-fitting process can be formed, providing an unprecedented data foundation for process research, optimization, and fault tracing.

[0056] Step 102: Based on the multi-source acquired data, identify the hot-loading process stage of the compressor rotor and generate the acquisition and control commands corresponding to the hot-loading process stage.

[0057] Among them, the acquisition control commands are used to control the acquisition strategies of different sensors in a multi-source heterogeneous sensor network. The acquisition strategy refers to the specific operating rules of each sensor at different hot-mounting stages, such as sampling frequency, triggering conditions (e.g., global hardware triggering, timed triggering), operating mode (e.g., normal scanning, fast scanning, standby), and data output format.

[0058] Correspondingly, the hot-loading process stage can refer to the execution stage divided according to the process logic during the hot-loading of the compressor rotor. Each stage has different physical states and control objectives. Different acquisition and control commands can be generated for different stages to carry out adaptive data acquisition, avoid missing key data at different stages, optimize system resources, and ensure that high-value data is captured in the critical process window.

[0059] For example, if multi-source data collection indicates that the rotor temperature rises rapidly from 25°C to 180°C at a rate greater than 5°C / min, the hot fitting process stage can be identified as the initial heating stage; if the rotor temperature stabilizes at 180°C ± 1°C for more than 10 minutes with a temperature uniformity of ≤ ± 2°C, the hot fitting process stage can be identified as the temperature equalization and heat preservation stage; if the pressing force increases from 0 kN and the axial displacement increases from 0 mm, the hot fitting process stage can be identified as the pressing assembly stage; if the pressing force stabilizes at 35 kN, the displacement reaches 45 mm (target value), and the rotor temperature begins to decrease, the hot fitting process stage can be identified as the pressure holding and cooling stage; if the pressing force decreases to 0 kN and the rotor temperature slowly decreases to room temperature, the hot fitting process stage can be identified as the free cooling stage.

[0060] Correspondingly, during the initial heating stage, acquisition and control instructions corresponding to the initial heating stage can be generated. These acquisition and control instructions may include: increasing the initial thermocouple sampling rate to 1kHz, increasing the infrared thermal imager frame rate to 30Hz, and putting the pressure / displacement sensor into standby mode, thereby monitoring the heating rate and thermal field uniformity, while not acquiring pressure and displacement, thus saving resources.

[0061] By using adaptive acquisition scheduling driven by process stage identification, system resources are concentrated on critical process windows, maximizing the "value density" of data and significantly reducing the load of invalid data storage and processing while ensuring information integrity.

[0062] Step 103: Obtain the rotor monitoring data corresponding to the acquisition control command.

[0063] In some embodiments, rotor monitoring data can be matched with acquisition control commands for each sensor. After adaptively adjusting the acquisition strategy, the multi-channel monitoring data acquired in real time reflects the effective data set of the real-time status during the rotor hot-fitting process. These data can have a unified microsecond-level timestamp and channel identifier, serving as the core input for the digital twin controller to perform state mapping and process adjustment.

[0064] Step 104: Based on the rotor monitoring data, map the rotor assembly panorama of the compressor rotor throughout the entire hot-loading process, and adjust the hot-loading process of the compressor rotor based on the rotor assembly panorama.

[0065] In some embodiments, a digital twin controller can be used to synchronously map the real-time rotor monitoring data corresponding to the physical rotor into a virtual rotor model to obtain a panoramic view of rotor assembly. The mapping needs to cover the state changes and process parameters of the entire process to achieve real-time synchronization between the physical state and the virtual state. This is used to visualize the physical assembly process and identify anomalies, so that by analyzing the anomalies in the panoramic view, process optimization instructions can be issued in real time, the physical thermal assembly process can be dynamically adjusted, assembly defects can be avoided, and assembly quality can be guaranteed.

[0066] Among them, the rotor assembly panorama can be a digital mirror of the entire rotor hot assembly process constructed by the digital twin controller. As an interactive and analyzable visual panoramic view, the rotor assembly panorama can specifically include: the rotor 3D geometric model and real-time status, such as temperature cloud map, pressing force curve, displacement trajectory, contact stress distribution, etc.; process parameters, such as heating temperature, holding time, pressing speed, cooling rate, etc.; and comparison results of virtual and real states, etc.

[0067] Compared with related technologies, this embodiment can determine the current compressor rotor hot-fitting process stage based on the multi-source acquisition data corresponding to the real-time collected compressor rotor. According to the acquisition control command corresponding to the hot-fitting process stage, the acquisition strategy of different sensors is adaptively adjusted to combine data acquisition with the hot-fitting process stage. Finally, based on the adaptively acquired rotor monitoring data, the rotor assembly panorama of the compressor rotor in the entire hot-fitting process is mapped, and the compressor rotor hot-fitting process is adjusted in real time. This realizes real-time rotor detection and process adjustment during the execution of the hot-fitting process, eliminating the need to rely on operator experience for detection after assembly, thus ensuring assembly quality and thereby ensuring the service performance of the compressor.

[0068] Specifically, the method in this embodiment may also include: outputting key control parameters corresponding to the hot-fitting process based on rotor monitoring data and a verifiable error boundary reduction model. The key control parameters include the inner ring temperature gradient, thermal deformation compensation amount, and contact stress evaluation value.

[0069] In some embodiments, the inner ring temperature gradient, thermal deformation compensation, and contact stress cannot be directly obtained through conventional thermocouples and pressure sensors. By using a provable error bound reduced-order model, key control parameters can be calculated based on rotor monitoring data, and the calculation results corresponding to the key control parameters are strictly limited to a controllable range. The output parameters have engineering credibility and meet the industrial assembly accuracy requirements, so as to support online process control and meet the high-speed decision-making needs of the transient process during the hot charging pressing stage.

[0070] This embodiment can use a proven error bound reduced-order model to calculate key control parameters that cannot be directly measured by physical sensors, in order to support process adjustments.

[0071] Based on the above Figure 5The specific implementation of the method shown in this embodiment provides a compressor rotor hot-fitting device based on multi-source data online monitoring, such as... Figure 6 As shown, the device includes: an acquisition module 31 and an adjustment module 32; The acquisition module 31 is configured to acquire multi-source acquisition data corresponding to the compressor rotor using different sensors configured on the compressor rotor; based on the multi-source acquisition data, identify the hot-fitting process stage of the compressor rotor, generate acquisition control instructions corresponding to the hot-fitting process stage, and use the acquisition control instructions to control the acquisition strategies of different sensors in the multi-source heterogeneous sensor network; and acquire rotor monitoring data corresponding to the acquisition control instructions. The adjustment module 32 is configured to map the rotor assembly panorama of the compressor rotor throughout the hot-loading process based on rotor monitoring data, and adjust the hot-loading process of the compressor rotor based on the rotor assembly panorama.

[0072] In some embodiments, the adjustment module 32 is further configured to output key control parameters corresponding to the hot-fitting process based on rotor monitoring data and a verifiable error boundary reduction model. The key control parameters include the inner ring temperature gradient, thermal deformation compensation amount, and contact stress assessment value.

[0073] It should be noted that other corresponding descriptions of the functional units involved in the compressor rotor hot-fitting device based on multi-source data online monitoring provided in this embodiment can be found in the following references. Figure 5 The corresponding description in [the document] will not be repeated here.

[0074] Based on the above, Figure 5 Accordingly, this embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figure 5 The method shown.

[0075] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0076] Based on the above, Figure 5 The method shown, and Figure 6 To achieve the above objectives, the present application also provides an electronic device, comprising a storage medium and a processor; the storage medium for storing a computer program; and the processor for executing the computer program to implement the above-described virtual device embodiments. Figure 5 The method shown.

[0077] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0078] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0079] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0080] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented using software plus necessary general-purpose hardware platforms, or it can be implemented in hardware. By applying the solution of this embodiment, this application can determine the current compressor rotor hot-fitting process stage based on the multi-source acquisition data corresponding to the real-time acquired compressor rotor. According to the acquisition control command corresponding to the hot-fitting process stage, the acquisition strategy of different sensors is adaptively adjusted to combine data acquisition with the hot-fitting process stage. Finally, based on the adaptively acquired rotor monitoring data, the rotor assembly panorama of the compressor rotor throughout the entire hot-fitting process is mapped, and the compressor rotor hot-fitting process is adjusted in real time. This achieves real-time rotor detection and process adjustment during the execution of the hot-fitting process, eliminating the need to rely on operator experience for inspection after assembly, thus ensuring assembly quality and thereby ensuring the service performance of the compressor.

[0081] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is 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 a process, method, article, or apparatus. Without further limitations, 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 the element.

[0082] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A compressor rotor hot-fitting system based on multi-source data online monitoring, characterized in that, The system includes: a multi-source heterogeneous sensor network, a data processing unit, and a digital twin controller; The multi-source heterogeneous sensor network is used to acquire multi-source data corresponding to the compressor rotor by utilizing different sensors configured on the compressor rotor. The data processing unit is used to identify the hot-fitting process stage of the compressor rotor based on the multi-source acquired data, generate an acquisition control command corresponding to the hot-fitting process stage, acquire rotor monitoring data corresponding to the acquisition control command, and send the rotor monitoring data to the digital twin controller; the acquisition control command is used to control the acquisition strategy of different sensors in the multi-source heterogeneous sensor network. The digital twin controller is used to map the rotor assembly panorama of the compressor rotor throughout the entire hot-fitting process based on the rotor monitoring data, and to adjust the hot-fitting process of the compressor rotor based on the rotor assembly panorama.

2. The compressor rotor hot-fitting system based on multi-source data online monitoring according to claim 1, characterized in that, The multi-source heterogeneous sensor network includes a pressure sensor, a laser displacement sensor, a distributed thermocouple array, and an infrared thermal imager; The pressure sensor is arranged at the contact position between the tooling platform and the impeller of the compressor rotor, and is used to measure the indentation force of the compressor rotor; The laser displacement sensor is arranged near the tooling platform of the compressor rotor, aligned with the rotor end face or the spindle end face, and is used to measure the axial pressing displacement of the compressor rotor. The distributed thermocouple array is arranged at the critical impeller part of the compressor rotor to measure the temperature of the critical impeller part, which includes the axial part and the radial part of the impeller. The infrared thermal imager is arranged on the impeller of the compressor rotor and is used to switch scanning modes according to the acquisition control command to detect the rotor thermal field data of the compressor rotor.

3. The compressor rotor hot-fitting system based on multi-source data online monitoring according to claim 2, characterized in that, The distributed thermocouple array includes K-type thermocouples and patch-type platinum resistance thermometers; The K-type thermocouple and the patch-type platinum resistance thermometer are arranged near the same measurement point on the rotor target assembly surface of the compressor rotor, forming a redundant sensing pair. The distance between the K-type thermocouple and the heat source is smaller than the distance between the patch-type platinum resistance thermometer and the heat source. The redundant sensing pair is used to perform redundant sensing measurements on the temperature of the rotor target assembly surface, and to detect redundant data of the rotor target assembly surface at the same time. The redundant data includes temperature measured by a K-type thermocouple and temperature measured by a patch-type platinum resistance thermometer.

4. The compressor rotor hot-fitting system based on multi-source data online monitoring according to claim 3, characterized in that, The data processing unit is also used to store the extreme temperature difference of the collection points corresponding to the redundant data in different hot-packing process stages; and to judge the validity of the redundant data at different times in different hot-packing process stages according to the preset data invalidity conditions. If the redundant data is detected as invalid, it is re-acquired using the redundant sensor; if the redundant data is detected as valid, the average value of the redundant data is determined as the effective temperature value of the rotor target assembly surface. The preset invalid data conditions include at least one of the following: the temperature measured by the K-type thermocouple is lower than the temperature measured by the patch-type platinum resistance thermometer, and the difference in redundant data is greater than the limit temperature difference of the acquisition point.

5. The compressor rotor hot-fitting system based on multi-source data online monitoring according to claim 1, characterized in that, The system also includes a data acquisition unit; The data acquisition unit is used to issue a global hardware trigger signal according to the hardware trigger logic, and send the global hardware trigger signal to the trigger ports of the different sensors at the same time to trigger the different sensors to start acquiring data at the same time. The global hardware trigger signal includes an LVTTL pulse signal. The data acquisition unit includes an FPGA, which is responsible for executing high-speed, parallel deterministic tasks, generating the global hardware trigger signal, receiving and caching rotor monitoring data corresponding to different sensors, injecting high-precision timestamps into the rotor monitoring data, and storing it in the FPGA's FIFO storage unit.

6. The compressor rotor hot-fitting system based on multi-source data online monitoring according to claim 5, characterized in that, The system also includes virtual sensors; the data processing unit includes a SoC. The SoC and the FPGA are connected via a high-speed bus to read the rotor monitoring data; The SoC is connected to the virtual sensor and the digital twin controller via an Ethernet interface, and the rotor monitoring data is synchronously transmitted to the virtual sensor and the digital twin controller. The SoC is used to deploy a high-precision synchronous clock source, generate second pulses, record clock offset and drift, provide a unified microsecond-level time reference for the data acquisition unit and the different sensors, and store the rotor monitoring data according to the channel identifiers corresponding to the different sensors.

7. The compressor rotor hot-fitting system based on multi-source data online monitoring according to claim 6, characterized in that, The virtual sensor is used to output key control parameters corresponding to the hot-fitting process based on the rotor monitoring data and the proven error boundary reduction model, and sends the key control parameters to the digital twin controller. The key control parameters include the inner ring temperature gradient, thermal deformation compensation amount, and contact stress evaluation value.

8. The compressor rotor hot-fitting system based on multi-source data online monitoring according to claim 7, characterized in that, The digital twin controller is also used to acquire the rotor monitoring data through the data processing unit when the virtual sensor fails, and to determine the key control parameters based on the rotor monitoring data.

9. A method for hot-fitting a compressor rotor based on online monitoring of multi-source data, characterized in that, The method is applied to the compressor rotor hot-fitting system based on multi-source data online monitoring as described in any one of claims 1-8, and the method includes: By utilizing different sensors configured on the compressor rotor, multi-source acquisition data corresponding to the compressor rotor is obtained; Based on the multi-source acquired data, the hot-fitting process stage of the compressor rotor is identified, and acquisition control instructions corresponding to the hot-fitting process stage are generated. The acquisition control instructions are used to control the acquisition strategies of different sensors in the multi-source heterogeneous sensor network. Obtain the rotor monitoring data corresponding to the acquisition control command; Based on the rotor monitoring data, the rotor assembly panorama of the compressor rotor during the entire hot-loading process is mapped, and the hot-loading process of the compressor rotor is adjusted based on the rotor assembly panorama.

10. The compressor rotor hot-fitting method based on multi-source data online monitoring according to claim 9, characterized in that, The method further includes: Based on the rotor monitoring data and the verifiable error boundary reduction model, the key control parameters corresponding to the hot-fitting process are output. The key control parameters include the inner ring temperature gradient, thermal deformation compensation, and contact stress evaluation value.

Images