Bearing clearance self-adaptive regulation and control method and device

Abstract

The invention discloses a bearing clearance self-adaptive regulation and control method and device, and relates to the technical field of bearing intelligent regulation and control, and the method comprises the steps: constructing a comprehensive working condition feature vector through data fusion and feature extraction based on a bearing friction force parameter, a temperature field distribution parameter and a radial and axial load vector of a shaft system which are monitored in real time; mapping the vector to a preset clearance-working condition relation model to determine a target clearance value; the difference value between the target value and the actual clearance value is calculated, and a corresponding control signal is generated; and the signal is used for driving executing mechanisms such as a piezoelectric brake, a shape memory alloy or a servo motor to apply pre-tightening force, so that the dynamic and accurate adjustment of the bearing clearance is realized. By means of the mode, online self-adaptive optimization of the bearing clearance can be achieved according to the actual working conditions, the operation efficiency and rigidity of the bearing are effectively improved, the service life of the bearing is effectively prolonged, meanwhile, vibration and noise are restrained, and the stability of a system under the complex working conditions of variable loads, variable speeds and the like is enhanced.

Description

Technical Field

[0001] This application relates to the field of bearing intelligent control technology, and in particular to a bearing clearance adaptive control method and device. Background Technology

[0002] Bearing clearance is a key parameter affecting its operating performance, rigidity, temperature rise, and lifespan. Traditional bearing clearance control methods are mostly static presets or manual adjustments after shutdown, which cannot adapt to the dynamic changes in operating conditions such as load, speed, and temperature during equipment operation. When the clearance is too large, it will lead to insufficient shaft rigidity and increased vibration and noise; while when the clearance is too small, it will cause increased frictional torque, excessive temperature rise, and even premature bearing failure.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a bearing clearance adaptive control method and device, which aims to solve the technical problem that the bearing clearance cannot be accurately adapted to the working conditions in real time in the prior art.

[0005] To achieve the above objectives, this application provides a bearing clearance adaptive control method, the method comprising: The comprehensive working condition feature vector is obtained by fusing data from real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system. The bearing target clearance value is obtained by projecting the comprehensive operating condition feature vector onto the clearance-operating condition mapping relationship. Based on the clearance difference between the target clearance value and the actual clearance value of the bearing, a clearance adjustment control signal is generated; Based on the clearance adjustment control signal, a preload is applied to adjust the actual clearance value of the bearing to the target clearance value of the bearing.

[0006] In one embodiment, the step of fusing data based on real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system to obtain a comprehensive operating condition feature vector includes: The bearing friction force parameters and bearing temperature field distribution parameters monitored in real time are subjected to time-frequency domain transformation and feature extraction to obtain the first feature set; Based on the radial and axial load vectors of the shaft system, a second feature set characterizing the spatial load state is constructed through vector operations; The first feature set and the second feature set are fused to obtain fused data; The dimensionality of the fused data is reduced to obtain a comprehensive operating condition feature vector.

[0007] In one embodiment, the step of reducing the dimensionality of the fused data to obtain the comprehensive operating condition feature vector includes: The fused data is input into a deep autoencoder network for nonlinear dimensionality reduction to obtain dimensionality-reduced fused data. Based on the different feature dimensions in the dimensionality-reduced fused data, weights are assigned to obtain feature allocation weights. The dimensionality-reduced and fused data are aggregated based on the weights assigned to the features to obtain a comprehensive working condition feature vector.

[0008] In one embodiment, the step of obtaining the bearing target clearance value by projecting the comprehensive operating condition feature vector onto the clearance-operating condition mapping relationship includes: The comprehensive operating condition feature vector is projected onto the clearance-operating condition mapping relationship to obtain the standard feature vector and the corresponding recommended clearance value; Calculate the similarity between the comprehensive working condition feature vector and the standard feature vector; The recommended gap value corresponding to the standard feature vector with the highest similarity is used as the baseline gap; By combining the bearing's rotational speed information and the reference clearance, the target clearance value of the bearing is obtained.

[0009] In one embodiment, the step of combining the bearing's rotational speed information and the reference clearance to obtain the target bearing clearance value includes: The corresponding correction coefficient is determined based on the bearing's rotational speed information; The initial corrected clearance value is obtained based on the reference clearance and the correction coefficient; The clearance compensation value under the current temperature field is determined based on the bearing temperature field distribution parameters. The initial corrected clearance value is then compensated based on the clearance compensation value to obtain the bearing target clearance value.

[0010] In one embodiment, the step of generating a clearance adjustment control signal based on the clearance difference between the target clearance value and the actual clearance value of the bearing includes: The actual bearing clearance value is filtered and denoised to obtain the preprocessed actual bearing clearance value; Calculate the instantaneous difference between the target clearance value of the bearing and the actual clearance value of the pretreated bearing, and the trend of the change of the instantaneous difference; A preliminary control quantity is generated based on the instantaneous difference and the trend of the instantaneous difference; The preliminary control quantity is encoded to obtain the clearance adjustment control signal.

[0011] In one embodiment, the step of filtering and denoising the actual bearing clearance value to obtain a preprocessed actual bearing clearance value includes: The noise reduction covariance matrix is ​​determined based on the bearing's rotational speed information; The actual bearing clearance value is filtered based on the denoised covariance matrix to eliminate high-frequency measurement noise and obtain filtered data. The filtered data is then used as the preprocessed actual bearing clearance value.

[0012] In one embodiment, the step of applying a preload force based on the clearance adjustment control signal to adjust the actual clearance value of the bearing to the target clearance value of the bearing includes: The piezoelectric brake, shape memory alloy actuator, and / or servo motor-driven screw mechanism are driven by the clearance adjustment control signal to generate mechanical displacement, so that the mechanical displacement is transmitted to the adjusting ring of the bearing to obtain the preload force on the bearing. The bearing's actual clearance value is adjusted to the target clearance value based on the preload force.

[0013] In one embodiment, after the step of applying preload based on the clearance adjustment control signal to adjust the actual clearance value of the bearing to the target clearance value of the bearing, the method further includes: Real-time acquisition of bearing vibration and operating noise signals; Spectral analysis is performed on the vibration signal and the operating noise signal to extract feature components that are strongly correlated with the clearance size; The amplitude or frequency characteristics of the characteristic components are judged to determine whether the expected state has been reached; If the expected state is not reached, a compensation signal is generated based on the characteristic components, and the clearance adjustment control signal is corrected based on the compensation signal.

[0014] Furthermore, to achieve the above objectives, this application also proposes a bearing clearance adaptive control device, which includes: The working condition fusion module is used to fuse data based on real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system to obtain a comprehensive working condition feature vector. The clearance decision module is used to obtain the target bearing clearance value by projecting the comprehensive working condition feature vector onto the clearance-working condition mapping relationship; The signal generation module is used to generate a clearance adjustment control signal based on the clearance difference between the target clearance value and the actual clearance value of the bearing. The preload execution module is used to apply a preload force based on the clearance adjustment control signal, so as to adjust the actual clearance value of the bearing to the target clearance value of the bearing.

[0015] In addition, to achieve the above objectives, this application also proposes a bearing clearance adaptive control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the bearing clearance adaptive control method described above.

[0016] In addition, to achieve the above objectives, the present invention also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the bearing clearance adaptive control method described above.

[0017] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the bearing clearance adaptive control method described above.

[0018] This application provides a method for adaptive control of bearing clearance. Based on real-time monitoring of bearing friction parameters, temperature field distribution parameters, and radial and axial load vectors of the shaft system, a comprehensive operating condition feature vector is constructed through data fusion and feature extraction. This vector is mapped to a preset clearance-operating condition relationship model to determine the target clearance value. The difference between the target value and the actual clearance value is calculated, and a corresponding control signal is generated. This signal is used to drive an actuator such as a piezoelectric brake, shape memory alloy, or servo motor to apply preload, thereby achieving dynamic and precise adjustment of the bearing clearance. Through this method, the bearing clearance can be adaptively optimized online according to actual operating conditions, effectively improving bearing operating efficiency, stiffness, and service life, while suppressing vibration and noise, and enhancing system stability under complex operating conditions such as variable loads and speeds. Attached Figure Description

[0019] 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.

[0020] 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.

[0021] Figure 1 This is a flowchart illustrating Embodiment 1 of the bearing clearance adaptive control method of this application; Figure 2 This is a flowchart illustrating the feature extraction process of an embodiment of the bearing clearance adaptive control method of this application. Figure 3This is a schematic diagram of the module structure of the bearing clearance adaptive control device according to an embodiment of this application; Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the bearing clearance adaptive control method in the embodiments of this application.

[0022] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0024] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0025] The main solution of this application embodiment is: to perform data fusion based on the real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system to obtain a comprehensive working condition feature vector; The bearing target clearance value is obtained by projecting the comprehensive operating condition feature vector onto the clearance-operating condition mapping relationship. Based on the clearance difference between the target clearance value and the actual clearance value of the bearing, a clearance adjustment control signal is generated; Based on the clearance adjustment control signal, a preload is applied to adjust the actual clearance value of the bearing to the target clearance value of the bearing.

[0026] Currently, bearing clearance is a key parameter affecting its operating performance, stiffness, temperature rise, and lifespan. Traditional bearing clearance control methods are mostly static presets or manual adjustments after shutdown, which cannot adapt to the dynamic changes in operating conditions such as load, speed, and temperature during equipment operation. When the clearance is too large, it will lead to insufficient shaft rigidity and increased vibration and noise; while when the clearance is too small, it will cause increased frictional torque, excessively rapid temperature rise, and even premature bearing failure.

[0027] This application provides a solution that constructs a comprehensive operating condition feature vector based on real-time monitored bearing friction parameters, temperature field distribution parameters, and radial and axial load vectors of the shaft system through data fusion and feature extraction. This vector is then mapped to a preset clearance-operating condition relationship model to determine the target clearance value. The difference between the target value and the actual clearance value is calculated, and a corresponding control signal is generated. This signal is used to drive actuators such as piezoelectric brakes, shape memory alloys, or servo motors to apply preload, achieving dynamic and precise adjustment of the bearing clearance. Through this method, the bearing clearance can be adaptively optimized online according to actual operating conditions, effectively improving bearing operating efficiency, stiffness, and service life, while suppressing vibration and noise, and enhancing system stability under complex operating conditions such as variable loads and speeds.

[0028] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as a bearing clearance adaptive control device. This embodiment does not specifically limit this. The following uses a bearing clearance adaptive control device as an example to describe this embodiment and the following embodiments.

[0029] All actions involving the acquisition of signals, information, or data in this application are carried out in accordance with the relevant data protection laws and policies of the country where the application is located, and with the authorization of the owner of the relevant device.

[0030] This application provides a method for adaptive control of bearing clearance, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the bearing clearance adaptive control method of this application.

[0031] In this embodiment, the bearing clearance adaptive control method includes steps S10~S40: Step S10: Based on the real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system, data fusion is performed to obtain a comprehensive working condition feature vector.

[0032] It should be noted that bearing friction parameters reflect the friction state between the rolling elements and raceways inside the bearing, while bearing temperature field distribution parameters are data sets collected by multi-point sensors, characterizing the temperature gradient and thermal properties of the inner and outer rings and surrounding areas of the bearing. The radial load vector and axial load vector of the shaft system are physical quantities describing the magnitude and direction of the forces acting on the bearing in the direction perpendicular to the shaft centerline (radial) and along the shaft centerline (axial), respectively.

[0033] Understandably, the process begins by synchronously acquiring raw signals through torque sensors, thermocouple arrays, and multi-axis load sensors deployed on bearing housings or shaft systems. Then, signal processing techniques are used to extract time-frequency domain features from friction and temperature fluctuation signals. Simultaneously, vector synthesis is used to calculate the magnitude and orientation angle of the load, forming the first and second feature sets, respectively. Finally, data dimensionality reduction algorithms such as principal component analysis (PCA) or deep autoencoders are employed to eliminate redundant information between features, merging and compressing the high-dimensional feature sets into a comprehensive working condition feature vector.

[0034] In one feasible implementation, the step of fusing data based on real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and the radial and axial load vectors of the shaft system to obtain a comprehensive operating condition feature vector includes: The bearing friction force parameters and bearing temperature field distribution parameters monitored in real time are subjected to time-frequency domain transformation and feature extraction to obtain the first feature set; Based on the radial and axial load vectors of the shaft system, a second feature set characterizing the spatial load state is constructed through vector operations; The first feature set and the second feature set are fused to obtain fused data; The dimensionality of the fused data is reduced to obtain a comprehensive operating condition feature vector.

[0035] In the specific implementation, refer to Figure 2 First, dynamic signals and static vector data are processed separately. For bearing friction parameters and temperature signals from multiple temperature measurement points, Fast Fourier Transform (FFT) is used to transform them from the time domain to the frequency domain, obtaining the spectrum. Subsequently, a set of statistical features is extracted from the time and frequency domain signals to form the first feature set. Then, based on the detected radial and axial load vectors, a second feature set is constructed through vector operations. The first and second feature sets are then concatenated to obtain high-dimensional fused data. Due to the high dimensionality of this data and the potential for multicollinearity, direct use is inefficient. Therefore, dimensionality reduction algorithms such as Principal Component Analysis (PCA) are used to process it. PCA finds the direction of maximum data variance (principal component) through linear transformation, projecting the original data onto a few principal components, thereby obtaining a low-dimensional, orthogonal comprehensive operating condition feature vector while retaining most of the information (such as more than 95% of the variance).

[0036] In one feasible implementation, the step of reducing the dimensionality of the fused data to obtain the comprehensive operating condition feature vector includes: The fused data is input into a deep autoencoder network for nonlinear dimensionality reduction to obtain dimensionality-reduced fused data. Based on the different feature dimensions in the dimensionality-reduced fused data, weights are assigned to obtain feature allocation weights. The dimensionality-reduced and fused data are aggregated based on the weights assigned to the features to obtain a comprehensive working condition feature vector.

[0037] It's important to note that a deep autoencoder network is an artificial neural network based on deep learning, consisting of an encoder and a decoder. The encoder compresses high-dimensional input data into dimensionality-reduced, fused data through multiple layers of nonlinear transformations, capturing the essential features of the data; the decoder then reconstructs the original input from the dimensionality-reduced, fused data. Feature weights represent numerical vectors indicating the importance of each dimension in the dimensionality-reduced feature vector. These weights are assigned based on the contribution of different feature dimensions to accurately reconstructing the original data or their predictive value for downstream tasks.

[0038] In practical implementation, a deep autoencoder model first needs to be trained offline. The encoder part of this network consists of multiple fully connected layers and activation functions (such as ReLU) stacked together, ultimately fusing high-dimensional data. Mapping to a low-dimensional latent space representation, i.e., dimensionality reduction and data fusion. :

[0039] in, and It refers to network weights and biases. This is the activation function. The decoder part uses... As input, attempt to reconstruct the original data. By minimizing the reconstruction loss (such as mean squared error) To train the entire network, ensure Includes refactoring The key information required.

[0040] Once the trained encoder is obtained, the data will be fused in real time when used online. You can get the answer by inputting it. Then, weights are assigned based on the different feature dimensions in the dimensionality-reduced fused data. In this embodiment, an attention mechanism is used to calculate the weight of each dimension. For example, it can be calculated using a small neural network.

[0041] in, , and These are learnable parameters. These are the weights after Softmax normalization.

[0042] Then, the dimensionality-reduced and fused data Z is weighted and aggregated according to the feature assignment weights to generate the final comprehensive working condition feature vector V:

[0043] Step S20: The bearing target clearance value is obtained by projecting the comprehensive working condition feature vector onto the clearance-working condition mapping relationship.

[0044] It should be noted that the clearance-operating condition mapping relationship is a functional relationship or corresponding rule between the comprehensive bearing operating condition and the optimal bearing clearance value, obtained through historical data or physical model learning. The target bearing clearance value is the set target for the intelligent adjustment mechanism to make precise adjustments.

[0045] In the specific implementation, a pre-established and trained machine learning model is used as the carrier of the clearance-operating condition mapping relationship. The comprehensive operating condition feature vector is used as input, and the output layer directly predicts the continuous target clearance value. By inputting the real-time comprehensive operating condition feature vector into the clearance-operating condition mapping relationship, a precise bearing target clearance value can be directly mapped and obtained through forward propagation calculation within the model.

[0046] In one feasible implementation, the step of obtaining the bearing target clearance value by projecting the comprehensive operating condition feature vector onto the clearance-operating condition mapping relationship includes: The comprehensive operating condition feature vector is projected onto the clearance-operating condition mapping relationship to obtain the standard feature vector and the corresponding recommended clearance value; Calculate the similarity between the comprehensive working condition feature vector and the standard feature vector; The recommended gap value corresponding to the standard feature vector with the highest similarity is used as the baseline gap; By combining the bearing's rotational speed information and the reference clearance, the target clearance value of the bearing is obtained.

[0047] In the specific implementation, it first relies on a pre-built standard operating condition database. This database stores M standard operating condition entries, each containing a standard feature vector. and its corresponding recommended clearance value ,in The system will acquire comprehensive operating condition feature vectors in real time. With all in the database Similarity calculations are performed. Cosine similarity is typically used to measure directional similarity.

[0048] The system traverses the database to find matching data. The standard feature vector with the highest similarity is selected, and its corresponding recommended gap value is determined as the baseline gap.

[0049] Subsequently, a speed-based correction is performed. Because the inner raceway expands due to centrifugal force during high-speed bearing operation, resulting in a decrease in actual clearance, compensation for the baseline clearance needs to be made based on the real-time speed n (in rpm). The correction formula is typically an empirical model, for example:

[0050] in, As the reference clearance, This is a correction factor.

[0051] In one feasible implementation, the step of combining the bearing's rotational speed information and the reference clearance to obtain the bearing target clearance value includes: The corresponding correction coefficient is determined based on the bearing's rotational speed information; The initial corrected clearance value is obtained based on the reference clearance and the correction coefficient; The clearance compensation value under the current temperature field is determined based on the bearing temperature field distribution parameters. The initial corrected clearance value is then compensated based on the clearance compensation value to obtain the bearing target clearance value.

[0052] It should be noted that the correction factor is used to quantify the dynamic effect of speed change on bearing clearance. The clearance compensation value is an adjustment value introduced to offset the clearance change caused by uneven thermal expansion of bearing components (inner ring, outer ring, rolling elements), and can be positive (increase clearance) or negative (decrease clearance).

[0053] In practical implementation, when determining the correction coefficient, the rotational speed... (Unit: rpm) is the main input. Correction factor. Obtained from a predefined functional relationship, using The model in which It is a constant determined by the bearing geometry and material properties. After obtaining the correction factor, the initial corrected clearance value is... By reference clearance With correction factor To calculate by addition: .

[0054] Then, bearing temperature field distribution parameters, such as the temperature difference between the inner and outer rings, are obtained through a temperature sensor network or thermal model. Due to the different degrees of expansion of different materials (such as steel rollers and ceramic rollers) and different parts, the clearance compensation value... It needs to be calculated based on the temperature difference and the coefficient of thermal expansion. A simplified linear model can be:

[0055] in, The coefficient of thermal expansion of the material. This is the pitch circle diameter of the bearing. Finally, the temperature compensation value is applied to the initial corrected clearance to obtain the final target bearing clearance value. :

[0056] Step S30: Generate a clearance adjustment control signal based on the clearance difference between the target clearance value and the actual clearance value of the bearing.

[0057] In practice, the controller uses the calculated clearance difference as the input deviation, calculates the control quantity required to eliminate the deviation through proportional-integral-derivative operations, and then converts this control quantity into a clearance adjustment control signal that the actuator can recognize, such as outputting a high-voltage signal proportional to the deviation to the piezoelectric ceramic actuator, thereby precisely driving the adjustment mechanism to approach the target clearance.

[0058] In one feasible implementation, the step of generating a clearance adjustment control signal based on the clearance difference between the target clearance value and the actual clearance value of the bearing includes: The actual bearing clearance value is filtered and denoised to obtain the preprocessed actual bearing clearance value; Calculate the instantaneous difference between the target clearance value of the bearing and the actual clearance value of the pretreated bearing, and the trend of the change of the instantaneous difference; A preliminary control quantity is generated based on the instantaneous difference and the trend of the instantaneous difference; The preliminary control quantity is encoded to obtain the clearance adjustment control signal.

[0059] In its implementation, the control signal generation process is a typical digital closed-loop control process. Firstly, because the actual bearing clearance value is directly measured... Susceptible to mechanical vibration and electromagnetic interference, it requires filtering and noise reduction using digital filters (such as low-pass filters or Kalman filters). A simple first-order low-pass filter can be expressed as:

[0060] in It is the preprocessed actual bearing clearance value at time k. These are the filter coefficients, used to balance response speed and smoothness.

[0061] Subsequently, the system calculates the instantaneous difference. and its changing trends Preliminary control quantity It is typically generated by an improved PD (proportional-derivative) controller, with the following formula:

[0062] in and To control the gain. Proportional term. It is responsible for quickly reducing the current deviation, while the differential term This allows for the prediction of future deviation changes, suppression of overshoot, and a smoother adjustment process.

[0063] Finally, the initial control quantity It needs to be encoded into a clearance adjustment control signal that the actuator can recognize. If the actuator is a digital stepper motor, The pulse sequence is quantized into the number and direction of pulses; if it is an analog piezoelectric ceramic driver, it is converted into a digital-to-analog converter (DAC). The signal is encoded into a corresponding analog voltage or current signal, thereby enabling precise closed-loop control of the bearing clearance.

[0064] In one feasible implementation, the step of filtering and denoising the actual bearing clearance value to obtain a preprocessed actual bearing clearance value includes: The noise reduction covariance matrix is ​​determined based on the bearing's rotational speed information; The actual bearing clearance value is filtered based on the denoised covariance matrix to eliminate high-frequency measurement noise and obtain filtered data. The filtered data is then used as the preprocessed actual bearing clearance value.

[0065] In the specific implementation, an adaptive filtering algorithm is adopted to enable the denoising process to dynamically respond to changes in the bearing's operating state. Since the vibration characteristics and statistical characteristics of the measured noise of the bearing change significantly at different speeds, filters with fixed parameters are unlikely to achieve optimal results. Therefore, the system first determines the denoising covariance matrix based on the bearing's speed information. The speed *n*, as a key state variable, is used to index the pre-calibrated or online calculated process noise covariance matrix Q(n) and measurement noise covariance matrix R(n). For example, vibration intensifies at high speeds, so a larger Q(n) can be set to represent increased model uncertainty; simultaneously, R(n) is adjusted according to the relationship between the speed and the sensor signal-to-noise ratio. Subsequently, filtering is performed based on the denoising covariance matrix. This implementation preferably uses a Kalman filter as the execution algorithm. The filter uses a simple state model that includes the play and its rate of change. In each filtering period k, the algorithm performs two steps: prediction and update. Prediction steps: Based on the state estimate from the previous time step, predict the current state and its covariance:

[0066]

[0067] in It is the state transition matrix.

[0068] Update steps: Utilize the new measured clearance values Correct the predicted values, calculate the Kalman gain K, and update the state estimate and covariance:

[0069]

[0070]

[0071] Finally, from the updated state vector Extracted gap estimate This refers to the pre-processed bearing clearance value that eliminates high-frequency measurement noise. This adaptive method effectively balances the smoothness of the filter with the dynamic response speed.

[0072] Step S40: Apply a preload force based on the clearance adjustment control signal to adjust the actual clearance value of the bearing to the target clearance value of the bearing.

[0073] It should be noted that preload refers to a controllable axial force applied by an external mechanism during bearing installation or operation to eliminate internal clearance or generate a specific negative clearance (interference). This force establishes a stable contact stress between the bearing raceway and rolling elements, thereby directly affecting the actual clearance size and support stiffness of the bearing.

[0074] Understandably, when adjusting bearing clearance, an electro-mechanical conversion actuator (such as a piezoelectric brake, shape memory alloy, or servo motor-driven screw mechanism) converts the force into precise mechanical displacement or force. This action acts on the bearing's adjusting ring (such as a spacer, tapered sleeve, etc.), thereby changing the magnitude of the preload applied to the bearing. This overcomes the elastic deformation inside the bearing, allowing the actual bearing clearance value to be dynamically and precisely adjusted to the target bearing clearance value calculated by the decision-making level.

[0075] In one feasible implementation, the step of applying a preload force based on the clearance adjustment control signal to adjust the actual clearance value of the bearing to the target clearance value of the bearing includes: The piezoelectric brake, shape memory alloy actuator, and / or servo motor-driven screw mechanism are driven by the clearance adjustment control signal to generate mechanical displacement, so that the mechanical displacement is transmitted to the adjusting ring of the bearing to obtain the preload force on the bearing. The bearing's actual clearance value is adjusted to the target clearance value based on the preload force.

[0076] In practical implementation, the type of control signal generated can be determined based on the actuator that adjusts the clearance. If driving a piezoelectric brake, the control signal is a high-voltage analog voltage. The piezoelectric brake operates based on the inverse piezoelectric effect, producing a tiny displacement. With applied voltage Proportional, that is ,in It is the piezoelectric constant. This actuator has an extremely fast response speed (down to the millisecond level) and high resolution, making it very suitable for high-frequency fine-tuning, but its stroke is relatively short. If driving a servo motor, the control signal is a pulse sequence, and the angular displacement of the motor rotation... Axial displacement is converted through a precise helical mechanism (such as a ball screw). ( The lead screw can be used to achieve precise control of large stroke and high thrust. For shape memory alloy (SMA) actuators, the control signal is typically a heating current. When the SMA wire undergoes an austenitic phase transformation upon heating, it generates recoverable shrinkage strain, resulting in a large restoring force. Its displacement exhibits a non-linear relationship with temperature (controlled by the current). Regardless of the mechanism used, the final output is to drive an adjusting ring (such as a spacer or a movable bearing housing) on ​​the bearing side to produce axial displacement.

[0077] The resulting mechanical displacement When applied to the adjusting ring of the bearing, it is converted into an axial preload force on the bearing race. This conversion relationship is determined by the stiffness of the entire transmission chain. Decision, that is The preload When applied to a bearing, it causes corresponding elastic deformation in the inner and outer rings and rolling elements. The relationship is determined by the bearing's stiffness characteristics. The decision ( It is precisely this micrometer-level deformation. This directly eliminates the original internal clearance, thus achieving precise control over the actual bearing clearance value. The system continuously monitors the feedback signal of the actual clearance, forming a closed-loop control that constantly finely adjusts the output displacement. This continues until the error between the actual clearance value and the calculated target clearance value is eliminated, thereby ensuring that the bearing is always in its optimal working condition under the current operating conditions.

[0078] In one feasible implementation, after the step of applying a preload based on the clearance adjustment control signal to adjust the actual clearance value of the bearing to the target clearance value of the bearing, the method further includes: Real-time acquisition of bearing vibration and operating noise signals; Spectral analysis is performed on the vibration signal and the operating noise signal to extract feature components that are strongly correlated with the clearance size; The amplitude or frequency characteristics of the characteristic components are judged to determine whether the expected state has been reached; If the expected state is not reached, a compensation signal is generated based on the characteristic components, and the clearance adjustment control signal is corrected based on the compensation signal.

[0079] In practical implementation, after the bearing clearance is adjusted by the main control loop, the system initiates a secondary feedback loop based on performance monitoring to achieve finer optimization. This process first uses accelerometers and acoustic sensors mounted on the bearing housing to collect the bearing's vibration acceleration signals in real time. and operating noise signals Subsequently, a Fast Fourier Transform (FFT) was performed on the two time-domain signals to transform them into the frequency domain, yielding the vibration spectrum. and noise spectrum Next, characteristic components strongly correlated with clearance size are extracted from the spectrum. These components are typically the natural vibration frequencies of various bearing components (such as the passing frequencies of bearing rings and rolling elements) and their harmonics. Non-optimal clearance conditions can induce impact vibrations, leading to increased amplitudes or the appearance of sidebands at these characteristic frequencies. For example, a comprehensive characteristic index reflecting the clearance state can be defined. It could be a key frequency. The amplitude at that point, or a weighted sum of several characteristic amplitudes: ,in , These are the weighting coefficients.

[0080] Calculated feature indicators Compared with the preset expected state threshold range The comparison is used to determine whether the clearance adjustment has achieved the expected optimal performance state. If the gap is within this threshold range, the current gap is considered optimal; if (This usually means that excessive clearance leads to increased vibration) or (This may indicate that the clearance is too small, resulting in abnormal constraints), in which case it is determined that the expected state has not been reached. At this time, the system will determine the deviation. (in The target value (which can be the median of the threshold) generates a compensation signal. This compensation amount is typically calculated by a simple PI controller:

[0081] in and This is the control gain of the secondary feedback loop. Ultimately, this compensation signal... The clearance decision module or signal generation module of the main control loop will be fed back to adjust the original bearing target clearance value. Or the clearance adjustment control signal can be superimposed and corrected (e.g.) This forms an advanced adaptive closed-loop control system that can self-optimize based on the final operating performance.

[0082] This embodiment provides a method for adaptive control of bearing clearance. Based on real-time monitoring of bearing friction parameters, temperature field distribution parameters, and radial and axial load vectors of the shaft system, a comprehensive operating condition feature vector is constructed through data fusion and feature extraction. This vector is mapped to a preset clearance-operating condition relationship model to determine the target clearance value. The difference between the target value and the actual clearance value is calculated, and a corresponding control signal is generated. This signal is used to drive an actuator such as a piezoelectric brake, shape memory alloy, or servo motor to apply preload, thereby achieving dynamic and precise adjustment of the bearing clearance. Through this method, the bearing clearance can be adaptively optimized online according to actual operating conditions, effectively improving bearing operating efficiency, stiffness, and service life, while suppressing vibration and noise, and enhancing system stability under complex operating conditions such as variable loads and speeds.

[0083] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the bearing clearance adaptive control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0084] This application also provides a bearing clearance adaptive adjustment device, please refer to... Figure 3 The bearing clearance adaptive control device includes: The working condition fusion module 10 is used to fuse data based on the real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system to obtain a comprehensive working condition feature vector. Clearance decision module 20 is used to obtain the bearing target clearance value by projecting the comprehensive working condition feature vector onto the clearance-working condition mapping relationship; The signal generation module 30 is used to generate a clearance adjustment control signal based on the clearance difference between the target clearance value and the actual clearance value of the bearing. The preload execution module 40 is used to apply a preload force based on the clearance adjustment control signal so that the actual clearance value of the bearing is adjusted to the target clearance value of the bearing.

[0085] In one feasible implementation, the working condition fusion module 10 is further used to perform time-frequency domain transformation and feature extraction on the real-time monitored bearing friction force parameters and bearing temperature field distribution parameters to obtain a first feature set; Based on the radial and axial load vectors of the shaft system, a second feature set characterizing the spatial load state is constructed through vector operations; The first feature set and the second feature set are fused to obtain fused data; The dimensionality of the fused data is reduced to obtain a comprehensive operating condition feature vector.

[0086] In one feasible implementation, the working condition fusion module 10 is further configured to input the fused data into a deep autoencoder network for nonlinear dimensionality reduction to obtain dimensionality-reduced fused data. Based on the different feature dimensions in the dimensionality-reduced fused data, weights are assigned to obtain feature allocation weights. The dimensionality-reduced and fused data are aggregated based on the weights assigned to the features to obtain a comprehensive working condition feature vector.

[0087] In one feasible implementation, the clearance decision module 20 is further configured to project the comprehensive operating condition feature vector onto the clearance-operating condition mapping relationship to obtain a standard feature vector and the corresponding recommended clearance value; Calculate the similarity between the comprehensive working condition feature vector and the standard feature vector; The recommended gap value corresponding to the standard feature vector with the highest similarity is used as the baseline gap; By combining the bearing's rotational speed information and the reference clearance, the target clearance value of the bearing is obtained.

[0088] In one feasible implementation, the clearance decision module 20 is further configured to determine a corresponding correction coefficient based on the bearing's rotational speed information; The initial corrected clearance value is obtained based on the reference clearance and the correction coefficient; The clearance compensation value under the current temperature field is determined based on the bearing temperature field distribution parameters. The initial corrected clearance value is then compensated based on the clearance compensation value to obtain the bearing target clearance value.

[0089] In one feasible implementation, the signal generation module 30 is further used to filter and denoise the actual bearing clearance value to obtain a preprocessed actual bearing clearance value. Calculate the instantaneous difference between the target clearance value of the bearing and the actual clearance value of the pretreated bearing, and the trend of the change of the instantaneous difference; A preliminary control quantity is generated based on the instantaneous difference and the trend of the instantaneous difference; The preliminary control quantity is encoded to obtain the clearance adjustment control signal.

[0090] In one feasible implementation, the signal generation module 30 is further configured to determine a denoising covariance matrix based on the bearing's rotational speed information; The actual bearing clearance value is filtered based on the denoised covariance matrix to eliminate high-frequency measurement noise and obtain filtered data. The filtered data is then used as the preprocessed actual bearing clearance value.

[0091] In one feasible implementation, the preload actuation module 40 is further configured to drive the piezoelectric brake, shape memory alloy actuator, and / or servo motor driven screw mechanism to generate mechanical displacement according to the clearance adjustment control signal, so that the mechanical displacement is transmitted to the adjusting ring of the bearing to obtain the preload force on the bearing; The bearing's actual clearance value is adjusted to the target clearance value based on the preload force.

[0092] In one feasible implementation, the preload execution module 40 is also used to collect the vibration signal and operating noise signal of the bearing in real time; Spectral analysis is performed on the vibration signal and the operating noise signal to extract feature components that are strongly correlated with the clearance size; The amplitude or frequency characteristics of the characteristic components are judged to determine whether the expected state has been reached; If the expected state is not reached, a compensation signal is generated based on the characteristic components, and the clearance adjustment control signal is corrected based on the compensation signal.

[0093] The bearing clearance adaptive control device provided in this application, employing the bearing clearance adaptive control method in the above embodiments, can solve the technical problem that bearing clearance cannot accurately adapt to operating conditions in real time. Compared with the prior art, the beneficial effects of the bearing clearance adaptive control device provided in this application are the same as those of the bearing clearance adaptive control method provided in the above embodiments, and other technical features in the bearing clearance adaptive control device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0094] This application provides a bearing clearance adaptive control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the bearing clearance adaptive control method in the above embodiment 1.

[0095] The following is for reference. Figure 4The diagram illustrates a structural schematic suitable for implementing the bearing clearance adaptive control device of the embodiments of this application. The bearing clearance adaptive control device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The bearing clearance adaptive control device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0096] like Figure 4 As shown, the bearing clearance adaptive control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the bearing clearance adaptive control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touch screens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 allows the bearing clearance adaptive control device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows bearing clearance adaptive control devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0097] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0098] The bearing clearance adaptive control device provided in this application, employing the bearing clearance adaptive control method in the above embodiments, can solve the technical problem of bearing clearance adaptive control. Compared with the prior art, the beneficial effects of the bearing clearance adaptive control device provided in this application are the same as those of the bearing clearance adaptive control method provided in the above embodiments, and other technical features in this bearing clearance adaptive control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0099] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0100] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0101] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the bearing clearance adaptive control method in the above embodiments.

[0102] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0103] The aforementioned computer-readable storage medium may be included in the bearing clearance adaptive control device; or it may exist independently and not assembled into the bearing clearance adaptive control device.

[0104] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the bearing clearance adaptive control device, the bearing clearance adaptive control device performs data fusion based on the real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system to obtain a comprehensive working condition feature vector. The bearing target clearance value is obtained by projecting the comprehensive operating condition feature vector onto the clearance-operating condition mapping relationship. Based on the clearance difference between the target clearance value and the actual clearance value of the bearing, a clearance adjustment control signal is generated; Based on the clearance adjustment control signal, a preload is applied to adjust the actual clearance value of the bearing to the target clearance value of the bearing.

[0105] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0107] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0108] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described bearing clearance adaptive control method, thereby solving the technical problem of bearing clearance adaptive control. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the bearing clearance adaptive control method provided in the above embodiments, and will not be repeated here.

[0109] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the bearing clearance adaptive control method described above.

[0110] The computer program product provided in this application can solve the technical problem of adaptive control of bearing clearance. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the adaptive control method of bearing clearance provided in the above embodiments, and will not be repeated here.

[0111] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for adaptive control of bearing clearance, characterized in that, The bearing clearance adaptive control method includes: The comprehensive working condition feature vector is obtained by fusing data from real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system. The bearing target clearance value is obtained by projecting the comprehensive operating condition feature vector onto the clearance-operating condition mapping relationship. Based on the clearance difference between the target clearance value and the actual clearance value of the bearing, a clearance adjustment control signal is generated; Based on the clearance adjustment control signal, a preload is applied to adjust the actual clearance value of the bearing to the target clearance value of the bearing.

2. The method as described in claim 1, characterized in that, The step of fusing data based on real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system to obtain a comprehensive operating condition feature vector includes: The bearing friction force parameters and bearing temperature field distribution parameters monitored in real time are subjected to time-frequency domain transformation and feature extraction to obtain the first feature set; Based on the radial and axial load vectors of the shaft system, a second feature set characterizing the spatial load state is constructed through vector operations; The first feature set and the second feature set are fused to obtain fused data; The dimensionality of the fused data is reduced to obtain a comprehensive operating condition feature vector.

3. The method as described in claim 2, characterized in that, The step of reducing the dimensionality of the fused data to obtain the comprehensive working condition feature vector includes: The fused data is input into a deep autoencoder network for nonlinear dimensionality reduction to obtain dimensionality-reduced fused data. Based on the different feature dimensions in the dimensionality-reduced fused data, weights are assigned to obtain feature allocation weights. The dimensionality-reduced and fused data are aggregated based on the weights assigned to the features to obtain a comprehensive working condition feature vector.

4. The method as described in claim 1, characterized in that, The step of obtaining the bearing target clearance value by projecting the comprehensive operating condition feature vector onto the clearance-operating condition mapping relationship includes: The comprehensive operating condition feature vector is projected onto the clearance-operating condition mapping relationship to obtain the standard feature vector and the corresponding recommended clearance value; Calculate the similarity between the comprehensive working condition feature vector and the standard feature vector; The recommended gap value corresponding to the standard feature vector with the highest similarity is used as the baseline gap; By combining the bearing's rotational speed information and the reference clearance, the target clearance value of the bearing is obtained.

5. The method as described in claim 4, characterized in that, The step of combining the bearing's rotational speed information and the reference clearance to obtain the target bearing clearance value includes: The corresponding correction coefficient is determined based on the bearing's rotational speed information; The initial corrected clearance value is obtained based on the reference clearance and the correction coefficient; The clearance compensation value under the current temperature field is determined based on the bearing temperature field distribution parameters. The initial corrected clearance value is then compensated based on the clearance compensation value to obtain the bearing target clearance value.

6. The method as described in claim 1, characterized in that, The step of generating a clearance adjustment control signal based on the clearance difference between the target clearance value and the actual clearance value of the bearing includes: The actual bearing clearance value is filtered and denoised to obtain the preprocessed actual bearing clearance value; Calculate the instantaneous difference between the target clearance value of the bearing and the actual clearance value of the pretreated bearing, and the trend of the change of the instantaneous difference; A preliminary control quantity is generated based on the instantaneous difference and the trend of the instantaneous difference; The preliminary control quantity is encoded to obtain the clearance adjustment control signal.

7. The method as described in claim 6, characterized in that, The step of filtering and denoising the actual bearing clearance value to obtain the preprocessed actual bearing clearance value includes: The noise reduction covariance matrix is ​​determined based on the bearing's rotational speed information; The actual bearing clearance value is filtered based on the denoised covariance matrix to eliminate high-frequency measurement noise and obtain filtered data. The filtered data is then used as the preprocessed actual bearing clearance value.

8. The method as described in claim 1, characterized in that, The step of applying a preload force based on the clearance adjustment control signal to adjust the actual clearance value of the bearing to the target clearance value of the bearing includes: The piezoelectric brake, shape memory alloy actuator, and / or servo motor-driven screw mechanism are driven by the clearance adjustment control signal to generate mechanical displacement, so that the mechanical displacement is transmitted to the adjusting ring of the bearing to obtain the preload force on the bearing. The bearing's actual clearance value is adjusted to the target clearance value based on the preload force.

9. The method as described in claim 1, characterized in that, After the step of applying preload based on the clearance adjustment control signal to adjust the actual clearance value of the bearing to the target clearance value of the bearing, the method further includes: Real-time acquisition of bearing vibration and operating noise signals; Spectral analysis is performed on the vibration signal and the operating noise signal to extract feature components that are strongly correlated with the clearance size; The amplitude or frequency characteristics of the characteristic components are judged to determine whether the expected state has been reached; If the expected state is not reached, a compensation signal is generated based on the characteristic components, and the clearance adjustment control signal is corrected based on the compensation signal.

10. A bearing clearance adaptive adjustment device, characterized in that, The bearing clearance adaptive adjustment device includes: The working condition fusion module is used to fuse data based on real-time monitored bearing friction parameters, bearing temperature field distribution parameters, and radial and axial load vectors of the shaft system to obtain a comprehensive working condition feature vector. The clearance decision module is used to obtain the target bearing clearance value by projecting the comprehensive working condition feature vector onto the clearance-working condition mapping relationship; The signal generation module is used to generate a clearance adjustment control signal based on the clearance difference between the target clearance value and the actual clearance value of the bearing. The preload execution module is used to apply a preload force based on the clearance adjustment control signal, so as to adjust the actual clearance value of the bearing to the target clearance value of the bearing.

Images