Air-suspended fan predictive maintenance method and system based on digital twinning

Abstract

The application provides an air suspension fan predictive maintenance method and system based on digital twinning, comprising: collecting airflow mutation characteristics when high-temperature dust-containing waste gas rushes into the air suspension fan, transmitting to a digital twinning system, and determining the airflow mutation characteristics; extracting a foil and bearing local gap narrowing trend from a foil non-uniform expansion amount, calculating a spatial distribution after the gap is narrowed, and obtaining a target gas film thickness value; comparing the target gas film thickness value with a preset collision and grinding threshold value, if the target gas film thickness value is less than the threshold value, then evaluating a collision and grinding risk probability through a Monte Carlo method; if the collision and grinding risk probability exceeds a preset safety range, then calculating a gas film stiffness fluctuation range based on a gas dynamics theory; and extracting vibration amplitude analysis results from air suspension fan foil bearing dynamic response parameters, and calculating a stability prediction index.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, and in particular to an air-suspended fan predictive maintenance method and system based on digital twinning. BACKGROUND

[0002] As the core equipment of the industrial waste heat recovery system, the stable operation of the air-suspended fan is of decisive significance to the efficient use of energy and environmental protection. Foil bearings become the key components supporting the efficient operation of the fan due to their oil-free lubrication and high-speed adaptability. However, under the extreme working condition of the sudden influx of high-temperature dust-containing exhaust gas, the stability of the bearing is severely tested, and research on heat shock protection technology based on digital twinning has become an important direction to improve system reliability. Currently, the industrial field generally relies on traditional simulation and experience design to optimize bearing performance, but these methods lack dynamic response capability in dealing with sudden conditions, often ignoring the real-time influence of transient thermal coupling and gas property changes, resulting in decreased prediction accuracy and difficulty in effectively preventing rubbing risks. Existing solutions focus on bearing design and optimization under static conditions, with few systematic studies on dynamic disturbances such as sudden changes in inlet gas temperature and composition. This limitation makes it difficult for traditional methods to accurately capture transient phenomena such as foil non-uniform thermal expansion, gas film stiffness and damping fluctuations, and minimum gas film thickness approaching the rubbing threshold, especially in high-temperature dust-containing environments, where gas viscosity fluctuates significantly due to changes in temperature and impurity content, further complicating the prediction. The core challenge is how to accurately characterize the rapid narrowing of the local gap caused by foil thermal expansion, the dynamic imbalance of gas film characteristics due to changes in gas properties, and the transient evolution process of the minimum gas film thickness approaching the rubbing threshold under sudden conditions. If these technical factors are not properly addressed, it will directly induce bearing instability and even failure, threatening the safe operation of the entire waste heat recovery system. Therefore, how to combine digital twinning system technology, integrate material thermal coupling effects and gas property changes through transient simulation models, and real-time assess rubbing risk probability, has become a key issue to ensure the effectiveness of the bearing stability prediction mechanism. SUMMARY

[0003] The present application provides an air-suspended fan predictive maintenance method based on digital twinning, mainly including:

[0004] Collecting the gas flow mutation characteristics when high-temperature dust-containing exhaust gas flows into the air-suspended fan, transmitting them to the digital twinning system, and determining the gas flow mutation characteristics;

[0005] According to the gas flow mutation characteristics, the foil transient thermal expansion distribution is calculated, and the mutual influence between the temperature field and the stress and strain field of the material is combined to obtain the non-uniform expansion amount of each region of the foil;

[0006] Extract the foil and bearing local gap narrowing trend from the foil non-uniform expansion amount, calculate the spatial distribution after the gap is narrowed, and obtain the target gas film thickness value;

[0007] Compare the target gas film thickness value with the preset rub threshold value, if less than the threshold value, then evaluate the rub risk probability by the Monte Carlo method;

[0008] If the rub risk probability exceeds the preset safety range, calculate the gas film stiffness fluctuation range based on the gas dynamics theory;

[0009] According to the gas film stiffness fluctuation range, combined with the real-time acquisition of the operating condition of the air suspension fan and the bearing structure, the fluid-structure coupling algorithm is used to calculate the dynamic response parameters of the air suspension fan foil bearing;

[0010] Extract the vibration amplitude analysis result from the air suspension fan foil bearing dynamic response parameters, and calculate the stability prediction index;

[0011] Adaptive filtering algorithm is used to optimize the real-time evaluation logic of the preset digital twin system, and the bearing wear monitoring data is updated based on the stability prediction index to determine the failure probability evaluation result;

[0012] According to the failure probability evaluation result, a control instruction is generated and transmitted to the thermal shock protection module of the air suspension fan to generate a dynamic adjustment scheme for bearing stability.

[0013] Further, the airflow mutation characteristics when the high-temperature dust-containing waste gas rushes into the air suspension fan are collected and transmitted to the digital twin system to determine the airflow mutation characteristics, including: collecting airflow pressure data through five measuring points arranged in the gas flow channel by piezoelectric pressure sensors, calculating the airflow pressure change rate according to the pressure difference between adjacent measuring points divided by the sampling time interval, dynamically adjusting the sampling frequency according to the airflow turbulence intensity, and generating an airflow pressure mutation data set. From the dust concentration sensor, obtain the dust concentration data in the waste gas, and according to the dust particle size range, divide the concentration data into three grades of less than 10 microns, 10 to 50 microns, and more than 50 microns for counting and statistics, and combine the airflow pressure mutation data set in step one to calculate the gas-solid two-phase flow velocity field distribution. According to the temperature data of the waste gas measured by the thermocouple temperature sensor, combined with the gas-solid two-phase flow velocity field distribution obtained in step two, a temperature field distribution parameter set containing temperature gradient, heat flux, and convective heat transfer coefficient is established for each measuring point. The data acquisition device is used to perform time synchronization processing on the airflow pressure mutation data set, the gas-solid two-phase flow velocity field distribution, and the temperature field distribution parameter set to generate a multi-dimensional airflow characteristic data group. According to the multi-dimensional airflow characteristic data group, a gas flow state space is constructed, and the mapping relationship between the gas flow pressure, flow, dust concentration, and temperature is calculated by the least squares method to obtain a gas flow mutation characteristic parameter matrix.

[0014] Further, according to the airflow mutation feature calculation foil transient thermal expansion distribution, combined with the mutual influence between the temperature field and the stress and strain field of the material, the non-uniform expansion amount of each region of the foil is obtained, including: based on the temperature field data in the airflow mutation feature value, the foil calculation grid is divided, the adaptive quadrilateral grid unit is used to subdivide the geometric region of the foil, when the temperature gradient difference of adjacent grid units is less than the preset threshold value, it is determined that the grid density meets the convergence condition, and the initial temperature field distribution of the foil is constructed. According to the thermal expansion coefficient and the elastic modulus of the material, the thermal stress coefficient matrix is calculated, the Lagrange interpolation method is used to solve the stress field distribution of each grid unit node of the foil, and the initial value of the stress and strain field of the foil is generated combined with the temperature field distribution obtained in step one. According to the initial value of the stress and strain field of the foil, the displacement increment of each grid unit node is calculated through the linear elastic constitutive equation, and the local deformation amount of the foil is solved combined with the temperature field distribution, and the transient deformation field data of the foil is obtained. Based on the transient deformation field data of the foil, a heat conduction equation set is established, and the least square method is used to fit and calculate the thermal conductivity distribution of the foil, and the temperature stress coupling coefficient of the foil is obtained combined with the stress field distribution. According to the temperature stress coupling coefficient of the foil, the thermal strain increment is calculated, and the thermal displacement vector of each grid unit node is solved by the finite difference method, and the non-uniform thermal expansion distribution data of the foil is obtained. According to the non-uniform thermal expansion distribution data of the foil, the node strain interpolation method is used to calculate the thermal deformation gradient of each region of the foil, and the non-uniform expansion amount of each grid unit of the foil is determined combined with the stress field distribution. Further, the foil and bearing local gap narrowing trend is extracted from the non-uniform expansion amount of the foil, the spatial distribution after the gap is narrowed is calculated, and the target gas film thickness value is obtained, including: based on the non-uniform expansion amount of the foil, a deformed grid matrix of the foil is constructed, the displacement distribution of the foil deformation amount on the bearing surface is calculated by Lagrange interpolation, the grid point coordinates are corrected according to the surface roughness parameters of the bearing surface, and the initial contact gap field is obtained. According to the initial contact gap field data, a contact stress distribution matrix is constructed, the foil and bearing surface contour feature points are fitted by using the Bezier curve, and the contact deformation amount is calculated combined with the surface normal vector, and the local contact pressure field is obtained. According to the local contact pressure field, the gap change rate is calculated, the least square method is used to fit the geometric surface equation of the contact area, and the real-time gap distribution function is determined combined with the elastic deformation amount of the foil. According to the real-time gap distribution function, the gas film pressure field equation is established, the gas film pressure gradient distribution is solved by Reynolds equation, and the gas film pressure distribution matrix is obtained. Based on the gas film pressure distribution matrix, the gas film carrying capacity is calculated, the spatial mapping method is used to establish the gas film thickness response function, and the target gas film thickness value is calculated combined with the gas film compression characteristic curve.

[0015] Further, the target gas film thickness value is compared with a preset collision threshold, if less than the threshold, the collision risk probability is evaluated by the Monte Carlo method, including: a grid space distribution function is established based on the target gas film thickness value, the numerical comparison is performed through the gas film thickness preset collision threshold, if less than the preset threshold, the local collision point position probability is calculated by using the Bernoulli distribution random sampling. The bearing load stress distribution is constructed according to the local collision point position probability, the local stress concentration coefficient is established based on the material surface finish parameter, and the collision contact stress field is calculated in combination with the friction coefficient. The radial displacement amount distribution is calculated for the collision contact stress field, a plurality of groups of random working conditions are generated by Monte Carlo sampling, and the collision contact time length distribution is determined in combination with the material loss rate. The friction heat power field is established based on the collision contact time length distribution, the dynamic stress evolution curve is predicted by using the random forest algorithm, and the foil vibration amplitude distribution is obtained. The gas film thickness attenuation law is calculated according to the foil vibration amplitude distribution, and the collision damage cumulative function is constructed in combination with the collision impact force data. The probability density distribution is constructed for the collision damage cumulative function, the maximum likelihood estimation is used to determine the collision risk probability distribution parameter, and the collision risk probability value is obtained.

[0016] Further, if the collision risk probability exceeds the preset safety range, the gas film stiffness fluctuation range is calculated based on the gas dynamics theory, including: if the foil bearing collision risk probability exceeds the preset safety range value, the waste gas temperature data is collected by the thermocouple sensor, the temperature gradient distribution is measured in combination with the thermistor array, and the gas temperature field function is fitted by using the least square method. The waste gas impurity concentration distribution is measured by the laser particle size sensor, the gas density change rate is calculated based on the gas state equation, and the gas-solid two-phase flow velocity field is solved in combination with the Navier-Stokes equation. The gas film pressure distribution data is obtained by the pressure sensor array, the gas film stress distribution function is established for the pressure fluctuation amplitude, and the gas film deformation response characteristic is calculated by using the finite difference method. The gas film stiffness calculation model is constructed based on the gas film deformation response characteristic, the aerodynamic load distribution is calculated in combination with the gas dynamic viscosity and the Reynolds number. The gas film supporting stiffness coefficient is solved according to the aerodynamic load distribution, and the upper and lower limits of the gas film stiffness fluctuation are calculated by the gas film damping characteristic equation. The gas film stability discrimination criterion is established for the upper and lower limits of the gas film stiffness fluctuation, and the dynamic change range of the gas film stiffness is predicted by using the Bayesian regression.

[0017] Further, according to the gas film stiffness fluctuation range, combined with the real-time acquisition of the operation condition of the air suspension fan and the bearing structure, the fluid-structure coupling algorithm is used to calculate the dynamic response parameters of the air suspension fan foil bearing, including: based on the gas film stiffness fluctuation range, the gas film flow field calculation grid is constructed, the fan speed fluctuation rate and dynamic balance degree data are collected in real time from the sensor, and the aerodynamic load distribution function is established combined with the bearing gap ratio and the bearing pre-tightening degree. According to the aerodynamic load distribution function, the foil structure stress field is solved, the foil deformation is calculated by using the elastic mechanics equation set, and the gas film pressure distribution field is constructed based on the finite volume method. The interaction between the gas film pressure and the foil deformation is calculated by using the fluid-structure coupling iterative solver, the shaft center offset is calculated by using the Newton iteration method, and the transient flow field distribution is obtained combined with the gas film compression ratio. The foil vibration control equation set is established for the transient flow field distribution, the vibration acceleration and the axial displacement are calculated by using the Runge-Kutta method, and the shaft center trajectory curve of the foil bearing is obtained. The harmonic analysis function is constructed based on the shaft center trajectory curve, the vibration amplitude spectrum is calculated by using the fast Fourier transform, and the main vibration frequency is determined combined with the vibration frequency ratio parameter. According to the main vibration frequency, the gas film thickness distribution function is constructed, the gas film pressure fluctuation curve is fitted by using the least square method, and the minimum gas film thickness is solved by using the aerodynamic force balance equation. Further, the vibration amplitude analysis result is extracted from the air suspension fan foil bearing dynamic response parameters, and the stability prediction index is calculated, including: the vibration time domain signal is extracted from the air suspension fan foil bearing dynamic response parameters, the vibration signal frequency component is decomposed by using the wavelet transform, and the vibration amplitude envelope spectrum is constructed by using the Hilbert transform. According to the vibration amplitude envelope spectrum, the amplitude ratio of two adjacent vibration periods is calculated, the vibration response equation is established according to the amplitude attenuation law, and the logarithmic decay rate is calculated combined with the damping coefficient. The bearing stability evaluation matrix is constructed based on the logarithmic decay rate and the dynamic stiffness ratio, the vortex component in the vibration signal is extracted by using the fast Fourier transform, and the vortex angular rate data is obtained. According to the vortex angular rate data, the vortex motion trajectory characteristics are calculated, the vortex main frequency signal is obtained by using the discrete Fourier transform, and the vortex frequency ratio is calculated combined with the critical speed. The bearing stability discrimination criterion is established according to the vortex frequency ratio, the vibration response function is calculated by using the spectral analysis method, and the stability prediction index is obtained. The dynamic characteristic evaluation function is constructed based on the stability prediction index, and the change trend of the logarithmic decay rate and the vortex frequency ratio is predicted by using the autoregressive model.

[0018] Further, the adaptive filtering algorithm is used to optimize the preset real-time evaluation logic of the digital twin system, the bearing wear monitoring data is updated based on the stability prediction index, the failure probability evaluation result is determined, including: an adaptive filtering parameter matrix is constructed based on the stability prediction index, a state observation equation is used to describe the bearing wear data characteristics, and a filtering gain coefficient is dynamically adjusted through measurement noise variance. The digital twin evaluator parameters are optimized according to the filtering gain coefficient, the state transition equation is established for the bearing wear monitoring data, and the state estimation function is constructed in combination with the real-time response characteristics. The bearing wear rate is calculated through the state estimation function, the wear development trend is predicted using a deep neural network, and a life degradation curve is established in combination with historical failure data. The failure probability transition matrix is constructed based on the life degradation curve, the bearing residual life distribution is calculated through Markov chain, and the failure probability threshold interval is obtained. The adaptive evaluation criterion is established for the failure probability threshold interval, the evaluation parameter correction amount is calculated in combination with the data update period, and the dynamic optimization of the evaluation logic is realized. The bearing wear monitoring parameters are updated according to the evaluation logic optimization result, and the failure probability is calculated through multiple sampling using the Monte Carlo method, and the failure probability evaluation result is obtained.

[0019] Further, a time-frequency domain joint index is extracted from the bearing wear monitoring data, input into a preset stability prediction model, and a prediction residual sequence is output. A covariance matrix is calculated based on the prediction residual sequence, which is used to update the noise suppression coefficient of the adaptive filtering algorithm. The bearing wear monitoring data is reconstructed according to the updated noise suppression coefficient, and a wear amount time series curve is generated. The prediction residual sequence and the wear amount time series curve are fused to calculate the cumulative failure probability value, including: the root mean square value and the spectral kurtosis value are extracted from the bearing wear monitoring data, the envelope spectrum characteristics are calculated through Hilbert transform, the time-frequency joint prediction function is established using a long short-term memory network, and the prediction residual sequence is obtained. A sample matrix is constructed according to the prediction residual sequence, the noise subspace eigenvalues are calculated using singular value decomposition, and the noise covariance matrix is established in combination with the residual convergence degree. The optimal filtering gain is calculated based on the noise covariance matrix, the noise suppression coefficient is updated through recursive least squares, and the filtering parameters are optimized for data reconstruction accuracy. The wear monitoring data is reconstructed according to the optimized filtering parameters, the wear feature coefficients are extracted using wavelet transform, and the wear amount evolution equation is established. A time series state matrix is generated based on the wear amount evolution equation, the state transition probability is calculated through Markov chain, and the wear amount time series curve is obtained in combination with the failure threshold. The wear amount time series curve and the prediction residual sequence are fused, the data redundancy is eliminated using a Wiener filter, and a failure probability density function is established. The state transition matrix is calculated according to the failure probability density function, and the cumulative failure probability value is solved through Bernoulli distribution.

[0020] Further, according to the failure probability evaluation result, a control instruction is generated and transmitted to a thermal shock protection module of the air suspension fan, and a bearing stability dynamic adjustment scheme is generated, including: constructing a thermal shock protection parameter set according to the failure probability evaluation result, generating a temperature control curve for the temperature regulation ratio and the cooling power value, and calculating a temperature dynamic adjustment sequence by using an adaptive controller. Based on the temperature dynamic adjustment sequence, a digital control instruction is generated and transmitted to the thermal shock protection device through a serial communication interface, and the instruction execution time sequence is optimized in combination with signal transmission delay compensation. According to the instruction execution time sequence, a bearing operation state parameter set is constructed, a bearing dynamic characteristic monitoring function is established for the stable range threshold, and a bearing adjustment gain curve is predicted by using support vector regression. Based on the bearing adjustment gain curve, a thermal power dynamic distribution ratio is calculated, a cooling power control sequence is generated in combination with the bearing temperature change rate, and the thermal shock response characteristic is optimized by using the dynamic programming method. According to the thermal shock response characteristic, a bearing stability evaluation criterion is established, an adjustment parameter correction amount is calculated for the temperature fluctuation amplitude, and the control parameter is updated by using the recursive least squares method. Based on the updated control parameter, a bearing thermal protection control strategy is generated, an adjustment execution instruction is calculated by using a fuzzy controller, and the dynamic adjustment scheme of the bearing stability is realized.

[0021] The application provides an air suspension fan predictive maintenance system based on digital twinning, mainly comprising:

[0022] An airflow mutation feature acquisition module is configured to acquire airflow mutation features when high-temperature dust-containing waste gas surges into the air suspension fan, and transmit the airflow mutation features to the digital twinning system to determine the airflow mutation features.

[0023] A foil transient thermal expansion calculation module is configured to calculate foil transient thermal expansion distribution according to the airflow mutation features, and obtain non-uniform expansion amounts of each region of the foil by combining the mutual influence between the temperature field and the stress-strain field of the material.

[0024] A gap narrowing trend extraction module is configured to extract a local gap narrowing trend of the foil and the bearing from the foil non-uniform expansion amounts, calculate a spatial distribution after the gap is narrowed, and obtain a target gas film thickness value.

[0025] A rub-impact risk evaluation module is configured to compare the target gas film thickness value with a preset rub-impact threshold value, and if the target gas film thickness value is less than the threshold value, evaluate a rub-impact risk probability by using a Monte Carlo method.

[0026] A gas film stiffness fluctuation calculation module is configured to calculate a gas film stiffness fluctuation range based on gas dynamics theory if the rub-impact risk probability exceeds a preset safety range.

[0027] A dynamic response parameter calculation module is configured to calculate foil bearing dynamic response parameters of the air suspension fan by using a fluid-structure coupling algorithm according to the gas film stiffness fluctuation range, in combination with the real-time obtained operation conditions and bearing structure of the air suspension fan.

[0028] a stability prediction index calculation module configured to extract vibration amplitude analysis results from the air-suspended fan foil bearing dynamic response parameters and calculate a stability prediction index;

[0029] a real-time evaluation logic optimization module configured to optimize the real-time evaluation logic of the preset digital twin system using an adaptive filtering algorithm, update the bearing wear monitoring data based on the stability prediction index, and determine a failure probability evaluation result;

[0030] a dynamic adjustment scheme generation module configured to generate a control instruction according to the failure probability evaluation result, transmit the control instruction to a thermal shock protection module of the air-suspended fan, and generate a dynamic adjustment scheme for bearing stability.

[0031] The technical scheme provided by the embodiment of the present application can include the following beneficial effects:

[0032] The present application discloses an air-suspended fan predictive maintenance method based on digital twinning, which calculates the foil non-uniform thermal expansion distribution by real-time collection of airflow mutation characteristics when high-temperature dust-containing waste gas rushes in, evaluates the local gap narrowing trend of the bearing, and compares it with the preset rubbing threshold. If there is a rubbing risk, calculate the gas film stiffness fluctuation range based on the gas dynamics theory, analyze the bearing dynamic response using the fluid-structure coupling algorithm, extract the vibration characteristics to calculate the stability index. Finally, the present application optimizes the evaluation logic using an adaptive filtering algorithm, updates the bearing wear monitoring data, determines the failure probability, and generates a dynamic adjustment scheme for bearing stability. This method can effectively predict and prevent the bearing rubbing risk of the air-suspended fan under harsh working conditions, and improve the equipment operation reliability and service life. BRIEF DESCRIPTION OF DRAWINGS

[0033] Fig. 1 The flowchart of the air-suspended fan predictive maintenance method based on digital twinning of the present application.

[0034] Fig. 2 The structural schematic diagram of the air-suspended fan predictive maintenance system based on digital twinning of the present application. DETAILED DESCRIPTION

[0035] The technical scheme of the present application will be described below in conjunction with the embodiments, obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor belong to the scope of protection of the present application.

[0036] As Figs. 1-2 , the air-suspended fan predictive maintenance method based on digital twinning of the present application can specifically include:

[0037] S101, Collect the airflow mutation characteristics of high-temperature dust-containing exhaust gas when it rushes into the air suspension fan in real time through the sensor, transmit to the digital twin system, and determine the airflow mutation characteristic parameters.

[0038] The running environment of the air suspension fan is complex, and the mutation of high-temperature dust-containing exhaust gas may cause bearing stability problems. Therefore, the sensor needs to collect airflow characteristic data in real time and transmit it to the digital twin system for analysis. The collected airflow characteristics include pressure, flow rate, dust concentration and temperature, and the specific operation is completed by multiple sensors in cooperation. The collection process needs to ensure the time synchronization and accuracy of the data to support subsequent transient simulation and risk assessment.

[0039] S1011, Collect airflow pressure data through a piezoelectric pressure sensor, calculate the pressure change rate, and generate an airflow pressure mutation data set.

[0040] The piezoelectric pressure sensor is arranged at multiple measurement points in the airflow channel to collect airflow pressure data in real time. According to the pressure difference between adjacent measurement points and the sampling time interval, the pressure change rate is calculated to form an airflow pressure mutation data set. The sampling frequency can be dynamically adjusted according to the airflow turbulence intensity to improve data accuracy. For example, five measurement points are arranged in the airflow channel with a spacing of 2 meters between adjacent measurement points, and the pressure values are 98 kPa, 97 kPa, 95 kPa, 92 kPa and 88 kPa, respectively. The sampling interval is 0.1 seconds, and the calculated pressure change rate reflects the trend of airflow energy loss.

[0041] S1012, Collect dust concentration data through a dust concentration sensor, combine with the airflow pressure mutation data set, and calculate the gas-solid two-phase flow velocity field distribution.

[0042] The dust concentration sensor is used to obtain the dust concentration data in the exhaust gas, and the concentration is classified and counted according to the particle size range, for example, it is divided into three grades of less than 10 microns, 10 to 50 microns and more than 50 microns, and the concentrations are 280 mg / m 3 , 150 mg / m 3 and 70 mg / m 3 . Combined with the airflow pressure mutation data set, the numerical calculation method is used to generate the gas-solid two-phase flow velocity field distribution, which represents the following characteristics of small particle size dust and the inertial lag characteristics of large particle size dust.

[0043] S1013, Collect exhaust gas temperature data through a thermocouple temperature sensor, combine with the gas-solid two-phase flow velocity field distribution, and generate a temperature field distribution parameter set.

[0044] The thermocouple temperature sensor measures the exhaust gas temperature, with an inlet temperature of 650 degrees Celsius and an outlet temperature of 580 degrees Celsius, showing a nonlinear decay along the way. Combined with the velocity field distribution of gas-solid two-phase flow, the temperature gradient, heat flux and convective heat transfer coefficient are calculated for each measuring point to form a temperature field distribution parameter set. For example, the heat flux in the inlet area is 4200 W / m 2 , and the convective heat transfer coefficient is 85 W / (m·K), which is used for thermal expansion analysis.

[0045] S1014, time synchronization processing is performed on the gas flow pressure mutation data set, the gas-solid two-phase flow velocity field distribution and the temperature field distribution parameter set, a gas flow state space is constructed, and a gas flow mutation characteristic parameter matrix is calculated.

[0046] The data collector is used to perform time synchronization processing on the above data set to generate a multi-dimensional gas flow characteristic data group. Based on this data group, a gas flow state space is constructed, and a mapping relationship between pressure, flow rate, dust concentration and temperature is fitted by the least squares method to generate a gas flow mutation characteristic parameter matrix. The matrix reflects the coupling relationship between parameters, for example, when the pressure decreases by 10 kPa, the flow rate decreases by 20%, the dust concentration increases by 35%, and the temperature increases by 60 degrees Celsius. When the monitoring parameters exceed the preset threshold interval, such as pressure fluctuation ± 15 kPa, an alarm signal is output.

[0047] Through multi-sensor cooperative collection and data synchronization processing, the mutation characteristics of high-temperature dust-containing exhaust gas can be accurately characterized, providing reliable input for foil thermal expansion and gas film thickness analysis. In practical applications, the gas flow mutation characteristic parameter matrix supports online monitoring and early warning, significantly improving the real-time performance and accuracy of bearing stability prediction, and reducing the risk of collision caused by gas flow disturbance.

[0048] S102, based on the gas flow mutation characteristic parameters, a finite element analysis method is used to calculate the transient thermal expansion distribution of the air suspension fan foil bearing, and the non-uniform expansion amount of each region of the foil is determined combined with the thermal-mechanical coupling characteristics of the material.

[0049] The gas flow mutation characteristic parameters provide key input for foil thermal expansion analysis, covering the dynamic changes of temperature, pressure and dust concentration. Finite element analysis accurately simulates the transient thermal expansion behavior under the action of high-temperature dust-containing exhaust gas by constructing a foil geometric model and combining the thermodynamic properties of the material. The interaction of temperature field, stress field and strain field needs to be considered in the calculation process to ensure the accuracy of the non-uniform expansion amount. The specific meshing algorithm is not limited in the embodiments of the present application, which can be adjusted by the technician according to the actual scene.

[0050] S1021, based on the temperature data in the gas flow mutation characteristic parameters, an adaptive meshing technique is used to generate an initial temperature field distribution of the foil.

[0051] The temperature data in the airflow mutation characteristic parameter is used for initializing the foil temperature field. The adaptive quadrilateral mesh is adopted for dividing the foil geometric region, and the mesh density is dynamically adjusted according to the temperature gradient. For example, when the airflow temperature fluctuates between 350 degrees Celsius and 650 degrees Celsius, the region with a large temperature gradient on the foil surface needs to be encrypted with the mesh, and the mesh size of the edge region is about 0.5 mm, and the mesh size of the center region is about 2 mm. When the temperature gradient difference of adjacent mesh units is less than the preset threshold of 5 degrees Celsius / mm, it is determined that the mesh converges, and the initial temperature field distribution of the foil is generated, providing a basis for stress analysis.

[0052] In S1022, the Lagrange interpolation method is used to calculate the stress field distribution of the foil, and the initial value of the stress and strain field is generated, in combination with the thermal expansion coefficient and the elastic modulus of the material.

[0053] The thermal expansion coefficient and the elastic modulus of the foil material are key parameters for calculating thermal stress. Taking a stainless steel foil as an example, the thermal expansion coefficient is 16.5x10 -6 / degrees Celsius, and the elastic modulus is 193 GPa. Based on the initial temperature field distribution, the Lagrange interpolation method is used to calculate the stress field distribution of each mesh unit node, and the initial value of the stress and strain field is generated. For example, when the temperature in the center region of the foil increases by 100 degrees Celsius, the main diagonal element of the thermal stress coefficient matrix is about 320 MPa, and the stress value in the center region can reach 275 MPa, reflecting the significant tensile stress caused by temperature change.

[0054] In S1023, the displacement increment of the mesh unit node is calculated by the linear elastic constitutive equation, and the transient deformation field data of the foil is generated in combination with the temperature field distribution.

[0055] The linear elastic constitutive equation is used to quantify the deformation of the foil under the combined action of temperature and stress. According to the initial value of the stress and strain field, the displacement increment of each mesh unit node is calculated. For example, when the stress in the center region is 275 MPa and the temperature increases by 100 degrees Celsius, the node displacement increment is about 0.18 mm, mainly distributed along the radial direction. In combination with the temperature field distribution, the local deformation of the foil is solved, and the transient deformation field data is generated, reflecting the nonlinear deformation characteristics of the foil in a high-temperature environment.

[0056] In S1024, the least squares method is used to fit the thermal conductivity distribution of the foil, and the node thermal displacement vector is calculated by the finite difference method in combination with the temperature stress coupling coefficient.

[0057] The foil thermal conductivity dynamically adjusts with temperature changes, for example, 15 W / (m·K) at 350 degrees Celsius and reduces to 12 W / (m·K) at 650 degrees Celsius. The thermal conductivity distribution is fitted by the least squares method, and the temperature stress coupling coefficient is calculated in combination with the stress field data. When the stress exceeds 200 MPa, the coupling coefficient is about 0.85. Based on the heat conduction equation set, the finite difference method is used to solve the thermal displacement vector of each grid element node. The maximum radial thermal expansion is about 0.45 mm, and the maximum circumferential thermal expansion is about 0.15 mm, reflecting the regional differences of non-uniform thermal expansion.

[0058] S1025, based on the foil transient deformation field data, the thermal deformation gradient is calculated by using the node strain interpolation method, and the non-uniform expansion of each region of the foil is determined.

[0059] The node strain interpolation method is used to analyze the spatial distribution of the thermal deformation gradient of the foil. In the transition region with large temperature and stress gradients, the thermal deformation gradient can reach 0.12 mm / mm, while in the uniform region it is only 0.03 mm / mm. Combined with the stress field distribution, the non-uniform expansion of each grid element of the foil is calculated, and the expansion of the central region is larger and the expansion of the edge region is smaller. This non-uniform expansion feature directly affects the gas film thickness and needs to provide accurate input for subsequent collision and wear risk assessment.

[0060] Through multi-level finite element analysis and thermal force coupling calculation, the transient thermal expansion behavior of the foil under sudden changes in airflow can be accurately characterized. Compared with traditional static analysis, this application dynamically adjusts the grid density and integrates the temperature stress coupling effect, significantly improving the calculation accuracy. In practical applications, accurate quantification of non-uniform expansion supports gas film thickness analysis and stability prediction, reduces the collision and wear risk caused by thermal expansion, and improves the operation reliability of air suspension fans.

[0061] S103, based on the non-uniform thermal expansion distribution data of the foil, the local gap change trend of the air suspension fan foil and the bearing is extracted, and the target gas film thickness distribution is calculated.

[0062] The non-uniform thermal expansion of the foil directly affects the bearing gap, and then determines the gas film thickness and stability. Based on the aforementioned thermal expansion data, this step accurately quantifies the influence of gap change on gas film thickness by constructing a deformed foil grid, calculating the contact stress distribution and gas film pressure field. The geometric mapping algorithm combined with fluid dynamics theory ensures the accuracy of gas film thickness calculation and the reliability of stability verification. This method dynamically responds to the gap change caused by high-temperature dust-containing exhaust gas through multi-level analysis, providing key input for subsequent collision and wear risk assessment.

[0063] S1031, according to the non-uniform thermal expansion data of the foil, a deformed foil grid matrix is constructed, the bearing surface displacement distribution is calculated by using the Lagrange interpolation method, and the influence of surface roughness is corrected.

[0064] The foil non-uniform thermal expansion data is used to generate a deformed mesh matrix. Taking a circular foil with a diameter of 200 mm as an example, 50x50 grid points are arranged along the radial and circumferential directions to discretely express the deformation variables. Thermal expansion causes the grid point coordinates to shift, with a maximum radial displacement of about 0.45 mm and a circumferential displacement of about 0.15 mm. The Lagrange interpolation method is used to calculate the displacement distribution of the bearing surface to generate a continuous displacement field. Considering the variation of the bearing surface roughness from 0.8 microns to 1.2 microns, the influence of roughness on the calculation of the gap is eliminated by coordinate correction to ensure the accuracy of the initial contact gap field.

[0065] S1032, based on the bearing surface displacement distribution, a contact stress distribution matrix is constructed, and a Bezier curve is used to fit the surface profile characteristics to calculate the local contact pressure field.

[0066] The bearing surface displacement distribution is used to construct the contact stress distribution matrix, reflecting the mechanical interaction between the foil and the bearing. A Bezier curve is used to fit the surface profile feature points, with a control point spacing of 5 mm to ensure the smoothness and accuracy of the fitted curve. The contact deformation is calculated based on the surface normal vector, with a normal inclination angle fluctuating within ±15 degrees and a local contact pressure distributed between 2 MPa and 5 MPa. The generation of the contact pressure field is based on the principles of contact mechanics, accurately representing the gap narrowing trend and providing a basis for gas film pressure analysis.

[0067] S1033, according to the local contact pressure field, the Reynolds equation is used to solve the gas film pressure field, a gas film pressure distribution matrix is constructed, and the gas film carrying capacity is calculated.

[0068] The local contact pressure field is used to establish the gas film pressure field equation, which follows the fluid dynamics law described by the Reynolds equation. Through numerical solution, a gas film pressure distribution matrix is generated, showing that the pressure peak is located in the foil inlet area, about 0.8 MPa. The circumferential pressure gradient shows periodic variation, with a maximum gradient of about 0.5 MPa / mm at the minimum gap. Based on the pressure distribution matrix, the gas film carrying capacity is calculated, with a unit area carrying capacity of about 0.4 MPa under typical working conditions, providing mechanical basis for gas film thickness response analysis.

[0069] S1034, based on the gas film pressure distribution matrix, a spatial mapping method is used to establish a gas film thickness response function, combined with the gas film compression characteristic curve, to calculate the target gas film thickness distribution.

[0070] The spatial mapping method is used to construct the gas film thickness response function to quantify the influence of pressure change on thickness. The gas film compression characteristic curve is nonlinear, with a compression ratio of 1.2 to 1.5. When the pressure increases by 0.1 MPa, the gas film thickness decreases by about 0.01 mm. Combined with the pressure distribution matrix, the target gas film thickness is calculated, with a thickness of 15 microns to 25 microns under stable working conditions, and a circumferential deviation of less than 5 microns, ensuring the uniformity and stability of the thickness distribution.

[0071] The rationality of the gas film thickness distribution is verified by the aerodynamic force balance equation, and the final gas film thickness field is generated.

[0072] The aerodynamic force balance equation is used to verify the stability of the gas film thickness field. When the gas film bearing capacity is balanced with the external load, the thickness field tends to be stable. The calculation results show that the circumferential uniformity of the gas film thickness field is good, and the maximum deviation is not more than 5 microns. This uniform distribution effectively reduces the risk of gas film disorder caused by uneven gap. In practical application, the accurate gas film thickness field provides reliable data for bearing stability evaluation, and supports the reliable operation of air suspension fan in high temperature dust environment.

[0073] S104, the target gas film thickness of the air suspension fan foil bearing is compared with the preset collision and grinding threshold, and if it is lower than the threshold, the Monte Carlo method is used to evaluate the collision and grinding risk probability.

[0074] The spatial distribution of the target gas film thickness directly affects the stability of the bearing, especially in high temperature dust environment, local gap may cause collision and grinding failure. By comparing with the preset threshold, the high risk area is identified, and the probability analysis and dynamic stress evolution are combined to quantify the possibility and damage degree of collision and grinding. The Monte Carlo method improves the robustness of risk assessment by simulating multiple random working conditions, and provides data support for subsequent maintenance strategy optimization. This method does not strictly limit the specific probability distribution model, which can be adjusted according to actual needs.

[0075] S1041, based on the numerical value of the target gas film thickness, a grid spatial distribution function is constructed, and the local collision and grinding point position probability is calculated by random sampling using Bernoulli distribution.

[0076] The target gas film thickness is processed by grid to generate a spatial distribution function, which represents the thickness change of each region on the bearing surface. For example, the gas film thickness is sampled every 10 degrees in the circumferential 360 degree range to construct a discrete distribution model. When the local thickness is lower than the preset collision and grinding threshold of 15 microns, Bernoulli distribution is used for random sampling to calculate the collision and grinding point position probability. The sampling results show that when the thickness decreases to 12 microns, the collision and grinding probability of local area can reach 0.35. This probability distribution reflects the direct influence of non-uniformity of gas film thickness on collision and grinding risk, and provides position basis for stress analysis.

[0077] S1042, according to the local collision and grinding point position probability, the bearing load stress distribution is constructed, and the collision and grinding contact stress field is calculated combined with the material surface finish parameters.

[0078] The local impact point position probability is used to generate the bearing load stress distribution, and the stress concentration effect is quantified by combining the material surface finish parameters. Taking the surface finish of 0.8 microns as an example, the local stress concentration coefficient is about 1.8, and under the nominal contact stress of 5 MPa, the maximum local stress can reach 9 MPa. Considering the friction coefficient of 0.15, the tangential stress component is calculated to be about 1.35 MPa, forming a complete impact contact stress field. This stress field reflects the mechanical properties of the impact area, laying the foundation for friction heat and vibration analysis.

[0079] S1043, based on the impact contact stress field, a friction heat power field is constructed, and a random forest algorithm is used to predict the dynamic stress evolution curve to generate a foil vibration amplitude distribution.

[0080] The impact contact stress field is used to calculate the friction heat power field, which characterizes the energy conversion during the impact process. When the impact duration exceeds 0.1 seconds, the local friction heat power can reach 250 watts per square centimeter, causing the temperature to rise rapidly. Using the random forest algorithm, through the integration of multiple decision trees, the dynamic stress evolution curve is predicted, and the input features include stress amplitude, contact duration and temperature change. The prediction results show that the stress fluctuation is between 0.5 MPa and 2 MPa, and the maximum foil vibration amplitude is 0.15 millimeters, reflecting the dynamic response characteristics caused by the impact.

[0081] According to the foil vibration amplitude distribution, the gas film thickness decay law is calculated, the impact damage cumulative function is constructed combined with the collision impact force data, and the maximum likelihood estimation is used to determine the impact risk probability.

[0082] The foil vibration amplitude distribution is used to analyze the gas film thickness decay law. For example, when the single collision impact force peak value is 15N, the gas film thickness decay rate is about 0.5 microns per second. The impact damage cumulative function is constructed by Weibull distribution to quantify the trend of damage accumulation over time. Using maximum likelihood estimation, the parameters of the lognormal distribution are fitted, and the mean-1.2, standard deviation 0.4 impact risk probability distribution is obtained. At the 95% confidence level, the impact risk probability is about 0.28, indicating that there is a 28% probability of significant damage. In practical applications, this probability prediction supports dynamic maintenance decisions and extends the bearing life.

[0083] S105, if the impact risk probability of the air-suspended fan foil bearing exceeds the preset safety range, the temperature and impurity content data of the high-temperature dust-containing waste gas are collected in real time through the sensor, and the gas film stiffness fluctuation range is calculated based on the gas dynamics theory.

[0084] When the risk probability of rubbing exceeds the preset safety threshold, it indicates that the bearing may face the risk of instability. To this end, through the cooperative collection of exhaust gas characteristic data by multiple sensors, combined with gas dynamics theory, the influence of gas film stiffness fluctuation on bearing stability is analyzed. The calculation process integrates temperature field, impurity concentration and pressure distribution to build a dynamic model of gas film stiffness, ensuring the accuracy and reliability of the evaluation results. This method supports dynamic adjustment of maintenance strategy and prolongs the service life of the bearing.

[0085] S1051, collect exhaust gas temperature and gradient distribution through thermocouple sensor and thermistor array, and fit the gas temperature field function by least squares method.

[0086] In the application embodiment, the thermocouple sensor is arranged along the circumference of the bearing with 8 measuring points, the sampling frequency is 100 Hz, the exhaust gas temperature is monitored in real time, and the range is 350-650 degrees Celsius. The thermistor array measures the temperature gradient, and the maximum value reaches 15 degrees Celsius per millimeter. The least squares method is used to fit the temperature field function to generate a continuous spatial distribution model reflecting the non-uniform characteristics of exhaust gas temperature. The fitting process is optimized by polynomial regression to ensure the accuracy of the function and provide reliable input for gas density calculation.

[0087] S1052, measure the exhaust gas impurity concentration distribution based on the laser particle size sensor, and calculate the gas density change rate and gas-solid two-phase flow velocity field based on the gas state equation and Navier-Stokes equation.

[0088] The laser particle size sensor analyzes the exhaust gas impurity concentration, and the particle size distribution is as follows: less than 10 microns accounts for 65%, 10-50 microns accounts for 25%, and more than 50 microns accounts for 10%. Based on the gas state equation, the gas density changes with temperature, for example, the density is 0.55 kg / m3 at 350 degrees Celsius and decreases to 0.35 kg / m3 at 650 degrees Celsius. Combined with the Navier-Stokes equation, the numerical solution of the gas-solid two-phase flow velocity field is obtained, and the gas flow velocity fluctuates between 15-25 m / s, which characterizes the small particle followability and large particle inertia lag, providing flow field data for gas film pressure analysis.

[0089] S1053, collect gas film pressure distribution through pressure sensor array, build gas film stress distribution function, and solve gas film deformation response characteristics by finite difference method.

[0090] The pressure sensor array is arranged along the circumference with 12 measuring points, and the peak value of the gas film pressure is 0.8 MPa, and the fluctuation amplitude is 0.2 MPa. Based on the pressure data, the gas film stress distribution function is constructed, and the maximum tangential stress 1.5 MPa appears in the region with the maximum pressure gradient. By discretizing the Reynolds equation, the finite difference method is used to calculate the gas film deformation response, and the thickness change rate reaches 0.5 microns / millisecond. This dynamic response characteristic reflects the deformation behavior of the gas film under pressure disturbance, providing mechanical basis for stiffness calculation.

[0091] S105, based on the gas film deformation response characteristics, combined with the gas dynamic viscosity and Reynolds number, the aerodynamic load distribution is calculated, and the gas film stiffness fluctuation range and stability are determined through the gas film damping characteristic equation and Bayesian regression.

[0092] The gas film deformation response characteristics are used to construct the stiffness calculation model. The gas dynamic viscosity changes with temperature, which is 2.3×10 -5 Pa·s at 350 degrees Celsius, and increases to 3.1×10 -5 Pa·s at 650 degrees Celsius. The Reynolds number is between 8000 and 12000, indicating a turbulent flow state. The aerodynamic load is calculated, and the bearing capacity per unit area is about 0.4 MPa. Based on the gas film damping characteristic equation, the radial stiffness coefficient is solved to be 1.2×10 5 to 1.8×10 5 N / m, and the angular stiffness is about 0.6 times of it, and the damping ratio is 0.15 to 0.25. Bayesian regression is used to integrate the stiffness and damping data to predict the stiffness fluctuation range of ±20% of the nominal value. When the fluctuation exceeds the limit, the stability decreases, and the operating parameters need to be adjusted to maintain the reliable operation of the bearing.

[0093] S106, based on the gas film stiffness fluctuation range, combined with the real-time collected air suspension fan operating conditions and bearing structure data, the fluid-structure coupling algorithm is used to calculate the dynamic response parameters of the foil bearing, including the shaft orbit, vibration amplitude and minimum gas film thickness.

[0094] The gas film stiffness fluctuation range reflects the disturbance effect of high-temperature dust-containing waste gas on the dynamic behavior of the bearing. Real-time fan operating data is collected by sensors, combined with the fluid-structure coupling algorithm, to accurately simulate the interaction between the gas film and the foil structure, and to quantify the dynamic response characteristics of the bearing. The calculation process considers the speed fluctuation, load distribution and material mechanics characteristics to ensure the reliability and accuracy of the results. This method supports dynamic optimization of operating parameters to improve the stability of the fan in complex environments.

[0095] S1061, the fan speed fluctuation rate and dynamic balance degree data are collected by sensors, combined with the bearing gap ratio and pre-tightening parameters, to construct the aerodynamic load distribution function.

[0096] The sensors real-time monitor the fan operating state, the speed fluctuation rate is about 5%, and the dynamic balance degree reaches G2.5 level. The bearing gap ratio is set to 2.5‰, and the pre-tightening degree is 0.15. These parameters generate the aerodynamic load distribution function through numerical mapping, which represents the spatial distribution characteristics of the load. The function is constructed based on polynomial interpolation, considering the non-linear effects of speed and gap, to ensure that the load distribution reflects the actual working condition and provides mechanical input for subsequent stress field calculation.

[0097] S1062. Based on the aerodynamic load distribution function, the stress field and deformation of the foil structure are calculated using the elasticity equations, and the air film pressure distribution field is generated by the finite volume method.

[0098] Aerodynamic load distribution functions were used to solve the stress field of the foil structure. Using the equations of elasticity, combined with Young's modulus and Poisson's ratio of the foil material, the stress distribution was calculated, with a maximum deformation of approximately 0.08 mm. The air film space was discretized using the finite volume method, with 120 grid points in the circumferential direction and 60 in the axial direction, generating the air film pressure distribution field. The results show that the pressure peak of 0.8 MPa occurs in the minimum gap region, and the circumferential pressure fluctuation amplitude is 0.2 MPa, reflecting the periodic mechanical characteristics of the air film.

[0099] The interaction between film pressure and foil deformation is calculated using a fluid-structure interaction iterative solver. Combined with the film compressibility ratio, the transient flow field distribution is generated and the axis offset is analyzed.

[0100] The fluid-structure interaction iterative solver calculates the dynamic equilibrium between film pressure and foil deformation using Newton's iteration method, achieving a convergence accuracy of 0.001 mm. The film compressibility ratio fluctuates between 1.2 and 1.5, reflecting the gas compressibility characteristics. The transient flow field distribution reveals the unsteady nature of the gas flow, with the axis offset varying between 0.15 mm and 0.25 mm. The ratio of the major axis to the minor axis of the elliptical axis trajectory is approximately 1.8, indicating the influence of bearing anisotropy on the dynamic response and providing data support for vibration analysis.

[0101] S1063. Based on the transient flow field distribution, a set of control equations for foil vibration is constructed. The Runge-Kutta method is used to calculate the vibration acceleration and axial displacement. The main vibration frequency is determined by fast Fourier transform.

[0102] The transient flow field distribution was used to establish the vibration control equations, describing the dynamic behavior of the foil under film disturbance. The Runge-Kutta method was used to solve the differential equations, calculating a peak vibration acceleration of 50 m / s² and a maximum axial displacement of 0.12 mm. Fast Fourier Transform analysis of the vibration signal revealed a dominant vibration frequency of 0.47 times the rotational frequency, accompanied by second and third harmonic components with amplitudes of 0.35 and 0.15 times the fundamental frequency, respectively. This frequency distribution reveals the multiharmonic characteristics of the vibration, supporting stability assessment.

[0103] S1064. Based on the vibration characteristics, construct the air film thickness distribution function, fit the air film pressure fluctuation curve using the least squares method, and calculate the minimum air film thickness using the aerodynamic balance equation.

[0104] The vibration characteristics are used to generate the gas film thickness distribution function, which characterizes the periodic variation of thickness with time and space. The least squares method is used to fit the gas film pressure fluctuation curve, the fluctuation frequency is synchronized with the rotating speed, and the amplitude is about 25% of the average pressure. Through the aerodynamic force balance equation, the minimum gas film thickness is calculated to be about 15 microns, located in the load-carrying area. The calculation error is controlled within 5%, which verifies the rationality of the thickness distribution and provides accurate data for the optimization of bearing dynamic response.

[0105] S107, extract the vibration amplitude analysis results from the dynamic response parameters of the air suspension fan foil bearing, calculate the stability prediction index, including the logarithmic decay rate and the whirling frequency ratio.

[0106] The dynamic response parameters of the foil bearing provide the basis for vibration characteristic analysis, through time-frequency domain signal processing and stability modeling, the dynamic behavior of the bearing in high temperature dust-containing waste gas environment is quantified. The calculation process considers the vibration attenuation and whirling characteristics, adopts multi-scale signal decomposition and spectrum analysis, ensures the accuracy of the stability index. This method provides a key basis for dynamic maintenance strategy optimization, supports reliable operation of the fan.

[0107] S1071, obtain the vibration time domain signal in the dynamic response parameters of the foil bearing, adopt wavelet transform to decompose the frequency components, and construct the vibration amplitude envelope spectrum.

[0108] The vibration time domain signal is collected by the sensor, the sampling frequency is 10 kHz, the duration is 10 seconds, and it presents periodic fluctuation. Wavelet transform is used for multi-scale decomposition, identifying the fundamental frequency 120 Hz and the multiple frequency 240 Hz and 360 Hz components. Wavelet transform decomposes the signal into different frequency subbands through discrete wavelet basis functions, preserving the time-frequency local characteristics. Based on the decomposition results, the Hilbert transform is used to generate the vibration amplitude envelope spectrum, with an amplitude range of 0.15 mm to 0.25 mm, reflecting the dynamic changes of vibration intensity, providing data basis for attenuation analysis.

[0109] S1072, according to the vibration amplitude envelope spectrum, calculate the amplitude ratio of adjacent vibration periods, combine with the damping coefficient, and use the vibration response equation to calculate the logarithmic decay rate.

[0110] The vibration amplitude envelope spectrum is used to quantify the attenuation characteristics of vibration. By comparing the amplitudes of adjacent periods, the ratio is about 1.12, indicating a 10.7% attenuation per period. Combined with the damping coefficient of 0.18, the vibration response equation is constructed, based on the exponential decay model, the logarithmic decay rate is calculated to be about 0.113. The equation considers the coupling effects of mass, stiffness and damping, reflects the vibration suppression ability of the bearing, ensures the physical consistency of the decay rate calculation.

[0111] Based on the logarithmic decrement and dynamic stiffness ratio, a bearing stability evaluation matrix is constructed, and the whirling component is extracted by fast Fourier transform to calculate the whirling frequency ratio.

[0112] The bearing stability evaluation matrix combines the logarithmic decrement and dynamic stiffness ratio, and the stiffness ratio ranges from 1.5 to 2.0. The vibration signal is processed by fast Fourier transform to extract the whirling component, with an amplitude of about 0.35 times the fundamental frequency and an angular velocity of 0.47 times the rotational speed. The main frequency of the whirl is 56 Hz, obtained by discrete Fourier transform, and compared with the critical speed of 32,000 rpm, the whirling frequency ratio is 0.105. The matrix analysis combined with the spectral analysis method generates the vibration response function, revealing the resonance peaks at 120 Hz, 240 Hz and 360 Hz, with an amplitude ratio of 1:0.35:0.15, reflecting the frequency characteristics of the system.

[0113] S1073, according to the whirling frequency ratio and the vibration response function, a dynamic characteristic evaluation function is constructed, and an autoregressive model is used to predict the trend of the logarithmic decrement and the whirling frequency ratio.

[0114] In the application embodiment, the whirling frequency ratio and the vibration response function are used to construct the dynamic characteristic evaluation function, and the system stability margin is quantified as about 0.28. An autoregressive model is used to fit the historical vibration data and predict the trend in the next 1000 rotor periods. The model is based on time series and considers autocorrelation, predicting that the logarithmic decrement fluctuates between 0.105 and 0.125, and the whirling frequency ratio fluctuates between 0.095 and 0.115. This prediction supports long-term stability evaluation, optimizes maintenance decisions, and improves the reliability of bearings in complex operating conditions.

[0115] S108, an adaptive filtering algorithm is used to optimize the real-time evaluation logic of the digital twin system, and the wear monitoring data of the air-suspended fan foil bearing is updated based on the stability prediction index to generate the failure probability evaluation result.

[0116] The wear monitoring data of the foil bearing is processed by an adaptive filtering algorithm, combined with the stability prediction index, to dynamically optimize the evaluation logic of the digital twin system. The algorithm integrates time and frequency domain features to construct a wear state model and accurately predict the failure probability. The processing process considers noise suppression, state estimation and probability analysis to ensure the robustness and real-time performance of the evaluation result. This method supports optimizing maintenance strategies and prolonging the service life of bearings in high-temperature dust-containing exhaust gas environments.

[0117] S1081, the bearing wear data features are extracted by a state observation equation, the measurement noise variance is calculated, the filtering gain coefficient is optimized, and a state transition equation is constructed.

[0118] The state observation equation is used to describe the dynamic characteristics of bearing wear data, and the input is the vibration signal and the wear measurement value. The measurement noise variance is adjusted from the initial 0.01 to 0.05, reflecting the change of operating conditions. Based on the noise variance, the filtering gain coefficient is calculated, ranging from 0.8 to 0.4, which optimizes the state estimation through the Kalman filtering principle. The state transition equation is based on the system noise covariance, and the covariance converges from 0.02 to 0.008, generating real-time response characteristics with a delay time of less than 100 milliseconds, providing high-precision input for wear rate analysis.

[0119] S1082, based on the real-time response characteristics, a state estimation function is constructed, a deep neural network is used to predict the wear rate, and a life degradation curve is generated.

[0120] The state estimation function is generated by the state transition equation, and the root mean square error is controlled within 3%. The wear rate is predicted by a deep neural network, and the network structure includes three fully connected layers with ReLU activation function, and the input features include vibration amplitude, temperature and load. The prediction results show that the wear rate is 0.5 microns / hour under normal conditions, and increases to 0.8 microns / hour when the load increases by 20%. Based on the predicted data, a life degradation curve is constructed, which conforms to the Weibull distribution, with a characteristic life of about 5000 hours, reflecting the degradation trend of the bearing.

[0121] Fusion of wear rate and stability prediction index, construction of failure probability transition matrix, calculation of bearing residual life distribution and failure probability by Markov chain and Monte Carlo method.

[0122] The failure probability transition matrix is constructed based on the wear rate and stability index, and the matrix elements represent the state transition probability, for example, the probability of normal to sub-health state is 0.15, and the probability of sub-health to failure is 0.25. The Markov chain is used to analyze the state evolution, and the Monte Carlo method is used for 10000 times of iteration sampling to generate the residual life distribution, and the failure probability threshold interval is 0.1 to 0.3. At the 95% confidence level, the early failure probability is 0.12, the normal life failure probability is 0.75, and the super long life probability is 0.13. The evaluation logic adjusts the parameters according to a 1-hour update cycle, with a correction of 15% of the original value, optimizing the prediction accuracy.

[0123] S1083, extract the time domain and frequency domain features of bearing wear monitoring data, generate a prediction residual sequence using a long short-term memory network, optimize the filtering parameters and reconstruct the wear data.

[0124] The wear monitoring data is characterized by a root mean square value of 0.35 mm / s and a spectral kurtosis value of 3.8. The Hilbert transform generates an envelope spectrum, and the fault characteristic frequency is 0.47 times the shaft frequency, with sideband frequencies ranging from 120 Hz to 360 Hz. A long short-term memory network is used to generate a prediction residual sequence combined with time-frequency joint features. Singular value decomposition is used to extract the noise subspace, with eigenvalues of 2.5, 1.8, and 0.9, a residual convergence degree of 0.95, and a noise covariance matrix trace value of 0.15. The recursive least squares method optimizes the noise suppression coefficient to 0.82, and the reconstructed data correlation coefficient reaches 0.96, significantly improving the signal-to-noise ratio.

[0125] S1084, based on the reconstructed data, a wavelet transform is used to extract wear feature coefficients, a wear amount evolution equation is constructed, and a wear amount time series curve and cumulative failure probability are generated through data fusion.

[0126] The wavelet transform extracts feature coefficients of 0.28 in the 250 Hz frequency band at the 4th layer decomposition, which is consistent with the fault frequency. The eigenvalues of the wear amount evolution equation are -0.15 ± 0.08j, reflecting the stable attenuation characteristics. Based on the evolution equation, a time series state matrix is generated, and a Markov chain is used to calculate the probability of normal to light wear 0.15 and light to moderate wear 0.25. A Wiener filter with a bandwidth of 100 Hz fuses the residual and time series data, and the wear amount growth rate is stable at 0.02 mm / hour, with an overload of 0.05 mm / hour. The failure probability density function shows a right-skewed distribution, and the state transition matrix predicts a failure probability of 0.28 within 1000 hours, with a fitting degree of 92%, providing a reliable basis for maintenance decisions.

[0127] S109, according to the failure probability evaluation results, control instructions are generated and transmitted to the thermal shock protection module of the air suspension fan, and the bearing stability regulation scheme is dynamically optimized.

[0128] The failure probability evaluation results provide key inputs for thermal shock protection, and by generating accurate control instructions, the bearing operating state is dynamically adjusted. The scheme considers temperature control, cooling power distribution, and stability monitoring, and uses adaptive control and intelligent algorithms to optimize the response characteristics, ensuring the reliable operation of the bearing under extreme working conditions. This method reduces the failure risk and prolongs the service life of the equipment through real-time feedback and dynamic optimization.

[0129] S1091, based on the failure probability evaluation results, a set of thermal shock protection parameters is constructed, a temperature control curve is generated, and a temperature dynamic adjustment sequence is calculated through an adaptive controller.

[0130] The thermal shock protection parameter set is triggered based on the failure probability, when the probability exceeds 0.35, the temperature adjustment ratio is set to 1.5, and the cooling power is 2.5 kW. Using these parameters, the temperature control curve is generated by polynomial interpolation, which represents the change rule of the target temperature over time. The adaptive controller generates a temperature dynamic adjustment sequence based on real-time temperature feedback using a proportional-integral-derivative algorithm, with a response time controlled within 100 milliseconds to ensure fast adaptation to temperature fluctuations and provide a basis for command generation.

[0131] S1092, the temperature dynamic adjustment sequence is converted into digital control instructions, which are transmitted to the thermal shock protection device through a serial communication interface, and the instruction execution timing is optimized.

[0132] The temperature dynamic adjustment sequence generates digital control instructions through encoding, which are transmitted to the thermal shock protection device through the RS485 interface at a rate of 115200 bits / s. Considering the 5ms signal transmission delay, a feedforward compensation algorithm is used to optimize the instruction execution timing, with a delay controlled within 10ms. The optimization process adjusts the transmission interval by predicting the signal propagation time to ensure accurate execution of the instructions and improve the real-time performance of the thermal shock protection.

[0133] Based on the instruction execution timing, a bearing operating state parameter set is constructed to generate a dynamic characteristic monitoring function, and a regulation gain curve is predicted to optimize the thermal power distribution.

[0134] The instruction execution timing is used to generate a bearing operating state parameter set, including a vibration amplitude of 0.15mm and a temperature fluctuation of ±15℃. Based on the parameter set, a dynamic characteristic monitoring function is constructed, and a regulation gain curve is predicted by support vector regression, with a normal working condition gain of 0.8 and an overload working condition gain of 0.5. Combined with a temperature change rate of 5℃ / min, the thermal power dynamic distribution ratio is calculated, and when the fast response mode is triggered, the cooling power reaches 85% of the rated value within 0.5s, effectively suppressing temperature overshoot.

[0135] S1093, the dynamic programming method is used to optimize the thermal shock response characteristics, and a fuzzy controller is used to generate a bearing thermal protection control strategy to dynamically adjust the stability parameters.

[0136] The dynamic programming method optimizes the thermal shock response by minimizing the temperature fluctuation amplitude, controlling the fluctuation within ±8℃. The fuzzy controller adopts a three-layer structure, with input temperature deviation, change rate and vibration amplitude, and output adjustment instruction strength and duration. After optimizing the membership function, the controller responds quickly to rapid fluctuations and adjusts smoothly to slow changes. When the temperature rises rapidly, the controller increases the cooling power and reduces the pre-tightening force, and restores the parameters after stabilization, reducing the failure probability by 45% and significantly improving the bearing life.

[0137] The present application provides an air suspension fan predictive maintenance system based on digital twinning, mainly comprising:

[0138] The air flow mutation feature acquisition module is configured to acquire the air flow mutation feature when the high-temperature dust-containing exhaust gas rushes into the air suspension fan, and transmit the air flow mutation feature to the digital twin system to determine the air flow mutation feature.

[0139] The foil transient thermal expansion calculation module is configured to calculate the foil transient thermal expansion distribution according to the air flow mutation feature, and obtain the non-uniform expansion amount of each region of the foil by combining the mutual influence between the temperature field and the stress-strain field of the material.

[0140] The gap narrowing trend extraction module is configured to extract the local gap narrowing trend of the foil and the bearing from the non-uniform expansion amount of the foil, calculate the spatial distribution after the gap is narrowed, and obtain the target gas film thickness value.

[0141] The rub-impact risk assessment module is configured to compare the target gas film thickness value with a preset rub-impact threshold value, and if the target gas film thickness value is less than the threshold value, assess the rub-impact risk probability by the Monte Carlo method.

[0142] The gas film stiffness fluctuation calculation module is configured to calculate the gas film stiffness fluctuation range based on the gas dynamics theory if the rub-impact risk probability exceeds a preset safety range.

[0143] The dynamic response parameter calculation module is configured to calculate the dynamic response parameter of the foil bearing of the air suspension fan by the fluid-structure coupling algorithm according to the gas film stiffness fluctuation range, in combination with the real-time acquired operating conditions and bearing structure of the air suspension fan.

[0144] The stability prediction index calculation module is configured to extract the vibration amplitude analysis result from the dynamic response parameter of the foil bearing of the air suspension fan, and calculate the stability prediction index.

[0145] The real-time evaluation logic optimization module is configured to optimize the real-time evaluation logic of the preset digital twin system by the adaptive filtering algorithm, update the bearing wear monitoring data based on the stability prediction index, and determine the failure probability evaluation result.

[0146] The dynamic adjustment scheme generation module is configured to generate a control instruction according to the failure probability evaluation result, and transmit the control instruction to the thermal shock protection module of the air suspension fan to generate a dynamic adjustment scheme for the bearing stability.

[0147] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above specific embodiments are merely specific embodiments of the present application and are not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A predictive maintenance method for air-suspended fans based on digital twins, characterized in that, The method includes: The characteristics of airflow abrupt change when high-temperature dust-laden exhaust gas enters the air suspension fan are collected and transmitted to the digital twin system to determine the characteristics of airflow abrupt change. The transient thermal expansion distribution of the foil is calculated based on the characteristics of sudden airflow changes. The non-uniform expansion amount in each region of the foil is obtained by combining the interaction between the temperature field and the stress-strain field of the material. The shrinkage trend of the local gap between the foil and the bearing is extracted from the non-uniform expansion of the foil, and the spatial distribution after the gap shrinkage is calculated to obtain the target air film thickness value. The target air film thickness is compared with a preset impact threshold. If it is less than the threshold, the probability of impact risk is assessed using the Monte Carlo method. If the probability of collision and abrasion exceeds the preset safety range, the range of air film stiffness fluctuation is calculated based on gas dynamics theory. Based on the fluctuation range of air film stiffness, combined with the real-time acquisition of the operating conditions and bearing structure of the air suspension fan, the dynamic response parameters of the foil bearing of the air suspension fan are calculated using a fluid-structure interaction algorithm. Vibration amplitude analysis results are extracted from the dynamic response parameters of the foil bearing of the air suspension fan, and stability prediction index is calculated. An adaptive filtering algorithm is used to optimize the real-time evaluation logic of the preset digital twin system, and the bearing wear monitoring data is updated based on the stability prediction index to determine the failure probability evaluation result. Based on the failure probability assessment results, control commands are generated and transmitted to the thermal shock protection module of the air suspension fan to generate a dynamic adjustment scheme for bearing stability.

2. The predictive maintenance method for air-suspended fans based on digital twins according to claim 1, characterized in that, The characteristics of airflow abrupt changes when high-temperature dust-laden exhaust gas enters the air suspension fan are collected and transmitted to the digital twin system to determine the characteristics of airflow abrupt changes, including: Airflow pressure data is acquired in the gas flow channel by a piezoelectric pressure sensor, and the pressure change rate of adjacent measuring points is calculated based on the airflow pressure data to obtain a data set of sudden airflow pressure changes. Based on the airflow pressure change dataset and the dust concentration data obtained from the dust concentration sensor, the dust concentration data is classified and statistically analyzed according to the dust particle size range, and the velocity field distribution of the gas-solid two-phase flow is calculated. Based on the velocity field distribution of the gas-solid two-phase flow and the exhaust gas temperature data obtained from the thermocouple temperature sensor, a temperature field distribution parameter set including temperature gradient, heat flux and convective heat transfer coefficient is established. The airflow pressure change dataset, the gas-solid two-phase flow velocity field distribution, and the temperature field distribution parameter set are time-synchronized to construct an airflow state space, and the airflow change characteristics are calculated by the least squares method.

3. The predictive maintenance method for air-suspended fans based on digital twins according to claim 1, characterized in that, The transient thermal expansion distribution of the foil is calculated based on the characteristics of sudden airflow changes. Combining the interaction between the material's temperature field and stress-strain field, the non-uniform expansion amount in each region of the foil is obtained, including: An adaptive quadrilateral grid cell is obtained based on the foil temperature field data. When the temperature gradient difference between adjacent grid cells is less than a preset threshold, the initial temperature field distribution of the foil is obtained. The stress field distribution at the nodes of the foil mesh element was calculated using the Lagrange interpolation method. The initial values ​​of the stress-strain field of the foil were obtained based on the initial temperature field distribution and the thermal stress coefficient matrix. The displacement increment of the grid element nodes is calculated by using the linear elastic constitutive equation, and the local deformation of the foil is solved based on the initial temperature field distribution of the foil to obtain the transient deformation field data of the foil. The thermal conductivity distribution of the foil is calculated using the least squares method. The temperature-stress coupling coefficient is obtained based on the transient deformation field data and stress field distribution of the foil. The thermal displacement vector of the grid unit node is solved by the finite difference method, and the non-uniform expansion of each region of the foil is obtained by solving the thermal displacement vector of each grid unit node by the finite difference method.

4. The predictive maintenance method for air-suspended fans based on digital twins according to claim 1, characterized in that, The process of extracting the trend of local gap reduction between the foil and the bearing from the non-uniform expansion of the foil, calculating the spatial distribution after the gap reduction, and obtaining the target air film thickness value includes: The foil deformation mesh matrix is ​​obtained based on the non-uniform expansion of the foil, and the bearing surface displacement distribution data is calculated by Lagrange interpolation using the foil deformation mesh matrix. A contact stress distribution matrix is ​​constructed based on the bearing surface displacement distribution data. The bearing surface contour feature points are fitted using a Bezier curve, and the local contact pressure field data is calculated using the surface normal vector. Based on the local contact pressure field data, an air film pressure field equation is established, and the air film pressure distribution matrix is ​​obtained by solving the air film pressure field equation using the Reynolds equation. A spatial mapping method is used to establish the air film thickness response function for the air film pressure distribution matrix, and the target air film thickness value is calculated through the air film compression characteristic curve.

5. The predictive maintenance method for air-suspended fans based on digital twins according to claim 1, characterized in that, The target air film thickness value is compared with a preset impact threshold. If it is less than the threshold, the probability of impact risk is assessed using the Monte Carlo method, including: A gridded spatial distribution function is established based on the target air film thickness value. If the air film thickness is less than the preset collision threshold, the probability value of the local collision point location is obtained by random sampling using Bernoulli distribution. The bearing load stress distribution is constructed based on the probability values ​​of the local rubbing point locations, and the local stress concentration coefficient is obtained through the material surface finish parameters to obtain the rubbing contact stress field. Based on the friction contact stress field, a frictional heat power field is established, the dynamic stress evolution curve is predicted, and the vibration amplitude distribution data of the foil is obtained. The attenuation law of air film thickness is calculated based on the vibration amplitude distribution data of the foil. The cumulative function of impact damage is constructed through the impact force data. The probability distribution parameters of impact risk are determined by maximum likelihood estimation, and the probability value of impact risk is obtained.

6. The predictive maintenance method for air-suspended fans based on digital twins according to claim 1, characterized in that, If the probability of impact and wear exceeds the preset safety range, the air film stiffness fluctuation range is calculated based on gas dynamics theory, including: By collecting exhaust gas temperature data and combining it with thermistor array measurements of temperature gradient distribution, the temperature field distribution function is obtained. Based on the temperature field distribution function and the concentration distribution of impurities in the exhaust gas measured by the laser particle size sensor, the gas density change rate is calculated using the gas state equation. The air film pressure distribution data is acquired by a pressure sensor array, an air film stress distribution function is established based on the air film pressure distribution data, and the air film deformation response characteristics are solved by the finite difference method. The aerodynamic load distribution is calculated based on the gas film deformation response characteristics and gas dynamic viscosity, and the upper and lower limits of gas film stiffness fluctuation are solved using the gas film damping characteristic equation.

7. The predictive maintenance method for air-suspended fans based on digital twins according to claim 1, characterized in that, The process involves calculating the dynamic response parameters of the foil bearings of the air-suspended fan based on the air film stiffness fluctuation range, combined with real-time acquisition of the air-suspended fan's operating conditions and bearing structure, using a fluid-structure interaction algorithm. This includes: Collect the fan speed fluctuation rate signal and dynamic balance signal, and establish the aerodynamic load distribution function based on the bearing clearance ratio parameter and bearing preload parameter; The stress field of the foil structure is solved based on the aerodynamic load distribution function, the deformation of the foil is calculated using the elasticity equations, and the air film pressure distribution field is obtained by the finite volume method. Based on the air film pressure distribution field and the foil deformation, the axis offset is calculated using a fluid-structure interaction iterative solver, and the transient flow field distribution is obtained through the air film compressibility ratio parameter. Based on the transient flow field distribution, a set of control equations for foil vibration was established. The vibration acceleration and axial displacement were calculated using the Runge-Kutta method, and the main vibration frequency was obtained through fast Fourier transform.

8. The predictive maintenance method for air-suspended fans based on digital twins according to claim 1, characterized in that, The process of extracting vibration amplitude analysis results from the dynamic response parameters of the foil bearings of the air-suspended fan and calculating stability prediction indices includes: The vibration time-domain signal in the dynamic response parameters of the foil bearing of the air suspension fan is obtained, and the vibration time-domain signal is decomposed by wavelet transform to obtain the frequency component of the vibration signal; The vibration amplitude envelope spectrum is constructed using Hilbert transform based on the frequency components of the vibration signal. The amplitude attenuation data is obtained by calculating the amplitude ratio of adjacent vibration periods in the vibration amplitude envelope spectrum. A bearing stability evaluation matrix is ​​constructed based on the amplitude attenuation data and the dynamic stiffness ratio. Whirl signal data is obtained by extracting the whirl component from the bearing stability evaluation matrix. If the eddy signal data meets the sampling theorem requirements, then the discrete Fourier transform is used to obtain the eddy dominant frequency signal, and the eddy frequency ratio is calculated based on the eddy dominant frequency signal and the critical speed.

9. The predictive maintenance method for air-suspended fans based on digital twins according to claim 1, characterized in that, The real-time evaluation logic of the preset digital twin system, which employs an adaptive filtering algorithm to optimize the system, updates bearing wear monitoring data based on stability prediction indices and determines the failure probability assessment result, includes: The bearing wear data characteristics are obtained by using the state observation equation, the measurement noise variance is calculated based on the bearing wear data characteristics, and the filter gain coefficient is obtained through the measurement noise variance. A state transition equation is constructed based on the filter gain coefficients, and the real-time response characteristics are obtained through the state transition equation. A state estimation function is then constructed based on the real-time response characteristics. The wear rate data is obtained based on the state estimation function, the wear rate data is processed by a deep neural network, and a life degradation curve is established based on the wear rate data. A failure probability transition matrix is ​​constructed based on the life degradation curve. A Markov chain is used to process the failure probability transition matrix, and an adaptive evaluation criterion is established to optimize the evaluation logic. The bearing wear monitoring parameters are updated based on the optimization results of the evaluation logic. The failure probability is calculated by sampling multiple times using the Monte Carlo method to obtain the failure probability evaluation result.

10. A predictive maintenance system for air-suspended fans based on digital twins, characterized in that, The system includes: The airflow change feature acquisition module is used to collect the airflow change features when high-temperature dusty exhaust gas rushes into the air suspension fan, and transmit it to the digital twin system to determine the airflow change features. The foil transient thermal expansion calculation module is used to calculate the transient thermal expansion distribution of the foil based on the characteristics of sudden airflow changes. It combines the interaction between the temperature field and stress-strain field of the material to obtain the non-uniform expansion amount in each region of the foil. The gap reduction trend extraction module is used to extract the local gap reduction trend between the foil and the bearing from the non-uniform expansion of the foil, calculate the spatial distribution after the gap reduction, and obtain the target air film thickness value. The collision and abrasion risk assessment module is used to compare the target air film thickness value with the preset collision and abrasion threshold. If it is less than the threshold, the probability of collision and abrasion risk is assessed by the Monte Carlo method. The air film stiffness fluctuation calculation module is used to calculate the air film stiffness fluctuation range based on gas dynamics theory if the probability of collision and abrasion exceeds the preset safety range. The dynamic response parameter calculation module is used to calculate the dynamic response parameters of the foil bearing of the air suspension fan based on the air film stiffness fluctuation range, combined with the real-time acquisition of the operating conditions and bearing structure of the air suspension fan, and using a fluid-structure interaction algorithm. The stability prediction index calculation module is used to extract vibration amplitude analysis results from the dynamic response parameters of the foil bearing of the air suspension fan and calculate the stability prediction index. The real-time evaluation logic optimization module is used to optimize the preset real-time evaluation logic of the digital twin system using an adaptive filtering algorithm, update the bearing wear monitoring data based on stability prediction indicators, and determine the failure probability evaluation results. The dynamic adjustment scheme generation module is used to generate control commands based on the failure probability assessment results, which are then transmitted to the thermal shock protection module of the air suspension fan to generate a dynamic adjustment scheme for bearing stability.

Images