Performance prediction method for high-performance composite material of hub type transmission device

Abstract

The invention relates to the technical field of composite material performance prediction, in particular to a method for predicting the performance of a high-performance composite material of a hub type transmission device, which comprises the following steps of: acquiring mechanical properties and load information of the composite material, defining a preliminary prediction framework and generating a preliminary dynamic response predicted value, collecting real-time data and denoising, and calculating the performance of the high-performance composite material of the hub type transmission device. Calculating a difference between a predicted value and an actual value, adjusting an input factor and updating the predicted value, obtaining strain data, analyzing strain distribution, screening a violent region, adjusting grid density, carrying out strength analysis, and generating a local strength prediction result. Input factors are optimized through real-time data and prediction difference analysis, the prediction precision is improved, local strain analysis and grid density adjustment reflect strength distribution of a material under specific conditions, a self-adaptive adjustment prediction framework can be optimized according to actual working conditions, excessive dependence on initial hypothesis is avoided, and the prediction accuracy is improved. Local strength prediction is provided through fine grid and strain analysis, and the flexibility and reliability of prediction are improved.

Description

Technical Field

[0001] The invention relates to the technical field of composite material performance prediction, and in particular to a method for predicting the performance of a high-performance composite material of a hub-type transmission device. Background Art

[0002] The field of composite material performance prediction technology includes the modeling, analysis and evaluation process of the physical and mechanical properties of various composite materials in specific application scenarios. The core content of this technical field is to obtain key performance indicators of composite materials under complex stress or service conditions, such as strength, stiffness, fatigue life, etc., through theoretical analysis, experimental measurement and data-driven modeling. Overall, composite material performance prediction technology involves multiple links such as material microstructure modeling, performance parameter identification, experimental data analysis, numerical simulation calculation, etc. It is widely used in the design and optimization of high-performance structural parts in aerospace, automobile, energy equipment, etc., especially for scenarios that need to quickly obtain material behavior in the early design stage.

[0003] Among them, the performance prediction method of high-performance composite materials for hub-type transmission devices refers to the use of a multi-scale mechanical modeling method based on the known material composition and geometric characteristics of high-performance composite materials used in hub-type transmission devices, combined with the thermal-mechanical coupling calculation theory and the structural response solution method, to build a prediction model for the anisotropic performance of composite materials, and determine the key parameters in the model through experimental data regression to achieve the analysis and prediction of its strength distribution and thermal deformation trend. This method is usually completed with the help of finite element modeling analysis, material lamination theory calculation, and stress-strain state analysis.

[0004] One of the deficiencies faced by existing technologies in practical applications is that the prediction of the mechanical properties of composite materials is usually too dependent on theoretical models and experimental data, while ignoring the dynamic feedback under actual working conditions. This method cannot fully deal with the impact of changes in working conditions on material properties, and the prediction parameters are usually locked in the early stages of design and cannot be adjusted based on subsequent data. Since these methods rely more on preliminary assumptions, the difference between the predicted results and the actual performance gradually widens during long-term use, and they cannot effectively deal with the material behavior in complex working environments. In addition, the existing technology is relatively rough in its analysis of stress and strain distribution, and it is impossible to make detailed response predictions for local areas. Especially in the application of high-performance structural parts, this deficiency may lead to inaccuracies in the design and affect the long-term service life and safety of the material. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a method for predicting the performance of a high-performance composite material of a hub-type transmission device.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for predicting the performance of a high-performance composite material of a hub transmission device, comprising the following steps: S1: Obtain the basic mechanical properties of composite materials, including elastic modulus, strength and fracture toughness data and working load information, define a preliminary prediction framework based on the operating environment, establish a benchmark dynamic response value, and generate preliminary dynamic response prediction values ​​through load data and environmental conditions; S2: Based on the preliminary dynamic response prediction value, real-time data of the composite material under actual working conditions is collected and noise filtered, and compared with the current working load and environmental data to generate a real-time monitoring data set; S3: Calculate the difference between the dynamic response prediction value and the actual measurement value according to the real-time monitoring data set, adjust the input factors in the prediction framework, and generate an updated dynamic response prediction value; S4: Based on the updated dynamic response prediction value, obtain the composite material strain data, analyze the regional strain distribution, screen the area with drastic strain changes and redistribute the grid density according to the relationship between load intensity and strain, and generate the local strain and load coupling area; S5: In combination with the local strain and load coupling area, the mesh density of the corresponding area is adjusted to perform a refined strength analysis, and a local strength prediction result is generated according to the load and strain relationship of the area.

[0007] As a further solution of the present invention, the preliminary dynamic response prediction value includes a benchmark dynamic response value, load data, and environmental conditions; the real-time monitoring data set includes sensor data, noise-filtered data, workload information, and environmental data; the updated dynamic response prediction value includes a prediction framework after error analysis, adjusted input factors, and optimized associated data; the local strain and load coupling area includes an area with drastic strain changes and a redistributed grid density; the local strength prediction result includes a strength analysis result after adjusting the grid density and a regional load-strain relationship.

[0008] As a further solution of the present invention, the specific steps of S1 are: S101: Obtain the elastic modulus, strength and fracture toughness of the composite material, simultaneously collect the amplitude, direction and frequency of the load in actual use, extract the temperature, humidity and corrosive medium type in the environment, and obtain material performance data and environmental load data; S102: calling the elastic modulus, strength, fracture toughness, temperature, humidity, and corrosive medium type in the material performance data and the environmental load data, converting the environmental data into a material performance adjustment value, calculating the standard frequency based on the elastic modulus, determining the material failure critical value in combination with the strength and fracture toughness, and establishing the benchmark response data; S103: calling the standard frequency, critical stress, and crack growth rate in the benchmark response data, calculating the difference between the load frequency and the standard frequency, comparing the critical stress and the load amplitude to obtain the remaining load range, adjusting the growth rate in combination with the crack growth rate and the environmental corrosion type, integrating the difference value, the remaining load range, and the adjusted growth rate, and generating a preliminary dynamic response prediction value.

[0009] As a further solution of the present invention, the specific steps of S2 are: S201: Based on the preliminary dynamic response prediction value, collect the real-time sensor data corresponding to the dynamic response prediction value of the composite material, smooth the fluctuation component of the sensor signal that exceeds the prediction range, compare the difference between the original data and the truncation threshold range, filter out abnormal fluctuation points, and generate a filtered sensor data set; S202: Based on the filtered sensor data set, the displacement gradient of the current working load and the ambient temperature data are called, the linear relationship between the sensor strain value and the load displacement gradient is calculated, the compensation correction item of the ambient temperature on the data is extracted, and the correction data is subjected to time series difference calculation with the load and environmental reference to generate the load difference and environmental deviation; S203: Integrate the load difference and environmental deviation with the filtered sensor data set, align time series nodes according to the load cycle period, update the data association relationship at a fixed sampling interval, and generate a real-time monitoring data set.

[0010] As a further solution of the present invention, the specific calculation formula for comparing the difference between the original data and the truncation threshold range is: ; in, Representative Sensors at time The dynamic fluctuation deviation value at the moment, Representative Sensors at time The original monitoring data at the moment, Representative Sensors at time The lower cutoff threshold at time, Representative Sensors at time The upper cutoff threshold at time, Representative The average value of all monitoring data of a sensor in a certain time window in the past. Represents the current time node The absolute value of the difference between the predicted and measured Represents the average absolute value of the difference of all time nodes in the current evaluation period.

[0011] As a further solution of the present invention, the specific steps of S3 are: S301: obtaining the current dynamic response prediction value and the actual measurement value in the real-time monitoring data set, calculating the numerical difference between the two at the same time node, taking the absolute value of the difference as a reference, and generating a dynamic difference value; S302: Based on the dynamic difference value, identify the time node where the difference value exceeds the preset error threshold, extract the original data of the input factor corresponding to the node, and perform reverse correction on the original impact ratio of the input factor according to the proportional relationship between the difference value and the error threshold to generate an input factor adjustment ratio; S303: calling the input factor adjustment ratio, performing cumulative operation on the associated data in the prediction framework, performing product summation on the corrected impact degree and the original input factor, recalculating the full-time dynamic response prediction value, and generating an updated dynamic prediction value.

[0012] As a further solution of the present invention, the specific steps of S4 are: S401: extracting strain data of the composite material under the updated dynamic response according to the updated dynamic response prediction value, collecting strain values ​​of multiple regions based on the load intensity and strain relationship, calculating strain distribution of the region, and analyzing the strain intensity difference and change trend of the region to obtain regional strain distribution data; S402: according to the regional strain distribution data, a strain change threshold is set, the region with drastic strain change is screened, key locations with stress concentration are identified, and marked as key areas, thereby obtaining data of drastic strain areas; S403: According to the severe strain area data, the mesh density of the screening area is adjusted, the mesh division is refined, the strain response of the adjusted area is calculated, and a local strain and load coupling area is generated.

[0013] As a further solution of the present invention, the specific calculation formula for the strain distribution in the calculation area is: ; Calculate the regional strain distribution and obtain the strain intensity and regional strain intensity difference; in, Representative area The strain value at represents the load intensity of the area. Represents the force-bearing area of ​​this region, represents the material elastic coefficient of the region, Represents the strain response radius of the area.

[0014] As a further solution of the present invention, the specific steps of S5 are: S501: extracting strain data and load information according to the local strain and load coupling area, establishing a meshing standard based on the regional strain and load relationship, determining a mesh refinement area, obtaining initial mesh data of the refinement area, and performing meshing optimization to generate a high-density mesh area; S502: extracting local stress-strain information of the high-density grid area based on the high-density grid area, calculating the local strength through the stress-strain relationship, and obtaining a local strength prediction value; S503: According to the local strength prediction value, the local strength prediction value is compared with the set safety strength standard to determine the strength exceeding standard area, and the local strength prediction result is generated by analyzing the relationship between the load effect and the local strain.

[0015] As a further solution of the present invention, the specific calculation formula for establishing the grid division standard based on the relationship between regional strain and load is: ; in, represents the refinement value of the grid cell, Representative The strain value at each grid point is represents the load at the corresponding grid point, represents the geometric area corresponding to the grid point, Represents the maximum strain value in the strain area, Represents the minimum strain value in the strain region, Represents the total number of points within the grid area.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, input factors are optimized and prediction accuracy is improved through real-time data and prediction difference analysis. Local strain analysis and grid density adjustment reflect the strength distribution of materials under specific conditions. The adaptive adjustment prediction framework can be optimized according to actual working conditions, avoiding over-reliance on initial assumptions. Refined grid and strain analysis provide local strength prediction, which improves the flexibility and reliability of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the steps of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0020] See also Figure 1 , a method for predicting the performance of a high-performance composite material for a hub transmission device, comprising the following steps: S1: Obtain the basic mechanical properties of composite materials, including elastic modulus, strength and fracture toughness data, and collect working load information, define a preliminary prediction framework based on the operating environment, establish a benchmark dynamic response value, and generate a preliminary dynamic response prediction value by inputting load data and environmental conditions; S2: Based on the preliminary dynamic response prediction value, collect real-time data of the composite material under actual working conditions, filter the noise of the collected sensor data, and compare the obtained data with the current working load and environmental data to generate a real-time monitoring data set; S3: Based on the real-time monitoring data set, the difference between the current dynamic response prediction value and the actual measurement value is calculated, and the input factors in the prediction framework are adjusted through error analysis, and the associated data are adjusted using optimization methods to generate updated dynamic response prediction values; S4: Based on the updated dynamic response prediction value, the strain data of the composite material is obtained, the regional strain distribution is analyzed, and according to the relationship between load intensity and strain, the area with drastic strain changes is screened, and the mesh density is redistributed to the area to generate the local strain and load coupling area; S5: Combine the local strain and load coupling area, adjust the mesh density of the corresponding area, perform refined strength analysis, and generate local strength prediction results based on the load and strain relationship of the area.

[0021] The preliminary dynamic response prediction values ​​include benchmark dynamic response values, load data, and environmental conditions; the real-time monitoring data set includes sensor data, noise-filtered data, working load information, and environmental data; the updated dynamic response prediction values ​​include the prediction framework after error analysis, adjusted input factors, and optimized associated data; the local strain and load coupling area includes areas with drastic strain changes and redistributed grid density; the local strength prediction results include the strength analysis results after adjusting the grid density and the relationship between regional load and strain.

[0022] The specific steps of S1 are: S101: Obtain the elastic modulus, strength and fracture toughness of the composite material, simultaneously collect the amplitude, direction and frequency of the load in actual use, extract the temperature, humidity and corrosive medium type in the environment, and obtain material performance data and environmental load data; A tensile test was performed on the composite material. Tension was applied at a constant rate until it broke. The slope of the linear segment of the stress-strain curve was recorded as the elastic modulus. For example, a stress of 700 MPa was measured to correspond to a strain of 0.2%. The elastic modulus was 350 GPa by dividing the stress by the strain. The sample was loaded until it broke through a three-point bending test. The maximum load was 800 N. The bending strength was calculated to be 300 MPa based on the span, sample width and thickness. A compact tensile sample was used to pre-crack and loaded to a critical state. The fracture toughness was calculated to be 35 MPa. , sensors are installed at the root of wind turbine blades to monitor the load amplitude, which fluctuates in the range of 50-200 kN, and the direction changes periodically between 0° and 90° as the blade rotates. The vibration frequency is determined to be 0.5-2 Hz through spectrum analysis. The coastal ambient temperature fluctuates in the range of 15-30 degrees Celsius, and the humidity is 60-95%. The corrosive medium is confirmed to contain 3.5% sodium chloride solution through chemical testing. The elastic modulus, strength, and fracture toughness are integrated as material performance data, and the load amplitude, direction, frequency, and environmental parameters are integrated as environmental load data to generate material performance data and environmental load data.

[0023] S102: calling the elastic modulus, strength, fracture toughness, temperature, humidity, and corrosive medium type in the material performance data and the environmental load data, converting the environmental data into a material performance adjustment value, calculating the standard frequency based on the elastic modulus, determining the material failure critical value in combination with the strength and fracture toughness, and establishing the benchmark response data; According to the elastic modulus of 350 GPa and the material density of 1600 kg per cubic meter, combined with the characteristic length of the structure of 5 meters, the standard frequency is calculated as the square root of the elastic modulus-density ratio divided by twice the product of the characteristic length and pi, and the result is 47.1 Hz. For a temperature of 30 degrees Celsius, the temperature attenuation coefficient is calculated to be 0.99 according to the rule that the elastic modulus decreases by 0.1% for every degree Celsius. For a humidity of 95%, the humidity attenuation coefficient is calculated to be 0.825 according to the rule that the strength decreases by 0.05% for every percentage of humidity. For the corrosive environment of sodium chloride solution, the fracture toughness attenuation coefficient of 0.7 is selected. After comprehensive adjustment, the critical stress is the original strength of 300 MPa multiplied by the temperature, humidity, and corrosion coefficient in turn, to obtain 171.6 MPa. The crack growth rate is based on the initial crack length of 2 mm and the load fluctuation amplitude of 100 MPa. The growth rate is calculated according to the empirical model to be 2.1×10^-3 mm per cycle. The standard frequency, critical stress, and growth rate are integrated as the benchmark response data.

[0024] S103: calling the standard frequency, critical stress, and crack growth rate in the benchmark response data, calculating the difference between the load frequency and the standard frequency, comparing the critical stress and the load amplitude to obtain the remaining load range, adjusting the growth rate in combination with the crack growth rate and the environmental corrosion type, integrating the difference value, the remaining load range, and the adjusted growth rate, and generating a preliminary dynamic response prediction value; The difference between the actual load frequency of 2 Hz and the standard frequency of 47.1 Hz is calculated, and the difference value is 45.1 Hz. The difference ratio is the proportion of the actual difference to the standard frequency, which is 95.7%. The load amplitude of 200 kN is converted into force per unit area. Assuming that the bearing area is 0.02 square meters, the actual stress is 10 MPa, and the critical stress is 171.6 MPa. The remaining bearing range is the difference between the two, which is 161.6 MPa. According to the corrosion environment of sodium chloride solution, the crack growth rate is increased by 1.5 times on the basis of the original rate. The adjusted rate is 3.15×10^-3 mm / cycle. According to the weight distribution rule of 60% difference ratio, 30% remaining bearing range and 10% growth rate, the dynamic response prediction value is calculated as the weighted sum of each sub-item 0.919 to generate the dynamic response prediction value.

[0025] The specific steps of S2 are: S201: Based on the preliminary dynamic response prediction value, real-time sensor data corresponding to the dynamic response prediction value of the composite material is collected, and the fluctuation component in the sensor signal that exceeds the prediction range is smoothed by the dynamic fluctuation threshold truncation method, and the original data is compared with the truncation threshold range to screen abnormal fluctuation points and generate a filtered sensor data set; The specific calculation formula for comparing the difference between the original data and the truncation threshold range is: ; in, Representative Sensors at time The dynamic fluctuation deviation value at the moment, Representative Sensors at time The original monitoring data at the moment, Representative Sensors at time The lower cutoff threshold at time, Representative Sensors at time The upper cutoff threshold at time, Representative The average value of all monitoring data of a sensor in a certain time window in the past. Represents the current time node The absolute value of the difference between the predicted and measured Represents the average absolute value of the difference of all time nodes in the current evaluation period; In a composite structure monitoring task, the data of sensor y=3 at time t=14:00 is collected and enters the analysis process. The original monitoring data collected by the sensor is mm, this value comes from the real-time data upload interface of the fiber Bragg grating displacement sensor, the sampling frequency is 1 Hz, and the data is included in the calculation after normalization, filtering and denoising.

[0026] In the past 60 minutes of statistics, the upper and lower limits of the dynamic thresholds generated by the fluctuation anomaly detection module are: mm, comes from the historical minimum volatility boundary set based on the sliding window method; mm, comes from the maximum stable fluctuation boundary in the past 60 minutes. The two are formed by screening the historical data at the sampling frequency by the range method and introducing median filtering.

[0027] The average value of sensor number 3 in the past hour is: mm, this value is obtained by averaging the monitoring data of the past 60 time points. The data comes from the monitoring upload cache table within a 60-minute period and is calculated by dividing the sum of all historical values ​​by the number of time points.

[0028] In the previous execution step, the predicted value obtained from the prediction model at this moment is 6.4mm, and the measured value is 5.6mm; the absolute value of the difference between the two is: mm; and the mean of the difference between the predicted and measured values ​​at all time points during the monitoring period is: ; The average value of the forecast difference series derived from the past 60 time points.

[0029] Weight term V t As the prediction error increases, the denominator is set to , ensuring the pull coefficient of the balanced offset term and maintaining the dynamic adjustment capability of the weight within the control range.

[0030] Substituting all the data into the formula, the calculation process is as follows: The first term is the absolute value of the midpoint difference of the truncated interval, calculated as: ; The second item is the volatility deviation adjustment item, which includes the square root of the historical mean deviation and the normalization item of the forecast difference, and is calculated as: ; The product of the two items is: ; Finally, the two parts of the results are merged: ; The result shows that the dynamic fluctuation deviation value of sensor No. 3 at 14:00 is 0.506mm, which is used to compare with the fluctuation recognition threshold. If it is greater than the set screening line value of 0.45mm, it is judged as an abnormal fluctuation point and written into the filtered sensor data set as an abnormal mark for subsequent data cleaning process and error feedback model calculation.

[0031] S202: Based on the filtered sensor data set, the displacement gradient of the current working load and the ambient temperature data are called, the linear relationship between the sensor strain value and the load displacement gradient is calculated, the compensation correction item of the ambient temperature on the data is extracted, and the correction data is subjected to time series difference calculation with the load and environmental reference to generate the load difference and environmental deviation; Based on the time series data of displacement gradient and ambient temperature, taking a bridge health monitoring scenario as an example, the original strain data under load cycle is collected. Assuming that the displacement gradient of the current working load is 0.25 mm per Newton and the ambient temperature is 25 degrees Celsius, the relationship between strain and displacement gradient is established through linear regression analysis. For example, the displacement gradients of the three sampling points are collected at 0.2, 0.25, and 0.3 mm per Newton, respectively, and the corresponding strain values ​​are 50, 62, and 75 microstrains. When calculating, the average value of the displacement gradient is 0.25 mm per Newton, and the average value of the strain is 62.33 microstrain. The linear regression is obtained by the ratio of covariance to variance. The coefficient of strain is 250 microstrain per millimeter per Newton. The temperature compensation item is calculated based on the difference between the ambient temperature and the reference temperature of 20 degrees Celsius. The temperature coefficient is 0.5 microstrain per degree Celsius. When the ambient temperature is 25 degrees Celsius, the compensation value is 2.5 microstrain. The corrected strain value is the original strain minus the compensation value. For example, the original strain of 62 microstrain is corrected to 59.5 microstrain. The load difference is calculated by the difference between the current load and the reference load of 1000 Newtons. For example, when the current load is 1050 Newtons, the difference is 50 Newtons. The environmental deviation is the difference between the ambient temperature and the reference temperature of 5 degrees Celsius. The final output is the time series of the load difference and the environmental deviation.

[0032] S203: Integrate the load difference and environmental deviation with the filtered sensor data set, align the time series nodes according to the load cycle period, update the data association relationship at a fixed sampling interval, establish a multidimensional structure including strain, load, and temperature, and generate a real-time monitoring data set; Taking wind turbine tower monitoring as an example, the load cycle period is 10 minutes, and the time nodes of load difference, environmental deviation and corrected strain data are aligned. The sampling interval is 5 seconds. Assuming that the load peak value in a certain cycle is 1200 Newtons, and the ambient temperature fluctuates between 18 and 22 degrees Celsius, the corrected strain data is divided into 120 groups according to the time window, each group contains strain value, load difference and temperature deviation. For example, the strain value at the 5th second is 58.3 microstrain, the load difference is 48 Newtons, and the temperature deviation is 4.2 degrees Celsius, which are stored as the first group of data. The data at the 10th second is 59.1 microstrain, 52 Newtons, and 4.5 degrees Celsius, which are stored as the second group of data. The missing time points are filled by interpolation of the previous and next data. For example, when the 7.5th second is missing, the middle value of the 5th and 10th second data is taken, the strain value is 58.7 microstrain, the load difference is 50 Newtons, and the temperature deviation is 4.35 degrees Celsius. After updating the data association, a real-time monitoring data set containing 120 groups of three-dimensional data points is formed.

[0033] The specific steps of S3 are: S301: obtaining the current dynamic response prediction value and the actual measurement value in the real-time monitoring data set, calculating the numerical difference between the two at the same time node, taking the absolute value of the difference as a benchmark, and generating a dynamic difference value; First, data is collected in real time through sensor devices installed on the target object. For example, monitoring devices such as accelerometers and inclinometers are deployed in a building to obtain actual measurement values ​​of structural response. At the same time, future structural response is predicted through data-driven models (such as finite element models based on long short-term memory networks (LSTM) or physical rules). The two types of data are aligned with timestamps to ensure that the data at each time node are comparable. In actual operation, the time node is set to every 5 minutes. The data will enter the main server for parsing through the data set middleware, and then the predicted value and actual value at each time point are extracted and the difference is calculated to obtain the dynamic value at that moment. The system will establish an association between the sequence and the sensor number, location, and data source to facilitate the subsequent tracking of abnormal points. For example, in a subway tunnel construction project, the monitoring system shows a predicted deformation of 3.6mm at a certain moment, while the actual measurement is 2.9mm. The difference at that time point is 0.7mm. The difference will be immediately marked and uploaded to become a dynamic difference value. This operation is completed in the server with streaming data processing. The data is sent to the operation module in real time through the pipeline. The difference calculation is completed one by one for all time periods and all sensor data, and the dynamic difference value sequence is output as the input for subsequent processing.

[0034] S302: Based on the dynamic difference value, identify the time node where the difference value exceeds the preset error threshold, extract the original data of the input factor corresponding to the node, and perform reverse correction on the original impact ratio of the input factor according to the proportional relationship between the difference value and the error threshold to generate the input factor adjustment ratio; After generating a dynamic difference value sequence, the platform needs to determine whether there are time nodes that exceed the error tolerance range. The set error threshold is usually determined by historical data analysis and safety requirements. For example, in deformation monitoring, it is usually set in the range of 1.0 mm to 2.0 mm. If the difference value at the current time point is higher than the threshold, the system identifies the time point as an abnormal node, and then retrieves the original data of all input factors corresponding to that moment from the database, including environmental parameters (such as wind speed, humidity), load factors, and structural characteristic parameters (such as stiffness and damping coefficient). Then, according to the ratio of the current difference value to the error threshold, the influencing weight is reversely corrected. That is, if the difference If the value is much larger than the threshold, it means that the original impact ratio of the current input factor is overestimated, and the system will lower its weight. On the contrary, if the difference value is close to the threshold, the correction will be smaller. The input factor weight here usually comes from the preliminary model fitting stage and is obtained through fitting training results. For example, in the building deformation prediction, it is found that the wind speed input value is 6m / s, but the model prediction result is too high, indicating that the contribution of wind speed to the predicted value is over-amplified. In this case, the originally set wind speed impact ratio is reduced to half of the original. Similarly, other parameters are adjusted according to the same ratio, and finally a new adjusted ratio data set containing all input factors is output for subsequent predictions.

[0035] S303: calling the input factor adjustment ratio, performing cumulative operation on the associated data in the prediction framework, performing product summation on the corrected impact degree and the original input factor, recalculating the full-time dynamic response prediction value, and generating an updated dynamic prediction value; After completing the correction ratio of the input factors, they need to be re-applied to the prediction model to update the overall prediction value. For the original prediction model, the system first applies the correction ratio to each input factor, and performs adjustments item by item according to the data correspondence. After that, the corrected data is input into the original prediction framework again, and the model is re-inferred to generate a full-time prediction value sequence. For example, in the structural displacement prediction, the original input factors such as wind speed, ground humidity and traffic load are 5, 0.3 and 200 respectively, and their corresponding impact ratios are 0.2, 0.4 and 0.4. After correction, the ratio becomes 0.1, 0.6 and 0.5, match the original data with the new proportions item by item to generate the corrected input data, input it into the prediction module again, and recalculate the prediction results at this time point. This process is carried out one by one according to each time point, so that the prediction results of the entire period are all corrected new values. If the system is a deep neural network structure, it will be re-inferred after dynamically adjusting the model weights, or the patch layer will be used to add processing logic before the original model to form a new prediction sequence after real-time correction of the input factor influence, and finally form an updated dynamic response prediction value data set for model result display and data release.

[0036] The specific steps of S4 are: S401: extracting strain data of the composite material under the updated dynamic response according to the updated dynamic response prediction value, collecting strain values ​​of multiple regions based on the load intensity and strain relationship, calculating the strain distribution of the region, and analyzing the strain intensity difference and change trend of the region to obtain regional strain distribution data; The specific calculation formula for the strain distribution in the calculation area is: ; Calculate the regional strain distribution and obtain the strain intensity and regional strain intensity difference; in, Representative area The strain value at represents the load intensity of the area. Represents the force-bearing area of ​​this region, represents the material elastic coefficient of the region, represents the strain response radius of the region; Assume that in a composite material structure, select the region The following parameter values ​​are obtained through experiments and calculations: ; ; ; ; Substituting the above values ​​into the formula: ; The calculation steps are as follows: calculate : ; calculate : ; Substituting the above results into the formula: ; Calculate the final result: ; The results show that the area The strain value at .

[0037] S402: according to the regional strain distribution data, a threshold of strain change is set, the region with drastic strain change is screened, key parts of stress concentration are identified, and marked as key areas, thereby obtaining data of drastic strain areas; According to the regional strain distribution data, a threshold for strain change can be set, and the area with drastic strain change can be screened out by the threshold. Areas with drastic strain change usually show strain values ​​different from those of the surrounding areas, or their strain values ​​fluctuate greatly. In actual operation, an initial threshold can be set based on historical data first. For example, areas with strain change values ​​greater than 0.003 are considered to be areas with drastic strain change. Then, the strain change rate of each area is calculated, and areas with a large change rate are judged to be areas with drastic strain change. For example, if the rate of change of strain in a certain area between two time steps is 0.008, which exceeds the set threshold of 0.003, then the area will be identified as an area with drastic strain change. In this way, key areas of stress concentration can be effectively identified. These areas may be at risk of crack initiation or material failure, and therefore should be marked as key monitoring areas to ensure continuous monitoring of material properties.

[0038] S403: According to the data of the severe strain area, the mesh density of the screening area is adjusted, the mesh division is refined, the strain response of the adjusted area is calculated, and the local strain and load coupling area is generated; According to the data of the severe strain area screened out, the mesh density of the area is adjusted. In actual operation, the density of the mesh division is a key factor. The denser the mesh, the more accurate the calculation result. Usually, the adjustment amount of the mesh density can be judged according to the severity of the strain change. For areas with large strain changes, a higher mesh density can be used. Assuming that the mesh size of a severe strain area is 10mm, and after analysis, it is found that the strain change in this area is large, so the mesh size is reduced to 5mm to improve the calculation accuracy. The strain response of the area after the mesh density is adjusted can be recalculated. When recalculating, the finite element analysis method can be used, combined with the geometric shape, material properties and load conditions of the area, to obtain more accurate strain response results. In this process, the accuracy of the strain response is improved by refining the mesh, which can better describe the load distribution and strain relationship in the local area, and finally obtain the local strain and load coupling area, which further provides a basis for subsequent design optimization.

[0039] The specific steps of S5 are: S501: Extract strain data and load information according to the local strain and load coupling area, establish a meshing standard based on the regional strain and load relationship, determine the mesh refinement area, obtain the initial mesh data of the refinement area, and perform meshing optimization to generate a high-density mesh area; The specific calculation formula for establishing the grid division standard based on the relationship between regional strain and load is: ; in, represents the refinement value of the grid cell, Representative The strain value at each grid point is represents the load at the corresponding grid point, represents the geometric area corresponding to the grid point, Represents the maximum strain value in the strain area, Represents the minimum strain value in the strain region, Represents the total number of points in the grid area; Formula derivation process: Calculate the weight factor for each grid point ; The weight factor comprehensively considers the influence of strain, load and geometric size, and is used to reflect the importance of each grid point in meshing.

[0040] Calculate the sum of squares of weight factors ; By summing the squares of all grid point weight factors, a comprehensive index is obtained to guide the accuracy requirements of grid division.

[0041] Calculate mesh refinement values ; Mesh refinement value It reflects the level of accuracy that needs to be achieved in meshing under the current load and strain distribution. The smaller the value, the finer the meshing is required.

[0042] Calculation example: Assume that in a certain structural analysis, the following are the actual data of each grid point: Grid Point 1: Strain , load N, area size m 2 .

[0043] Grid Point 2: Strain , load N, area size m 2 .

[0044] Grid Point 3: Strain , load N, area size m 2 .

[0045] Grid Point 4: Strain , load N, area size m 2 .

[0046] Grid point 5: Strain , load N, area size m 2 .

[0047] Among them, the maximum strain value , minimum strain value ,therefore .

[0048] Calculate the weight factor for each grid point

[0049] ; ; ; ; ; Calculate the sum of squares of weight factors

[0050] ; ; Calculate mesh refinement values

[0051] ; Result analysis: The calculated mesh refinement value is 4.863, which means that under the current strain and load distribution conditions, the mesh refinement should be controlled below this value to ensure the accuracy and precision of the calculation results.

[0052] S502: based on the high-density grid area, extracting local stress-strain information of the dense grid area, calculating the local strength through the stress-strain relationship, and obtaining a local strength prediction value; Based on the optimized high-density mesh area, local stress-strain data are extracted from each mesh node. The relationship between stress and strain is described by the known material constitutive relationship (such as the linear elastic material model). The material constitutive model can help predict the stress borne by the material at different strain levels. In this way, the corresponding local stress can be calculated in each mesh area. Next, the strength of the local area is inferred using a mechanical model. This can be done by, for example, using the vonMises stress criterion to predict the strength, ensuring that the strength prediction of the local area is accurate under different load conditions. The key to this process is to be able to calculate the corresponding local strength prediction value based on the specific load and strain information of each area, and further provide data support for subsequent structural safety assessments.

[0053] S503: According to the local strength prediction value, the local strength prediction value is compared with the set safety strength standard to determine the strength exceeding standard area, and the local strength prediction result is generated by analyzing the relationship between the load effect and the local strain; First, set a safety strength standard, which can be determined by the tensile strength of the material or the safety factor specified in the engineering design. For example, if the safety strength standard is set to 300MPa, and the predicted strength value of a local area is 350MPa, the area is judged to be an area with excessive strength. Next, by comparing the local strength prediction value with the set safety standard, find out all areas where the strength exceeds the standard. In this process, the relationship between the load action and the local strain must also be carefully analyzed, because the change in local strain under different loads will affect the strength prediction. For example, when the wing surface is subjected to a large load, the local strain increases, causing the local stress and strength to reach or exceed the safety strength standard. By analyzing the interaction between load and strain, the areas that may exceed the standard can be accurately determined, and local strength prediction results can be generated.

[0054] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for predicting the performance of high-performance composite materials for a hub transmission, characterized in that: The following steps are involved: S1: Obtain the basic mechanical properties of composite materials, including elastic modulus, strength and fracture toughness data and working load information, define a preliminary prediction framework based on the operating environment, establish a benchmark dynamic response value, and generate preliminary dynamic response prediction values ​​through load data and environmental conditions; S2: Based on the preliminary dynamic response prediction value, real-time data of the composite material under actual working conditions is collected and noise filtered, and compared with the current working load and environmental data to generate a real-time monitoring data set; S3: Calculate the difference between the dynamic response prediction value and the actual measurement value according to the real-time monitoring data set, adjust the input factors in the prediction framework, and generate an updated dynamic response prediction value; S4: Based on the updated dynamic response prediction value, obtain the composite material strain data, analyze the regional strain distribution, screen the area with drastic strain changes and redistribute the grid density according to the relationship between load intensity and strain, and generate the local strain and load coupling area; S5: In combination with the local strain and load coupling area, the mesh density of the corresponding area is adjusted to perform a refined strength analysis, and a local strength prediction result is generated according to the load and strain relationship of the area.

2. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 1, characterized in that: The preliminary dynamic response prediction value includes the benchmark dynamic response value, load data, and environmental conditions; the real-time monitoring data set includes sensor data, noise-filtered data, workload information, and environmental data; the updated dynamic response prediction value includes the prediction framework after error analysis, adjusted input factors, and optimized associated data; the local strain and load coupling area includes the area with drastic strain changes and the redistributed grid density; the local strength prediction result includes the strength analysis result after adjusting the grid density and the regional load-strain relationship.

3. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 1, characterized in that: The specific steps of S1 are: S101: Obtain the elastic modulus, strength and fracture toughness of the composite material, simultaneously collect the amplitude, direction and frequency of the load in actual use, extract the temperature, humidity and corrosive medium type in the environment, and obtain material performance data and environmental load data; S102: calling the elastic modulus, strength, fracture toughness, temperature, humidity, and corrosive medium type in the material performance data and the environmental load data, converting the environmental data into a material performance adjustment value, calculating the standard frequency based on the elastic modulus, determining the material failure critical value in combination with the strength and fracture toughness, and establishing the benchmark response data; S103: calling the standard frequency, critical stress, and crack growth rate in the benchmark response data, calculating the difference between the load frequency and the standard frequency, comparing the critical stress and the load amplitude to obtain the remaining load range, adjusting the growth rate in combination with the crack growth rate and the environmental corrosion type, integrating the difference value, the remaining load range, and the adjusted growth rate, and generating a preliminary dynamic response prediction value.

4. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 3, characterized in that: The specific steps of S2 are: S201: Based on the preliminary dynamic response prediction value, collect the real-time sensor data corresponding to the dynamic response prediction value of the composite material, smooth the fluctuation component of the sensor signal that exceeds the prediction range, compare the difference between the original data and the truncation threshold range, filter out abnormal fluctuation points, and generate a filtered sensor data set; S202: Based on the filtered sensor data set, the displacement gradient of the current working load and the ambient temperature data are called, the linear relationship between the sensor strain value and the load displacement gradient is calculated, the compensation correction item of the ambient temperature on the data is extracted, and the correction data is subjected to time series difference calculation with the load and environmental reference to generate the load difference and environmental deviation; S203: Integrate the load difference and environmental deviation with the filtered sensor data set, align time series nodes according to the load cycle period, update the data association relationship at a fixed sampling interval, and generate a real-time monitoring data set.

5. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 4, characterized in that: The specific calculation formula for comparing the difference between the original data and the truncation threshold range is: ； in, Representative Sensors at time The dynamic fluctuation deviation value at the moment, Representative Sensors at time The original monitoring data at the moment, Representative Sensors at time The lower cutoff threshold at time, Representative Sensors at time The upper cutoff threshold at time, Representative The average value of all monitoring data of a sensor in a certain time window in the past. Represents the current time node The absolute value of the difference between the predicted and measured Represents the average absolute value of the difference of all time nodes in the current evaluation period.

6. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 4, characterized in that: The specific steps of S3 are: S301: obtaining the current dynamic response prediction value and the actual measurement value in the real-time monitoring data set, calculating the numerical difference between the two at the same time node, taking the absolute value of the difference as a reference, and generating a dynamic difference value; S302: Based on the dynamic difference value, identify the time node where the difference value exceeds the preset error threshold, extract the original data of the input factor corresponding to the node, and perform reverse correction on the original impact ratio of the input factor according to the proportional relationship between the difference value and the error threshold to generate an input factor adjustment ratio; S303: calling the input factor adjustment ratio, performing cumulative operation on the associated data in the prediction framework, performing product summation on the corrected impact degree and the original input factor, recalculating the full-time dynamic response prediction value, and generating an updated dynamic prediction value.

7. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 6, characterized in that: The specific steps of S4 are: S401: extracting strain data of the composite material under the updated dynamic response according to the updated dynamic response prediction value, collecting strain values ​​of multiple regions based on the load intensity and strain relationship, calculating strain distribution of the region, and analyzing the strain intensity difference and change trend of the region to obtain regional strain distribution data; S402: according to the regional strain distribution data, a strain change threshold is set, the region with drastic strain change is screened, key locations with stress concentration are identified, and marked as key areas, thereby obtaining data of drastic strain areas; S403: According to the severe strain area data, the mesh density of the screening area is adjusted, the mesh division is refined, the strain response of the adjusted area is calculated, and a local strain and load coupling area is generated.

8. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 7, characterized in that: The specific calculation formula for the strain distribution in the calculation area is: ； Calculate the regional strain distribution and obtain the strain intensity and regional strain intensity difference; in, Representative area The strain value at represents the load intensity of the area. Represents the force-bearing area of ​​this region, represents the material elastic coefficient of the region, Represents the strain response radius of the area.

9. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 7, characterized in that: The specific steps of S5 are: S501: extracting strain data and load information according to the local strain and load coupling area, establishing a meshing standard based on the regional strain and load relationship, determining a mesh refinement area, obtaining initial mesh data of the refinement area, and performing meshing optimization to generate a high-density mesh area; S502: extracting local stress-strain information of the high-density grid area based on the high-density grid area, calculating the local strength through the stress-strain relationship, and obtaining a local strength prediction value; S503: According to the local strength prediction value, the local strength prediction value is compared with the set safety strength standard to determine the strength exceeding standard area, and the local strength prediction result is generated by analyzing the relationship between the load effect and the local strain.

10. The method for predicting the performance of high-performance composite materials for a hub transmission according to claim 9, characterized in that: The specific calculation formula for establishing the grid division standard based on the relationship between regional strain and load is: ； in, represents the refinement value of the grid cell, Representative The strain value at each grid point is represents the load at the corresponding grid point, represents the geometric area corresponding to the grid point, represents the maximum strain value in the strain region, Represents the minimum strain value in the strain region, Represents the total number of points within the grid area.

Images