Service life prediction method and system based on application analysis main shaft

Abstract

The invention relates to the technical field of equipment life management, in particular to a life prediction method and system based on an application analysis spindle, and the method comprises the steps: building a modal sensing network, collecting multi-source operation data in the operation process of the spindle, and generating a multi-source operation characteristic matrix; based on the multi-source operation characteristic matrix, establishing multi-application characteristic mapping, and generating a multi-scene characteristic vector for describing an equipment operation state; performing multi-dimensional coupling fatigue analysis on the multi-scene feature vector, and outputting a fatigue damage accumulated value of the main shaft; and according to the fatigue damage accumulated value, obtaining and combining historical motion data of the main shaft, establishing a different-parameter life prediction model, and outputting a residual life prediction value based on the different-parameter life prediction model. According to the invention, the problems of single data source, insufficient prediction precision under complex working conditions, difficult modeling of nonlinear fatigue damage and lack of dynamic feedback and correction capability in a traditional main shaft life prediction method are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment life management, and particularly to a method and system for predicting the life of a spindle based on application analysis. Background Art

[0002] The spindle is a key component in various mechanical equipment, and its operating state directly affects the overall performance and reliability of the equipment. However, due to the spindle being in a complex and variable working environment for a long time, its fatigue damage gradually accumulates, and ultimately it may lead to failure. Therefore, how to accurately analyze the fatigue damage of the spindle and predict the remaining life is an important research topic in the field of mechanical equipment health management.

[0003] Currently, traditional life prediction methods mainly rely on empirical formulas or single-sensor monitoring, and have problems such as single data source, insufficient model accuracy, and lack of a dynamic feedback mechanism. These methods usually analyze only the monitoring data of a single physical quantity (such as temperature, vibration, or stress), and cannot comprehensively reflect the multi-source characteristics during the operation of the spindle. Moreover, the prediction model usually assumes that the spindle operation application is stable, ignoring the dynamic changes under multi-application operating conditions, resulting in a large deviation in the prediction results. In addition, traditional methods are difficult to achieve real-time feedback and dynamic adjustment of the spindle operating state and cannot adapt to the fatigue evolution under complex applications.

[0004] The information disclosed in this background art section is only intended to deepen the understanding of the overall background art of the present disclosure, and should not be regarded as an admission or any form of implication that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0005] The present invention provides a method and system for predicting the life of a spindle based on application analysis, which can effectively solve the problems in the background art.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: A method for predicting the life of a spindle based on application analysis, the method comprising: Establish a modal perception network, collect multi-source operation data during the operation of the spindle, and generate a multi-source operation characteristic matrix; Based on the multi-source operation characteristic matrix, establish a multi-application feature mapping, and generate a multi-scenario feature vector describing the equipment operating state; Perform multi-dimensional coupled fatigue analysis on the multi-scenario feature vector, and output the fatigue damage accumulation value of the spindle; According to the fatigue damage accumulation value, obtain and combine the historical motion data of the spindle, establish a heterogeneous parameter life prediction model, and output a remaining life prediction value based on the heterogeneous parameter life prediction model.

[0007] Further, predicting the remaining life value based on the heterogeneous parameter life prediction model includes: Extracting the fatigue damage accumulation law of the spindle historical operation data based on multiple application scenarios, and generating an application fatigue correlation feedback as the input of the heterogeneous parameter life prediction model; According to the fatigue damage accumulation value and the application fatigue correlation feedback, combining with the time series analysis method, establishing a fatigue damage accumulation curve under the current application scenario; Based on the fatigue damage accumulation curve, simulating the fatigue accumulation change trend of the spindle under multiple applications, and predicting the fatigue critical point according to the trend direction and the trend intersection time series; Integrating the fatigue critical points, and calculating the comprehensive remaining life of the spindle in the current and future applications according to the integrated point set, where the comprehensive remaining life is the predicted life under the current application; According to the comprehensive remaining life, combining with the single-application and multi-application superposition conditions of the spindle, calculating and outputting the remaining life prediction value.

[0008] Further, predicting the fatigue critical point according to the trend direction and the trend intersection time series includes: Analyzing the fatigue damage accumulation law of multiple spindles under multi-application operation conditions, sorting out the trend direction according to the fatigue damage accumulation law, and setting the fatigue critical point determination conditions; Establishing a fatigue evolution model according to the application fatigue correlation feedback and the fatigue damage accumulation curve, and simulating the non-linear dynamic characteristics of the spindle fatigue damage accumulation; Taking the multi-scenario feature vector as the input, analyzing the weights of the fatigue influence factors of the spindle under multiple operation scenarios, and using the fatigue influence factors to feedback and adjust the prediction accuracy of the fatigue evolution model; According to the fatigue influence factors, for multiple multi-scenario feature vectors, predicting the time series when the spindle reaches the fatigue critical point and the corresponding application characteristics according to the trend direction to generate a simulation prediction result; Comparing the simulation prediction result with the fatigue critical point determination conditions for dynamic correction to generate the fatigue critical points under the current application and future applications.

[0009] Further, simulating the non-linear dynamic characteristics of the spindle fatigue damage accumulation includes: Through the structured analysis of the multi-source operation data, constructing a fatigue damage accumulation simulation framework, and mapping the multi-scenario feature vector of the spindle operation to the fatigue damage accumulation simulation framework; Simulating the non-linear evolution process under the multi-application superposition conditions of fatigue damage under multiple operation scenarios, and describing the coupling characteristics and the change of fatigue accumulation rate in multiple applications; Calculate the fatigue accumulation coefficient according to the fatigue accumulation rate to adjust the fatigue damage accumulation simulation framework; Integrate the accumulation laws of the main shaft in multiple stages, integrate the simulation results of each stage, and generate a non-linear trend of fatigue damage accumulation throughout the life cycle; Compare the historical operation data of the main shaft with the determination conditions of the fatigue damage critical point to verify the accuracy of the simulation results and correct the deviation.

[0010] Furthermore, establish a multi-application feature mapping, including: Based on the multi-source operation data during the operation of the main shaft, extract key features related to the operation state of the main shaft, and generate a multi-source operation characteristic matrix containing time series information; Classify the multi-source operation characteristic matrix, and generate corresponding application category labels according to various operation states; According to the statistical correlation analysis method between the key features, identify the core feature parameters closely related to the operation state of the main shaft; Establish a mapping that maps the multi-source operation characteristic matrix to the application category labels, generate a multi-application feature mapping that can distinguish multiple operation applications, and transform the key features into the multi-scenario feature vectors.

[0011] Furthermore, transform the key features into the multi-scenario feature vectors, including: Apply a feature dimensionality reduction method to reduce the redundant information of the key features and extract the main feature components that can characterize the changes in multi-application characteristics; Based on the multi-application feature mapping, encode and combine the main feature components to generate application characteristic vectors corresponding to each application category label; Based on the changes in the time series information during the operation of the main shaft, use the time series sliding window method to perform time series fusion on the application characteristic vectors to generate a preliminary multi-scenario feature vector containing time correlation; Smooth the transitional changes between the preliminary multi-scenario feature vectors to generate the multi-scenario feature vectors.

[0012] Furthermore, perform multi-dimensional coupled fatigue analysis on the multi-scenario feature vectors, including: Based on the multi-scenario feature vectors, extract the damage characteristic parameters that affect the fatigue damage of the main shaft, quantify the contribution degree of the damage characteristic parameters to the fatigue damage accumulation, and generate a multi-dimensional feature contribution matrix of the main shaft fatigue damage; According to the multi-dimensional feature contribution matrix, establish a non-linear interaction relationship between multiple damage characteristic parameters to characterize the fatigue damage accumulation effect; Quantify the change in the fatigue damage accumulation rate caused by application switching according to the fatigue damage accumulation effect, and generate a fatigue response curve of the main shaft under dynamic operating conditions; Based on the fatigue response curve and the multi-scenario feature vector, analyze the fatigue damage accumulation trend of the main shaft under multiple operating scenarios, calculate the fatigue damage accumulation value, and predict and verify the change trend of the fatigue accumulation rate.

[0013] Further, calculating the fatigue damage accumulation value includes: Perform step-by-step cumulative analysis on the multi-scenario feature vector, and generate basic analysis data describing fatigue damage accumulation based on the change trends under multiple operating states; Divide the operation process into multiple time intervals, perform independent damage assessment on the basic analysis data within each time interval, and generate an interval fatigue damage accumulation value; In response to changes in the operating state, adjust the cumulative weights of each time interval in the cumulative calculation process to reflect the impact on the fatigue damage accumulation rate in multiple applications; Integrate the cumulative weights and the interval fatigue damage accumulation values globally to generate a fatigue damage accumulation value as the quantification result of the damage state in the current operation stage.

[0014] A life prediction system for the main shaft based on application analysis, the system includes: A modal perception module, which establishes a modal perception network, collects multi-source operation data during the operation of the main shaft, and generates a multi-source operation characteristic matrix; A feature mapping module, which establishes a multi-application feature mapping based on the multi-source operation characteristic matrix and generates a multi-scenario feature vector describing the device operation state; A fatigue analysis module, which performs multi-dimensional coupled fatigue analysis on the multi-scenario feature vector and outputs the fatigue damage accumulation value of the main shaft; A life prediction module, which obtains and combines the historical motion data of the main shaft according to the fatigue damage accumulation value, establishes a heteroparametric life prediction model, and outputs a remaining life prediction value based on the heteroparametric life prediction model.

[0015] Further, the life prediction module includes: A rule statistics unit, which extracts the fatigue damage accumulation rules of the historical operation data of the main shaft based on multiple application scenarios and generates an application fatigue correlation feedback as the input of the heteroparametric life prediction model; A time series analysis unit, which establishes a fatigue damage accumulation curve in the current application scenario by combining the fatigue damage accumulation value and the application fatigue correlation feedback with the time series analysis method; A critical prediction unit that simulates the fatigue cumulative change trend of the main shaft under various applications based on the fatigue damage accumulation curve, and predicts the fatigue critical point according to the trend direction and the timing of trend intersection; An integrated calculation unit that integrates the fatigue critical points and calculates the comprehensive remaining life of the main shaft in the current and future applications according to the integrated point set. The comprehensive remaining life is the predicted life under the current application; A scenario superposition unit that calculates and outputs the predicted value of the remaining life according to the comprehensive remaining life, in combination with the single-application and multi-application superposition conditions of the main shaft.

[0016] Through the technical solution of the present invention, the following technical effects can be achieved: It solves the problems of single data source, insufficient prediction accuracy under complex working conditions, difficulty in modeling non-linear fatigue damage, and lack of dynamic feedback and correction ability in the traditional main shaft life prediction method, and realizes the accurate prediction of the comprehensive remaining life of the main shaft under single-condition and multi-condition superposition conditions.

[0017] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically given below. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic flowchart of the life prediction method for the main shaft based on application analysis; Figure 2 It is a schematic flowchart of predicting the fatigue critical point; Figure 3 It is a schematic structural diagram of multi-application feature mapping; Figure 4 It is a schematic structural diagram for performing multi-dimensional coupled fatigue analysis. Detailed Embodiments

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used in the description of this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0022] Embodiment 1; As Figure 1 shown, this application provides a method for predicting the life of a spindle based on application analysis, and the method includes: S10: Establish a modal perception network, collect multi-source operation data during the operation of the spindle, and generate a multi-source operation characteristic matrix; S20: Based on the multi-source operation characteristic matrix, establish a multi-application feature mapping, and generate a multi-scenario feature vector describing the operation state of the device; S30: Perform multi-dimensional coupled fatigue analysis on the multi-scenario feature vector, and output the cumulative fatigue damage value of the spindle; S40: According to the cumulative fatigue damage value, obtain and combine the historical motion data of the spindle, establish a heterogeneous parameter life prediction model, and output the remaining life prediction value based on the heterogeneous parameter life prediction model.

[0023] Specifically, first, sensors (such as acceleration sensors, temperature sensors, vibration sensors, etc.) are arranged at different positions on the main shaft to collect multi-source operation data generated during the operation of the main shaft in real time, including various operation state indicators such as vibration signals, temperature changes, rotational speed, and load. The collected multi-source operation data is preprocessed (such as denoising and standardization), and a multi-source operation characteristic matrix is generated according to the time series characteristics of the multi-source operation data. The multi-source operation characteristic matrix contains characteristic information under different operation conditions, such as time series data of vibration, temperature, etc., and can comprehensively describe the dynamic operation state of the main shaft. Based on the obtained multi-source operation characteristic matrix, data analysis methods (such as principal component analysis (PCA), clustering analysis, etc.) are used to classify different working conditions, extract key characteristics related to the operation state of the main shaft, establish a multi-application feature mapping through the key characteristics, map the feature vectors under different operation states, and finally generate multi-scenario feature vectors. The multi-scenario feature vectors can describe the state of the main shaft under different operation environments and reflect the working condition characteristics under multiple scenarios. Perform multi-dimensional coupled fatigue analysis on the multi-scenario feature vectors, adopt a fatigue damage accumulation model (such as Miner's rule) combined with the multi-scenario feature vectors of the main shaft for quantitative analysis of fatigue damage, and output the fatigue damage accumulation value of the main shaft by analyzing the contribution of each operation state to the fatigue damage of the main shaft, which can help determine the fatigue state of the main shaft under the current working condition and provide basic data for the remaining life prediction. According to the fatigue damage accumulation value and combined with the historical motion data of the main shaft, an anisotropic parameter life prediction model is established. The anisotropic parameter life model uses methods such as multi-factor analysis and regression analysis, combines fatigue damage, historical operation data, and working condition characteristics to accurately predict the remaining life of the main shaft, and outputs the remaining life prediction value of the main shaft under the current and future working conditions through the prediction results of the anisotropic parameter model.

[0024] Through the technical solution of the present invention, the problems in the traditional main shaft life prediction method, such as single data source, insufficient prediction accuracy under complex working conditions, difficulty in modeling non-linear fatigue damage, and lack of dynamic feedback and correction ability, are solved, and the accurate prediction of the comprehensive remaining life of the main shaft under single working condition and multi-working condition superposition is realized.

[0025] Furthermore, based on the anisotropic parameter life prediction model to output the remaining life prediction value, it includes: Extract the fatigue damage accumulation law of the historical operation data of the main shaft based on multiple application scenarios and generate an application fatigue correlation feedback as the input of the anisotropic parameter life prediction model; According to the fatigue damage accumulation value and the application fatigue correlation feedback, combined with the time series analysis method, establish a fatigue damage accumulation curve under the current application scenario; Based on the fatigue damage accumulation curve, simulate the fatigue accumulation change trend of the main shaft under multiple applications, and predict the fatigue critical point according to the trend direction and the trend intersection time series; Integrate the fatigue critical points, and calculate the comprehensive remaining life of the spindle in the current and future applications based on the integrated point set. The comprehensive remaining life is the predicted life under the current application. Based on the comprehensive remaining life, combine the single-application and multi-application superposition conditions of the spindle, and calculate and output the predicted value of the remaining life.

[0026] As an optimization of the above embodiment, first collect and organize the historical operation data of the spindle in multiple application scenarios. According to these data, use a fatigue damage model (such as Miner's rule or other non-linear fatigue models) to extract the fatigue damage accumulation law of the spindle under different working conditions (such as different loads, speeds, ambient temperatures, etc.). Through statistical analysis and pattern recognition, generate the fatigue damage accumulation characteristics in each application scenario, generate application fatigue correlation feedback, which is used as the input of the heterogeneous parameter life prediction model, reflecting the differences and regularities of the spindle fatigue evolution under different application scenarios; according to the fatigue damage accumulation value and application fatigue correlation feedback, combine time series analysis methods (such as sliding window, time series modeling, etc.) to establish the fatigue damage accumulation curve of the spindle in the current application scenario. The fatigue damage accumulation curve depicts the evolution trend of the spindle fatigue damage over time or operating conditions in a specific application environment, can reflect the accumulation of fatigue damage in real time, and provide a basis for predicting future fatigue critical points; use the fatigue damage accumulation curve to further simulate the fatigue damage accumulation change trend of the spindle in multiple application scenarios. By comparing and analyzing the fatigue damage accumulation curves of multiple application scenarios, predict the future change trend of fatigue damage, especially the fatigue critical point at the intersection of trends (i.e., the critical moment when the spindle will suffer serious damage or failure). This process not only focuses on the local trends in each application scenario, but also analyzes the overall fatigue evolution of multiple applications to predict the occurrence time of the fatigue critical point; after obtaining the fatigue critical points in different application scenarios, integrate these critical points into an integrated point set. By analyzing each fatigue critical point and combining the working condition changes of the spindle in the current and future applications, calculate the comprehensive remaining life of the spindle. The comprehensive remaining life refers to the predicted value of the remaining life of the spindle considering the current application and future multiple application scenarios, integrating the fatigue damage accumulation effects of the spindle under different application conditions; according to the integrated comprehensive remaining life, combine the single-application and multi-application superposition conditions of the spindle, and output the predicted value of the remaining life of the spindle in multiple application scenarios. During this process, dynamically adjust the prediction according to the changes in the actual operating environment and working conditions to ensure that the prediction results can adapt to the actual fatigue evolution in different applications. In this way, the predicted value can not only reflect the life of the current application, but also adapt to the fatigue damage situation of the spindle in future multiple possible application environments.

[0027] Furthermore, as Figure 2 shown, predicting the fatigue critical point according to the trend direction and the trend intersection time series includes: Analyze the fatigue damage accumulation law of multiple spindles under multi-application operating conditions, sort out the trend according to the fatigue damage accumulation law, and set the judgment conditions for the fatigue critical point; Establish a fatigue evolution model based on the application fatigue correlation feedback and the fatigue damage accumulation curve to simulate the non-linear dynamic characteristics of the spindle fatigue damage accumulation; Take the multi-scenario feature vector as the input, analyze the weights of the fatigue influence factors of the spindle under multiple operating scenarios, and use the fatigue influence factors to feedback and adjust the prediction accuracy of the fatigue evolution model; According to the fatigue influence factors, for multiple multi-scenario feature vectors, predict the time sequence when the spindle reaches the fatigue critical point according to the trend, and generate the simulation prediction results of the corresponding application characteristics; Compare the simulation prediction results with the fatigue critical point judgment conditions for dynamic correction to generate the fatigue critical points under the current application and future applications.

[0028] Preferably, as in the above embodiments, the operation data of different spindles under various application conditions (such as different speeds, loads, temperatures, etc.) are collected and analyzed to extract the fatigue damage accumulation law of the spindles. For each application condition, the fatigue damage accumulation rate, damage characteristics, and non-linear characteristics of the accumulation process of the spindles are analyzed. These laws provide basic data for subsequent trend prediction. Based on the fatigue damage accumulation laws under different conditions, the fatigue damage development trends of each application scenario are further sorted out. Through trend analysis methods (such as regression analysis, Fourier analysis, etc.), the key change points and trend turning points existing in the fatigue damage accumulation process are identified. Combining historical data and theoretical analysis, the fatigue critical point determination conditions are set. These conditions may include that the fatigue damage reaches a certain preset threshold, the damage rate exceeds a certain critical value, or a certain specific form of the damage accumulation curve, etc. Based on the extracted fatigue damage accumulation laws, fatigue damage accumulation curves, and set fatigue critical point determination conditions, combined with the application of fatigue correlation feedback, a fatigue damage evolution model of the spindle is established. This model should be able to simulate the non-linear dynamic characteristics of the fatigue damage of the spindle under multiple conditions, taking into account the influence of condition switching, load fluctuation, and environmental change on fatigue evolution. Taking the multi-scene feature vector as the input, through weight analysis, the weights of the fatigue influencing factors (such as temperature, load, speed, etc.) affecting the fatigue damage of the spindle are determined. Through sensitivity analysis, the contribution degree of each factor to the fatigue damage accumulation is quantified. These fatigue influencing factors are used to dynamically adjust the fatigue evolution model to improve the prediction accuracy. Especially in application scenarios with large condition changes, by real-time adjusting the fatigue evolution model, the prediction deviation can be reduced. Using the extracted fatigue influencing factors and fatigue evolution model, for the multi-scene feature vectors under multiple operation scenarios, combined with the trend direction, the time sequence when the spindle reaches the fatigue critical point under different application conditions is predicted. Specifically, by analyzing the accumulation trend under different conditions, the moment when the fatigue damage reaches the critical value is identified, and the corresponding simulation prediction results are generated. After generating the simulation prediction results, they are compared with the set fatigue critical point determination conditions. According to the error size and the deviation of the actual data, dynamic correction is carried out. By comparing with the actual operation data, the fatigue evolution model is gradually corrected to improve its prediction accuracy, and finally the fatigue critical points under the current application and future applications are generated.

[0029] Furthermore, simulating the non-linear dynamic characteristics of the fatigue damage accumulation of the spindle includes: Through the structured analysis of multi-source operation data, a fatigue damage accumulation simulation framework is constructed, and the multi-scene feature vectors of the spindle operation are mapped to the fatigue damage accumulation simulation framework; Simulating the non-linear evolution process under the multi-application superposition conditions of fatigue damage under multiple operation scenarios, and describing the coupling characteristics and the change of fatigue accumulation rate in multiple applications; Calculate the fatigue cumulative coefficient according to the fatigue cumulative rate to adjust the fatigue damage cumulative simulation framework; Integrate the cumulative laws of the main shaft in multiple stages, integrate the simulation results of each stage, and generate the non-linear trend of fatigue damage accumulation in the whole life cycle; Verify the accuracy of the simulation results by comparing the historical operation data of the main shaft with the determination conditions of the fatigue damage critical point, and correct the deviation.

[0030] As an optimization of the above embodiments, the multi-source operation data of the main shaft (such as vibration signals, temperature, load, rotational speed, etc.) is structurally analyzed. Through methods such as data preprocessing and feature extraction, the original data is transformed into a format that meets the analysis requirements. According to different fatigue damage models (such as Miner's rule, nonlinear cumulative model, etc.), a fatigue damage cumulative simulation framework is constructed. This framework can be dynamically adjusted according to different working conditions of the main shaft and adapt to the fatigue damage change characteristics of the main shaft under different application conditions. The multi-scenario feature vectors of the main shaft are mapped into this framework to fully consider the influence of different operating scenarios in the simulation. Based on the constructed fatigue damage cumulative simulation framework, the fatigue damage cumulative evolution process of the main shaft under multiple operating scenarios is simulated. Considering the nonlinear characteristics of fatigue damage and the change of cumulative rate under different working conditions, a nonlinear evolution model (such as a dynamic system model, neural network model, etc.) is used to describe the change of the main shaft's fatigue damage. Specifically, the superposition condition of multiple applications needs to be considered during the simulation process. The main shaft often operates in an environment of multiple working conditions superimposed in actual operation. Therefore, it is necessary to simulate the superposition effect of fatigue damage and the interaction between different working conditions under multiple working conditions. The interaction between different application conditions may affect the fatigue damage cumulative rate. For example, a high rotational speed condition under high load may cause a higher fatigue damage rate than a single low load condition. Based on the fatigue cumulative rate, at each operation stage, the parameters of the fatigue damage cumulative simulation framework are adjusted according to the current working condition, and the fatigue cumulative coefficient is calculated. The fatigue cumulative coefficient reflects the change law of the fatigue damage rate under different working conditions. By dynamically adjusting the fatigue cumulative coefficient in the simulation framework, the fatigue damage evolution process of the main shaft under different working conditions can be described more accurately, and the accuracy of the simulation can be improved. According to the change trend under different working conditions, the model is continuously optimized by combining the historical data of fatigue damage. During the simulation process, the main shaft undergoes multiple operation stages, and the fatigue damage cumulative law of each stage may be different. By integrating the fatigue damage cumulative results of each stage, the cumulative laws of each stage are integrated to generate a nonlinear trend of fatigue damage cumulative throughout the life cycle of the main shaft. The nonlinear trend of fatigue damage cumulative can describe the fatigue damage evolution path of the main shaft at different life cycle stages. By comparing the fatigue damage cumulative trend with the historical operation data of the main shaft, the accuracy of the simulation results is verified. The historical operation data of the main shaft can be used as a reference standard. By comparing with the actual fatigue damage situation, the deviation of the simulation results is analyzed, and the model is corrected according to the fatigue damage situation under the actual working condition.

[0031] Furthermore, as Figure 3 shown, a multi-application feature mapping is established, including: Based on the multi-source operation data during the operation of the main shaft, key features related to the operation state of the main shaft are extracted to generate a multi-source operation characteristic matrix containing time series information; Classify the multi-source operation characteristic matrix and generate corresponding application category labels according to various operation states; Identify the core characteristic parameters closely related to the spindle operation state according to the statistical correlation analysis method between key characteristics; Establish a mapping that maps the multi-source operation characteristic matrix to the application category label, generate a multi-application characteristic mapping that can distinguish multiple operation applications, and transform the key characteristics into multi-scenario characteristic vectors.

[0032] Preferably, for the above embodiments, key features closely related to the spindle operating state are extracted from the multi-source operating data of the spindle. The key features are the feature information in the frequency domain, time domain, and time-frequency domain extracted from the original data. The extracted features may include instantaneous frequency, vibration amplitude, energy distribution, instantaneous phase, etc. Combining the time series information of the spindle operation, the key features are organized in chronological order to form a multi-source operating characteristic matrix. Each column of the multi-source operating characteristic matrix corresponds to the features under a different operating state, and the rows represent the values of the features at specific time points. The data in the multi-source operating characteristic matrix is classified according to the working environment or working conditions of the spindle to generate different application category labels. For example, according to different working conditions, the spindle operation can be divided into different categories such as normal operation, overload, abnormal vibration, high temperature, etc. The data under different states is grouped into different categories according to the change pattern of the operating data. Each application category label represents a specific state of the spindle operation (such as operating under a certain specific load and speed condition). In the multi-source operating data of the spindle, some features may be closely related to the spindle operating state, while other features may have a weaker relationship with fatigue damage or changes in working performance. Therefore, a statistical correlation analysis method is used to identify and screen out the core features closely related to the spindle health state. Through correlation analysis, it is possible to identify which features have a high correlation in changes under different application states and use them as the key features for model input, which can effectively reflect the operating changes of the spindle under different working conditions. The multi-source operating characteristic matrix is mapped to the application category label. The goal of the mapping process is to be able to distinguish different operating states and working conditions and output a multi-application feature mapping, associating different operating states and working conditions with the operating features of the spindle. During the training process, a mapping function with high discrimination is generated by learning the multi-source feature matrix and application labels. According to the multi-application feature mapping, the identified key features are converted into multi-scenario feature vectors. Through feature reduction techniques (such as principal component analysis (PCA), linear discriminant analysis (LDA), etc.), the redundant information of the key features is reduced, and the main components are extracted from the reduced key features to generate multi-scenario feature vectors that can characterize the changes in different operating application characteristics. Based on the diversity of application working conditions and the changes in the spindle operating state, methods such as time series sliding windows are used to perform time series fusion on the multi-scenario feature vectors, which contain the key features of the spindle operation under different application working conditions.

[0033] Furthermore, converting the key features into multi-scenario feature vectors includes: Applying a feature reduction method to reduce the redundant information of the key features and extract the main feature components that can characterize the changes in multi-application characteristics; Based on the multi-application feature mapping, encoding and combining the main feature components to generate application characteristic vectors corresponding to each application category label; Based on the changes in the time series information during the operation of the main shaft, the time series sliding window method is used to perform time series fusion on the application feature vectors to generate preliminary multi-scenario feature vectors containing time correlation. Smooth the transitional changes between vectors of the preliminary multi-scenario feature vectors to generate multi-scenario feature vectors.

[0034] As an optimization of the above embodiment, dimensionality reduction is performed on the key features extracted from the multi-source operation data. The covariance matrix of the feature matrix is calculated using principal component analysis (PCA), and the principal components with high feature contribution rates are extracted. The components with the cumulative contribution rate of the feature variance reaching the set threshold are retained. Or through linear discriminant analysis (LDA), the within-class scatter matrix and between-class scatter matrix are calculated based on the application category labels, the classification interval is optimized, and the discriminant features related to the category are extracted. The output result is the main feature components after dimensionality reduction. Based on the multi-application feature mapping, the main feature components are encoded and combined to generate application feature vectors. According to the multi-application feature mapping, combining the main feature components and the application category labels, application feature vectors are generated through an encoding method. A binary feature matrix is created for each category label, and the main feature components are used as continuous value features and combined with the category label encoding to form feature vectors. The feature vectors are normalized to ensure the consistency of the numerical range and avoid biases caused by differences in feature scales. The output set of feature vectors covers the operating states of the main shaft in different application scenarios. Based on the changes in the time series information, the time series sliding window method is used for time series fusion. For the time series changes of the application feature vectors, the sliding window length and sliding step are set, and the weighted average value of the feature vectors within the window is calculated. The weights can be assigned according to the time distance or feature importance. The feature vectors within the window are cumulatively summed to extract the cumulative features of the operating state, and the feature vectors after window fusion are output, retaining the time dynamic information and eliminating short-term fluctuations at the same time. The generated preliminary multi-scenario feature vectors contain time correlation and application state characteristics. Smooth optimization is performed on the preliminary multi-scenario feature vectors to generate the final multi-scenario feature vectors. The preliminary multi-scenario feature vectors are smoothed. The moving average method is used to calculate the mean value of adjacent feature vectors to reduce short-term fluctuations, or the exponential smoothing method is used to weight the current feature vector and the historical smoothing results. The weights are controlled by the smoothing factor (such as 0.2). The smoothed vectors are standardized to ensure that the feature values are within a unified range, and the continuity and accuracy of the vectors are confirmed by verifying and comparing the original data with the optimized results. The finally generated multi-scenario feature vectors completely describe the operating state and dynamic change trend of the main shaft under multi-application scenarios.

[0035] Furthermore, as Figure 4 shown, multi-dimensional coupled fatigue analysis is performed on the multi-scenario feature vectors, including: Based on multi-scenario feature vectors, extract damage characteristic parameters that affect the fatigue damage of the main shaft, quantify the contribution degree of the damage characteristic parameters to the fatigue damage accumulation, and generate a multi-dimensional feature contribution matrix for the fatigue damage of the main shaft; According to the multi-dimensional feature contribution matrix, establish a non-linear interaction relationship between multiple damage characteristic parameters to characterize the fatigue damage accumulation effect; According to the fatigue damage accumulation effect, quantify the change in the fatigue damage accumulation rate caused by application switching, and generate a fatigue response curve of the main shaft under dynamic operating conditions; Based on the fatigue response curve and multi-scenario feature vectors, analyze the fatigue damage accumulation trend of the main shaft under various operating scenarios, calculate the fatigue damage accumulation value, and predict and verify the change trend of the fatigue accumulation rate.

[0036] As an optimization of the above embodiment, based on multi-scenario feature vectors, extract characteristic parameters closely related to fatigue damage, including but not limited to operating indicators such as rotational speed, vibration amplitude, temperature, and load. Through sensitivity analysis or correlation analysis, calculate the contribution degree of each characteristic parameter to the fatigue damage accumulation. For example, use statistical methods (such as regression analysis, weight assignment model) to determine the weight values of different parameters for fatigue damage, and construct a multi-dimensional feature contribution matrix. The rows of the multi-dimensional feature contribution matrix represent the characteristic parameters in the multi-scenario feature vectors, the columns represent the influence indicators of fatigue damage, and the matrix element values are the contribution degrees of the characteristic parameters; use machine learning methods (such as neural networks, support vector machines) or mathematical modeling methods (such as high-order polynomial fitting, non-linear regression model) to establish an interaction relationship model between damage characteristic parameters to characterize the complex non-linear interaction between parameters. Based on the non-linear interaction relationship, simulate the comprehensive accumulation effect of multiple characteristic parameters on fatigue damage, which is used to describe the dynamic evolution process of damage accumulation; according to the change of operating characteristic parameters under different working conditions (such as increased load, rotational speed fluctuation), quantify the change in the fatigue damage accumulation rate caused by working condition switching, calculate the amplitude and time constant of the damage rate change, and combine the damage rate change with time series data to draw the fatigue response curve of the main shaft under dynamic operating conditions. The fatigue response curve describes the speed and trend of fatigue damage accumulation under different operating scenarios; based on the fatigue response curve, analyze the fatigue damage accumulation trend of the main shaft under various operating scenarios, extract the change pattern of the damage rate (such as accelerated accumulation or slowed accumulation), integrate the accumulated damage in different time intervals according to the fatigue response curve, calculate the fatigue damage accumulation value, and use it as a fatigue damage quantification index for the current operating state; use time series analysis methods to predict the future change trend of the fatigue damage accumulation rate, obtain the damage evolution path under future operating scenarios, and compare the prediction results with the actual operating data of the main shaft to verify the accuracy of the prediction.

[0037] Furthermore, calculating the fatigue damage accumulation value includes: Perform step-by-step cumulative analysis on the multi-scenario feature vectors, and generate basic analysis data for describing fatigue damage accumulation based on the change trends under various operating states; Divide the operation process into multiple time intervals, and perform independent damage assessment on the basic analysis data within each time interval to generate the interval fatigue damage accumulation value; In response to the change in the operating state, adjust the cumulative weights of each time interval in the cumulative calculation process to reflect the influence on the fatigue damage accumulation rate in various applications; Integrate the cumulative weights and the interval fatigue damage accumulation values for global cumulative integration to generate the fatigue damage accumulation value, which is used as the quantification result of the damage state in the current operation stage.

[0038] As an optimization of the above embodiment, based on the multi-scenario feature vectors, gradually analyze the fatigue damage change trends of the main shaft under various operating states, extract characteristic parameters related to fatigue damage (such as rotational speed, load, vibration amplitude, etc.), combine with time series information to construct basic analysis data, and gradually accumulate the contributions of each characteristic parameter to fatigue damage to obtain basic analysis data describing the cumulative change of fatigue damage; divide the operation process into multiple time intervals, and perform independent damage assessment on each time interval. According to the time series characteristics of the main shaft operating state, divide the entire operation process into multiple time intervals (such as time periods of fixed length or adaptive time intervals based on changes in the operating state). Within each time interval, perform independent evaluation on the basic analysis data to quantify the fatigue damage accumulation value within that interval, and use mathematical methods (such as time-weighted integration or the average value of characteristic parameters within the interval) to calculate the fatigue damage accumulation value of each time interval; adjust the cumulative weights of each time interval in the cumulative calculation process. In response to the change in the operating state, calculate the cumulative weights of different time intervals to reflect the different influences of the operating conditions in each interval on the fatigue damage accumulation rate. The cumulative weights can be dynamically adjusted according to factors such as the importance of characteristic parameters, the influence of working condition switching, and the change in load level. For example, the weight for the high-load operating state can be set to a higher value, while the weight for the low-load operating state is set to a lower value to accurately reflect the actual damage contribution; integrate the cumulative weights and the interval fatigue damage accumulation values to generate the global cumulative result. Weight the fatigue damage accumulation values of each time interval according to the weights to generate the global cumulative result, using the formula: where, D total is the global cumulative value of fatigue damage, D i is the cumulative value of the i-th time interval, W iis the weight of the corresponding interval, and N is the total number of time intervals. By integrating the cumulative weight and the interval damage cumulative value, the global cumulative value of fatigue damage is obtained as the quantification result of the fatigue state in the current operation stage.

[0039] Embodiment 2; Based on the same inventive concept as the spindle life prediction method based on application analysis in the foregoing embodiment, the present invention also provides a spindle life prediction system based on application analysis, which includes: A modal perception module that establishes a modal perception network, collects multi-source operation data during the operation of the spindle, and generates a multi-source operation characteristic matrix; A feature mapping module that establishes a multi-application feature mapping based on the multi-source operation characteristic matrix and generates a multi-scene feature vector describing the operation state of the device; A fatigue analysis module that performs multi-dimensional coupled fatigue analysis on the multi-scene feature vector and outputs the cumulative value of the fatigue damage of the spindle; A life prediction module that obtains and combines the historical motion data of the spindle according to the cumulative value of the fatigue damage, establishes a heterogeneous parameter life prediction model, and outputs a remaining life prediction value based on the heterogeneous parameter life prediction model.

[0040] The above adjustment system in the present invention can effectively implement the spindle life prediction method based on application analysis, and the technical effects that can be achieved are as described in the foregoing embodiment, which will not be elaborated here.

[0041] Furthermore, the life prediction module includes: A rule statistics unit that extracts the fatigue damage accumulation rule of the spindle historical operation data based on multiple application scenarios and generates an application fatigue correlation feedback as the input of the heterogeneous parameter life prediction model; A time series analysis unit that establishes a fatigue damage accumulation curve in the current application scenario according to the cumulative value of the fatigue damage and the application fatigue correlation feedback, in combination with the time series analysis method; A critical prediction unit that simulates the fatigue accumulation change trend of the spindle under multiple applications based on the fatigue damage accumulation curve, and predicts the fatigue critical point according to the trend direction and the trend intersection time series; An integrated calculation unit that integrates the fatigue critical points and calculates the comprehensive remaining life of the spindle in the current and future applications according to the integrated point set. The comprehensive remaining life is the predicted life in the current application; A scenario superposition unit that calculates and outputs a remaining life prediction value according to the comprehensive remaining life, in combination with the single-application and multi-application superposition conditions of the spindle.

[0042] Similarly, for the above optimization solutions of the system, the corresponding optimization effects of the method in Embodiment 1 can also be realized respectively, which will not be elaborated here either.

[0043] Although the present application has been described in connection with specific features and their embodiments, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the present application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined by the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A life prediction method for a main shaft based on application analysis, characterized in that: The method comprises: Establish a modal perception network to collect multi-source operation data during the operation of the spindle and generate a multi-source operation characteristic matrix; Based on the multi-source operation characteristic matrix, a multi-application feature map is established, and a multi-scenario feature vector describing the operation status of the device is generated; Performing multi-dimensional coupled fatigue analysis on the multi-scenario feature vectors, and outputting a fatigue damage accumulation value of the main shaft; According to the fatigue damage accumulation value, the historical motion data of the main shaft is obtained and combined to establish a heterogeneous parameter life prediction model, and the remaining life prediction value is output based on the heterogeneous parameter life prediction model.

2. The life prediction method based on application analysis spindle according to claim 1 is characterized in that: Outputting a remaining life prediction value based on the heterogeneous life prediction model includes: Extracting fatigue damage accumulation rules of the spindle historical operation data based on multiple application scenarios, and generating application fatigue correlation feedback as input of the heterogeneous parameter life prediction model; According to the fatigue damage accumulation value and the application fatigue correlation feedback, combined with the time series analysis method, a fatigue damage accumulation curve in the current application scenario is established; Based on the fatigue damage accumulation curve, the fatigue accumulation change trend of the main shaft under various applications is simulated, and the fatigue critical point is predicted according to the trend direction and the trend intersection time sequence; Integrate the fatigue critical points, and calculate the comprehensive remaining life of the spindle in current and future applications based on the integrated point set, wherein the comprehensive remaining life is the predicted life under the current application; According to the comprehensive remaining life, combined with the single-application and multi-application superposition conditions of the main shaft, the remaining life prediction value is calculated and output.

3. The life prediction method based on application analysis spindle according to claim 2 is characterized in that: Predict fatigue critical points based on trend trends and trend intersection timing, including: Analyze the fatigue damage accumulation rules of various spindles under multiple application operating conditions, sort out the trend trends and set fatigue critical point judgment conditions according to the fatigue damage accumulation rules; A fatigue evolution model is established according to the applied fatigue correlation feedback and the fatigue damage accumulation curve to simulate the nonlinear dynamic characteristics of the main shaft fatigue damage accumulation; Taking the multi-scenario feature vector as input, analyzing the weights of fatigue influencing factors of the main shaft under various operation scenarios, and using the fatigue influencing factors as feedback to adjust the prediction accuracy of the fatigue evolution model; According to the fatigue influencing factors, for a plurality of the multi-scenario feature vectors, according to the trend trend, the timing of the main axis reaching the fatigue critical point and the corresponding application characteristics are predicted to generate simulation prediction results; The simulation prediction result is compared with the fatigue critical point determination condition to perform dynamic correction, and generate the fatigue critical point for current application and future application.

4. The life prediction method based on application analysis spindle according to claim 3 is characterized in that: Simulate the nonlinear dynamic characteristics of spindle fatigue damage accumulation, including: By structurally analyzing the multi-source operation data, a fatigue damage accumulation simulation framework is constructed, and the multi-scenario feature vectors of the spindle operation are mapped to the fatigue damage accumulation simulation framework; Simulate the nonlinear evolution of fatigue damage under multiple application superposition conditions in various operating scenarios, and describe the changes in coupling characteristics and fatigue accumulation rates in multiple applications; According to the fatigue accumulation rate, a fatigue accumulation coefficient is calculated to adjust the fatigue damage accumulation simulation framework; The accumulation rules of the main shaft in various stages are integrated, and the simulation results of each stage are integrated to generate the nonlinear trend of fatigue damage accumulation in the whole life cycle; By comparing the historical operating data of the spindle with the fatigue damage critical point determination conditions, the accuracy of the simulation results is verified and the deviation is corrected.

5. The life prediction method based on application analysis spindle according to claim 1 is characterized in that: Build multi-application feature maps, including: Based on the multi-source operation data during the operation of the spindle, key features related to the operation state of the spindle are extracted to generate a multi-source operation characteristic matrix containing time series information; Classifying the multi-source operating characteristic matrix, and generating corresponding application category labels according to various operating states; According to the statistical correlation analysis method between the key features, identifying the core characteristic parameters closely related to the spindle operation state; A mapping is established to map the multi-source operating characteristic matrix to the application category label, a multi-application feature map is generated that can distinguish between multiple operating applications, and the key features are converted into the multi-scenario feature vector.

6. The life prediction method based on application analysis spindle according to claim 5 is characterized in that: Converting the key features into the multi-scenario feature vector includes: Applying a feature dimensionality reduction method to reduce redundant information of the key features and extracting main feature components that can characterize changes in multi-application characteristics; Based on the multi-application feature mapping, the main feature components are encoded and combined to generate application characteristic vectors corresponding to each of the application category labels; Based on the change of time series information during the operation of the main axis, the application characteristic vector is time-series fused using a time series sliding window method to generate a preliminary multi-scenario feature vector containing time correlation; The preliminary multi-scene feature vector is subjected to a transition change between smoothing vectors to generate the multi-scene feature vector.

7. The life prediction method based on application analysis spindle according to claim 1 is characterized in that: Performing multi-dimensional coupled fatigue analysis on the multi-scenario feature vectors includes: Based on the multi-scenario feature vectors, extract damage characteristic parameters that affect the fatigue damage of the main shaft, quantify the contribution of the damage characteristic parameters to the accumulation of fatigue damage, and generate a multi-dimensional feature contribution matrix of the fatigue damage of the main shaft; According to the multidimensional feature contribution matrix, a nonlinear interaction relationship between the plurality of damage characteristic parameters is established to characterize the cumulative effect of fatigue damage; According to the fatigue damage accumulation effect, the change of fatigue damage accumulation rate caused by application switching is quantified to generate a fatigue response curve of the spindle under dynamic operating conditions; Based on the fatigue response curve and the multi-scenario feature vector, the fatigue damage accumulation trend of the main shaft in various operating scenarios is analyzed, the fatigue damage accumulation value is calculated, and the change trend of the fatigue accumulation rate is predicted and verified.

8. The life prediction method based on application analysis of the main axis according to claim 7 is characterized in that: Calculating the fatigue damage accumulation value includes: Performing a step-by-step cumulative analysis on the multi-scenario feature vectors, and generating basic analysis data describing fatigue damage accumulation based on the changing trends under various operating states; Divide the operation process into multiple time intervals, perform independent damage assessment on the basic analysis data in each time interval, and generate interval fatigue damage accumulation value; According to the changes in operating conditions, the cumulative weights of each time interval in the cumulative calculation process are adjusted to reflect the impact of various applications on the fatigue damage accumulation rate; The cumulative weight and the interval fatigue damage cumulative value are combined to perform global cumulative integration to generate a fatigue damage cumulative value as a quantified result of the damage state in the current operation stage.

9. The life prediction system of the main shaft based on application analysis is characterized by: The system comprises: The modal perception module establishes a modal perception network, collects multi-source operation data during the operation of the spindle, and generates a multi-source operation characteristic matrix; The feature mapping module establishes a multi-application feature mapping based on the multi-source operation characteristic matrix and generates a multi-scenario feature vector describing the operation status of the device; The fatigue analysis module performs multi-dimensional coupled fatigue analysis on multi-scenario feature vectors and outputs the fatigue damage accumulation value of the main shaft; The life prediction module obtains and combines the historical motion data of the spindle according to the accumulated value of fatigue damage, establishes a heterogeneous parameter life prediction model, and outputs the remaining life prediction value based on the heterogeneous parameter life prediction model.

10. The life prediction system based on application analysis spindle according to claim 9 is characterized in that: The life prediction module comprises: The law statistics unit extracts the fatigue damage accumulation law of the spindle historical operation data based on various application scenarios, and generates application fatigue correlation feedback as the input of the heterogeneous parameter life prediction model; The time series analysis unit establishes the fatigue damage accumulation curve under the current application scenario based on the fatigue damage accumulation value and the application fatigue correlation feedback combined with the time series analysis method; The critical prediction unit simulates the fatigue accumulation trend of the main shaft under various applications based on the fatigue damage accumulation curve, and predicts the fatigue critical point according to the trend direction and trend intersection timing; Comprehensive calculation unit, integrating fatigue critical points, and calculating the comprehensive remaining life of the main shaft in current and future applications based on the integrated point set. The comprehensive remaining life is the predicted life under the current application; The scenario overlay unit calculates and outputs the remaining life prediction value based on the comprehensive remaining life and the main axis single application and multi-application overlay conditions.

Images