A multi-factor consideration friction plate fatigue life prediction method

Abstract

The application discloses a kind of multi-factor influence's friction plate fatigue life prediction method, comprising: obtaining the performance parameters of friction plate under actual working condition multi-factor influence, introduce average friction coefficient calculation key parameter;Multi-dimensional feature input vector is constructed, and the nonlinear mapping relationship between the fatigue life of friction plate and each influencing factor is established based on deep neural network model;Real-time monitoring the performance of the friction plate, obtain corresponding fatigue life prediction value;Adopt fuzzy comprehensive evaluation method to analyze the change trend of the optimal characteristic parameter, establish the fuzzy evaluation model of state evaluation, obtain the wear degree prediction value of friction plate;The confidence analysis module is used to the wear degree prediction value of the friction plate, the confidence of the prediction result of the wear degree prediction value of the friction plate is evaluated, the fatigue life prediction interval containing error range is generated, the prediction accuracy and model generalization ability are significantly improved, and the credibility and explainability of prediction result are enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of friction plate, and in particular to a friction plate fatigue life prediction method considering multi-factor influence. BACKGROUND

[0002] With the development of modern industry, the reliability and maintenance cost of mechanical equipment have become the focus of attention. As an important component in many key mechanical systems, such as brake systems, clutches, etc., the fatigue life of the friction plate directly affects the safety and service life of the equipment. In order to accurately predict the fatigue life of the friction plate, various methods and technologies have been adopted. However, the existing technology still has deficiencies in handling fatigue life prediction under the influence of multiple factors:

[0003] (1) Single factor analysis ignores complex interactions. Most current friction plate fatigue life prediction methods mainly rely on single factors such as temperature, pressure or sliding speed to model the influence on performance. However, in actual working conditions, the wear and fatigue life of the friction plate is the result of the combined action of multiple factors, and there may be complex nonlinear relationships between these factors.

[0004] (2) Lack of effective methods for comprehensive modeling of multiple factors. When dealing with high-dimensional data and complex nonlinear relationships, linear relationship modeling is used, which cannot handle the nonlinear coupling between multiple factors and is prone to large errors. Existing comprehensive modeling methods for multiple factors usually require a large amount of experimental data for calibration, and it is often challenging to obtain sufficient high-quality data in actual applications. SUMMARY

[0005] The present application aims to provide a friction plate fatigue life prediction method considering multi-factor influence, to solve the technical problems of single factor analysis ignoring complex interactions and lack of effective methods for comprehensive modeling of multiple factors in the prior art.

[0006] To solve the above technical problems, the present application specifically provides the following technical solutions:

[0007] The present application provides a friction plate fatigue life prediction method considering multi-factor influence, comprising the following steps:

[0008] Obtain the performance parameters of the friction plate under the influence of multiple factors in actual working conditions, and introduce the average friction coefficient as a key parameter for state monitoring of the friction plate.

[0009] Normalize the key parameters, construct a multi-dimensional feature input vector, train a deep neural network based on historical fatigue test data, and establish a nonlinear mapping relationship between the fatigue life of the friction plate and each influencing factor.

[0010] According to the nonlinear mapping relationship, the performance of the friction plate is monitored in real time, current friction plate operation parameters to be predicted are input into the trained deep neural network model, and a corresponding fatigue life prediction value is acquired;

[0011] According to the fatigue life prediction value, the wear amount of the friction plate is simulated, a corresponding relationship between the optimal characteristic parameter of the friction plate and state evaluation is established, a fuzzy evaluation model of state evaluation is established by analyzing the change trend of the optimal characteristic parameter by using a fuzzy comprehensive evaluation method, and a friction plate wear degree prediction value is acquired;

[0012] The confidence analysis module is used for the friction plate wear degree prediction value, the confidence of the prediction result of the friction plate wear degree prediction value is evaluated, and a fatigue life prediction interval containing an error range is generated.

[0013] As a preferred scheme of the application, the performance parameters of the friction plate under the influence of multiple factors in actual working conditions are acquired, and the average friction coefficient is introduced as a key parameter for state monitoring of the friction plate, including:

[0014] The performance parameters of the friction plate under the influence of multiple factors in actual working conditions are acquired, and the influence factors at least include friction material properties, working temperature, contact pressure, sliding speed, lubrication state, load cycle frequency and friction force change curve in the friction process;

[0015] In the friction plate operation process, the instantaneous friction force and normal pressure data at multiple time points are collected in real time, and the average friction coefficient of the friction is calculated, and the expression is:

[0016] ;

[0017] Wherein, represents the friction force of the i th sampling point, represents the normal pressure of the i th sampling point, represents the total number of sampling points;

[0018] The average friction coefficient is used as a characteristic parameter reflecting the surface wear state and friction stability of the friction plate, and is used as a key parameter for state monitoring of the friction plate.

[0019] As a preferred scheme of the application, the key parameter is normalized, a multi-dimensional feature input vector is constructed, the deep neural network is trained based on the deep neural network model and combined with historical fatigue test data, a nonlinear mapping relationship between the fatigue life of the friction plate and each influence factor is established, and the nonlinear mapping relationship includes:

[0020] The key parameters are subjected to minimum-maximum normalization processing, and the normalized key parameters are sorted according to the friction plate wear degree, the friction plate wear degree being determined by the friction coefficient on the corresponding friction plate The expression is:

[0021] ;

[0022] Wherein, represents the number of friction pairs of the friction plate, q represents the pressure ratio between the friction plates, 、 represents the inner diameter and outer diameter of the friction plate, represents the friction torque of the friction plate;

[0023] The sorted normalized key parameters are generated into a feature input vector of uniform dimension , wherein n represents the number of feature dimensions;

[0024] A fully connected feedforward neural network model is constructed, a history fatigue test data is trained by fusing an attention mechanism, running parameters under different working conditions are recorded, the fatigue failure time of the friction plate is determined according to the cycle number, and the parameters of the fully connected feedforward neural network model are optimized;

[0025] Influencing factors of the friction plate during the allowed process under different working conditions are input into the fully connected feedforward neural network model, a highly nonlinear, multivariate coupling relationship between the fatigue life of the friction plate and the influencing factors thereof is established, and the interaction effect between multiple factors is obtained.

[0026] As a preferred scheme of the present application, the performance of the friction plate is monitored in real time according to the nonlinear mapping relationship, the current friction plate running parameters to be predicted are input into the trained deep neural network model, and the corresponding fatigue life prediction value is obtained, including:

[0027] The friction plate running parameters under the current working condition are collected in real time by a sensor, the running parameters are input into the fully connected feedforward neural network model according to the nonlinear mapping relationship, and a multi-dimensional feature input vector of multiple factors is obtained , wherein represents the average friction coefficient, represents the working temperature, represents the contact pressure, represents the sliding speed of the friction plate in actual operation, represents the lubricating oil film thickness of the friction plate surface, represents the load cycle frequency of the friction plate, represents the material density, represents the material thermal conductivity, and the like;

[0028] The multidimensional features are input into the vector The ReLU activation function is used to enhance the nonlinear expression capability when inputting the deep neural network model. After forward propagation calculation, the deep neural network model outputs the corresponding predicted value, which represents the estimated remaining fatigue life of the friction plate under current conditions.

[0029] As a preferred solution of the present invention, simulating the wear amount of the friction plate according to the fatigue life prediction value includes:

[0030] The Archard wear model is used to simulate the wear process of the friction plate under different working conditions, and its expression is:

[0031] ;

[0032] in, represents the average friction coefficient, W represents the normal load of the friction plate, d represents the relevant sliding friction distance, and V represents the wear volume;

[0033] According to the multi-dimensional feature input vector under the current working condition Calculate the wear amount of the friction plate in each cycle based on the fatigue life prediction value;

[0034] The wear of the friction plate throughout its life cycle is dynamically simulated using the ANSYS simulation tool to generate a wear curve graph and obtain the wear variation trend over time or the number of cycles.

[0035] As a preferred solution of the present invention, a corresponding relationship between the optimal characterization parameters of the friction plate and the state evaluation is established based on the wear amount of the friction plate, including:

[0036] According to the wear trend of the friction plate over time, n data points are randomly extracted. , , , establish a linear regression equation for the n data points to obtain the wear amount of the friction plate during the stable wear period and wear life The offline relationship between them is expressed as:

[0037] ;

[0038] in, represents the initial wear amount, Indicates the growth rate of wear;

[0039] The degree of fit between the regression model and the actual data is determined by calculating the standard error of the n data points, and the warning baseline and abnormal baseline of the wear element changing over time are obtained according to the linear regression equation and the standard error;

[0040] The wear amount is analyzed by using a random forest algorithm, and a mapping relationship between a characteristic parameter and a wear state is established.

[0041] According to the characteristic parameter values obtained through real-time monitoring, a few key parameters that have the greatest impact on the wear state are identified through sensitivity analysis of each characteristic parameter.

[0042] Based on a weighted fusion strategy, weights are assigned to different characteristic parameters, and a comprehensive scoring system is constructed to quantify the overall wear state of the friction plate, and the expression is:

[0043]

[0044] Among them, respectively represent the weight of the corresponding characteristic parameter, represent the comprehensive score.

[0045] As a preferred scheme of the present application, a fuzzy comprehensive evaluation method is used to analyze the weight of the optimal characteristic parameter, including:

[0046] A factor set containing each index is created for the comprehensive score , The mth element that affects the evaluation object is represented, and an evaluation set is established for the comprehensive score , and the elements in the evaluation set represent the evaluation results of the corresponding influencing factors;

[0047] The weight of the corresponding sample under the ith factor index is calculated using the positive evaluation index, and the entropy value of the jth index is obtained, and the expression is:

[0048]

[0049] Among them, n represents the number of samples, represents the number of elements in the factor set , and represents the weight of the jth index under the ith factor index.

[0050] According to the entropy value, the difference of each index is calculated, the weight of multiple indexes in the comprehensive evaluation system is calculated, and the weight of the optimal characteristic parameter is obtained, and the expression is:

[0051]

[0052] As a preferred scheme of the present application, a fuzzy evaluation model of state assessment is established for the weight of the optimal characteristic parameter, and a friction plate wear degree prediction value is obtained, including: ​​​​

[0053] For each characterization parameter, its fuzzy membership function under different wear states is defined, and a fuzzy evaluation matrix R is constructed, where each row represents a characterization parameter, each column represents a wear state level, and the matrix elements are It represents the membership value of the i-th characterization parameter under the j-th wear state level, and its expression is:

[0054] ;

[0055] Where m is the number of characterization parameters and n is the number of wear state levels;

[0056] The fuzzy comprehensive evaluation formula is calculated according to the weight of the optimal characterization parameter to obtain a comprehensive evaluation result vector B, which is expressed as follows:

[0057] ;

[0058] in, , represents the comprehensive membership value of the friction plate at each wear state level;

[0059] Comprehensive evaluation result vector Perform normalization processing to obtain the membership value and determine the current wear state level of the friction plate;

[0060] The wear degree prediction value is obtained according to the wear degree range corresponding to the wear state level with the highest membership value.

[0061] As a preferred solution of the present invention, a confidence analysis module is used for the predicted value of the friction plate wear degree, and a confidence evaluation is performed on the predicted result of the predicted value of the friction plate wear degree, including:

[0062] The wear degree prediction value is combined with each sample in the historical data set, the residual between the wear degree prediction value and the true value is calculated, and the distribution characteristics of the residual are statistically analyzed;

[0063] The distribution characteristics of the residuals are calculated using the properties of the normal distribution to calculate the confidence interval and set the confidence level , calculate the upper and lower limits of the confidence interval, the expression is:

[0064] ;

[0065] in, represents the lower limit of the confidence interval, represents the upper limit of the confidence interval, represents the predicted value of wear degree, Indicates the corresponding confidence level under normal distribution The critical value of Represents the standard deviation of the residuals.

[0066] As a preferred scheme of the present application, in combination with the wear degree prediction value and its confidence interval, a fatigue life prediction interval containing an error range is generated, including:

[0067] The remaining service life of the wear degree prediction value under the current wear rate is calculated using the Archard wear model;

[0068] The confidence interval of the wear degree prediction value is converted into the upper and lower limits of the fatigue life prediction interval according to the change trend of the wear over time;

[0069] The confidence is monitored online using a state evaluation algorithm to track the state of the friction plate in real time;

[0070] The current wear degree prediction value and its confidence interval are displayed in real time, and when the friction plate is detected to enter a moderate wear or more severe state, the system automatically triggers an alarm.

[0071] Compared with the prior art, the present application has the following beneficial effects:

[0072] The present application introduces the average friction coefficient as a key state monitoring parameter, combines multi-dimensional feature normalization processing and deep neural network modeling, establishes a nonlinear mapping relationship between the fatigue life of the friction plate and its operating conditions, and significantly improves the prediction accuracy and model generalization ability.

[0073] Based on the Archard wear model, the wear process of the friction plate is dynamically simulated, and a state evaluation model is constructed using a fuzzy comprehensive evaluation method. The optimal characteristic parameter is scientifically weighted using an entropy weight method, the current wear stage of the friction plate is effectively identified, a quantitative wear degree prediction value is output, a confidence analysis module is introduced, the confidence interval is calculated by statistically analyzing the historical residual error, a fatigue life prediction interval containing an error range is generated, the credibility and interpretability of the prediction result are enhanced, and at the same time, online confidence monitoring and real-time warning functions are realized by combining the state evaluation algorithm. When the friction plate is detected to enter a moderate wear or more severe state, the system automatically triggers an alarm, assisting the operation and maintenance personnel to take timely intervention measures to avoid equipment failure. BRIEF DESCRIPTION OF DRAWINGS

[0074] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of the provided drawings.

[0075] Figure 1A flowchart of the friction plate fatigue life prediction method considering the influence of multiple factors is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0076] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0077] As shown in the drawings, Figure 1 The present application provides a friction plate fatigue life prediction method considering the influence of multiple factors, comprising the following steps:

[0078] Obtaining the performance parameters of the friction plate under the influence of multiple factors in actual working conditions, introducing the average friction coefficient as the key parameter for state monitoring of the friction plate to the performance parameters;

[0079] In the embodiment, by collecting multiple performance parameters under actual working conditions and introducing the average friction coefficient as a core index reflecting the friction stability and wear state, the perception ability of the model to the real-time state of the friction plate is improved, and the physical meaning and engineering practicability of the data input are enhanced.

[0080] Normalizing the key parameters, constructing a multi-dimensional feature input vector, training the deep neural network based on the deep neural network model and combining historical fatigue test data, establishing a nonlinear mapping relationship between the fatigue life of the friction plate and each influencing factor;

[0081] In the embodiment, the normalization processing method is used to unify the input parameters of different dimensions to the same scale range, avoiding the model training deviation caused by too large difference in feature values; and the constructed multi-dimensional feature input vector provides a structured basis for subsequent establishment of a nonlinear mapping relationship.

[0082] According to the nonlinear mapping relationship, the performance of the friction plate is monitored in real time, the current friction plate operating parameters to be predicted are input into the trained deep neural network model, and the corresponding fatigue life prediction value is obtained;

[0083] In the embodiment, the deep neural network model is trained based on the deep neural network model and combined with historical fatigue test data, and a highly nonlinear mapping relationship between the fatigue life of the friction plate and each influencing factor is successfully established. The model not only can capture the influence of a single factor, but also can effectively identify the interaction between multiple factors, thereby significantly improving the prediction accuracy and generalization ability.

[0084] According to the fatigue life prediction value, the wear amount of the friction plate is simulated, the correspondence between the optimal characteristic parameters of the friction plate and the state evaluation is established, the change trend of the optimal characteristic parameters is analyzed by using a fuzzy comprehensive evaluation method, a fuzzy evaluation model of the state evaluation is established, and a friction plate wear degree prediction value is obtained.

[0085] In the embodiment, the wear amount of the friction plate is simulated according to the fatigue life prediction result, representative optimal characteristic parameters are extracted, the change trend of the parameters is modeled by using a fuzzy comprehensive evaluation method, a fuzzy evaluation model of the state evaluation is constructed, and a quantitative prediction value of the wear degree of the friction plate is obtained, so that the state evaluation is more scientific and operable.

[0086] The confidence analysis module is used for the friction plate wear degree prediction value, the confidence of the prediction result of the friction plate wear degree prediction value is evaluated, and a fatigue life prediction interval containing an error range is generated.

[0087] In the embodiment, the confidence analysis module is introduced to evaluate the uncertainty of the wear degree prediction result, generate a fatigue life prediction interval containing an error range, improve the credibility and engineering applicability of the prediction result, and help to realize the intelligent operation and maintenance and preventive replacement strategy of the friction plate.

[0088] The performance parameters of the friction plate under the influence of multiple factors in actual working conditions are obtained, and the average friction coefficient is introduced as a key parameter for state monitoring of the friction plate, including:

[0089] The performance parameters of the friction plate under the influence of multiple factors in actual working conditions are obtained, and the influence factors at least include: friction material properties, working temperature, contact pressure, sliding speed, lubrication state, load cycle frequency and friction force change curve in the friction process;

[0090] The instantaneous friction force and normal pressure data at multiple time points are collected in real time during the operation of the friction plate, and the average friction coefficient of the friction is calculated, and the expression is:

[0091] ;

[0092] Wherein, F i represents the friction force of the i th sampling point, P i represents the normal pressure of the i th sampling point, N represents the total number of sampling points;

[0093] In this embodiment, the average friction coefficient can effectively reflect the wear degree of the surface material of the friction plate during long-term operation. As the friction plate gradually ages or wears, its friction coefficient will change significantly. Traditional friction plate monitoring methods usually rely on a single physical parameter, such as temperature or pressure, which makes it difficult to accurately capture the dynamic changes of the friction process. However, the average friction coefficient integrates the trends of friction force and normal pressure, and can more comprehensively reflect the stability of the friction system.

[0094] The average friction coefficient is used as a characteristic parameter reflecting the wear state of the friction plate surface and the stability of friction, and as a key parameter for monitoring the state of the friction plate.

[0095] In this embodiment, the average friction coefficient can be directly used to construct the input vector of the deep neural network model, which helps to improve the training efficiency and prediction accuracy of the model.

[0096] In this embodiment, by combining the average friction coefficient with other key parameters, a more accurate nonlinear mapping relationship between the fatigue life of the friction plate and its operating state can be modeled, thereby achieving more scientific and reasonable life prediction and maintenance decisions.

[0097] The key parameters are normalized to construct a multi-dimensional feature input vector. Based on a deep neural network model, the deep neural network is trained based on historical fatigue test data to establish a nonlinear mapping relationship between the fatigue life of the friction plate and various influencing factors, including:

[0098] The key parameters are normalized by minimum-maximum normalization. The normalized key parameters are sorted according to the wear degree of the friction plate, which is determined by the friction coefficient on the corresponding friction plate. The friction coefficient The expression is:

[0099] ;

[0100] Wherein, represents the number of friction pairs of the friction plate, and q represents the pressure ratio between the friction plates, 、 represents the inner diameter and outer diameter of the friction plate, represents the friction torque of the friction plate;

[0101] The sorted and normalized key parameters are generated into a unified dimension feature input vector where n represents the number of feature dimensions.

[0102] In this embodiment, the normalization processing and the introduction of the attention mechanism enable the model to more effectively capture key features and avoid prediction bias caused by large scale differences in certain parameters, thereby significantly improving prediction accuracy and stability.

[0103] In this embodiment, the construction of the feature input vector takes into account both physical significance and data-driven characteristics, so that the model is not only suitable for single material or working condition, but also can be extended to various types of friction plates and complex operating environment.

[0104] A fully connected feedforward neural network model is constructed, and historical fatigue test data are trained by fusing attention mechanism. The operating parameters under different working conditions are recorded, and the fatigue failure time or cycle number corresponding to the friction plate is used to optimize the parameters of the fully connected feedforward neural network model.

[0105] In this embodiment, a large amount of friction plate fatigue test data from laboratory tests or actual service environment are collected, including: operating parameter records under different working conditions and corresponding fatigue failure time or cycle number. The data are divided into training set, validation set and test set. Mean square error is used as loss function. Model parameters are continuously optimized by back propagation algorithm until validation set error is stable.

[0106] The influencing factors of friction plate during operation under different working conditions are input into the fully connected feedforward neural network model, and a highly nonlinear, multivariate coupling relationship between friction plate fatigue life and its influencing factors is established to obtain the interactive effect between multiple factors.

[0107] In this embodiment, after sufficient training, the deep neural network can automatically learn and model the complex nonlinear relationship between the fatigue life of the friction plate and its influencing factors, including: nonlinear dependence of material properties and fatigue life, attenuation effect of temperature rise on friction stability and life, influence of lubrication state change on friction coefficient fluctuation, and dynamic correlation between average friction coefficient and wear rate.

[0108] According to the nonlinear mapping relationship, the performance of the friction plate is monitored in real time. The current friction plate operating parameters to be predicted are input into the trained deep neural network model to obtain the corresponding fatigue life prediction value, including:

[0109] The operating parameters of the friction plate under the current working condition are collected in real time by the sensor, and the operating parameters are input into the fully connected feedforward neural network model according to the nonlinear mapping relationship to obtain a multi-dimensional feature input vector of multiple factors , wherein represents the average friction coefficient, represents the working temperature, represents the contact pressure, represents the sliding speed of the friction plate in actual operation, represents the lubricating oil film thickness of the friction plate surface, represents the load cycle frequency of the friction plate, represents the material density, representing material thermal conductivity and the like;

[0110] In this embodiment, the multi-dimensional feature input vector integrates multiple key parameters such as average friction coefficient, working temperature, and contact pressure, so that the model can identify the coupling relationship between different factors and improve the robustness and adaptability of the prediction.

[0111] The multi-dimensional feature input vector is input into the deep neural network model. In the input deep neural network model, a ReLU activation function is used to enhance the non-linear expression capability. After forward propagation calculation, the deep neural network model outputs the corresponding predicted value, representing the predicted remaining fatigue life of the friction plate under the current condition.

[0112] In this embodiment, based on the trained deep neural network model, the complex non-linear relationship between the fatigue life of the friction plate and its influencing factors can be accurately captured, thereby improving the prediction accuracy, and the system can complete a complete fatigue life prediction in a short time.

[0113] According to the fatigue life prediction value, the wear amount of the friction plate is simulated, including:

[0114] The Archard wear model is used to simulate the wear process of the friction plate under different working conditions, and its expression is:

[0115] ;

[0116] wherein, represents the average friction coefficient, represents the normal load of the friction plate, and d represents the relevant sliding friction distance, represents the wear volume;

[0117] According to the multi-dimensional feature input vector under the current working condition In combination with the fatigue life prediction value, the wear amount of the friction plate in each cycle is calculated;

[0118] The ANSYS simulation tool is used to dynamically simulate the wear of the friction plate throughout its life cycle, generate a wear curve graph, and obtain the change trend of wear over time or cycle number.

[0119] In this embodiment, the Archard wear model is introduced and combined with the ANSYS simulation tool to model and simulate the wear process of the friction plate, which can accurately simulate the wear evolution process of the friction plate under different working conditions and display the wear trend through a graphical interface, facilitating engineers to understand and apply. On the basis of data-driven prediction, the physical wear model is integrated, so that the fatigue life prediction not only depends on statistical learning, but also has clear mechanical basis, enhancing the credibility and interpretability of the model.

[0120] In this embodiment, the wear curve can be used to estimate when the friction plate will reach the maximum allowable wear, so that a replacement plan can be formulated in advance to avoid equipment downtime or safety accidents caused by sudden failure.

[0121] According to the wear amount of the friction plate, a corresponding relationship between the optimal characterization parameter of the friction plate and the state evaluation is established, including:

[0122] According to the wear trend of the friction plate over time, n data points are randomly extracted. , , , establish a linear regression equation for the n data points to obtain the wear amount of the friction plate during the stable wear period and wear life The offline relationship between them is expressed as:

[0123] ;

[0124] in, represents the initial wear amount, Indicates the growth rate of wear;

[0125] The degree of fit between the regression model and the actual data is determined by calculating the standard error of the n data points, and the warning baseline and abnormal baseline of the wear element changing over time are obtained according to the linear regression equation and the standard error;

[0126] In this embodiment, the standard error of the regression model is calculated to measure the degree of fit of the linear regression model to the actual wear data. According to the size of the standard error, it can be determined whether the current wear process conforms to the expected stable wear law.

[0127] The wear amount is analyzed using random forest algorithm Conduct analysis and establish a mapping relationship between characterization parameters and wear status;

[0128] Based on the characterization parameter values ​​obtained from real-time monitoring, sensitivity analysis is performed on each characterization parameter to identify the key parameters that have the greatest impact on the wear state.

[0129] Based on the weighted fusion strategy, weights are assigned to different characterization parameters, and a comprehensive scoring system is constructed to quantify the overall wear state of the friction plate. Its expression is:

[0130] ;

[0131] in, Represent the weights of the corresponding characterization parameters, Indicates the comprehensive score.

[0132] In this embodiment, through linear regression modeling and standard error analysis, the wear stage and development trend of the friction plate can be accurately identified. The warning baseline and abnormal baseline generated by the regression model can be used to provide timely warnings before the wear amount reaches the failure threshold, effectively avoiding the occurrence of sudden failures.

[0133] In this embodiment, the random forest algorithm can capture the complex dependency between the friction plate wear state and multiple operating parameters, improve the accuracy and robustness of state recognition, and integrate multiple characterization parameters into a highly interpretable numerical indicator, making it easier for engineers to quickly determine the current state level of the friction plate.

[0134] The fuzzy comprehensive evaluation method is used to analyze the weights affecting the optimal characterization parameters, including:

[0135] Create a factor set containing each indicator for the comprehensive score , Represents the mth element that affects the evaluation object, and establishes an evaluation set for the comprehensive score , the evaluation set The middle element represents the evaluation result of its corresponding influencing factor;

[0136] The positive evaluation index is used to calculate the weight of the corresponding sample under the i-th factor index, and the entropy value of the j-th index is obtained. The expression is:

[0137] ;

[0138] Where n represents the number of samples, Representation factor set The number of elements in It represents the weight of the jth indicator under the i-th factor indicator;

[0139] In this embodiment, the information content and difference of each indicator are automatically calculated based on the actual data distribution to obtain the entropy value, which avoids the deviation caused by subjective experience weighting and makes the weight distribution more objective and reasonable.

[0140] The difference of each indicator is calculated according to the entropy value, the weights of multiple indicators in the comprehensive evaluation system are calculated, and the weights affecting the optimal characterization parameters are obtained. The expression is:

[0141] .

[0142] In this embodiment, by performing system modeling and weight analysis on multiple influencing factors, the key parameters that have the most significant impact on the wear state of the friction plate can be effectively identified, which helps to improve the accuracy and stability of the evaluation results.

[0143] A fuzzy judgment model for state evaluation is established for the weights of the optimal characterization parameters to obtain a predicted value of the degree of friction plate wear, including:

[0144] For each characterization parameter, its fuzzy membership function under different wear states is defined, and a fuzzy evaluation matrix R is constructed, where each row represents a characterization parameter, each column represents a wear state level, and the matrix elements are It represents the membership value of the i-th characterization parameter under the j-th wear state level, and its expression is:

[0145] ;

[0146] Where m is the number of characterization parameters and n is the number of wear state levels;

[0147] In this embodiment, by defining the fuzzy membership function of each characterization parameter under different wear states and constructing a fuzzy evaluation matrix, the originally fuzzy and uncertain wear state judgment process is transformed into a computable and quantifiable mathematical model, thereby improving the accuracy and consistency of the evaluation results.

[0148] The fuzzy comprehensive evaluation formula is calculated according to the weight of the optimal characterization parameter to obtain a comprehensive evaluation result vector B, which is expressed as follows:

[0149] ;

[0150] in, , represents the comprehensive membership value of the friction plate at each wear state level;

[0151] Comprehensive evaluation result vector Perform normalization processing to obtain the membership value and determine the current wear state level of the friction plate;

[0152] In this embodiment, the fuzzy comprehensive evaluation method can effectively handle the uncertainty and nonlinear problems existing in the operation of the friction plate, is applicable to various working conditions and material types, and has good generalization ability and engineering practicality.

[0153] The wear degree prediction value is obtained according to the wear degree range corresponding to the wear state level with the highest membership value.

[0154] In this embodiment, by collecting a large amount of actual wear data of the friction plate under different working conditions, the membership value of each characterization parameter under different wear states is calculated, and a fuzzy evaluation matrix R is constructed. The optimal characterization parameter weights obtained based on methods such as the entropy weight method are introduced into the fuzzy comprehensive evaluation process, so that the model can pay more attention to the key factors that have a greater impact on the wear state during the evaluation process. Through the normalization processing of the fuzzy evaluation result vector, the current wear state level of the friction plate can be clearly identified.

[0155] In this embodiment, according to the wear degree range corresponding to the wear state level with the highest membership degree, the wear degree prediction value of the friction plate is output, which can be used to estimate the remaining service life thereof.

[0156] The confidence analysis module is adopted for the wear degree prediction value of the friction plate, and confidence evaluation is performed on the prediction result of the wear degree prediction value, including:

[0157] The residual error between the wear degree prediction value and the true value is calculated by combining each sample in the historical data set, and the distribution characteristics of the residual error are counted;

[0158] In this embodiment, by statistically analyzing the residual error between the prediction value and the true value of each sample in the historical data set, the distribution characteristics of the residual error, such as mean and standard deviation, are obtained, so that the prediction error is no longer a “black box”, but a quantifiable uncertainty range, thereby enhancing the credibility and interpretability of the model output.

[0159] The confidence interval is calculated by adopting the properties of normal distribution for the distribution characteristics of the residual error, and the confidence level is set The upper and lower limits of the confidence interval are calculated, and the expression is:

[0160] ;

[0161] wherein, represents the lower limit of the confidence interval, represents the upper limit of the confidence interval, represents the wear degree prediction value, represents the critical value corresponding to the confidence level under the normal distribution, represents the standard deviation of the residual error.

[0162] In this embodiment, the upper and lower limits of the confidence interval calculated based on the normal distribution assumption can provide a clear error range for equipment maintenance personnel, assist them to make more reasonable maintenance or replacement decisions under different risk preferences, and avoid excessive maintenance or sudden failure caused by misjudgment.

[0163] In this embodiment, in actual operation, the friction plate may face various non-steady-state working conditions, and the prediction error will fluctuate with the change of the environment. After introducing the confidence analysis, the system can dynamically reflect the prediction stability, and improve the adaptability and robustness of the model under varying conditions.

[0164] In this embodiment, the introduction of the confidence interval not only can be used to numerically express the prediction accuracy, but also can be used as part of the visual display, presented in the form of error band in the monitoring interface, which helps the operation and maintenance personnel to intuitively judge the state of the friction plate, and set different warning levels accordingly.

[0165] In combination with the wear degree prediction value and its confidence interval, a fatigue life prediction interval containing an error range is generated, including:

[0166] The remaining service life of the wear degree prediction value under the current wear rate is calculated using the Archard wear model;

[0167] In this embodiment, the wear degree prediction value is converted into the remaining service life based on the Archard wear model, establishing a physical correlation between the wear rate and the fatigue life, improving the mechanism support of the life prediction model, and enhancing the interpretability of the prediction results.

[0168] The confidence interval of the wear degree prediction value is converted into the upper and lower limits of the fatigue life prediction interval according to the change trend of the wear over time;

[0169] In this embodiment, by converting the wear degree confidence interval into the fatigue life prediction interval, the system can identify which wear stage the current friction plate is in, such as initial wear, stable wear or accelerated failure, and accordingly divide different risk levels, providing a basis for operation and maintenance decisions.

[0170] The confidence is analyzed and monitored online using a state evaluation algorithm, and the state of the friction plate is tracked in real time;

[0171] The current wear degree prediction value and its confidence interval are displayed in real time, and when the friction plate enters a moderate wear or more severe state, the system automatically triggers an alarm.

[0172] In this embodiment, the current wear degree prediction value and its confidence interval are displayed in real time, enabling operation and maintenance personnel to intuitively grasp the change trend of the friction plate health state, assisting in quickly determining whether to replace or adjust the operating parameters, and improving the operability and intelligent level of the system.

[0173] In this embodiment, the confidence interval is introduced on the basis of traditional single-point life prediction, not only providing the prediction value itself, but also giving its possible error range, making the prediction results more valuable and engineering operable, and helping to develop a scientific and reasonable maintenance plan.

[0174] The present application introduces the average friction coefficient as a key state monitoring parameter, combines multi-dimensional feature normalization processing and deep neural network modeling, establishes a nonlinear mapping relationship between the fatigue life of the friction plate and its operating conditions, and significantly improves the prediction accuracy and model generalization ability.

[0175] Based on the Archard wear model, the wear process of the friction plate is dynamically simulated, a state evaluation model is constructed by using a fuzzy comprehensive evaluation method, scientific weighting of the optimal characteristic parameters is realized by combining an entropy weight method, the current wear stage of the friction plate is effectively identified, a quantitative wear degree prediction value is output, a confidence analysis module is introduced, a fatigue life prediction interval containing an error range is generated by statistically analyzing historical residuals and calculating a confidence interval, the credibility and interpretability of the prediction result are enhanced, and meanwhile, online confidence monitoring and real-time early warning functions are realized in combination with the state evaluation algorithm, when it is detected that the friction plate enters a moderate wear or a more serious state, the system automatically triggers an alarm, assists operation and maintenance personnel to take timely intervention measures, and sudden equipment failure is avoided.

[0176] The above examples are only exemplary embodiments of the present application and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Those skilled in the art can make various modifications or equivalent replacements to the present application within the spirit and protection scope of the present application, and such modifications or equivalent replacements are also regarded as falling within the protection scope of the present application.

Claims

1. A method for predicting the fatigue life of a friction plate considering the influence of multiple factors, characterized in that: The following steps are involved: Obtaining performance parameters of the friction plate under actual working conditions that are affected by multiple factors, and introducing an average friction coefficient into the performance parameters as a key parameter for state monitoring of the friction plate; Normalizing the key parameters to construct a multidimensional feature input vector, training the deep neural network based on a deep neural network model and combining historical fatigue test data to establish a nonlinear mapping relationship between the fatigue life of the friction plate and various influencing factors; The performance of the friction plate is monitored in real time according to the nonlinear mapping relationship, and the current operating parameters of the friction plate to be predicted are input into the trained deep neural network model to obtain the corresponding fatigue life prediction value; Simulating the wear of the friction plate according to the fatigue life prediction value, establishing a corresponding relationship between the optimal characterization parameters of the friction plate and the state evaluation, analyzing the change trend of the optimal characterization parameters using a fuzzy comprehensive evaluation method, establishing a fuzzy evaluation model for state evaluation, and obtaining a predicted value of the wear degree of the friction plate; A confidence analysis module is used for the predicted value of the degree of wear of the friction plate, and a confidence assessment is performed on the prediction result of the predicted value of the degree of wear of the friction plate to generate a fatigue life prediction interval including an error range.

2. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 1, characterized in that: Obtaining performance parameters of the friction plate under actual working conditions that are affected by multiple factors, and introducing the average friction coefficient into the performance parameters as a key parameter for state monitoring of the friction plate, including: Obtaining performance parameters of the friction plate under actual working conditions influenced by multiple factors, wherein the influencing factors include at least: friction material properties, operating temperature, contact pressure, sliding speed, lubrication state, load cycle frequency, and friction force variation curve during the friction process; During the operation of the friction plate, instantaneous friction force and normal pressure data at multiple time points are collected in real time to calculate the average friction coefficient of the friction, which is expressed as: ； in, represents the friction force at the i-th sampling point, represents the positive pressure at the i-th sampling point, Indicates the total number of sampling points; The average friction coefficient is used as a characteristic parameter reflecting the wear state and friction stability of the friction plate surface, and as a key parameter for state monitoring of the friction plate.

3. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 2, characterized in that: The key parameters are normalized to construct a multidimensional feature input vector. Based on a deep neural network model, the deep neural network is trained in combination with historical fatigue test data to establish a nonlinear mapping relationship between the fatigue life of the friction plate and various influencing factors, including: The key parameters are normalized to the minimum and maximum values, and the normalized key parameters are sorted according to the degree of wear of the friction plate. The degree of wear of the friction plate is determined by the friction coefficient on the corresponding friction plate. The expression is: ； in, represents the number of friction pairs of the friction plate, q represents the pressure ratio between the friction plates, 、 Indicates the inner and outer diameters of the friction plate, Indicates the friction torque of the friction plate; Normalize the key parameters after sorting to generate a feature input vector of uniform dimension , where n represents the number of feature dimensions; A fully connected feedforward neural network model is constructed, and the attention mechanism is integrated to train historical fatigue test data. The operating parameters under different working conditions are recorded, and the parameters of the fully connected feedforward neural network model are optimized based on the fatigue failure time and cycle number corresponding to the friction plate. The influencing factors of the allowable process of the friction plate under different industrial and mining conditions are input into the fully connected feedforward neural network model to establish a highly nonlinear, multivariable coupling relationship between the fatigue life of the friction plate and its influencing factors, and obtain the interaction effect between multiple factors.

4. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 3, characterized in that: The performance of the friction plate is monitored in real time according to the nonlinear mapping relationship, and the current friction plate operating parameters to be predicted are input into the trained deep neural network model to obtain the corresponding fatigue life prediction value, including: The friction plate operating parameters under the current working conditions are collected in real time by sensors, and the operating parameters are input into the fully connected feedforward neural network model according to the nonlinear mapping relationship to obtain a multi-factor multi-dimensional feature input vector ,in represents the average friction coefficient, Indicates the operating temperature, Indicates the contact pressure, Indicates the sliding speed of the friction plate during actual operation. Indicates the thickness of the lubricating oil film on the friction plate surface. Indicates the friction plate load cycle frequency, represents the material density, Represents the thermal conductivity of the material; The multidimensional features are input into the vector The ReLU activation function is used to enhance the nonlinear expression capability when inputting the deep neural network model. After forward propagation calculation, the deep neural network model outputs the corresponding predicted value, which represents the estimated remaining fatigue life of the friction plate under current conditions.

5. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 3, characterized in that: The wear amount of the friction plate is simulated according to the fatigue life prediction value, including: The Archard wear model is used to simulate the wear process of the friction plate under different working conditions, and its expression is: ； in, represents the average friction coefficient, W represents the normal load of the friction plate, d represents the relevant sliding friction distance, and V represents the wear volume; According to the multi-dimensional feature input vector under the current working condition Calculate the wear amount of the friction plate in each cycle based on the fatigue life prediction value; The wear of the friction plate throughout its life cycle is dynamically simulated using the ANSYS simulation tool to generate a wear curve graph and obtain the wear variation trend over time or the number of cycles.

6. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 5, characterized in that: According to the wear amount of the friction plate, a corresponding relationship between the optimal characterization parameter of the friction plate and the state evaluation is established, including: According to the wear trend of the friction plate over time, n data points are randomly extracted. 、 , , establish a linear regression equation for the n data points to obtain the wear amount of the friction plate during the stable wear period and wear life The offline relationship between them is expressed as: ； in, represents the initial wear amount, Indicates the growth rate of wear; The degree of fit between the regression model and the actual data is determined by calculating the standard error of the n data points, and the warning baseline and abnormal baseline of the wear element changing over time are obtained according to the linear regression equation and the standard error; The wear amount is analyzed using random forest algorithm Conduct analysis and establish a mapping relationship between characterization parameters and wear status; Based on the characterization parameter values ​​obtained from real-time monitoring, sensitivity analysis is performed on each characterization parameter to identify the key parameters that have the greatest impact on the wear state. Based on the weighted fusion strategy, weights are assigned to different characterization parameters, and a comprehensive scoring system is constructed to quantify the overall wear state of the friction plate. Its expression is: ； in, Represent the weights of the corresponding characterization parameters, Indicates the comprehensive rating.

7. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 6, characterized in that: The fuzzy comprehensive evaluation method is used to analyze the weights affecting the optimal characterization parameters, including: Create a factor set containing each indicator for the comprehensive score , Represents the mth element that affects the evaluation object, and establishes an evaluation set for the comprehensive score , the evaluation set The middle element represents the evaluation result of its corresponding influencing factor; The positive evaluation index is used to calculate the weight of the corresponding sample under the i-th factor index, and the entropy value of the j-th index is obtained. The expression is: ； Where n represents the number of samples, Representation factor set The number of elements in It represents the weight of the jth indicator under the i-th factor indicator; The difference of each indicator is calculated according to the entropy value, the weights of multiple indicators in the comprehensive evaluation system are calculated, and the weights affecting the optimal characterization parameters are obtained. The expression is: 。 8. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 7, characterized in that: A fuzzy judgment model for state evaluation is established for the weights of the optimal characterization parameters to obtain a predicted value of the degree of friction plate wear, including: For each characterization parameter, its fuzzy membership function under different wear states is defined, and a fuzzy evaluation matrix R is constructed, where each row represents a characterization parameter, each column represents a wear state level, and the matrix elements are It represents the membership value of the i-th characterization parameter under the j-th wear state level, and its expression is: ； Where m is the number of characterization parameters and n is the number of wear state levels; The fuzzy comprehensive evaluation formula is calculated according to the weight of the optimal characterization parameter to obtain a comprehensive evaluation result vector B, which is expressed as follows: ； in, , represents the comprehensive membership value of the friction plate at each wear state level; Comprehensive evaluation result vector Perform normalization processing to obtain the membership value and determine the current wear state level of the friction plate; The wear degree prediction value is obtained according to the wear degree range corresponding to the wear state level with the highest membership value.

9. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 8, characterized in that: A confidence analysis module is used for the predicted value of the friction plate wear degree to perform a confidence assessment on the predicted result of the predicted value of the friction plate wear degree, including: The wear degree prediction value is combined with each sample in the historical data set, the residual between the wear degree prediction value and the true value is calculated, and the distribution characteristics of the residual are statistically analyzed; The distribution characteristics of the residuals are calculated using the properties of the normal distribution to calculate the confidence interval and set the confidence level , calculate the upper and lower limits of the confidence interval, the expression is: ； in, represents the lower limit of the confidence interval, represents the upper limit of the confidence interval, represents the predicted value of wear degree, Indicates the corresponding confidence level under normal distribution The critical value of Represents the standard deviation of the residuals.

10. The method for predicting fatigue life of a friction plate considering multiple factors according to claim 9, characterized in that: Combine the wear degree prediction value and its confidence interval to generate a fatigue life prediction interval with an error range, including: Calculating the remaining useful life of the wear degree prediction value at the current wear rate using the Archard wear model; Converting the confidence interval of the wear degree prediction value into the upper and lower limits of the fatigue life prediction interval according to the wear change trend over time; Using a state assessment algorithm to perform online analysis and monitoring of the confidence level, and to track the state of the friction plate in real time; The current wear level prediction value and its confidence interval are displayed in real time. When it is detected that the friction plate enters a state of moderate wear or more serious wear, the system automatically triggers an alarm.

Images