Mechanical equipment lubrication reliability analysis method and device

Abstract

The application provides a mechanical equipment lubrication reliability analysis method and device, the method comprises the following steps: determining the properties of each monitoring index of mechanical equipment lubrication; monitoring the index data corresponding to each lubrication monitoring index property during the operation of the mechanical equipment; calculating the edge distribution joint weight factor of each lubrication monitoring index property according to the index data; constructing the oil physical and chemical performance reliability Copula function, the oil pollution reliability Copula function and the mechanical equipment wear reliability Copula function according to the index data; constructing a comprehensive multivariate Copula reliability analysis model according to the edge distribution joint weight factor and the above-mentioned multiple Copula functions; and determining the system comprehensive relative reliability of the mechanical equipment lubrication according to the model. It can be seen that the method can analyze the mechanical equipment lubrication reliability without dimension reduction, avoid information loss, improve the accuracy of the mechanical equipment lubrication monitoring result, and then realize lubrication fault diagnosis and reliability analysis.

Description

Technical Field

[0001] This application relates to the field of mechanical equipment technology, and more specifically, to a method and apparatus for analyzing the reliability of lubrication in mechanical equipment. Background Technology

[0002] In recent years, with the widespread application of real-time data acquisition systems and data processing technologies in industry, data-driven process monitoring technologies have also developed rapidly. As a key component of mechanical equipment, lubricating oils function much like blood in the human body, ensuring the reliability and stability of the equipment's operation and serving as a carrier of information about its operational status. During the operation of mechanical equipment, malfunctions can lead to minor equipment failures or even accidents. As a lubricating medium, lubricating oils contain a wealth of equipment status information. For example, in a diesel engine system, the content of wear elements Fe and Cu indicates the degree of wear on the crankshaft or copper bushing bearings; the base number indicates the content of detergent-dispersant; the flash point indicates whether fuel has entered the oil; and soot indicates the content of combustion products. Current methods typically monitor various parameters of the lubricating oil, then use multivariate projection techniques to project the high-dimensional parameters into a low-dimensional feature space for dimensionality reduction, and finally extract data features to build a model describing the system state. However, in practice, it has been found that existing data dimensionality reduction methods can lead to information loss, thereby reducing the accuracy of mechanical equipment reliability analysis results and making it impossible to accurately detect equipment failures. Summary of the Invention

[0003] The purpose of this application is to provide a method and apparatus for analyzing the lubrication reliability of mechanical equipment, which can perform lubrication reliability analysis of mechanical equipment without reducing dimensionality, avoid information loss, thereby improving the accuracy of lubrication monitoring results of mechanical equipment, accurately realizing lubrication fault diagnosis and reliability analysis, and ensuring personal and property safety.

[0004] The first aspect of this application provides a method for analyzing the reliability of lubrication in mechanical equipment, including: Determine the attributes of each monitoring indicator for the lubrication of mechanical equipment; During the operation of the mechanical equipment, the indicator data corresponding to each monitoring indicator attribute are monitored; Calculate the joint weighting factor of the marginal distribution of each monitoring indicator attribute based on the indicator data; Based on the aforementioned index data, construct Copula functions for oil physical and chemical performance reliability, oil contamination reliability, and mechanical equipment wear reliability. A comprehensive multivariate Copula reliability analysis model is constructed based on the joint weighting factor of the edge distribution, the Copula function for the reliability of the physical and chemical properties of oil, the Copula function for the reliability of oil contamination, and the Copula function for the reliability of mechanical equipment wear. The overall relative reliability of the mechanical equipment lubrication system is determined based on the comprehensive multivariate Copula reliability analysis model.

[0005] In the above implementation process, this method can first determine the various monitoring index attributes of mechanical equipment; and during the operation of the mechanical equipment, monitor the index monitoring data corresponding to each monitoring index attribute; then, calculate the joint weighting factor of the marginal distribution of each monitoring index attribute based on the index monitoring data; and construct the Copula function for physicochemical performance reliability, pollution reliability, and wear reliability based on the index monitoring data; subsequently, construct a comprehensive multivariate Copula reliability analysis model based on the joint weighting factor of the marginal distribution, the Copula function for physicochemical performance reliability, the Copula function for pollution reliability, and the Copula function for wear reliability; finally, determine the comprehensive relative reliability of the mechanical equipment system based on the comprehensive multivariate Copula reliability analysis model. It is evident that this method can perform lubrication reliability analysis of mechanical equipment without dimensionality reduction, avoiding information loss, thereby improving the accuracy of lubrication monitoring results, accurately realizing lubrication fault diagnosis and reliability analysis, and ensuring personal and property safety.

[0006] Further, the step of calculating the joint weighting factor of the marginal distribution of each monitoring indicator attribute based on the indicator data includes: Establish marginal distribution equations for the attributes of each monitoring indicator based on the indicator data; The joint weighting factor of the marginal distribution of each monitoring indicator attribute is calculated using the entropy method based on the marginal distribution equation.

[0007] Furthermore, the construction of the oil physicochemical property reliability Copula function, the oil contamination reliability Copula function, and the mechanical equipment wear reliability Copula function based on the index data includes: The monitoring indicators are categorized into oil physicochemical properties, oil contamination, and mechanical equipment wear. Calculate the correlation coefficient matrix of the physical and chemical properties of the oil, the correlation coefficient matrix of the oil pollution index, and the correlation coefficient matrix of the mechanical equipment wear index based on the index data. The T1 tree structure of the oil physicochemical performance index is calculated based on the correlation coefficient matrix of the oil physicochemical performance index, the T1 tree structure of the oil pollution index is calculated based on the correlation coefficient matrix of the oil pollution index, and the T1 tree structure of the mechanical equipment wear index is calculated based on the correlation coefficient matrix of the mechanical equipment wear index. A Copula function for the reliability of the physical and chemical properties of oil products is established based on the T1 tree structure of the oil product's physical and chemical properties index, a Copula function for the reliability of oil product contamination is established based on the T1 tree structure of the oil product's contamination index, and a Copula function for the reliability of mechanical equipment wear is established based on the T1 tree structure of the mechanical equipment wear index.

[0008] Furthermore, the physicochemical properties of the oil include viscosity, acid value, base value, Ca content, Zn content, and P content. The oil contamination indicators include moisture content, soot content, oxidation value, nitration value, Si content, and n-pentane content. The wear indicators of the mechanical equipment include Fe content, Cu content, Ni content, Sn content, and Cr content.

[0009] Furthermore, the step of establishing a Copula function for the reliability of the physicochemical properties of the oil based on the T1 tree structure of the oil's physicochemical properties includes: The D-vine characteristics were determined based on the T1 tree structure of the oil's physicochemical properties. Generate D-Vine Copula functions based on D-vine features; The D-Vine Copula function is iterated through to obtain the traversal data; Based on the traversal data, the optimal binary function between adjacent nodes is determined using the AIC criterion; Construct a Copula function for the reliability of the physicochemical properties of oil products based on the optimal binary function.

[0010] A second aspect of this application provides a mechanical equipment lubrication reliability analysis device, the mechanical equipment lubrication reliability analysis device comprising: The determination unit is used to determine the attributes of various monitoring indicators for the lubrication of mechanical equipment; The monitoring unit is used to monitor the indicator data corresponding to each monitoring indicator attribute during the operation of the mechanical equipment. The calculation unit is used to calculate the joint weighting factor of the marginal distribution of each monitoring indicator attribute based on the indicator data; The first construction unit is used to construct the Copula function for the reliability of the physical and chemical properties of oil, the Copula function for the reliability of oil contamination, and the Copula function for the reliability of mechanical equipment wear based on the index data. The second construction unit is used to construct a comprehensive multivariate Copula reliability analysis model based on the edge distribution joint weighting factor, the oil physicochemical property reliability Copula function, the oil contamination reliability Copula function, and the mechanical equipment wear reliability Copula function. The determination unit is used to determine the overall relative reliability of the lubrication system of the mechanical equipment based on the comprehensive multivariate Copula reliability analysis model.

[0011] In the above implementation process, the device can determine the various monitoring index attributes of the mechanical equipment through a determination unit; monitor the index monitoring data corresponding to each monitoring index attribute during the operation of the mechanical equipment through a monitoring unit; calculate the marginal distribution joint weight factor of each monitoring index attribute based on the index monitoring data through a calculation unit; construct physicochemical performance reliability Copula functions, pollution reliability Copula functions, and wear reliability Copula functions based on the index monitoring data through a first construction unit; construct a comprehensive multivariate Copula reliability analysis model based on the marginal distribution joint weight factor, the physicochemical performance reliability Copula function, the pollution reliability Copula function, and the wear reliability Copula function through a second construction unit; and finally, determine the overall relative reliability of the mechanical equipment system based on the comprehensive multivariate Copula reliability analysis model through a determination unit. It is evident that this device can perform lubrication reliability analysis of mechanical equipment without dimensionality reduction, avoiding information loss, thereby improving the accuracy of lubrication monitoring results, accurately realizing lubrication fault diagnosis and reliability analysis, and ensuring personal and property safety.

[0012] Furthermore, the monitoring unit includes: The first sub-unit is used to establish the marginal distribution equation of each monitoring indicator attribute based on the indicator data. The first calculation subunit is used to calculate the joint weight factor of the marginal distribution of each monitoring indicator attribute using the entropy method according to the marginal distribution equation.

[0013] Furthermore, the first building unit includes: Sub-units are used to divide the monitoring index attributes into oil physicochemical performance indicators, oil pollution indicators, and mechanical equipment wear indicators. The second calculation subunit is used to calculate the correlation coefficient matrix of the physical and chemical properties of the oil, the correlation coefficient matrix of the oil pollution index, and the correlation coefficient matrix of the mechanical equipment wear index based on the index data; and to calculate the T1 tree structure of the physical and chemical properties of the oil, the T1 tree structure of the oil pollution index, and the T1 tree structure of the mechanical equipment wear index based on the correlation coefficient matrix of the physical and chemical properties of the oil; The second sub-unit is used to establish a Copula function for the reliability of the physical and chemical properties of the oil based on the T1 tree structure of the oil's physical and chemical properties index, a Copula function for the reliability of the oil's contamination based on the T1 tree structure of the oil's contamination index, and a Copula function for the reliability of the mechanical equipment's wear based on the T1 tree structure of the mechanical equipment's wear index.

[0014] Furthermore, the physicochemical properties of the oil include viscosity, acid value, base value, Ca content, Zn content, and P content. The oil contamination indicators include moisture content, soot content, oxidation value, nitration value, Si content, and n-pentane content. The wear indicators of the mechanical equipment include Fe content, Cu content, Ni content, Sn content, and Cr content.

[0015] Furthermore, the second establishment subunit includes: The determination module is used to determine the D-vine characteristics based on the T1 tree structure of the physicochemical properties of the oil. The generation module is used to generate D-Vine Copula functions based on D-vine features; The traversal module is used to traverse the D-Vine Copula function to obtain the traversal data; The determining module is also used to determine the optimal binary function between adjacent nodes based on the traversal data using the AIC criterion; A construction module is used to construct a Copula function for the reliability of the physicochemical properties of oil products based on the optimal binary function.

[0016] A third aspect of this application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to cause the electronic device to perform the mechanical equipment lubrication reliability analysis method as described in any one of the first aspects of this application.

[0017] The fourth aspect of this application provides a computer-readable storage medium storing computer program instructions, which, when read and executed by a processor, perform the mechanical equipment lubrication reliability analysis method described in any one of the first aspects of this application. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for analyzing the lubrication reliability of mechanical equipment, provided in an embodiment of this application; Figure 2 A schematic diagram of the structure of a mechanical equipment lubrication reliability analysis device provided in this application embodiment; Figure 3 A schematic diagram of a D-Vine Copula provided for an embodiment of this application; Figure 4 A schematic diagram of a D-Vine Copula T1 structure provided in an embodiment of this application; Figure 5 This is a schematic diagram of a D-vine Copula result provided in an embodiment of this application. Detailed Implementation

[0020] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0021] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] Example 1 Please refer to Figure 1 , Figure 1 This embodiment provides a flowchart illustrating a method for analyzing the lubrication reliability of mechanical equipment. The method includes: S101. Determine the attributes of each monitoring indicator for the lubrication of mechanical equipment.

[0023] S102. During the operation of mechanical equipment, monitor the index data corresponding to each lubrication monitoring index attribute.

[0024] S103. Establish the marginal distribution equations for each monitoring indicator attribute based on the indicator data.

[0025] S104. Calculate the joint weight factor of the marginal distribution of each monitoring indicator attribute using the entropy method based on the marginal distribution equation.

[0026] S105. The attributes of each monitoring indicator are divided into oil physical and chemical properties indicators, oil pollution indicators and mechanical equipment wear indicators.

[0027] In this embodiment, the physicochemical properties of the oil include viscosity, acid value, base value, Ca content, Zn content, and P content.

[0028] In this embodiment, the oil contamination indicators include moisture content, soot content, oxidation value, nitration value, Si content, and n-pentane content.

[0029] In this embodiment, the wear indicators of mechanical equipment include Fe content, Cu content, Ni content, Sn content, and Cr content.

[0030] S106. Calculate the correlation coefficient matrix of the physical and chemical properties of oil, the correlation coefficient matrix of oil pollution indicators, and the correlation coefficient matrix of mechanical equipment wear indicators based on the indicator data.

[0031] S107. Calculate the T1 tree structure of the physicochemical properties of oil products based on the correlation coefficient matrix of the physicochemical properties of oil products, calculate the T1 tree structure of the contamination index of oil products based on the correlation coefficient matrix of the contamination index of oil products, and calculate the T1 tree structure of the wear index of mechanical equipment based on the correlation coefficient matrix of the wear index of mechanical equipment.

[0032] S108. Determine the D-vine characteristics based on the T1 tree structure of the physicochemical properties of the oil.

[0033] S109. Generate the D-Vine Copula function based on the D-vine characteristics.

[0034] S110, Traverse the D-Vine Copula function to obtain the traversal data.

[0035] S111. Determine the optimal binary function between adjacent nodes based on the traversal data using the AIC criterion.

[0036] S112. Construct the Copula function for the reliability of the physicochemical properties of oil based on the optimal bivariate function.

[0037] S113. Establish the oil pollution reliability Copula function based on the T1 tree structure of oil pollution indicators, and establish the mechanical equipment wear reliability Copula function based on the T1 tree structure of mechanical equipment wear indicators.

[0038] S114. Based on the joint weighting factor of the edge distribution, the Copula function for the reliability of the physical and chemical properties of oil, the Copula function for the reliability of oil contamination, and the Copula function for the reliability of mechanical equipment wear, a comprehensive multivariate Copula reliability analysis model is constructed.

[0039] S115. Determine the overall relative reliability of the mechanical equipment lubrication system based on the comprehensive multivariate Copula reliability analysis model.

[0040] In this embodiment, the method utilizes lubricating oil data from mechanical equipment and establishes a lubrication reliability model based on Copula functions. Specifically, the method first constructs the marginal distributions of each variable based on its data distribution characteristics; then, it verifies and determines suitable Copula functions and their parameters, using them as tools to describe the correlations between the variables. The forms of Copula functions mainly include the normal-Copula function, the t-Copula function, and the Archimedes Copula function. Common binary Copula functions are shown in the table below, where u and v represent the marginal distribution functions, respectively.

[0041]

[0042] In this embodiment, the Copula function introduces a graphical tool called "vine" on the basis of the Copula function, which transforms high-dimensional data problems into problems that combine multiple two-dimensional data for solution, making the solution of high-dimensional data more intuitive.

[0043] In this embodiment, the R-Vine Coula is a special form of vine, containing both two-dimensional and conditional binary distributions. Formally, it utilizes the transformation formula between conditional and joint distributions to calculate the joint distribution. Since the R-Vine Coula can extend the binary Coula to Coula models of arbitrary dimensions, its structure is rich and diverse by controlling nodes and branch degrees. However, as the dimension increases, the number of vine structures also increases exponentially. To avoid problems arising from determining the optimal structure and computational burden, the board method can employ C-vine and D-vine Coulas, thereby simplifying the diversity of its structures.

[0044] Please refer to Figure 3 , Figure 3 A schematic diagram of a D-Vine Copula is shown.

[0045] In this embodiment, the D-vine model has a clear parallel structure and exhibits good accuracy when the correlation between each pair of multiple variables is close. Its logic diagram is as follows: Figure 1 As shown, when using the D-vine structure to analyze the correlation of multidimensional related variables, its probability expression is as follows.

[0046]

[0047] Due to the structural characteristics of D-Vine, once Once the tree is determined, then This also significantly reduces the computational load of the model. Therefore, to determine the T1 order, this invention uses a genetic algorithm for optimization and utilizes the correlation coefficient matrix to calculate the dimensional order of the maximum sum of correlation coefficients.

[0048] The first step in establishing a Copula model is to determine each marginal distribution. Since lubrication monitoring data is a continuous variable, in the statistical analysis process, functions such as normal, Weibull, and Gamma are usually used to make assumptions about the sample population, while the parameter estimation method is used to calculate the model parameters. Given that the maximum likelihood method has the property of unbiased estimation and its convergence performance is better as the number of samples increases

[10] , this paper uses the maximum likelihood method to calculate the parameters of the function. Taking the three-parameter Weibull as an example, the parameters of the Weibull function of the marginal distribution are calculated. The probability density function of the three-parameter Weibull function is: (1) in, These represent shape parameters, scale parameters, and position parameters, respectively; through The Weibull distribution can approximate various data distributions and has good generalization ability, given the numerical variation of the likelihood function. The likelihood function is given by equation (2), where... For the parameters to be estimated, This indicates the value that a random variable can take.

[0049] (2) The purpose of the maximum likelihood method is to solve for the parameters. : (3) Therefore, combining equation (3), the maximum likelihood function of the probability density function of the three-parameter Weibull distribution is: (4) Taking the logarithm of the above expression, we get: (5) Since the maximum likelihood estimation of parameters results in the maximum value of the likelihood function, when the likelihood function is given by three parameters... When the expression is continuously differentiable and its maximum value lies within the domain, i.e., when the partial derivatives of the three parameters in the above equation are taken separately, solving the system of simultaneous equations yields the result of the maximum likelihood estimator: (6) (7) (8) The parameter values ​​are obtained by solving the likelihood equations by combining equations (6), (7) and (8), thus obtaining the marginal distribution equation.

[0050] For the PairCopula in D-VineCopula, this paper adopts the approach of traversing all families of Copula functions. For its parameters, the maximum likelihood method is still used to calculate the correlation coefficient and its parameters. Taking the GumbelCopula function as an example, the process of finding its parameter derivative is shown below. The GumbelCopula formula is as follows: (9) in , Representing the marginal distribution, solve for the parameters. The maximum likelihood equation: (10) Taking the logarithm of equation (12), we get the generative equation (13): (11) The parameter is obtained when equation (13) takes its maximum value. Right now: (12) The optimal binary Copula function is determined by the AIC information criterion, thereby ensuring that the selected Copula can adequately describe the characteristics of the original data.

[0051] (13) In the formula For binary Copula parameters, This represents the number of Copula parameters. This is calculated... The Copula with the smallest binary parameter is selected as the final optimal candidate Copula.

[0052] As mentioned above, the first step in establishing a multivariate Copula function is to address the marginal distribution of each monitoring indicator attribute. Based on the linear fitting results of the probability plots of each distribution, it can be seen that each sample point is strictly within the 95% confidence interval, which indicates that each marginal distribution function can fit the distribution characteristics of the current sample.

[0053] Because there is no clear correlation between some state indicators, the oil product Copula function is decomposed into: C = (C1 + C2 + C3) / 3, where C1: C represents the reliability of physical and chemical properties, C2: C represents the reliability of contamination, and C3: C represents the reliability of wear. The reliability functions of the three states of the oil are coupled to obtain the overall reliability function of the oil. C1 is the Copula function for the reliability of physical and chemical properties of the oil, and its characteristic set includes viscosity, acid value, base value, Ca, Zn, and P content; C2 is the Copula function for the reliability of contamination of the oil, and its characteristic set includes moisture, soot, oxidation value, nitration value, Si content, and n-pentane; C3 is the Copula function for the reliability of mechanical equipment wear, and its characteristic set includes Fe, Cu, Ni, Sn, and Cr content.

[0054] Given the varying characterization abilities or dispersion of different factors in the reliability of petroleum products, the joint weighting factors of the marginal distributions of each attribute are calculated before calculating the joint copula function. This scheme uses the entropy method to calculate the degree of influence of each index on the joint function.

[0055] In information theory, entropy is a measure of uncertainty. The greater the amount of information, the lower the uncertainty and the lower the entropy; conversely, the smaller the amount of information, the greater the uncertainty and the greater the entropy. Based on the properties of entropy, we can calculate the entropy value to determine the randomness and disorder of an event, and we can also use the entropy value to determine the dispersion of a certain indicator. The greater the dispersion of an indicator, the greater its impact on the overall evaluation. The entropy weight of the i-th indicator... The calculated weights are then incorporated into the calculation process of the pairCopula function.

[0056] (14) in Information entropy is represented by the set of attribute weights calculated using the entropy method. The following table shows the weights of each indicator calculated using the entropy weight method:

[0057] The correlation coefficient, calculated using the Pearson phase, is also known as the Pearson product-moment correlation coefficient or simple correlation coefficient. It describes the strength of the relationship between two interval variables and measures the correlation (linear correlation) between them. Its value ranges between -1 and 1. It is generally used... The calculation formula is as follows: (15) The correlation coefficients show that different attributes of the sample are correlated and not completely independent. Therefore, by observing the correlation coefficient matrix in Table 3 (taking physicochemical analysis as an example), the correlation characteristics are suitable for Copula modeling. The correlation coefficient matrices for each monitoring indicator are shown below:

[0058] After calculating the correlation coefficient matrices, the T1 structure was optimized using a genetic algorithm. The initial crossover probability Pc = 0.7, mutation probability Pm = 0.3, population size popsize = 50, and the maximum number of iterations was 5000. Initial individuals were generated randomly, and the stopping condition was reaching the maximum number of generations or the optimal fitness value within the iteration limit. Taking the physicochemical properties of oil as an example, the resulting order, i.e., the structural order of the T1 structure, is as follows: Figure 4 As shown.

[0059] After determining the T1 structure, based on the D-vine characteristics, This also led to the determination of the D-VineCopula. Then, by traversing the Copula function and using the AIC criterion, the optimal binary function between adjacent nodes was determined. The structure of the Copula function is shown below. Figure 5 .

[0060] Observing the model's fitting results, it can be seen that most of the first-level trees are StudentCopulas, while most of the pairCopulas in the lower-level trees are dependent on each other. This demonstrates that under the D-VineCopula structure, the correlation between dimensions gradually disappears as the tree structure extends, and the correlation between coupled derived nodes decreases while their independence increases. By incorporating the weights into the calculation process of the binary Copula function, a multivariate VineCopula model is ultimately formed.

[0061] Finally, the relationship between the joint Copula and the system's relative reliability is calculated, thus yielding the relative reliability curves for the Copula functions of contamination, physicochemical properties, and the model. Specifically, the Copula functions for contamination status, wear index, and physicochemical properties are used to derive the overall system reliability function. C= （C 1 +C 2 +C 3 ） / 3, C=( C i ( w i u i)+ C j ( w j v j )+ C m ( w m x m )) / 3; in, u i ，v j ，x m These represent physical and chemical, pollution, and wear indicators, respectively. w i ，w j ，w m The corresponding weights are used to ultimately derive the Copula relative reliability analysis results for the combined lubrication of mechanical equipment.

[0062] In this embodiment, the subject executing the method can be a computing device such as a computer or server, and no limitation is made in this embodiment.

[0063] In this embodiment, the subject executing the method can also be a smart device such as a smartphone or tablet computer, and no limitation is made in this embodiment.

[0064] As can be seen, implementing the mechanical equipment lubrication reliability analysis method described in this embodiment can perform mechanical equipment lubrication reliability analysis without dimensionality reduction, avoid information loss, thereby improving the accuracy of mechanical equipment test results, and thus accurately detecting equipment failures and ensuring personal and property safety.

[0065] Example 2 Please refer to Figure 2 , Figure 2 This is a schematic diagram of a mechanical equipment lubrication reliability analysis device provided in this embodiment. Figure 2 As shown, the lubrication reliability analysis device for mechanical equipment includes: Unit 210 is used to determine the attributes of various monitoring indicators for the lubrication of mechanical equipment; The monitoring unit 220 is used to monitor the indicator data corresponding to each monitoring indicator attribute during the operation of the mechanical equipment; Calculation unit 230 is used to calculate the joint weight factor of the marginal distribution of each monitoring indicator attribute based on the indicator data; The first construction unit 240 is used to construct the Copula function for the reliability of the physical and chemical properties of oil, the Copula function for the reliability of oil contamination, and the Copula function for the reliability of mechanical equipment wear based on the index data. The second building unit 250 is used to construct a comprehensive multivariate Copula reliability analysis model based on the edge distribution joint weighting factor, the Copula function for the reliability of the physical and chemical properties of oil, the Copula function for the reliability of oil contamination, and the Copula function for the reliability of mechanical equipment wear. Unit 260 is used to determine the overall relative reliability of the mechanical equipment lubrication system based on the comprehensive multivariate Copula reliability analysis model.

[0066] As an optional implementation, the monitoring unit 220 includes: The first sub-unit 221 is used to establish the marginal distribution equation of each monitoring indicator attribute based on the indicator data; The first calculation subunit 222 is used to calculate the joint weight factor of the marginal distribution of each monitoring indicator attribute using the entropy method based on the marginal distribution equation.

[0067] As an optional implementation, the first building unit 240 includes: Sub-unit 241 is used to divide the attributes of each monitoring indicator into oil physical and chemical performance indicators, oil pollution indicators and mechanical equipment wear indicators. The second calculation subunit 242 is used to calculate the correlation coefficient matrix of the physical and chemical properties of oil products, the correlation coefficient matrix of oil pollution indicators, and the correlation coefficient matrix of mechanical equipment wear indicators based on the index data; and to calculate the T1 tree structure of the physical and chemical properties of oil products based on the correlation coefficient matrix of the physical and chemical properties of oil products, the T1 tree structure of the oil pollution indicators based on the correlation coefficient matrix of the oil pollution indicators, and the T1 tree structure of the mechanical equipment wear indicators based on the correlation coefficient matrix of the mechanical equipment wear indicators. The second subunit 243 is used to establish a Copula function for the reliability of the physical and chemical properties of oil products based on the T1 tree structure of the oil product's physical and chemical properties index, a Copula function for the reliability of oil product contamination based on the T1 tree structure of the oil product's contamination index, and a Copula function for the reliability of mechanical equipment wear based on the T1 tree structure of the mechanical equipment wear index.

[0068] In this embodiment, the physicochemical properties of the oil include viscosity, acid value, base value, Ca content, Zn content, and P content. Oil pollution indicators include moisture content, soot content, oxidation value, nitration value, Si content, and n-pentane content. Wear indicators for mechanical equipment include Fe content, Cu content, Ni content, Sn content, and Cr content.

[0069] As an optional implementation, the second building subunit 243 includes: The determination module is used to determine the D-vine characteristics based on the T1 tree structure of the physicochemical properties of oil products; The generation module is used to generate D-Vine Copula functions based on D-vine features; The traversal module is used to traverse the D-Vine Copula function and obtain the traversal data. The determination module is also used to determine the optimal binary function between adjacent nodes based on the traversal data using the AIC criterion; The module is used to construct a Copula function for the reliability of the physicochemical properties of oil products based on the optimal binary function.

[0070] In this embodiment, the explanation of the mechanical equipment lubrication reliability analysis device can be referred to the description in Embodiment 1, and will not be repeated here.

[0071] As can be seen, implementing the mechanical equipment lubrication reliability analysis device described in this embodiment can perform mechanical equipment lubrication reliability analysis without dimensionality reduction, avoid information loss, thereby improving the accuracy of mechanical equipment detection results, and thus accurately detecting equipment failures and ensuring personal and property safety.

[0072] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the mechanical equipment lubrication reliability analysis method in embodiment 1 of this application.

[0073] This application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the mechanical equipment lubrication reliability analysis method in embodiment 1 of this application is performed.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0075] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0076] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0077] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0078] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0079] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for analyzing the reliability of lubrication in mechanical equipment, characterized in that, include: Determine the attributes of each monitoring indicator for the lubrication of mechanical equipment; During the operation of the mechanical equipment, the indicator data corresponding to each monitoring indicator attribute are monitored; Based on the indicator data, establish the marginal distribution equations for the attributes of each monitoring indicator; The joint weighting factor of the marginal distribution of each monitoring indicator attribute is calculated using the entropy method based on the marginal distribution equation. The monitoring indicators are categorized into oil physicochemical properties, oil contamination, and mechanical equipment wear. Calculate the correlation coefficient matrix of the physical and chemical properties of the oil, the correlation coefficient matrix of the oil pollution index, and the correlation coefficient matrix of the mechanical equipment wear index based on the index data. The T1 tree structure of the oil physicochemical performance index is calculated based on the correlation coefficient matrix of the oil physicochemical performance index, the T1 tree structure of the oil pollution index is calculated based on the correlation coefficient matrix of the oil pollution index, and the T1 tree structure of the mechanical equipment wear index is calculated based on the correlation coefficient matrix of the mechanical equipment wear index. A Copula function for the reliability of the physical and chemical properties of oil products is established based on the T1 tree structure of the oil product physicochemical property index, a Copula function for the reliability of oil product contamination is established based on the T1 tree structure of the oil product contamination index, and a Copula function for the reliability of mechanical equipment wear is established based on the T1 tree structure of the mechanical equipment wear index. A comprehensive multivariate Copula reliability analysis model is constructed based on the joint weighting factor of the edge distribution, the Copula function for the reliability of the physical and chemical properties of oil, the Copula function for the reliability of oil contamination, and the Copula function for the reliability of mechanical equipment wear. The overall relative reliability of the mechanical equipment lubrication system is determined based on the comprehensive multivariate Copula reliability analysis model.

2. The method for analyzing the reliability of lubrication in mechanical equipment according to claim 1, characterized in that, The physicochemical properties of the oil include viscosity, acid value, base value, Ca content, Zn content, and P content. The oil contamination indicators include moisture content, soot content, oxidation value, nitration value, Si content, and n-pentane content. The wear indicators of the mechanical equipment include Fe content, Cu content, Ni content, Sn content, and Cr content.

3. The method for analyzing the reliability of lubrication in mechanical equipment according to claim 1, characterized in that, The step of establishing a Copula function for the reliability of the physicochemical properties of the oil based on the T1 tree structure of the oil's physicochemical properties includes: The D-vine characteristics were determined based on the T1 tree structure of the oil's physicochemical properties. Generate D-Vine Copula functions based on D-vine features; The D-Vine Copula function is iterated through to obtain the traversal data; Based on the traversal data, the optimal binary function between adjacent nodes is determined using the AIC criterion; Construct a Copula function for the reliability of the physicochemical properties of oil products based on the optimal binary function.

4. A device for analyzing the reliability of lubrication in mechanical equipment, characterized in that, The mechanical equipment lubrication reliability analysis device includes: The determination unit is used to determine the attributes of various monitoring indicators for the lubrication of mechanical equipment; The monitoring unit is used to monitor the indicator data corresponding to each monitoring indicator attribute during the operation of the mechanical equipment. The calculation unit is used to calculate the joint weighting factor of the marginal distribution of each monitoring indicator attribute based on the indicator data; The first construction unit is used to construct the Copula function for the reliability of the physical and chemical properties of oil, the Copula function for the reliability of oil contamination, and the Copula function for the reliability of mechanical equipment wear based on the index data. The second construction unit is used to construct a comprehensive multivariate Copula reliability analysis model based on the edge distribution joint weighting factor, the oil physicochemical property reliability Copula function, the oil contamination reliability Copula function, and the mechanical equipment wear reliability Copula function. The determining unit is used to determine the overall relative reliability of the mechanical equipment lubrication system based on the comprehensive multivariate Copula reliability analysis model. The monitoring unit includes: The first sub-unit is used to establish the marginal distribution equation of each monitoring indicator attribute based on the indicator data. The first calculation subunit is used to calculate the joint weight factor of the marginal distribution of each monitoring indicator attribute according to the marginal distribution equation using the entropy method. The first building unit includes: Sub-units are used to divide the monitoring index attributes into oil physicochemical performance indicators, oil pollution indicators, and mechanical equipment wear indicators. The second calculation subunit is used to calculate the correlation coefficient matrix of the physical and chemical properties of the oil, the correlation coefficient matrix of the oil pollution index, and the correlation coefficient matrix of the mechanical equipment wear index based on the index data; and to calculate the T1 tree structure of the physical and chemical properties of the oil, the T1 tree structure of the oil pollution index, and the T1 tree structure of the mechanical equipment wear index based on the correlation coefficient matrix of the physical and chemical properties of the oil; The second sub-unit is used to establish a Copula function for the reliability of the physical and chemical properties of the oil based on the T1 tree structure of the oil's physical and chemical properties index, a Copula function for the reliability of the oil's contamination based on the T1 tree structure of the oil's contamination index, and a Copula function for the reliability of the mechanical equipment's wear based on the T1 tree structure of the mechanical equipment's wear index.

5. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the mechanical equipment lubrication reliability analysis method according to any one of claims 1 to 3.

6. A readable storage medium, characterized in that, The readable storage medium stores computer program instructions, which are read and executed by a processor to perform the mechanical equipment lubrication reliability analysis method according to any one of claims 1 to 3.

Images