System-level reliability modeling method driven by data-physics joint

Abstract

This application proposes a data-physics joint-driven system-level reliability modeling method, which obtains damage parameter data through the external load conditions and finite element model of the mechanical system; selects a baseline variable, and applies a machine learning model to establish the system external load-baseline variable and baseline variable-part damage parameter proxy models based on the damage parameter data set; obtains external load data information, and obtains the probability distribution of the baseline variable through the external load-baseline variable machine learning model; reflects the failure correlation between each part in the system through the baseline variable-part damage parameter machine learning model; based on the probability distribution of the baseline variable and the failure correlation between parts, applies the system-level reliability modeling method to establish a data-physics joint-driven system-level reliability model to solve the system reliability under complex load conditions and improve the accuracy and rationality of system reliability evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical system reliability assessment, and in particular to a data-physics jointly driven system-level reliability modeling method. Background Art

[0002] Systems are composed of components. However, system reliability is not solely determined by the reliability of its components. The relationship between system reliability and component reliability is also related to the degree of failure correlation between components. In reliability analysis, a system in which each component fails independently is called an independent-failure system. In such a system, the failure of each component (or any component at a certain level of the system, such as a subsystem or component, collectively referred to as a "unit") is an independent random event. Traditional system reliability models are built under the assumption that each component fails independently. Typical system reliability analysis methods calculate component reliability using interference models or estimate component reliability based on test data. Then, under the assumption that each component in the system fails independently, a system reliability model is constructed based on the system's logical structure (series, parallel, voting system, etc.). This system reliability model, constructed directly from component reliability, fails to reflect the important role of failure correlation. Traditional approaches to calculating system reliability based on component reliability require the assumption of independent component failure; otherwise, it is difficult to build a system reliability model. However, almost all mechanical systems are not independent-failure systems. Only when the loads borne by the various components in a system are uncorrelated (no logical connection between them, independent of each other) or when the loads are deterministic (no randomness), will the failures of the various components in the system be independent of each other. Generally speaking, failure events of various components in a system are statistically correlated random events. The degree of correlation between the failures of various components in a system depends on the relative magnitude of the uncertainty in the load (workload) and the uncertainty in the strength (the component's ability to resist failure). Traditional system reliability models will exhibit significant errors unless the uncertainty in the load is very small (especially relative to the uncertainty in the component's strength).

[0003] In recent years, the concepts and methods of systems engineering have seen significant development and widespread application in many fields. In system reliability analysis, "system-level" or "system-layer" reliability analysis and modeling methods have been proposed. Applying this approach allows for the simple establishment of accurate system reliability models while avoiding the unrealistic assumption that component failures are independent of each other. This truly demonstrates the principle that "the whole is simpler than the sum of its parts" in modeling.

[0004] Taking the stress-strength interference model as an example, when each component in the system is under a certain stress sUnder the action of , the conditional failure probability of the parts is completely determined by their strength distribution. In this case, the failure of each part is independent of each other. The load-damage parameter mapping relationship is a key link in the system-level reliability model, which can effectively reflect the failure correlation between the parts in the system. However, there is usually a complex nonlinear relationship between the load of the mechanical system and the damage parameters of the parts, so the load-damage parameter mapping relationship is often difficult to obtain. In addition, for systems with multiple external loads, how to solve the multi-layer integral is a key issue in solving the system reliability model. At present, there is no more effective multi-layer integral solution method or tool, which limits the promotion and application of such system reliability models in engineering. On the other hand, most of the existing system reliability models are suitable for the design stage and do not have the function of real-time update during the service of the system. It is difficult to meet the needs of high-precision reliability evaluation of the system under complex load conditions. Summary of the Invention

[0005] Based on this, it is necessary to propose a data-physics joint driven system-level reliability modeling method to address the technical problem that the existing technology has not taken into account the difficulty of existing technology to meet the requirements of high-precision reliability evaluation of systems under complex load conditions.

[0006] First, a data-physical joint-driven system-level reliability modeling method is provided, including:

[0007] Acquiring damage parameter data of the mechanical system based on external load condition data of the mechanical system and a finite element model of the mechanical system;

[0008] Selecting a baseline variable and, based on the damage parameter data, establishing a system external load-baseline variable proxy model and a baseline variable-part damage parameter proxy model through machine learning technology;

[0009] Acquiring external load data information according to sensor data, and inputting the external load data information into the system external load-reference variable proxy model to obtain a probability distribution of the reference variable;

[0010] Inputting the reference variable into the reference variable-part damage parameter proxy model to obtain the failure correlation relationship between the parts in the mechanical system;

[0011] Based on the probability distribution and the failure correlation, a system-level reliability modeling method is applied to establish a data-physics joint-driven system-level reliability model, and the reliability of the mechanical system is determined according to the system-level reliability model.

[0012] Optionally, the step of acquiring damage parameter data of the mechanical system based on external load condition data of the mechanical system and a finite element model of the mechanical system includes:

[0013] Acquiring attribute information of the mechanical system, and establishing a finite element model of the mechanical system according to the attribute information;

[0014] External load condition data of the mechanical system determined by orthogonal experimental design method;

[0015] Finite element analysis is performed on the mechanical system based on the finite element model and the load condition, and combined with a damage parameter model, damage parameter data corresponding to each part in the mechanical system and the external load condition data are obtained.

[0016] Optionally, the step of selecting a baseline variable and establishing a system external load-baseline variable proxy model and a baseline variable-part damage parameter proxy model based on the damage parameter data by machine learning technology includes:

[0017] Selecting any part in the mechanical system as a reference part, using the damage parameter corresponding to the reference part in the damage parameter data as a reference variable, and establishing and training a machine learning model based on the damage parameter data using a machine learning technique, with an external load variable as an input variable and a reference variable as an output variable, to obtain an external load-reference variable proxy model of the system;

[0018] A machine learning model is established and trained based on the damage parameter data using a reference variable as an input variable and the damage parameters of each part in the mechanical system as an output variable through machine learning technology to obtain the reference variable-part damage parameter proxy model.

[0019] Optionally, the step of acquiring external load data information according to sensor data and inputting the external load data information into the system external load-reference variable proxy model to obtain the probability distribution of the reference variable includes:

[0020] determining a probability distribution of an external load variable based on the external load data information;

[0021] Monte Carlo sampling method is applied to obtain external load combinations according to the probability distribution of external load variables;

[0022] Obtaining a benchmark variable corresponding to the external load combination through the system external load-benchmark variable proxy model;

[0023] A statistical analysis method is applied to obtain a probability distribution of the benchmark variables corresponding to the external load combination.

[0024] Optionally, the step of applying a system-level reliability modeling method based on the probability distribution and the failure correlation to establish a data-physics jointly driven system-level reliability model, and determining the reliability of the mechanical system according to the system-level reliability model includes:

[0025] Based on the load-strength interference theory, according to the probability distribution and the failure correlation, a system-level reliability modeling method is applied to establish a data-physics joint driven system-level reliability model.

[0026] Optionally, the mathematical representation of the system layer reliability model is:

[0027]

[0028] Where, R s is the system reliability; v b is the baseline variable; g ( v b ) is the probability density function of the benchmark variable; s i ( v b ) indicates parts i The damage parameter is the baseline variable v b function; S i For the i The strength of a component indicates its ability to resist damage and has a game relationship with the damage parameter, not limited to the strength of the material or structure; f i ( S i ) is the i The strength of each part S i The probability density function of n is the number of parts in the system.

[0029] The present application obtains damage parameter data of the mechanical system based on the external load working condition data of the mechanical system and the finite element model of the mechanical system; selects a baseline variable, and based on the damage parameter data, establishes a system external load-baseline variable proxy model and a baseline variable-part damage parameter proxy model through machine learning technology; obtains external load data information according to sensor data, and inputs the external load data information into the system external load-baseline variable proxy model to obtain the probability distribution of the baseline variable; inputs the baseline variable into the baseline variable-part damage parameter proxy model to obtain the failure correlation between the parts in the mechanical system; based on the probability distribution and the failure correlation, applies the system-level reliability modeling method to establish a data-physics joint driven system-level reliability model, and determines the reliability of the mechanical system according to the system-level reliability model. By using a single benchmark variable to replace multiple load random variables, multiple outer-level integrals in the traditional system-level reliability model can be converted into a single outer-level integral, solving the problem of the difficulty of solving multi-level integrals in the traditional system-level reliability model. A complex mapping relationship between the benchmark variable and the damage parameters of each component is established, solving the problem of the difficulty in obtaining the complex nonlinear relationship between the mechanical system load and the component damage parameters, reflecting the failure correlation between the various components in the system. The reliability model can be updated in real time during the service phase, obtaining more accurate real-time reliability of the mechanical system. This approach has better engineering practicality and higher application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] in:

[0032] Figure 1 A flowchart of a data-physical joint driven system layer reliability modeling method is provided for an embodiment of the present invention;

[0033] Figure 2 A schematic diagram of a finite element model in a data-physics joint driven system layer reliability modeling method is provided for an embodiment of the present invention;

[0034] Figure 3 A schematic diagram of dangerous parts of a mechanical system in a data-physics joint driven system layer reliability modeling method is provided for an embodiment of the present invention;

[0035] Figure 4A schematic diagram of the topological structure of the system external load-reference variable model provided in an embodiment of the present invention;

[0036] Figure 5 A diagram showing the prediction effect of the system external load-reference variable model provided by an embodiment of the present invention;

[0037] Figure 6 A schematic diagram of the topological structure of the mapping relationship model between the reference variable and the component damage parameter provided in an embodiment of the present invention;

[0038] Figure 7 A diagram showing the prediction effect of the mapping relationship model between the reference variable and the component damage parameter provided in an embodiment of the present invention;

[0039] Figure 8 This is the reliability assessment result of the steam turbine rotor system provided by the embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0041] The present invention is described in detail below through specific examples.

[0042] See also Figure 1 As shown, Figure 1 A data-physical joint-driven system-level reliability modeling method provided in an embodiment of the present invention includes:

[0043] S101, acquiring damage parameter data of the mechanical system based on external load condition data of the mechanical system and a finite element model of the mechanical system;

[0044] S102, selecting a baseline variable, and establishing a system external load-baseline variable proxy model and a baseline variable-part damage parameter proxy model based on the damage parameter data using machine learning technology;

[0045] S103, acquiring external load data information according to sensor data, and inputting the external load data information into the system external load-reference variable proxy model to obtain a probability distribution of the reference variable;

[0046] S104, inputting the reference variable into the reference variable-part damage parameter proxy model to obtain the failure correlation relationship between the parts in the mechanical system;

[0047] S105 . Based on the probability distribution and the failure correlation, apply a system-level reliability modeling method to establish a data-physics jointly driven system-level reliability model, and determine the reliability of the mechanical system according to the system-level reliability model.

[0048] The damage parameter data of the mechanical system is obtained based on the external load working condition data of the mechanical system and the finite element model of the mechanical system; a baseline variable is selected, and based on the damage parameter data, a system external load-baseline variable proxy model and a baseline variable-part damage parameter proxy model are established through machine learning technology; external load data information is obtained according to sensor data, and the external load data information is input into the system external load-baseline variable proxy model to obtain the probability distribution of the baseline variable; the baseline variable is input into the baseline variable-part damage parameter proxy model to obtain the failure correlation between the parts in the mechanical system; based on the probability distribution and the failure correlation, a system-level reliability modeling method is applied to establish a data-physics joint driven system-level reliability model, and the reliability of the mechanical system is determined according to the system-level reliability model. By using a single benchmark variable to replace multiple load random variables, multiple outer-level integrals in the traditional system-level reliability model can be converted into a single outer-level integral, solving the problem of the difficulty of solving multi-level integrals in the traditional system-level reliability model. A complex mapping relationship between the benchmark variable and the damage parameters of each component is established, solving the problem of the difficulty in obtaining the complex nonlinear relationship between the mechanical system load and the component damage parameters, reflecting the failure correlation between the various components in the system. The reliability model can be updated in real time during the service phase, obtaining more accurate real-time reliability of the mechanical system. This approach has better engineering practicality and higher application value.

[0049] In a possible implementation, the step of acquiring damage parameter data of the mechanical system based on external load condition data of the mechanical system and a finite element model of the mechanical system includes:

[0050] Acquiring attribute information of the mechanical system, and establishing a finite element model of the mechanical system according to the attribute information;

[0051] External load condition data of the mechanical system determined by orthogonal experimental design method;

[0052] Finite element analysis is performed on the mechanical system based on the finite element model and the load condition, and combined with a damage parameter model, damage parameter data corresponding to each part in the mechanical system and the external load condition data are obtained.

[0053] In one possible implementation, the steps of selecting a baseline variable and establishing a system external load-baseline variable proxy model and a baseline variable-part damage parameter proxy model based on the damage parameter data using machine learning techniques include:

[0054] Selecting any part in the mechanical system as a reference part, using the damage parameter corresponding to the reference part in the damage parameter data as a reference variable, and establishing and training a machine learning model based on the damage parameter data using a machine learning technique, with an external load variable as an input variable and a reference variable as an output variable, to obtain an external load-reference variable proxy model of the system;

[0055] A machine learning model is established and trained based on the damage parameter data using a reference variable as an input variable and the damage parameters of each part in the mechanical system as an output variable through machine learning technology to obtain the reference variable-part damage parameter proxy model.

[0056] In one possible implementation, the step of acquiring external load data information based on sensor data and inputting the external load data information into the system external load-reference variable proxy model to obtain a probability distribution of the reference variable includes:

[0057] determining a probability distribution of an external load variable based on the external load data information;

[0058] Monte Carlo sampling method is applied to obtain external load combinations according to the probability distribution of external load variables;

[0059] Obtaining a benchmark variable corresponding to the external load combination through the system external load-benchmark variable proxy model;

[0060] A statistical analysis method is applied to obtain a probability distribution of the benchmark variables corresponding to the external load combination.

[0061] In one possible implementation, the steps of applying a system-level reliability modeling method based on the probability distribution and the failure correlation to establish a data-physics-co-driven system-level reliability model, and determining the reliability of the mechanical system according to the system-level reliability model include:

[0062] Based on the load-strength interference theory, according to the probability distribution and the failure correlation, a system-level reliability modeling method is applied to establish a data-physics joint driven system-level reliability model.

[0063] In a possible implementation, the mathematical representation of the system layer reliability model is:

[0064]

[0065] Where, R s is the system reliability; v b is the baseline variable; g ( v b ) is the probability density function of the benchmark variable; s i ( v b ) indicates parts i The damage parameter is the baseline variable v b function; S i For the i The strength of a component indicates its ability to resist damage and has a game relationship with the damage parameter, not limited to the strength of the material or structure; f i ( S i ) is the i The strength of each part S i The probability density function of n is the number of parts in the system.

[0066] Exemplary steps for implementing the data-physics joint driven system-level reliability modeling method include:

[0067] Finite element modeling is performed on the turbine rotor system (mechanical system) to be evaluated. The established finite element model is as follows: Figure 2 shown.

[0068] According to the actual load conditions, the stress conditions of the system are simulated and the dangerous parts of the system are determined according to the stress state, such as Figure 3 As shown in the figure, the results show that the stress at the stress relief groove and blade root groove of the turbine rotor system is relatively large, which is a dangerous part of the system.

[0069] Based on the variation ranges of different types of external loads, an orthogonal experimental design method was used to design several representative load conditions. In this embodiment, for the steam turbine rotor, the monitorable parameters include steam temperature, steam pressure, speed, and load. In finite element simulation, steam temperature, speed, and load are primarily used to apply loads. Therefore, orthogonal experimental sampling was performed on these three load parameters, combining them into several groups of representative load conditions.

[0070] Finite element analysis of the steam turbine rotor is performed under several designed representative load conditions to obtain the damage parameters of the dangerous parts under each load condition. Combined with the damage calculation model, the cumulative damage of each dangerous part under each load condition is obtained to obtain the proxy model data set.

[0071] The cumulative damage of the stress relief groove is selected as the benchmark variable.

[0072] A machine learning model is established with the external load variable as the input variable and the cumulative damage of the stress relief groove as the output variable, which is called the system external load-reference variable proxy model (proxy model 1). The machine learning model established in this embodiment is a three-layer artificial neural network model, such as Figure 4 As shown, the input layer of the artificial neural network model includes 7 nodes, the hidden layer includes 3 nodes, and the output layer includes 1 node. In this embodiment, the machine learning model includes but is not limited to the artificial neural network model and other high-performance machine learning models, which are not limited here. The cross-validation method is used to verify the prediction accuracy of the artificial neural network model. The data in the data set is divided into 10 groups, and 9 groups of data are extracted to train the artificial neural network model. The remaining 1 group of data is used to verify the artificial neural network model. The prediction effect of the artificial neural network model is shown in Figure 2. Figure 5 As shown. Root mean square error (RMSE) and Pearson correlation coefficient (R 2 ) can represent the prediction accuracy of the model. The smaller the RMSE, the better the R 2 The closer it is to 1, the better the model effect. The prediction results show that the artificial neural network model has a good prediction effect.

[0073] Based on the actual working condition data collected by the sensor, the statistical analysis method is applied to obtain the probability distribution of various external loads. The Monte Carlo sampling method is applied to obtain several load parameters, which are combined into several groups of load conditions. The cumulative damage value of the stress relief groove corresponding to each group of load conditions is output through the proxy model 1. The statistical analysis method is applied to obtain the probability distribution of the cumulative damage value of the stress relief groove, that is, the probability density function of the benchmark variable is obtained.

[0074] A machine learning model is established with the baseline variable as the input variable and the cumulative damage of each dangerous part as the output variable, which is called the baseline variable-part damage parameter mapping agent model (agent model 2). The machine learning model established in this embodiment is a three-layer artificial neural network model, such as Figure 6As shown, the input layer of the artificial neural network model includes 2 nodes, the hidden layer includes 3 nodes, and the output layer includes 11 nodes. In this embodiment, the machine learning model includes but is not limited to the artificial neural network model and other high-performance machine learning models, which are not limited here. 90% of the data is used to train the artificial neural network model, and the remaining 10% of the data is used to verify the artificial neural network model. The prediction effect of the artificial neural network model is shown in FIG. Figure 7 The prediction results show that the artificial neural network model has a good prediction effect.

[0075] Based on the obtained proxy model and the probability distribution of the benchmark variables, a system-level reliability model driven by data-physics is established:

[0076]

[0077] Where, R s ( m )for m System reliability corresponding to the start-stop process; D rml for m The logarithm of the cumulative damage of the stress relief slot corresponding to the start-stop process; h rm ( D rml )for D rml The probability density function of b is the number of dangerous parts; D iml ( D rml )for m Dangerous parts corresponding to the start-stop process i The cumulative damage logarithm of D rml function; T is the critical value of cumulative damage, which can be obtained through experiments; f 0( T ) is the probability density function of the standard normal distribution; μ Til is the logarithmic mean of the cumulative damage threshold; σ Til is the logarithmic standard deviation of the cumulative damage threshold.

[0078] Solve the system layer reliability model to obtain the reliability-start-stop number relationship of the steam turbine rotor system in this embodiment as follows: Figure 8 shown.

[0079] Specifically, during the design phase of a mechanical system, the system reliability can be calculated based on a given load probability distribution. During the service phase of a mechanical system, the statistical characteristics of the load can be calculated in real time based on sensor monitoring data, and the probability distribution of the baseline variables can be updated to achieve real-time updating of the reliability model and obtain the real-time reliability of the mechanical system.

Claims

1. A data-physical joint driven system layer reliability modeling method, characterized by: include: Acquiring damage parameter data of the mechanical system based on external load condition data of the mechanical system and a finite element model of the mechanical system; Selecting a baseline variable and, based on the damage parameter data, establishing a system external load-baseline variable proxy model and a baseline variable-part damage parameter proxy model through machine learning technology; The steps of selecting a baseline variable and establishing a system external load-baseline variable proxy model and a baseline variable-part damage parameter proxy model based on the damage parameter data by machine learning technology include: Selecting any part in the mechanical system as a reference part, using the damage parameter corresponding to the reference part in the damage parameter data as a reference variable, and establishing and training a machine learning model based on the damage parameter data using a machine learning technique, with an external load variable as an input variable and a reference variable as an output variable, to obtain an external load-reference variable proxy model of the system; Establishing and training a machine learning model based on the damage parameter data using a machine learning technique, with a reference variable as an input variable and the damage parameters of each component in the mechanical system as an output variable, to obtain the reference variable-component damage parameter proxy model; Acquiring external load data information according to sensor data, and inputting the external load data information into the system external load-reference variable proxy model to obtain a probability distribution of the reference variable; Inputting the reference variable into the reference variable-part damage parameter proxy model to obtain the failure correlation relationship between the parts in the mechanical system; Based on the probability distribution and the failure correlation, a system-level reliability modeling method is applied to establish a data-physics joint-driven system-level reliability model, and the reliability of the mechanical system is determined according to the system-level reliability model.

2. The data-physical joint driven system layer reliability modeling method according to claim 1 is characterized in that: The step of obtaining damage parameter data of the mechanical system based on external load condition data of the mechanical system and a finite element model of the mechanical system comprises: Acquiring attribute information of the mechanical system, and establishing a finite element model of the mechanical system according to the attribute information; External load condition data of the mechanical system determined by orthogonal experimental design method; Finite element analysis is performed on the mechanical system based on the finite element model and the load condition, and combined with a damage parameter model, damage parameter data corresponding to each part in the mechanical system and the external load condition data are obtained.

3. The data-physical joint driven system layer reliability modeling method according to claim 1 is characterized in that: The step of acquiring external load data information according to sensor data, and inputting the external load data information into the system external load-reference variable proxy model to obtain the probability distribution of the reference variable includes: determining a probability distribution of an external load variable based on the external load data information; Monte Carlo sampling method is applied to obtain external load combinations according to the probability distribution of external load variables; Obtaining a benchmark variable corresponding to the external load combination through the system external load-benchmark variable proxy model; A statistical analysis method is applied to obtain a probability distribution of the benchmark variables corresponding to the external load combination.

4. The data-physical joint driven system layer reliability modeling method according to claim 1 is characterized in that: The steps of applying a system-level reliability modeling method based on the probability distribution and the failure correlation to establish a data-physics-co-driven system-level reliability model, and determining the reliability of the mechanical system according to the system-level reliability model include: Based on the load-strength interference theory, according to the probability distribution and the failure correlation, a system-level reliability modeling method is applied to establish a data-physics joint driven system-level reliability model.

5. The data-physical joint driven system layer reliability modeling method according to claim 1 is characterized in that: The mathematical representation of the system layer reliability model is: Where R s is the system reliability; v b is the benchmark variable; g(v b ) is the probability density function of the benchmark variable; s i (v b ) represents the damage parameter of part i, which is the reference variable v b Function of S i is the strength of the i-th component, indicating its ability to resist damage, which has a game relationship with the damage parameter and is not limited to the strength of the material or structure; f i (S i ) is the strength S of the i-th part i The probability density function of ; n is the number of parts in the system.

Images