Fault diagnosis method, device, equipment and storage medium for spring energy storage seal

Abstract

The present invention relates to the field of data processing and discloses a fault diagnosis method, device, equipment and storage medium for a spring energy storage sealing ring, which are used to improve the accuracy of fault diagnosis of a spring energy storage sealing ring. The method comprises: collecting information of a target liquid slip ring and a target spring energy storage sealing ring to obtain an entity information set; constructing a finite element model through the entity information set to obtain a target virtual entity model; performing simulation calculations through the target virtual entity model to obtain a simulated working condition data set; inputting the simulated working condition data set into a fault diagnosis model to perform fault analysis, generate a fault analysis result and judge the fault analysis result to obtain a judgment result; when the judgment result is a fault, performing a root cause analysis on the fault analysis result to determine a fault cause set; collecting actual detection data corresponding to the target virtual entity model, and matching and analyzing the fault cause set through the actual detection data to generate target fault cause data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a fault diagnosis method, device, equipment and storage medium for a spring energy storage sealing ring. Background Art

[0002] FPSOs (Floating Production, Storage and Offloading) are a key component of offshore oil development. The "FPSO + production platform / subsea production system + shuttle tanker" development approach offers numerous advantages. It can be combined not only with offshore platforms but also with subsea production systems to form a complete, all-sea development system. The single-point mooring system, the core component connecting the FPSO to the production platform / subsea production system, handles core tasks such as well fluid, power, and communications transmission. A failure in the single-point mooring system can directly lead to reduced oilfield production or even shutdown.

[0003] In recent years, several major accidents have occurred in the inner turret, riser, and mooring system of FPSOs in extreme marine environments, resulting in reduced or even shutdown oilfield production. To ensure the safety of single-point mooring systems, domestic and foreign engineering communities have conducted research in environmental monitoring and mooring force monitoring, and developed FPSO monitoring systems to monitor and alarm for hull attitude, structural vibration, and electric slip ring arcing. However, these systems do not yet cover key components such as bearings and torque arms. In particular, while mooring force monitoring is relatively complete on various FPSOs, most monitoring information on slip rings is directly connected to the central control system, with simple alarm thresholds set and historical slip ring data passively recorded. Active processing and analysis of slip ring data is not performed, and multi-parameter fault models have not been established, making it impossible to trace slip ring faults and provide fault warnings. Consequently, there is a problem of insufficient accuracy in fault diagnosis of spring energy storage seals in the liquid slip rings of single-point mooring systems. Summary of the Invention

[0004] In view of this, the embodiments of the present invention provide a fault diagnosis method, device and system for a spring energy storage sealing ring, which solve the technical problem of low accuracy when performing fault detection on a spring energy storage sealing ring.

[0005] The first aspect of the present invention provides a fault diagnosis method for a spring energy storage sealing ring, comprising: collecting information on a target liquid slip ring and a target spring energy storage sealing ring based on a preset physical entity model to obtain a corresponding entity information set; constructing a finite element model through the entity information set to obtain a corresponding target virtual entity model; performing finite element numerical simulation calculations through the target virtual entity model to obtain a corresponding simulated working condition data set; inputting the simulated working condition data set into a preset fault diagnosis model, performing a preliminary fault analysis on the target virtual entity model, generating a corresponding fault analysis result, and judging the fault analysis result to obtain a corresponding judgment result, wherein the judgment result includes fault and normal; when the judgment result is a fault, performing a root cause analysis on the fault analysis result to determine a corresponding fault cause set; collecting actual detection data corresponding to the target virtual entity model, and matching and analyzing the fault cause set through the actual detection data to generate corresponding target fault cause data.

[0006] The fault diagnosis method for a spring energy storage sealing ring provided by the present invention can realize real-time monitoring of the spring performance sealing ring in the liquid lubricating ring by establishing a physical model of the spring energy storage sealing ring in the liquid lubricating ring, provide accurate data support for subsequent fault diagnosis, and improve the accuracy of fault diagnosis. By inputting the simulated working condition data set into a preset fault diagnosis model, a preliminary fault analysis is performed on the target virtual entity model to generate a corresponding fault analysis result, and the fault analysis result is judged to obtain a corresponding judgment result, and actual detection data corresponding to the target virtual entity model is collected, and the fault cause set is matched and analyzed through the actual detection data to generate corresponding target fault cause data. In this scheme, by adopting a fault diagnosis model with two-level comprehensive indicators, it is possible to accurately judge whether a fault occurs and give a fault level, which can further improve the accuracy of fault diagnosis of spring performance sealing rings.

[0007] In combination with the first aspect, in the first embodiment of the first aspect, the step of collecting information on the target liquid slip ring and the target spring energy storage seal ring based on the preset physical entity model to obtain the corresponding entity information set includes: extracting the identification of the target liquid slip ring and the target spring energy storage seal ring to obtain identification information corresponding to the target liquid slip ring and the target spring energy storage seal ring; analyzing the storage position of the preset physical entity model through the identification information to generate a corresponding information storage address; collecting information according to the information storage address to obtain a corresponding entity information set.

[0008] In combination with the first embodiment of the first aspect, in the second embodiment of the first aspect, the step of constructing a finite element model through the entity information set to obtain a corresponding target virtual entity model includes: extracting features from the entity information set to obtain corresponding entity feature information; performing parameter matching based on the entity feature information to determine corresponding entity feature parameters; and constructing a finite element model based on the entity feature parameters and the entity feature information to obtain a corresponding target virtual entity model.

[0009] In this scheme, by combining the failure criteria of the liquid slip ring seal with the finite element model, the qualitative analysis criteria of the simple alarm threshold judgment standard of the liquid slip ring leakage are converted into quantitative analysis criteria, which can further improve the accuracy of fault detection of the spring energy storage seal ring in the liquid slip ring.

[0010] In combination with the second embodiment of the first aspect, in the third embodiment of the first aspect, the step of performing finite element numerical simulation calculations on the target virtual entity model to obtain a corresponding simulated working condition data set includes: performing unit information matching on the target virtual entity model to determine a corresponding unit information set, wherein the unit information set includes unit shape and unit type; based on the unit set information, performing working condition matching on the target virtual entity model through a preset grid division algorithm to obtain a corresponding working condition environment set; performing working condition simulation calculations on the target virtual entity model through the working condition environment to obtain a corresponding simulated working condition data set.

[0011] In this solution, the calculation results given by the finite element model are clear, intuitive and highly reliable. It can obtain data information that cannot be obtained by general monitoring means, and comprehensively display the operating status of the liquid slip ring under different working conditions, so as to ensure the accuracy of fault diagnosis in the subsequent fault diagnosis of the spring performance sealing ring.

[0012] In combination with the first aspect, in the fourth embodiment of the first aspect, before the step of performing finite element numerical simulation operation through the target virtual entity model to obtain the corresponding simulation working condition data set, after the step of constructing a finite element model through the entity information set to obtain the corresponding target virtual entity model, it also includes: performing simulation calculation based on a single variable parameter on the target virtual entity model to obtain corresponding multiple performance evaluation parameters; performing fluctuation range analysis on the multiple performance evaluation parameters to obtain the fluctuation range corresponding to each of the performance evaluation parameters; performing weight analysis on the multiple performance evaluation parameters to obtain the parameter weight corresponding to each of the performance evaluation parameters.

[0013] In combination with the fourth embodiment of the first aspect, in the fifth embodiment of the first aspect, the simulated operating condition data set is input into a preset fault diagnosis model, a preliminary fault analysis is performed on the target virtual entity model, a corresponding fault analysis result is generated, and the fault analysis result is judged to obtain a corresponding judgment result, wherein the judgment result includes fault and normal steps, including: inputting the simulated operating condition data set into the fault diagnosis model, traversing the simulated operating condition data through the non-parametric classification algorithm in the fault diagnosis model to obtain corresponding parameter data to be analyzed; based on the fluctuation range corresponding to each of the performance evaluation parameters, the parameter data to be analyzed is screened to obtain corresponding target parameter data; fault diagnosis is performed through the target parameter data to obtain corresponding fault analysis results, and the fault analysis results are judged to obtain corresponding judgment results, wherein the judgment results include fault and normal.

[0014] In combination with the fourth embodiment of the first aspect or the fifth embodiment of the first aspect, in the sixth embodiment of the first aspect, when the judgment result is a fault, performing a root cause analysis on the fault analysis result to determine the corresponding fault cause set step includes: when the judgment result is a fault, performing fault data matching on the fault analysis result to determine the corresponding fault data; based on the parameter weight corresponding to each of the performance evaluation parameters, performing a root cause analysis on the fault data through the decision tree algorithm of the fault diagnosis model to determine the corresponding fault cause set.

[0015] According to a second aspect, an embodiment of the present invention provides a fault diagnosis device for a spring energy storage seal ring, comprising:

[0016] An acquisition module is used to collect information about the target liquid slip ring and the target spring energy storage seal ring based on a preset physical entity model to obtain a corresponding entity information set;

[0017] A construction module, configured to construct a finite element model using the entity information set to obtain a corresponding target virtual entity model;

[0018] A calculation module, configured to perform finite element numerical simulation calculations on the target virtual entity model to obtain a corresponding simulation working condition data set;

[0019] a judgment module, configured to input the simulated working condition data set into a preset fault diagnosis model, perform preliminary fault analysis on the target virtual entity model, generate corresponding fault analysis results, and judge the fault analysis results to obtain corresponding judgment results, wherein the judgment results include fault and normal;

[0020] An analysis module, configured to, when the judgment result is a fault, perform a root cause analysis on the fault analysis result to determine a corresponding set of fault causes;

[0021] The matching module is used to collect actual detection data corresponding to the target virtual entity model, and perform matching analysis on the fault cause set through the actual detection data to generate corresponding target fault cause data.

[0022] According to the third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to execute the fault diagnosis method for the spring energy storage sealing ring described in the first aspect or any one embodiment of the first aspect, or to execute the fault diagnosis method for the spring energy storage sealing ring described in the second aspect or any one embodiment of the second aspect.

[0023] According to the fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the fault diagnosis method of the spring energy storage sealing ring described in the first aspect or any one embodiment of the first aspect, or to execute the fault diagnosis method of the spring energy storage sealing ring described in the second aspect or any one embodiment of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are 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.

[0025] Figure 1 This is a flow chart of a fault diagnosis method for a spring energy storage seal ring according to an embodiment of the present invention;

[0026] Figure 2 Schematic diagram of the relationship between the contact stress of the left and right lips of the spring energy storage seal ring and the contact position in an embodiment of the present invention

[0027] Figure 3 Flowchart for analyzing performance evaluation parameters in an embodiment of the present invention;

[0028] Figure 4 Schematic diagram of shear stress cloud diagram of spring energy storage seal ring jacket under different pressures in an embodiment of the present invention;

[0029] Figure 5Schematic diagram of the maximum contact stress curve of the spring energy storage seal ring under different medium pressures in an embodiment of the present invention;

[0030] Figure 6 Schematic diagram of maximum contact stress curves of a spring energy storage seal ring at different compression rates in an embodiment of the present invention;

[0031] Figure 7 Schematic diagram of shear stress cloud diagram of the spring energy storage seal ring jacket at different compression rates in an embodiment of the present invention;

[0032] Figure 8 Schematic diagram of the Mises stress and maximum shear stress of the spring energy storage seal ring at different temperatures in an embodiment of the present invention;

[0033] Figure 9 Schematic diagram of the maximum contact stress of the spring energy storage seal ring at different temperatures in an embodiment of the present invention;

[0034] Figure 10 This is a flow chart of performing finite element numerical simulation calculations in an embodiment of the present invention;

[0035] Figure 11 This is a flow chart of performing preliminary fault analysis on a target virtual entity model in an embodiment of the present invention;

[0036] Figure 12 Schematic diagram of a fault diagnosis device for a spring energy storage seal ring according to an embodiment of the present invention;

[0037] Figure 13 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention.

[0038] Reference numerals:

[0039] 501, acquisition module; 502, construction module; 503, operation module; 504, judgment module; 505, analysis module; 506, matching module; 601, processor; 602, memory. DETAILED DESCRIPTION

[0040] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. 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] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0042] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0043] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , Figure 1 FIG. 1 is a flow chart of a fault diagnosis method for a spring energy storage seal ring according to an embodiment of the present invention. Figure 1 As shown, the flow chart includes the following steps:

[0044] Step S101: collecting information of a target liquid slip ring and a target spring energy storage seal ring based on a preset physical entity model to obtain a corresponding entity information set;

[0045] It is understandable that the execution subject of the present invention may be a fault diagnosis device for a spring energy storage seal ring, or may be a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0046] Specifically, the server collects information on the target liquid lubricating ring and the target spring energy storage sealing ring based on a preset physical entity model, wherein the server determines the structural form of the target liquid lubricating ring and the target spring energy storage sealing ring through the physical entity model, and obtains the liquid lubricating ring structure corresponding to the target liquid lubricating ring and the sealing ring structure corresponding to the target spring energy storage sealing ring. Furthermore, the server collects information on the physical entity according to the liquid lubricating ring structure and the sealing ring structure, and obtains a corresponding entity information set, wherein it should be noted that the entity information set includes but is not limited to the diameters of the inner and outer rings of the liquid lubricating ring, the gap between the inner and outer rings, and the assembly relationship between the inner and outer rings and components such as the spring energy storage sealing ring.

[0047] Step S102: constructing a finite element model through the entity information set to obtain a corresponding target virtual entity model;

[0048] Specifically, when constructing a finite element model, the server constructs the model through a preset finite element model. The service collects data on the material model, contact parameters, boundary conditions, and loads in the entity information set, and sets parameters through the finite element model, thereby realizing the setting of state parameters of the target liquid slip ring under actual working conditions and obtaining the corresponding target virtual entity model.

[0049] Among them, it should be noted that when the server sets parameters and constructs the finite element model through the finite element model, the server first imports parameter information such as material model, contact parameters, boundary conditions, load, etc. into the finite element model, and establishes the curve corresponding to the solid model through the geometric dimensions corresponding to the above multiple parameter information and the surface mesh in the finite element model, and generates multiple surfaces based on the generated curve to establish a geometric model.

[0050] Step S103: performing finite element numerical simulation calculations on the target virtual entity model to obtain a corresponding simulation working condition data set;

[0051] Specifically, the server collects the material parameters of the built-in spring and jacket material in the target spring energy storage seal (such as elastic modulus, Poisson's ratio, etc.), and the specific grid density, unit shape, unit type, and grid division technology of the target spring energy storage seal and target liquid slip ring in the target virtual entity model. It should be noted that due to the motion characteristics of the target liquid slip ring, in terms of contact analysis, in the present application scheme, the server pre-sets the rigid components and reference points corresponding to the target virtual entity model, and defines the contact properties, contact relationship, and contact surface.

[0052] Among them, in the present application scheme, the complete construction process of the finite element model also includes the parameter setting of the analysis step and boundary conditions during the loading process. Specifically, the server sets the parameters for the constraints of the inner and outer rings, the simulation process of applying the preload force, and the pressure simulation process of the target spring energy storage sealing ring with high-pressure oil. After completing the parameter setting, the server performs finite element numerical simulation operations to obtain the corresponding simulation working condition data set.

[0053] Step S104: Inputting the simulated working condition data set into a preset fault diagnosis model, performing preliminary fault analysis on the target virtual entity model, generating corresponding fault analysis results, and judging the fault analysis results to obtain corresponding judgment results, wherein the judgment results include fault and normal;

[0054] Specifically, the server inputs the simulated working condition data set into a preset fault diagnosis model and performs a preliminary fault analysis on the target virtual entity model. It should be noted that the fault diagnosis model adopts the KNN algorithm, where the KNN algorithm is a non-parametric classification algorithm. The server classifies the simulated working condition data through the non-parametric classification algorithm and obtains two types of data, including "fault" data and "normal" data. In a further solution, the server performs root cause analysis on the "fault" data.

[0055] It should be noted that when the simulated working condition data set is input into the preset fault diagnosis model and the target virtual entity model is subjected to preliminary fault analysis, the fault working conditions are screened out from 1440 sets of data using the nearest neighbor algorithm and then the data are classified.

[0056] Step S105: When the judgment result is a fault, a root cause analysis is performed on the fault analysis result to determine the corresponding fault cause set;

[0057] Specifically, when the judgment result is a fault, a root cause analysis is performed on the fault analysis result, wherein the server adopts a decision tree algorithm to pre-locate multiple historical fault problems through problem analysis and generates a fault cause location criterion. Furthermore, the server performs a root cause analysis on the fault analysis result according to the fault cause location criterion, and generates a corresponding fault cause set. At the same time, a corresponding fault level set is generated, wherein the fault level set includes four categories: "fault level 0", "fault level 1", "fault level 2", and "fault level 3".

[0058] Step S106: collecting actual detection data corresponding to the target virtual entity model, and performing matching analysis on the fault cause set through the actual detection data to generate corresponding target fault cause data.

[0059] It should be noted that when the server performs fault diagnosis through the fault diagnosis model, there is a certain degree of uncertainty in the parameter setting. Therefore, after completing the fault diagnosis, the server also needs to collect actual detection data corresponding to the target virtual entity model. Furthermore, the server extracts data parameter features through the actual detection data to obtain the corresponding actual data parameters, and matches and analyzes the fault cause set based on the actual data parameters to obtain the corresponding target fault cause data.

[0060] By executing the above steps, a physical model of the spring energy storage seal ring in the liquid lubricating ring is established, which can realize real-time monitoring of the spring performance seal ring in the liquid lubricating ring, provide accurate data support for subsequent fault diagnosis, and improve the accuracy of fault diagnosis. By inputting the simulated working condition data set into the preset fault diagnosis model, a preliminary fault analysis is performed on the target virtual entity model, and the corresponding fault analysis results are generated. The fault analysis results are judged to obtain the corresponding judgment results, and the actual detection data corresponding to the target virtual entity model is collected. The fault cause set is matched and analyzed through the actual detection data to generate the corresponding target fault cause data. In this scheme, by adopting a fault diagnosis model with two-level comprehensive indicators, it can accurately determine whether a fault occurs and give a fault level, which can further improve the accuracy of fault diagnosis of the spring performance seal ring.

[0061] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0062] (1) extracting the identification information of the target liquid slip ring and the target spring energy storage seal ring to obtain the identification information corresponding to the target liquid slip ring and the target spring energy storage seal ring;

[0063] (2) Analyzing the storage location of the preset physical entity model through identification information to generate a corresponding information storage address;

[0064] (3) Collect information according to the information storage address and obtain the corresponding entity information set.

[0065] Specifically, the server extracts the identification of the target liquid slip ring and the target spring energy storage seal, wherein the server pre-acquires the identification extraction function corresponding to the target liquid slip ring and the target spring energy storage seal, and uses the identification extraction functions corresponding to the target liquid slip ring and the target spring energy storage seal respectively to obtain the identification information corresponding to the target liquid slip ring and the target spring energy storage seal. Furthermore, the server matches the information storage address according to the identification information, and determines the corresponding address description protocol based on the preset address resolution rules, and generates the corresponding information storage address. Finally, the server collects information according to the information storage address to obtain the corresponding entity information set.

[0066] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0067] (1) Extract features from the entity information set to obtain corresponding entity feature information;

[0068] (2) Perform parameter matching based on entity feature information to determine the corresponding entity feature parameters;

[0069] (3) Construct a finite element model based on entity feature parameters and entity feature information to obtain the corresponding target virtual entity model.

[0070] In the present application, the server takes the target liquid lubricating ring physical entity as the object, collects data on its geometric dimensions and assembly mode, and obtains the corresponding entity feature information. On the basis of the construction of the entity feature information, the inner and outer ring structures are simplified into the boundary conditions of the target spring energy storage sealing ring to obtain the entity feature parameters. In this solution, the server takes the spring energy storage sealing ring as the core research object, constructs it as a two-dimensional axisymmetric model in the finite element model, and obtains the corresponding target virtual entity model.

[0071] This solution is illustrated using an example. Specifically, the outer diameter of the hydraulic ring is set to 1000 mm, and the gap between the inner and outer rings is set to 2.5 mm. Regarding material parameters, the target spring accumulator seal is constructed of stainless steel with an elastic modulus E = 210,000 MPa and a Poisson's ratio μ = 0.3. The jacket is constructed of polytetrafluoroethylene (PTFE) with an elastic modulus of 488.38 MPa and a Poisson's ratio μ = 0.457. The meshing of the PTFE jacket is performed using CAX4IH elements, a type of element in the finite element model, totaling 3506 elements. Due to the two-dimensional model, the shape selection uses a quadrilateral-dominant surface. Furthermore, the server uses an advanced algorithm for free-sweep meshing. The jacket and inner spring are constructed as two separate components. Reduced integration is used for the inner spring, totaling 759 CAX4R elements. In terms of contact settings, a penalty function is used to define the friction formula, and its specific formula is as follows:

[0072] Π p =1 / 2p T E p p

[0073] Among them, E p is the penalty factor, Π pis the penalty function, P is the unit implantation depth matrix, and T represents the transpose of the unit implantation depth matrix P. In the present application, the friction coefficient is selected as 0.2. In terms of the setting of the contact surface, the "surface-to-surface contact" method is adopted. The contact surface between the sliding ring wall and the built-in spring is set as the main surface, and the inner and outer contact surfaces of the jacket structure are set as the slave surface. In terms of boundary conditions and loading, the outer wall of the sliding ring is set to constrain its 6 degrees of freedom to achieve a fixed support constraint. This constraint is placed in the analysis step of the finite element analysis model. It should be noted that in the analysis step, a displacement of 0.625mm is applied to the inner ring to achieve a 5% compression rate of the sealing ring, so that a certain degree of stress occurs inside the sealing ring structure, simulating the process of applying preload in actual engineering. A uniform load of 5MPa is applied to the built-in spring to simulate the load formed by high-pressure oil on the spring energy storage sealing ring in actual working conditions, so as to complete the finite element model construction and obtain the corresponding target virtual solid model.

[0074] It should be noted that, based on the establishment of the target virtual entity model, the present application also proposes a sealing criterion for a spring energy storage seal ring. According to the sealing environment of the liquid lubricating ring, the spring energy storage seal ring is in a relative motion state with the inner and outer rings under working conditions. However, due to the slow motion process, the sealing form of the spring energy storage seal ring is approximately considered to be a static seal, that is, the seal ring is simulated using the "quasi-sealing" principle, wherein the sealing performance of the spring energy storage seal ring relies on the rebound performance of its jacket material and the internal metal spring to achieve self-tightening sealing. When the seal ring is installed, the tension generated by the internal energy storage spring and the restoring force of the jacket material itself work together to press the lip of the seal ring against the inner wall of the sealing groove reserved in the outer ring. In addition, due to the design of the oil boosting system, the high-pressure oil inside the cavity in the target virtual entity model will give the seal ring an additional expansion force, causing the jacket to further deform, thereby making the sealing effect more significant.

[0075] In actual engineering applications, the basis for determining whether the sealing ring achieves effective sealing is whether the contact pressure between the lip and the inner and outer ring walls is greater than the medium pressure of the pressurized oil. On the other hand, the interaction between the sealing ring and the lip should not be too strong. Since the sealing ring jacket is prestressed during installation, the tension of the internal energy storage spring and the high-pressure oil pressure in actual operation will cause large shear stresses within the material. To prevent shear failure and structural damage, the shear stress value should not be too high.

[0076] Therefore, this solution provides the sealing criteria for the spring-energized seal ring, including the maximum contact pressure criterion and the maximum shear stress criterion. The maximum contact stress criterion means that the maximum contact stress between the lip of the spring-energized seal ring and the corresponding rigid walls on both sides must exceed the pressure of the high-pressure oil, which can be expressed as follows:

[0077] P≤min(P1,P2)

[0078] Where: P is the high-pressure oil pressure; P1 and P2 are the maximum contact pressures between the seal ring and the sliding ring walls on both sides. The physical meaning of this formula is that the maximum contact pressure stress between the left and right sides of the seal ring and the inner and outer rings must be greater than the high-pressure oil pressure to achieve a sealing effect. The maximum shear stress criterion formula is as follows

[0079] τ max ≤[τ b ]

[0080] Among them, τ max Indicates the maximum shear force of the sealing ring jacket; [τ b ] represents the ultimate shear strength of the sealing ring jacket material polytetrafluoroethylene. Based on the above sealing criteria, the finite element model is used to calculate the distribution of the contact pressure along the contact surface of the lip sealing area. The results are as follows: Figure 2 As shown, this is a schematic diagram of the relationship between the contact stress of the left and right lips of the spring energy storage seal ring and the contact position in the present application scheme, and the maximum shear stress of the jacket structure in the simulated working condition is calculated at the same time. In this example, the maximum contact stress is 22.7MPa, and the maximum shear stress is 12.1MPa. This is used as an important indicator for evaluating the health status and fault diagnosis of the spring energy storage seal ring. In the present application scheme, by combining the liquid slip ring seal failure criterion with the finite element model, the qualitative analysis criterion of the simple alarm threshold judgment standard for liquid slip ring leakage is converted into a quantitative analysis criterion, which can further improve the accuracy of fault detection of the spring energy storage seal ring in the liquid slip ring.

[0081] In a specific embodiment, if Figure 3 As shown, after executing step S102 and before executing step S103, the following steps are further included:

[0082] S201: performing simulation calculation on a target virtual entity model based on a single variable parameter to obtain corresponding multiple performance evaluation parameters;

[0083] S202: Analyzing the fluctuation range of multiple performance evaluation parameters to obtain the fluctuation range corresponding to each performance evaluation parameter;

[0084] S203: Perform weight analysis on multiple performance evaluation parameters to obtain a parameter weight corresponding to each performance evaluation parameter.

[0085] It should be noted that when the server simulates and calculates the target virtual entity model based on a single variable parameter to obtain corresponding multiple performance evaluation parameters, the active sealing oil pressure may change in actual working conditions. In the present application, the server pre-sets 10 sets of sealing oil pressure data, and the sealing oil pressure data is in the range of 0-10MPa. Furthermore, the server sets the sealing ring compression rate parameter to 5%, the elastic modulus to 488.38MPa, the Poisson's ratio parameter to 0.457, and the lip friction coefficient in the target virtual entity model to 0.2. Then, based on the sealing oil pressure data being set to the range of 0-10MPa, the server calculates the maximum shear stress value and outputs the corresponding maximum shear stress data set, wherein the maximum shear stress data set is shown in Table 1. At the same time, the shear stress cloud map of the finite element model under pressures of 0MPa, 3MPa, 6MPa, and 9MPa is selected, as shown in FIG. Figure 4 The figure shows a schematic diagram of the shear stress cloud diagram of the spring energy storage sealing ring jacket under different pressures in the present application solution.

[0086]

[0087] Table 1

[0088] According to the results, it can be seen that the maximum shear stress in the finite element model gradually increases with the increase of oil pressure. When the maximum oil pressure is set to 10 MPa, the shear stress reaches a maximum value of 16.8 MPa. At the same time, from the shear stress cloud diagram ( Figure 3 ) It can be seen that the locations with large shear stress in the finite element model are concentrated in the left and right contact area lips and the area where the back pressure ring contacts the target spring. Under several different working conditions, the maximum shear stress location basically occurs in the area where the inner ring contacts the lip, and the shear stress distribution is basically the same, such as Figure 5 Figure 2 shows the maximum contact stress curves for a spring-energized seal ring under different medium pressures. As medium pressure increases, the maximum contact pressure gradually increases, remaining significantly greater than the pressure of the transmitted medium. Numerical calculations show that the spring-energized seal ring structure maintains a good seal even at very low medium pressures.

[0089] At the same time, in the present application, the server sets 10 groups of change values ​​for the sealing ring compression rate parameter from 1% to 10%, and analyzes the numerical changes of the maximum shear stress and the maximum contact stress. Among them, the calculation results of the relationship between the sealing ring compression rate, the inner ring displacement and the maximum shear stress change in the finite element model are shown in Table 2.

[0090]

[0091] Table 2

[0092] According to the calculation results, the maximum shear stress is not sensitive to the change of the compression rate of the sealing ring. The shear stress value fluctuates repeatedly around 12.5MPa. After the compression rate exceeds 6%, the maximum shear stress has a downward trend, but remains stable overall. The reason for this problem is that the parameter elastic modulus is 488.38MPa, which is more prone to deformation than the built-in spring and the inner and outer ring structures. When the inner ring is squeezed, the entire structure undergoes a large deformation, and the external force does not cause a large internal stress. The shear stress distribution is as follows: Figure 6 The figure shows the maximum contact stress curve of the spring energy storage seal ring under different compression rates. It is worth noting that when the compression rate is less than 10%, the maximum shear stress occurs in the right lip contact area. However, when the compression rate reaches 10%, the maximum shear stress appears at the bottom of the back pressure ring and the contact part with the built-in spring. Similar to the above analysis, the reason for this is that the material undergoes large deformation, resulting in stress concentration in the area where it contacts the spring. Under different compression rates, such as Figure 7 As shown in Figure 1, it is a schematic diagram of the shear stress cloud diagram of the spring energy storage seal ring jacket at different compression rates. As the compression rate of the seal ring continues to increase, the maximum contact stress value of the lip sealing area continues to rise.

[0093] Furthermore, in the process of thermal analysis in the finite element model of the present application, the following assumptions are made: (1) Due to the slow movement of the liquid sliding ring, the heat generated by the friction between the jacket of polytetrafluoroethylene material and the inner and outer rings is ignored in the present application; (2) In the process of temperature calculation, the present application assumes that the temperature does not change with time, and a steady-state thermal analysis is performed; (3) Considering the size of the sealing ring and its long-term close contact with the high-pressure oil, when setting the temperature field in the finite element model, it is assumed that the jacket material is in a temperature state at the same time, that is, the temperature field is set to be uniformly distributed; (4) Considering that the inner and outer rings and the built-in spring are made of steel, the sensitivity of the material to temperature is much less than that of the jacket of polytetrafluoroethylene material, so the present application only considers the influence of temperature on the sealing ring jacket material; (5) In the present application, the heat transfer methods of heat convection and heat radiation are not considered.

[0094] In this application, the thermodynamic parameters of the server pair are set as follows:

[0095]

[0096] Table 3

[0097] The rest of the mechanical parameters, load settings, and structural dimensions remain unchanged. The server uses a predefined field to define the initial temperature as 0°C. Since the freezing point of crude oil transmitted by the slip ring is between -50°C and 25°C, and considering the influence of seawater temperature, the server sets the working temperature in the finite element model from 0°C to 110°C in 12 groups with an interval of 10°C to calculate the maximum shear stress, such as Figure 8 As shown in the figure, it is a schematic diagram of the Mises stress and maximum shear stress of the spring energy storage seal ring at different temperatures, as shown in the figure. Figure 9 The figure shows the schematic diagram of the maximum contact stress of the spring energy storage seal at different temperatures.

[0098] According to the calculation results, it can be seen that from 0 to 70 ° C, as the temperature rises, the maximum shear stress, maximum Mises stress (it should be noted that the maximum Mises stress is an equivalent stress based on shear strain energy), and maximum contact stress all maintain an upward trend. When the temperature exceeds 70 ° C, the changes in the stress values ​​tend to be gentle or even have a slight downward trend. The reason for this phenomenon is that the material is affected by temperature changes, and thermal expansion and contraction cause the components to squeeze each other, resulting in an increase in internal Mises stress, shear stress, and surface contact stress. However, when the thermal expansion reaches a certain value, this squeezing effect also reaches its maximum effect. If the temperature continues to increase, the structural stress value will not change significantly.

[0099] In the steps of this solution, the server performs a fluctuation range analysis on multiple performance evaluation parameters to obtain the fluctuation range corresponding to each performance evaluation parameter. Among them, the server performs a fluctuation range analysis on the transmission medium pressure, temperature, sealing ring compression rate, etc. according to the calculation results based on finite element calculation. Specifically, the server analyzes the digital characteristics of the parameters, further performs parameter standardization on the digital characteristics of the parameters, and draws a parameter relationship curve diagram to obtain the fluctuation range corresponding to each performance evaluation parameter, and performs weight analysis on multiple performance evaluation parameters to obtain the parameter weight corresponding to each performance evaluation parameter.

[0100] In a specific embodiment, if Figure 10 As shown, the process of executing step S103 may specifically include the following steps:

[0101] S301: performing unit information matching on the target virtual entity model to determine a corresponding unit information set, wherein the unit information set includes unit shape and unit type;

[0102] S302: Based on the unit set information, a preset meshing algorithm is used to match the target virtual entity model with the working environment to obtain a corresponding working environment set;

[0103] S303: Performing working condition simulation calculation on the target virtual entity model by combining the working condition environment to obtain a corresponding simulated working condition data set.

[0104] Specifically, after completing the parameter weighting of each parameter on the overall sealing performance of the target spring energy storage seal ring, this step determines the multi-parameter analysis of several physical information parameters that have a greater impact on the sealing performance of the seal ring, including but not limited to the transmission medium pressure, temperature, seal ring compression rate, etc. First, the server matches the unit information of the target virtual entity model to determine the corresponding unit information set, wherein the unit information set includes unit shape and unit type. In order to improve the analysis accuracy of the finite element model, the server controls the specific grid density, unit shape, unit type, and grid division technology of different units in the finite element model to determine the corresponding unit information set. At the same time, due to the motion characteristics of the liquid slip ring, in terms of contact analysis, the server determines the rigid components and reference points corresponding to the target virtual entity model, and defines and sets the contact properties, contact relationships, and contact surfaces. Then, based on the unit set information, the server matches the target virtual entity model to the working environment through a preset grid division algorithm to obtain the corresponding working environment set.

[0105] It should be noted that, on the basis of single variable analysis, by setting the load parameters in the finite element model, experiments are designed to simulate various working conditions that the liquid slip ring may encounter during actual operation, and working condition simulation calculations are performed to obtain the corresponding simulated working condition data set. In this application scheme, the server uses the Python language to realize the automatic output of stress calculation results, thereby obtaining a sufficient number of simulated working condition data sets.

[0106] It should be noted that when the server performs working condition simulation calculations and obtains the corresponding simulated working condition data set, the server determines the physical information parameters that affect the performance of the sealing ring as: transmission medium pressure, temperature, sealing ring compression rate, elastic modulus, and lip area friction coefficient. The settings of each parameter are shown in Table 4.

[0107]

[0108] Table 4

[0109] The server performed simulation calculations based on the parameter settings, and obtained a total of 1,440 sets of working condition data, which were used as the simulated working condition data set. In this solution, the calculation results given by the finite element model are clear, intuitive, and highly reliable. Data information that cannot be obtained by general monitoring methods can be obtained, and the operating status of the liquid slip ring under different working conditions is fully displayed, which ensures the accuracy of fault diagnosis in the subsequent fault diagnosis of the spring performance sealing ring.

[0110] In a specific embodiment, if Figure 11 As shown, the above step S104 specifically includes the following steps:

[0111] S401: Inputting a set of simulated operating condition data into a fault diagnosis model, traversing the simulated operating condition data using a non-parametric classification algorithm in the fault diagnosis model, and obtaining corresponding parameter data to be analyzed;

[0112] S402: Filtering the parameter data to be analyzed based on the fluctuation range corresponding to each performance evaluation parameter to obtain corresponding target parameter data;

[0113] S403: Perform fault diagnosis through target parameter data to obtain corresponding fault analysis results, and judge the fault analysis results to obtain corresponding judgment results, wherein the judgment results include fault and normal.

[0114] Specifically, the server performs parameter traversal on the simulated working condition data through the K-Nearest Neighbor (KNN) algorithm in the fault diagnosis model. It should be noted that the above-mentioned non-parametric classification algorithm is the KNN algorithm. The main principle of the KNN algorithm is to use training data to divide the feature vector space and use the division result as the final algorithm model. There is a sample data set, also called a training sample set, and each data in the sample set has a label. The label is used to indicate the correspondence between each data in the sample set and its corresponding classification. After inputting unlabeled data, each feature of the unlabeled data is compared with the feature corresponding to the data in the sample set, and then the classification label of the data with the closest feature in the sample (nearest neighbor) is extracted. Generally speaking, the server selects the first K most similar data in the sample data set. Finally, the category with the most occurrences in the K most similar data is selected as the classification of the new data.

[0115] Among them, since the size of the simulated working condition data set output by the finite element model is 1440 groups (of which 1228 groups are valid data), the K value is first set to 30 in the KNN algorithm. It should be noted that K is a hyperparameter in the KNN algorithm. Then, the server sets a priority queue of 30 according to the order of distance from far to near to store training data tuples, randomly selects 30 tuples from the training data tuples as the initial nearest neighbor training tuples, calculates the distance from the test tuple to these 30 tuples, and stores the training tuple label and distance in the priority queue. Further, the server traverses the training tuple set, calculates the distance between the current training tuple and the test tuple, and compares the obtained distance L with the maximum distance L in the priority queue. max Compare, if L≥L max , then discard the tuple and traverse the next data tuple. If L<L max, then delete the tuple with the maximum distance in the priority queue and store the current simulation condition data tuple into the priority queue.

[0116] After the traversal is completed, the server calculates the majority class of the 30 data tuples in the priority queue and uses it as the category of the test tuple. At the same time, the test error rate of the test tuple set is calculated. In this application scheme, when K=30, the accuracy of the calculated result is 0.943089430894309. In this application scheme, different K values ​​are continued to be set for re-training, and finally the K value with the smallest error rate is taken. After multiple calculations, in this application scheme, the final K value is selected as 52. After testing the test tuple set, it is found that its accuracy is: 0.9512195121951219, and the error is below 5%, which meets the test requirements.

[0117] It should be noted that the data size of the test tuple set also affects the accuracy value of the output. When the test tuple set is larger, the accuracy of the feedback data is closer to the actual situation. When the K value remains unchanged, the size of the test tuple is increased, and its accuracy will be lower than the test tuple with a smaller data volume. Specifically, in this solution, the server inputs the fault diagnosis model into the simulated working condition data set based on the condition setting of selecting the hyperparameter as 52, and traverses the simulated working condition data through the KNN classification algorithm in the fault diagnosis model to obtain the corresponding parameter data to be analyzed. Further, the server filters the parameter data to be analyzed based on the fluctuation range corresponding to each performance evaluation parameter to obtain the corresponding target parameter data, wherein the target parameter data includes but is not limited to the transmission medium pressure, temperature, sealing ring compression rate, elastic modulus, friction coefficient and other data. Further, the server performs fault diagnosis through the target parameter data to obtain the corresponding fault analysis result, wherein it should be noted that in the embodiment of the present application, 705 groups of problem data are finally screened out. In a specific embodiment, the above-mentioned step S105 specifically includes the following steps:

[0118] (1) When the judgment result is a fault, the fault data is matched with the fault analysis result to determine the corresponding fault data;

[0119] (2) Based on the parameter weight corresponding to each performance evaluation parameter, the fault data is subjected to root cause analysis through the decision tree algorithm of the fault diagnosis model to determine the corresponding set of fault causes.

[0120] Specifically, when the judgment result is a fault, the server matches the fault data of the fault analysis result to determine the corresponding fault data. It should be noted that the fault data here are 705 groups of fault operating condition data. Further, the server inputs the 705 groups of fault data into the preset decision tree algorithm to obtain the calculation results. It should be noted that since it is known that the parameter that has the greatest impact on the fault evaluation of the spring energy storage seal ring is the elastic modulus, the parameter weight corresponding to the pre-set performance evaluation parameter can be used to basically locate the cause of the fault and determine the target liquid slip ring fault cause set. At the same time, in the present application scheme, the fault level is also classified, as shown in Table 6.

[0121]

[0122] Table 6

[0123] The embodiment of the present invention also provides a fault diagnosis device for a spring energy storage seal ring, such as Figure 12 As shown, the fault diagnosis device of the spring energy storage seal ring specifically includes:

[0124] The acquisition module 501 is used to collect information of the target liquid slip ring and the target spring energy storage seal ring based on a preset physical entity model to obtain a corresponding entity information set;

[0125] A construction module 502 is configured to construct a finite element model using the entity information set to obtain a corresponding target virtual entity model;

[0126] A calculation module 503 is used to perform finite element numerical simulation calculations on the target virtual entity model to obtain a corresponding simulation working condition data set;

[0127] The judgment module 504 is configured to input the simulated working condition data set into a preset fault diagnosis model, perform a preliminary fault analysis on the target virtual entity model, generate a corresponding fault analysis result, and judge the fault analysis result to obtain a corresponding judgment result, wherein the judgment result includes fault and normal;

[0128] An analysis module 505 is configured to perform root cause analysis on the fault analysis result to determine a corresponding fault cause set when the judgment result is a fault;

[0129] The matching module 506 is configured to collect actual detection data corresponding to the target virtual entity model, and perform matching analysis on the fault cause set using the actual detection data to generate corresponding target fault cause data.

[0130] The further functional description of each of the above modules is the same as that of the above corresponding method embodiments and will not be repeated here.

[0131] By the coordinated cooperation of the above-mentioned components, a physical model of the spring energy storage sealing ring in the liquid lubricating ring is established, which can realize real-time monitoring of the spring performance sealing ring in the liquid lubricating ring, provide accurate data support for subsequent fault diagnosis, and improve the accuracy of fault diagnosis. By inputting the simulated working condition data set into the preset fault diagnosis model, a preliminary fault analysis is performed on the target virtual entity model, and the corresponding fault analysis results are generated. The fault analysis results are judged to obtain the corresponding judgment results, and the actual detection data corresponding to the target virtual entity model is collected, and the fault cause set is matched and analyzed through the actual detection data to generate corresponding target fault cause data. In this scheme, by adopting a fault diagnosis model with two-level comprehensive indicators, it is possible to accurately determine whether a fault occurs and give a fault level, which can further improve the accuracy of fault diagnosis of the spring performance sealing ring.

[0132] The embodiment of the present invention further provides an electronic device, such as Figure 13 As shown, the electronic device may include a processor 601 and a memory 602, wherein the processor 601 and the memory 602 may be connected via a bus or other means. Figure 6 The bus connection is taken as an example.

[0133] The processor 601 can be a central processing unit (CPU). The processor 601 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above-mentioned various chips. The memory 602, as a non-transient computer-readable storage medium, can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the method in the embodiment of the present invention. The processor 601 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory 602, that is, implementing the above-mentioned method.

[0134] The memory 602 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created by the processor 601, etc. In addition, the memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 602 may optionally include a memory remotely located relative to the processor 601, and these remote memories may be connected to the processor 601 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0135] One or more modules are stored in the memory 602 and, when executed by the processor 601 , perform the above method.

[0136] An embodiment of the present invention further provides a non-transitory computer storage medium storing computer-executable instructions that can execute the personnel counting method in any of the above method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); the storage medium can also include a combination of the above types of memory.

[0137] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0138] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A fault diagnosis method for a spring energy storage seal ring, characterized in that: The steps include: Based on the preset physical entity model, information of the target liquid slip ring and the target spring energy storage seal is collected to obtain the corresponding entity information set; Constructing a finite element model through the entity information set to obtain a corresponding target virtual entity model; Performing finite element numerical simulation calculations on the target virtual entity model to obtain a corresponding simulated working condition data set; Inputting the simulated working condition data set into a preset fault diagnosis model, performing preliminary fault analysis on the target virtual entity model, generating corresponding fault analysis results, and judging the fault analysis results to obtain corresponding judgment results, wherein the judgment results include fault and normal; When the judgment result is a fault, performing a root cause analysis on the fault analysis result to determine a corresponding fault cause set; Actual detection data corresponding to the target virtual entity model is collected, and matching analysis is performed on the fault cause set using the actual detection data to generate corresponding target fault cause data.

2. The fault diagnosis method of the spring energy storage seal ring according to claim 1 is characterized in that: The step of collecting information of the target liquid slip ring and the target spring energy storage seal ring based on the preset physical entity model to obtain corresponding entity information collection includes: Extracting identification information of the target liquid slip ring and the target spring energy storage seal ring to obtain identification information corresponding to the target liquid slip ring and the target spring energy storage seal ring; Performing storage location analysis on the preset physical entity model using the identification information to generate a corresponding information storage address; Information is collected according to the information storage address to obtain a corresponding entity information set.

3. The fault diagnosis method of the spring energy storage seal ring according to claim 1 is characterized in that: The step of constructing a finite element model using the entity information set to obtain a corresponding target virtual entity model includes: Performing feature extraction on the entity information set to obtain corresponding entity feature information; Perform parameter matching based on the entity feature information to determine corresponding entity feature parameters; A finite element model is constructed based on the entity feature parameters and the entity feature information to obtain a corresponding target virtual entity model.

4. The fault diagnosis method of the spring energy storage seal ring according to claim 1 is characterized in that: The step of performing finite element numerical simulation calculation on the target virtual entity model to obtain a corresponding simulation working condition data set includes: Performing unit information matching on the target virtual entity model to determine a corresponding unit information set, wherein the unit information set includes a unit shape and a unit type; Based on the unit set information, the target virtual entity model is matched with the working environment by a preset grid division algorithm to obtain a corresponding working environment set; The target virtual entity model is simulated and calculated by combining the working condition environment to obtain a corresponding simulated working condition data set.

5. The fault diagnosis method of the spring energy storage seal ring according to claim 1 is characterized in that: Before the step of performing finite element numerical simulation calculations on the target virtual entity model to obtain a corresponding simulation condition data set, and after the step of performing finite element model construction on the entity information set to obtain a corresponding target virtual entity model, the method further includes: Performing simulation calculation on the target virtual entity model based on a single variable parameter to obtain corresponding multiple performance evaluation parameters; Performing a fluctuation range analysis on the multiple performance evaluation parameters to obtain a fluctuation range corresponding to each performance evaluation parameter; A weight analysis is performed on the multiple performance evaluation parameters to obtain a parameter weight corresponding to each performance evaluation parameter.

6. The fault diagnosis method of the spring energy storage seal ring according to claim 5, characterized in that: The step of inputting the simulated working condition data set into a preset fault diagnosis model, performing preliminary fault analysis on the target virtual entity model, generating corresponding fault analysis results, and judging the fault analysis results to obtain corresponding judgment results, wherein the judgment results include fault and normal steps, includes: Inputting the simulated operating condition data set into the fault diagnosis model, traversing the simulated operating condition data using a non-parametric classification algorithm in the fault diagnosis model to obtain corresponding parameter data to be analyzed; Based on the fluctuation range corresponding to each of the performance evaluation parameters, the parameter data to be analyzed is screened to obtain corresponding target parameter data; Fault diagnosis is performed using the target parameter data to obtain corresponding fault analysis results, and the fault analysis results are judged to obtain corresponding judgment results, wherein the judgment results include fault and normal.

7. The fault diagnosis method for a spring energy storage seal ring according to any one of claims 5 or 6, characterized in that: When the judgment result is a fault, performing root cause analysis on the fault analysis result to determine a corresponding set of fault causes includes: When the judgment result is a fault, performing fault data matching on the fault analysis result to determine corresponding fault data; Based on the parameter weight corresponding to each of the performance evaluation parameters, a root cause analysis is performed on the fault data using a decision tree algorithm of the fault diagnosis model to determine a corresponding set of fault causes.

8. A fault diagnosis device for a spring-energy storage seal ring, used to execute the fault diagnosis method for a spring-energy storage seal ring according to any one of claims 1 to 7, characterized in that: include: An acquisition module is used to collect information about the target liquid slip ring and the target spring energy storage seal ring based on a preset physical entity model to obtain a corresponding entity information set; A construction module, configured to construct a finite element model using the entity information set to obtain a corresponding target virtual entity model; A calculation module, configured to perform finite element numerical simulation calculations on the target virtual entity model to obtain a corresponding simulation working condition data set; a judgment module, configured to input the simulated working condition data set into a preset fault diagnosis model, perform preliminary fault analysis on the target virtual entity model, generate corresponding fault analysis results, and judge the fault analysis results to obtain corresponding judgment results, wherein the judgment results include fault and normal; An analysis module, configured to, when the judgment result is a fault, perform a root cause analysis on the fault analysis result to determine a corresponding set of fault causes; The matching module is used to collect actual detection data corresponding to the target virtual entity model, and perform matching analysis on the fault cause set through the actual detection data to generate corresponding target fault cause data.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the fault diagnosis method for the spring energy storage seal ring according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the fault diagnosis method for the spring-energy storage seal ring according to any one of claims 1 to 7.

Images