Sealing structure optimization method and device for extra-high pressure wellhead equipment

Abstract

The embodiment of the application provides a sealing structure optimization method and device of extra-high pressure wellhead equipment, and relates to the technical field of oil exploitation equipment. The method converts the sealing structure to be optimized into a parameterized model and determines a control point set through curve fitting, generates initial parameters based on Cauchy distribution sampling of the control point set, reduces the number of sample points falling in the parameter boundary area by using the thick tail characteristics of Cauchy distribution, avoids the problem that the search range is limited due to the sample concentration in the boundary, makes the initial parameters more uniformly distributed in the entire parameter interval, and continuously optimizes the parameters by combining the performance evaluation values obtained by the preset simulation model through multi-stage iterative updating. Finally, the target optimization parameters can be directly used to construct the target sealing structure, and the sealing reliability of the sealing structure on the extra-high pressure wellhead equipment is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil extraction equipment, and particularly relates to a sealing structure optimization method and device for super-high pressure wellhead equipment. BACKGROUND

[0002] In oil and gas drilling and production operations, the sealing structure as the core component of the wellhead sealing system directly relates to the safety of the entire operation in the high-pressure working condition. With the continuous increase of drilling depth, the wellhead pressure continues to rise, and the performance requirements for the sealing structure are increasingly stringent. Therefore, it is crucial to optimize the sealing structure parameters to improve the high-pressure sealing reliability.

[0003] In the prior art, some research attempts to use a group intelligence algorithm to optimize the sealing structure parameters. However, in the initial parameter generation stage, most of them rely on normal distribution to extract sample points. Since the mean and variance calculation method of the normal distribution has the concentration feature, a large number of sample points fall in the boundary region of the parameters, thereby affecting the sealing reliability of the sealing structure on the super-high pressure wellhead equipment. SUMMARY

[0004] The embodiments of the present application provide a sealing structure optimization method and device for super-high pressure wellhead equipment to achieve the effect of the reliability of the sealing structure on the super-high pressure wellhead equipment.

[0005] In a first aspect, the embodiments of the present application provide a sealing structure optimization method for super-high pressure wellhead equipment, comprising: converting a to-be-optimized sealing structure into a parameterized model through curve fitting, and determining a control point set of the parameterized model; sampling the control point set based on Cauchy distribution to generate multiple groups of initial parameters; inputting the multiple groups of initial parameters into a preset simulation model respectively to obtain first performance evaluation values corresponding to each group of initial parameters; iteratively updating each group of initial parameters according to the first performance evaluation values and a preset update strategy until a first convergence condition is met, and outputting multiple groups of basic sealing performance parameters; inputting the multiple groups of basic sealing performance parameters into the preset simulation model respectively to obtain second performance evaluation values corresponding to each group of basic sealing performance parameters; iteratively updating the multiple groups of basic sealing performance parameters according to the second performance evaluation values and a preset rule until a second convergence condition is met, and outputting multiple groups of reinforced sealing performance parameters; inputting the multiple groups of reinforced sealing performance parameters into the preset simulation model respectively to obtain third performance evaluation values corresponding to each group of reinforced sealing performance parameters; processing the multiple groups of reinforced sealing performance parameters according to the third performance evaluation values and a preset screening strategy to obtain multiple groups of reliable adaptive parameters; inputting the multiple groups of reliable adaptive parameters into the preset simulation model respectively to obtain fourth performance evaluation values corresponding to each group of reliable adaptive parameters; sorting the multiple groups of reliable adaptive parameters according to the fourth performance evaluation values to obtain target optimization parameters; and constructing a target sealing structure according to the target optimization parameters.

[0006] In one possible implementation, the initial parameters of each group are iteratively updated according to a first performance evaluation value and a preset update strategy until a first convergence condition is met, and multiple sets of basic sealing performance parameters are output. This includes: sorting the initial parameters according to the first performance evaluation value and dividing the multiple initial parameters into dominant parameters and follower parameters according to a first preset scaling factor; iteratively executing the following steps based on the dominant parameters and follower parameters: updating the dominant parameters for any group of dominant parameters based on a preset step size to obtain the updated dominant parameters; inputting the updated dominant parameters into a preset simulation model to obtain the performance evaluation value corresponding to the updated dominant parameters; if the performance evaluation value corresponding to the updated dominant parameters is better than the performance evaluation value corresponding to the original dominant parameters... Then, the updated dominant parameter replaces the previous dominant parameter; for any group of follower parameters, the update step size is determined based on the distance between the follower parameter and the parameter space boundary, and the updated parameter value is calculated according to the update step size, where the parameter space boundary is the upper and lower limits of the initial parameter value range; according to the first preset judgment rule and the updated parameter value, each group of follower parameters is updated to obtain the updated follower parameters; according to the performance evaluation value corresponding to each group of updated parameters, the updated group of parameters is sorted, and each group of parameters is divided into dominant parameters and follower parameters according to the first preset scaling factor; it is determined whether the number of iterations has reached the first threshold; if the number of iterations has reached the first threshold, the updated group of parameters is used as multiple groups of basic sealing performance parameters and output.

[0007] In one possible implementation, multiple sets of basic sealing performance parameters are iteratively updated according to a second performance evaluation value and a preset rule until a second convergence condition is met, and multiple sets of enhanced sealing performance parameters are output. This includes: sorting the multiple sets of basic sealing performance parameters according to the second performance evaluation value, and dividing the multiple sets of basic sealing performance parameters into dominant parameters and follower parameters according to a second preset scaling factor; iteratively executing the following steps based on the dominant parameters and follower parameters: for any set of follower parameters, randomly selecting any set of dominant parameters, and calculating updated parameter values ​​based on any set of dominant parameters; updating each set of follower parameters according to the second preset judgment rule and the updated parameter values ​​to obtain updated follower parameters; inputting the dominant parameters and updated follower parameters into a preset simulation model to obtain performance evaluation values ​​corresponding to each set of updated parameters; sorting the updated sets of parameters based on the performance evaluation values ​​corresponding to each set of updated parameters, and dividing the updated sets of parameters into dominant parameters and follower parameters according to a second preset scaling factor; determining whether the number of iterations reaches a second threshold; if the number of iterations reaches the second threshold, then the updated sets of parameters are used as multiple sets of enhanced sealing performance parameters and output.

[0008] In one possible implementation, multiple sets of enhanced sealing performance parameters are processed according to a third performance evaluation value and a preset screening strategy to obtain multiple sets of reliable adaptation parameters. This includes: sorting the multiple sets of enhanced sealing performance parameters according to the third performance evaluation value, and dividing the multiple sets of enhanced sealing performance parameters into dominant parameters and follower parameters according to a third preset scaling factor; generating multiple sets of new parameters for any given set of dominant parameters; inputting the multiple sets of new parameters into a preset simulation model to obtain the performance evaluation value corresponding to each set of new parameters; for each set of new parameters, if the performance evaluation value of a new parameter is better than the performance evaluation value of the corresponding dominant parameter, then the new parameter replaces the follower parameter with the smallest current performance evaluation value; after processing the new parameters corresponding to each set of dominant parameters, the current sets of parameters are determined as multiple sets of reliable adaptation parameters.

[0009] In one possible implementation, the sealing structure to be optimized is transformed into a parametric model by curve fitting, and the control point set of the parametric model is determined, including: obtaining the coordinate points of the cross-sectional curve of the sealing structure to be optimized; fitting the coordinate points with a B-spline curve to generate a parametric model corresponding to the cross-sectional curve; extracting the feature control points in the parametric model, and determining the coordinate parameters of the feature control points as the control point set of the parametric model.

[0010] Secondly, embodiments of this application provide a sealing structure optimization device for ultra-high pressure wellhead equipment, comprising: a control point set determination module, used to convert the sealing structure to be optimized into a parameterized model through curve fitting, and determine the control point set of the parameterized model; an initial parameter sampling module, used to sample the control point set based on Cauchy distribution to generate multiple sets of initial parameters; a first performance evaluation value acquisition module, used to input the multiple sets of initial parameters into a preset simulation model to obtain the first performance evaluation value corresponding to each set of initial parameters; a basic sealing performance parameter output module, used to iteratively update each set of initial parameters according to the first performance evaluation value and a preset update strategy until a first convergence condition is met, and output multiple sets of basic sealing performance parameters; a second performance evaluation value acquisition module, used to input the multiple sets of basic sealing performance parameters into a preset simulation model to obtain the second performance evaluation value corresponding to each set of basic sealing performance parameters; and an enhanced sealing performance parameter output module. The system comprises the following modules: a first module for iteratively updating multiple sets of basic sealing performance parameters based on a second performance evaluation value and preset rules until a second convergence condition is met, outputting multiple sets of enhanced sealing performance parameters; a second module for obtaining a third performance evaluation value, inputting multiple sets of enhanced sealing performance parameters into a preset simulation model to obtain the third performance evaluation value corresponding to each set of enhanced sealing performance parameters; a third module for outputting multiple sets of reliable adaptation parameters, processing multiple sets of enhanced sealing performance parameters based on the third performance evaluation value and a preset screening strategy to obtain multiple sets of reliable adaptation parameters; a fourth module for obtaining a fourth performance evaluation value, inputting multiple sets of reliable adaptation parameters into a preset simulation model to obtain the fourth performance evaluation value corresponding to each set of reliable adaptation parameters; a fourth module for determining target optimization parameters, sorting multiple sets of reliable adaptation parameters based on the fourth performance evaluation value to obtain target optimization parameters; and a fifth module for constructing a target sealing structure based on the target optimization parameters.

[0011] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0012] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0013] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0014] The sealing structure optimization method and apparatus for ultra-high pressure wellhead equipment provided in this application converts the sealing structure to be optimized into a parameterized model and determines a set of control points through curve fitting. Initial parameters are generated by sampling the control point set based on the Cauchy distribution. By utilizing the thick tail characteristic of the Cauchy distribution, the number of sample points falling in the parameter boundary region is reduced, avoiding the problem of limited search range caused by samples being concentrated at the boundary. This makes the initial parameters more evenly distributed throughout the parameter range. Through multi-stage iterative updates, the parameters are continuously optimized by combining the performance evaluation values ​​obtained from the preset simulation model. The final target optimized parameters can be directly used to construct the target sealing structure, effectively improving the sealing reliability of the sealing structure on ultra-high pressure wellhead equipment. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] Figure 1 A schematic diagram illustrating a scenario for optimizing the sealing structure of ultra-high voltage wellhead equipment provided in this application embodiment;

[0017] Figure 2 A flowchart illustrating the method for optimizing the sealing structure of ultra-high voltage wellhead equipment provided in this application embodiment;

[0018] Figure 2a This is a schematic diagram comparing the parameter search distribution provided in the embodiments of this application;

[0019] Figure 2b Schematic diagram of iteration time curves for different implementation methods provided in the embodiments of this application;

[0020] Figure 2c A schematic diagram of the global optimal iteration curves for different implementation methods provided in the embodiments of this application;

[0021] Figure 2d A schematic diagram of the contemporary optimal iteration curves for different implementation methods provided in the embodiments of this application;

[0022] Figure 2e A schematic diagram comparing the time consumption of different implementation methods provided in the embodiments of this application;

[0023] Figure 3 A schematic diagram of the sealing structure optimization device for ultra-high voltage wellhead equipment provided in this application embodiment;

[0024] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0025] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0027] To clearly understand the technical solution of this application, the existing technology solutions are first described in detail. In oil and gas drilling and production operations, the sealing structure, as the core component of the wellhead sealing system, directly affects the safety of the entire operation under high-pressure conditions. As drilling depth increases, wellhead pressure continues to rise, and the performance requirements for the sealing structure become increasingly stringent. Therefore, optimizing the sealing structure parameters to improve its high-pressure sealing reliability is crucial. In the existing technology, some studies have attempted to use swarm intelligence algorithms to optimize the sealing structure parameters. However, the sealing design of ultra-high pressure wellhead equipment has high dimensionality, and the value range of each dimension varies greatly. In the initial parameter generation stage, swarm intelligence algorithms mostly rely on normal distribution to extract sample points. Since the mean and variance calculation method of the normal distribution has a concentration characteristic, a large number of sample points fall in the boundary region of the parameters, making it difficult to quickly find the number of sealing structures that meet the sealing performance requirements under high-pressure conditions, thus affecting the sealing reliability of the sealing structure in ultra-high pressure wellhead equipment.

[0028] To address the aforementioned technical challenges, a Cauchy distribution with tail characteristics can be used for sampling. Leveraging its more dispersed sample point distribution, initial parameters can uniformly cover the parameter space, reducing boundary clustering issues. Simultaneously, considering the need for progressively improving sealing structure parameters, a multi-stage iterative strategy can be designed. First, differentiated management of dominant and follower parameters, combined with dynamic updates based on performance evaluation values, generates a parameter set with basic sealing performance. Then, based on these basic sealing performance parameters, follower parameters are updated specifically by referencing the characteristics of the dominant parameters, resulting in enhanced sealing performance parameters. Finally, through adaptation adjustments, reliable adaptable parameters that can be directly used to construct the sealing structure are obtained. By focusing on different optimization objectives in stages, the comprehensiveness of parameter exploration is ensured while progressively improving sealing performance, ultimately enhancing the reliability of the sealing structure in ultra-high pressure wellhead equipment.

[0029] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0030] Figure 1 This is a schematic diagram illustrating a scenario for the method of optimizing the sealing structure of ultra-high voltage wellhead equipment provided in this application embodiment, such as... Figure 1 As shown, the specific application scenarios of this application include: receiving device 101, processing device 102 and display device 103.

[0031] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the method for optimizing the sealing structure of ultra-high voltage wellhead equipment. In other feasible embodiments of this application, the above architecture may include more or fewer components than illustrated, or combine some components, or split some components, or arrange different components, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of both.

[0032] In the specific implementation process, the receiving device 101 can be an input / output interface or a communication interface, used to receive the sealing structure to be optimized.

[0033] The processing device 102 can transform the sealing structure to be optimized into a parametric model through curve fitting, determine the control point set of the parametric model, obtain the target optimization parameters by performing a series of processing on the control point set, and construct the target sealing structure based on the target optimization parameters.

[0034] The display device 103 can be used to display the target sealing structure.

[0035] The display device can also be a touch screen, used to receive user commands while displaying the above content, so as to realize the operation interaction with the user.

[0036] Figure 2 A flowchart illustrating the method for optimizing the sealing structure of ultra-high voltage wellhead equipment provided in this application embodiment is shown below. Figure 2 As shown, the method includes:

[0037] S201: The sealing structure to be optimized is transformed into a parametric model through curve fitting, and the control point set of the parametric model is determined.

[0038] Specifically, the process of determining the control point set of the parameterized model includes Sa1~Sa3:

[0039] Sa1: Obtain the coordinates of the cross-sectional curve of the sealing structure to be optimized.

[0040] Specifically, the cross-sectional curve of the sealed structure is obtained by scanning, and multiple coordinate points on the cross-sectional curve are extracted.

[0041] For example, taking the double U-shaped wellhead sealing structure as the object to be optimized, the process of determining the control point set of the parameterized model includes: sampling 50 coordinate points at intervals of 0.2 mm, wherein the coordinate point data includes the coordinate values ​​of the apex of the U-shaped groove, the inner inflection point of the U-shape, and the starting point of the outer arc.

[0042] Sa2: By fitting the coordinate points with a B-spline curve, a parametric model corresponding to the cross-sectional curve is generated.

[0043] Specifically, a 3rd-order B-spline curve was used to fit the collected coordinate points of 50. The curve order was set to 3, and the node vectors were generated in a uniform distribution. The curve parameters were adjusted by the least squares method to control the deviation between the fitted curve and the original cross-sectional curve within 0.05 mm, thereby generating a parametric model of the double U-shaped sealed structure cross-section.

[0044] Sa3: Extract the feature control points in the parametric model and determine the coordinate parameters of the feature control points as the control point set of the parametric model.

[0045] Specifically, multiple feature control points are extracted from the parametric model. For example, in a double U-shaped sealing structure, the feature control points include vertices, inflection points, and the midpoint of the arc. The coordinate parameters of the multiple feature control points are determined as the control point set of the parametric model.

[0046] S202: Based on the Cauchy distribution, the control point set is sampled to generate multiple sets of initial parameters.

[0047] Specifically, for a given set of control points, the value range of each control point is first defined. For example, the coordinates of the first control point are x∈[8,12] mm and y∈[4.6] mm. Then, random sampling is performed based on the Cauchy distribution within the value range of each control point. Each sampling generates a complete set of coordinate values ​​for multiple control points. This process is repeated until a preset number of parameter combinations are obtained. The preset number of parameter combinations are defined as multiple sets of initial parameters. For example, 50 sets of initial parameters are generated, each set containing the specific coordinate values ​​of 12 feature control points.

[0048] S203: Input multiple sets of initial parameters into the preset simulation model to obtain the first performance evaluation value corresponding to each set of initial parameters.

[0049] The preset simulation model is a finite element simulation model. The design process of the finite element simulation model is as follows: A two-dimensional axisymmetric model of the sealing structure to be optimized is established. Components that cooperate with the sealing structure, such as the hanger and casing head, are set as analytical rigid bodies, while only the sealing structure to be optimized is modeled as a deformable body. For example, taking a double U-shaped sealing structure, the hanger and casing head are key components that directly cooperate with the double U-shaped sealing structure, together constituting the wellhead sealing system. The casing head, as the basic component of the wellhead, provides the installation reference for the entire wellhead sealing system; the hanger is used to suspend the downhole casing, and its outer wall forms an annular space with the inner wall of the casing head. The double U-shaped sealing structure is installed within this annular space, and through its own deformation, it tightly fits the contact surfaces of the hanger and casing head, achieving a seal in the annular space.

[0050] The simulation analysis of the finite element simulation model is divided into two steps. The first step is to simulate the pre-tightening condition through interference fit to obtain the initial contact state between the sealing structure to be optimized and the rigid component. The second step is to automatically extract performance indicators such as equivalent stress, contact stress, and effective sealing length based on the contact stress results obtained in the first step using a script. Furthermore, the sealing performance evaluation position is automatically determined through path extraction and cutting point calculation, and the effective sealing length of 8 positions is extracted. This length is the length of the contact stress range greater than 350MPa.

[0051] Specifically, the initial parameters of each group are input into the preset simulation model, the structural dimensions of the sealing structure to be optimized are updated, and after the model runs, the effective sealing length, equivalent stress, contact stress and other indicators of the 8 evaluation positions are automatically extracted. These data are then comprehensively calculated to obtain the first performance evaluation value corresponding to each group of initial parameters.

[0052] S204: Iteratively update each set of initial parameters according to the first performance evaluation value and the preset update strategy until the first convergence condition is met, and output multiple sets of basic sealing performance parameters.

[0053] Specifically, the optimization process for multiple sets of basic sealing performance parameters includes:

[0054] Sb01: Sort the initial parameters of each group according to the first performance evaluation value, and divide the multiple initial parameters into dominant parameters and follower parameters according to the first preset scaling factor.

[0055] Specifically, all initial parameters are sorted from highest to lowest according to the first performance evaluation value, and then divided into dominant parameters and follower parameters using a first preset scaling factor. The first preset scaling factor is 2 by default. For example, for 50 sets of initial parameters, the first 25 sets of initial parameters sorted from highest to lowest are defined as dominant parameters, and the remaining 25 sets are defined as follower parameters.

[0056] Sb02: Based on the dominant parameter and the follower parameter, iteratively execute the following steps:

[0057] Sb03: For any set of dominant parameters, update the dominant parameters based on a preset step size to obtain the updated dominant parameters.

[0058] Specifically, for any set of dominant parameters, the position is updated according to a preset fixed small step size. For example, for the dominant parameter of the control point coordinate (10,5) of the double U-shaped sealing structure, the step size is set to ±0.02mm, then the updated dominant parameter may be (10.2,5) or (9.8,5).

[0059] Sb04: Input the updated dominant parameters into the preset simulation model to obtain the performance evaluation values ​​corresponding to the updated dominant parameters.

[0060] Specifically, the updated dominant parameters are input into the structural dimensions of the sealing structure of the preset simulation model. After the model runs, the effective sealing length, equivalent stress, contact stress and other indicators at the eight evaluation positions are automatically extracted. These data are then comprehensively calculated to obtain the performance evaluation values ​​corresponding to the updated dominant parameters.

[0061] Sb05: If the performance evaluation value corresponding to the updated dominant parameter is better than the performance evaluation value corresponding to the original dominant parameter, then the updated dominant parameter will replace the original dominant parameter.

[0062] Specifically, if the performance evaluation value corresponding to the updated dominant parameter is better than that before the update, it means that the dominant parameter has moved to a better position with this small step, so the updated dominant parameter replaces the one before the update; otherwise, the original dominant parameter is retained.

[0063] Sb06: For any set of following parameters, determine the update step size based on the distance between the following parameters and the parameter space boundary, and calculate the updated parameter value based on the update step size, where the parameter space boundary is the upper and lower limits of the initial parameter value range.

[0064] Specifically, the update step size of the following parameter is based on the shortest distance to the parameter space boundary in different dimensions. For example, if the current value of a following parameter in the x-dimensional dimension is 5.5mm, and the parameter space boundary is 5mm and 7mm, then the distance between this value and the lower limit is 0.5mm, and the distance to the upper limit is 1.5mm. The shortest distance of 0.5mm is taken to determine the floating-point number of the update step size. The update step size is determined by multiplying the random floating-point number sampled from the standard Cauchy distribution that follows the probability density function with the update compensation floating-point number. The update parameter value is obtained by summing the update step size with the current value.

[0065] Sb07: Based on the first preset judgment rule and the updated parameter value, update the following parameters of each group to obtain the updated following parameters.

[0066] Specifically, for each set of following parameters, in the first 80% of the iteration, there is a 20% probability that the following parameters are directly updated based on the updated parameter value; and an 80% probability that if the performance evaluation value corresponding to the updated parameter value is better than the performance evaluation value corresponding to the following parameters before the update, then the following parameters are updated based on the updated parameter value. In the last 20% of the iteration, if the performance evaluation value corresponding to the updated parameter value is better than the performance evaluation value corresponding to the following parameters before the update, then the following parameters are updated based on the updated parameter value.

[0067] Sb08: Based on the performance evaluation values ​​corresponding to each updated set of parameters, sort the updated set of parameters and divide each set of parameters into dominant parameters and follower parameters according to the first preset scaling factor.

[0068] Specifically, after each iteration, all the updated parameters are input into the simulation model, the performance evaluation values ​​are recalculated and sorted, and the updated parameters are still divided into dominant parameters and follower parameters according to the first preset scaling factor.

[0069] Sb09: Determine if the number of iterations has reached the first threshold.

[0070] Specifically, a counter records the number of iterations. If a first threshold, such as 100 iterations, is reached, the iteration stops. Alternatively, if the performance evaluation value of all parameters increases by less than 0.5% during a preset number of consecutive iterations, the convergence condition is also considered met.

[0071] Sb10: If the number of iterations reaches the first threshold, the updated parameters will be used as multiple sets of basic sealing performance parameters and output.

[0072] Specifically, when the iteration terminates, the multiple sets of basic sealing performance parameters output have relatively stable sealing capabilities under actual working conditions.

[0073] S205: Input multiple sets of basic sealing performance parameters into the preset simulation model to obtain the second performance evaluation value corresponding to each set of basic sealing performance parameters.

[0074] Specifically, the output of multiple sets of basic sealing performance parameters is input into a preset simulation model. When the model runs, it re-simulates the high-pressure sealing condition based on the geometric data of the sealing structure cross-section corresponding to each set of basic sealing performance parameters, calculates indicators such as effective sealing length and the proportion of contact stress above 350MPa, and calculates the second performance evaluation value corresponding to each set of basic sealing performance parameters by combining these indicators.

[0075] S206: Iteratively update multiple sets of basic sealing performance parameters according to the second performance evaluation value and preset rules until the second convergence condition is met, and output multiple sets of enhanced sealing performance parameters.

[0076] Specifically, the optimization process for multiple sets of enhanced sealing performance parameters includes:

[0077] Sc1: Sort multiple sets of basic sealing performance parameters according to the second performance evaluation value, and divide the multiple sets of basic sealing performance parameters into dominant parameters and follower parameters according to the second preset scaling factor.

[0078] Specifically, based on the obtained second performance evaluation values, multiple sets of basic sealing performance parameters are sorted from high to low. According to a second preset scaling factor, the top-ranked parameters are designated as dominant parameters, and the rest as follower parameters. For example, for 30 sets of basic sealing performance parameters, with a second preset scaling factor of 10, the top 3 sets of basic sealing performance parameters are selected as dominant parameters, and the remaining 27 sets are follower parameters.

[0079] Sc2: Based on the dominant and follower parameters, iteratively execute the following steps:

[0080] Sc3: For any set of follower parameters, randomly select any set of dominant parameters, and calculate the updated parameter value based on the set of dominant parameters.

[0081] Specifically, for any set of following parameters, a set is randomly selected from the set of dominant parameters, and the updated parameter values ​​are calculated according to the following formula:

[0082]

[0083] In the formula, This is the current following parameter; GBH is a vector consisting of real numbers 1 and -1. It is a randomly selected dominant parameter. This updates the parameter value, where r is the random perturbation factor.

[0084] Sc4: Based on the second preset judgment rule and the updated parameter value, update the following parameters of each group to obtain the updated following parameters.

[0085] Specifically, the dominant parameter remains unchanged. During the first 80% of the iteration, the follower parameter is updated directly based on the updated parameter value 60% of the time, and updated based on the updated parameter value 40% of the time if the performance evaluation value corresponding to the updated parameter value is better than the performance evaluation value corresponding to the follower parameter before the update. During the last 20% of the iteration, the follower parameter is updated based on the updated parameter value if the performance evaluation value corresponding to the updated parameter value is better than the performance evaluation value corresponding to the follower parameter before the update.

[0086] Sc5: Input the dominant parameter and the updated follower parameter into the preset simulation model to obtain the performance evaluation values ​​corresponding to each set of updated parameters.

[0087] Specifically, the unadjusted dominant parameters and the updated follower parameters are input into the preset simulation model, and the model re-simulates the high-pressure sealing condition, calculates and outputs the performance evaluation values ​​corresponding to each set of parameters.

[0088] Sc6: Based on the performance evaluation values ​​corresponding to each updated set of parameters, sort the updated set of parameters and divide them into dominant parameters and follower parameters according to the second preset scaling factor.

[0089] Specifically, based on the updated performance evaluation values ​​of each group of parameters, all parameters are re-sorted from high to low, and then the dominant parameters and follower parameters are re-divided according to the second preset scaling factor.

[0090] Sc7: Determine if the number of iterations has reached the second threshold.

[0091] Specifically, a counter records the number of iterations to determine whether the current iteration count has reached the second threshold, such as 80. If it has, it means that the parameter optimization is sufficient and the iteration can be stopped; if it has not, the above iteration steps are repeated.

[0092] Sc8: If the number of iterations reaches the second threshold, the updated parameters will be used as multiple sets of enhanced sealing performance parameters and output.

[0093] Specifically, when the number of iterations reaches the second threshold, the iteration stops, and the updated parameters output at this time are multiple sets of enhanced sealing performance parameters.

[0094] S207: Input multiple sets of enhanced sealing performance parameters into the preset simulation model to obtain the third performance evaluation value corresponding to each set of enhanced sealing performance parameters.

[0095] Specifically, multiple sets of enhanced sealing performance parameters obtained through iterative optimization are input one by one into the preset simulation model. Based on the sealing structure characteristics corresponding to each set of parameters, the model will re-simulate more stringent high-pressure sealing conditions, calculate in-depth evaluation indicators such as contact stress distribution uniformity, effective sealing length retention rate under extreme conditions, and equivalent stress peak control level, and synthesize these indicators to derive the third performance evaluation value corresponding to each set of parameters.

[0096] S208: Based on the third performance evaluation value and the preset screening strategy, multiple sets of enhanced sealing performance parameters are processed to obtain multiple sets of reliable adaptation parameters.

[0097] Specifically, the optimization process for multiple sets of reliable adaptation parameters includes:

[0098] Sd1: Sort multiple sets of enhanced sealing performance parameters according to the third performance evaluation value, and divide the multiple sets of enhanced sealing performance parameters into dominant parameters and follower parameters according to the third preset scaling factor.

[0099] Specifically, multiple sets of enhanced sealing performance parameters are sorted from high to low according to the third performance evaluation value, and then divided according to the third preset scaling factor. The parameters ranked first are the dominant parameters, and the rest are the follower parameters. For example, in this embodiment, the third preset scaling factor is 10. For 30 sets of enhanced sealing performance parameters, the first 3 sets are the dominant parameters, and the last 27 sets are the follower parameters.

[0100] Sd2: Generates multiple new sets of parameters for any set of dominant parameters.

[0101] Specifically, for any set of dominant parameters, five new sets of parameters are generated according to the following formula:

[0102]

[0103]

[0104]

[0105]

[0106]

[0107] In the formula, This represents the i-th new parameter group. Indicates the dominant parameter, This represents the smallest integer greater than x. This indicates that the largest integer less than x is returned. Int(x) returns the integer part of x, and Fra(x) returns the fractional part of x. P1 and P2 are weighting coefficients. express and A one-to-one mapping relationship.

[0108] Sd3: Input multiple sets of new parameters into the preset simulation model to obtain the performance evaluation values ​​corresponding to each set of new parameters.

[0109] Specifically, the five newly generated sets of parameters are input into the preset simulation model to simulate high-pressure sealing conditions, calculate indicators such as contact stress and effective sealing length, and obtain their respective performance evaluation values.

[0110] Sd4: For each new parameter group, if the performance evaluation value of the new parameter is better than the performance evaluation value of the corresponding dominant parameter, then the new parameter is used to replace the follower parameter with the smallest current performance evaluation value.

[0111] Specifically, for each new set of parameters, if its performance evaluation value is better than the corresponding dominant parameter, then the set with the smallest performance evaluation value among the current follower parameters is replaced with the new parameter.

[0112] Sd5: After processing the new parameters corresponding to each group of dominant parameters, the current group of parameters is determined as multiple reliable adaptation parameters.

[0113] Specifically, repeat the process from Sd2 to Sd4 until all dominant parameters have been processed. Once all the new parameters corresponding to the dominant parameters have been processed, all the parameters at this point constitute multiple sets of reliable adaptation parameters.

[0114] S209: Input multiple sets of reliable adaptation parameters into the preset simulation model to obtain the fourth performance evaluation value corresponding to each set of reliable adaptation parameters.

[0115] Specifically, multiple sets of reliable adaptation parameters are input into the preset simulation model. When the model runs, it will re-simulate the high-pressure sealing condition based on the geometric data of the sealing structure section corresponding to each set of basic sealing performance parameters, calculate indicators such as effective sealing length and the proportion of contact stress above 350MPa, and calculate the fourth performance evaluation value corresponding to each set of basic sealing performance parameters by combining these indicators.

[0116] S210: Sort multiple sets of reliable adaptation parameters according to the fourth performance evaluation value to obtain the target optimization parameters.

[0117] Specifically, based on the fourth performance evaluation value, multiple sets of reliable adaptation parameters are sorted from high to low, and the parameter ranked in the first group is the target optimization parameter.

[0118] S211: The target sealing structure is constructed based on the target optimization parameters.

[0119] Specifically, the target optimization parameters include the cross-sectional geometric data of the sealing structure. Based on this data, a three-dimensional model of the sealing structure is generated in three-dimensional modeling software, and finally a target sealing structure that can be directly used for production and manufacturing is obtained.

[0120] In summary, curve fitting transforms the sealing structure to be optimized into a parameterized model and determines the control point set. Initial parameters are generated by sampling the control point set based on the Cauchy distribution. The thick-tailed characteristic of the Cauchy distribution reduces the number of sample points falling in the parameter boundary region, avoiding the problem of limited search range caused by samples being concentrated at the boundary. This makes the initial parameters more evenly distributed throughout the parameter range. Through multi-stage iterative updates and combined with the performance evaluation values ​​obtained from the preset simulation model, the parameters are continuously optimized. The final target optimized parameters can be directly used to construct the target sealing structure, effectively improving the sealing reliability of the sealing structure in ultra-high pressure wellhead equipment.

[0121] Table 1 shows the performance comparison results between the improved swarm robot search and rescue algorithm provided in the embodiments of this application and the traditional robot search and rescue algorithm.

[0122] Table 1: Performance Comparison Results of Improved Swarm Robot Search and Rescue Algorithm and Traditional Robot Search and Rescue Algorithm

[0123]

[0124] The solution result refers to the sum of the maximum equivalent stresses in the preset simulation model corresponding to the target optimization parameters of the target sealing structure.

[0125] As shown in Table 1, the running time for finding the target optimization parameters based on the improved swarm robot search and rescue algorithm is 28.7% faster than that based on the traditional robot search and rescue algorithm. The target optimization parameters based on the traditional robot search and rescue algorithm get stuck in a local optimum and begin ineffective computation after 48 iterations, while the target optimization parameters based on the improved swarm robot search and rescue algorithm can still update the optimal solution after 272 iterations. This indicates that the improved swarm robot search and rescue algorithm performs better in both search efficiency and optimization capability. The sum of the maximum equivalent stresses of the target parameters found by the improved swarm robot search and rescue algorithm in the preset simulation model is significantly lower than that of the target optimization parameters found by the traditional robot search and rescue algorithm in the preset simulation model. This suggests that the target sealing structure exhibits less stress concentration under pre-tightening and pressure conditions in the preset simulation model, resulting in stronger structural strength and less susceptibility to plastic deformation failure or damage.

[0126] Figure 2a This is a schematic diagram comparing the parameter search distribution provided in the embodiments of this application. For example... Figure 2a As shown, the left figure is a parameter search distribution map based on the traditional robot search and rescue algorithm, and the right figure is a parameter search distribution map based on the improved swarm robot search and rescue algorithm provided in this application embodiment. In the figures, black dots represent following parameters, and red dots represent dominant parameters. In the visualization of the traditional robot search and rescue algorithm, following parameters are mostly clustered at the search boundary, and the number of dominant parameters remains constant at one with minimal positional variation. However, in the visualization of the improved swarm robot search and rescue algorithm provided in this application embodiment, following parameters gradually concentrate towards high-quality areas, and the number of dominant parameters adaptively adjusts according to search requirements.

[0127] Figure 2b Schematic diagrams of iteration time curves for different implementation methods provided in the embodiments of this application, such as... Figure 2bAs shown, the horizontal axis represents the number of iterations, and the vertical axis represents the time consumed. The black curve represents the traditional robot search and rescue algorithm, denoted by SRSR; the red curve represents the improved swarm robot search and rescue algorithm provided in this application embodiment, denoted by ISRSR. ISRSR generates more follower parameters based on the dominant parameter and runs in a single thread, theoretically resulting in a longer computation time per generation. However, because the test function is calculated quickly and is unaffected by input values, its computational efficiency advantage is not apparent. In practical scenarios of sealed structure performance optimization, the performance evaluation value of each set of parameters takes 3-15 minutes to calculate. If the performance evaluation value is calculated in parallel, the additional computational load of ISRSR has a far smaller impact on the computation time per generation than the time consumption caused by the inherent defects of the SRSR algorithm itself.

[0128] Figure 2c This diagram illustrates the globally optimal iterative curves for different implementation methods provided in the embodiments of this application. Global optimality refers to the optimal solution found during historical execution. For example... Figure 2c As shown, traditional robot search and rescue algorithms are represented by SRSR, while the improved swarm robot search and rescue algorithm provided in this application embodiment is represented by ISRSR. The global optimum of ISRSR converges faster and more smoothly, and the final solution found is of higher quality.

[0129] Figure 2d This diagram illustrates the contemporary optimal iteration curves for different implementation methods provided in the embodiments of this application. Contemporary optimal refers to the optimal solution found in each generation. For example... Figure 2d As shown, traditional robot search and rescue algorithms are represented by SRSR, while the improved swarm robot search and rescue algorithm provided in this application embodiment is represented by ISRSR. ISRSR saves the best solutions found in the past, while SRSR loses the best solutions found in the past.

[0130] Figure 2e This diagram illustrates a comparison of the time consumption of different implementation methods provided in the embodiments of this application. Figure 2e As shown, the horizontal axis represents the number of iterations, and the vertical axis represents the computation time. The red curve represents the traditional robot search and rescue algorithm, denoted by SRSR; the black curve represents the improved swarm robot search and rescue algorithm provided in this application embodiment, denoted by ISRSR. During the 300 iterations, the computation time of the SRSR algorithm fluctuated significantly and was generally high, with frequent large peaks. The computation time of the ISRSR algorithm was relatively more stable; although it also fluctuated, the peak values ​​and overall time were significantly lower than those of SRSR.

[0131] In this application embodiment, a double U-shaped metal sealing structure based on an improved swarm robot search and rescue algorithm is provided. Table 2 shows the comparison results of the initial parameters and target parameters of the double U-shaped metal sealing structure provided in this application embodiment.

[0132] Table 2: Comparison of initial and target parameters of the double U-shaped metal sealing structure

[0133]

[0134] As shown in Table 2, the initial structures corresponding to the initial parameters before optimization show that control points 5-8 and 15-17 are relatively dispersed in the X-coordinate, while the X-coordinates of the optimized structures corresponding to the target parameters after optimization show a more concentrated adjustment trend. By slightly contracting or expanding, the double U-shaped metal seal structure is made smoother in high-stress areas, such as the bottom of the U-shaped groove, reducing stress concentration caused by structural abrupt changes. The Y-coordinate affects the cross-sectional height and curvature of the double U-shaped metal seal structure. The Y-coordinates of control points 1-3 and 36 are slightly adjusted from 3mm to 2.5207mm, reducing the initial height of the double U-shaped metal seal structure and reducing excessive deformation during pre-tightening. The Y-coordinate of control point 4, where stress is concentrated during the pressure bearing stage, is adjusted from 6.0642mm to 6.5518mm, and the Y-coordinate of control point 35 is adjusted from 6.0642mm to 6.5002mm, increasing the curvature radius of the double U-shaped metal seal structure and making the stress distribution under pressure load more reasonable. In the initial structure, there are slight differences in the Y coordinates of some symmetrical control points, such as control points 2 and 19. In the optimized structure, the Y coordinates of the symmetrical control points are more consistent, which reduces the problem of insufficient local contact stress caused by asymmetrical deformation. Furthermore, the coordinate changes of the control points in the optimized structure are more continuous, the curve transition is smoother, and the corresponding effective sealing length distribution is more uniform.

[0135] Multiple sets of initial parameters are input into a preset simulation model, and a script automatically applies pre-tightening and pressure-bearing conditions to extract performance indicators such as equivalent stress, contact stress, and effective sealing length. Similarly, target optimization parameters are input into the preset simulation model, and a script automatically applies pre-tightening and pressure-bearing conditions to extract performance indicators such as equivalent stress, contact stress, and effective sealing length.

[0136] By comparing equivalent stresses, during the pre-tightening stage, the maximum equivalent stress of the initial structure corresponding to multiple initial parameters was 583.64 MPa, while the maximum equivalent stress of the optimized structure corresponding to the target optimized parameters decreased to 543.76 MPa. This shows that the optimized structure has a smaller high-stress area and lower stress value, indicating that the optimized structure designed according to the improved swarm robot search and rescue algorithm provided in this application's embodiments experiences more uniform stress and exhibits better strength performance during pre-tightening installation. During the pressure-bearing stage, the maximum equivalent stress of the initial structure corresponding to multiple initial parameters was 563.83 MPa, while the maximum equivalent stress of the optimized structure corresponding to the target optimized parameters further decreased to approximately 412.48 MPa. The stress concentration phenomenon of the optimized structure is significantly alleviated, indicating that under annular pressure loads, the optimized structure can more effectively disperse stress, avoiding structural damage caused by excessive local stress, and significantly improving strength and safety.

[0137] By comparing contact stress, during the pre-tightening stage, the maximum contact stress of the initial structure corresponding to multiple initial parameters was 1407.2095 MPa, while the maximum contact stress of the optimized structure corresponding to the target optimized parameters decreased to 1068.6554 MPa. This shows that the optimized structure has a more uniform contact stress distribution and a complete effective sealing area. All preset sealing positions meet the sealing requirements, verifying that the optimized structure can form a reliable initial seal during the pre-tightening stage. During the pressure-bearing stage, the maximum contact stress of the initial structure corresponding to multiple initial parameters was 1194.2627 MPa, while the maximum contact stress of the optimized structure corresponding to the target optimized parameters was 825.3651 MPa. Although the contact stress value decreased after optimization, the distribution range of the contact stress still covered all key sealing surfaces, and the effective sealing length of all preset sealing positions was not zero. This demonstrates that under working pressure, the optimized structure designed according to the improved swarm robot search and rescue algorithm provided in this application embodiment can still maintain good sealing performance, and no sealing failure area appears.

[0138] In summary, compared with the initial structures corresponding to multiple sets of initial parameters, the optimized structure designed according to the improved swarm robot search and rescue algorithm provided in this application embodiment has significantly improved both strength and sealing performance, achieving the dual optimization goals of reducing stress concentration in UHV wellhead equipment and ensuring the sealing reliability of UHV wellhead equipment.

[0139] Figure 3 A schematic diagram of the sealing structure optimization device for ultra-high pressure wellhead equipment provided in this application embodiment is shown below. Figure 3As shown, the device includes: a control point set determination module 301, an initial parameter sampling module 302, a first performance evaluation value acquisition module 303, a basic sealing performance parameter output module 304, a second performance evaluation value acquisition module 305, a reinforced sealing performance parameter output module 306, a third performance evaluation value acquisition module 307, a multiple set of reliable adaptation parameter output modules 308, a fourth performance evaluation value acquisition module 309, a target optimization parameter determination module 310, and a target sealing structure construction module 311.

[0140] The control point set determination module 301 is used to transform the sealing structure to be optimized into a parametric model through curve fitting, and to determine the control point set of the parametric model.

[0141] The initial parameter sampling module 302 is used to sample the control point set based on the Cauchy distribution and generate multiple sets of initial parameters.

[0142] The first performance evaluation value acquisition module 303 is used to input multiple sets of initial parameters into a preset simulation model to obtain the first performance evaluation value corresponding to each set of initial parameters.

[0143] The basic sealing performance parameter output module 304 is used to iteratively update each set of initial parameters according to the first performance evaluation value and the preset update strategy until the first convergence condition is met, and output multiple sets of basic sealing performance parameters.

[0144] The second performance evaluation value acquisition module 305 is used to input multiple sets of basic sealing performance parameters into a preset simulation model to obtain the second performance evaluation value corresponding to each set of basic sealing performance parameters.

[0145] The enhanced sealing performance parameter output module 306 is used to iteratively update multiple sets of basic sealing performance parameters according to the second performance evaluation value and preset rules until the second convergence condition is met, and output multiple sets of enhanced sealing performance parameters.

[0146] The third performance evaluation value acquisition module 307 is used to input multiple sets of enhanced sealing performance parameters into a preset simulation model to obtain the third performance evaluation value corresponding to each set of enhanced sealing performance parameters.

[0147] The multi-set reliable adaptation parameter output module 308 is used to process multiple sets of enhanced sealing performance parameters according to the third performance evaluation value and the preset screening strategy to obtain multiple sets of reliable adaptation parameters.

[0148] The fourth performance evaluation value acquisition module 309 is used to input multiple sets of reliable adaptation parameters into a preset simulation model to obtain the fourth performance evaluation value corresponding to each set of reliable adaptation parameters.

[0149] The target optimization parameter determination module 310 is used to sort multiple sets of reliable adaptation parameters according to the fourth performance evaluation value to obtain the target optimization parameters.

[0150] The target sealing structure construction module 311 is used to construct the target sealing structure based on the target optimization parameters.

[0151] In one possible implementation, the basic sealing performance parameter output module 304 is specifically used to sort each group of initial parameters according to the first performance evaluation value, and divide the multiple groups of initial parameters into dominant parameters and follower parameters according to the first preset scaling factor; based on the dominant parameters and follower parameters, iteratively execute the following steps: for any group of dominant parameters, update the dominant parameters based on a preset step size to obtain the updated dominant parameters; input the updated dominant parameters into a preset simulation model to obtain the performance evaluation value corresponding to the updated dominant parameters; if the performance evaluation value corresponding to the updated dominant parameters is better than the performance evaluation value corresponding to the original dominant parameters, then replace the original dominant parameters with the updated dominant parameters. The process involves several steps: First, determining the update step size for any set of following parameters based on the distance between the following parameters and the parameter space boundary. Then, calculating the updated parameter value based on the update step size, where the parameter space boundary represents the upper and lower limits of the initial parameter value range. Next, updating each set of following parameters according to the first preset judgment rule and the updated parameter value, resulting in updated following parameters. Finally, sorting the updated sets of parameters according to their corresponding performance evaluation values, and dividing each set of parameters into dominant parameters and following parameters according to the first preset scaling factor. The process also involves determining whether the number of iterations has reached a first threshold. If the number of iterations reaches the first threshold, the updated sets of parameters are used as multiple sets of basic sealing performance parameters and output.

[0152] In one possible implementation, the enhanced sealing performance parameter output module 306 is specifically used to sort multiple sets of basic sealing performance parameters according to a second performance evaluation value, and divide the multiple sets of basic sealing performance parameters into dominant parameters and follower parameters according to a second preset scaling factor; based on the dominant parameters and follower parameters, iteratively execute the following steps: for any set of follower parameters, randomly select any set of dominant parameters, and calculate the updated parameter value based on the set of dominant parameters; update each set of follower parameters according to the second preset judgment rule and the updated parameter value to obtain the updated follower parameters; input the dominant parameters and the updated follower parameters into a preset simulation model respectively to obtain the performance evaluation value corresponding to each set of updated parameters; based on the performance evaluation value corresponding to each set of updated parameters, sort the updated sets of parameters, and divide the updated sets of parameters into dominant parameters and follower parameters according to the second preset scaling factor; determine whether the number of iterations has reached a second threshold; if the number of iterations has reached the second threshold, then output the updated sets of parameters as multiple sets of enhanced sealing performance parameters.

[0153] In one possible implementation, the multi-set reliable adaptation parameter output module 308 is specifically used to sort the multi-set reinforced sealing performance parameters according to the third performance evaluation value, and divide the multi-set reinforced sealing performance parameters into dominant parameters and follower parameters according to the third preset scaling factor; for any set of dominant parameters, generate multiple sets of new parameters; input the multiple sets of new parameters into a preset simulation model to obtain the performance evaluation value corresponding to each set of new parameters; for each set of new parameters, if the performance evaluation value of the new parameter is better than the performance evaluation value of the corresponding dominant parameter, then use the new parameter to replace the follower parameter with the smallest current performance evaluation value; after processing the new parameters corresponding to each set of dominant parameters, determine the current sets of parameters as multiple sets of reliable adaptation parameters.

[0154] In one possible implementation, the control point set determination module 301 is specifically used to obtain the coordinate points of the cross-sectional curve of the sealing structure to be optimized; fit the coordinate points with a B-spline curve to generate a parameterized model corresponding to the cross-sectional curve; extract the feature control points in the parameterized model, and determine the coordinate parameters of the feature control points as the control point set of the parameterized model.

[0155] The sealing structure optimization method and device for ultra-high pressure wellhead equipment provided in this embodiment can execute the method provided in the above-mentioned method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0156] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the electronic device further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0157] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0158] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0159] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0160] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0161] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0162] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0163] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0164] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0165] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0166] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0167] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0168] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0169] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0170] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0171] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for optimizing the sealing structure of ultra-high pressure wellhead equipment, characterized in that, include: The sealing structure to be optimized is transformed into a parametric model through curve fitting, and the set of control points of the parametric model is determined. The control point set is sampled based on the Cauchy distribution to generate multiple sets of initial parameters; The multiple sets of initial parameters are respectively input into a preset simulation model to obtain the first performance evaluation value corresponding to each set of initial parameters; The initial parameters are iteratively updated according to the first performance evaluation value and the preset update strategy until the first convergence condition is met, and multiple sets of basic sealing performance parameters are output, including: dividing the multiple sets of initial parameters into dominant parameters and follower parameters according to the first performance evaluation value; starting the iteration, for any set of dominant parameters, obtaining the performance evaluation value corresponding to the updated dominant parameter based on the preset step size and the preset simulation model; for any set of follower parameters, updating each set of follower parameters to obtain the updated follower parameters; dividing each set of parameters into dominant parameters and follower parameters according to the performance evaluation value corresponding to each set of updated parameters, until the iteration ends; The multiple sets of basic sealing performance parameters are respectively input into the preset simulation model to obtain the second performance evaluation value corresponding to each set of basic sealing performance parameters. The multiple sets of basic sealing performance parameters are iteratively updated according to the second performance evaluation value and preset rules until the second convergence condition is met, and multiple sets of enhanced sealing performance parameters are output. This includes: dividing the multiple sets of basic sealing performance parameters into dominant parameters and follower parameters; starting the iteration, for any set of follower parameters, selecting any set of dominant parameters, and calculating the updated parameter value based on the set of dominant parameters; updating each set of follower parameters according to the updated parameter value to obtain the updated follower parameters; inputting the dominant parameters and the updated follower parameters into a preset simulation model to obtain the performance evaluation value corresponding to each set of updated parameters; and re-dividing the dominant parameters and follower parameters according to the performance evaluation value corresponding to each set of updated parameters until the iteration ends. The multiple sets of enhanced sealing performance parameters are respectively input into the preset simulation model to obtain the third performance evaluation value corresponding to each set of enhanced sealing performance parameters. The multiple sets of enhanced sealing performance parameters are processed according to the third performance evaluation value and a preset screening strategy to obtain multiple sets of reliable adaptation parameters. This includes: dividing the multiple sets of enhanced sealing performance parameters into dominant parameters and follower parameters based on the third performance evaluation value; generating multiple sets of new parameters for any dominant parameter; inputting the multiple sets of new parameters into a preset simulation model to obtain the performance evaluation value corresponding to each set of new parameters; for each set of new parameters, if the performance evaluation value of the new parameter is better than the performance evaluation value of the corresponding dominant parameter, then using the new parameter to replace the follower parameter with the smallest current performance evaluation value; until all dominant parameters are processed, the current sets of parameters are determined as multiple sets of reliable adaptation parameters. The multiple sets of reliable adaptation parameters are respectively input into the preset simulation model to obtain the fourth performance evaluation value corresponding to each set of reliable adaptation parameters; The multiple sets of reliable adaptation parameters are sorted according to the fourth performance evaluation value to obtain the target optimization parameters; The target sealing structure is constructed based on the target optimization parameters.

2. The method according to claim 1, characterized in that, Based on the first performance evaluation value, multiple sets of initial parameters are divided into dominant parameters and follower parameters, including: The initial parameters are sorted according to the first performance evaluation value, and the initial parameters are divided into dominant parameters and follower parameters according to the first preset scaling factor. The step of obtaining the performance evaluation value corresponding to the updated dominant parameters based on a preset step size and a preset simulation model for any set of dominant parameters includes: For any set of dominant parameters, the dominant parameters are updated based on a preset step size to obtain the updated dominant parameters; The updated dominant parameters are input into the preset simulation model to obtain the performance evaluation values ​​corresponding to the updated dominant parameters; After obtaining the performance evaluation value corresponding to the updated dominant parameters for any set of dominant parameters based on a preset step size and a preset simulation model, the process further includes: If the performance evaluation value corresponding to the updated dominant parameter is better than the performance evaluation value corresponding to the original dominant parameter, then the updated dominant parameter replaces the original dominant parameter. The step of updating each set of following parameters for any given set to obtain the updated following parameters includes: For any set of following parameters, an update step size is determined based on the distance between the following parameters and the parameter space boundary, and the updated parameter value is calculated based on the update step size, wherein the parameter space boundary is the upper and lower limits of the initial parameter value range; According to the first preset judgment rule and the updated parameter value, the following parameters of each group are updated to obtain the updated following parameters; The parameters are divided into dominant parameters and follower parameters based on the updated performance evaluation values ​​corresponding to each group of parameters, including: Based on the performance evaluation values ​​corresponding to each updated set of parameters, the updated set of parameters are sorted, and the set of parameters are divided into dominant parameters and follower parameters according to the first preset scaling factor. Determine if the number of iterations has reached the first threshold; If the number of iterations reaches the first threshold, the updated parameters will be used as the multiple sets of basic sealing performance parameters and output.

3. The method according to claim 1, characterized in that, The multiple sets of basic sealing performance parameters are divided into dominant parameters and follower parameters, including: The multiple sets of basic sealing performance parameters are sorted according to the second performance evaluation value, and the multiple sets of basic sealing performance parameters are divided into dominant parameters and follower parameters according to the second preset scaling factor. The step of updating each group of following parameters according to the updated parameter value to obtain the updated following parameters includes: According to the second preset judgment rule and the updated parameter value, the following parameters of each group are updated to obtain the updated following parameters; The process of reclassifying the dominant and follower parameters based on the updated performance evaluation values ​​corresponding to each group of parameters includes: Based on the performance evaluation values ​​corresponding to the updated groups of parameters, the updated groups of parameters are sorted, and the updated groups of parameters are divided into dominant parameters and follower parameters according to the second preset scaling factor. Determine if the number of iterations has reached the second threshold; If the number of iterations reaches the second threshold, the updated sets of parameters are used as the multiple sets of enhanced sealing performance parameters and output.

4. The method according to claim 1, characterized in that, Based on the third performance evaluation value, multiple sets of enhanced sealing performance parameters are divided into dominant parameters and follower parameters, including: The multiple sets of enhanced sealing performance parameters are sorted according to the third performance evaluation value, and then divided into dominant parameters and follower parameters according to the third preset scaling factor.

5. The method according to claim 1, characterized in that, The process of converting the sealing structure to be optimized into a parametric model through curve fitting and determining the control point set of the parametric model includes: Obtain the coordinate points of the cross-sectional curve of the sealing structure to be optimized; The coordinate points are fitted with B-spline curves to generate a parametric model corresponding to the cross-sectional curve. Extract the feature control points from the parameterized model, and determine the coordinate parameters of the feature control points as the control point set of the parameterized model.

6. A sealing structure optimization device for ultra-high pressure wellhead equipment, characterized in that, include: The control point set determination module is used to transform the sealing structure to be optimized into a parametric model through curve fitting, and to determine the control point set of the parametric model. The initial parameter sampling module is used to sample the control point set based on the Cauchy distribution to generate multiple sets of initial parameters; The first performance evaluation value acquisition module is used to input the multiple sets of initial parameters into a preset simulation model to obtain the first performance evaluation value corresponding to each set of initial parameters. The basic sealing performance parameter output module is used to iteratively update each set of initial parameters according to the first performance evaluation value and a preset update strategy until a first convergence condition is met, and output multiple sets of basic sealing performance parameters, including: dividing multiple sets of initial parameters into dominant parameters and follower parameters according to the first performance evaluation value; starting iteration, for any set of dominant parameters, obtaining the performance evaluation value corresponding to the updated dominant parameter based on a preset step size and a preset simulation model; updating each set of follower parameters for any set of follower parameters to obtain the updated follower parameters; dividing each set of parameters into dominant parameters and follower parameters according to the performance evaluation value corresponding to each set of updated parameters, until the iteration ends; The second performance evaluation value acquisition module is used to input the multiple sets of basic sealing performance parameters into the preset simulation model to obtain the second performance evaluation value corresponding to each set of basic sealing performance parameters. The enhanced sealing performance parameter output module is used to iteratively update the multiple sets of basic sealing performance parameters according to the second performance evaluation value and preset rules until the second convergence condition is met, and output multiple sets of enhanced sealing performance parameters. This includes: dividing the multiple sets of basic sealing performance parameters into dominant parameters and follower parameters; starting iteration; for any set of follower parameters, selecting any set of dominant parameters, and calculating updated parameter values ​​based on the set of dominant parameters; updating each set of follower parameters according to the updated parameter values ​​to obtain updated follower parameters; inputting the dominant parameters and updated follower parameters into a preset simulation model to obtain performance evaluation values ​​corresponding to each set of updated parameters; and re-dividing the dominant parameters and follower parameters according to the performance evaluation values ​​corresponding to each set of updated parameters until the iteration ends. The third performance evaluation value acquisition module is used to input the multiple sets of enhanced sealing performance parameters into the preset simulation model to obtain the third performance evaluation value corresponding to each set of enhanced sealing performance parameters. A multi-set reliable adaptation parameter output module is used to process the multiple sets of enhanced sealing performance parameters according to the third performance evaluation value and a preset screening strategy to obtain multiple sets of reliable adaptation parameters. This includes: dividing the multiple sets of enhanced sealing performance parameters into dominant parameters and follower parameters based on the third performance evaluation value; generating multiple sets of new parameters for any given dominant parameter; inputting the multiple sets of new parameters into a preset simulation model to obtain the performance evaluation value corresponding to each set of new parameters; for each set of new parameters, if the performance evaluation value of the new parameter is better than the performance evaluation value of the corresponding dominant parameter, then replacing the follower parameter with the smallest current performance evaluation value with the new parameter; until all dominant parameters have been processed, the current sets of parameters are determined as multiple sets of reliable adaptation parameters. The fourth performance evaluation value acquisition module is used to input the multiple sets of reliable adaptation parameters into the preset simulation model to obtain the fourth performance evaluation value corresponding to each set of reliable adaptation parameters. The target optimization parameter determination module is used to sort the multiple sets of reliable adaptation parameters according to the fourth performance evaluation value to obtain the target optimization parameters; The target sealing structure construction module is used to construct the target sealing structure based on the target optimization parameters.

7. The apparatus according to claim 6, characterized in that, The control point set determination module is specifically used for: Obtain the coordinate points of the cross-sectional curve of the sealing structure to be optimized; fit the coordinate points with a B-spline curve to generate a parametric model corresponding to the cross-sectional curve; extract the feature control points in the parametric model, and determine the coordinate parameters of the feature control points as the control point set of the parametric model.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 5.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 5.

Images