A pipeline combination system impact resistance optimization method, device, equipment and medium

Abstract

The present application relates to a kind of pipeline combination system impact optimization method, device, equipment and medium, belong to structural impact design technical field, its method includes: the three-dimensional finite element model of pipeline combination system is constructed, based on the boundary condition, load condition and material parameter set to three-dimensional finite element model is carried out impact performance simulation, obtains the maximum plastic strain of pipeline under different design scheme;Corresponding design parameter is obtained with different design scheme, based on design parameter and the maximum plastic strain of pipeline neural network model is trained to be constructed, to determine the mapping relationship of design parameter and maximum plastic strain, design parameter includes isolator stiffness configuration, stopper arrangement mode and damper position;Based on the mapping relationship of design parameter and maximum plastic strain, with the minimum as optimization goal of maximum plastic strain, using sequential quadratic programming algorithm to optimize design parameter and obtain optimal design scheme, improve the efficiency and quality of impact design.

Description

Technical Field

[0001] This invention relates to the field of structural impact resistance design technology, and in particular to a method, apparatus, equipment and medium for optimizing the impact resistance of a pipeline combination system. Background Technology

[0002] In engineering fields such as shipbuilding, nuclear power, and aerospace, the dynamic response of equipment and pipeline systems under impact loads directly affects the safety and reliability of the system.

[0003] Traditional shock resistance optimization methods mostly rely on empirical design or finite element simulation. In the combination system of equipment, pipelines and elastic components such as vibration isolators, limiters and dampers, shock resistance optimization using empirical design or finite element simulation is costly, time-consuming and difficult to quickly identify the optimal configuration among various stiffness configurations and layouts, resulting in low efficiency and quality of shock resistance design. Summary of the Invention

[0004] In view of this, it is necessary to provide a method, apparatus, equipment and medium for optimizing the impact resistance of pipeline combination systems, so as to solve the technical problem of low efficiency and quality in impact resistance design.

[0005] To address the aforementioned problems, in a first aspect, the present invention provides a method for optimizing the shock resistance of a pipeline combination system, comprising: A three-dimensional finite element model of the pipeline system is constructed. Based on the set boundary conditions, load conditions and material parameters, the impact resistance performance of the three-dimensional finite element model is simulated to obtain the maximum plastic strain of the pipeline under different design schemes. Obtain design parameters corresponding to different design schemes, and train the constructed neural network model based on the design parameters and the maximum plastic strain of the pipeline to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangement methods, and different damper positions. Based on the mapping relationship between the design parameters and the maximum plastic strain, with the minimum maximum plastic strain as the optimization objective, the design parameters are optimized and solved using a sequential quadratic programming algorithm to obtain the optimal design scheme.

[0006] In one possible implementation, the three-dimensional finite element model of the pipeline assembly system includes: A three-dimensional finite element model of a pipeline system including equipment, pipelines, vibration isolators, limiters, and dampers is constructed. Shell elements are used to divide the equipment, and eight-node hexahedral linear reduced integral elements are used to divide the pipeline. The equipment is a shell structure, and the pipeline is a tubular structure.

[0007] In one possible implementation, the boundary conditions include the ends of vibration isolators and limiters installed in the middle of the equipment being set to be completely fixed, and the load conditions include vibration isolators and limiters installed at the bottom of the equipment applying an acceleration load.

[0008] In one possible implementation, the neural network model has a backpropagation (BP) neural network architecture, which includes an input layer, hidden layers, and an output layer; training the constructed neural network model based on the design parameters and the maximum plastic strain value of the pipeline includes: The design parameters and the maximum plastic strain of the pipeline are input into the BP neural network. The design parameters are normalized based on the input layer, and the normalized parameters are input into the hidden layer. Feature extraction is performed on the normalized parameters based on the hidden layer; Based on the activation function of the output layer, the extracted features are nonlinearly mapped to output the predicted value of the maximum plastic strain of the pipeline. Based on the predicted maximum plastic strain of the pipeline and the maximum plastic strain of the pipeline, a loss function of the BP neural network is constructed. The parameters of the BP neural network are updated based on the loss function to obtain a trained BP neural network.

[0009] In one possible implementation, the step of optimizing the design parameters based on the mapping relationship between the design parameters and the maximum plastic strain, with the minimum value of the maximum plastic strain as the optimization objective, and using a sequential quadratic programming algorithm to solve for the design parameters to obtain the optimal design scheme includes: An objective function is constructed with the goal of minimizing the maximum plastic strain value. Design variables and constraints are determined based on the design parameters, wherein the constraints include stiffness constraints and strain constraints. Initialize the objective function value, constraint function value, and Hessian approximation matrix, wherein the constraint function includes a stiffness constraint function and a strain constraint function; Based on the mapping relationship between the design parameters and the maximum plastic strain, the objective function value, constraint function value, objective function gradient, and constraint function gradient corresponding to the design variables are calculated. Based on the gradient of the objective function and the gradient of the constraint function, the objective function and the constraint function are approximated by second order and linearized by first order, respectively, to obtain a quadratic programming subproblem. Solve the quadratic programming subproblem to obtain the search direction; A line search is performed on the objective function based on the search direction to determine the search step size; The design variables and Hessian approximation matrix are updated based on the search step size to obtain the optimal design scheme.

[0010] In one possible implementation, the quadratic programming subproblem is: , , in, To explore directions, For the first The design variables of the second time, For the first The Hessian approximation matrix of order 1 The gradient of the objective function. For stiffness constraint gradient, For strain constraint gradient, Let be the strain constraint function. Here is the stiffness constraint function. Let be the objective function. This is the transpose operator.

[0011] In one possible implementation, the design variable is updated as follows: , in, For the updated design variables, For the search step size, Indicates the search direction.

[0012] Secondly, the present invention also provides a shock resistance optimization device for a pipeline combination system, comprising: The simulation module is used to construct a three-dimensional finite element model of the pipeline combination system. Based on the set boundary conditions, load conditions and material parameters, the impact resistance performance of the three-dimensional finite element model is simulated to obtain the maximum plastic strain of the pipeline under different design schemes. The prediction module is used to obtain design parameters corresponding to different design schemes. Based on the design parameters and the maximum plastic strain of the pipeline, the constructed neural network model is trained to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangement methods, and different damper positions. The optimization module is used to optimize the design parameters based on the mapping relationship between the design parameters and the maximum plastic strain, with the minimum maximum plastic strain as the optimization objective, and to obtain the optimal design scheme by using a sequential quadratic programming algorithm.

[0013] Thirdly, the present invention also provides an electronic device, comprising: a processor and a memory; The memory stores a computer-readable program that can be executed by the processor; When the processor executes the computer-readable program, it implements the steps in the shock resistance optimization method for pipeline combination systems as described above.

[0014] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the pipeline combination system shock resistance optimization method described in any one of the above method items.

[0015] The beneficial effects of this invention are as follows: A three-dimensional finite element model of the pipeline system is constructed. Based on set boundary conditions, load conditions, and material parameters, the impact resistance performance of the three-dimensional finite element model is simulated to obtain the maximum plastic strain of the pipeline under different design schemes. Design parameters corresponding to different design schemes are obtained. Based on the design parameters and the maximum plastic strain of the pipeline, the constructed neural network model is trained to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangements, and different damper positions. Based on the mapping relationship between the design parameters and the maximum plastic strain, with the minimum maximum plastic strain as the optimization objective, a sequential quadratic programming algorithm is used to optimize and solve the design parameters to obtain the optimal design scheme. A rich training sample library is constructed through simulation. A nonlinear mapping relationship between the design parameters and the maximum plastic strain is established using a neural network, achieving rapid and accurate prediction of impact resistance performance. Optimization is performed using a sequential quadratic programming algorithm to quickly find the optimal stiffness configuration and layout scheme, improving the efficiency and quality of impact resistance design. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of an embodiment of the shock resistance optimization method for pipeline combination systems provided by the present invention; Figure 2 A schematic diagram of a three-dimensional finite element model of the pipeline combination system impact resistance optimization method provided by the present invention; Figure 3 A schematic diagram illustrating the applied boundary conditions and load conditions for the impact resistance optimization method of the pipeline combination system provided by the present invention; Figure 4 The maximum plastic strain fitting curves of the pipeline under different vibration isolator stiffness configurations for the pipeline combination system impact resistance optimization method provided by the present invention; Figure 5The maximum plastic strain of the pipeline at different damper positions as a function of stiffness ratio is shown in the pipeline combination system impact resistance optimization method provided by the present invention. Figure 6 The maximum plastic strain fitting curves of the pipeline under different limiter positions in the pipeline combination system impact resistance optimization method provided by the present invention; Figure 7 The training loss variation diagram under different combination forms of the pipeline combination system shock resistance optimization method provided by the present invention; Figure 8 A schematic diagram of an embodiment of the pipeline combination system impact resistance optimization device provided by the present invention; Figure 9 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0018] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0019] In this document, the term "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] This invention discloses a method, apparatus, device, and medium for optimizing the shock resistance of a pipeline combination system, which can be used in a computer. The method, apparatus, or computer-readable storage medium involved in this invention can be integrated with the aforementioned apparatus or can be relatively independent.

[0021] One specific embodiment of the present invention discloses a method for optimizing the impact resistance of a pipeline combination system, which can be executed by a computer, specifically by one or more processors of the computer. For example... Figure 1 As shown, the shock resistance optimization method for pipeline combination systems includes: S101. Construct a three-dimensional finite element model of the pipeline combination system. Based on the set boundary conditions, load conditions and material parameters, simulate the impact resistance performance of the three-dimensional finite element model to obtain the maximum plastic strain of the pipeline under different design schemes.

[0022] It should be noted that a rich training sample library is built through simulation, providing a data foundation for training the neural network.

[0023] S102. Obtain the design parameters corresponding to different design schemes. Train the constructed neural network model based on the design parameters and the maximum plastic strain of the pipeline to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangement methods, and different damper positions. It should be noted that by using a neural network to establish a nonlinear mapping relationship between design parameters and maximum plastic strain, rapid and accurate prediction of impact resistance performance was achieved.

[0024] S103. Based on the mapping relationship between design parameters and maximum plastic strain, with the minimum maximum plastic strain as the optimization objective, the design parameters are optimized and solved using a sequential quadratic programming algorithm to obtain the optimal design scheme.

[0025] It should be noted that by using a sequential quadratic programming algorithm for optimization, the optimal stiffness configuration and layout scheme can be quickly found, thus improving the efficiency and quality of impact-resistant design.

[0026] In some embodiments, in step S101, a three-dimensional finite element model of the piping system is constructed. This model includes equipment, piping, vibration isolators, limiters, and dampers. A schematic diagram of the three-dimensional finite element model can be found in [reference needed]. Figure 2 ,like Figure 2 As shown, the three-dimensional geometric model includes equipment, pipelines, vibration isolators, limiters, and dampers. Specifically, a three-dimensional geometric model containing equipment, pipelines, vibration isolators, limiters, and dampers is created using 3D modeling software (Abaqus / CAE). The pipeline assembly system includes equipment, pipelines, and elastic components. The equipment is a shell structure, the pipelines are tubular structures, and the elastic components include vibration isolators, limiters, and dampers. Specifically, the pipeline assembly system contains 10 elastic components (4 vibration isolators, 4 limiters, and 2 dampers). Meshing is performed using Abaqus / CAE. The equipment is discretized using shell elements (S4R), and the pipelines are meshed using eight-node hexahedral linear reduced integral elements (C3D8R), with two mesh layers specified in the thickness direction. Impact resistance simulation was performed on a three-dimensional finite element model based on the set boundary conditions, load conditions, and material parameters to obtain the maximum plastic strain of the pipeline under different design schemes. For a schematic diagram of the applied boundary conditions and load conditions, please refer to [link / reference needed]. Figure 3 ,like Figure 3As shown, the boundary conditions are set as follows: the vibration isolators and limiters installed in the middle (waist) of the equipment are completely fixed at their ends. The load conditions are: the vibration isolators and limiters installed at the bottom of the equipment are subjected to acceleration loads, and a working pressure of 15MPa is applied inside the pipeline. The material parameters are set according to the actual engineering materials. The equipment uses Q235 steel, and the pipeline uses 316LN stainless steel. To study the influence of different stiffness configurations and layouts on the impact resistance performance, multiple working conditions are set for calculation, including different vibration isolator stiffness values, different limiter arrangements, and different damper positions. Nine combinations (including three limiter arrangements and three...) were calculated. The system response of the damper position combination under 324 working conditions under 36 vibration isolator stiffness configurations was simulated in a three-dimensional finite element model. The impact performance was simulated by setting boundary conditions, load conditions and material parameters. The dynamic response law under different combinations was analyzed and the maximum plastic strain value of the pipeline under each working condition was extracted. That is, the simulation results of all working conditions were automatically extracted by calling the ODB interface of Abaqus / Viewer through Python script, and an impact performance database was established. During the simulation, the analysis type was set to dynamic explicit analysis, considering geometric nonlinearity and material nonlinearity effects, and an appropriate time step and total analysis time were set.

[0027] In some embodiments, in step S102, design parameters corresponding to different design schemes are obtained. Based on the design parameters and the maximum plastic strain of the pipeline, the constructed neural network model is trained to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangements, and different damper positions. Different design schemes correspond to different working conditions, and each design scheme has different vibration isolator stiffness values, limiter arrangements, and damper positions. The design parameters and the maximum plastic strain of the pipeline can be obtained through an impact resistance performance database. Based on the established impact resistance performance database, a BP neural network is used for training to establish a nonlinear mapping relationship between the vibration isolator stiffness and the maximum plastic strain of the pipeline. The neural network model is constructed using the Scikit-learn machine learning library. The network comprises an input layer, hidden layers, and an output layer. Its training process is as follows: Design parameters and the maximum plastic strain of the pipeline are input into the BP neural network; the design parameters are normalized based on the input layer, and the normalized parameters are input into the hidden layer; features are extracted from the normalized parameters based on the hidden layer; the extracted features are nonlinearly mapped based on the activation function of the output layer to output the predicted value of the maximum plastic strain of the pipeline; a loss function for the BP neural network is constructed based on the predicted value and the maximum plastic strain of the pipeline; the parameters of the BP neural network are updated based on the loss function to obtain a trained BP neural network. By training the BP neural network, a nonlinear mapping relationship between the design parameters and the maximum plastic strain of the pipeline is established. For fitting curves of the maximum plastic strain of the pipeline under different vibration isolator stiffness configurations, please refer to [link / reference needed]. Figure 4 ,like Figure 4 As shown, the relationship between the vibration isolator stiffness and the maximum plastic strain of the pipeline is nonlinear. For the curves showing the variation of the maximum plastic strain of the pipeline with stiffness ratio at different damper locations, please refer to [link / reference needed]. Figure 5 Please refer to the fitting curves of the maximum plastic strain of the pipeline under different limiter positions. Figure 6 ,like Figure 5 and Figure 6 As shown, in YH04-1, YH04-2, and YH04-3, 04 represents the combination of the vibration isolator and the limiter, which is the 4th working condition out of 324. Different working conditions represent different vibration isolator stiffness configurations and different layouts of the limiters and dampers. 1, 2, and 3 represent the positions of the dampers. In the BP neural network, the mean square error is used as the loss function, and the Adam optimizer optimizes the parameters. For the training loss variation graph under different combinations, please refer to [link / reference]. Figure 7 ,like Figure 7As shown, under the combination of YH04, YH22, YH40, etc., the training result of the BP neural network is normal and convergent. The BP neural network is used to establish a nonlinear mapping relationship between the system response and the design parameters, so as to realize the rapid and accurate prediction of the system's shock resistance performance.

[0028] In some embodiments, in step S103, based on the mapping relationship between design parameters and maximum plastic strain, and with the minimum maximum plastic strain value as the optimization objective, a sequential quadratic programming algorithm is used to optimize and solve the design parameters to obtain the optimal design scheme. An objective function is constructed with the minimum maximum plastic strain value as the optimization objective. Design variables and constraints are determined based on the design parameters, where the constraints include stiffness constraints and strain constraints. The design variables include the vibration isolator stiffness parameters and elastic component parts (position / type). The objective function value, constraint function value, and Hessian approximation matrix are initialized, where the constraint functions include stiffness constraint functions and strain constraint functions. Based on the mapping relationship between design parameters and maximum plastic strain, the objective function value, constraint function value, objective function gradient, and constraint function gradient corresponding to the design variables are calculated. Based on the objective function gradient and constraint function gradient, a second-order approximation and a first-order linearization are performed on the objective function and constraint function, respectively, to obtain a quadratic programming subproblem, which is: , , in, To explore directions, For the first The design variables of the second time, For the first The Hessian approximation matrix of order 1 The gradient of the objective function. For stiffness constraint gradient, For strain constraint gradient, Let be the strain constraint function. Indicates equality constraints. Here is the stiffness constraint function. To represent inequality constraints, Let be the objective function. It is the transpose operator; The quadratic programming subproblem is solved to obtain the search direction. Based on the search direction, a line search is performed on the objective function to determine the search step size. Based on the search step size, the design variables and the Hessian approximation matrix are updated. The Hessian approximation matrix is ​​updated using quasi-Newton methods such as BFGS to obtain the optimal design scheme. The convergence conditions of the sequential quadratic programming algorithm include whether the improvement of the objective function is small enough, whether the constraint violation is small enough, whether the size of the exploration direction is small enough, or whether the maximum number of iterations has been reached. When any one of the convergence conditions is met, the iteration stops and the optimal solution is output. The optimal solution includes the optimal vibration isolator stiffness configuration and the optimal component arrangement of elastic elements. The optimized scheme is re-verified by finite element simulation to confirm that its impact resistance performance meets the design requirements.

[0029] After establishing the objective function based on the trained neural network model, a sequential quadratic programming algorithm is used to handle the nonlinear constraint optimization problem during the optimization process. By constructing a series of quadratic programming sub-problems during the iteration process, the objective function is approximated in the second order, the constraints are linearized, and the update direction of the design variables is obtained by solving the sub-problems. Combined with the line search and Hessian matrix approximation update strategy, the optimization variables are gradually converged. Finally, under the premise of satisfying the constraints, the optimization solution with the goal of minimizing the maximum plastic strain of the pipeline is achieved, thereby determining the optimal scheme for the vibration isolator stiffness configuration and the layout of elastic components.

[0030] A three-dimensional finite element model was established using Python parameterization. Through batch simulation calculations of the 3D finite element model, the dynamic response law of the system under various combinations of elastic components and stiffness configurations was analyzed. The influence mechanism of each design parameter on the impact resistance performance was revealed. A rich training sample library was constructed, and a high-precision surrogate model was established using machine learning algorithms (BP neural network). The nonlinear mapping relationship between system performance indicators and design parameters was constructed. Finally, the optimal design scheme was found through optimization algorithms, realizing the rapid identification of the optimal configuration from a massive number of design schemes, improving optimization efficiency by tens of times, and significantly reducing the maximum plastic strain of the pipeline from 0.038 to 0.0094. The optimization effect was obvious. Through the organic combination of machine learning and numerical simulation, the traditional mode of "empirical design-simulation verification" was realized to the advanced design mode of "intelligent prediction-automatic optimization", which greatly improved design efficiency and quality and provided a brand-new solution for the impact resistance design of complex mechanical systems.

[0031] In summary, the impact resistance optimization method for pipeline combination systems provided by this invention constructs a three-dimensional finite element model of the pipeline combination system. Based on set boundary conditions, load conditions, and material parameters, the impact resistance performance of the three-dimensional finite element model is simulated to obtain the maximum plastic strain of the pipeline under different design schemes. Design parameters corresponding to different design schemes are obtained. Based on the design parameters and the maximum plastic strain of the pipeline, the constructed neural network model is trained to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangements, and different damper positions. Based on the mapping relationship between the design parameters and the maximum plastic strain, with the minimum maximum plastic strain as the optimization objective, a sequential quadratic programming algorithm is used to optimize and solve the design parameters to obtain the optimal design scheme, thus improving the efficiency and quality of impact resistance design.

[0032] To better implement the pipeline combination system shock resistance optimization method in this embodiment of the invention, based on the pipeline combination system shock resistance optimization method, correspondingly, as follows: Figure 8 As shown, this embodiment of the invention also provides a pipeline combination system shock resistance optimization device, the pipeline combination system shock resistance optimization device 800 includes: Simulation module 801 is used to construct a three-dimensional finite element model of the pipeline combination system. Based on the set boundary conditions, load conditions and material parameters, the three-dimensional finite element model is used to simulate the impact resistance performance and obtain the maximum plastic strain of the pipeline under different design schemes. The prediction module 802 is used to obtain design parameters corresponding to different design schemes. Based on the design parameters and the maximum plastic strain of the pipeline, the constructed neural network model is trained to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangement methods, and different damper positions. The optimization module 803 is used to optimize the design parameters based on the mapping relationship between the design parameters and the maximum plastic strain, with the minimum maximum plastic strain as the optimization objective, and to obtain the optimal design scheme by using a sequential quadratic programming algorithm.

[0033] like Figure 9 As shown, the present invention also provides an electronic device 900, which can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing device. The electronic device 900 includes a processor 901, a memory 902, and a display 903. Figure 9 Only some components of the electronic device 900 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0034] In some embodiments, memory 902 may be an internal storage unit of the electronic device 900, such as a hard disk or memory of the electronic device 900. In other embodiments, memory 902 may be an external storage device of the electronic device 900, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 900. Furthermore, memory 902 may include both internal and external storage units of the electronic device 900. Memory 902 is used to store application software and various types of data installed on the electronic device 900, such as program code installed on the electronic device 900. Memory 902 may also be used to temporarily store data that has been output or will be output. In one embodiment, memory 902 stores a pipeline system shock resistance optimization program, which can be executed by processor 901 to implement the pipeline system shock resistance optimization method of various embodiments of the present invention.

[0035] In some embodiments, processor 901 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 902 or process data, such as a pipeline combination system shock resistance optimization method.

[0036] In some embodiments, display 903 may be an LED display, a liquid crystal display, a touch-screen liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 903 is used to display identification information of the pipeline assembly system's shock resistance optimization program and to display a visual user interface. Components 901-903 of electronic device 900 communicate with each other via a system bus.

[0037] In some embodiments, when the processor 901 executes the pipeline system shock resistance optimization program in the memory 902, it implements each step of the pipeline system shock resistance optimization method as described in the above embodiments. Since the pipeline system shock resistance optimization method has been described in detail above, it will not be repeated here.

[0038] Accordingly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps or functions of the pipeline combination system shock resistance optimization method provided in the above-described method embodiments.

[0039] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0040] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing a piping system against impact, characterized in that, include: A three-dimensional finite element model of the pipeline system is constructed. Based on the set boundary conditions, load conditions and material parameters, the impact resistance performance of the three-dimensional finite element model is simulated to obtain the maximum plastic strain of the pipeline under different design schemes. Obtain design parameters corresponding to different design schemes, and train the constructed neural network model based on the design parameters and the maximum plastic strain of the pipeline to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangement methods, and different damper positions. Based on the mapping relationship between the design parameters and the maximum plastic strain, with the minimum maximum plastic strain as the optimization objective, the design parameters are optimized and solved using a sequential quadratic programming algorithm to obtain the optimal design scheme.

2. The method of claim 1, wherein, The three-dimensional finite element model of the pipeline combination system includes: A three-dimensional finite element model of a pipeline system including equipment, pipelines, vibration isolators, limiters, and dampers is constructed. Shell elements are used to divide the equipment, and eight-node hexahedral linear reduced integral elements are used to divide the pipeline. The equipment is a shell structure, and the pipeline is a tubular structure.

3. The method of claim 1, wherein, The boundary conditions include the vibration isolators and limiters installed in the middle of the equipment being set to be completely fixed at their ends, and the load conditions include the vibration isolators and limiters installed at the bottom of the equipment applying an acceleration load.

4. The method for optimizing the impact resistance of a pipeline combination system according to claim 1, characterized in that, The neural network model has a backpropagation (BP) neural network architecture, which includes an input layer, a hidden layer, and an output layer. Training the constructed neural network model based on the design parameters and the maximum plastic strain value of the pipeline includes: The design parameters and the maximum plastic strain of the pipeline are input into the BP neural network. The design parameters are normalized based on the input layer, and the normalized parameters are input into the hidden layer. Feature extraction is performed on the normalized parameters based on the hidden layer; Based on the activation function of the output layer, the extracted features are nonlinearly mapped to output the predicted value of the maximum plastic strain of the pipeline. Based on the predicted maximum plastic strain of the pipeline and the maximum plastic strain of the pipeline, a loss function of the BP neural network is constructed. The parameters of the BP neural network are updated based on the loss function to obtain a trained BP neural network.

5. The method for optimizing the impact resistance of a pipeline combination system according to claim 4, characterized in that, Based on the mapping relationship between the design parameters and the maximum plastic strain, and with the minimum maximum plastic strain value as the optimization objective, a sequential quadratic programming algorithm is used to optimize and solve the design parameters to obtain the optimal design scheme, including: An objective function is constructed with the goal of minimizing the maximum plastic strain value. Design variables and constraints are determined based on the design parameters, wherein the constraints include stiffness constraints and strain constraints. Initialize the objective function value, constraint function value, and Hessian approximation matrix, wherein the constraint function includes a stiffness constraint function and a strain constraint function; Based on the mapping relationship between the design parameters and the maximum plastic strain, the objective function value, constraint function value, objective function gradient, and constraint function gradient corresponding to the design variables are calculated. Based on the gradient of the objective function and the gradient of the constraint function, the objective function and the constraint function are approximated by second order and linearized by first order, respectively, to obtain a quadratic programming subproblem. Solve the quadratic programming subproblem to obtain the search direction; A line search is performed on the objective function based on the search direction to determine the search step size; The design variables and Hessian approximation matrix are updated based on the search step size to obtain the optimal design scheme.

6. The method for optimizing the impact resistance of a pipeline combination system according to claim 5, characterized in that, The quadratic programming subproblem is: ， ， in, To explore directions, For the first The design variables of the second time, For the first The Hessian approximation matrix of order 1 The gradient of the objective function. For stiffness constraint gradient, For strain constraint gradient, Let be the strain constraint function. Here is the stiffness constraint function. Let be the objective function. This is the transpose operator.

7. The method for optimizing the impact resistance of a pipeline combination system according to claim 5, characterized in that, The design variables are updated as follows: ， in, For the updated design variables, For the search step size, Indicates the search direction.

8. A device for optimizing the impact resistance of a pipeline combination system, characterized in that, include: The simulation module is used to construct a three-dimensional finite element model of the pipeline combination system. Based on the set boundary conditions, load conditions and material parameters, the impact resistance performance of the three-dimensional finite element model is simulated to obtain the maximum plastic strain of the pipeline under different design schemes. The prediction module is used to obtain design parameters corresponding to different design schemes. Based on the design parameters and the maximum plastic strain of the pipeline, the constructed neural network model is trained to determine the mapping relationship between the design parameters and the maximum plastic strain. The design parameters include different vibration isolator stiffness configurations, different limiter arrangement methods, and different damper positions. The optimization module is used to optimize the design parameters based on the mapping relationship between the design parameters and the maximum plastic strain, with the minimum maximum plastic strain as the optimization objective, and to obtain the optimal design scheme by using a sequential quadratic programming algorithm.

9. An electronic device, characterized in that, Including memory and processor; The memory stores a computer-readable program that can be executed by the processor; When the processor executes the computer-readable program, it implements the steps in the shock resistance optimization method for pipeline combination systems as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the pipeline combination system shock resistance optimization method according to any one of claims 1-7.

Images