Pipeline multi-fidelity digital twinning method, system, equipment, product and medium

Abstract

The invention relates to the technical field of pipeline safety, and provides a pipeline multi-fidelity digital twinning method, system, equipment, product and medium, and the method comprises the steps: building a full-size pipeline test platform, carrying out the pipeline load test of a pipeline through the full-size pipeline test platform, and obtaining high-fidelity data; constructing a finite element simulation network, and obtaining original low-fidelity data through the finite element simulation network; obtaining first low-fidelity data; constructing a first regression tree set to obtain second low-fidelity data; obtaining preprocessed second low-fidelity data through the second low-fidelity data, constructing an initial multi-fidelity digital twin network, training and preprocessing the second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, and iterating the initial multi-fidelity digital twin network to obtain third low-fidelity data; and completing the training of the initial multi-fidelity digital twin network. According to the method, the precision of simulation data of the pipeline is effectively improved by training the multi-fidelity digital twin network.

Description

Technical Field

[0001] The present invention relates to the field of pipeline safety technology, and in particular to a pipeline multi-fidelity digital twin method, system, equipment, product and medium. Background Art

[0002] One of the key links in the development of submarine oil and gas resources is the oil and gas transportation system based on thin-walled pipelines. However, the complex and harsh environment of the deep seabed may cause the submarine pipeline to fail locally due to external water pressure, collision, vibration, and its own ovality defects, which may lead to serious production safety accidents. Therefore, it is necessary to accurately measure and simulate the mechanical state of the submarine pipeline.

[0003] The current mainstream measurement and simulation methods include physical sensor monitoring and numerical simulation analysis. Among them, physical sensor monitoring monitors key parts in real time by placing sensors at local locations of physical structures. Although the fidelity of the first-hand monitoring data obtained by the sensor is high, the monitoring information obtained by this method cannot reflect the full-field mechanical response of the pipeline due to the density and cost of sensor layout. At the same time, the sensor has the risk of failure in complex and harsh environments, which will greatly reduce the stability and reliability of the monitoring information. In comparison, although the numerical model simulation technology is lower in cost and can obtain the global mechanical response of the structure under the corresponding working conditions. However, since the numerical simulation technology based on finite element analysis makes idealized assumptions and simplifications on the structure in modeling and analysis, the analysis results have low fidelity. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the related art. To this end, the present invention provides a pipeline multi-fidelity digital twin method, system, equipment, product and medium to achieve the establishment and training of a multi-fidelity digital twin network of a deep-sea pipeline.

[0005] The present invention provides a pipeline multi-fidelity digital twin method, comprising: S1: Build a full-scale pipeline test platform, conduct pipeline load tests on the pipeline through the full-scale pipeline test platform, and obtain high-fidelity data; S2: constructing a finite element simulation network, constructing a pipeline model, and simulating the pipeline model through the finite element simulation network to obtain original low-fidelity data; S3: clustering the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; S4: constructing a first regression tree set, obtaining regression tree residuals through the first low-fidelity data, substituting the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, constructing a loss function, constructing an intermediate regression tree through the loss function, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set to obtain a target second regression tree set, predicting the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data; S5: Preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain a target multi-fidelity digital twin network.

[0006] According to a pipeline multi-fidelity digital twin method provided by the present invention, step S4 further includes: S41: constructing a first regression tree set, determining an initial prediction, an actual target, and a preset number of regression trees through first low-fidelity data, calculating a residual between the initial prediction and the actual target to obtain a regression tree residual, substituting the regression tree residual into the first regression tree set to obtain an initial second regression tree set; S42: construct a loss function, and calculate the sample residual of the initial second regression tree set through the loss function; S43: constructing an intermediate regression tree through sample residuals, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set until the number of regression trees in the initial second regression tree set reaches a preset number of regression trees, and using the iterated initial second regression tree set as the target second regression tree set; S44: Substitute the first low-fidelity data into the target second regression tree set, and predict the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data.

[0007] According to a pipeline multi-fidelity digital twin method provided by the present invention, step S5 further includes: S51: preprocessing the second low-fidelity data by using a stacking algorithm and K-fold cross validation to obtain preprocessed second low-fidelity data; S52: Construct a feedforward neural network and use the feedforward neural network as the initial multi-fidelity digital twin network; S53: Substituting the preprocessed second low-fidelity data into the initial multi-fidelity digital twin network for training to obtain third low-fidelity data; S54: Construct a minimax game training network, calculate the difference between the third low-fidelity data and the high-fidelity data, and iterate the initial multi-fidelity digital twin network through the minimax game training network until the difference between the third low-fidelity data and the high-fidelity data converges, and use the iterated initial multi-fidelity digital twin network as the target multi-fidelity digital twin network.

[0008] According to a pipeline multi-fidelity digital twin method provided by the present invention, step S3 further includes: S31: filling the internal hollow area of ​​the pipeline model with entities, obtaining nodes in the pipeline model, and layering the pipeline model to obtain pipeline layers; S32: Acquire original low-fidelity data of nodes in the same pipeline layer as a layer node data set, and cluster the layer node data set layer by layer using geodesic distance to obtain the first low-fidelity data.

[0009] The present invention also provides a pipeline multi-fidelity digital twin system, comprising: High-fidelity data acquisition module: used to build a full-size pipeline test platform, conduct pipeline load tests on the pipeline through the full-size pipeline test platform, and obtain high-fidelity data; Original low-fidelity data acquisition module: used to construct a finite element simulation network, construct a pipeline model, simulate the pipeline model through the finite element simulation network, and obtain original low-fidelity data; A first low-fidelity data acquisition module: used for clustering the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; A second low-fidelity data acquisition module: used to construct a first regression tree set, obtain regression tree residuals through the first low-fidelity data, substitute the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, construct a loss function, construct an intermediate regression tree through the loss function, merge the intermediate regression tree into the initial second regression tree set and iterate the initial second regression tree set to obtain a target second regression tree set, predict the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data; Multi-fidelity digital twin network training module: used to preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain the target multi-fidelity digital twin network.

[0010] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a pipeline multi-fidelity digital twin method as described in any one of the above are implemented.

[0011] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a pipeline multi-fidelity digital twin method as described in any one of the above.

[0012] The present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the steps of a pipeline multi-fidelity digital twin method as described in any one of the above-mentioned methods.

[0013] The above one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: The present invention provides a pipeline multi-fidelity digital twin method, system, equipment, product and medium, which can complete the training of the multi-fidelity digital twin network through the digital twin technology. The multi-fidelity digital twin network after training can process the simulation data of the pipeline structure, and convert the low-fidelity data obtained by simulation into data with higher prediction accuracy, solving the problem that the simulation data of the pipeline has low fidelity and does not match the actual situation; The present invention utilizes regression tree iteration and multi-fidelity digital twin networks to fuse low-fidelity data obtained by numerical simulation with high-fidelity data obtained by full-scale tests, trains the multi-fidelity digital twin networks, and improves the accuracy of structural response prediction.

[0014] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of a pipeline multi-fidelity digital twin method provided by the present invention.

[0017] Figure 2It is an overall schematic diagram of the installation method of a pipeline in a full-size pipeline test platform provided by the present invention for a pipeline multi-fidelity digital twin method.

[0018] Figure 3 It is a cross-sectional schematic diagram of an installation method of a pipeline in a full-size pipeline test platform provided by the present invention for a pipeline multi-fidelity digital twin method.

[0019] Figure 4 It is a schematic diagram of a pipeline model of a pipeline multi-fidelity digital twin method provided by the present invention.

[0020] Figure 5 It is a schematic diagram of the result of clustering layer node data sets layer by layer in a pipeline multi-fidelity digital twin method provided by the present invention.

[0021] Figure 6 It is a structural schematic diagram of a pipeline multi-fidelity digital twin system provided by the present invention.

[0022] Figure 7 A schematic diagram of the structure of a pipeline multi-fidelity digital twin device provided by the present invention.

[0023] Figure numerals: 1. test tube; 11. tail end cover; 12. pressure liquid; 13. vibration clamp; 2. pipeline; 100. high-fidelity data acquisition module; 200. original low-fidelity data acquisition module; 300. first low-fidelity data acquisition module; 400. second low-fidelity data acquisition module; 500. multi-fidelity digital twin network training module; 810. processor; 820. communication interface; 830. memory; 840. communication bus. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme in the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0025] Furthermore, the terms “first”, “second”, and “third” are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0026] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0027] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0028] Combine the following Figure 1 Embodiments of the present invention are described.

[0029] Figure 1 The present invention is a flow chart of a pipeline multi-fidelity digital twin method. The present invention preferably adopts an embodiment. The specific implementation process of this embodiment is divided into 5 steps, wherein S1 is the acquisition of high-fidelity data, including full-scale deep-sea pipeline testing, sensor data collection and processing, and finally obtaining high-fidelity data. S2 to S4 are the acquisition of low-fidelity data, including constructing a finite element simulation network for finite element analysis, clustering the finite element result data, and obtaining the second low-fidelity data through regression tree iteration. S5 is the construction of a multi-fidelity digital twin network, including pre-processing the second low-fidelity data through K-fold cross validation and stacking algorithm ensemble learning, network construction of the multi-fidelity digital twin network, obtaining the third low-fidelity data, and completing the training through the third low-fidelity data and high-fidelity data.

[0030] The present invention provides a pipeline multi-fidelity digital twin method, comprising: S1: Build a full-scale pipeline test platform, conduct pipeline load tests on the pipeline through the full-scale pipeline test platform, and obtain high-fidelity data; Furthermore, the purpose of this phase is to build a full-scale pipeline test platform, conduct pipeline load tests on the pipeline through the full-scale pipeline test platform, collect data from the measurement points of the pipeline during the pipeline load test, and obtain high-fidelity data.

[0031] First, a full-size pipeline test platform is built. The full-size pipeline test platform built in this embodiment has a total length of 11.5m, an inner diameter of 1.25m, a designed pressure bearing capacity of 120MPa, and can accommodate full-size test pipes with a length of less than 8m. It has the loading functions of external water pressure, axial force, torque, bending moment, and vibration of the pipeline. The full-size pipeline test platform includes a sensor system composed of strain gauges, acceleration sensors, wires, and watertight penetration interfaces, and also includes a data acquisition system composed of a data acquisition instrument, a data cable, a computer, and data acquisition software. In addition, the full-size pipeline test platform also includes a test support system, an automatic pressurization system, and an automatic opening and closing system for the hatch cover, which can realize the automated operation and remote control of the test process.

[0032] Then, pipeline 2 is obtained and installed in a full-scale pipeline test platform. Figure 2 This is an overall schematic diagram of the installation method of pipeline 2 in the full-scale pipeline test platform. Figure 3 The schematic cross-sectional view of the installation method of the pipeline 2 in the full-size pipeline test platform. In this embodiment, the pipeline 2 adopts a full-size X65 seamless thin-walled pipeline with a total length of 7755 mm, a diameter of 406 mm, and a wall thickness of 10 mm. The geometric parameters of the pipeline 2 are measured and the pipeline 2 is polished, the positions of multiple measuring points on the pipeline 2 and the performance parameters of the pipeline 2 are determined, the strain gauges and acceleration sensors in the sensor system are glued to the measuring points of the pipeline 2 and the wires are welded, the pipeline 2 is clamped with a vibration clamp 13, and the tail end cover 11 is installed at the tail of the pipeline 2. The pipeline 2 is fixed in the test tube 1 through the vibration clamp 13 and the tail end cover 11, wherein the test tube 1 is fixed on the full-size pipeline test platform; then, the pressure liquid 12 is injected into the test tube 1, and a pre-test is performed. After passing the pre-test, the test parameters of the full-size pipeline test platform are determined according to the performance parameters, and the pipeline load test is performed on the pipeline 2 according to the test parameters to obtain high-fidelity data until the pipeline 2 is crushed and fails. During the pipeline load test, the sensor system and data acquisition system can continuously obtain high-fidelity data at the measurement points.

[0033] S2: constructing a finite element simulation network, constructing a pipeline model, and simulating the pipeline model through the finite element simulation network to obtain original low-fidelity data; Furthermore, in this stage, a finite element simulation network is constructed, and a pipeline model is constructed at the same time, where Figure 4It is a schematic diagram of the pipeline model. According to the load and geometric symmetry, a 1 / 2 symmetric model is established for the pipeline and the fluid in the cabin as the pipeline model. The pipeline model is divided using the 8-node non-coordinated unit C3D8I, and the fixed structure attached to the pipeline model is set as a symmetrical rigid body constraint; for the finite element simulation network, the liquid environment in which the pipeline model is located is established, and the Euler calculation domain is used for simulation. The normal zero velocity boundary is used on the fluid symmetry surface, and the constant pressure boundary condition is used on the outer surface of the fluid to simulate the deep-sea constant pressure condition. The general contact algorithm is used to simulate the interaction of the Euler body. The Euler calculation domain is meshed using the 8-node linear simplified integration unit EC3D8R.

[0034] The finite element simulation network is used to simulate the pipeline model to obtain strain, stress, displacement and other data. The strain, stress, displacement and other data on the pipeline model are extracted, exported and sorted to obtain the original low-fidelity data.

[0035] S3: clustering the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; Furthermore, the purpose of this stage is to cluster the original low-fidelity data in layers to obtain the first low-fidelity data, so as to reduce the amount of original low-fidelity data, thereby reducing the time and computing resources consumed by subsequent processes, and solving the problem that the geodesic distance of internal nodes of the model is difficult to calculate, and avoiding the phenomenon of local optimality, that is, the clustering results are more inclined to achieve the optimal locally rather than the optimal globally, and also avoid the clustering center being outside the model range.

[0036] Wherein, step S3 further comprises: S31: filling the internal hollow area of ​​the pipeline model with entities, obtaining nodes in the pipeline model, and layering the pipeline model to obtain pipeline layers; S32: Acquire original low-fidelity data of nodes in the same pipeline layer as a layer node data set, and cluster the layer node data set layer by layer using geodesic distance to obtain the first low-fidelity data.

[0037] With respect to the above steps, the specific implementation methods in this embodiment are as follows: First, fill the internal hollow area of ​​the pipeline model with entities, then obtain nodes in the pipeline model and extract the original low-fidelity data on the nodes; layer the pipeline model from outside to inside according to the modeling accuracy of the pipeline model to obtain pipeline layers, and use the original low-fidelity data of the nodes in the same pipeline layer as the layer node data set. Finally, cluster the layer node data set layer by layer from outside to inside by geodesic distance until all nodes of the pipeline model are clustered and the first low-fidelity data is obtained. The geodesic distance is the shortest distance between two points along the surface path of the pipeline model as the distance between nodes. Figure 5This is a schematic diagram of the result of clustering the layer node data set layer by layer.

[0038] S4: constructing a first regression tree set, obtaining regression tree residuals through the first low-fidelity data, substituting the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, constructing a loss function, constructing an intermediate regression tree through the loss function, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set to obtain a target second regression tree set, predicting the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data; Furthermore, the purpose of this stage is to obtain the second low-fidelity data. First, the first regression tree set is constructed, and the initial second regression tree set is constructed through the first low-fidelity data and the first regression tree set. Then, the intermediate regression tree is constructed through the sample residuals of the child nodes of the initial second regression tree set, and the intermediate regression tree is continuously merged into the initial second regression tree set and the initial second regression tree set is iterated to obtain the target second regression tree set, and finally the first low-fidelity data is converted into the second low-fidelity data using the target second regression tree set.

[0039] Wherein, step S4 further comprises: S41: constructing a first regression tree set, determining an initial prediction, an actual target, and a preset number of regression trees through first low-fidelity data, calculating a residual between the initial prediction and the actual target to obtain a regression tree residual, substituting the regression tree residual into the first regression tree set to obtain an initial second regression tree set; S42: construct a loss function, and calculate the sample residual of the initial second regression tree set through the loss function; S43: constructing an intermediate regression tree through sample residuals, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set until the number of regression trees in the initial second regression tree set reaches a preset number of regression trees, and using the iterated initial second regression tree set as the target second regression tree set; S44: Substitute the first low-fidelity data into the target second regression tree set, and predict the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data.

[0040] With respect to the above steps, the specific implementation methods in this embodiment are as follows: First, the first regression tree set is constructed by fitting the regression objective function through the second-order Taylor expansion and the regression tree regularization term. Then, the initial prediction and the actual target of the first low-fidelity data are calculated. The preset number of regression trees is determined according to the first low-fidelity data. The difference between the initial prediction and the actual target can be used to obtain the regression tree residual. Subsequently, the regression tree residual is substituted into each child node of the first regression tree set to obtain the initial second regression tree set. Then, a loss function is constructed, and the sample residual of the initial second regression tree set is calculated through the loss function.

[0041] Further, a blank intermediate regression tree is established and the sample residuals are substituted into each child node of the intermediate regression tree to construct the intermediate regression tree, and the intermediate regression tree is merged into the initial second regression tree set; the process of "establishing a blank intermediate regression tree and substituting the sample residuals into each child node of the intermediate regression tree to construct the intermediate regression tree, and merging the intermediate regression tree into the initial second regression tree set" is repeated and iterated until the number of regression trees in the initial second regression tree set reaches the preset number of regression trees, and the iterated initial second regression tree set is used as the target second regression tree set. Finally, the first low fidelity is substituted into the target second regression tree set for prediction to obtain the second low fidelity data.

[0042] Furthermore, the first low-fidelity data can be divided into a training set and a test set. In this embodiment, the training set accounts for 80% of the first low-fidelity data, and the test set accounts for 20%. The training set is used to replace the first low-fidelity data to obtain the second low-fidelity data, and the validity of the second low-fidelity data is verified by calculating the difference between the test set and the second low-fidelity data. When the difference between the second low-fidelity data and the test set is less than a threshold, the second low-fidelity data is considered to be valid.

[0043] S5: Preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain a target multi-fidelity digital twin network.

[0044] Furthermore, in this stage, in order to obtain the target multi-fidelity digital twin network, after preprocessing the second low-fidelity data to obtain preprocessed second low-fidelity data, the third low-fidelity data is obtained through the initial multi-fidelity digital twin network and the preprocessed second low-fidelity data, and the difference between the third low-fidelity data and the high-fidelity data is calculated; at the same time, a minimax game training network is constructed, and the initial multi-fidelity digital twin network is iterated using the minimax game training network until the difference between the third low-fidelity data and the high-fidelity data converges, completing the training of the multi-fidelity digital twin network and obtaining the target multi-fidelity digital twin network.

[0045] Wherein, step S5 further comprises: S51: preprocessing the second low-fidelity data by using a stacking algorithm and K-fold cross validation to obtain preprocessed second low-fidelity data; S52: Construct a feedforward neural network and use the feedforward neural network as the initial multi-fidelity digital twin network; S53: Substituting the preprocessed second low-fidelity data into the initial multi-fidelity digital twin network for training to obtain third low-fidelity data; S54: Construct a minimax game training network, calculate the difference between the third low-fidelity data and the high-fidelity data, and iterate the initial multi-fidelity digital twin network through the minimax game training network until the difference between the third low-fidelity data and the high-fidelity data converges, and use the iterated initial multi-fidelity digital twin network as the target multi-fidelity digital twin network.

[0046] With respect to the above steps, the specific implementation methods in this embodiment are as follows: First, the second low-fidelity data is preprocessed by stacking algorithm and K-fold cross validation. The preprocessing process is divided into two steps, namely, firstly, the second low-fidelity data is divided by K-fold cross validation, and then the second low-fidelity data after data division is integrated and learned by stacking algorithm, and the preprocessed second low-fidelity data is used as the preprocessed second low-fidelity data. Then, a feedforward neural network is constructed, and the feedforward neural network is used as the initial multi-fidelity digital twin network. Then, the preprocessed second low-fidelity data is substituted into the initial multi-fidelity digital twin network for training to obtain the third low-fidelity data. Furthermore, a minimax game training network is constructed, and the third low-fidelity data and high-fidelity data are played through the minimax game training network. The initial multi-fidelity digital twin network is iterated according to the game results, and the difference between the third low-fidelity data and the high-fidelity data is calculated until the difference between the third low-fidelity data and the high-fidelity data is less than the threshold to achieve convergence, that is, the training of the multi-fidelity digital twin network is completed, and the iterated initial multi-fidelity digital twin network is used as the target multi-fidelity digital twin network.

[0047] The present invention also verifies the effectiveness of a pipeline multi-fidelity digital twin method. During the verification process, the global accuracy of the multi-fidelity digital twin network is evaluated by the root mean square error (RRMSE), and the maximum relative error (RE) is used to evaluate the global accuracy of the multi-fidelity digital twin network. max Evaluate the local accuracy, root mean square error (RRMSE), and maximum relative error (RE) of multi-fidelity digital twin networks max The expression is as follows: in, represents the amount of high-fidelity data, Indicates The value of high-fidelity data at each measurement point, represents the first The value of the third low-fidelity data at the measurement point, represents the mean of high-fidelity data, Represents the value of high-fidelity data at the most dangerous test point, It represents the value of the third lowest fidelity data at the most dangerous test point, where the most dangerous test point is the measurement point corresponding to the maximum value of the Mises stress value in the high fidelity data. Table 1 shows the root mean square error RRMSE, maximum relative error RE of the present invention and other proxy models max Comparison of training time and multi-fidelity digital twin network is the method proposed in the present invention: Table 1 Comparison of prediction accuracy and training time of surrogate models using different methods

[0048] It can be seen that compared with proxy models based on single-fidelity data and other multi-fidelity models, the multi-fidelity digital twin network has higher global and local accuracy while also having a more reasonable training time.

[0049] A pipeline multi-fidelity digital twin system provided by the present invention is described below. The pipeline multi-fidelity digital twin system described below and the pipeline multi-fidelity digital twin method described above can refer to each other.

[0050] Figure 6 The following is a schematic diagram of the structure of a pipeline multi-fidelity digital twin system. Figure 6 As shown, a pipeline multi-fidelity digital twin method for executing the above-mentioned method includes: High-fidelity data acquisition module 100: used to build a full-size pipeline test platform, and perform pipeline load test on the pipeline through the full-size pipeline test platform to obtain high-fidelity data; The original low-fidelity data acquisition module 200 is used to construct a finite element simulation network, construct a pipeline model, and simulate the pipeline model through the finite element simulation network to obtain the original low-fidelity data; The first low-fidelity data acquisition module 300 is used to cluster the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; The second low-fidelity data acquisition module 400 is used to construct a first regression tree set, obtain regression tree residuals through the first low-fidelity data, substitute the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, construct a loss function, construct an intermediate regression tree through the loss function, merge the intermediate regression tree into the initial second regression tree set and iterate the initial second regression tree set to obtain a target second regression tree set, predict the first low-fidelity data through the target second regression tree set, and obtain second low-fidelity data; Multi-fidelity digital twin network training module 500: used to preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain a target multi-fidelity digital twin network.

[0051] on the other hand, Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute a pipeline multi-fidelity digital twin method, which includes: S1: Build a full-scale pipeline test platform, conduct pipeline load tests on the pipeline through the full-scale pipeline test platform, and obtain high-fidelity data; S2: constructing a finite element simulation network, constructing a pipeline model, and simulating the pipeline model through the finite element simulation network to obtain original low-fidelity data; S3: clustering the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; S4: constructing a first regression tree set, obtaining regression tree residuals through the first low-fidelity data, substituting the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, constructing a loss function, constructing an intermediate regression tree through the loss function, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set to obtain a target second regression tree set, predicting the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data; S5: Preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain a target multi-fidelity digital twin network.

[0052] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0053] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, and when the program instructions are executed by a computer, the computer can execute a pipeline multi-fidelity digital twin method provided by the above methods, the method comprising: S1: Build a full-scale pipeline test platform, conduct pipeline load tests on the pipeline through the full-scale pipeline test platform, and obtain high-fidelity data; S2: constructing a finite element simulation network, constructing a pipeline model, and simulating the pipeline model through the finite element simulation network to obtain original low-fidelity data; S3: clustering the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; S4: constructing a first regression tree set, obtaining regression tree residuals through the first low-fidelity data, substituting the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, constructing a loss function, constructing an intermediate regression tree through the loss function, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set to obtain a target second regression tree set, predicting the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data; S5: Preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain a target multi-fidelity digital twin network.

[0054] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute a pipeline multi-fidelity digital twin method provided by the above methods, the method comprising: S1: Build a full-scale pipeline test platform, conduct pipeline load tests on the pipeline through the full-scale pipeline test platform, and obtain high-fidelity data; S2: constructing a finite element simulation network, constructing a pipeline model, and simulating the pipeline model through the finite element simulation network to obtain original low-fidelity data; S3: clustering the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; S4: constructing a first regression tree set, obtaining regression tree residuals through the first low-fidelity data, substituting the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, constructing a loss function, constructing an intermediate regression tree through the loss function, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set to obtain a target second regression tree set, predicting the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data; S5: Preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain a target multi-fidelity digital twin network.

[0055] The above described system, device, product and medium embodiments are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Ordinary technicians in this field can understand and implement them without creative work.

[0056] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0057] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A pipeline multi-fidelity digital twin method, characterized in that: include: S1: Build a full-scale pipeline test platform, conduct pipeline load tests on the pipeline through the full-scale pipeline test platform, and obtain high-fidelity data; S2: constructing a finite element simulation network, constructing a pipeline model, and simulating the pipeline model through the finite element simulation network to obtain original low-fidelity data; S3: clustering the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; S4: constructing a first regression tree set, obtaining regression tree residuals through the first low-fidelity data, substituting the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, constructing a loss function, constructing an intermediate regression tree through the loss function, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set to obtain a target second regression tree set, predicting the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data; S5: Preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain a target multi-fidelity digital twin network.

2. A pipeline multi-fidelity digital twin method according to claim 1, characterized in that: Step S4 further comprises: S41: constructing a first regression tree set, determining an initial prediction, an actual target, and a preset number of regression trees through first low-fidelity data, calculating a residual between the initial prediction and the actual target to obtain a regression tree residual, substituting the regression tree residual into the first regression tree set to obtain an initial second regression tree set; S42: construct a loss function, and calculate the sample residual of the initial second regression tree set through the loss function; S43: constructing an intermediate regression tree through sample residuals, merging the intermediate regression tree into the initial second regression tree set and iterating the initial second regression tree set until the number of regression trees in the initial second regression tree set reaches a preset number of regression trees, and using the iterated initial second regression tree set as the target second regression tree set; S44: Substitute the first low-fidelity data into the target second regression tree set, and predict the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data.

3. A pipeline multi-fidelity digital twin method according to claim 1, characterized in that: Step S5 further comprises: S51: preprocessing the second low-fidelity data by using a stacking algorithm and K-fold cross validation to obtain preprocessed second low-fidelity data; S52: Construct a feedforward neural network and use the feedforward neural network as the initial multi-fidelity digital twin network; S53: Substituting the pre-processed second low-fidelity data into the initial multi-fidelity digital twin network for training to obtain third low-fidelity data; S54: Construct a minimax game training network, calculate the difference between the third low-fidelity data and the high-fidelity data, and iterate the initial multi-fidelity digital twin network through the minimax game training network until the difference between the third low-fidelity data and the high-fidelity data converges, and use the iterated initial multi-fidelity digital twin network as the target multi-fidelity digital twin network.

4. A pipeline multi-fidelity digital twin method according to claim 1, characterized in that: Step S3 further comprises: S31: filling the internal hollow area of ​​the pipeline model with entities, obtaining nodes in the pipeline model, and layering the pipeline model to obtain pipeline layers; S32: Acquire original low-fidelity data of nodes in the same pipeline layer as a layer node data set, and cluster the layer node data set layer by layer using geodesic distance to obtain the first low-fidelity data.

5. A pipeline multi-fidelity digital twin system, used to execute a pipeline multi-fidelity digital twin method as claimed in any one of claims 1 to 4, characterized in that: include: High-fidelity data acquisition module: used to build a full-size pipeline test platform, conduct pipeline load tests on the pipeline through the full-size pipeline test platform, and obtain high-fidelity data; Original low-fidelity data acquisition module: used to construct a finite element simulation network, construct a pipeline model, simulate the pipeline model through the finite element simulation network, and obtain original low-fidelity data; A first low-fidelity data acquisition module: used for clustering the original low-fidelity data by a hierarchical clustering method to obtain first low-fidelity data; A second low-fidelity data acquisition module: used to construct a first regression tree set, obtain regression tree residuals through the first low-fidelity data, substitute the regression tree residuals into the first regression tree set to obtain an initial second regression tree set, construct a loss function, construct an intermediate regression tree through the loss function, merge the intermediate regression tree into the initial second regression tree set and iterate the initial second regression tree set to obtain a target second regression tree set, predict the first low-fidelity data through the target second regression tree set to obtain second low-fidelity data; Multi-fidelity digital twin network training module: used to preprocess the second low-fidelity data to obtain preprocessed second low-fidelity data, construct an initial multi-fidelity digital twin network, train the preprocessed second low-fidelity data through the initial multi-fidelity digital twin network to obtain third low-fidelity data, construct a minimax game training network, iterate the initial multi-fidelity digital twin network through the minimax game training network, high-fidelity data and third low-fidelity data to obtain the target multi-fidelity digital twin network.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a pipeline multi-fidelity digital twin method as described in any one of claims 1 to 4 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a pipeline multi-fidelity digital twin method as described in any one of claims 1 to 4 are implemented.

8. A computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, characterized in that: When the program instructions are executed by a computer, the computer can perform the steps of a pipeline multi-fidelity digital twin method as described in any one of claims 1 to 4.

Images