Multi-fidelity data fusion method, device, equipment, medium and product

Abstract

The invention discloses a multi-fidelity data fusion method and device, equipment, a medium and a product, and relates to the field of structural health monitoring, and the method comprises the steps: carrying out a structural damage expansion test on a sample piece, and obtaining a damage state parameter value set and a first structural response data set; performing static simulation of the test on each simulation model in the first simulation model set to obtain a second structure response data set; performing static simulation of the test on each simulation model in the second simulation model set to obtain a third structure response data set; training the first neural network according to the third structure response data set and each preset damage state parameter value to obtain a low-fidelity network; according to the first structure response data set, the second structure response data set and the damage state parameter value at each moment, training a second neural network to obtain a feature mapping network; and constructing a structural damage evaluation model according to the trained network. The structural damage evaluation model training method is suitable for structural damage evaluation model training.

Description

Technical Field

[0001] The present application relates to the field of structural health monitoring, and in particular to a multi-fidelity data fusion method, device, equipment, medium and product. Background Art

[0002] Structural health monitoring technology uses monitoring data collected during the operation of a pre-established structural damage assessment model to assess the damage state of the structure. The training of such structural damage assessment models requires a large amount of reliable high-fidelity damage data as support. However, for large and complex structures, it is unrealistic to conduct a large number of destructive damage tests to obtain high-fidelity damage data for model training. In contrast, damage simulation based on structural models is more feasible and can generate a large amount of damage data in a shorter time and at a lower cost. However, the fidelity of the damage data obtained by these simulations is relatively low, resulting in a lack of high-fidelity data and low accuracy of low-fidelity data, which is not conducive to the training of structural damage assessment models.

[0003] The existing multi-fidelity data fusion algorithms are usually used for model training in forward problem solving. However, the structural damage assessment problem is an inverse problem, and the existing multi-fidelity data fusion algorithms are not suitable for structural damage assessment model training. Summary of the invention

[0004] The purpose of this application is to provide a multi-fidelity data fusion method, device, equipment, medium and product suitable for structural damage assessment model training.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In the first aspect, the present application provides a multi-fidelity data fusion method, comprising: conducting a structural damage extension test on a sample, and collecting damage state parameter values ​​on the sample at each moment during the structural damage extension test and structural response data of a preset position of the sample under each damage state parameter value, to obtain a damage state parameter value set and a first structural response data set.

[0007] A static simulation of a structural damage extension test is performed on each simulation model in the first simulation model set, and structural response data of a preset position of each simulation model in the first simulation model set is obtained to obtain a second structural response data set; the first simulation model set includes multiple simulation models obtained by processing the simulation model of the sample according to each damage state parameter value in the damage state parameter value set.

[0008] Static simulation of the structural damage extension test is performed on each simulation model in the second simulation model set, and the structural response data of the preset position of each simulation model in the second simulation model set is obtained to obtain a third structural response data set; the second simulation model set includes multiple simulation models obtained by processing the simulation model of the sample according to each preset damage state parameter value.

[0009] The first neural network is trained according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network.

[0010] According to the first structural response data set, the second structural response data set and the damage state parameter values ​​at each moment, the second neural network is trained to obtain a feature mapping network.

[0011] A structural damage assessment model is constructed according to a low-fidelity network and a feature mapping network; the structural damage assessment model includes a feature mapping network and a low-fidelity network connected in sequence.

[0012] Optionally, the first neural network is trained according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network, specifically comprising: taking the structural response data in the third structural response data set as input, taking each preset damage state parameter value as output, and taking minimizing the value of the first loss function as the goal, and training the first neural network to obtain a low-fidelity network.

[0013] Optionally, according to the first structural response data set, the second structural response data set and the damage state parameter values ​​at each moment, the second neural network is trained to obtain a feature mapping network, specifically including: constructing an overall network; the overall network includes a second neural network and a low-fidelity network connected in sequence.

[0014] The structural response data in the first structural response data set is used as the input of the second neural network, the structural response data in the second structural response data set is used as the output of the second neural network, the damage state parameter value at each moment is used as the output of the low-fidelity network, and the goal is to minimize the value of the second loss function. The second neural network in the overall neural network is trained to obtain a feature mapping network.

[0015] Optionally, the first loss function for: ,in, Represents the total number of preset damage state parameter values, Indicates that the third structure response data set The output obtained by inputting the structural response data into the first neural network is Indicates the third structure response data set The preset damage state parameter value corresponding to the structural response data is Calculates the square of the absolute value.

[0016] Optionally, the second loss function for: ,in, represents the total number of damage state parameter values ​​collected at each moment, Indicates that The output of the low-fidelity network is input, Represents the first structure response data set The damage state parameter value corresponding to the structural response data is: represents the weight coefficient, Indicates that the first structure response data set The output obtained by inputting the structural response data into the second neural network is Indicates the first Structural response data, Calculates the square of the absolute value.

[0017] Optionally, when the damage state parameter value is the crack length, a structural damage extension test is performed on the sample, and the damage state parameter values ​​of the sample at each moment during the structural damage extension test and the structural response data of the preset position of the sample at each damage state parameter value are collected to obtain a damage state parameter value set and a first structural response data set. Specifically, a structural crack extension test is performed on the sample, and the crack lengths of the sample at each moment during the structural crack extension test and the structural response data of the preset position of the sample at each crack length are collected to obtain a damage state parameter value set and a first structural response data set.

[0018] In the second aspect, the present application provides a multi-fidelity data fusion device, including: a test module, used to perform a structural damage extension test on a sample, and collect damage state parameter values ​​on the sample at each moment during the structural damage extension test and structural response data of a preset position of the sample under each damage state parameter value, to obtain a damage state parameter value set and a first structural response data set.

[0019] The first simulation module is used to perform static simulation of structural damage extension test on each simulation model in the first simulation model set, obtain structural response data of a preset position of each simulation model in the first simulation model set, and obtain a second structural response data set; the first simulation model set includes multiple simulation models obtained by processing the simulation model of the sample according to each damage state parameter value in the damage state parameter value set.

[0020] The second simulation module is used to perform static simulation of structural damage extension test on each simulation model in the second simulation model set, obtain structural response data of a preset position of each simulation model in the second simulation model set, and obtain a third structural response data set; the second simulation model set includes multiple simulation models obtained by processing the simulation model of the sample according to each preset damage state parameter value.

[0021] The first training module is used to train the first neural network according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network.

[0022] The second training module is used to train the second neural network to obtain a feature mapping network according to the first structural response data set, the second structural response data set and the damage state parameter value at each moment.

[0023] The structural damage assessment model construction module is used to construct a structural damage assessment model based on a low-fidelity network and a feature mapping network; the structural damage assessment model includes a feature mapping network and a low-fidelity network connected in sequence.

[0024] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the multi-fidelity data fusion methods described above.

[0025] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the multi-fidelity data fusion methods described above.

[0026] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the multi-fidelity data fusion methods described above.

[0027] According to the specific embodiments provided by the present application, the present application has the following technical effects: the present application provides a multi-fidelity data fusion method, device, equipment, medium and product. In the positive problem, the data features of the high-fidelity and low-fidelity data sets used for model training have the same spatial distribution; while in the structural damage assessment problem, the data features of the high-fidelity and low-fidelity data sets used for model training often have different spatial distributions. Existing multi-fidelity data fusion algorithms are difficult to effectively handle the difference in the distribution space of high-fidelity and low-fidelity data features, which makes it difficult to directly apply them to the training of structural damage assessment models. The structural response data obtained by the experiment is high-fidelity data, and the data obtained by simulation is low-fidelity data. The feature mapping network of the present application uses high-fidelity structural response data from the experiment and low-fidelity structural response data from the simulation with the same damage state parameter value for training, which can realize the mapping of the feature space of high-fidelity data to the feature space of low-fidelity data, solving the problem that the existing multi-fidelity data fusion algorithm is difficult to effectively handle the difference in the distribution space of high-fidelity and low-fidelity data features, and is suitable for the training of structural damage assessment models. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 A flow chart of a multi-fidelity data fusion method provided in one embodiment of the present application.

[0030] Figure 2 A schematic diagram of a multi-fidelity data fusion method provided in an embodiment of the present application.

[0031] Figure 3 This is a schematic diagram of the first neural network structure provided in this application.

[0032] Figure 4 A schematic diagram of the second neural network structure provided for this application.

[0033] Figure 5 A structural diagram of a test piece provided in one embodiment of the present application.

[0034] Figure 6 This is a graph showing the error reduction during the first neural network training process in one embodiment of the present application.

[0035] Figure 7 This is a graph of the prediction results of the first neural network in the test set in one embodiment of the present application.

[0036] Figure 8This is a graph showing the error reduction during the second neural network training process in one embodiment of the present application.

[0037] Fig. 9 A diagram of damage state parameter prediction results in a structural damage assessment scenario using a multi-fidelity data fusion method provided in an embodiment of the present application.

[0038] Fig.10 A neural network architecture diagram for comparing model effects.

[0039] Fig.11 The following are the prediction results of each comparison model.

[0040] Fig.12 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0043] In an exemplary embodiment, Figure 1 As shown, a multi-fidelity data fusion method is provided, including the following steps 201 to 206.

[0044] Step 201: Perform a structural damage extension test on the sample and collect the damage state parameter values ​​of the sample at each moment during the structural damage extension test. And the structural response data of the preset position of the sample under each damage state parameter value , a set of damage state parameter values ​​and a first set of structural response data are obtained. Specifically, multiple sets of high-fidelity data are obtained by performing structural damage extension tests on samples containing damaged structures. The high-fidelity data include damage state parameter values ​​and corresponding structural response data.

[0045] Step 202: Perform static simulation of a structural damage extension test on each simulation model in the first simulation model set to obtain structural response data of a preset position of each simulation model in the first simulation model set. , and obtain a second structural response data set; the first simulation model set includes multiple simulation models obtained by processing the simulation model of the sample according to each damage state parameter value in the damage state parameter value set. The second structural response data set, the damage state parameter value set and the first structural response data set constitute a multi-fidelity data set. Specifically, the load corresponding to the damage state parameter value at each moment of step 201 is sampled, and a static simulation of the structure with a damaged state is carried out. During the static simulation process, the structural damage parameter value in the simulation model is the same as the structural damage parameter value measured in the test, and the static load size in the simulation corresponds one-to-one to the load size when the structural damage parameter value is collected in the test.

[0046] Step 203: Perform static simulation of the structural damage extension test on each simulation model in the second simulation model set to obtain structural response data of a preset position of each simulation model in the second simulation model set. , and obtain the third structural response data set; the second simulation model set includes the preset damage state parameter values ​​according to The simulation models of the samples are processed respectively to obtain multiple simulation models. The third structural response data set and each preset damage state parameter value constitute a low-fidelity data set. Specifically, global sampling is carried out within the reasonable value range of the damage state parameter. The preset damage state parameter value is used and the corresponding low-fidelity structural response data is obtained through simulation.

[0047] Step 204: training the first neural network according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network.

[0048] Step 205: According to the first structural response data set, the second structural response data set and the damage state parameter values ​​at each moment, the second neural network is trained to obtain a feature mapping network.

[0049] Step 206: construct a structural damage assessment model based on the low-fidelity network and the feature mapping network; the structural damage assessment model includes the feature mapping network and the low-fidelity network connected in sequence. Structural damage assessment can be achieved by inputting the structural response data obtained by the airborne health monitoring sensor into the structural damage assessment model as a high-fidelity signal feature.

[0050] The above steps 201 to 206 may be implemented for training a structural damage assessment model.

[0051] In another exemplary embodiment of the present application, the first neural network is trained according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network, specifically comprising: taking the structural response data in the third structural response data set as input, taking each preset damage state parameter value as output, and taking minimizing the value of the first loss function as the goal, to train the first neural network to obtain a low-fidelity network.

[0052] In another exemplary embodiment of the present application, the second neural network is trained according to the first structural response data set, the second structural response data set and the damage state parameter values ​​at each moment to obtain a feature mapping network, specifically including: constructing an overall network; the overall network includes a second neural network and a low-fidelity network connected in sequence.

[0053] The structural response data in the first structural response data set is used as the input of the second neural network, the structural response data in the second structural response data set is used as the output of the second neural network, the damage state parameter value at each moment is used as the output of the low-fidelity network, and the goal is to minimize the value of the second loss function. The second neural network in the overall neural network is trained to obtain a feature mapping network.

[0054] In another exemplary embodiment of the present application, the first loss function for: ,in, Represents the total number of preset damage state parameter values, Indicates that the third structure response data set The output obtained by inputting the structural response data into the first neural network is Indicates the third structure response data set The preset damage state parameter value corresponding to the structural response data is Calculates the square of the absolute value.

[0055] In another exemplary embodiment of the present application, the second loss function for: ,in, represents the total number of damage state parameter values ​​collected at each moment, Indicates that The output of the low-fidelity network is input, Represents the first structure response data set The damage state parameter value corresponding to the structural response data is: represents the weight coefficient, Indicates that the first structure response data set The output obtained by inputting the structural response data into the second neural network is Indicates the first Structural response data, Indicates the calculation of the square of the absolute value. In this loss function, Corresponding to the prediction error ,and This corresponds to the feature mapping error .

[0056] In another exemplary embodiment of the present application, when the damage state parameter value is the crack length, a structural damage extension test is performed on the sample, and the damage state parameter values ​​of the sample at each moment during the structural damage extension test and the structural response data of the preset position of the sample at each damage state parameter value are collected to obtain a damage state parameter value set and a first structural response data set. Specifically, a structural crack extension test is performed on the sample, and the crack lengths of the sample at each moment during the structural crack extension test and the structural response data of the preset position of the sample at each crack length are collected to obtain a damage state parameter value set and a first structural response data set.

[0057] In another exemplary embodiment of the present application, when the damage state parameter value is the crack length, a static simulation of a structural damage extension test is performed on each simulation model in the first simulation model set, and the structural response data of a preset position of each simulation model in the first simulation model set is obtained to obtain the second structural response data set. Specifically, a first simulation model set is constructed; the first simulation model set includes a plurality of simulation models obtained by inserting cracks of various crack lengths in the damage state parameter value set into the simulation model of the sample.

[0058] A static simulation of a structural crack propagation test is performed on each simulation model in the first simulation model set, and structural response data of a preset position of each simulation model in the first simulation model set is obtained to obtain a second structural response data set.

[0059] In another exemplary embodiment of the present application, when the damage state parameter value is the crack length, a static simulation of a structural damage extension test is performed on each simulation model in the second simulation model set, and the structural response data of a preset position of each simulation model in the second simulation model set is obtained to obtain a third structural response data set, which specifically includes: constructing a second simulation model set; the second simulation model set includes a plurality of simulation models obtained by inserting cracks of each preset crack length into the simulation model of the sample.

[0060] Static simulation of the structural crack propagation test is performed on each simulation model in the second simulation model set, and structural response data of a preset position of each simulation model in the second simulation model set is obtained to obtain a third structural response data set.

[0061] In another exemplary embodiment of the present application, when the damage state parameter value is the crack length, the first neural network is trained according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network, specifically: the first neural network is trained according to the third structural response data set and each preset crack length to obtain a low-fidelity network.

[0062] In another exemplary embodiment of the present application, when the damage state parameter value is the crack length, the second neural network is trained according to the first structural response data set, the second structural response data set and the damage state parameter value at each moment to obtain a feature mapping network. Specifically: according to the first structural response data set, the second structural response data set and the crack length at each moment, the second neural network is trained to obtain a feature mapping network.

[0063] In another exemplary embodiment of the present application, the structural response data is stress, strain or displacement.

[0064] This application provides a specific embodiment, such as Figure 2 As shown, the above multi-fidelity data fusion method is described in detail, which specifically includes the following steps 1 to 4.

[0065] Step 1: Construct a dataset for model training through structural damage extension test and damage simulation.

[0066] Step 1.1: Figure 5 As shown, the test piece is a simple sample with an artificial prefabricated notch, and its material is 2A12-T4 aluminum alloy. The size of the sample is 50mm 200mm 3mm, with a size of 1mm in the longitudinal middle of the sample 6mm 3mm artificial prefabricated notch. Four FBG strain sensors are pasted on the sample, numbered 1 to 4. FBG strain sensor No. 1 is 50mm away from the upper end of the test piece and is in the middle in the horizontal direction; FBG strain sensors No. 2 to No. 4 are 85mm away from the upper end of the test piece and are evenly distributed in the horizontal direction.

[0067] Step 1.2: Construct a multi-fidelity data set through experiments and static simulations. First, a structural crack growth test is carried out. The load is a tensile cyclic load applied to both ends of the specimen, and the stress ratio of the load cycle is 0.1. When measuring the crack length and structural strain response, the load is maintained at 55% of the peak value of the cyclic load. During the test, the crack length continues to grow, and the crack length is measured at regular intervals. A total of 34 sets of crack lengths and high-fidelity measured strain values ​​at the corresponding moments are measured. Then, a simulation model corresponding to the specimen is established, and cracks of the lengths measured above are inserted into the expected crack growth path behind the prefabricated notch, such as Figure 5 As shown in the figure, 34 simulation models are obtained, and static simulation is performed under a constant load (i.e., 55% of the cyclic load) to obtain low-fidelity simulation strain values ​​corresponding to the test data, i.e., 34 strain values ​​corresponding to the crack lengths collected above. Finally, the high-fidelity measured strain values, crack lengths, and low-fidelity simulation strain values ​​are combined to form a multi-fidelity data set.

[0068] Step 1.3: Construct a low-fidelity data set through static simulation. According to the test results of step 1.2 above, the maximum crack length of the sample before the unstable fracture is about 35mm~37mm. Therefore, 350 values ​​are randomly sampled in the range of [1mm, 35mm] to obtain the preset crack length. Through batch simulation, and extracting the low-fidelity simulation strain value at the same position as the real sensor, a low-fidelity data set is constructed according to the preset crack length inserted into the model and the low-fidelity simulation strain value corresponding to each preset crack length.

[0069] Step 2: Build and train the first neural network to get a low-fidelity network . The structure and training method of the first neural network, such as Figure 3 As shown, the input of the first neural network is the low-fidelity simulated strain value in the low-fidelity data set, and the output is the predicted crack length. The number of neurons in the input layer and the number of neurons in the output layer of the network are determined by the number of channels of the structural response data, while the number of layers of the internal hidden layer, the number of neurons in each layer and other hyperparameters are set according to conventional methods as needed. According to the specific circumstances of this embodiment, the input layer of the network is 4 neurons, corresponding to 4 FBG strain sensors respectively; the output layer is 1 neuron, corresponding to the crack length; 1 hidden layer is set, which contains 4 neurons. The network uses the tanh activation function and the Adam training algorithm. The initial value of the learning rate is set to 0.01, and a learning rate decreasing training strategy is adopted. The low-fidelity data set is randomly divided into three parts in a ratio of 0.8:0.1:0.1, which are used as the training set, validation set and test set of the low-fidelity network respectively. The error decrease curve of the training process is shown in the figure. Figure 6 As shown, the network performs well in the test set. Figure 7As shown, it can be seen that the network is fully trained and converged, and the prediction effect is good in the test set. The predicted root mean square error of the structural crack length is 0.0807mm.

[0070] Step 3: Build and train the second neural network to obtain the feature mapping network The network realizes the mapping of strain from high fidelity to low fidelity. The input and output of the network have the same number of neurons, and each neuron corresponds to a FBG strain sensor. After the first neural network training is completed, the network parameters remain fixed and the second neural network is connected in series. The structure and training method of the second neural network, such as Figure 4 As shown, the input of the second neural network is a high-fidelity measured strain value, and the output is a low-fidelity strain value; the low-fidelity strain value output by the network is input into the low-fidelity network to obtain the crack length output by the low-fidelity network. The input and output layers of the second neural network are determined by the number of channels of the structural response data, while other hyperparameters of the network are set in a conventional manner. According to the specific circumstances of this embodiment, the input layer and output layer of the network are both 4 neurons, corresponding to 4 FBG strain sensors respectively. The network is set with 1 hidden layer, which contains 8 neurons. The network uses the tanh activation function, the Adam training algorithm, the initial value of the learning rate is set to 0.01, and a learning rate decreasing training strategy is adopted. In order to facilitate the verification of the model effect, only 90% of the data in the multi-fidelity data set is used as the training set and the validation set in this embodiment. The error reduction curve results of the training process are shown in the figure. Figure 8 As shown, it can be seen that the network is fully trained and converged.

[0071] Step 4: Construct a structural damage assessment model based on the low-fidelity network and feature mapping network, deploy the structural damage assessment model online, and apply the structural damage assessment model to structural damage assessment. Use the remaining 10% of the data in the multi-fidelity dataset that did not participate in model training and verification as a test set to test the effect of the model. The high-fidelity measured strain value in the test set is used as input, and the output of the structural damage assessment model is the crack length prediction value. Its prediction effect is as follows: Fig. 9 As shown, the predicted root mean square error of the structural crack length is 0.6715 mm.

[0072] In order to verify the structural damage assessment model proposed in this application ( Fig.11 FM-MFNN is used in the inverse problem scenario of structural damage assessment. The most common multi-fidelity Gaussian process regression model ( Fig.11 ) and the classic multi-fidelity neural network ( Fig.11The multi-fidelity Gaussian process regression model is constructed using the most commonly used co-kriging algorithm, and uses the commonly used radial basis kernel function and zero mean assumption. The observation noise is 0.01, and the kernel function hyperparameters are optimized by maximum likelihood estimation. The architecture of the classic multi-fidelity neural network is as follows: Fig.10 As shown, it contains two networks, namely the low-fidelity network and high-fidelity correction network . The structure of is consistent with the low-fidelity network described in step 2 above, with the input being the low-fidelity simulation strain value, containing 4 neurons, and the output being the crack length prediction value, containing 1 neuron; The input is The output and high-fidelity measured strain value contain 5 neurons, and the output is the crack length prediction value, which contains 1 neuron. In order to avoid the influence of randomness such as training set division and model parameter initialization, the training and test verification of the above three models were repeated 100 times respectively, and the average value of the prediction error was taken to compare the model accuracy. In addition, the interquartile range (IQR) indicator of the model prediction error is used to evaluate the stability of the model. The prediction effect of the structural damage assessment model constructed in this application and the above two existing multi-fidelity algorithm models is as follows Fig.11 As shown, it can be seen that the average prediction error of the structural damage assessment model proposed in this application is 0.72mm, and the IQR range is 0.37; while the average prediction error of the multi-fidelity Gaussian process regression model is 0.78mm, and the IQR range is 0.69; the average prediction error of the classic multi-fidelity neural network is 2.43mm, and the IQR range is 1.70233084. It can be seen that the average prediction error and IQR range of the model proposed in this application are significantly lower than those of the existing algorithm model, indicating that the model proposed in this application has better prediction accuracy and model stability.

[0073] This application first constructs a data set for model training through structural damage extension tests and damage simulations; then uses low-fidelity data to train low-fidelity networks; further, uses multi-fidelity data sets to train feature mapping networks to achieve multi-fidelity data fusion; and finally deploys the model online to achieve accurate assessment of the structural damage state. It can be used to fuse multi-fidelity data in the inverse problem of structural damage assessment.

[0074] This application has the advantages of low demand for high-fidelity data and high accuracy in structural damage assessment. It can effectively integrate multi-fidelity data in inverse problem scenarios such as structural damage assessment, and has high engineering application value in the field of structural health monitoring where high-fidelity data is scarce and low-fidelity data has poor accuracy.

[0075] The present application uses the second loss function to train the second neural network, which can ensure the effectiveness of the network training process.

[0076] Based on the same inventive concept, the embodiment of the present application also provides a multi-fidelity data fusion device for implementing the multi-fidelity data fusion method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more multi-fidelity data fusion device embodiments provided below can refer to the limitations of the multi-fidelity data fusion method above, and will not be repeated here.

[0077] In an exemplary embodiment, a multi-fidelity data fusion device is provided, including: a test module, used to perform a structural damage extension test on a sample, and collect damage state parameter values ​​on the sample at each moment during the structural damage extension test and structural response data of a preset position of the sample under each damage state parameter value, to obtain a damage state parameter value set and a first structural response data set.

[0078] The first simulation module is used to perform static simulation of structural damage extension test on each simulation model in the first simulation model set, obtain structural response data of a preset position of each simulation model in the first simulation model set, and obtain a second structural response data set; the first simulation model set includes multiple simulation models obtained by processing the simulation model of the sample according to each damage state parameter value in the damage state parameter value set.

[0079] The second simulation module is used to perform static simulation of structural damage extension test on each simulation model in the second simulation model set, obtain structural response data of a preset position of each simulation model in the second simulation model set, and obtain a third structural response data set; the second simulation model set includes multiple simulation models obtained by processing the simulation model of the sample according to each preset damage state parameter value.

[0080] The first training module is used to train the first neural network according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network.

[0081] The second training module is used to train the second neural network to obtain a feature mapping network according to the first structural response data set, the second structural response data set and the damage state parameter value at each moment.

[0082] The structural damage assessment model construction module is used to construct a structural damage assessment model based on a low-fidelity network and a feature mapping network; the structural damage assessment model includes a feature mapping network and a low-fidelity network connected in sequence.

[0083] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig.12 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store multi-fidelity data fusion data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a multi-fidelity data fusion method is implemented.

[0084] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned method embodiments when executing the computer program.

[0085] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0086] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0087] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0088] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0089] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0090] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A multi-fidelity data fusion method, characterized in that: The multi-fidelity data fusion method comprises: Performing a structural damage extension test on the sample, and collecting damage state parameter values ​​of the sample at each moment during the structural damage extension test and structural response data of a preset position of the sample under each damage state parameter value, to obtain a damage state parameter value set and a first structural response data set; Performing static simulation of the structural damage extension test on each simulation model in the first simulation model set, acquiring structural response data of a preset position of each simulation model in the first simulation model set, and obtaining a second structural response data set; the first simulation model set includes a plurality of simulation models obtained by processing the simulation model of the sample according to each damage state parameter value in the damage state parameter value set; Performing static simulation of the structural damage extension test on each simulation model in the second simulation model set, obtaining structural response data of a preset position of each simulation model in the second simulation model set, and obtaining a third structural response data set; the second simulation model set includes a plurality of simulation models obtained by processing the simulation model of the sample according to each preset damage state parameter value; Training the first neural network according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network; According to the first structural response data set, the second structural response data set and the damage state parameter value at each moment, the second neural network is trained to obtain a feature mapping network; A structural damage assessment model is constructed according to a low-fidelity network and a feature mapping network; the structural damage assessment model includes a feature mapping network and a low-fidelity network connected in sequence.

2. The multi-fidelity data fusion method according to claim 1, characterized in that: The first neural network is trained according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network, specifically including: Taking the structural response data in the third structural response data set as input, taking the preset damage state parameter values ​​as output, and taking the minimum value of the first loss function as the goal, the first neural network is trained to obtain a low-fidelity network.

3. The multi-fidelity data fusion method according to claim 1, characterized in that: According to the first structural response data set, the second structural response data set and the damage state parameter value at each moment, the second neural network is trained to obtain a feature mapping network, specifically including: Constructing an overall network; the overall network includes a second neural network and a low-fidelity network connected in sequence; The structural response data in the first structural response data set is used as the input of the second neural network, the structural response data in the second structural response data set is used as the output of the second neural network, the damage state parameter value at each moment is used as the output of the low-fidelity network, and the goal is to minimize the value of the second loss function. The second neural network in the overall neural network is trained to obtain a feature mapping network.

4. The multi-fidelity data fusion method according to claim 2, characterized in that: The first loss function for: ,in, Represents the total number of preset damage state parameter values, Indicates that the third structure response data set The output obtained by inputting the structural response data into the first neural network is Indicates the third structure response data set The preset damage state parameter value corresponding to the structural response data is Calculates the square of the absolute value.

5. The multi-fidelity data fusion method according to claim 3, characterized in that: The second loss function for: ,in, represents the total number of damage state parameter values ​​collected at each moment, Indicates that The output of the low-fidelity network is input, Represents the first structure response data set The damage state parameter value corresponding to the structural response data is: represents the weight coefficient, Indicates that the first structure response data set The output obtained by inputting the structural response data into the second neural network is Indicates the first Structural response data, Calculates the square of the absolute value.

6. The multi-fidelity data fusion method according to claim 1, characterized in that: When the damage state parameter value is the crack length, a structural damage extension test is performed on the sample, and the damage state parameter values ​​of the sample at each moment during the structural damage extension test and the structural response data of the preset position of the sample under each damage state parameter value are collected to obtain a damage state parameter value set and a first structural response data set, specifically: A structural crack growth test is performed on the sample, and the crack lengths at various moments on the sample during the structural crack growth test and the structural response data of a preset position of the sample at various crack lengths are collected to obtain a damage state parameter value set and a first structural response data set.

7. A multi-fidelity data fusion device, characterized in that: The multi-fidelity data fusion device comprises: A test module is used to perform a structural damage extension test on the sample, and collect damage state parameter values ​​of the sample at each moment during the structural damage extension test and structural response data of a preset position of the sample under each damage state parameter value, to obtain a damage state parameter value set and a first structural response data set; The first simulation module is used to perform static simulation of a structural damage extension test on each simulation model in the first simulation model set, obtain structural response data of a preset position of each simulation model in the first simulation model set, and obtain a second structural response data set; the first simulation model set includes a plurality of simulation models obtained by processing the simulation model of the sample according to each damage state parameter value in the damage state parameter value set; The second simulation module is used to perform static simulation of the structural damage extension test on each simulation model in the second simulation model set, obtain the structural response data of the preset position of each simulation model in the second simulation model set, and obtain a third structural response data set; the second simulation model set includes a plurality of simulation models obtained by processing the simulation model of the sample according to each preset damage state parameter value; A first training module is used to train the first neural network according to the third structural response data set and each preset damage state parameter value to obtain a low-fidelity network; A second training module is used to train the second neural network to obtain a feature mapping network according to the first structural response data set, the second structural response data set and the damage state parameter value at each moment; The structural damage assessment model construction module is used to construct a structural damage assessment model based on a low-fidelity network and a feature mapping network; the structural damage assessment model includes a feature mapping network and a low-fidelity network connected in sequence.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the multi-fidelity data fusion method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the multi-fidelity data fusion method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the multi-fidelity data fusion method according to any one of claims 1 to 6 is implemented.

Images