A crack resistance analysis method and system based on load factors and environmental factors

Abstract

This application relates to the field of component analysis technology, specifically a crack resistance analysis method and system based on load factors and environmental factors. The method includes: acquiring historical load data and historical temperature data of the object to be analyzed, wherein the historical load data and historical temperature data are acquired in a simulation model; establishing a load-temperature coupled field model based on the historical load data and historical temperature data; inputting the load-temperature coupled field model into a crack resistance prediction model to obtain crack resistance analysis results, specifically including: obtaining corresponding second variable values ​​based on changes in first variable values ​​in the load-temperature coupled field model; obtaining corresponding first variable values ​​based on changes in second variable values ​​in the load-temperature coupled field model; constructing a variable dataset based on the acquired multiple first variable values ​​and multiple second variable values; and inputting the variable dataset into the crack resistance prediction model to obtain crack resistance analysis results.

Description

Technical Field

[0001] This application relates to the field of component analysis technology, specifically to a crack resistance analysis method and system based on load factors and environmental factors. Background Technology

[0002] Crack resistance analysis of building materials has always been a challenge in the construction industry because there are many reasons for cracks in building materials. If a single variable method is used for crack resistance analysis, the results will be inaccurate due to insufficient sample parameters and data. Therefore, it is necessary to develop a method that can fully realize the judgment of crack resistance analysis results.

[0003] Concrete is the primary building material used in construction. Due to its low cost and superior performance, concrete is the most widely used and consumed building material in the world today. However, the early cracking phenomenon in many concrete projects affects the safety and durability of concrete structures. Therefore, research on the early crack resistance of concrete has become a key focus for researchers both domestically and internationally. The academic and engineering communities have conducted theoretical and experimental studies on the crack resistance of concrete from different perspectives. However, existing technologies often suffer from inaccurate predictions and insufficient comprehensiveness due to the limited number of variables introduced in crack resistance analysis. Summary of the Invention

[0004] To address the aforementioned technical issues, this application provides a crack resistance analysis method and system based on load factors and environmental factors, which can achieve accurate and comprehensive crack resistance analysis results based on multiple variables.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0006] In a first aspect, a crack resistance analysis method based on load factors and environmental factors is provided, characterized in that the method includes: acquiring historical load data and historical temperature data of the object to be analyzed, wherein the historical load data and the historical temperature data are acquired in a simulation model; establishing a load-temperature coupled field model based on the historical load data and the historical temperature data; and inputting the load-temperature coupled field model as input to a crack resistance prediction model to obtain crack resistance analysis results, specifically including: obtaining corresponding second variable values ​​based on changes in first variable values ​​in the load-temperature coupled field model; obtaining corresponding first variable values ​​based on changes in second variable values ​​in the load-temperature coupled field model; constructing a variable dataset based on the multiple first variable values ​​and multiple second variable values ​​obtained above; and inputting the variable dataset into the crack resistance prediction model to obtain crack resistance analysis results.

[0007] In a first possible implementation of the first aspect, establishing a load-temperature coupled field model based on the historical load data and the historical temperature data includes: establishing a finite element model; establishing a temperature field model; establishing a load field model; and establishing a load-environment coupled field model based on the finite element model, the temperature field model, and the load field model.

[0008] In conjunction with the first possible implementation of the first aspect, in the second possible implementation, establishing the finite element model includes: establishing a hierarchical structure based on the material as the distinguishing point of the object to be analyzed; obtaining the material parameters of the hierarchical structure based on the simulation model, wherein the material parameters include Young's modulus, Poisson's ratio, thermal conductivity, density, specific heat capacity, and coefficient of thermal contraction; and constructing a structural model based on the hierarchical structure and the material parameters, wherein the structural model is a finite element model.

[0009] In conjunction with the second possible implementation of the first aspect, in the third possible implementation, establishing the temperature field model includes: obtaining the historical temperature data based on the simulation model; combining the historical temperature data with the structural model to obtain the temperature change curves of different levels of the structure in the structural model, wherein the temperature change curves are the temperature field model.

[0010] In conjunction with the third possible implementation of the first aspect, in the fourth possible implementation, the load field model is the stress variation curve of different hierarchical structures obtained based on the simulation model.

[0011] In conjunction with the fourth possible implementation of the first aspect, in the fifth possible implementation, a load-temperature coupled field model is constructed, including: obtaining a coupling curve based on the stress change curve and the temperature change curve through the changes of temperature variables and stress variables, wherein the coupling curve is the load-temperature coupled field model.

[0012] In the sixth possible implementation of the first aspect, inputting the variable dataset into the crack resistance prediction model to obtain crack resistance analysis results includes: constructing a crack resistance index system; labeling the variable dataset based on the crack resistance index system to obtain a sample dataset; determining the optimal parameters based on the sample dataset, and establishing an initial crack resistance prediction model based on the optimal parameters; adjusting the parameters of the initial crack resistance prediction model to obtain a target crack resistance prediction model; and inputting the optimal parameters into the target crack resistance prediction model to obtain prediction results.

[0013] In conjunction with the sixth possible implementation of the first aspect, in the seventh possible implementation, the step of tuning the initial crack resistance prediction model to obtain the target crack resistance prediction model includes: constructing a regression tree from multiple independent samples randomly selected from the sample dataset; using multiple sets of out-of-bag data obtained each time samples are drawn as test sample sets to test the model, and obtaining the mean square residuals of multiple out-of-bag data; configuring random permutation variables; obtaining multiple new data sets based on the random permutation variables and multiple out-of-bag data, and inputting them as test sets into the established initial prediction model for prediction, obtaining the mean square of the residuals after random permutation, and generating the corresponding matrix; subtracting the corresponding row of elements in the matrix from multiple features in the matrix, taking the average value, and then dividing by the standard error to obtain the average reduction of the mean square residuals of the variables, wherein the average reduction of the mean square residuals is the tuning parameter; and tuning the initial prediction model based on the tuning parameter to obtain the target crack resistance prediction model.

[0014] In conjunction with the seventh possible implementation of the first aspect, in the eighth possible implementation, the optimal parameters are input into the target crack resistance prediction model to obtain the prediction result, including: inputting the optimal parameters into the target crack resistance prediction model to obtain trend data.

[0015] Secondly, a crack resistance analysis system based on load factors and environmental factors is characterized by comprising a simulation model and an analysis device configured corresponding to the simulation model; the analysis device comprises: a data acquisition module for acquiring historical load data and historical temperature data of the object to be analyzed; a field model establishment module for establishing a load-temperature coupled field model based on the historical load data and the historical temperature data; and a crack resistance analysis module for analyzing the load-temperature coupled field model as input to obtain crack resistance analysis results.

[0016] Thirdly, a terminal device is provided, including 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 method described in any of the preceding claims.

[0017] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0018] The technical solution provided in this application constructs a field model by comprehensively combining load factors and environmental factors, builds a dataset based on the data corresponding to the field model, and obtains the prediction results based on the dataset and the constructed target prediction model. This approach provides more comprehensive results and higher accuracy compared to existing technologies that predict results using single indicators and variables. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] The methods, systems, and / or procedures shown in the accompanying drawings will be further described with reference to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example figures represent similar mechanisms in the various views of the drawings.

[0021] Figure 1 This is a schematic diagram of the system provided in the embodiments of this application.

[0022] Figure 2 This is a schematic diagram of the crack resistance analysis method based on load factors and environmental factors, as shown in some embodiments of this application.

[0023] Figure 3 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0024] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0025] In the detailed description below, numerous specific details are illustrated with examples to provide a comprehensive understanding of the relevant guidance. However, it will be apparent to those skilled in the art that this application can be practiced without these details. In other instances, well-known methods, procedures, systems, components, and / or circuits have been described at a relatively high level without detail to avoid unnecessarily obscuring aspects of this application.

[0026] This application uses flowcharts to illustrate the execution process performed by a system according to embodiments of this application. It should be clearly understood that the execution processes in the flowcharts may not be executed sequentially. Instead, these execution processes may be executed in reverse order or simultaneously. Additionally, at least one other execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0027] Before providing a further detailed description of the embodiments of the present invention, the nouns and terms involved in the embodiments of the present invention will be explained, and the nouns and terms involved in the embodiments of the present invention shall be interpreted as follows.

[0028] (1) In response to, used to indicate the conditions or states on which the operation performed depends, when the conditions or states on which it depends are met, one or more operations performed may be performed in real time or may have a set delay; unless otherwise specified, there is no restriction on the order of execution of the multiple operations performed.

[0029] (2) Based on, used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which it depends are met, one or more operations can be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order of execution of the multiple operations.

[0030] (3) Random forest: Random forest is a classifier that contains multiple decision trees, and the class of its output is determined by the mode of the class of the individual tree output.

[0031] The technical solution provided in this application is primarily used for crack resistance analysis of concrete, the main material in buildings. Crack resistance analysis is a method to determine whether cracks will occur under material stress conditions. This method can predict the likelihood and cause of cracks in concrete. Existing crack resistance analysis mainly relies on finite element models combined with simulation devices for graphical analysis, and introduces expert systems to obtain results based on expert experience. However, this method introduces relatively few variables, and the reliance on experience for expert system predictions reduces the objectivity and comprehensiveness of the process.

[0032] Based on the above technical background, this application provides a crack resistance analysis system 100 based on load factors and environmental factors. The system includes a simulation model 110 and an analysis device 120 configured corresponding to the simulation model. The analysis device 120 includes: a data acquisition module 121, used to acquire historical load data and historical temperature data of the object to be analyzed; a field model establishment module 122, used to establish a load-temperature coupled field model based on the historical load data and the historical temperature data; and a crack resistance analysis module 123, used to analyze the load-temperature coupled field model as input to obtain crack resistance analysis results.

[0033] See Figure 2 For crack resistance analysis methods based on load factors and environmental factors, the following procedures are included:

[0034] Step S210. Obtain historical load data and historical temperature data of the object to be analyzed.

[0035] In this embodiment, the object to be analyzed is a concrete material structure, and the historical load data and the historical temperature data are obtained in the simulation model.

[0036] Step S220. Establish a load-temperature coupled field model based on the historical load data and the historical temperature data.

[0037] In this embodiment, the process includes the following methods:

[0038] Establish a finite element model.

[0039] Establish a temperature field model.

[0040] Establish a load field model.

[0041] A load-environment coupled field model is established based on the finite element model, the temperature field model, and the load field model.

[0042] The construction of the finite element model includes:

[0043] Based on the object to be analyzed, a hierarchical structure is constructed using materials as the distinguishing point.

[0044] The material parameters of the hierarchical structure are obtained based on the simulation model. These material parameters include Young's modulus, Poisson's ratio, thermal conductivity, density, specific heat capacity, and coefficient of thermal shrinkage.

[0045] A structural model is constructed based on the hierarchical structure and material parameters. The structural model is a finite element model.

[0046] Establishing a temperature field model includes:

[0047] The historical temperature data is obtained based on the simulation model.

[0048] The historical temperature data is combined with the structural model to obtain the temperature change curves of different levels of the structure in the structural model. In this embodiment, the temperature change curve is the temperature field model.

[0049] In this embodiment, the load field model is the stress variation curve of different hierarchical structures obtained based on the simulation model.

[0050] Step S230. Input the load-temperature coupled field model into the crack resistance prediction model to obtain the crack resistance analysis results.

[0051] This process includes the following methods:

[0052] Step S231. Obtain the corresponding second variable value based on the change of the first variable value in the load-temperature coupled field model.

[0053] Step S232. Obtain the corresponding first variable value based on the change of the second variable value in the load-temperature coupled field model.

[0054] Step S233. Construct a variable dataset based on the multiple first variable values ​​and multiple second variable values ​​obtained above.

[0055] Step S234. Input the variable dataset into the crack resistance prediction model to obtain the crack resistance analysis results.

[0056] In this embodiment, the variable dataset is constructed based on the data points in the load-temperature field coupling model in step S220. Specifically, the logic of inputting the variable dataset into the crack resistance prediction model to obtain crack resistance analysis results in step S234 first involves parameter optimization of the initial prediction model, followed by modeling. The importance of influencing factors is calculated using random forest feature selection. Prediction results are output using the training set, and the accuracy and applicability of the model are verified using the test set to obtain the target prediction model. The analysis results are then predicted based on the target prediction model. The target prediction model is mainly based on the following steps:

[0057] Construct a crack resistance index system.

[0058] The variable dataset is labeled based on the crack resistance index system to obtain the sample dataset. In this embodiment, the variable dataset in this step is different from the variable data in step S220. In this embodiment, the variable dataset is the variable data obtained after extracting features from the cracked sample concrete structure based on the load-temperature field coupling model in step S220. The variable data is used to characterize the cracking of concrete, and the subsequent model is trained based on this data.

[0059] The crack resistance index system is based on the mechanism of concrete cracking phenomenon, and the direct factors affecting the early crack resistance of concrete are obtained. Starting from concrete materials and mix proportions, and considering the influence of various concrete indicators on crack resistance, 10 factors are selected as independent variables: Young's modulus, Poisson's ratio, thermal conductivity, density, specific heat capacity, thermal shrinkage coefficient, solar radiation, effective radiation of road surface, air temperature and convective heat exchange, and total crack area as dependent variable. A primary evaluation index system for early crack resistance of concrete is constructed. The above indicators are also key indicators in the finite element model and temperature field model.

[0060] The optimal parameters are determined based on the sample dataset, and an initial crack resistance prediction model is established based on the optimal parameters.

[0061] In this embodiment, the original dataset is recorded as follows: The Bootstrap sampling method is used to draw k samples from a sample T of size n to form k independent datasets. The k sample sets contain 2 / 3 of the data in the original dataset and are used as the training dataset in the model. The out-of-bag data that was not selected accounts for about 1 / 3 of the original dataset and is used as the test dataset in the model.

[0062] In this embodiment, the prediction model is based on the random forest algorithm, so the structure of the prediction model is the random forest algorithm structure.

[0063] When building a prediction model based on a dataset, the parameter `mtyr` defaults to `n / 3`, where `n` is the number of input features. The optimal `ntree` is determined by searching for stable values ​​on the OOB error curve, ensuring that the training set error tends to stabilize while maintaining the model's training speed from slowing down due to excessively large structures in the prediction model. Based on the ideal `ntree` parameters, a five-fold cross-validation method is used with `mtry` values ​​of 1, 2, ..., k, where `k` is the number of explanatory variables. This process iterates through the model to select the optimal `mtry` parameters.

[0064] The initial crack resistance prediction model is adjusted to obtain the target crack resistance prediction model.

[0065] In this embodiment, the process specifically includes the following methods:

[0066] A regression tree is constructed from multiple independent samples randomly selected from the sample dataset. Multiple sets of out-of-bag data obtained each time samples are drawn are used as test sample sets to test the model, and the mean squared residuals of multiple out-of-bag data are obtained.

[0067] Specifically, a regression tree is constructed for b randomly selected independent samples. The b sets of out-of-bag data obtained each time samples are drawn are used as the test sample set to test the model, and the mean squared residuals of the b out-of-bag data are obtained, namely MSE1, MSE2, ..., MSEn.

[0068] By randomly permuting variable Xi, b new OOB data sets can be obtained. These sets are then used as test sets and input into the established random forest regression model for prediction. The mean squared residuals (MSEij) of the OOB data after random permutation are obtained, and the generated matrix A is:

[0069] Where p is the number of influencing factor variables and b is the number of samples.

[0070] Subtracting the corresponding values ​​from the i-th row of matrix A using MSE1, MSE2, ..., MSEb, and then averaging the results and dividing by the standard error, yields the average decrease in the mean squared residuals of variable xi. This means the importance score can be expressed as:

[0071] ;

[0072] Where MSEj is the mean square of the residuals of the j-th sample; SE is the standard error, 1 ≤ i ≤ p.

[0073] Calculating feature importance using random forests essentially involves randomly introducing noise into the feature variables and comparing the change in the model's prediction accuracy before and after. The magnitude of this change is used to characterize the importance of the feature. If the model's accuracy increases, it indicates that the feature is more important. The formula above more intuitively shows that the higher the importance score, the greater the perceived influence of the feature variable on the prediction result, and the more prominent its importance.

[0074] The optimal parameters are input into the target crack resistance prediction model to obtain the prediction result.

[0075] In this embodiment, the optimized parameters are substituted into the model to output the prediction results. The quality of the prediction model needs to be evaluated using appropriate metrics, mainly from the perspectives of accuracy and stability. The root mean square error (RMSE) measures the deviation between the predicted and actual values, reflecting the dispersion of the sample. The closer the predicted and actual values ​​are, the closer the RMSE will be to 0, indicating higher model accuracy and smaller error. The coefficient of determination measures the goodness of fit between variables; the closer its value is to 1, the better the model fit and the higher its interpretability. Specifically:

[0076] ;

[0077] .

[0078] in , and , , and , respectively, represent the observed value, predicted value, and average of the observed values ​​for the i-th sample, where n is the sample size for the corresponding sample.

[0079] See Figure 3The above methods can be integrated into a terminal device 300. This terminal device includes a memory 310, a processor 320, and a computer program stored in the memory and executable on the processor. The processor executes a crack resistance analysis method based on load factors and environmental factors. In this embodiment, the terminal device communicates with a user terminal, sending the acquired detection information to the corresponding user terminal, thus implementing the transmission of detection information in hardware. The information transmission is network-based, and an association needs to be established between the user terminal and the terminal device before the terminal device can be used. This association can be established through registration. The terminal device can be used with multiple user terminals or with a single user terminal, and the user terminal communicates with the terminal device using a password and other encryption methods.

[0080] This embodiment provides a crack resistance analysis method based on load and environmental factors. It constructs a field model by comprehensively combining these factors, builds a dataset based on the data corresponding to the field model, and obtains prediction results based on the dataset and the constructed target prediction model. This method offers more comprehensive results and higher accuracy compared to existing technologies that predict results using single indicators and variables.

[0081] In this embodiment, the memory, processor, and communication unit are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The memory is used to store specific information and programs, and the communication unit is used to send the processed information to the corresponding user terminal.

[0082] In this embodiment, the storage module is divided into two storage areas: a program storage unit and a data storage unit. The program storage unit is equivalent to the firmware area, and its read / write permissions are set to read-only mode, meaning the data stored therein cannot be erased or modified. The data storage unit, on the other hand, allows for erasure and reading / writing. When the data storage area is full, newly written data will overwrite the oldest historical data.

[0083] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc.

[0084] The processor may be an integrated circuit chip with signal processing capabilities. The aforementioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application-Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0085] It should be understood that for the technical terms for which no definition has been provided above, those skilled in the art can infer their meanings without doubt based on the disclosed content, and no limitation is made here.

[0086] Those skilled in the art can, without question, determine certain preset, benchmark, predetermined, set, and preference-labeled technical features / terms, such as thresholds, threshold intervals, and threshold ranges, based on the aforementioned disclosed content. For some unexplained technical feature terms, those skilled in the art can reasonably and unambiguously deduce them based on the logical relationship between the context, thereby clearly and completely implementing the aforementioned technical solution. Prefixes of unexplained technical feature terms, such as "first," "second," "example," and "target," can be unambiguously deduced and determined based on the context. Suffixes of unexplained technical feature terms, such as "set" and "list," can also be unambiguously deduced and determined based on the context.

[0087] The content disclosed in the embodiments of this application is clear and complete to those skilled in the art. It should be understood that the process by which those skilled in the art derive and analyze the unexplained technical terms based on the above disclosure is based on the content recorded in this application, and therefore the above content is not a judgment of the inventiveness of the overall solution.

[0088] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art can make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0089] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different parts of this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in at least one embodiment of the application can be appropriately combined.

[0090] Furthermore, it will be understood by those skilled in the art that various aspects of this application can be described and illustrated through several patentable types or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, various aspects of this application can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software can be referred to as a “unit,” “component,” or “system.” Moreover, various aspects of this application can be embodied as a computer product residing in at least one computer-readable medium, said product including computer-readable program code.

[0091] A computer-readable signal medium may contain a propagated data signal containing computer program encoding, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and so on, or suitable combinations thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program encoding located on the computer-readable signal medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0092] The computer program code required for the execution of any aspect of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., or similar conventional programming languages ​​such as the "C" programming language, Visual Basic, Fortran2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby, and Groovy, or other programming languages. The program code can be executed entirely on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as Software as a Service (SaaS).

[0093] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of digits, or other names described in this application are not intended to limit the order of the processes and methods of this application. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. Rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments of this application. For example, while the system components described above can be implemented by hardware devices, they can also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

[0094] It should also be understood that, in order to simplify the description disclosed in this application and thus aid in the understanding of at least one embodiment of the invention, multiple features may sometimes be grouped into a single embodiment, drawing, or description thereof in the foregoing description of the embodiments of this application. However, this method of disclosure does not imply that the subject matter of this application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

Claims

1. A crack resistance analysis method based on load factors and environmental factors, characterized in that, The method includes: Historical load data and historical temperature data of the object to be analyzed are obtained in the simulation model. A load-temperature coupled field model is established based on the historical load data and the historical temperature data. The load-temperature coupled field model is used as input to the crack resistance prediction model to obtain crack resistance analysis results, specifically including: The corresponding second variable value is obtained based on the change of the first variable value in the load-temperature coupled field model; The corresponding first variable value is obtained based on the change of the second variable value in the load-temperature coupled field model; A variable dataset is constructed based on the multiple first variable values ​​and multiple second variable values ​​obtained above; The variable dataset is input into the crack resistance prediction model to obtain crack resistance analysis results, including: Construct a crack resistance index system; The variable dataset is obtained by labeling the variable dataset based on the crack resistance index system. The variable dataset is the variable data obtained by extracting features from the cracked sample concrete structure based on the load-temperature field coupling model. The variable data is used to characterize the cracking of concrete and is used to train the subsequent model. The optimal parameters are determined based on the sample dataset, and an initial crack resistance prediction model is established based on the optimal parameters. The initial crack resistance prediction model is adjusted to obtain a target crack resistance prediction model; the optimal parameters are input into the target crack resistance prediction model to obtain the prediction result; the adjustment of the initial crack resistance prediction model to obtain the target crack resistance prediction model includes: A regression tree is constructed from multiple independent samples randomly selected from the sample dataset. Multiple sets of out-of-bag data obtained each time samples are drawn are used as test sample sets to test the model, and the mean squared residuals of multiple out-of-bag data are obtained. Configure random permutation variables, obtain multiple new data sets based on the random permutation variables and multiple out-of-bag data, and input them as test sets into the established initial prediction model for prediction, obtain the residual mean square after random permutation, and generate the corresponding matrix; The mean squared residual of the variable is obtained by subtracting the corresponding row of the element sequence of the matrix from the multiple features in the matrix, taking the average value, and then dividing by the standard error. The mean squared residual is used as a parameter for parameter tuning. The target crack resistance prediction model is obtained by adjusting the parameters of the initial prediction model. The logic of inputting the variable dataset into the crack resistance prediction model to obtain the crack resistance analysis results firstly involves optimizing the parameters of the initial prediction model and then modeling it. The importance of influencing factors is calculated through random forest feature selection. The prediction results are output through the training set, and the accuracy and applicability of the model are verified using the test set to obtain the target prediction model. The analysis results are then predicted based on the target prediction model.

2. The crack resistance analysis method based on load factors and environmental factors according to claim 1, characterized in that, A load-temperature coupled field model is established based on the historical load data and the historical temperature data, including: Establish a finite element model; Establish a temperature field model; Establish a load field model; A load-environment coupled field model is established based on the finite element model, the temperature field model, and the load field model.

3. The crack resistance analysis method based on load factors and environmental factors according to claim 2, characterized in that, Establishing a finite element model includes: Based on the object to be analyzed, a hierarchical structure is constructed using materials as distinguishing points; The material parameters of the hierarchical structure are obtained based on the simulation model. The material parameters include Young's modulus, Poisson's ratio, thermal conductivity, density, specific heat capacity, and coefficient of thermal shrinkage. A structural model is constructed based on the hierarchical structure and material parameters. The structural model is a finite element model.

4. The crack resistance analysis method based on load factors and environmental factors according to claim 3, characterized in that, Establishing a temperature field model includes: The historical temperature data was obtained based on a simulation model. The historical temperature data is combined with the structural model to obtain temperature change curves for different levels of the structure in the structural model, and the temperature change curves are the temperature field model.

5. The crack resistance analysis method based on load factors and environmental factors according to claim 4, characterized in that, The load field model is based on the stress variation curves of different structural levels obtained from the simulation model.

6. The crack resistance analysis method based on load factors and environmental factors according to claim 5, characterized in that, Constructing a load-temperature coupled field model includes: Based on the stress change curve and the temperature change curve, a coupling curve is obtained by changing the temperature variable and the stress variable. The coupling curve is the load-temperature field coupling model.

7. The crack resistance analysis method based on load factors and environmental factors according to claim 1, characterized in that, The process of inputting the optimal parameters into the target crack resistance prediction model to obtain prediction results includes: inputting the optimal parameters into the target crack resistance prediction model to obtain trend data.

8. A crack resistance analysis system based on load factors and environmental factors, characterized in that, The crack resistance analysis method based on load factors and environmental factors as described in any one of claims 1 to 7 includes a simulation model and an analysis device configured corresponding to the simulation model; the analysis device includes: The data acquisition module is used to acquire historical load data and historical temperature data of the object to be analyzed. The field model building module is used to build a load-temperature coupled field model based on the historical load data and the historical temperature data. The crack resistance analysis module analyzes the load-temperature coupled field model as input to obtain crack resistance analysis results.

Images