A response prediction-based structural construction unloading monitoring method and device

Abstract

The application discloses a kind of structural construction unloading monitoring method and device based on response prediction, and it is related to civil engineering technical field.The method includes: using regression method to establish the influence relationship of monitoring response to structure shape;According to the influence relationship and the prediction of monitoring response to structure shape;Using uniform test design method to optimize structure shape prediction range.The application judges structure shape based on structure monitoring point displacement, carries out uniform test design using monitoring component elastic modulus change, and the judgment of structure shape is based on real-time monitoring data or whole-process simulation analysis.Uniform test design is based on whole-process simulation analysis, and the range size of structure shape is predicted and optimized by both, to ensure that structure shape meets construction monitoring requirements.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of civil engineering, and particularly relates to a structure construction unloading monitoring method and device based on response prediction. BACKGROUND

[0002] The research on construction monitoring in the aspect of data processing and application includes mining of construction stage data, research on response correlation, and supplement of missing data, etc., but the data processing of the same stage after the conversion of the structural mechanics system cannot accurately reflect the influence law between the structural responses. The structural unloading reduces the difference between the structure completion state and the structure design state through the construction monitoring in stages, and realizes the stage-by-stage prediction of the structure shape by using the characteristics that the monitoring responses and the structure shape are uniquely corresponding under the same mechanics system.

[0003] In the conversion process of different mechanics systems, the shape is uniquely determined with the determination of the stress state of the structure under the condition that the degrees of freedom are unchanged, which indicates that there is a stable correlation between the structural responses. The parameterization method is used to analyze the influence of the structural factors on the overall performance, to determine the distribution and transmission law of the component responses, and to judge the influence of the structural responses on the components according to the stress state of the components under a specific stress state. In addition, the correlation between the variables is established according to the invariants in the conversion process of the mechanics system, the response change law is extracted, such as the unstressed length which is the invariant in the conversion process of the cable structure mechanics system, and the cable force value under a specific mechanics system state is solved by the unstressed length of the cable, so that the geometric state equation and the state transmission matrix in the construction process of the complex structure are established by the geometric state variables to solve the structural responses. Through the analysis of multiple working conditions and failure working conditions, the weak parts and dangerous components of the structure are found, or the component stiffness is changed to simulate damage, so as to achieve the purpose of internal force redistribution, and then the structural failure is analyzed. In the correlation analysis of the structural internal force, the influence range of the component parameter change is related to the stress characteristics of the component, and the influence degree is determined by the component parameters, at this time, the parameters which are difficult to determine in the construction are identified by measuring the related parameters. The above research solves the structure by the finite element model analysis based on the response correlation, but the number of response samples obtained by the actual construction monitoring is much less than that of the finite element model analysis.

[0004] In addition, the correlation between responses is generated under the influence of structural characteristics, and data mining and response prediction are realized through the correlation between responses under different mechanical systems. The response prediction methods used include deep learning methods and regression prediction methods. The multivariate nonlinear relationship between responses determines the use of improved regression methods for modeling analysis, and the correlation between the influencing factors and the construction control conditions is studied by using the optimized nonlinear information mining capability, so as to realize the prediction of the construction control conditions. The multivariate nonlinear relationship between responses meets the mechanical conditions and the coordination conditions of spatial deformation. According to the data characteristics, the kernel function of Gaussian regression is selected to realize the prediction of the construction control conditions. The deformation conditions in the construction monitoring process are determined by displacement, angle and the like, and the structural displacement is estimated according to the relationship between deformation and nodes. Regression analysis of response changes under the action of multiple factors is suitable for various engineering control fields, including battery life prediction, and the advantage of regression analysis is that the influence of uncertain factors is considered, and the measured data is combined with the mechanism equation. Regression analysis includes multivariate regression, Gaussian regression and other methods, and only by selecting appropriate regression methods can more accurate data be obtained. The above research proposes various response prediction methods, and uses the multivariate nonlinear relationship between responses for response prediction research, but lacks the judgment of the response prediction value.

[0005] At present, the response correlation and prediction method mainly depends on a large number of data samples and is based on responses with strong correlation for data analysis, which does not meet the situation of limited monitoring points and easy installation in actual construction monitoring, and the purpose of response correlation and prediction research is not strong. Therefore, it is necessary to determine the structural shape distribution based on the structural mechanics characteristics on the basis of obtaining the monitoring response in the response correlation analysis of the construction unloading stage.

[0006] In related technologies, in order to obtain the predicted displacement of the structural shape, one technology is to use the correlation between responses to predict the structural shape by using the least square method. This method only considers the correlation between responses, ignores the influence relationship between responses and structural shape, and makes the accuracy of predicting the structural shape of the construction unloading monitoring low, which is difficult to ensure that the structural shape in the construction stage meets the construction requirements. SUMMARY

[0007] In order to at least partially overcome the problems in the related art, the present application provides a structural construction unloading monitoring method and device based on response prediction.

[0008] In a first aspect, the structural construction unloading monitoring method based on response prediction provided by the embodiments of the present application comprises the following steps:

[0009] S10: establishing the influence relationship of the monitoring response on the structural shape by using a regression method;

[0010] S20: predicting the structural configuration according to the influence relationship and the monitoring response;

[0011] S30: optimizing the prediction range of the structural configuration by using the uniform design method.

[0012] Further, the influence relationship is the influence relationship of the monitoring response increment on the structural configuration increment, and the influence relationship is a multivariate nonlinear relationship.

[0013] Further, the regression method is a Gaussian regression method.

[0014] Further, the Gaussian regression method is used to solve the occurrence probability of the structural configuration by using the conditional probability based on Bayesian inference.

[0015] Further, the step S20 specifically comprises:

[0016] S21: establishing the influence relationship of the monitoring response on the structural configuration by using the monitoring response data and the structural configuration data under a known mechanical system;

[0017] S22: predicting the structural configuration by using the monitoring response data and the influence relationship.

[0018] Further, the uniform design method uses a finite element model, and the range of the structural configuration change is determined by changing the elastic modulus of the component.

[0019] Further, the uniform design method is a test design method considering the stiffness error of the component under multiple conditions.

[0020] Further, the prediction range of the structural configuration is an interval composed of the maximum value and the minimum value of the structural node configuration prediction under multiple combinations of the stiffness error.

[0021] Further, the prediction of the structural configuration is based on the measured monitoring response or the full-process simulation analysis data, and the uniform design is based on the full-process simulation analysis data.

[0022] In a second aspect, an embodiment of the present application provides a structural construction unloading monitoring device based on response prediction, which comprises:

[0023] An influence relationship establishing module is configured to establish the influence relationship of the monitoring response on the structural configuration by using a regression method;

[0024] A structural configuration predicting module is configured to predict the structural configuration according to the influence relationship and the monitoring response;

[0025] A prediction range optimizing module is configured to optimize the prediction range of the structural configuration by using a uniform design method.

[0026] The technical scheme provided by the embodiment of the present application has the following beneficial effects:

[0027] The embodiment of the present application firstly establishes the influence relationship of the monitoring response on the structural configuration by using a regression method; then realizes the prediction of the structural configuration according to the influence relationship and the monitoring response; and finally optimizes the prediction range of the structural configuration by using the uniform test design method. The prediction of the structural configuration is based on real-time monitoring data or whole-process simulation analysis, and the optimization of the prediction result of the structural configuration is based on the whole-process simulation analysis, so as to jointly predict and optimize the range of the structural configuration, provide a judgment basis for construction unloading monitoring, and ensure that the structural configuration in the construction phase meets the construction requirements.

[0028] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0029] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

[0030] Figure 1 is a flow diagram of a structural construction unloading monitoring method based on response prediction according to an embodiment of the present application.

[0031] Figure 2 is a structural block diagram of a structural construction unloading monitoring device based on response prediction according to an embodiment of the present application.

[0032] In the drawings, the reference signs are:

[0033] The influence relationship establishment module 100; the structural configuration prediction module 200; and the prediction range optimization module 300. DETAILED DESCRIPTION

[0034] The exemplary embodiments will be described in detail herein with reference to the drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of methods and apparatuses consistent with some aspects of the present application as detailed in the appended claims.

[0035] Embodiment 1

[0036] In order to make the purposes, technical schemes and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0037] Figure 1is a flowchart of a structural construction unloading monitoring method based on response prediction provided by an embodiment of the present application, which can include the following steps:

[0038] Step S10: establishing an influence relationship of the monitoring response on the structure shape by using a regression method.

[0039] In this embodiment, the influence relationship is an influence relationship of the monitoring response increment on the structure shape increment, and the influence relationship is a multivariate nonlinear relationship.

[0040] The regression method is a Gaussian regression method. The Gaussian regression method is used to solve the occurrence probability of the structure shape by using the conditional probability based on Bayesian inference.

[0041] During the structural construction unloading process, the correlation between the component response and the structure shape is strong. After the monitoring point positions in the construction unloading stage are determined, the number of monitoring point positions is optimized compared to the number of associated components of the structure shape, and the response matrix x of the selected monitoring point positions is:

[0042]

[0043] In the formula, is the i th monitoring response value under the k th mechanical system; m is the number of structural mechanical systems of construction unloading; and g is the number of monitoring point positions.

[0044] The monitoring response x of the k th mechanical system is k

[0045]

[0046] The increment of the i th monitoring response in the conversion process of the k th mechanical system is

[0047]

[0048] The monitoring response increment in the conversion process of the k th mechanical system is

[0049]

[0050] The structure shape increment Δu at this time is k

[0051] Δu k = A k' Δx k

[0052] The influence matrix A between the monitoring response and the structure shape is k' is

[0053] ​

[0054] where, is the influence relationship of the i-th monitoring response on the j-th node shape under the k-th mechanical system.

[0055] x is the non-monitoring associated member response related to the structural shape but not screened out. k' is the number of non-monitoring associated member responses related to the structural shape.

[0056]

[0057] where, is the j-th non-monitoring associated member response under the k-th mechanical system.

[0058] Since x k and x k' have strong correlation with the structural shape, and x k and x k' are both important members in the load transfer path, there is an influence relationship between x k and x k' ; d is the number of members that have influence on the structural shape.

[0059] The increment of the j-th non-monitoring associated member response

[0060]

[0061] where, is the non-monitoring associated member response under the k+1-th mechanical system; is the non-monitoring associated member response under the k-th mechanical system.

[0062] The increment of the non-monitoring associated member response k' :

[0063]

[0064] The increment of the non-monitoring associated member response k' :

[0065] Δx k' = A k” Δx k

[0066] The influence matrix A between the non-monitoring associated response and the monitoring response k”

[0067]

[0068] where, is the influence coefficient of the j-th monitoring response on the i-th non-monitoring associated response under the k-th mechanical system.

[0069] wherein the influence coefficient

[0070]

[0071] A under the kth mechanical system k” the jth row of the influence coefficient is expressed as

[0072]

[0073] wherein, is the influence coefficient of the e th monitoring response on the j th non-monitoring associated response under the k th mechanical system.

[0074] The influence formula of the monitoring response and the structural configuration is:

[0075]

[0076] Step S20: predicting the structural configuration according to the influence relationship and the monitoring response.

[0077] Specifically, the essence of the Gaussian regression method is to solve the occurrence probability of the structural configuration by using the conditional probability based on Bayesian inference. For the Bayesian distribution, the joint probability function p(x, u) is:

[0078] p(x, u) = p(x|u) p(u) = p(u|x) p(x)

[0079] wherein p(u|x) is the structural configuration probability under the condition that the monitoring response x occurs; p(u) is the occurrence probability of the structural configuration u; and p(x) is the occurrence probability of the monitoring response x.

[0080] The Bayesian inference of the construction unloading stage refers to the conditional probability p(u|x) of the structural configuration under the condition that the monitoring response p(x) occurs, and the monitoring response probability p(x|u) under the condition that the structural configuration u occurs:

[0081]

[0082] The joint probability p(u, u * ) of the structural configuration and the predicted structural configuration and the conditional probability p(u * |u) of the predicted structural configuration occurrence are:

[0083] p(u, u * ) = p(u * |u) p(u)

[0084] The expression of the conditional probability mean and variance of the monitoring response and the structure configuration is obtained by Bayesian inference in the case of the known mean function and covariance function of the Gaussian process, the prediction of the structure configuration is performed by solving the conditional probability of the occurrence of the structure predicted configuration, and the prediction accuracy is related to the accuracy of the solved structure configuration distribution mean and variance.

[0085] The covariance represents the similarity of the change trends of the two groups of responses, and the purpose is to obtain the corresponding posterior distribution according to the prior distribution of the response, and the covariance between the two responses

[0086]

[0087] In the formula, is the i-th and j-th monitoring response under the i-th mechanical system; is the mathematical expectation of the i-th and j-th monitoring response under the i-th mechanical system.

[0088] For the response set, the calculated covariance matrix K(x i ,x j ) composed of the covariances between the monitoring responses:

[0089]

[0090] The covariance matrix K(x,x) between the monitoring response sets:

[0091]

[0092] The structure configuration u in the mechanical system conversion process of the monitoring response prediction by using the Gaussian regression method is represented as

[0093] u=g(x)+ε'

[0094] In the formula, g(x) is a linear model of the monitoring response and the structure configuration; x is the monitoring response; and ε' is a configuration impact caused by a non-monitoring associated response.

[0095] The linear model g(x) is:

[0096]

[0097] The linear model ignores the impact of the non-monitoring associated component response, and therefore there is model noise, and according to the component distribution law, the configuration impact ε caused by the non-monitoring associated response is:

[0098] ε'~N(μ',σ')

[0099] In the formula, μ' is the mean of the configuration impact caused by the non-monitoring associated response; and σ' is the variance of the configuration impact caused by the non-monitoring associated response.

[0100] Existing monitoring response x t :

[0101]

[0102] wherein, is the existing ith monitoring response value under the jth mechanical system; h is the number of mechanical systems corresponding to the existing data.

[0103] Existing structural configuration u t :

[0104]

[0105] wherein, is the existing ith node configuration under the jth mechanical system.

[0106] Predicted structural configuration required monitoring response x * :

[0107]

[0108] wherein, is the ith monitoring response value required by the predicted structural configuration under the jth mechanical system; p is the number of mechanical systems corresponding to the predicted structural configuration.

[0109] Corresponding predicted result u t* :

[0110]

[0111] The structural configuration prediction using Gaussian regression is similar to the structural configuration solution using influence matrix, the existing structural configuration u t and the distribution of the predicted result u * :

[0112]

[0113] wherein, I is the unit matrix.

[0114] Response sample function k(x t ,x * ):

[0115]

[0116] wherein, γ is the hyperparameter of the Gaussian regression kernel function, which is related to the response variance.

[0117] Further, the step S20 specifically comprises:

[0118] S21: establishing the influence relationship between the monitoring response and the structure position using the monitoring response data and the structure position data under the known mechanical system;

[0119] S22: predicting the structure position using the monitoring response data and the influence relationship.

[0120] Step S30: predicting the structure position using the monitoring response data and the influence relationship.

[0121] In the embodiment, the uniform test design method uses the finite element model, and the structure position variation range is determined by changing the component elastic modulus analysis.

[0122] The uniform test design method is a test design method considering the stiffness error of the component under multiple conditions. The structure position prediction range is an interval composed of the maximum value and the minimum value of the structure node position prediction under multiple combinations of the stiffness error.

[0123] The prediction of the structure position is based on the measured monitoring response or the whole process simulation analysis data, and the uniform test design is based on the whole process simulation analysis data.

[0124] Specifically, in the actual construction unloading process, the construction error factors are multi-sources, including the construction method, installation error, etc., causing the response error

[0125]

[0126] In the formula, is the i-th structure response error under the k-th mechanical system.

[0127] The response error causes stress accumulation and deformation accumulation, and the error accumulation ε x under different mechanical systems:

[0128]

[0129] In the formula, m is the number of mechanical systems in the construction unloading process.

[0130] The error in the construction process will cause the coupling of the error, because the causes and distribution laws of the error are different, the construction error is accompanied by the unidirectional propagation of the positive construction process, and the influence caused by the error is different under different mechanical system states. The structure response error ε:

[0131] ε = ε x + b + ε r

[0132] In the formula, ε x is the accumulated installation error; b is the component initialization error; and ε rFor the random error in construction.

[0133] When the component only has the error in processing length, the stiffness matrix K * For

[0134] K * = TK e T T

[0135] In the formula, T is the coordinate transformation matrix of the component; K e is the element stiffness matrix affected by error.

[0136] When the component has the error in length, the treatment of error is divided into two cases, the first is to continue construction under the condition of the existing component configuration, and the construction configuration error Δu e :

[0137]

[0138] In the formula, u is the theoretical position of the component; is the actual position of the component.

[0139] The cumulative component configuration error Δu under different mechanical systems:

[0140]

[0141] In the formula, Δu is the construction configuration error of the ith component; n is the number of components.

[0142] The second way is to force into position, which means that the component is forced to be fixed in the design configuration by stretching or other construction methods. The disadvantage of this method is that the component is given an initial stress, and the component stress error Δε e :

[0143]

[0144] After multiple forced into position, the cumulative stress of the component Δε:

[0145]

[0146] The distribution law of the component processing error and construction error is Gaussian distribution, and the error is mainly related to the construction method and quality management mechanism and other conditions, so the structure configuration distribution under the influence of construction error

[0147]

[0148] In the formula, σ is the distribution range of the structure configuration; μ uThe mean value of the structural shape distribution; The variance of the structural shape distribution; The influence of the construction random error on the structural shape.

[0149] From the above analysis, the distribution of the structural shape is affected by the stiffness of the components in space, and it is necessary to use experimental methods to study the influence of errors on the shape.

[0150] The uniform experimental design method is to let the test points be uniformly distributed in high-dimensional space, so that limited data has wide representativeness. In the uniform design method, the influencing factors are divided into several levels, when the number of levels increases, the number of tests increases in proportion to the number of levels, the advantage is that the test points of the uniform test are more evenly distributed and more representative.

[0151] The uniform experimental design method uses finite element model analysis to determine the range of structural shape change, and achieves the purpose of uniform test by changing the elastic modulus of the components, at this time the elastic modulus level matrix of the components at different levels

[0152]

[0153] In the formula, is the i-th elastic modulus level value of the j-th monitoring component; b is the number of elastic modulus levels.

[0154] The response results of different groups of experiments are obtained by uniform experimental design, in which the monitoring response

[0155]

[0156] In the formula, is the response value of the j-th monitoring component at the i-th elastic modulus level.

[0157] The monitoring response at the i-th elastic modulus level

[0158]

[0159] When performing finite element simulation or construction monitoring, the influence relationship is established according to the monitoring response and the structural shape without stiffness change, and the monitoring response under the uniform test method and the influence relationship can obtain the structural shape prediction matrix under different stiffness level combinations

[0160]

[0161] In the formula, is the predicted shape of the j-th node at the i-th elastic modulus level.

[0162] The jth node's configuration prediction range considering error

[0163]

[0164] The embodiment of the application is based on whole-process construction simulation, and verifies the construction scheme according to comparison between a predicted configuration of a structure and a measured configuration of the structure. A Gauss regression method is determined as an analysis method according to correlation between a component response and a configuration of the structure, on the basis of obtaining a monitored component response, a configuration of the structure is predicted by using the influence relationship and the monitored response, in finite element simulation analysis, the component stiffness is changed, and the uniform test design method is used to optimize the configuration prediction range of the structure. In combination with whole-process simulation analysis in the construction stage, a structure construction unloading monitoring method based on response prediction is realized, and the configuration of the structure is predicted by considering response changes before and after a mechanical system conversion.

[0165] Embodiment 2

[0166] The embodiment of the application also provides a structure construction unloading monitoring device based on response prediction, which can be applied to the structure construction unloading monitoring method based on response prediction. Figure 2 is a structure block diagram of the structure construction unloading monitoring device based on response prediction. The device mainly includes an influence relationship establishing module 100, a configuration prediction module 200 and a prediction range optimization module 300.

[0167] Specifically, the influence relationship establishing module 100 is used to establish an influence relationship of a monitored response on a configuration of a structure by using a regression method.

[0168] The configuration prediction module 200 is used to predict the configuration of the structure according to the influence relationship and the monitored response.

[0169] The prediction range optimization module 300 is used to optimize the configuration prediction range of the structure by using the uniform test design method.

[0170] The embodiment of the application is based on whole-process construction simulation, and verifies the construction scheme according to comparison between a predicted configuration of a structure and a measured configuration of the structure. The influence relationship establishing module 100 determines a Gauss regression method as an analysis method according to correlation between a component response and a configuration of the structure, on the basis of obtaining a monitored component response, the configuration prediction module 200 predicts the configuration of the structure by using the influence relationship and the monitored response, and the prediction range optimization module 300 changes the component stiffness in finite element simulation analysis, and uses the uniform test design method to optimize the configuration prediction range of the structure. In combination with whole-process simulation analysis in the construction stage, a structure construction unloading monitoring method based on response prediction is realized, and the configuration of the structure is predicted by considering response changes before and after a mechanical system conversion.

[0171] As to the device in the above-mentioned embodiments, the specific steps in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here. Each module in the above-mentioned device for construction unloading monitoring based on response prediction can be realized by software, hardware and combinations thereof, in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0172] In summary, the embodiments of the present application first establish the influence relationship of the monitoring response on the structural shape by using the regression method; then realize the prediction of the structural shape according to the influence relationship and the monitoring response; and finally optimize the prediction range of the structural shape by using the uniform experimental design method. The prediction of the structural shape is based on real-time monitoring data or whole-process simulation analysis, and the optimization of the prediction result of the structural shape is based on the whole-process simulation analysis, so as to jointly predict and optimize the range of the structural shape, provide a judgment basis for construction unloading monitoring, and ensure that the structural shape in the construction phase meets the construction requirements.

[0173] It can be understood that the same or similar parts in the above-mentioned embodiments can be mutually referred to, and the contents not elaborated in some embodiments can be referred to the same or similar contents in other embodiments.

[0174] It should be noted that in the description of the present application, the terms "first", "second" and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise specified, the meaning of "a plurality of" is at least two.

[0175] Any process or method descriptions in flow charts or described elsewhere herein can be understood as representing code modules, segments, or portions of code which include one or more executable instructions for performing specific logic functions or steps in the process, and that the various embodiments of the application include the additional implementation that the functions can be performed in different orders, in different ways, or in different combinations or sub-combinations, and that the application should not be limited to the order or specific combinations of functions illustrated or discussed.

[0176] It should be understood that each of the elements of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following technologies known in the art or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0177] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium, and when executed, include one or a combination of steps of the method embodiments.

[0178] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can be physically present separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of a software function module. The integrated module, if realized in the form of a software function module and sold or used as an independent product, can also be stored in a computer readable storage medium.

[0179] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0180] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0181] Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A response prediction-based structural construction unloading monitoring method, characterized by, The method comprises the following steps: S10: establishing an influence relationship of monitoring responses on structural configurations by using a regression method; S20: predicting the structural configurations according to the influence relationship and the monitoring responses; S30: optimizing a prediction range of the structural configurations by using a uniform test design method, the uniform test design method using a finite element model and determining a structural configuration variation range by changing elastic modulus analysis of components, the uniform test design method being a test design method considering stiffness errors of components in multiple cases, and the prediction range of the structural configurations being an interval composed of maximum and minimum values of structural node configuration predictions under multiple combinations of the stiffness errors. The influence relationship is an influence relationship of monitoring response increments on structural configuration increments, and the influence relationship is a multivariate nonlinear relationship.

2. The response prediction based construction unloading monitoring method according to claim 1, wherein, The regression method is a Gaussian regression method.

3. The response prediction based construction unloading monitoring method of claim 2, wherein, The Gaussian regression method is used to solve occurrence probabilities of the structural configurations by using conditional probabilities based on Bayesian inference.

4. The response prediction based construction unloading monitoring method according to any one of claims 1-3, characterized in that, The prediction of the structural configurations is based on measured monitoring responses or full-process simulation analysis data, and the uniform test design is based on full-process simulation analysis data.

5. A response prediction-based structural construction unloading monitoring device, characterized by, The device comprises: an influence relationship establishing module configured to establish an influence relationship of monitoring responses on structural configurations by using a regression method; a structural configuration predicting module configured to predict the structural configurations according to the influence relationship and the monitoring responses; a prediction range optimizing module configured to optimize a prediction range of the structural configurations by using a uniform test design method, the uniform test design method using a finite element model and determining a structural configuration variation range by changing elastic modulus analysis of components, the uniform test design method being a test design method considering stiffness errors of components in multiple cases, and the prediction range of the structural configurations being an interval composed of maximum and minimum values of structural node configuration predictions under multiple combinations of the stiffness errors. The influence relationship is an influence relationship of monitoring response increments on structural configuration increments, and the influence relationship is a multivariate nonlinear relationship.

Images