Digital construction method and system of ETFE hyperbolic negative Gaussian cable membrane based on big data

Abstract

The present invention discloses a digital construction method and system for ETFE hyperbolic negative Gaussian cable membranes based on big data, which relates to the field of digital building technology. It includes obtaining the mechanical property data and historical data of the cable membrane, preprocessing the data, and extracting the features related to the cable membrane structure modeling according to the mechanical property data; calculating the mechanical property evaluation coefficient based on the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable membrane; real-time monitoring the cable membrane data, comparing and analyzing the real-time monitored cable membrane data with the pre-constructed three-dimensional geometric model, and adjusting the tension force of the cable according to the deviation size; establishing a performance prediction model for the ETFE hyperbolic negative Gaussian cable membrane structure, predicting the material aging speed of the cable membrane structure, and selecting the ETFE hyperbolic negative Gaussian cable membrane modeling structure in combination with the adjusted tension force. The present invention solves the problems of insufficient data utilization and lack of material aging prediction, and improves the accuracy and reliability of the model.

Description

Technical Field

[0001] The present invention relates to the field of digital building technology. More specifically, the present invention relates to a digital construction method and system for ETFE hyperbolic negative Gaussian cable-membrane based on big data. Background Art

[0002] The membrane structure, as a new type of building structure form, uses high-strength thin film materials and strengthening members (such as steel frames, steel columns or steel cables) to form a stable spatial structure through a specific tensioning method to bear external loads. ETFE (ethylene-tetrafluoroethylene copolymer) cable-membrane, as an excellent membrane material in the membrane structure, is widely used in modern buildings due to its excellent physical and chemical properties (light weight, good light transmittance, strong durability). The ETFE membrane can form a certain shape by air inflation or can be used as part of the cable-membrane system. The hyperbolic negative Gaussian surface is a common form of building surface with a curved structure that can be designed by certain geometric methods. The negative Gaussian surface usually refers to a surface with negative Gaussian curvature. Such surfaces are very beautiful and structurally stable in architectural design and are suitable for the design of membrane structures and other modern buildings. The cable-membrane structure is a building method with cables as the main support structure. The steel cables or other tensile elements bear the tension of the membrane material to form a stable building form. This structural form is very suitable for large-span buildings and buildings with special geometric shapes. In digital construction, big data can be used in multiple aspects, including: Design optimization: By analyzing a large amount of design and construction data, designers can optimize the shape, material usage and construction method of the membrane structure, reduce resource waste and improve the structural performance. Construction monitoring: Through sensors and real-time data collection technology, the construction process can be accurately monitored and controlled to ensure the construction quality and progress. Performance prediction and analysis: Big data technology can help predict the performance of the membrane structure under different climate conditions, including factors such as durability, light transmittance, wind load, etc. Digital construction: Digital construction refers to the precise management and control of the entire life cycle of building design, construction, management, etc. through information technologies (such as BIM, CAD, 3D modeling, laser scanning, robotic construction, etc.). Digital construction can make all links such as building design, construction, and operation more efficient, reduce human errors and improve construction accuracy. In the construction of ETFE hyperbolic negative Gaussian cable-membrane, digital construction technology combines advanced geometric calculation, simulation, and simulation tools as well as real-time data analysis. It can fully consider the shape, load of the membrane material and the impact of the external environment on the structure during the design stage, and guide the construction team to implement an accurate construction process through digital tools to ensure the stability and beauty of the structure.

[0003] For example, the digital construction method and system of ETFE hyperbolic negative Gaussian cable membrane based on big data disclosed in the invention patent with the publication number of CN114329746B includes the following steps: designing a structural model based on ETFE hyperbolic negative Gaussian cable membrane; constructing a tension change prediction model; obtaining first environmental data based on the coordinate position information of the construction site; predicting the tension change values of cable membranes of different materials through the tension change prediction model based on the first environmental data; judging whether the tension change values exceed the corresponding tension change limit values, if not, adding the corresponding material cable membranes to the first candidate queue; obtaining the light transmittance requirement, judging whether the light transmittance of each material cable membrane in the first candidate queue meets the light transmittance requirement, if so, adding the corresponding material cable membranes to the second candidate queue; selecting the target material cable membrane based on the anti-tension change ability and light transmittance of the cable membrane, and carrying out physical construction. The construction method of the present invention can improve the stability of the building structure and enhance the user experience.

[0004] Deficiencies of the prior art:

[0005] In traditional construction technologies, the mining and utilization of mechanical property data and historical data of cable membrane structures are insufficient, resulting in incomplete extraction of modeling features and deviations between the structural model and the actual working conditions. This solution constructs a more practical three-dimensional geometric model through systematic data collection, preprocessing, and accurate feature extraction, solving the problem of low model accuracy. In the past construction process, the monitoring and control means for cable membrane structures were limited, and it was difficult to adjust construction parameters in real time according to the actual situation. This solution realizes the dynamic control of the construction process by comparing and analyzing real-time monitoring data with the model, and timely adjusting the tension of the cables when deviations occur, avoiding potential structural safety hazards or rework caused by construction deviations. The prior art lacks effective prediction means for the aging of cable membrane structure materials, making maintenance work often lack pertinence and planning, resulting in waste of resources or untimely maintenance. This solution uses machine learning algorithms to establish a performance prediction model to predict the material aging speed in advance, providing a basis for scientific and reasonable maintenance decisions. Traditional construction methods are difficult to comprehensively consider various factors to optimize the construction plan, resulting in the cable membrane structures constructed being difficult to achieve the optimal balance in terms of safety, economy, and functionality. This solution combines the adjusted cable tension and material aging prediction to select the optimal modeling structure for physical construction, realizing the optimization of the construction plan.

[0006] In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a digital construction method and system of ETFE hyperbolic negative Gaussian cable membrane based on big data, and solve the problems raised in the above-mentioned background technology through the digital construction method and system of ETFE hyperbolic negative Gaussian cable membrane based on big data.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A digital construction method and system for ETFE hyperbolic negative Gaussian cable-membrane based on big data, comprising the following steps:

[0010] Obtain the mechanical property data and historical data of the cable-membrane, and preprocess the data. Extract the features related to the cable-membrane structure modeling from the mechanical property data, including elastic modulus, Poisson's ratio, and the initial tension of the cable;

[0011] Using finite element analysis software, combine the extracted features to construct a three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane, and calculate the mechanical property evaluation coefficient according to the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane;

[0012] Real-time monitor the cable-membrane data, and compare and analyze the real-time monitored cable-membrane data with the pre-constructed three-dimensional geometric model. If the deviation between the real-time monitored cable-membrane data and the mechanical property evaluation coefficient exceeds the preset threshold, adjust the tension force of the cable according to the deviation size;

[0013] Use machine learning algorithms to analyze the historical data and the real-time monitored cable-membrane data, establish a performance prediction model for the ETFE hyperbolic negative Gaussian cable-membrane structure, predict the material aging speed of the cable-membrane structure, select the ETFE hyperbolic negative Gaussian cable-membrane modeling structure in combination with the adjusted tension force, and perform physical construction according to the structural model.

[0014] In a preferred embodiment, the process of preprocessing the data is as follows:

[0015] Check whether there are missing values in the data. For a small number of missing values, use the method of mean filling;

[0016] For samples with a large number of missing values, if it does not affect the integrity of the overall data, delete the sample;

[0017] Use the box plot method to identify outliers. For the data points identified by the box plot, if it is less than the lower quartile subtracted by 1.5 times the interquartile range IQR or greater than the upper quartile plus 1.5 times the IQR, it is regarded as an outlier and the outlier is deleted; and use the Z-score normalization method to normalize the data.

[0018] In a preferred embodiment, the process of obtaining the elastic modulus is as follows:

[0019] Cut standard specimens from the ETFE membrane and cable materials, and obtain the cross-sectional area A and the original length of the specimens , install the specimen on a tensile testing machine, apply tensile force at a constant rate, and record the tensile force F and the corresponding elongation ΔL;

[0020] Divide the tensile force F by the cross-sectional area A of the specimen to obtain the stress, and divide the elongation ΔL by the original length to obtain the strain;

[0021] According to Hooke's law, within the elastic range, the stress σ is proportional to the strain ϵ. Calculate the elastic modulus through the linear part of the stress-strain curve. The specific calculation formula is as follows:

[0022] ;

[0023] In the formula, E is the elastic modulus, F is the tensile force, A is the cross-sectional area of the specimen, is the original length of the specimen, and ΔL is the elongation.

[0024] In a preferred embodiment, the process for obtaining the Poisson's ratio is as follows:

[0025] While measuring the elastic modulus during the tensile test, use an extensometer to measure the deformation of the specimen in the transverse and longitudinal directions, record the longitudinal elongation and the transverse contraction, and obtain the original transverse dimension of the specimen;

[0026] According to the definition of Poisson's ratio, calculate the ratio of the transverse strain to the longitudinal strain. The specific calculation formula is as follows:

[0027] ;

[0028] In the formula, B is Poisson's ratio, is the original length of the specimen, ΔL is the elongation, is the transverse contraction, is the original transverse dimension of the specimen.

[0029] In a preferred embodiment, the process for obtaining the initial tension of the cable is as follows:

[0030] For the installed cable structure, use the vibration frequency method and use a vibration sensor to measure the vibration frequency of the cable;

[0031] Obtain the length and mass of the cable, and calculate the mass per unit length of the cable;

[0032] According to the relationship between the vibration frequency and the tension of the cable, combined with the mass per unit length and the length of the cable, calculate the initial tension of the cable. The specific calculation formula is as follows:

[0033] ;

[0034] In the formula, T is the initial tension of the cable, L is the length of the cable, m is the mass of the cable, is the first-order vibration frequency measured;

[0035] For newly produced cables, their initial tensions are directly measured using a tensile testing machine before installation.

[0036] In a preferred embodiment, the specific calculation formula for the mechanical property evaluation coefficient calculated according to the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane is as follows:

[0037] ;

[0038] In the formula, P is the mechanical property evaluation coefficient, E is the elastic modulus, B is the Poisson's ratio, T is the initial tension of the cable, are the weight coefficients of the elastic modulus, Poisson's ratio, and initial tension of the cable respectively, which are obtained by calculating and analyzing historical data.

[0039] In a preferred embodiment, the process of adjusting the tensioning force of the cable according to the deviation size is as follows:

[0040] Real-time monitor the mechanical property data of the cable-membrane, and compare and analyze the cable-membrane data with the mechanical property evaluation coefficient, and calculate the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient;

[0041] Compare and analyze the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient with a preset threshold. If the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient is less than the preset threshold, there is no need to adjust the tensioning force of the cable;

[0042] If the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient is greater than the preset threshold, it is necessary to adjust the tensioning force of the cable according to the deviation size.

[0043] In a preferred embodiment, the formula for adjusting the tensioning force of the cable according to the deviation size is as follows:

[0044] ;

[0045] In the formula, is the current tensioning force of the cable, is the adjusted tensioning force of the cable, k is the proportional coefficient, which can be determined by experiments or finite element analysis, P is the mechanical property evaluation coefficient, is the mechanical property data of the cable-membrane monitored in real time.

[0046] In a preferred embodiment, the process of selecting the modeling structure of the ETFE hyperbolic negative Gaussian cable-membrane is as follows:

[0047] Based on the material aging rate and the adjusted tension force, perform fuzzy inference to determine whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure;

[0048] Define the material aging rate and the adjusted tension force as input variables, and divide them into different fuzzy sets respectively;

[0049] Define whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure as the output variable, and divide it into a fuzzy set;

[0050] Formulate fuzzy rules to describe the influence of the material aging rate and the adjusted tension force on whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure;

[0051] Based on the fuzzy rules, perform fuzzy inference to determine whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure.

[0052] In a preferred embodiment, it includes an acquisition module, an evaluation module, an adjustment module, and a selection module, and there are connections between the modules:

[0053] The acquisition module is used to acquire the mechanical property data and historical data of the cable-membrane, preprocess the data, and extract the features related to the cable-membrane structure modeling according to the mechanical property data, including elastic modulus, Poisson's ratio, and the initial tension of the cable;

[0054] The evaluation module is used to utilize finite element analysis software, combine the extracted features, construct a three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane, and calculate the mechanical property evaluation coefficient according to the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane;

[0055] The adjustment module is used to monitor the cable-membrane data in real time, compare and analyze the real-time monitored cable-membrane data with the pre-constructed three-dimensional geometric model. If the deviation between the real-time monitored cable-membrane data and the mechanical property evaluation coefficient exceeds the preset threshold, adjust the tension force of the cable according to the deviation magnitude;

[0056] The selection module is used to analyze the historical data and the real-time monitored cable-membrane data by using machine learning algorithms, establish a performance prediction model of the ETFE hyperbolic negative Gaussian cable-membrane structure, predict the material aging rate of the cable-membrane structure, select the ETFE hyperbolic negative Gaussian cable-membrane modeling structure in combination with the adjusted tension force, and perform entity construction according to the structure model.

[0057] The technical effects and advantages of the digital construction method and system of the ETFE hyperbolic negative Gaussian cable-membrane based on big data of the present invention:

[0058] 1. Through comprehensive data processing and feature extraction, combined with the three-dimensional geometric model constructed by finite element analysis, the present invention can more accurately simulate the mechanical behavior of the cable-membrane structure under different working conditions, improve the accuracy and reliability of the model, and provide a solid foundation for subsequent construction and performance prediction. The real-time monitoring and dynamic adjustment mechanism makes the construction process more precise, can correct deviations in a timely manner, ensure the construction quality of the cable-membrane structure, make the completed structure more in line with the design requirements, and improve the safety and stability of the structure. The application of machine learning algorithms realizes the accurate prediction of the aging rate of the cable-membrane structure materials, transforms the maintenance work from passive response to active prevention, and extends the service life of the cable-membrane structure. The modeling structure selected after comprehensively considering construction parameter adjustment and material aging factors can achieve a balance in multiple aspects such as the safety, durability, and economy of the cable-membrane structure, optimize the construction plan, and enhance the overall benefit of the project.

[0059] 2. Based on big data and running through the whole process of data collection, processing, analysis, and application, the present invention makes the construction process based on scientific data support, reducing the limitations and uncertainties of human experience judgment. By integrating multiple advanced technologies such as finite element analysis, real-time monitoring technology, and machine learning algorithms, a complete digital construction system is formed, representing the application of cutting-edge technologies in the field of building construction and promoting the technological upgrading of the industry. From the model construction before construction, to the control during the construction process, and then to the performance prediction and maintenance after completion, the whole life cycle management of the ETFE hyperbolic negative Gaussian cable-membrane structure is realized, improving the efficiency and level of project management. Through precise construction and optimized construction plans, construction errors and resource waste are reduced, construction costs are lowered; accurate prediction of material aging and maintenance decisions extend the service life of the structure and reduce later maintenance costs, with good economic benefits. At the same time, the structural safety is ensured, providing a more reliable space environment for users, with significant social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic structural diagram of the digital construction method and system of the ETFE hyperbolic negative Gaussian cable-membrane based on big data of the present invention.

[0061] Figure 2 It is a schematic structural diagram of the digital construction method and system of the ETFE hyperbolic negative Gaussian cable-membrane based on big data of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0063] Example 1 Figure 1 This invention provides a digital construction method for ETFE hyperbolic negative Gaussian cable-membrane based on big data.

[0064] Obtain the mechanical property data and historical data of the cable-membrane, and preprocess the data. Extract the features related to the cable-membrane structure modeling from the mechanical property data, including elastic modulus, Poisson's ratio, and the initial tension of the cable;

[0065] Obtain the mechanical property data and historical data of the cable-membrane, and preprocess the data. Check whether there are missing values in the dataset. For a small number of missing values, the method of mean filling can be used; for samples with a large number of missing values, if it does not affect the integrity of the overall data, the sample can be considered for deletion;

[0066] Use the box plot method to identify outliers. For the data points identified through the box plot, if it is less than the lower quartile minus 1.5 times the interquartile range IQR or greater than the upper quartile plus 1.5 times the IQR, it is regarded as an outlier. For outliers, they can be deleted according to the actual situation;

[0067] In order to eliminate the influence of the dimension of different data indicators, the Z-score standardization method is adopted.

[0068] The process of extracting the features related to the cable-membrane structure modeling from the mechanical property data, including elastic modulus, Poisson's ratio, and the initial tension of the cable, is as follows:

[0069] Directly extract the elastic modulus, Poisson's ratio, and the initial tension of the cable from the preprocessed mechanical property data as the features related to the cable-membrane structure modeling. These features will be used as important input parameters for the subsequent cable-membrane structure modeling;

[0070] The process of obtaining the elastic modulus is as follows:

[0071] Cut standard specimens from the ETFE membrane and cable materials, and obtain the cross-sectional area A and the original length , install the specimen on a tensile testing machine, apply a tensile force at a constant rate, and record the tensile force F and the corresponding elongation ΔL at the same time;

[0072] Divide the tensile force F by the cross-sectional area A of the specimen to obtain the stress, and divide the elongation ΔL by the original length to obtain the strain;

[0073] According to Hooke's law, within the elastic range, the stress σ is proportional to the strain ϵ. Calculate the elastic modulus through the linear part of the stress-strain curve. The specific calculation formula is as follows:

[0074] ;

[0075] Wherein, E is the elastic modulus, F is the tensile force, A is the cross-sectional area of the specimen, is the original length of the specimen, and ΔL is the elongation;

[0076] The process of obtaining the Poisson's ratio is as follows:

[0077] While measuring the elastic modulus during the tensile test, use an extensometer to measure the deformation of the specimen in the transverse and longitudinal directions, record the longitudinal elongation and the transverse contraction, and obtain the original transverse dimension of the specimen;

[0078] According to the definition of Poisson's ratio, calculate the ratio of the transverse strain to the longitudinal strain. The specific calculation formula is as follows:

[0079] ;

[0080] Wherein, B is the Poisson's ratio, is the original length of the specimen, ΔL is the elongation, is the transverse contraction, is the original transverse dimension of the specimen;

[0081] The process of obtaining the initial tension of the cable is as follows:

[0082] For the installed cable structure, adopt the vibration frequency method and use a vibration sensor to measure the vibration frequency of the cable;

[0083] Obtain the length and mass of the cable, and calculate the mass per unit length of the cable;

[0084] According to the relationship between the vibration frequency and the tension of the cable, combined with the mass per unit length and the length of the cable, calculate the initial tension of the cable. The specific calculation formula is as follows:

[0085] ;

[0086] Wherein, T is the initial tension of the cable, L is the length of the cable, m is the mass of the cable, is the measured first-order vibration frequency;

[0087] For the newly produced cable, directly measure its initial tension using a tensile testing machine before installation.

[0088] Using finite element analysis software, combined with the extracted features, construct a three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane, and calculate the mechanical property evaluation coefficient according to the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane;

[0089] According to the design drawings and actual dimensions, use the geometric modeling tool of the finite element analysis software to construct a three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane structure;

[0090] Assign the previously extracted characteristics related to the cable-membrane structure modeling, namely the elastic modulus, Poisson's ratio, and the initial tension of the cable, to the corresponding cable and membrane elements;

[0091] Carry out mesh division on the geometric model, discretize it into a finite number of elements, and select the element type and mesh density according to the complexity of the model and the requirements of calculation accuracy; for the cable structure, rod elements or cable elements can be used; for the membrane structure, shell elements can be selected;

[0092] Identify the different working conditions that need to be considered for the cable-membrane structure, such as self-weight, wind load, and snow load. According to the requirements of different working conditions, apply the corresponding loads to the finite element model to obtain the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane structure;

[0093] The specific calculation formula for the mechanical property evaluation coefficient calculated according to the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane structure is as follows:

[0094] ;

[0095] In the formula, P is the mechanical property evaluation coefficient, E is the elastic modulus, B is Poisson's ratio, T is the initial tension of the cable, are the weight coefficients of the elastic modulus, Poisson's ratio, and the initial tension of the cable respectively, which are obtained by calculation and analysis of historical data.

[0096] Real-time monitor the cable-membrane data, and compare and analyze the real-time monitored cable-membrane data with the pre-constructed three-dimensional geometric model. If the deviation between the real-time monitored cable-membrane data and the mechanical property evaluation coefficient exceeds the preset threshold, adjust the tensioning force of the cable according to the deviation size;

[0097] Real-time monitor the mechanical property data of the cable-membrane, and compare and analyze the cable-membrane data with the mechanical property evaluation coefficient, and calculate the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient;

[0098] Compare and analyze the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient with the preset threshold. If the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient is less than the preset threshold, there is no need to adjust the tensioning force of the cable; if the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient is greater than the preset threshold, it is necessary to adjust the tensioning force of the cable according to the deviation size. The specific calculation formula is as follows:

[0099] ;

[0100] In the formula, is the tension force of the current cable, is the adjusted tension force of the cable, k is the proportionality coefficient, which can be determined by experiments or finite element analysis, and P is the mechanical property evaluation coefficient. are the mechanical property data of the cable-membrane structure monitored in real time.

[0101] Use machine learning algorithms to analyze historical data and real-time monitored cable-membrane data, establish a performance prediction model for the ETFE hyperbolic negative Gaussian cable-membrane structure, predict the material aging rate of the cable-membrane structure, select the ETFE hyperbolic negative Gaussian cable-membrane modeling structure in combination with the adjusted tension force, and carry out physical construction according to the structural model.

[0102] Preprocess the historical data and real-time monitored cable-membrane data, and select machine learning algorithms according to the data characteristics and prediction objectives;

[0103] Extract features related to the material aging rate from the preprocessed data, such as stress level, temperature change, and cumulative amount of ultraviolet radiation;

[0104] Divide the historical data and real-time monitored data into training sets and test sets, use the training sets to train the selected machine learning model, and adjust the parameters of the model so that the model can learn the patterns and rules in the data; during the training process, methods such as cross-validation can be used to evaluate the performance of the model and prevent overfitting;

[0105] Input the current real-time monitored data into the trained model to predict the material aging rate of the ETFE hyperbolic negative Gaussian cable-membrane structure;

[0106] Conduct fuzzy inference based on the material aging rate and the adjusted tension force to determine whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure;

[0107] The specific steps are as follows:

[0108] Step C1, define the material aging rate and the adjusted tension force as input variables, and divide them into different fuzzy sets respectively.

[0109] For example, "Low", "Medium", "High" for the material aging rate, and "Low", "Medium", "High" for the adjusted tension force;

[0110] Step C2, define whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure as the output variable, and divide it into a fuzzy set. For example, "No", "Yes" for whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure;

[0111] Step C3: Develop a set of fuzzy rules to describe the influence of different input variables on the output variable. The definition of the rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0112] Mark the material aging rate as H, and the adjusted tension force as , and mark whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure as D. Then, the following can be defined

[0113] Rule 1: IF (H is High) AND ( is Low) THEN (D is No )

[0114] Rule 2: IF (H is Low) AND ( is High) THEN (D is Yes ) ...

[0115] Step C4: Perform fuzzy reasoning according to the fuzzy rules to determine whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure.

[0116] It should be noted that the division of the fuzzy set can be adjusted according to the actual situation. For example, although this embodiment takes three fuzzy sets as an example, in fact, the material aging rate, the adjusted tension force, and whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure can be divided into more than three sets to facilitate better precise adjustment.

[0117] Furthermore, for the judgment of whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure, a threshold can be set for judgment according to the actual situation. For example, when the material aging rate exceeds 0.8, it is calibrated as "High", and when the adjusted tension force is higher than 10, it is calibrated as "High", etc. Details are not elaborated here.

[0118] Example 2 Figure 2 A digital construction system for ETFE hyperbolic negative Gaussian cable-membrane based on big data is presented.

[0119] The digital construction system for ETFE hyperbolic negative Gaussian cable-membrane based on big data includes an acquisition module, an evaluation module, an adjustment module, and a selection module. There are connections between the modules:

[0120] The acquisition module is used to acquire the mechanical property data and historical data of the cable-membrane, and preprocess the data. Extract the features related to the cable-membrane structure modeling from the mechanical property data, including elastic modulus, Poisson's ratio, and the initial tension of the cable;

[0121] An evaluation module, which is used to construct a three-dimensional geometric model of an ETFE hyperbolic negative Gaussian cable membrane by using finite element analysis software in combination with the extracted features, and calculate a mechanical property evaluation coefficient based on the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable membrane;

[0122] An adjustment module, which is used to monitor the cable membrane data in real time, and conduct a comparative analysis of the real-time monitored cable membrane data with the pre-constructed three-dimensional geometric model. If the deviation between the real-time monitored cable membrane data and the mechanical property evaluation coefficient exceeds a preset threshold, the tension force of the cable is adjusted according to the size of the deviation;

[0123] A selection module, which is used to analyze the historical data and the real-time monitored cable membrane data by using machine learning algorithms, establish a performance prediction model of the ETFE hyperbolic negative Gaussian cable membrane structure, predict the material aging speed of the cable membrane structure, select the ETFE hyperbolic negative Gaussian cable membrane modeling structure in combination with the adjusted tension force, and carry out physical construction according to the structural model.

[0124] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0125] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product.

[0126] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0127] In addition, the functional modules in each embodiment of this application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0128] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claimed rights.

[0129] Finally, the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A digital construction method for ETFE hyperbolic negative Gaussian cable membranes based on big data, characterized in that, The method includes the following steps: Obtain the mechanical property data and historical data of the cable-membrane, and preprocess the data. Extract the features related to the cable-membrane structure modeling from the mechanical property data, including elastic modulus, Poisson's ratio, and the initial tension of the cable. Use finite element analysis software, combined with the extracted features, to construct a three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane, and calculate the mechanical property evaluation coefficient based on the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane. The specific calculation formula is as follows: ； Wherein, P is the mechanical property evaluation coefficient, E is the elastic modulus, B is the Poisson's ratio, and T is the initial tension of the cable. are the weight coefficients of the elastic modulus, Poisson's ratio, and initial tension of the cable, respectively. Real-time monitor the cable-membrane data, and compare and analyze the real-time monitored cable-membrane data with the pre-constructed three-dimensional geometric model. If the deviation between the real-time monitored cable-membrane data and the mechanical property evaluation coefficient exceeds the preset threshold, adjust the tension force of the cable according to the deviation size. Use machine learning algorithms to analyze the historical data and the real-time monitored cable-membrane data, establish a performance prediction model of the ETFE hyperbolic negative Gaussian cable-membrane structure, predict the material aging speed of the cable-membrane structure, select the modeling structure of the ETFE hyperbolic negative Gaussian cable-membrane in combination with the adjusted tension force, and carry out entity construction according to the structure model.

2. The digital construction method of ETFE hyperbolic negative Gaussian cable membrane based on big data according to claim 1, wherein, The process of preprocessing the data is as follows: Check whether there are missing values in the data. For a small number of missing values, use the method of mean filling. For samples with a large number of missing values, if they do not affect the integrity of the overall data, delete the samples. Use the box plot method to identify outliers. For the data points identified by the box plot, if it is less than the lower quartile minus 1.5 times the interquartile range IQR or greater than the upper quartile plus 1.5 times the IQR, it is regarded as an outlier and the outlier is deleted; and the Z-score normalization method is used to normalize the data.

3. The digital construction method of ETFE hyperbolic negative Gaussian cable membrane based on big data according to claim 2, wherein, The process of obtaining the elastic modulus is as follows: Cut standard specimens from the ETFE film and cable materials, and obtain the cross-sectional area A and the original length of the specimens. Install the specimens on a tensile testing machine, apply a tensile force at a constant rate, and record the tensile force F and the corresponding elongation ΔL. Dividing the tensile force F by the cross-sectional area A of the specimen gives the stress, and dividing the elongation ΔL by the original length gives the strain; According to Hooke's law, within the elastic range, the stress σ is proportional to the strain ϵ. Calculate the elastic modulus through the linear part of the stress-strain curve. The specific calculation formula is as follows: ； Where E is the elastic modulus, F is the tensile force, A is the cross-sectional area of the specimen, is the original length of the specimen, and ΔL is the elongation.

4. The digital construction method of ETFE hyperbolic negative Gaussian cable membrane based on big data according to claim 3, characterized in that, The process of obtaining Poisson's ratio is as follows: While measuring the elastic modulus during the tensile test, use an extensometer to measure the deformation of the specimen in the transverse and longitudinal directions, record the longitudinal elongation and the transverse contraction, and obtain the original transverse size of the specimen. According to the definition of Poisson's ratio, calculate the ratio of the transverse strain to the longitudinal strain. The specific calculation formula is as follows: ; where B is the Poisson's ratio, is the original length of the specimen, ΔL is the elongation, is the lateral contraction, is the original lateral dimension of the specimen.

5. The digital construction method of ETFE hyperbolic negative Gaussian cable membrane based on big data according to claim 4, characterized in that, The process of obtaining the initial tension of the cable is as follows: For the installed cable structure, use the vibration frequency method and use a vibration sensor to measure the vibration frequency of the cable. Obtain the length and mass of the cable, and calculate the mass per unit length of the cable. According to the relationship between the vibration frequency and the tension of the cable, combined with the mass per unit length and the length of the cable, calculate the initial tension of the cable. The specific calculation formula is as follows: ; where T is the initial tension of the cable, L is the length of the cable, m is the mass of the cable, is the measured first-order vibration frequency; For newly produced cables, directly measure their initial tension using a tensile testing machine before installation.

6. The digital construction method of ETFE hyperbolic negative Gaussian cable membrane based on big data according to claim 5, characterized in that, The process of adjusting the tension force of the cable according to the deviation size is as follows: Real-time monitor the mechanical property data of the cable-membrane, and compare and analyze the cable-membrane data with the mechanical property evaluation coefficient, and calculate the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient. Compare and analyze the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient with the preset threshold. If the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient is less than the preset threshold, there is no need to adjust the tension force of the cable. If the deviation value between the mechanical property data of the cable-membrane and the mechanical property evaluation coefficient is greater than the preset threshold, it is necessary to adjust the tension force of the cable according to the deviation size.

7. The digital construction method of ETFE hyperbolic negative Gaussian cable membrane based on big data according to claim 6, characterized in that, Adjust the tension force of the cable according to the deviation size. The specific calculation formula is as follows: ； In the formula, is the tension force of the current cable, is the adjusted tension force of the cable, k is the proportionality coefficient, which can be determined by experiments or finite element analysis, P is the mechanical property evaluation coefficient, is the mechanical property data of the cable-membrane monitored in real time.

8. The digital construction method of ETFE hyperbolic negative Gaussian cable membrane based on big data according to claim 7, characterized in that The process of selecting the ETFE hyperbolic negative Gaussian cable-membrane modeling structure is as follows: Based on the material aging rate and the adjusted tension force, perform fuzzy inference to determine whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure; Define the material aging rate and the adjusted tension force as input variables, and divide them into different fuzzy sets respectively; Define whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure as the output variable, and divide it into a fuzzy set; Formulate fuzzy rules to describe the influence of the material aging rate and the adjusted tension force on whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure; Based on the fuzzy rules, perform fuzzy inference to determine whether to select this modeling structure as the ETFE hyperbolic negative Gaussian cable-membrane modeling structure.

9. A digital construction system for ETFE hyperbolic negative Gaussian cable membranes based on big data, characterized in that, It includes an acquisition module, an evaluation module, an adjustment module, and a selection module, and there are connections between the modules: The acquisition module is used to acquire the mechanical property data and historical data of the cable-membrane, preprocess the data, and extract the features related to the cable-membrane structure modeling from the mechanical property data, including the elastic modulus, Poisson's ratio, and the initial tension of the cable; The evaluation module is used to use finite element analysis software, combine the extracted features, construct a three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane, and calculate the mechanical property evaluation coefficient according to the three-dimensional geometric model of the ETFE hyperbolic negative Gaussian cable-membrane; the specific calculation formula is as follows: ； Wherein, P is the mechanical property evaluation coefficient, E is the elastic modulus, B is the Poisson's ratio, and T is the initial tension of the cable. They are respectively the weight coefficients of the elastic modulus, the Poisson's ratio, and the initial tension of the cable. The adjustment module is used to monitor the cable-membrane data in real time, and compare and analyze the real-time monitored cable-membrane data with the pre-constructed three-dimensional geometric model. If the deviation between the real-time monitored cable-membrane data and the mechanical property evaluation coefficient exceeds the preset threshold, adjust the tension force of the cable according to the deviation size; The selection module is used to analyze the historical data and the real-time monitored cable-membrane data by using machine learning algorithms, establish a performance prediction model of the ETFE hyperbolic negative Gaussian cable-membrane structure, predict the material aging rate of the cable-membrane structure, select the ETFE hyperbolic negative Gaussian cable-membrane modeling structure in combination with the adjusted tension force, and perform entity construction according to the structural model.

Images