Multifunctional assembly type heat insulation wall system and assembly method

Abstract

The invention relates to the technical field of building construction, and discloses a multifunctional assembly type heat insulation wall system and an assembly method.The system integrates a parameter input module, an intelligent analysis module and a data storage module, and full-process intelligent management from design to performance prediction is achieved. A user submits key parameters such as wall size, heat insulation material selection and structural frame design and regional climate data through the parameter input module, and the intelligent analysis module accurately predicts the heat insulation performance, the expected service life and the construction cost of the wall under different environmental conditions by applying an advanced machine learning algorithm. And the data storage module ensures that all design parameters and prediction results are completely recorded, so that subsequent analysis and optimization are facilitated. According to the system, dynamic environmental factors and user requirements are comprehensively considered, and the scientificity and economical efficiency of wall design are remarkably improved.

Description

Technical Field

[0001] The invention relates to the technical field of building construction, in particular to a multifunctional assembled heat-insulating wall system and an assembly method. Background Art

[0002] In the field of architecture, walls, as an important part of buildings, not only bear the function of structural support, but also directly affect the energy consumption, comfort and durability of buildings. With the global emphasis on energy conservation, emission reduction and sustainable development, the development of wall systems with efficient thermal insulation performance has become an important direction of current architectural technology innovation. Current wall designs mostly rely on engineers' experience and static analysis, and it is difficult to fully consider the dynamic environmental changes and diverse user needs in actual use.

[0003] The thermal insulation effect of walls in actual use is affected by many factors, such as regional climate differences, seasonal changes, solar radiation angle and intensity, etc. The current lack of accurate prediction and consideration of these dynamic factors often leads to a large deviation between the thermal insulation performance of walls and design expectations, affecting the energy efficiency and living comfort of buildings.

[0004] Moreover, the service life of the wall is affected by multiple factors such as material aging, environmental factors (such as temperature and humidity changes, wind pressure, ultraviolet radiation), and construction quality. Most existing design methods focus on the durability test of the material itself, while ignoring the long-term performance evolution of the wall system as a whole in a complex environment, resulting in inaccurate service life prediction and difficulty in guiding maintenance plans and long-term cost management. Summary of the invention

[0005] The object of the present invention is to provide a multifunctional assembled heat-insulating wall system and an assembly method to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a multifunctional assembled heat-insulating wall system, the system comprising:

[0007] A parameter input module, used for receiving wall design parameters input by a user;

[0008] Intelligent analysis module, used to predict the thermal insulation performance index, expected service life and construction cost of the wall under different environmental conditions through machine learning algorithm according to the wall design parameters obtained by the parameter input module;

[0009] The data storage module is used to store the design parameters input by the user and their corresponding prediction results output by the intelligent analysis module.

[0010] Preferably, the wall design parameters include the size of the wall, the choice of insulation materials, the design method of the structural frame, the connection method of the connectors and the climate data of the area where the wall is located; the climate data includes the average, maximum and minimum values ​​of the temperature, humidity, solar radiation intensity and wind speed recorded in the history of the area.

[0011] Preferably, the intelligent analysis module uses a machine learning algorithm to respectively construct a thermal insulation performance index prediction model, a service life prediction model and a construction cost prediction model.

[0012] Preferably, the machine learning algorithms used by the intelligent analysis module to construct the three prediction models are all linear regression algorithms.

[0013] Preferably, the steps of constructing three prediction models by the intelligent analysis module include:

[0014] Step 1: Extract historical wall design parameters and their corresponding actual thermal insulation performance indicators, service life and construction cost data from the data storage module;

[0015] Step 2: Clean the data, including removing outliers and missing values; and standardize the cleaned data;

[0016] Step 3: From the data processed in step 2, select features related to thermal insulation performance index, service life and construction cost as input variables of the model to form a feature data set; further divide the feature data set into a training data set and a validation data set according to a certain ratio;

[0017] Step 4: Based on the feature data set, the thermal insulation performance index prediction model, service life prediction model and construction cost prediction model are constructed using the linear regression algorithm respectively; the parameters of the model are obtained by fitting the linear relationship between the input variables and the output variables in the historical data;

[0018] Step 5: Use the training data set to train the constructed model, and continuously adjust the model parameters through iterative optimization algorithms to minimize the error between the model's prediction results and the actual data;

[0019] Step 6: Use the validation data set to validate the trained model and evaluate the model's predictive performance; if the model's predictive performance meets expectations, the training ends; otherwise, return to step 3 to rebuild the model or adjust feature selection.

[0020] Preferably, the formula of the linear regression algorithm is:

[0021] y=β0+β1x1+β2x2+...+β n x n +∈

[0022] Among them, y represents the predicted value, x1, x2, ..., x n represents the wall design parameters that affect the prediction results input by the user, including the wall size, the choice of insulation materials, the design of the structural frame, the connection method of the connectors, and the climate data of the area where the wall is located; β1, β2, ..., β n is the parameter of the model, obtained through model training; β0 is the intercept term, which represents the expected value of y when all control items x are 0; ∈ is the error term, which represents the difference between the actual value and the model predicted value.

[0023] Preferably, when initializing the model parameters, the intelligent analysis module is used to initialize the model parameters for each feature x in the linear regression model. i The corresponding parameter β i Assign an initial value, which is set to a random number close to 0, and also assign an initial value to the intercept term β0; these initial parameter values ​​will serve as the starting point for model training, and will be continuously optimized and adjusted through subsequent training processes until the goal of minimizing the gap between the predicted value and the actual value is achieved.

[0024] Preferably, the intelligent analysis module uses the data in the training data set to continuously iterate and update the parameters of the linear regression model through a gradient descent algorithm. In each iteration, the values ​​of the model parameters are adjusted according to the gradient information of the loss function to the model parameters until the loss function converges or reaches a preset number of iterations, wherein the calculation formula of the gradient descent algorithm is:

[0025]

[0026] Among them, θ represents the model parameters, including all weights and biases that the model needs to learn; ω represents the learning rate, which is used to control the step size of parameter update; represents the gradient of the loss function J(θ) with respect to the parameter θ, is a vector pointing to the direction where the loss function grows fastest; := represents the assignment operation, that is, updating the value of the parameter θ.

[0027] Preferably, the intelligent analysis module uses a mean square error (MSE) algorithm to evaluate the performance of the prediction model, and the algorithm formula is:

[0028]

[0029] Where n is the number of data points, Y pred，i is the predicted value of the model, Y actual，i is the actual value; the prediction accuracy of the model is evaluated according to the MSE value. The smaller the MSE value, the higher the prediction accuracy of the model.

[0030] Preferably, an assembly method is applied to the above-mentioned multifunctional prefabricated thermal insulation wall system, the method comprising: a user dynamically adjusts the input design parameters through a parameter input module to obtain different prediction results, and compares the prediction results with the actual expected thermal insulation performance indicators, expected service life and construction costs to determine whether the prediction results meet the requirements. When the prediction results meet the requirements, this design parameter is determined as the design parameter for the actual wall construction.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The parameter input module collects wall design parameters, including wall size, insulation material selection, structural frame design, connection methods, and regional climate data. This system can fully consider the dynamic environmental changes in actual use. The intelligent analysis module uses machine learning algorithms to accurately predict the thermal insulation performance indicators of the wall under different environmental conditions. This dynamic and comprehensive prediction method significantly improves the accuracy of thermal insulation performance evaluation, which helps to achieve efficient energy utilization of buildings and improve living comfort.

[0033] This system not only focuses on the durability of the material itself, but also comprehensively considers the long-term performance evolution of the wall system as a whole in a complex environment. The service life prediction model built by the intelligent analysis module can accurately evaluate the expected service life of the wall under the combined effects of multiple factors (such as material aging, temperature and humidity changes, wind pressure, ultraviolet radiation, etc.), which helps to formulate reasonable maintenance plans and long-term cost management strategies, reduce maintenance costs, and extend the overall service life of the building.

[0034] This system can accurately estimate the wall construction cost through the construction cost prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is the overall structure diagram of the system of the present invention;

[0036] Figure 2 is a flow chart of the assembly method of the present invention;

[0037] Figure 3 Flowchart for building a predictive model for the smart analytics module. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] See also Figure 1-3 The present invention provides a technical solution: a multifunctional assembled heat-insulating wall system, the system comprising:

[0040] Parameter input module, which is responsible for receiving the wall design parameters input by the user, and the wall design parameters cover the basic physical characteristics of the wall and external environmental factors. Specifically, the user needs to input the size of the wall (including length, width and height), the type of thermal insulation material selected, the design method of the structural frame, the connection method of the connectors, and the climate data of the area where the wall is located. Climate data includes but is not limited to the average, maximum and minimum values ​​of the temperature in the historical records of the area, the average, maximum and minimum values ​​of humidity, the average and maximum values ​​of solar radiation intensity, and the average and maximum values ​​of wind speed.

[0041] Intelligent analysis module, based on machine learning algorithm, conducts in-depth analysis and prediction on the data obtained by parameter input module. This module builds three main prediction models: thermal insulation performance index prediction model, service life prediction model and construction cost prediction model.

[0042] Thermal insulation performance index prediction model: Taking into account the wall design parameters and climate data, the thermal insulation performance indicators of the wall under different environmental conditions, such as thermal conductivity, thermal resistance, etc., are predicted through machine learning algorithms, thereby evaluating the thermal insulation effect of the wall.

[0043] Service life prediction model: Combines material aging characteristics, environmental factors (such as temperature and humidity changes, wind pressure, ultraviolet radiation), and construction quality to predict the expected service life of the wall through machine learning algorithms.

[0044] Construction cost prediction model: Based on the wall design parameters and current market price information, the construction cost of the wall is estimated through a machine learning algorithm to help users make economically reasonable design choices.

[0045] The data storage module is used to store the design parameters input by the user and the corresponding prediction results output by the intelligent analysis module. These data not only provide design references for the current project, but also serve as historical data to provide training samples for intelligent analysis of similar projects in the future, and continuously optimize the accuracy of the prediction model.

[0046] The present invention will be further described below in conjunction with Examples 1 to 2:

[0047] Embodiment 1:

[0048] This embodiment is used to describe the implementation method of the intelligent analysis module using a linear regression algorithm to construct a thermal insulation performance index prediction model, a service life prediction model, and a construction cost prediction model. The specific steps include:

[0049] Step 1: Extract historical wall design parameters and their corresponding actual insulation performance indicators, service life and construction cost data from the data storage module. These data come from past construction projects and include wall dimensions, insulation material selection, structural frame design, connector connection methods, climate data in the area (such as temperature, humidity, solar radiation intensity, wind speed, etc.), and actual measured insulation performance indicators (such as thermal conductivity), service life (in years) and construction cost (in monetary units). The database data in the data storage module can be initialized by collecting historical construction data or simulation data constructed by engineers.

[0050] Step 2: Clean the extracted data, first remove outliers and missing values ​​caused by recording errors or measurement equipment failures. Next, standardize the cleaned data and convert the eigenvalues ​​of different dimensions to the same scale to eliminate the impact of dimensional differences on model training. For example, the Z-score standardization method can be used to subtract the mean of each eigenvalue and divide it by the standard deviation, so that the processed data conforms to the standard normal distribution.

[0051] Step 3: From the cleaned and standardized data, select features that are closely related to thermal insulation performance indicators, service life, and construction costs as input variables of the model. The features include the size parameters of the wall (such as area, thickness), the thermal conductivity of the insulation material, the material and form of the structural frame, the type of connectors, and the temperature, humidity, solar radiation intensity, etc. in the climate data. Then, the data set containing these features is divided into a training data set and a validation data set according to a certain ratio (such as 70% training set, 30% validation set) for model training and validation.

[0052] Step 4: Based on the selected feature data set, use the linear regression algorithm to build the thermal insulation performance index prediction model, service life prediction model and construction cost prediction model. The linear regression model assumes that there is a linear relationship between the input variable and the output variable, that is, this relationship can be approximated by fitting a straight line (or hyperplane). Through the subsequent training process, continuous optimization and adjustment are carried out to find the model parameters that minimize the error between the predicted value and the actual value; the formula of the linear regression algorithm is:

[0053] y=β0+β1x1+β2x2+...+β n x n +∈

[0054] Among them, y represents the predicted value, x1, x2, ..., x nrepresents the wall design parameters that affect the prediction results input by the user, including the wall size, the choice of insulation materials, the design of the structural frame, the connection method of the connectors, and the climate data of the area where the wall is located; β1, β2, ..., β n is the parameter of the model, obtained through model training; β0 is the intercept term, which represents the expected value of y when all control items x are 0; ∈ is the error term, which represents the difference between the actual value and the model predicted value.

[0055] When initializing the model parameters, for each feature x in the linear regression model i The corresponding parameter β i Assign an initial value, which is set to a random number close to 0, and also assign an initial value to the intercept term β0; these initial parameter values ​​will serve as the starting point for model training, and will be continuously optimized and adjusted through subsequent training processes until the goal of minimizing the gap between the predicted value and the actual value is achieved.

[0056] Step 5: Use the training data set to train the constructed model. During the training process, the parameters of the linear regression model are continuously updated through the gradient descent algorithm. In each iteration, the values ​​of the model parameters are adjusted according to the gradient information of the loss function to the model parameters. The calculation formula of the gradient descent algorithm is:

[0057]

[0058] Among them, θ represents the model parameters, including all weights and biases that the model needs to learn; ω represents the learning rate, which is used to control the step size of parameter update; represents the gradient of the loss function J(θ) with respect to the parameter θ, is a vector pointing to the direction where the loss function grows fastest; := represents the assignment operation, that is, updating the value of the parameter θ.

[0059] During the training process, you can set stop conditions, such as reaching the maximum number of iterations, the error change rate being less than a certain threshold, etc., to control the termination of the training process.

[0060] Step 6: Use the validation data set to validate the trained model and evaluate its prediction performance. Common evaluation indicators include mean square error (MSE). The mean square error MSE algorithm evaluates the performance of the prediction model. Its algorithm formula is:

[0061]

[0062] Where n is the number of data points, Y pred,i is the predicted value of the model, Y actual,iis the actual value; the prediction accuracy of the model is evaluated according to the MSE value. The smaller the MSE value, the higher the prediction accuracy of the model. If the prediction performance of the model meets expectations (such as MSE is less than a certain set value), the training ends; otherwise, it is necessary to return to step 3 to rebuild the model or adjust the feature selection. When rebuilding the model, you can try different feature combinations, increase or decrease features, or use other machine learning algorithms (such as decision trees, random forests, neural networks, etc.) to train the model to find a better prediction model.

[0063] Embodiment 2:

[0064] The following will describe in detail an assembly method using the multifunctional assembled heat-insulating wall system described above in conjunction with a specific example, the method comprising:

[0065] First, the user inputs the initial design parameters through the parameter input module. These design parameters include but are not limited to the size of the wall (such as length, width, height), the type and thickness of the insulation material, the material and form of the structural frame, the type and arrangement of the connectors, etc. In addition, the user also needs to input the climate data of the area, such as the average annual temperature, humidity, solar radiation intensity, wind speed, etc., in order to more accurately predict the thermal insulation performance of the wall.

[0066] Based on the design parameters input by the user, the system calls the thermal insulation performance index prediction model, service life prediction model and construction cost prediction model in the intelligent analysis module to calculate the corresponding prediction results. These prediction results include the thermal insulation performance index of the wall (such as thermal conductivity, thermal resistance, etc.), expected service life (in years) and construction cost (including material cost, construction cost, etc.).

[0067] The user will compare the predicted results with the actual expected thermal insulation performance indicators, expected service life and construction costs. If the predicted results meet or exceed the actual needs of the user, it means that the current design parameters are feasible, and the user can determine this design parameter as the design parameter for the actual wall construction.

[0068] If the prediction results do not meet the user's needs, the user can dynamically adjust the input design parameters through the parameter input module. For example, the user can try to replace the insulation material, increase the thickness of the insulation layer, change the material or form of the structural frame, adjust the layout of the connectors, etc. to obtain new prediction results. The user can compare and judge again based on the new prediction results until the design parameters that meet the needs are found.

[0069] In the specific implementation, taking a building in a certain area as an example, the user first inputs the preliminary design parameters of the wall through the parameter input module, including the wall size of 10 meters × 3 meters × 0.3 meters (length × width × thickness), the selection of a certain insulation material, the structural frame is a steel structure, the connection parts are bolted, and the climate data of the area is input. After the system calls the intelligent analysis module for calculation, it obtains the predicted value of the thermal insulation performance index of 0.45W / (m·K), the expected service life is 25 years, and the construction cost is 200 yuan per square meter.

[0070] The user compared these prediction results with the actual expectations and found that the thermal insulation performance index and expected service life met the requirements, but the construction cost was slightly higher than expected. Therefore, the user adjusted the type of thermal insulation material through the parameter input module, selected a material with lower cost but similar thermal insulation performance, and re-predicted. The new prediction results showed that the thermal insulation performance index decreased slightly but still met the requirements, the expected service life remained unchanged, and the construction cost was reduced to 180 yuan per square meter, which met the user's expectations. Finally, the user determined this set of design parameters as the design parameters for the actual wall construction.

[0071] Through the above methods, users can flexibly adjust the design parameters and use the prediction function of the intelligent analysis module to quickly find a wall design solution that meets actual needs and is economically reasonable.

[0072] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0073] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multifunctional assembled heat-insulating wall system, characterized in that: The system comprises: A parameter input module, used for receiving wall design parameters input by a user; Intelligent analysis module, used to predict the thermal insulation performance index, expected service life and construction cost of the wall under different environmental conditions through machine learning algorithm according to the wall design parameters obtained by the parameter input module; The data storage module is used to store the design parameters input by the user and their corresponding prediction results output by the intelligent analysis module.

2. A multifunctional assembled heat-insulating wall system according to claim 1, characterized in that: The wall design parameters include the size of the wall, the choice of insulation materials, the design method of the structural frame, the connection method of the connectors and the climate data of the area where the wall is located; the climate data includes the average, maximum and minimum values ​​of the temperature, humidity, solar radiation intensity and wind speed recorded in the history of the area.

3. The multifunctional assembled heat-insulating wall system according to claim 1, characterized in that: The intelligent analysis module uses a machine learning algorithm to respectively construct a thermal insulation performance index prediction model, a service life prediction model, and a construction cost prediction model.

4. A multifunctional assembled heat-insulating wall system according to claim 3, characterized in that: The machine learning algorithms used by the intelligent analysis module to construct the three prediction models are all linear regression algorithms.

5. A multifunctional assembled heat-insulating wall system according to claim 4, characterized in that: The steps of constructing three prediction models by the intelligent analysis module include: Step 1: Extract historical wall design parameters and their corresponding actual thermal insulation performance indicators, service life and construction cost data from the data storage module; Step 2: Clean the data, including removing outliers and missing values; and standardize the cleaned data; Step 3: From the data processed in step 2, select features related to thermal insulation performance index, service life and construction cost as input variables of the model to form a feature data set; further divide the feature data set into a training data set and a validation data set according to a certain ratio; Step 4: Based on the feature data set, the thermal insulation performance index prediction model, service life prediction model and construction cost prediction model are constructed using the linear regression algorithm respectively; the parameters of the model are obtained by fitting the linear relationship between the input variables and the output variables in the historical data; Step 5: Use the training data set to train the constructed model, and continuously adjust the model parameters through iterative optimization algorithms to minimize the error between the model's prediction results and the actual data; Step 6: Use the validation data set to validate the trained model and evaluate the model's predictive performance; if the model's predictive performance meets expectations, the training ends; otherwise, return to step 3 to rebuild the model or adjust feature selection.

6. A multifunctional assembled heat-insulating wall system according to claim 5, characterized in that: The formula for the linear regression algorithm is: y=β0+β1x1+β2x2+...+β n x n +∈ Among them, y represents the predicted value, x1, x2, ..., x n represents the wall design parameters that affect the prediction results input by the user, including the wall size, the choice of insulation materials, the design of the structural frame, the connection method of the connectors, and the climate data of the area where the wall is located; β1, β2, ..., β n is the parameter of the model, obtained through model training; β0 is the intercept term, which represents the expected value of y when all control items x are 0; ∈ is the error term, which represents the difference between the actual value and the model predicted value.

7. The multifunctional assembled heat-insulating wall system according to claim 5, characterized in that: When initializing the model parameters, the intelligent analysis module is used to initialize the model parameters for each feature x in the linear regression model. i The corresponding parameter β i Assign an initial value, which is set to a random number close to 0, and also assign an initial value to the intercept term β0; These initial parameter values ​​will serve as the starting point for model training and will be continuously optimized and adjusted through subsequent training processes until the goal of minimizing the gap between the predicted values ​​and the actual values ​​is achieved.

8. The multifunctional assembled heat-insulating wall system according to claim 5, characterized in that: The intelligent analysis module uses the data in the training data set to continuously iterate and update the parameters of the linear regression model through the gradient descent algorithm. In each iteration, the value of the model parameter is adjusted according to the gradient information of the loss function to the model parameter until the loss function converges or reaches a preset number of iterations. The calculation formula of the gradient descent algorithm is: Among them, θ represents the model parameters, including all weights and biases that the model needs to learn; ω represents the learning rate, which is used to control the step size of parameter update; represents the gradient of the loss function J(θ) with respect to the parameter θ, is a vector pointing to the direction where the loss function grows fastest; := represents the assignment operation, that is, updating the value of the parameter θ.

9. A multifunctional assembled heat-insulating wall system according to claim 8, characterized in that: The intelligent analysis module uses the mean square error MSE algorithm to evaluate the performance of the prediction model, and its algorithm formula is: Where n is the number of data points, Y pred,i is the predicted value of the model, Y actual,i is the actual value; the prediction accuracy of the model is evaluated according to the MSE value. The smaller the MSE value, the higher the prediction accuracy of the model.

10. An assembly method for the multifunctional assembled heat-insulating wall system according to any one of claims 1 to 9, characterized in that: The method comprises: a user dynamically adjusts input design parameters through a parameter input module to obtain different prediction results, and judges whether the prediction results meet the requirements by comparing with the actual expected thermal insulation performance index, expected service life and construction cost. When the prediction results meet the requirements, the design parameters are determined as the design parameters for actual wall construction.

Images