Method for controlling stability of assembly type embedded pipeline integrated partition board

By setting monitoring points in prefabricated buildings and building a time domain convolutional network model, the stability of partition wall panels and embedded pipelines is solved in real time, and the stability of integrated partition wall panels in prefabricated buildings is solved. Control problems, intelligent early warning and active control are achieved, and construction safety and quality are improved.

CN118933363APending Publication Date: 2024-11-12SHENZHEN SPECIAL ECONOMIC ZONE CONSTR ENG GRP SHENGTENG TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410992001.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In prefabricated buildings, the stability of integrated partition panels in embedded pipelines is difficult to effectively control during prefabrication, transportation and assembly, resulting in construction efficiency and quality problems.

Method used

Using monitoring point settings, installation and data analysis methods, by building a time domain convolution network model, the stability changes of partition panels and embedded pipelines are monitored and predicted in real time, and early warnings are issued according to early warning standards to achieve active control.

Benefits of technology

It realizes intelligent monitoring and prediction of the stability of integrated partition panels of prefabricated pre-embedded pipelines, improves construction safety and quality control, and is suitable for the field of equipment construction in construction projects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118933363A_ABST
    Figure CN118933363A_ABST
Patent Text Reader

Abstract

The invention provides a method for controlling the stability of an assembly type embedded pipeline integrated partition board, which is suitable for the field of constructional engineering equipment type construction and comprises the steps of setting monitoring point positions, installing the monitoring point positions, acquiring monitoring data, analyzing the monitoring data and realizing a control purpose. The stability control method for the assembly type embedded pipeline integrated partition wall board has the advantages of being high in safety performance and high in comprehensiveness and can be widely applied to the field of constructional engineering equipment type construction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a method for controlling the stability of an assembled pre-buried pipeline integrated partition wall plate, which is applicable to the field of equipment-type construction of building engineering. Background Art

[0002] In the field of construction engineering, prefabricated buildings have received more and more attention and applications due to their advantages such as fast construction speed, controllable quality, energy saving and environmental protection. The core of prefabricated buildings lies in the design and manufacture of prefabricated components. After these components are produced in the factory, they are transported to the construction site for rapid assembly. The pre-buried pipeline integrated partition board is an important part of prefabricated buildings. It not only bears the function of separating spaces, but also may integrate pipeline systems such as electricity, communications, water supply and drainage, thereby realizing the diversification and intelligence of the internal functions of the building.

[0003] However, with the development and application of prefabricated building technology, the stability problem of pre-buried pipeline integrated partition boards has gradually emerged. In traditional construction methods, the stability of partition boards mainly depends on the accuracy and quality control of on-site construction, which needs to be ensured through the design and manufacture of prefabricated components in prefabricated construction. The existence of pre-buried pipelines increases the complexity of partition boards. How to ensure the stability of partition boards during prefabrication, transportation, assembly and use has become a technical problem that needs to be solved in the field of prefabricated buildings.

[0004] In order to overcome the shortcomings of the existing technology and improve the construction efficiency and building quality of prefabricated buildings, the present invention proposes a method for controlling the stability of prefabricated pre-buried pipeline integrated partition boards. The method effectively controls the stability of pre-buried pipeline integrated partition boards through innovative design and construction technology to meet the needs of the field of equipment-based construction of construction projects, and has important practical application value and market prospects. Summary of the invention

[0005] The purpose of the present invention is to ensure the stability of the assembled pre-buried pipeline integrated partition wall board during use, to effectively sense the dangerous state of the assembled pre-buried pipeline integrated partition wall board during use, and to propose a stability control method for the assembled pre-buried pipeline integrated partition wall board.

[0006] The purpose of the present invention can be achieved by adopting the following technical solutions:

[0007] A method for controlling the stability of an assembled pre-buried pipeline integrated partition wall panel, characterized in that the method comprises the following steps:

[0008] S101, setting of monitoring points;

[0009] The setting of the monitoring points includes setting monitoring points according to the characteristics of the assembled pre-buried pipeline integrated partition wall panel, and the monitoring points are divided into two categories, namely, partition wall panel stability monitoring points and pre-buried pipeline stability monitoring points;

[0010] S102, installation of monitoring points;

[0011] The installation of the monitoring points includes installing the monitoring points during the production process of the assembled pre-buried pipeline integrated partition board, and the fixing method of the monitoring points is a bracket fixing method;

[0012] S103, acquisition of monitoring data;

[0013] The acquisition of the monitoring data includes the monitoring point transmitting the monitoring data to the data processing system by a wireless method at a fixed time interval t, the data processing system including a data receiving module, a data analysis module and a display screen module, the data receiving module is used to receive the monitoring data transmitted by the monitoring point, the data analysis module is used to analyze the monitoring data, and the display screen module is used to display the monitoring data and the analysis results;

[0014] S104, analysis of monitoring data;

[0015] The analysis of the monitoring data includes analyzing the monitoring data to obtain a predicted value of the monitoring data. The steps of the monitoring data analysis method are as follows:

[0016] a) Organize the monitoring data, organize the monitoring data according to the monitoring points and monitoring time,

[0017] b) Preliminary processing of monitoring data, including checking and filling missing values ​​of the monitoring data, wherein the missing value filling method adopts K-nearest neighbor filling method,

[0018] c) data preprocessing, wherein the monitoring data is divided into a training set and a test set, and a sliding window method is used to generate input queues and target value pairs for the training set and the test set.

[0019] d) constructing a time domain convolutional network model, setting the input sequence length of the input layer of the time domain convolutional network model to the window length of the sliding window method, setting the activation function of the time domain convolutional network model to adopt a self-regularized non-monotonic neural activation function, and the expression of the self-regularized non-monotonic neural activation function is formula (1),

[0020] f(x)=x*tanh(ln(1+e x )) (1)

[0021] e) compiling a time domain convolutional network model, wherein the model compilation includes defining a loss function of the time domain convolutional network model, wherein the loss function uses a mean square error or a mean square logarithmic error according to the monitoring data. When the monitoring data is obtained from the partition board stability monitoring point, the mean square error is used. When the monitoring data is obtained from the embedded pipeline stability monitoring point, the mean square logarithmic error MSLE is used. The mean square logarithmic error MSLE is expressed as formula (2).

[0022]

[0023] In the formula, ε is a small positive number with a value of 1×10 -8 ,

[0024] f) time domain convolutional network model training, wherein the time domain convolutional network model training includes using a training set to carry out model training on the time domain convolutional network model, and the time domain convolutional network model training includes defining a batch size, a number of rounds, and a callback function for training,

[0025] g) evaluating a time domain convolutional network model, wherein the time domain convolutional network model evaluation includes evaluating the prediction performance of the time domain convolutional network model using the test set, making adjustments according to the prediction performance, and finally obtaining an adjusted time domain convolutional network model.

[0026] h) Deploy the model and apply it.

[0027] S105, realization of control objectives;

[0028] The realization of the control purpose includes comparing the predicted value of the monitoring data obtained with the established early warning standard. If the early warning standard is reached, an early warning is issued to achieve the control purpose.

[0029] Furthermore, in the above S101, the stability monitoring points of the partition wall panels are arranged along the edges of the wall panels, and the stability monitoring points of the pre-buried pipelines are arranged on the pre-buried pipelines.

[0030] Furthermore, in the above S104, the method for controlling the stability of an assembled pre-buried pipeline integrated partition wall panel according to claim 1 is characterized in that, in the analysis of the monitoring data, the calculation distance of the K nearest neighbor filling method is calculated using Euclidean distance.

[0031] The beneficial effects of the present invention are:

[0032] The beneficial effects of the present invention are as follows: by constructing a time domain convolutional network model and conducting in-depth analysis and prediction of the monitoring data, the stability change trend of partition boards and pre-buried pipelines can be intelligently predicted, and an early warning can be issued according to the early warning standards to achieve active control; according to the characteristics of the data obtained at different monitoring points, the mean square error or the mean square logarithmic error is selected as the loss function, so that the model training is more in line with the actual monitoring needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 : Flow chart of a method for controlling stability of an assembled pre-buried pipeline integrated partition board of the present invention. DETAILED DESCRIPTION

[0034] The specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings; it should be understood that the specific embodiments given here are only used to illustrate and explain the present invention and cannot be used to limit the present invention.

[0035] The following is a specific embodiment of a method for controlling the stability of an assembled pre-buried pipeline integrated partition wall panel.

[0036] like Figure 1 Shown is a flow chart of a method for controlling stability of an assembled pre-buried pipeline integrated partition wall panel according to the present invention.

[0037] A method for controlling the stability of an assembled pre-buried pipeline integrated partition wall panel, characterized in that the method comprises the following steps:

[0038] S101, setting of monitoring points;

[0039] The setting of the monitoring points includes setting monitoring points according to the characteristics of the assembled pre-buried pipeline integrated partition wall panel, and the monitoring points are divided into two categories, namely, partition wall panel stability monitoring points and pre-buried pipeline stability monitoring points;

[0040] Furthermore, the stability monitoring points of the partition wall panels are arranged along the edges of the wall panels, and the stability monitoring points of the pre-buried pipelines are arranged on the pre-buried pipelines.

[0041] S102, installation of monitoring points;

[0042] The installation of the monitoring points includes installing the monitoring points during the production process of the assembled pre-buried pipeline integrated partition board, and the fixing method of the monitoring points is a bracket fixing method;

[0043] S103, acquisition of monitoring data;

[0044] The acquisition of the monitoring data includes the monitoring point transmitting the monitoring data to the data processing system by a wireless method at a fixed time interval t, the data processing system including a data receiving module, a data analysis module and a display screen module, the data receiving module is used to receive the monitoring data transmitted by the monitoring point, the data analysis module is used to analyze the monitoring data, and the display screen module is used to display the monitoring data and the analysis results;

[0045] S104, analysis of monitoring data;

[0046] The analysis of the monitoring data includes analyzing the monitoring data to obtain a predicted value of the monitoring data. The steps of the monitoring data analysis method are as follows:

[0047] a) Organize the monitoring data, organize the monitoring data according to the monitoring points and monitoring time,

[0048] b) Preliminary processing of monitoring data, including checking and filling missing values ​​of the monitoring data, wherein the missing value filling method adopts K-nearest neighbor filling method,

[0049] c) Data preprocessing, wherein the monitoring data is divided into a training set and a test set, and a sliding window method is used to generate input queues and target value pairs for the training set and the test set. Furthermore, the window size of the sliding window method is set to 25.

[0050] d) constructing a time domain convolutional network model, setting the input sequence length of the input layer of the time domain convolutional network model to the window length of the sliding window method, setting the activation function of the time domain convolutional network model to adopt a self-regularized non-monotonic neural activation function, and the expression of the self-regularized non-monotonic neural activation function is formula (1),

[0051] f(x)=x*tanh(ln(1+e x )) (1)

[0052] e) compiling a time domain convolutional network model, wherein the model compilation includes defining a loss function of the time domain convolutional network model, wherein the loss function uses a mean square error or a mean square logarithmic error according to the monitoring data. When the monitoring data is obtained from the partition board stability monitoring point, the mean square error is used. When the monitoring data is obtained from the embedded pipeline stability monitoring point, the mean square logarithmic error MSLE is used. The mean square logarithmic error MSLE is expressed as formula (2).

[0053]

[0054] In the formula, ε is a small positive number with a value of 1×10-8 ,Furthermore, the temporal convolutional network model compilation also includes setting the number of filters to 64, setting the filter size to 3, and setting the expansion coefficient to [1,2,4,8],

[0055] f) time domain convolutional network model training, wherein the time domain convolutional network model training includes using a training set to carry out model training on the time domain convolutional network model, and the time domain convolutional network model training includes defining a training batch size, a number of rounds, and a callback function, and further the training batch size is set to 32, and the number of training rounds is set to 50,

[0056] g) evaluating a time domain convolutional network model, wherein the time domain convolutional network model evaluation includes evaluating the prediction performance of the time domain convolutional network model using the test set, making adjustments according to the prediction performance, and finally obtaining an adjusted time domain convolutional network model.

[0057] h) Deploy the model and apply it.

[0058] Furthermore, in the above S104, the method for controlling the stability of an assembled pre-buried pipeline integrated partition wall panel according to claim 1 is characterized in that, in the analysis of the monitoring data, the calculation distance of the K nearest neighbor filling method is calculated using Euclidean distance.

[0059] S105, realization of control objectives;

[0060] The realization of the control purpose includes comparing the predicted value of the monitoring data obtained with the established early warning standard. If the early warning standard is reached, an early warning is issued to achieve the control purpose.

[0061] In the above embodiments, the present invention discloses a method for controlling the stability of an integrated partition wall panel for prefabricated pre-buried pipelines, including the setting of monitoring points, the installation of monitoring points, the acquisition of monitoring data, the analysis of monitoring data and the realization of control purposes; the method for controlling the stability of an integrated partition wall panel for prefabricated pre-buried pipelines proposed in the present invention has the advantages of high safety performance and strong comprehensiveness, and can be widely used in the field of equipment-type construction of construction projects.

[0062] The above description is a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for controlling the stability of an assembled pre-buried pipeline integrated partition wall, characterized in that: The steps of the stability control method of the assembled pre-buried pipeline integrated partition wall panel are as follows: 1) Setting of monitoring points; 2) Installation of monitoring points; 3) Acquisition of monitoring data; 4) Analysis of monitoring data; 5) Achievement of control objectives; The setting of the monitoring points includes setting monitoring points according to the characteristics of the assembled pre-buried pipeline integrated partition wall panel, and the monitoring points are divided into two categories, namely, partition wall panel stability monitoring points and pre-buried pipeline stability monitoring points; The installation of the monitoring points includes installing the monitoring points during the production process of the assembled pre-buried pipeline integrated partition board, and the fixing method of the monitoring points is a bracket fixing method; The acquisition of the monitoring data includes the monitoring point transmitting the monitoring data to the data processing system by a wireless method at a fixed time interval t, the data processing system including a data receiving module, a data analysis module and a display screen module, the data receiving module is used to receive the monitoring data transmitted by the monitoring point, the data analysis module is used to analyze the monitoring data, and the display screen module is used to display the monitoring data and the analysis results; The analysis of the monitoring data includes analyzing the monitoring data to obtain a predicted value of the monitoring data. The steps of the monitoring data analysis method are as follows: a) Organize the monitoring data, organize the monitoring data according to the monitoring points and monitoring time, b) Preliminary processing of monitoring data, including checking and filling missing values ​​of the monitoring data, wherein the missing value filling method adopts K-nearest neighbor filling method, c) data preprocessing, wherein the monitoring data is divided into a training set and a test set, and a sliding window method is used to generate input queues and target value pairs for the training set and the test set. d) constructing a time domain convolutional network model, setting the input sequence length of the input layer of the time domain convolutional network model to the window length of the sliding window method, setting the activation function of the time domain convolutional network model to adopt a self-regularized non-monotonic neural activation function, and the expression of the self-regularized non-monotonic neural activation function is formula (1), f(x)=x*tanh(ln(1+e x )) (1) e) compiling a time domain convolutional network model, wherein the model compilation includes defining a loss function of the time domain convolutional network model, wherein the loss function uses a mean square error or a mean square logarithmic error according to the monitoring data. When the monitoring data is obtained from the partition board stability monitoring point, the mean square error is used. When the monitoring data is obtained from the embedded pipeline stability monitoring point, the mean square logarithmic error MSLE is used. The mean square logarithmic error MSLE is expressed as formula (2). In the formula, ε is a small positive number with a value of 1×10 -8 , f) time domain convolutional network model training, wherein the time domain convolutional network model training includes using a training set to carry out model training on the time domain convolutional network model, and the time domain convolutional network model training includes defining a batch size, a number of rounds, and a callback function for training, g) evaluating a time domain convolutional network model, wherein the time domain convolutional network model evaluation includes evaluating the prediction performance of the time domain convolutional network model using the test set, making adjustments according to the prediction performance, and finally obtaining an adjusted time domain convolutional network model. h) Deploy the model and apply it. The realization of the control purpose includes comparing the predicted value of the monitoring data obtained with the established early warning standard. If the early warning standard is reached, an early warning is issued to achieve the control purpose.

2. The method for controlling the stability of an assembled pre-buried pipeline integrated partition wall according to claim 1, characterized in that: The stability monitoring points of the partition wall panels are arranged along the edges of the wall panels, and the stability monitoring points of the pre-buried pipelines are arranged on the pre-buried pipelines.

3. The method for controlling the stability of an assembled pre-buried pipeline integrated partition wall according to claim 1, characterized in that: In the analysis of the monitoring data, the calculation distance of the K nearest neighbor filling method is calculated using Euclidean distance.

Citation Information

Patent Citations

  • Curtain wall safety monitoring and early warning system

    CN108663003A

  • Access flow prediction method based on time convolutional neural network

    CN112468326A

  • Cigarette factory energy consumption prediction method, system, equipment and medium

    CN115936236A

  • Prefabricated building wall inclination monitoring and early warning method

    CN117928480A

  • Artificial intelligence image restoration method for enhancing sampling

    CN118351028A