Construction monitoring method for freeze method based on physical simulation and memory network

Abstract

The application discloses a frozen method construction monitoring method based on physical simulation and a memory network, and comprises the following steps: a comsol large physical finite element model of the frozen method under different construction conditions is constructed to simulate and calculate to obtain the temperature distribution of a construction area, the frozen wall thickness, the soil frost heaving displacement and the soil stress distribution of the frozen method construction process under different environmental factor conditions at different time points; the temperature and the soil frost heaving displacement of the construction area are taken as input features of a machine learning model, and the soil stress and the frozen wall thickness of the construction area are taken as output labels of the machine learning model; soil parameters of a frozen method construction area to be monitored are acquired in real time; the soil stress and the frozen wall thickness of the frozen method construction area are predicted in real time based on the soil parameters and through the trained machine learning model; and when the soil stress and the frozen wall thickness exceed a warning threshold range, a warning notice is generated. The application solves the problem that the existing frozen method construction monitoring method has low efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building construction, and particularly relates to a frozen method construction monitoring method based on physical simulation and memory network. BACKGROUND

[0002] In the field of civil engineering, the frozen method construction technology is valued for its effective support in underground engineering. This technology forms a frozen soil wall in the soil through freezing action, which serves as a temporary support structure for excavation operations. Although the frozen method construction technology has achieved certain success in practice, there are still deficiencies in monitoring and control during the construction process. Traditional monitoring methods mainly rely on manual measurement and periodic inspection, which not only are inefficient, but also cannot achieve continuous real-time monitoring of the construction process, resulting in the inability to timely discover and respond to potential problems during the construction process. In addition, these traditional methods have limitations in data collection and analysis, making it difficult to fully utilize the large amount of data generated during the construction process, especially time series data, which limits the ability of the model to predict the stability of the construction.

[0003] With the development of computer simulation technology, physical simulation methods have been introduced into the monitoring of frozen method construction to simulate key parameters such as ground frost heaving changes, frozen wall thickness, and frozen soil expansion. However, these simulation models are often based on theoretical assumptions and lack the combination of actual construction data, resulting in deviations between simulation results and actual conditions. In addition, although machine learning technology has shown great potential in construction safety monitoring, existing machine learning models are mostly trained for specific construction conditions and lack the ability to generalize under varying geological conditions and environmental factors. These models can usually only handle a single type of data and fail to fully consider the interactive effects of multiple factors during the construction process, resulting in limited effectiveness in actual applications.

[0004] The information disclosed in this BACKGROUND section is only intended to increase an understanding of the general context in which the present application can be practiced. It is not intended to be nor should it be taken as admission that the information disclosed in this BACKGROUND section constitutes prior art to the present application. SUMMARY

[0005] To overcome the defects of the prior art, a frozen method construction monitoring method based on physical simulation and memory network is provided to solve the problem of low efficiency of existing frozen method construction monitoring methods.

[0006] To achieve the above-mentioned purpose, a frozen method construction monitoring method based on physical simulation and memory network is provided, comprising the following steps:

[0007] Constructing a large physical finite element model of comsol under different construction conditions of the frozen method;

[0008] The temperature distribution, the frozen wall thickness, the soil frost heaving displacement and the soil stress distribution of the construction area in the construction process under different environmental factors at different time points are obtained through simulation calculation of the comsol large physical finite element model;

[0009] The long short-term memory network LSTM sequence model is used as the machine learning model, the temperature and the soil frost heaving displacement of the construction area are used as the input features of the machine learning model, and the soil stress and the frozen wall thickness of the construction area are used as the output labels of the machine learning model, so as to train the machine learning model.

[0010] The soil parameters of the freezing construction area to be monitored are acquired in real time.

[0011] Based on the soil parameters, the soil stress and the frozen wall thickness of the freezing construction area are predicted in real time through the trained machine learning model.

[0012] When the soil stress and the frozen wall thickness of the freezing construction area predicted in real time exceed the warning threshold range, a warning notification is generated.

[0013] Further, the soil parameters of the freezing construction area to be monitored and the soil stress and the frozen wall thickness of the freezing construction area predicted in real time are further displayed in real time through a Web page.

[0014] Further, after the warning notification is generated, the warning notification is notified to the monitoring personnel through the modes of short message, email and telephone.

[0015] The freezing construction monitoring method based on physical simulation and memory network has the advantages that the whole process of freezing construction under specific geological conditions is simulated by using a physical simulation method as training data of a machine learning model; a machine learning model is established, a machine learning model capable of predicting soil stress and frozen wall thickness according to input ground frost heaving displacement and temperature conditions is established by using a deep learning method; and a real-time warning platform is established, and a platform capable of real-time monitoring and warning is established by using the machine learning model, thereby serving as a tool for management and maintenance of construction stability.

[0016] The freezing construction monitoring method based on physical simulation and memory network realizes rapid and accurate evaluation of freezing construction stability by combining the accuracy of physical simulation and the efficiency of machine learning, and provides a scientific basis for long-term maintenance and management of construction stability. The freezing construction monitoring method based on physical simulation and memory network not only improves the real-time performance and accuracy of construction monitoring, but also enhances the generalization ability of the model, can adapt to changing construction environments, and ensures the safety and efficiency of the construction process. BRIEF DESCRIPTION OF DRAWINGS

[0017] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments thereof, when read in conjunction with the accompanying drawings:

[0018] Figure 1 The layout of the monitoring points of the frozen method construction of the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0019] The application will be further described below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related application, and not to limit the application. In addition, it should be noted that only the parts related to the application are shown in the drawings for ease of description.

[0020] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0021] The application provides a frozen method construction monitoring method based on physical simulation and memory network, comprising the following steps:

[0022] S1, constructing a comsol large physical finite element model of the frozen method under different construction conditions.

[0023] Soil and soil thermal parameters under different geological conditions are collected, and parameters reflecting soil shear strength characteristics, hydraulic characteristics and the like in typical soil are obtained through experimental data and literature synthesis. Subsequently, necessary parameter settings will be provided for constructing the comsol large physical finite element model to ensure the accuracy of numerical simulation.

[0024] The comsol large physical finite element model under different construction conditions is constructed. The different construction conditions specifically include:

[0025] Geological conditions, such as soil type, density, water content, permeability and the like;

[0026] Environmental factors, such as temperature, humidity, wind speed and other climate conditions;

[0027] Material properties, such as the thermal physical properties of the freezing pipe material and the coolant;

[0028] Construction progress, such as the stages of the initial, middle and late freezing periods.

[0029] Considering different construction time conditions, the stress conditions of the frozen wall and the surrounding soil of the finite element model changing with time can be calculated, and the initial conditions required for setting the finite element model are provided under specific construction background.

[0030] A physical model under different construction conditions is constructed, considering different construction parameters, and a geometric model and initial conditions of the entire construction area are constructed. When constructing the comsol large-scale physical finite element model, the entire construction area is comprehensively considered based on the constructed geometric model to ensure that the model can accurately simulate the actual construction conditions and process. Through comprehensive analysis, accurate training data is provided for subsequent machine learning models, thereby realizing effective monitoring and early warning of the freezing method construction process.

[0031] S2, the temperature distribution, frozen wall thickness, soil frost heaving displacement and soil stress distribution of the construction area in the freezing method construction process under different environmental factor conditions at different time points are obtained by simulation calculation of the comsol large-scale physical finite element model.

[0032] The comsol large-scale physical finite element model can be used to simulate the freezing method construction process under different environmental factors. The influence of different environmental factors on the construction time can be considered by calculating the freezing wall closure time, and the soil frost heaving displacement and frozen soil temperature during the construction process can be calculated by the comsol large-scale physical finite element model.

[0033] The comsol large-scale physical finite element model outputs parameters such as temperature distribution, ground frost heaving displacement and soil stress distribution during construction. According to the simulation results, the temperature distribution, frozen wall, ground frost heaving displacement and soil stress distribution of the construction area at different time points are calculated. This process is the establishment and calculation of the physical model.

[0034] S3, a long short-term memory network LSTM sequence model is used as a machine learning model, and the temperature and soil frost heaving displacement of the construction area are used as input features of the machine learning model, and the soil stress and frozen wall thickness of the construction area are used as output labels of the machine learning model. Train the machine learning model.

[0035] Specifically, step S3 includes:

[0036] Step S31: determination of input features, selecting temperature, ground frost heaving displacement and the like during construction as input features.

[0037] Step S32: definition of output label, taking the soil stress and frozen wall thickness parameters obtained in numerical simulation as the output label, i.e. the target prediction value of the model.

[0038] Step S33: model selection, using a long short-term memory network LSTM sequence model as a machine learning model to consider the influence of time series information on construction stability evaluation.

[0039] A long short-term memory network (LSTM) is used as a machine learning model to consider the influence of time series information in stability evaluation. The long short-term memory network (LSTM) is a variant of recurrent neural network (RNN) in deep learning. It is more superior in modeling time series data. The long short-term memory network (LSTM) can effectively process data at different time points in evaluation. The long short-term memory network (LSTM) sequence model is used as a machine learning model to consider the influence of time series information in construction stability evaluation.

[0040] Step S34: Model training, using the data set generated by numerical simulation to train the model to adjust the model parameters to adapt to the actual construction conditions.

[0041] Step S35: Model verification and optimization, verify the model through the verification set, adjust and optimize the structure and parameters of the model to improve its generalization ability and prediction accuracy.

[0042] S4, real-time acquisition of soil parameters of the freezing construction area to be monitored.

[0043] Referring to Figure 1 , by setting monitoring points (ground monitoring points, stress monitoring points and pipeline monitoring points, etc.) in the freezing construction area to be monitored for data access and integration, real-time monitoring data is obtained from the monitoring points.

[0044] S5, based on the soil parameters, real-time prediction of the soil stress and frozen wall thickness of the freezing construction area by the trained machine learning model.

[0045] Real-time prediction by machine learning model, using the trained long short-term memory network (LSTM) time series model to make real-time prediction of construction stability based on real-time data.

[0046] When the real-time predicted soil stress and frozen wall thickness of the freezing construction area exceed the warning threshold range, a warning notice is generated.

[0047] According to the warning rules and threshold settings, based on the risk rules and warning thresholds of the prediction results, by comparing the real-time data with the set thresholds, it is determined whether to trigger the risk to generate a warning notice.

[0048] By continuously monitoring the changes of construction parameters and updating the prediction results in real time, a notification system is constructed. Once potential risks of construction stability are monitored, the notification system sends a warning notice to take timely measures

[0049] The soil parameters of the freezing construction area to be monitored and the real-time predicted soil stress and frozen wall thickness of the freezing construction area are displayed in real time through the Web page.

[0050] In the embodiment, by constructing a visual interface to display real-time data and reports, the real-time monitoring data and model prediction results are intuitively presented, so that relevant personnel can clearly understand the construction status, generate periodic reports, record historical data of construction stability, early warning conditions, and use them for post-analysis and improvement of system performance.

[0051] The freezing construction monitoring method based on physical simulation and memory network can realize accurate evaluation and early warning of regional stability, improve the safety and sustainability of the project, and is superior to the traditional physical simulation and machine learning methods.

[0052] The above description is only the preferred embodiment of the application and the explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application involved in the application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features disclosed in the application (but not limited to) having similar functions to form technical solutions.

Claims

1. A construction monitoring method of a freezing method based on physical simulation and a memory network, characterized by, The method comprises the following steps: constructing a comsol large-scale physical finite element model of the freezing method under different construction conditions; obtaining the temperature distribution, the frozen wall thickness, the soil frost heaving displacement and the soil stress distribution of the construction area in the freezing method construction process at different time points and under different environmental factor conditions through simulation calculation of the comsol large-scale physical finite element model; using a long short-term memory network LSTM sequence model as a machine learning model, taking the temperature and the soil frost heaving displacement of the construction area as input features of the machine learning model, taking the soil stress and the frozen wall thickness of the construction area as output labels of the machine learning model, and training the machine learning model; real-time acquisition of soil parameters of a freezing method construction area to be monitored; based on the soil parameters, real-time prediction of the soil stress and the frozen wall thickness of the freezing method construction area by the trained machine learning model; when the real-time predicted soil stress and frozen wall thickness of the freezing method construction area exceed a warning threshold range, generating a warning notification.

2. The physical simulation and memory network based monitoring method for freeze construction according to claim 1, wherein, The method further comprises real-time display of the soil parameters of the freezing method construction area to be monitored and the real-time predicted soil stress and frozen wall thickness of the freezing method construction area through a Web webpage.

3. The physical simulation and memory network based monitoring method for freeze construction according to claim 1, wherein, After the warning notification is generated, the warning notification is notified to monitoring personnel through short message, email and telephone modes.

Images