An intelligent control method and control system for deep foundation pit deformation

Abstract

The present invention discloses an intelligent control method and control system for deep foundation pit deformation, including: obtaining the historical monitoring data of the foundation pit monitoring system, the surrounding environment monitoring system of the foundation pit, the precipitation - recharge system and the servo control system, establishing a deep learning model for foundation pit deformation based on the historical monitoring data, transmitting the collected real - time monitoring data into the deep learning model for foundation pit deformation for prediction to obtain a prediction result, judging whether the prediction result exceeds the warning value, if it exceeds, sending linkage control instructions to the servo control system and the precipitation - recharge system respectively, and adjusting the preset output results of the servo control system and the precipitation - recharge system according to the linkage control instructions respectively. The present invention realizes the intelligent linkage of the deformation control measures for deep and large foundation pits and the dynamic feedback of real - time monitoring data, saves a large amount of time for on - site personnel, improves the comprehensive coordination level and work efficiency of the project. Through effective risk analysis and control, the precise control of the deformation of deep and large foundation pits is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction engineering, and particularly relates to an intelligent control method and control system for deep foundation pit deformation. Background Art

[0002] With the rapid development of engineering construction, urban renewal faces an increasingly complex surrounding environment. Therefore, the stable control of deep foundation pit engineering has become increasingly complex. Usually, the foundation pit dewatering unit only collects water volume data, and the monitoring unit only collects deformation data. During the construction process of deep foundation pit engineering, the various systems cannot operate intelligently in a coordinated manner, and the contradictions in manual coordination control management are prominent. In order to cope with the construction in a complex and sensitive environment and respond to the strategic needs of the country and local governments for promoting the urban renewal of old communities, it is urgent to develop an intelligent linkage system to meet the precise control of foundation pit deformation in a complex environment. Summary of the Invention

[0003] In order to solve the above problems, the present invention provides an intelligent control method and control system for deep foundation pit deformation to solve the problem that during the construction process of traditional deep foundation pit engineering, manual coordination control is adopted among various systems, resulting in the inability to accurately control the deformation of the foundation pit in a complex environment.

[0004] To achieve the above object, the present invention provides an intelligent control method for deep foundation pit deformation, including:

[0005] Obtaining the historical monitoring data of the foundation pit monitoring system, the surrounding environment monitoring system of the foundation pit, the dewatering - recharge system, and the servo control system;

[0006] Establishing a deep learning model for foundation pit deformation based on the historical monitoring data;

[0007] Transmitting the collected real - time monitoring data to the deep learning model for foundation pit deformation for prediction to obtain a prediction result;

[0008] Judging whether the prediction result exceeds the warning value. If it exceeds, sending linkage control instructions to the servo control system and the dewatering - recharge system respectively;

[0009] Adjusting the preset output results of the servo control system and the dewatering - recharge system respectively according to the linkage control instructions.

[0010] According to a specific embodiment of the present invention, further including establishing a deep learning model for foundation pit deformation based on the historical monitoring data:

[0011] Establishing the relationship between the supporting force and deformation control, and the relationship between the dewatering - recharge water volume and deformation control according to the historical monitoring data;

[0012] A WaveNet model is established based on the relationship between the supporting force and deformation control, as well as the relationship between the precipitation - recharge water volume and deformation control.

[0013] The historical monitoring data is transmitted into the WaveNet model for training to obtain the foundation pit deformation training model.

[0014] The parameters of the foundation pit deformation training model are set, and the real - time monitoring data is transmitted into the foundation pit deformation training model for testing, where the parameters include the length of the predicted data and the time interval.

[0015] The foundation pit deformation training model is optimized according to the test results to obtain the foundation pit deformation deep - learning model.

[0016] According to a specific embodiment of the present invention, establishing the relationship between the supporting force and deformation control, as well as the relationship between the precipitation - recharge water volume and deformation control based on the historical monitoring data includes: substituting the historical monitoring data into the linear regression model for calculation to obtain the relationship between the supporting force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control. The relationship between the supporting force and deformation control, as well as the relationship between the precipitation - recharge water volume and deformation control are both negatively correlated.

[0017] According to a specific embodiment of the present invention, the historical monitoring data includes the historical monitoring data of the supporting structure deformation, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force. The real - time monitoring data includes the real - time monitoring data of the supporting structure deformation, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force.

[0018] According to a specific embodiment of the present invention, optimizing the foundation pit deformation training model according to the test results to obtain the foundation pit deformation deep - learning model includes: adjusting the learning rate and the number of iterations of the foundation pit deformation training model according to the test results to obtain the foundation pit deformation deep - learning model.

[0019] According to a specific embodiment of the present invention, judging whether the prediction result exceeds the warning value. If it exceeds, sending linkage control instructions to the servo control system and the precipitation - recharge system respectively includes:

[0020] Comparing the predicted values corresponding to each stage control node in the construction process with the warning value, judging whether the predicted value exceeds the warning value. If it exceeds, correcting and analyzing the servo control system and the precipitation - recharge system respectively, and sending linkage control instructions to the servo control system and the precipitation - recharge system according to the analysis results, where the predicted values include the predicted value of the supporting structure deformation, the predicted value of the deformation of the surrounding ground surface and buildings, the predicted value of the groundwater level, and the predicted value of the jack support axial force, and the warning values include the supporting structure deformation threshold, the surrounding ground surface settlement threshold, and the horizontal and vertical displacement thresholds of the surrounding buildings.

[0021] According to a specific embodiment of the present invention, the control node includes the groundwater level drawdown depth and the foundation pit excavation depth.

[0022] According to a specific embodiment of the present invention, respectively adjusting the preset output results of the servo control system and the precipitation - recharge system according to the linkage control instruction includes: respectively adjusting the prestress application threshold of the jack axial force of the servo control system and the pumping volume threshold of the precipitation - recharge system according to the linkage control instruction.

[0023] An intelligent control system for deep foundation pit deformation includes:

[0024] A data acquisition module, configured to collect historical monitoring data and real - time monitoring data of the foundation pit monitoring system, the foundation pit surrounding environment monitoring system, the precipitation - recharge system, and the servo control system;

[0025] A data prediction module, configured to establish a deep learning model for foundation pit deformation based on the historical monitoring data, and transmit the real - time monitoring data into the deep learning model for foundation pit deformation for prediction to obtain a prediction result;

[0026] An early warning module, configured to determine whether the prediction result exceeds the early warning value, and if it exceeds, send linkage control instructions to the servo control system and the precipitation - recharge system respectively;

[0027] A linkage control module, configured to respectively adjust the preset output results of the servo control system and the precipitation - recharge system according to the linkage control instructions;

[0028] A display module, configured to display the real - time monitoring data and the interaction information of each monitoring data.

[0029] According to a specific embodiment of the present invention, the historical monitoring data includes the historical monitoring data of the supporting structure deformation, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force, and the real - time monitoring data includes the real - time monitoring data of the supporting structure deformation, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force.

[0030] Compared with the prior art, a deep foundation pit deformation intelligent control method and control system provided by the present invention establish a deep learning theoretical model by establishing the relationship between the supporting force, the precipitation - recharge water volume and the deformation control, and use the deep learning model to predict the development trend of data, so as to realize the linkage of the foundation pit deformation monitoring data, the groundwater level data and the applied force of the servo support system. From the perspectives of the active control of the deformation support of the deep and large foundation pit, the automatic monitoring, the precipitation - recharge and the prestress application, the present application realizes the intelligent linkage of the deformation control measures of the deep and large foundation pit and the dynamic feedback of the real - time monitoring data, saves a large amount of coordination time for the on - site personnel, and improves the comprehensive coordination level of the project management department and the working efficiency of the command and dispatch. Through effective risk analysis and control, the intelligent linkage control of the deformation of the deep and large foundation pit is realized in the complex and sensitive urban renewal environment, the stability of the surrounding building environment is maintained, the environmental disturbance is reduced, and the deformation control of the deep and large foundation pit is made more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 FIG. is a flow chart of a deep foundation pit deformation intelligent control method provided by an embodiment of the present invention.

[0032] Figure 2 FIG. is a flow chart of a method for establishing a deep learning model for foundation pit deformation provided by an embodiment of the present invention.

[0033] Figure 3 FIG. is a schematic structural diagram of a deep foundation pit deformation intelligent control system provided by an embodiment of the present invention.

[0034] Reference Signs:

[0035] 01 - data acquisition module; 02 - data prediction module; 03 - warning module; 04 - linkage control module; 05 - display module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] In order to enable those skilled in the art to more clearly understand the concepts and ideas of the present invention, the present invention will be described in detail below with reference to specific embodiments. It should be understood that the embodiments given herein are only a part of all possible embodiments of the present invention. After reading the specification of the present application, those skilled in the art are capable of making improvements, modifications, or substitutions to some or all of the following embodiments, and these improvements, modifications, or substitutions are also included within the scope of protection required by the present invention.

[0037] In this text, terms such as "first", "second" and other similar words are not intended to imply any order, quantity or importance, but are merely used to distinguish different elements. In this text, terms such as "a", "an" and other similar words are not intended to mean that there is only one thing, but rather that the relevant description only refers to one of the things, and the thing may have one or more. In this text, terms such as "comprising", "including" and other similar words are intended to represent a logical relationship, rather than a spatial structural relationship. For example, "A includes B" is intended to mean that logically B belongs to A, rather than indicating that B is located inside A spatially. Additionally, the meanings of terms such as "comprising", "including" and other similar words should be regarded as open-ended, rather than closed. For example, "A includes B" is intended to mean that B belongs to A, but B does not necessarily constitute the whole of A, and A may also include other elements such as C, D, E, etc.

[0038] In this text, terms such as "embodiment", "the present embodiment", "an embodiment", "one embodiment" do not mean that the relevant description only applies to a specific embodiment, but rather that these descriptions may also apply to one or more other embodiments. Those skilled in the art should understand that in this text, any description made for a certain embodiment can be substituted, combined, or otherwise combined with the relevant descriptions in one or more other embodiments, and the new embodiments generated by substitution, combination, or other means are easily conceivable by those skilled in the art and fall within the protection scope of the present invention.

[0039] Embodiment 1

[0040] Additional aspects and advantages of the embodiments of the present invention will be given in part in the following description, will become apparent in part from the following description, or will be understood through the practice of the embodiments of the present invention. In combination with Figure 1 and Figure 2 , an embodiment of the present invention provides an intelligent control method for deep foundation pit deformation, including:

[0041] S1: Obtain the historical monitoring data of the foundation pit monitoring system, the surrounding environment monitoring system of the foundation pit, the precipitation - recharge system and the servo control system, where the historical monitoring data includes the historical monitoring data of the deformation of the supporting structure, the deformation of the ground surface and buildings around the foundation pit, the underground water level, and the axial force of the jack support.

[0042] The embodiment of the present invention respectively collects the historical monitoring data of the deformation of the supporting structure of the foundation pit monitoring system, the historical monitoring data of the deformation of the ground surface and surrounding buildings around the foundation pit of the surrounding environment monitoring system of the foundation pit, the historical monitoring data of the axial force of the jack of the servo control system, and the historical monitoring data of the underground water level of the precipitation - recharge system, and stores each of the collected historical monitoring data in a database for training the deep learning model of foundation pit deformation.

[0043] S2: Establish a deep learning model for foundation pit deformation based on historical monitoring data, which further includes:

[0044] S21: Establish the relationship between the supporting force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control according to the historical monitoring data.

[0045] In the embodiment of the present invention, by substituting the historical monitoring data into the linear regression model for calculation and analysis, the relationship between the supporting force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control can be obtained. Through analysis, it can be known that the deformation of the foundation pit can be controlled by applying the supporting force. The greater the applied supporting force, the smaller the deformation of the foundation pit. Therefore, there is an "inverse correlation" relationship between the supporting force and the foundation pit deformation. The settlement of the ground surface and the deformation of the foundation pit can be effectively controlled by the precipitation - recharge water volume. The greater the recharge water volume, the smaller the ground surface settlement. Therefore, there is an "inverse correlation" relationship between the recharge water volume and the ground surface settlement. Thus, both the relationship between the supporting force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control are negatively correlated.

[0046] S22: Establish a WaveNet model based on the relationship between the supporting force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control.

[0047] S23: Transmit the historical monitoring data to the WaveNet model for training to obtain a foundation pit deformation training model.

[0048] S24: Set the parameters of the foundation pit deformation training model, and transmit the real - time monitoring data to the foundation pit deformation training model for testing, where the parameters include the length of the predicted data and the time interval.

[0049] S25: Optimize the foundation pit deformation training model according to the test results to obtain a deep learning model for foundation pit deformation.

[0050] The WaveNet model is a time series model, and the model establishment process is as follows: First, train the model by importing the historical monitoring data in the database; Second, set the model parameters, that is, set the length and time interval of the predicted data; Third, conduct data prediction; Third, optimize the model, that is, the learning rate and the number of iterations; Finally, output the predicted data. In the embodiment of the present invention, according to the above training steps, a WaveNet model is first established based on the relationship between the support force and deformation control, and the relationship between the precipitation-recharge water volume and deformation control. Then, the collected historical monitoring data of the support structure deformation, the historical monitoring data of the surface and building deformation around the foundation pit, the historical monitoring data of the groundwater level, and the historical monitoring data of the jack support axial force are imported into the WaveNet model for training. Then, set the model parameters, that is, set the length and time interval of the predicted data of the model. Then, import the real-time monitoring data into the WaveNet model with the set parameters for testing, and adjust the learning rate and the number of iterations of the foundation pit deformation training model according to the test results. Finally, obtain the deep learning model of the foundation pit deformation.

[0051] S3: Transmit the collected real-time monitoring data to the deep learning model of the foundation pit deformation for prediction to obtain a prediction result, where the real-time monitoring data includes the real-time monitoring data of the support structure deformation, the surface and building deformation around the foundation pit, the groundwater level, and the jack support axial force.

[0052] In the embodiment of the present invention, by importing the real-time monitoring data of the support structure deformation, the surface and building deformation around the foundation pit, the groundwater level, and the jack support axial force into the deep learning model of the foundation pit deformation for prediction, the prediction results of each real-time monitoring data, that is, the predicted values, are obtained, including the predicted value of the support structure deformation, the predicted value of the surface and building deformation around, the predicted value of the groundwater level, and the predicted value of the jack support axial force. Thus, the relationship between each monitoring data can be judged. When one type of data changes, the control means can be analyzed. For example, when the ground settlement displacement increases, according to this model, it can be obtained how much axial force should be applied and how much water should be recharged to effectively reduce the surface settlement displacement.

[0053] S4: Judge whether the prediction result exceeds the warning value. If it exceeds, send linkage control instructions to the servo control system and the precipitation-recharge system respectively, where the warning value includes the support structure deformation threshold, the surrounding surface settlement threshold, and the horizontal and vertical displacement thresholds of the surrounding buildings. The warning value needs to be specifically determined in combination with the foundation pit deformation and the prestress application situation.

[0054] In the embodiments of the present invention, the predicted results corresponding to the control nodes at each stage during the construction process are compared with the warning values to determine whether the predicted values exceed the warning values. If they exceed, corrective analyses are respectively performed on the servo control system and the precipitation - recharge system, and linkage control instructions are sent to the servo control system and the precipitation - recharge system according to the analysis results. Here, the control nodes refer to the phased nodes during the construction process, including the precipitation depth of the groundwater level and the excavation depth of the foundation pit. The warning value refers to the threshold of the control system. By comparing the predicted values of the real - time monitoring data with the threshold of the control system, according to the magnitude of the difference, it is determined whether the predicted value exceeds the threshold of the control system, and the development trend of the real - time monitoring data is predicted, so as to accurately monitor and evaluate the states of each system in real - time, analyze the magnitude of the existing risks, and finally output the risk assessment results and linkage control instructions.

[0055] S5: Adjust the preset output results of the servo control system and the precipitation - recharge system respectively according to the linkage control instructions.

[0056] In the embodiments of the present invention, the prestress application threshold of the jacking force of the servo control system and the pumping volume threshold of the precipitation - recharge system are adjusted respectively according to the linkage control instructions.

[0057] The linkage control instruction is an automatic control instruction sent by the control system to the servo control system and the precipitation - recharge system simultaneously. By analyzing the real - time monitoring data, the risk assessment results of the monitoring data can be obtained. According to the data risk assessment results and the warning values, combined with the relationship between the support force and deformation control and the relationship between the precipitation - recharge water volume and deformation control, as well as the magnitude of the difference between the real - time monitoring data and the warning values, corresponding execution operation instructions are output to adjust and correct the measures of the servo control system and the precipitation - recharge system. For example, when the difference between the predicted value of the deformation of the support structure and the deformation threshold of the support structure is less than the preset value, the control system sends linkage control instructions to the servo control system and the precipitation - recharge system simultaneously to adjust the jacking force of the servo control system and the pumping and recharging of the precipitation - recharge system.

[0058] Traditional foundation pit deformation control methods usually only involve the foundation pit dewatering unit collecting foundation pit water volume data, and the foundation pit deformation monitoring unit collecting deformation data of the supporting structure. There is a lack of a linkage operation mechanism among various departments and manual coordination and control are required. However, during the construction of deep foundation pit projects, for complex surrounding environments, the stable control of deep foundation pit projects has become increasingly complex. It is difficult to achieve precise control of foundation pit deformation through manual coordination and command and dispatch. Compared with traditional foundation pit deformation control methods, the present invention can realize the linkage of deformation monitoring data, groundwater level data, and the applied force of the servo support system by collecting deformation data of the supporting structure, deformation of the ground surface and buildings around the foundation pit, groundwater level, and jack support axial force. This saves a large amount of coordination time for on-site personnel, improves the comprehensive coordination level of the project management department and the response level of command and dispatch, and realizes precise linkage control of foundation pit deformation in complex, sensitive, and old urban areas.

[0059] Embodiment 2

[0060] Combined with Figure 3 , the embodiment of the present invention provides an intelligent control system for deep foundation pit deformation, including:

[0061] A data acquisition module 01, which is used to collect historical monitoring data and real-time monitoring data of the foundation pit monitoring system, the surrounding environment monitoring system of the foundation pit, the precipitation - recharge system, and the servo control system. The historical monitoring data includes historical monitoring data of the deformation of the supporting structure, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force. The real-time monitoring data includes real-time monitoring data of the deformation of the supporting structure, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force.

[0062] This module collects historical monitoring data and real-time monitoring data of four systems, namely the foundation pit monitoring system, the surrounding environment monitoring system of the foundation pit, the precipitation - recharge system, and the servo control system, including the relevant data of relevant instruments and additional sensors arranged. All the collected data is stored in the control system and can be transmitted to the display module 05, including the visualization platform of the mobile terminal. Through the visualization platform, the situation of each real-time monitoring data can be observed.

[0063] A data prediction module 02, which is used to establish a deep learning model for foundation pit deformation based on historical monitoring data, and transmit real-time monitoring data into the deep learning model for foundation pit deformation for prediction to obtain a prediction result.

[0064] This module has the function of data analysis and prediction based on deep learning. The real-time monitoring data of each system collected can be imported into this module for prediction analysis, establishing data interaction among each system. The monitoring data and prediction results of each system can be displayed on the display module 05.

[0065] The early warning module 03 is used to determine whether the prediction result exceeds the early warning value. If it exceeds, linkage control instructions are sent to the servo control system and the precipitation - recharge system respectively.

[0066] This module conducts deviation correction and calibration analysis on the prediction results output by the deep learning model of foundation pit deformation through the set early warning value, and sends linkage control instructions to the servo control system and the precipitation - recharge system. The linkage control module 04 is used to adjust the preset output results of the servo control system and the precipitation - recharge system respectively according to the linkage control instructions.

[0067] This module adjusts the measures of prestress application or precipitation of the servo control system and the precipitation - recharge system through the received linkage control instructions.

[0068] The display module 05 is used to display real - time monitoring data and the interaction information of each monitoring data.

[0069] In summary, an intelligent control method and control system for deep foundation pit deformation provided by the present invention establish a deep learning theoretical model by establishing the relationship between the supporting force, precipitation - recharge water volume and deformation control, and use the deep learning model to predict the development trend of data, realizing the linkage of foundation pit deformation monitoring data, groundwater level data and the applied force of the servo support system. From the perspectives of active control of deep and large foundation pit deformation, automatic monitoring, precipitation - recharge and prestress application, this application realizes the intelligent linkage of deep and large foundation pit deformation control measures and the dynamic feedback of real - time monitoring data, saving a large amount of coordination time for on - site personnel, improving the comprehensive coordination level of the project management department and the working efficiency of command and dispatch. Through effective risk analysis and control, the intelligent linkage control of deep and large foundation pit deformation is realized in a complex and sensitive urban renewal environment, maintaining the stability of the surrounding building environment, reducing environmental disturbance, and making the deformation control of deep and large foundation pits more accurate.

[0070] The concept, principle and idea of the present invention have been described in detail above in combination with specific implementation manners (including embodiments and examples). Those skilled in the art should understand that the implementation manners of the present invention are not limited to the several forms given above. After reading the application documents of the present application, those skilled in the art can make any possible improvements, substitutions and equivalent forms to the steps, methods, systems and components in the above - mentioned implementation manners. These improvements, substitutions and equivalent forms should be regarded as falling within the scope of the present invention, and the protection scope of the present invention is only subject to the claims.

Claims

1. An intelligent control method for deep foundation pit deformation, characterized in that Including: Obtain the historical monitoring data of the foundation pit monitoring system, the surrounding environment monitoring system of the foundation pit, the precipitation - recharge system, and the servo control system; Establish a deep learning model for foundation pit deformation based on the historical monitoring data; Transmit the collected real - time monitoring data into the deep learning model for foundation pit deformation for prediction to obtain a prediction result; Judge whether the prediction result exceeds the warning value. If it exceeds, send linkage control instructions to the servo control system and the precipitation - recharge system respectively; Adjust the preset output results of the servo control system and the precipitation - recharge system respectively according to the linkage control instructions; The establishing the deep learning model for foundation pit deformation based on the historical monitoring data further includes: Establish the relationship between the support force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control according to the historical monitoring data; Establish a WaveNet model based on the relationship between the support force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control; Transmit the historical monitoring data into the WaveNet model for training to obtain a foundation pit deformation training model; Set the parameters of the foundation pit deformation training model, and transmit the real - time monitoring data into the foundation pit deformation training model for testing, where the parameters include the length of predicted data and the time interval; Optimize the foundation pit deformation training model according to the test results to obtain a deep learning model for foundation pit deformation; The judging whether the prediction result exceeds the warning value and, if it exceeds, sending linkage control instructions to the servo control system and the precipitation - recharge system respectively includes: Compare the predicted values corresponding to each stage control node during the construction process with the warning value, judge whether the predicted value exceeds the warning value. If it exceeds, conduct a correction analysis on the servo control system and the precipitation - recharge system respectively, and send linkage control instructions to the servo control system and the precipitation - recharge system according to the analysis results, where the predicted values include the predicted value of the support structure deformation, the predicted value of the surrounding ground surface and building deformation, the predicted value of the groundwater level, and the predicted value of the jack support axial force, and the warning values include the support structure deformation threshold, the surrounding ground surface settlement threshold, and the horizontal and vertical displacement thresholds of the surrounding buildings.

2. The intelligent control method for deep foundation pit deformation according to claim 1, characterized in that The establishing the relationship between the support force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control according to the historical monitoring data includes: Substitute the historical monitoring data into a linear regression model for calculation to obtain the relationship between the support force and deformation control, and the relationship between the precipitation - recharge water volume and deformation control. Both the relationship between the support force and deformation control and the relationship between the precipitation - recharge water volume and deformation control are negatively correlated.

3. The intelligent control method for deep foundation pit deformation according to claim 1 or 2, characterized in that, The historical monitoring data includes the historical monitoring data of the support structure deformation, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force. The real - time monitoring data includes the real - time monitoring data of the support structure deformation, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force.

4. The intelligent control method for deep foundation pit deformation according to claim 1, wherein, Optimizing the foundation pit deformation training model according to the test results to obtain a deep learning model for foundation pit deformation includes: adjusting the learning rate and the number of iterations of the foundation pit deformation training model according to the test results to obtain the deep learning model for foundation pit deformation.

5. The intelligent control method for deep foundation pit deformation according to claim 1, characterized in that, The control node includes the groundwater level lowering depth and the foundation pit excavation depth.

6. The intelligent control method for deep foundation pit deformation according to claim 1, characterized in that, Respectively adjusting the preset output results of the servo control system and the precipitation - recharge system according to the linkage control instruction includes: respectively adjusting the prestress application threshold of the jack axial force of the servo control system and the pumping volume threshold of the precipitation - recharge system according to the linkage control instruction.

7. An intelligent control system for deep foundation pit deformation, characterized in that, For implementing the intelligent control method for deep foundation pit deformation according to any one of claims 1 to 6, it includes: A data acquisition module, configured to collect historical monitoring data and real - time monitoring data of the foundation pit monitoring system, the foundation pit surrounding environment monitoring system, the precipitation - recharge system, and the servo control system; A data prediction module, configured to establish a deep learning model for foundation pit deformation based on the historical monitoring data, and transmit the real - time monitoring data into the deep learning model for foundation pit deformation for prediction to obtain a prediction result; An early warning module, configured to determine whether the prediction result exceeds the early warning value, and if it exceeds, send linkage control instructions to the servo control system and the precipitation - recharge system respectively; A linkage control module, configured to respectively adjust the preset output results of the servo control system and the precipitation - recharge system according to the linkage control instruction; A display module, configured to display the real - time monitoring data and the interaction information of each monitoring data.

8. The intelligent control system for deep foundation pit deformation according to claim 7, characterized in that The historical monitoring data includes historical monitoring data of the deformation of the supporting structure, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force, and the real - time monitoring data includes real - time monitoring data of the deformation of the supporting structure, the deformation of the ground surface and buildings around the foundation pit, the groundwater level, and the jack support axial force.

Images