Intelligent monitoring system and method for deep foundation pit steel support servo in surrounding sensitive geotechnical environment

Abstract

The invention belongs to the technical field of foundation pit deformation control in foundation pit engineering, and provides an intelligent monitoring system and method for a deep foundation pit steel support servo in a surrounding sensitive geotechnical environment, and the system comprises a steel support sensing servo layer, a multi-source data transmission layer, a structure safety intelligent prediction layer and a safety early warning application interaction layer. The steel support sensing servo layer can collect original data of a foundation pit and meanwhile has the effect of controlling axial force of the steel support, the structure safety intelligent prediction layer has the function of training a model and the function of predicting the structure change of the foundation pit in real time, and the safety early warning application interaction layer has the functions of safety early warning and decision regulation and control. A traditional steel support mode is fused with a wireless network, the working mode of servo support of the steel support is improved, the efficiency of regulating and controlling the axial force of the steel support is improved, and the safety of an engineering project is improved.

Description

Technical Field

[0001] This invention belongs to the field of control technology for foundation pit deformation in foundation pit engineering, specifically relating to an intelligent monitoring system and method for servo-controlled steel supports of deep foundation pits in sensitive geotechnical environments. Background Technology

[0002] An excavation pit is a pit dug to provide construction space for underground engineering projects. Due to the stress generated by soil unloading, the soil on the sides of the pit can collapse inwards. Therefore, excavation pits require support to prevent deformation and damage to underground structures, as well as safety issues. In deep excavation pit projects, steel supports are widely used due to their advantages such as short construction period and low cost.

[0003] Traditional steel supports are applied and re-stressed manually. This method is inefficient, poses safety hazards to construction workers, and cannot promptly re-stress losses during foundation pit construction. Over time, excessive prestress loss will render the steel supports ineffective, causing soil deformation and displacement of the retaining structure, leading to damage and safety issues for underground structures.

[0004] Therefore, designing a steel support servo system that can effectively control the deformation of deep foundation pits is of great engineering practical significance. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides an intelligent monitoring system and method for servo-driven deep foundation pit steel supports in sensitive geotechnical environments, thereby resolving the issues in the prior art. The technical solution adopted by this invention is as follows: An intelligent monitoring system for steel support servoing in deep foundation pits under sensitive geotechnical environments includes a steel support sensing servo layer, a multi-source data transmission layer, a structural safety intelligent prediction layer, and a safety early warning application interaction layer. The steel support sensing servo layer is used to collect raw data and to adjust the axial force of the transverse steel support structure. The multi-source data transmission layer is used to transmit raw data to the structural safety intelligent prediction layer; The structural safety intelligent prediction layer is used to predict changes in the foundation pit structure in real time based on the original data. The safety early warning application interaction layer is used to provide real-time early warnings based on predicted changes in the foundation pit structure, and to feed back the warnings to the steel support sensing servo layer to adjust the axial force to a set range.

[0006] Furthermore, the steel support sensing servo layer includes an operation module and a sensing module; The sensing module includes a vibrating wire axial force gauge, an inclinometer, and a fiber optic displacement sensor, which are used to collect raw data in real time, including axial force, tilt, and displacement. The operation module includes a CNC hydraulic device and a support head assembly; the CNC hydraulic device and the support head assembly are connected by an oil circuit, and the support head assembly and the steel support are spliced ​​together to form a transverse steel support structure, which is installed in the foundation pit retaining structure.

[0007] Furthermore, the CNC hydraulic device integrates a servo control system and a hydraulic station. The hydraulic station is equipped with a pressure sensor to monitor oil pressure. The pressure sensor is connected to a pressure data wireless transmission unit to wirelessly transmit pressure data to the structural safety intelligent prediction layer and receive control commands from the safety early warning application interaction layer. The servo control system and the hydraulic station are connected by a line. After receiving the control command from the safety early warning application interaction layer, the pressure data wireless transmission unit uses the real-time monitoring value of the pressure sensor as feedback. The servo control system then controls the output of the hydraulic station to maintain the pressure at the set value.

[0008] Furthermore, the support head assembly includes a flange, a support head frame, a jack, and a wedge-shaped groove. The flange is used to connect the steel support. An axial force gauge mounting bracket is installed at the front end of the support head frame for mounting the vibrating wire axial force gauge. A reinforcing pad is installed at the front end of the vibrating wire axial force gauge. The vibrating wire axial force gauge is connected to an axial force data transmission unit for transmitting the collected axial force data to the structural safety intelligent prediction layer through the axial force data transmission unit.

[0009] Furthermore, the structural safety intelligent prediction layer includes a servo time series database, a foundation pit prediction model training module, and a foundation pit structure real-time prediction module. The servo timing database has several built-in databases, which store the raw data collected from the i-th transverse steel support structure into database i, where i represents the sequence number of the transverse steel support structure. The foundation pit prediction model training module constructs and trains the model by retrieving historical data from the servo time series database and stores the model file in the built-in model repository; The real-time prediction module for the foundation pit structure achieves real-time prediction of foundation pit structure changes by calling model files in the model repository and inputting the latest data from the servo time series database.

[0010] Furthermore, the security early warning application interaction layer includes an early warning decision area, a data visualization area, and an integrated command area; The early warning decision area includes an early warning module and a decision module. The early warning module includes a servo axial force upper and lower limit early warning mechanism and a foundation pit retaining structure lateral deformation early warning mechanism. The lateral deformation early warning mechanism for the foundation pit retaining structure determines the early warning level by comparing the predicted values ​​of the lateral deformation parameters of the foundation pit retaining structure with the set values. It includes three levels: If the foundation pit retaining structure does not experience abnormal acceleration in deformation and the deformation characteristic curve tends to converge, this is a normal state. If the deformation of the foundation pit retaining structure accelerates abnormally, the deformation characteristic curve shows no signs of convergence, and the daily average deformation rate difference is greater than mm / day for several consecutive days, then it is a level two warning state. If the deformation of the foundation pit retaining structure accelerates abnormally, the deformation characteristic curve shows no signs of convergence, and the daily average deformation rate difference is greater than mm / day for several consecutive days, then it is a first-level warning state. When the early warning module reports an early warning status, the decision module provides suggested decisions through the suggestion window. The data visualization area displays real-time data and predicted data in an image format. The integrated command area is used to issue control commands to adjust the CNC hydraulic device in the steel support sensing servo layer so that the axial force is maintained within the set range.

[0011] Furthermore, in the servo axial force upper and lower limit early warning mechanism, the lower limit of the servo end axial force is not less than the design axial force KN, and the upper limit of the servo end axial force is not greater than the design axial force KN.

[0012] A monitoring method for a servo-driven deep foundation pit steel support in a sensitive geotechnical environment, applied to the aforementioned monitoring system for a servo-driven deep foundation pit steel support in a sensitive geotechnical environment, includes the following steps: The steps are as follows: Install the steel support sensing servo layer; splice the support head assembly with the steel support to form a transverse steel support structure, and install it inside the foundation pit retaining structure to collect raw data; Step 1: Connect the support head assembly to the CNC hydraulic device through an oil circuit. The hydraulic station is equipped with a pressure sensor, which is connected to a pressure data wireless transmission unit. Step 2: Start the monitoring system. The steel support sensing servo layer collects raw data in real time and transmits the raw data to the multi-source data transmission layer. Step 3: The multi-source data transmission layer transmits the received raw data to the structural safety intelligent prediction layer; Step 4: The servo time-series database of the structural safety intelligent prediction layer stores the collected raw data into the corresponding database according to the serial number of the transverse steel support structure; the foundation pit prediction model training module retrieves historical data from the servo time-series database to build and train the model, and stores the trained model file in the built-in model repository; the foundation pit structure real-time prediction module calls the model file in the model repository and inputs the latest data from the servo time-series database to realize real-time prediction of foundation pit structure changes; Step 5: The early warning decision area of ​​the safety early warning application interaction layer makes an early warning judgment based on the prediction results of the real-time prediction module of the foundation pit structure. Among them, the early warning mechanism for lateral deformation of the foundation pit retaining structure determines the early warning level by comparing the predicted value and the set value of the lateral deformation parameter of the foundation pit retaining structure, which is divided into normal state, level two early warning state and level one early warning state. When an early warning state is reported, the decision module provides suggested decisions through the suggestion window. At the same time, the data visualization area displays real-time data and predicted data in the form of images. Step 6: The integrated command area of ​​the safety early warning application interaction layer receives decision information from the early warning decision area and sends control commands to the pressure data wireless transmission unit of the CNC hydraulic device via wireless transmission or wired connection. The pressure data wireless transmission unit then transmits the control commands to the servo control system. The servo control system adjusts the output of the hydraulic station according to the control commands, thereby controlling the extension and retraction of the jack, and finally adjusting the axial force of the transverse steel support structure to keep the axial force within the set range.

[0013] The present invention has the following beneficial effects: This invention collects raw data from the foundation pit in real time and constructs a predictive model for analysis, thereby providing suggested measures to achieve real-time control of the axial force of the steel supports. This solves the problem of the inability to promptly compensate for prestress loss in the steel supports, and significantly reduces the number of times the axial force of the steel supports needs to be manually adjusted in actual engineering projects. It also reduces errors from manual operation, achieving higher accuracy, and minimizes the risks associated with manual operation, thus providing a safety guarantee for foundation pit engineering. Attached Figure Description

[0014] Figure 1 This is a three-dimensional layout diagram of the system provided in the embodiment of the present invention; Figure 2 This is a diagram showing the internal structure of the support head assembly in an embodiment of the present invention; Figure 3 This is a diagram showing the internal structure of the CNC hydraulic device in an embodiment of the present invention; Figure 4 This is a system flowchart provided in an embodiment of the present invention; Figure 5 This is a flowchart of the structural safety intelligent prediction layer provided in the embodiments of the present invention; Figure 6 This is a flowchart of the security early warning application interaction layer provided in this embodiment of the invention. Detailed Implementation

[0015] The following will be based on embodiments of the present invention. Figures 1-6The technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Unless otherwise specified, the technical means used in the embodiments are conventional means well known to those skilled in the art.

[0016] This invention proposes an intelligent monitoring system and method for steel support servo systems in deep foundation pits under sensitive geotechnical environments. This system aims to reduce the deformation of deep foundation pits in sensitive geotechnical environments caused by the inability of traditional steel support servo systems to respond promptly to changes in the foundation pit, thereby improving the safety and reliability of the project.

[0017] like Figures 1-3 This invention proposes an intelligent monitoring system for steel support servo in deep foundation pits under sensitive geotechnical environments, comprising a steel support sensing servo layer, a multi-source data transmission layer, a structural safety intelligent prediction layer, and a safety early warning application interaction layer. The steel support sensing servo layer is used to collect raw data and to adjust the axial force of the transverse steel support structure. The multi-source data transmission layer is used to transmit raw data to the structural safety intelligent prediction layer; The structural safety intelligent prediction layer is used to predict changes in the foundation pit structure in real time based on the original data. The safety early warning application interaction layer is used to provide real-time early warnings based on predicted changes in the foundation pit structure, and to feed back the warnings to the steel support sensing servo layer to adjust the axial force to a set range.

[0018] In this invention, the steel support sensing servo layer can collect raw data of the foundation pit and also controls the axial force of the steel support. The multi-source data transmission layer consists of several wireless transmission devices. The structural safety intelligent prediction layer has the function of training models and predicting changes in the foundation pit structure in real time. The safety early warning application interaction layer has the function of safety early warning and provides an application interaction window, which will give the system's suggested decisions and provide axial force adjustment options. The multi-source data transmission layer consists of several wireless transmission devices. The structural safety intelligent prediction layer and the safety early warning application interaction layer are integrated on the mobile terminal 20.

[0019] Furthermore, the steel support sensing servo layer is arranged inside and outside the foundation pit using physical instruments, and the steel support sensing servo layer includes an operation module and a sensing module. The sensing module includes a vibrating wire axial force gauge 6, an inclinometer 7, and a fiber optic grating displacement sensor 8, which are used to collect raw data in real time, including axial force, tilt, and displacement. The operation module includes a CNC hydraulic device 1 and a support head assembly 2; the CNC hydraulic device 1 and the support head assembly 2 are connected by an oil circuit 3, and the support head assembly 2 and the steel support 4 are spliced ​​together to form a transverse steel support structure, which is installed in the foundation pit retaining structure 5.

[0020] The inclinometer 7 includes an inclinometer tube 13, a probe 14, a cable 15, and a reader 16. The inclinometer tube 13 is pre-embedded and installed inside the foundation pit retaining structure 5. During installation, the inclinometer tube 13 must be kept vertical, and the installation spacing is selected according to project requirements. The fiber optic displacement sensor 8 is securely bound to the reinforcing cage 17 with stainless steel cable ties. The fiber optic displacement sensors 8 are symmetrically installed on both sides of the longitudinal section of the center of the reinforcing cage 17 as the plane of symmetry. The fiber optic displacement sensor 8 is connected to the signal demodulator 19 through the transmission optical cable 18 and transmits reflected light signals carrying information. After receiving the reflected light signals, the signal demodulator 19 accurately calculates the strain using a built-in algorithm and wirelessly transmits the calculation results to the structural safety intelligent prediction layer.

[0021] Furthermore, the CNC hydraulic device 1 integrates a servo control system 9 and a hydraulic station 10. The hydraulic station 10 is equipped with a pressure sensor 11 for monitoring oil pressure. The pressure sensor 11 is connected to a pressure data wireless transmission unit 12 for wirelessly transmitting pressure data to the structural safety intelligent prediction layer and receiving control commands from the safety early warning application interaction layer. The servo control system 9 is connected to the hydraulic station 10 via a line. After receiving the control command from the safety warning application interaction layer, the pressure data wireless transmission unit 12 uses the real-time monitoring value of the pressure sensor 11 as feedback. The servo control system 9 controls the output of the hydraulic station 10 to maintain the pressure at the set value.

[0022] Furthermore, the support head assembly 2 includes a flange edge 21, a support head frame 22, a jack 23, and a wedge-shaped groove 24. The flange edge 21 is used to connect the steel support 4. The front end of the support head frame 22 is equipped with an axial force gauge mounting bracket 25 for mounting the vibrating wire axial force gauge 6. The front end of the vibrating wire axial force gauge 6 is equipped with a reinforcing pad 26 to ensure the uniformity of axial force transmission and to avoid inaccurate measurement or equipment damage due to uneven force. The vibrating wire axial force gauge 6 is connected to an axial force data transmission unit 27 for transmitting the collected axial force data to the structural safety intelligent prediction layer through the axial force data transmission unit 27.

[0023] like Figure 4As shown, during operation, the steel support sensing servo layer collects data such as the axial force of the transverse steel support structure, the displacement of the foundation pit retaining structure 5, and the hydraulic pressure. This data is sent to the structural safety intelligent prediction layer through the multi-source data transmission layer. The structural safety intelligent prediction layer trains the foundation pit prediction model using the data and uses it to predict real-time changes in the foundation pit structure. The obtained foundation pit structure change prediction results are input into the safety early warning application interaction layer. The safety early warning application interaction layer performs decision analysis on the prediction results and provides corresponding suggested measures. Under normal conditions, it will issue instructions to continuously monitor data. Under early warning conditions, an early warning window will pop up, where staff can view suggested measures and input axial force control instructions. These instructions will be sent to the steel support sensing servo layer, forming a closed loop to achieve real-time control of the steel support axial force.

[0024] Furthermore, such as Figure 5 The structural safety intelligent prediction layer includes a servo time series database, a foundation pit prediction model training module, and a foundation pit structure real-time prediction module. The servo timing database has several built-in databases, which store the raw data collected from the i-th transverse steel support structure into database i, where i represents the sequence number of the transverse steel support structure. The foundation pit prediction model training module constructs and trains the model by retrieving historical data from the servo time series database and stores the model file in the built-in model repository; The real-time prediction module for the foundation pit structure achieves real-time prediction of foundation pit structure changes by calling model files in the model repository and inputting the latest data from the servo time series database.

[0025] Specifically, the structural safety intelligent prediction layer uses LSTM for prediction. LSTM (Long Short-Term Memory) network, through the design of the "gate" structure, allows information to pass selectively. It can be divided into three stages: the first stage is the forget gate, which determines which information needs to be forgotten; the second stage is the input gate, which determines which new information can be stored; and the last stage is the output gate, which determines what value to output. Forget Gate: The Forget Gate is the output of the layer above. and the sequence data to be input to this layer As input, it passes through an activation function sigmoid, and the output is... . The output value takes a value in the range [0,1], representing the probability that the cell state of the previous layer is forgotten; 1 means "completely retained", and 0 means "completely discarded". ; Input gate: The input gate consists of two parts. The first part uses the sigmoid activation function, and the output is... The value takes a value in the interval [0,1], indicating that The degree to which information is preserved is determined in the second part using the tanh activation function, and the output is... , It is the output of the forget gate that controls the state of the cell in the previous layer. The degree to which they are forgotten The two outputs of the input gate are multiplied, indicating how much new information is retained. This describes the cellular state of this layer.

[0026] ; ; ; Output gate: The output gate controls how many cell states in this layer are filtered. First, a sigmoid activation function is used to obtain a value in the range [0,1]. Next, the cell state After processing with the tanh activation function and Multiplication is the output of this layer. .

[0027] ; ; First, LSTM systematically retrieves historical data from the servo time series database, performs preprocessing and feature engineering on this raw data such as handling missing values ​​and removing outliers, and uses the sliding window technique to construct learning samples from continuous time series data. Using the monitoring data sequence of the past tens to hundreds of hours as input features, it predicts the key deformation values ​​for the next few hours.

[0028] The next step is to input this preprocessed data into the constructed LSTM neural network for training. After training, the LSTM model with predictive capabilities is serialized into a model file and saved to the model repository.

[0029] When entering the real-time prediction phase, the real-time prediction module loads the model file from the model repository and continuously retrieves the latest real-time monitoring sequences that conform to the preset time window length from the database. After undergoing the same standardization process as in the training phase, the sequences are input into the loaded LSTM model for calculation and output the prediction results of the foundation pit structure changes in the future period.

[0030] Furthermore, such as Figure 6 The security early warning application interaction layer includes an early warning decision area, a data visualization area, and an integrated command area; The early warning decision area includes an early warning module and a decision module. The early warning module includes a servo axial force upper and lower limit early warning mechanism and a foundation pit retaining structure lateral deformation early warning mechanism. The lateral deformation early warning mechanism for the foundation pit retaining structure determines the early warning level by comparing the predicted values ​​of the lateral deformation parameters of the foundation pit retaining structure with the set values. It includes three levels: If the foundation pit retaining structure does not experience abnormal acceleration in deformation and the deformation characteristic curve tends to converge, this is a normal state. If the deformation of the foundation pit retaining structure accelerates abnormally, the deformation characteristic curve shows no signs of convergence, and the daily average deformation rate difference is greater than 2 mm / day for two consecutive days, then it is a level two warning state. If the deformation of the foundation pit retaining structure accelerates abnormally, the deformation characteristic curve shows no signs of convergence, and the daily average deformation rate difference is greater than 2 mm / day for 3 consecutive days, then it is a Level 1 warning state. When the warning module reports a warning status, the decision module provides suggested decisions through the suggestion window. The data visualization area displays real-time data and predicted data in the form of images. The integrated command area is used to issue control commands to adjust the CNC hydraulic device 1 in the steel support sensing servo layer so that the axial force is maintained within the set range.

[0031] Specifically, the integrated command area receives decision information from the early warning decision area and sends control commands to the pressure data wireless transmission unit 12 of the CNC hydraulic device 1 via wireless transmission or wired connection. The pressure data wireless transmission unit 12 then transmits the commands to the servo control system 9. The servo control system 9 adjusts the output of the hydraulic station 10 according to the commands, thereby controlling the extension and retraction of the jack 23, and ultimately achieving the adjustment of the axial force of the transverse steel support structure.

[0032] The early warning decision area uses a program written in code to determine whether to issue an early warning and provide relevant decision suggestions based on the results obtained from the prediction model. It is specifically divided into an early warning module and a decision module. The data visualization area uses code (such as Python) to build a web interface. After the backend processes the prediction data, it generates a visualization and displays it on the web interface, which can be accessed and viewed through terminals (computers and mobile phones). The integrated command area is also built in the same web interface with code, and engineers interact with it to send commands.

[0033] Furthermore, in the servo axis force upper and lower limit early warning mechanism, the lower limit of the servo axis force is not less than the design axis force of 100KN, and the upper limit of the servo axis force is not greater than the design axis force of 200KN.

[0034] like Figure 4The present invention also proposes a monitoring method for a servo system of a deep foundation pit steel support in a sensitive geotechnical environment, which is applied to the aforementioned intelligent monitoring system for a deep foundation pit steel support in a sensitive geotechnical environment, and includes the following steps: Step 1: Install the steel support sensing servo layer; splice the support head assembly 2 with the steel support 4 to form a transverse steel support structure, and install it inside the foundation pit retaining structure 5 to collect raw data; Step 2: Connect the support head assembly 2 to the CNC hydraulic device 1 through the oil circuit 3. The hydraulic station 10 is equipped with a pressure sensor 11, and the pressure sensor 11 is connected to the pressure data wireless transmission unit 12. Step 3: Start the monitoring system. The steel support sensing servo layer collects raw data in real time and transmits the raw data to the multi-source data transmission layer. Step 4: The multi-source data transmission layer transmits the received raw data to the structural safety intelligent prediction layer; Step 5: The servo time-series database of the structural safety intelligent prediction layer stores the collected raw data into the corresponding database according to the serial number of the transverse steel support structure; the foundation pit prediction model training module retrieves historical data from the servo time-series database to build and train the model, and stores the trained model file in the built-in model repository; the foundation pit structure real-time prediction module calls the model file in the model repository and inputs the latest data from the servo time-series database to realize real-time prediction of foundation pit structure changes; Step 5: The early warning decision area of ​​the safety early warning application interaction layer makes an early warning judgment based on the prediction results of the real-time prediction module of the foundation pit structure. Among them, the early warning mechanism for lateral deformation of the foundation pit retaining structure determines the early warning level by comparing the predicted value and the set value of the lateral deformation parameter of the foundation pit retaining structure, which is divided into normal state, level two early warning state and level one early warning state. When an early warning state is reported, the decision module provides suggested decisions through the suggestion window. At the same time, the data visualization area displays real-time data and predicted data in the form of images. Step 6: The integrated command area of ​​the safety early warning application interaction layer receives decision information from the early warning decision area and sends control commands to the pressure data wireless transmission unit 12 of the CNC hydraulic device 1 via wireless transmission or wired connection. The pressure data wireless transmission unit 12 then transmits the control commands to the servo control system 9. The servo control system 9 adjusts the output of the hydraulic station 10 according to the control commands, thereby controlling the extension and retraction of the jack 23, and finally realizing the adjustment of the axial force of the transverse steel support structure, so that the axial force is maintained within the set range.

[0035] This invention provides an intelligent monitoring system and method for servo control of steel supports in deep foundation pits under sensitive geotechnical environments. Through the interconnectedness of different layers of a cloud system, it utilizes the powerful computing efficiency of computers to analyze the original foundation pit data and uses a predictive model to predict structural changes in the foundation pit in real time. By adopting a decision-making control approach, it achieves real-time regulation of the axial force of the steel supports, solving the problem of timely replenishment of prestress loss in steel supports during actual engineering projects. Furthermore, it significantly reduces the number of times manual adjustment of the axial force of the steel supports is required in actual engineering projects, reducing errors from manual operation and achieving higher accuracy. It also reduces the risks associated with manual operation, providing a safety guarantee for foundation pit engineering.

[0036] The above embodiments are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Any modifications, alterations, alterations, or substitutions made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. An intelligent monitoring system for servoing of steel support of deep foundation pit in circumjacent sensitive geotechnical environment, characterized in that, The steel support sensing servo layer, the multi-source data transmission layer, the structure safety intelligent prediction layer, and the safety warning application interaction layer are included. The steel support sensing servo layer is used for collecting original data and adjusting the axial force size of the transverse steel support structure. The multi-source data transmission layer is used for transmitting the original data to the structure safety intelligent prediction layer. The structure safety intelligent prediction layer is used for predicting the foundation pit structure changes in real time according to the original data. The safety warning application interaction layer is used for performing real-time warning according to the predicted foundation pit structure changes and feeding back to the steel support sensing servo layer to adjust the axial force to the set range.

2. The intelligent monitoring system for servoing of steel support of deep foundation pit in peripheral sensitive soil environment according to claim 1, characterized in that, The steel support sensing servo layer includes an operation module and a sensing module. The sensing module includes a vibrating wire axial force gauge (6), an inclinometer (7), and a fiber bragg grating displacement sensor (8) and is used for collecting original data including axial force, inclination, and displacement in real time. The operation module includes a numerical control hydraulic device (1) and a support head assembly (2). The numerical control hydraulic device (1) is connected with the support head assembly (2) through an oil circuit (3). The support head assembly (2) is spliced with a steel support (4) to form a transverse steel support structure together and is installed in a foundation pit enclosure structure (5).

3. The intelligent monitoring system for servoing of steel support of deep foundation pit in peripheral sensitive soil environment according to claim 2, characterized in that, The numerical control hydraulic device (1) integrates a servo control system (9) and a hydraulic station (10). The hydraulic station (10) is installed with a pressure sensor (11) for monitoring oil pressure. The pressure sensor (11) is connected with a pressure data wireless transmission unit (12) for wirelessly transmitting pressure data to the structure safety intelligent prediction layer and receiving control instructions of the safety warning application interaction layer. The servo control system (9) is connected with the hydraulic station (10) through a line. After receiving the control instructions of the safety warning application interaction layer, the pressure data wireless transmission unit (12) takes the real-time monitoring value of the pressure sensor (11) as feedback. The servo control system (9) controls the output of the hydraulic station (10) to maintain the pressure at a set value.

4. The intelligent monitoring system for servoing of steel support of deep foundation pit in peripheral sensitive soil environment according to claim 2, characterized in that, The support head assembly (2) includes a flange edge (21), a support head frame (22), a jack (23), and a wedge-shaped clamping groove (24). The flange edge (21) is used for connecting the steel support (4). The support head frame (22) is installed with an axial force gauge mounting rack (25) at the front end for installing the vibrating wire axial force gauge (6). The vibrating wire axial force gauge (6) is installed with a reinforcing backing plate (26) at the front end. The vibrating wire axial force gauge (6) is connected with an axial force data transmission unit (27) for sending the collected axial force data to the structure safety intelligent prediction layer through the axial force data transmission unit (27).

5. The intelligent monitoring system for servoing of steel support of deep foundation pit in peripheral sensitive geo-environment according to claim 1, characterized in that, The structure safety intelligent prediction layer includes a servo time sequence database, a foundation pit prediction model training module, and a foundation pit structure real-time prediction module. The servo time sequence database is built-in with a plurality of databases. The original data collected in the i-th transverse steel support structure is stored in the database i, where i represents the serial number of the transverse steel support structure. The foundation pit prediction model training module constructs and trains a model by calling historical data in the servo time sequence database and stores the model file in a built-in model warehouse. The foundation pit structure real-time prediction module realizes real-time prediction of the foundation pit structure change by calling the model file in the model warehouse and inputting the latest data of the servo time sequence database.

6. The intelligent monitoring system for servoing of steel support of deep foundation pit in peripheral sensitive geo-environment according to claim 1, characterized in that, The safety warning application interaction layer includes a warning decision area, a data visualization area, and an integrated instruction area. The warning decision area includes a warning module and a decision module, and the warning module includes a servo shaft force upper and lower limit warning mechanism and a foundation pit enclosure structure lateral deformation warning mechanism. The foundation pit enclosure structure lateral deformation warning mechanism determines the warning level by comparing the predicted value of the lateral deformation parameter of the foundation pit enclosure structure with the set value, including three levels, which are: If the foundation pit enclosure structure has no abnormal acceleration of deformation, the deformation characteristic curve tends to converge, which is a normal state; If the foundation pit enclosure structure has abnormal acceleration of deformation, the deformation characteristic curve has no convergence, and the daily average deformation rate difference is greater than 2mm / day for 2 consecutive days, which is a secondary warning state; If the foundation pit enclosure structure has abnormal acceleration of deformation, the deformation characteristic curve has no convergence, and the daily average deformation rate difference is greater than 2mm / day for 3 consecutive days, which is a primary warning state; When the warning module reports the warning state, the decision module gives a suggested decision through a suggestion window, the data visualization area displays real-time data and prediction data in the form of images, and the integrated instruction area is used to issue control commands to adjust the numerical control hydraulic device (1) in the steel support perception servo layer, so that the shaft force is maintained within the set range.

7. The intelligent monitoring system for servoing of steel support of deep foundation pit in peripheral sensitive soil environment according to claim 6, characterized in that, The servo end shaft force lower limit in the servo shaft force upper and lower limit warning mechanism is not less than 100KN of the design shaft force, and the servo end shaft force upper limit is not greater than 200KN of the design shaft force.

8. A monitoring method of servo of steel support of deep foundation pit in sensitive soil environment, applied to the intelligent monitoring system of servo of steel support of deep foundation pit in sensitive soil environment according to any one of claims 1-7, characterized in that, The method comprises the following steps: Step 1, install the steel support perception servo layer; splice the support head assembly (2) and the steel support (4) to form a transverse steel support structure together, and install it in the foundation pit enclosure structure (5) to collect original data; Step 2, connect the support head assembly (2) and the numerical control hydraulic device (1) through the oil line (3), and the hydraulic station (10) is provided with a pressure sensor (11), and the pressure sensor (11) is connected with a pressure data wireless transmission unit (12); Step 3, start the monitoring system, and the steel support perception servo layer collects real-time original data and transmits the original data to the multi-source data transmission layer; Step 4, the multi-source data transmission layer transmits the received original data to the structure safety intelligent prediction layer; Step 5, the servo time sequence database of the structure safety intelligent prediction layer stores the collected original data into the corresponding database according to the serial number of the transverse steel support structure; the foundation pit prediction model training module calls the historical data in the servo time sequence database to construct and train the model, and stores the trained model file in the built-in model warehouse; the foundation pit structure real-time prediction module calls the model file in the model warehouse and inputs the latest data of the servo time sequence database to realize real-time prediction of the foundation pit structure change. Step 5, the warning decision area of the safety warning application interactive layer makes a warning judgment according to the prediction result of the foundation pit structure real-time prediction module; wherein the lateral deformation warning mechanism of the foundation pit retaining structure determines the warning level by comparing the predicted value of the lateral deformation parameter of the foundation pit retaining structure with the set value, and is divided into a normal state, a secondary warning state and a primary warning state; when reporting the warning state, the decision module gives a suggestion decision through a suggestion window; at the same time, the data visualization area displays the real-time data and the predicted data in the form of images; Step 6, the integrated instruction area of the safety warning application interactive layer receives the decision information from the warning decision area, and sends the control command to the pressure data wireless transmission unit (12) of the numerical control hydraulic device (1) through wireless transmission or wired connection; the pressure data wireless transmission unit (12) further transmits the control command to the servo control system (9), and the servo control system (9) adjusts the output of the hydraulic station (10) according to the control command, and then controls the extension amount of the jack (23), and finally realizes the adjustment of the axial force of the transverse steel support structure, so that the axial force is maintained within the set range.

Images