Pipe jacking machine posture control method and system for municipal engineering construction

Abstract

The application relates to the technical field of posture control, in particular to a pipe jacking machine posture control method and system for municipal engineering construction, which comprises the following steps: acquiring various monitoring data of the pipe jacking machine; dividing a monitoring time into multiple monitoring time periods, and dividing each monitoring time period into multiple time periods according to the phased differences of the posture changes of the pipe jacking machine in the monitoring time periods; acquiring a change response characteristic value of a single kind of monitoring data in a single time period according to the discrete characteristics of the single kind of monitoring data in the single time period and the correlation characteristics and difference characteristics of the single kind of monitoring data and other various kinds of monitoring data; and acquiring a moving time window parameter of the single kind of monitoring data in a single monitoring time period according to the total number of data of the single kind of monitoring data in each time period of the single monitoring time period and the change response characteristic value, so as to control the monitoring data in the posture control process of the pipe jacking machine. The moving time window length of different time periods is adaptively optimized, and the accuracy of the pipe jacking posture control is improved.

Description

Technical Field

[0001] This application relates to the field of attitude control technology, specifically to a method and system for attitude control of pipe jacking machines used in municipal engineering construction. Background Technology

[0002] In municipal engineering construction, pipe jacking technology is widely used in projects such as water supply and drainage pipeline laying and power and communication line crossings due to its advantages of not requiring large-scale ground excavation and having minimal impact on the surrounding environment. As the core equipment in pipe jacking construction, the attitude control of the pipe jacking machine directly affects project quality, construction safety, and cost control. Precise attitude control is crucial to ensuring construction quality. If the pipe jacking machine loses attitude control, the pipeline axis will deviate from the design path, leading to problems such as misalignment and leakage, seriously affecting the pipeline's functionality and durability. Furthermore, efficient attitude control can optimize the construction process, reduce equipment failure and rework risks, lower construction costs, and improve overall project efficiency.

[0003] However, traditional pipe jacking machine attitude control methods do not fully consider the impact of differences in the actual geological environment on attitude analysis. This results in low efficiency and large errors in real-time attitude control, where the method relies on monitoring and collecting attitude data during operation and comparing it with preset target attitude data. With the increasing scale and complexity of municipal engineering projects, existing attitude monitoring and control methods for pipe jacking machines struggle to cope with the influence of complex geological environments on attitude changes, leading to significant attitude control errors and potential safety hazards during construction. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide a method and system for controlling the attitude of a pipe jacking machine in municipal engineering construction. The specific technical solution adopted is as follows:

[0005] In a first aspect, embodiments of this application provide a method for controlling the attitude of a pipe jacking machine in municipal engineering construction, the method comprising the following steps:

[0006] Real-time acquisition of various monitoring data during the operation of the pipe jacking machine;

[0007] The set of all monitoring data at each time point is taken as the monitoring data set at each time point; the monitoring time is evenly divided into multiple monitoring periods, and the distance matrix of each monitoring period is obtained based on the distance between the monitoring data sets at all times within each monitoring period; irrelevant variables in a single distance matrix are obtained, and the monitoring period corresponding to the distance matrix is ​​divided into multiple time periods based on the time points corresponding to the irrelevant variables;

[0008] Based on the dispersion of a single type of monitoring data within a single time period and its correlation with other types of monitoring data, the significant impact value of a single type of monitoring data within a single time period is obtained; and by combining the difference between a single type of monitoring data and its preset value within a single time period, and the difference between the difference between a single type of monitoring data and its preset value with other types of monitoring data within a single time period, the change response characteristic value of a single type of monitoring data within a single time period is obtained.

[0009] Based on the total number of data and change response characteristic values ​​of a single type of monitoring data in each time period of a single monitoring period, the movement time window parameters of the single type of monitoring data in a single monitoring period are obtained, and then the monitoring data in the attitude control process of the pipe jacking machine are controlled by the model predictive control algorithm.

[0010] Preferably, the specific process of obtaining the distance matrix for each monitoring period is as follows: A distance matrix for a single monitoring period is constructed based on the Euclidean distance between the monitoring data sets of any two times within a single monitoring period. The distance matrix for the single monitoring period contains the distance matrix for the [missing information - likely a specific time period]. Line 1 The column element is the first [element] within a single monitoring period. The moment and the first The Euclidean distance between the monitoring data sets at each time point.

[0011] Preferably, the specific process for obtaining the extraneous variables in a single distance matrix is ​​as follows: using the PCA principal component analysis method to obtain the extraneous variables in a single distance matrix.

[0012] Preferably, the specific process of dividing the monitoring period corresponding to the distance matrix into multiple time periods is as follows: the two moments corresponding to each irrelevant variable are recorded as the abrupt change moments of the corresponding distance matrix; the monitoring period corresponding to the distance matrix is ​​divided into multiple time periods using all the abrupt change moments of the distance matrix.

[0013] Preferably, the process for obtaining the significance value of the single type of monitoring data within a single time period is as follows:

[0014] The sequence formed by sorting each type of monitoring data in chronological order within a single time period is taken as the monitoring data sequence for each type of monitoring data within the single time period.

[0015] Calculate the Pearson correlation coefficient between a single type of monitoring data and other types of monitoring data within a single time period, and use the mean of all Pearson correlation coefficients as the first characteristic value of the single type of monitoring data within a single time period.

[0016] The product of the coefficient of variation of all data for a single type of monitoring data within a single time period and the first eigenvalue is taken as the significance value of the single type of monitoring data within a single time period.

[0017] Preferably, the formula for calculating the change response characteristic value of the single type of monitoring data in a single time period is: In the formula, Indicates the first The monitoring data in the first The change response characteristic value over a time period; Indicates the first The monitoring data in the first The significant value of the impact over a time period; and They represent the first The monitoring data in the first The and the first The mean of the absolute differences between all monitoring data and their corresponding preset values ​​over a given time period; This represents the total number of time periods within the monitoring period containing the y-th time period.

[0018] Preferably, the preset value is a standard value for each monitoring data that is automatically set by the pipe jacking machine based on the on-site exploration results during actual operation.

[0019] Preferably, the formula for calculating the moving time window parameter of the single type of monitoring data within a single monitoring period is: In the formula, Indicates the first The moving time window parameter of the monitoring data within a single monitoring period; Indicates the first The monitoring data in the first The number of data points within a given time period; Indicates the first The monitoring data in the first The change response characteristic value over a time period Indicates the first The summation of the change response characteristic values ​​of a type of monitoring data across all time periods within a single monitoring period; This represents the total number of time periods within the monitoring period containing the y-th time period.

[0020] Preferably, the specific process of using the model predictive control algorithm to control the monitoring data in the attitude control process of the pipe jacking machine is as follows: the calculated moving time window parameter of each monitoring data in a single monitoring period is used as the moving time window length for the MPC algorithm to predict each monitoring data in a single monitoring period, and the operating attitude of the pipe jacking machine is optimized and controlled.

[0021] Secondly, embodiments of this application also provide a posture control system for a pipe jacking machine in municipal engineering construction, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described posture control methods for pipe jacking machines in municipal engineering construction.

[0022] This application has at least the following beneficial effects:

[0023] In municipal engineering pipe jacking construction, the complexity of the operating environment of the pipe jacking machine significantly increases the difficulty of attitude control. Due to differences in geological conditions, surrounding environment, and equipment operating conditions at different stages of construction, traditional attitude control methods struggle to dynamically adapt to these changes, leading to significant attitude control deviations and impacting project quality. Therefore, this application proposes an attitude control method for pipe jacking machines in municipal engineering construction. Firstly, based on the phased changes in the actual operating environment of the pipe jacking machine, the method analyzes the phased characteristics of monitoring data by dividing monitoring periods, accurately identifying the phased differences in the attitude changes of the pipe jacking machine, and thus defining the time periods for the response characteristics of different monitoring data to attitude changes. Next, it analyzes the dynamic response characteristics of each monitoring data point to attitude deviations at different stages of advancement. Based on the analysis results, it dynamically adjusts the moving time window parameters of the model predictive control algorithm at each monitoring point, optimizing the moving time window length. The beneficial effect is that it fully considers the dynamic changes in environmental conditions and advancement progress during pipe jacking operation. By conducting refined analysis of the response characteristics of different monitoring data at different time periods, a dynamic and adaptive attitude control strategy is constructed, effectively improving the accuracy and reliability of attitude control during pipe jacking construction, ensuring construction safety and project quality. Attached Figure Description

[0024] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 A flowchart illustrating the steps of a pipe jacking machine attitude control method in municipal engineering construction, as provided in one embodiment of this application;

[0026] Figure 2 This is a flowchart illustrating the acquisition of the moving time window parameter of a single type of monitoring data within a single monitoring period, as provided in one embodiment of this application. Detailed Implementation

[0027] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the pipe jacking machine attitude control method and system for municipal engineering construction proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0029] The following description, in conjunction with the accompanying drawings, details the specific scheme of the posture control method and system for pipe jacking machines used in municipal engineering construction provided in this application.

[0030] Please see Figure 1 The diagram illustrates a flowchart of a method for controlling the attitude of a pipe jacking machine in municipal engineering construction, according to an embodiment of this application. The method includes the following steps:

[0031] The pipe jacking machine attitude control method adopted in this application includes data acquisition, data analysis, and attitude optimization control, which realizes precise control of the pipe jacking machine attitude. The specific control process is as follows:

[0032] Step 1: Acquire various monitoring data during the operation of the pipe jacking machine in real time.

[0033] During the operation of the pipe jacking machine, monitoring data can be collected through various attitude data acquisition devices, including an inertial measurement unit (IMU), a laser guidance system, and pressure and torque sensors. The IMU integrates an accelerometer, gyroscope, and magnetometer, enabling real-time measurement of the pipe jacking machine's acceleration, angular velocity, and magnetic field strength, thereby obtaining its pitch, roll, and yaw angles. The laser guidance system projects a laser beam onto a target inside the pipe jacking machine using a laser emitter located within the working shaft, calculating the horizontal and vertical offsets based on the laser's positional deviation on the target. Pressure and torque sensors collect jacking pressure and cutterhead torque operating parameters to analyze the pipe jacking machine's attitude change characteristics.

[0034] Due to the complex environment at construction sites, the raw data collected often contains noise and outliers, requiring preprocessing. Specifically, filtering algorithms are used to denoise the data collected by the inertial measurement unit, pressure sensor, and torque sensor, eliminating sensor measurement errors. In this embodiment, a Gaussian filtering algorithm is used; in other embodiments, Kalman filtering or Wiener filtering algorithms can also be used. Secondly, outlier detection is performed on the position data collected by the laser guidance system to remove erroneous data caused by changes in ambient light and vibration interference. Finally, the collected pressure and torque data are normalized to convert them into uniform units for easier subsequent data analysis.

[0035] Step 2: Take the set of all monitoring data at each time moment as the monitoring data set at each time moment; divide the monitoring time evenly into multiple monitoring periods, and obtain the distance matrix of each monitoring period based on the distance between the monitoring data sets at all times within each monitoring period; obtain the irrelevant variables in a single distance matrix, and divide the monitoring period corresponding to the distance matrix into multiple time periods based on the time corresponding to the irrelevant variables.

[0036] During actual operation, the attitude of a pipe jacking machine can deviate horizontally, vertically, and change in pitch and roll angles due to geological conditions and variations in equipment and forces during construction. Uneven soil texture and asymmetrical jacking force distribution can cause the machine to deviate from its design axis in the left-right direction. Uneven weight distribution at the machine's front end or variations in jacking speed can also lead to vertical deviations. Pitch angle changes reflect the degree of tilt at the machine's front end; excessive pitch angles can cause "head-knocking" or "pipe drifting." Roll angle changes reflect the machine's rotation around its own axis, potentially affecting the sealing performance of pipe joints.

[0037] Therefore, the attitude changes of a pipe jacking machine during operation are interconnected and complex. Traditional monitoring and feedback control may overlook differences in geological environment and the varying responses of monitoring parameters to attitude changes at different advancement stages, leading to significant errors in the analysis of the pipe jacking machine's attitude deviation and resulting in attitude control errors. For example, horizontal and vertical deviations may occur simultaneously and are influenced by various factors such as jacking force and soil conditions; changes in pitch and roll angles also affect the measurements of the laser guidance system. To address the impact of complex construction environments on attitude control, this application considers the phased characteristics of the response changes of different monitoring parameters to attitude changes during actual construction, i.e., the differences in the variation characteristics of pipe jacking machine monitoring parameters at different advancement stages; the parameters in the attitude control process are optimized and adjusted to achieve precise control of the pipe jacking machine's attitude; the specific optimization and adjustment analysis process is as follows:

[0038] During the pipe jacking process, the geological conditions, soil parameters, and mechanical response characteristics at different construction stages exhibit significant spatiotemporal heterogeneity. This heterogeneity leads to the dynamic evolution of the pipe jacking machine's attitude characteristics with the jacking depth, manifested in differences in the response rate, sensitivity, and coupling relationship of different monitoring data to environmental changes within different monitoring periods. Therefore, in real-time monitoring, the pitch angle, roll angle, yaw angle, horizontal offset, vertical offset, jacking pressure, and cutterhead torque data acquired at each moment are combined into a set as the monitoring data set for each moment.

[0039] Since pipe jacking machines primarily operate in underground tunnels, the impact of different geological environments varies at different advancement distances. To achieve timely and accurate control of the pipe jacking machine's attitude, this application sets a monitoring point for phased attitude control adjustment and optimization every 10 minutes, and uses the 10 minutes preceding each monitoring point as the monitoring period for each monitoring point. The following analysis is based on the monitoring period corresponding to a single monitoring point. The Euclidean distance between the monitoring data sets of any two times within a single monitoring period is calculated to reflect the differences in monitoring data at different times. A distance matrix for a single monitoring period is constructed based on the obtained Euclidean distance. The distance matrix for a single monitoring period contains the distance of the [missing information - likely a specific type of distance matrix]. Line 1 The column element is the first [element] within a single monitoring period. The moment and the first The Euclidean distance between monitoring data sets at each moment can be used to reflect the differences in instantaneous attitude information within a single monitoring period through a distance matrix.

[0040] Using the distance matrix of a single monitoring period as input, Principal Component Analysis (PCA) is employed to identify significantly different extraneous variables within the distance matrix. The two times corresponding to each extraneous variable are recorded as abrupt change points in the distance matrix. Based on all abrupt change points in the distance matrix, the monitoring period for the current monitoring point is divided into time periods with different attitude change response characteristics, providing a data foundation for subsequent precise attitude control. PCA is a well-known technique, and its specific process will not be elaborated upon here.

[0041] Step 3: Based on the dispersion of a single type of monitoring data within a single time period and its correlation with other types of monitoring data, obtain the significant impact value of a single type of monitoring data within a single time period; and combine the difference between a single type of monitoring data and its preset value within a single time period, as well as the difference between other types of monitoring data and their preset values ​​within a single time period, obtain the change response characteristic value of a single type of monitoring data within a single time period.

[0042] Based on the divided time periods, the characteristics of the monitoring data changes under attitude control during the propulsion process at the current monitoring point are analyzed. The analysis results are used to obtain the characteristics of attitude changes of the pipe jacking machine at different propulsion stages for different monitoring data. Specifically, it should be noted that the purpose of obtaining the distance matrix based on the set monitoring points and further dividing the time period is to fully consider the differences in environmental impact under different propulsion stages, to accurately analyze the stage-by-stage changes in attitude monitoring data during subsequent model predictive control, and thus optimize the parameters in the actual control process at the monitoring points.

[0043] Therefore, for each divided time period, the sequence formed by arranging each type of monitoring data in chronological order within each time period is taken as the monitoring data sequence for each type of monitoring data within that time period. The Pearson correlation coefficient between each type of monitoring data and all other types of monitoring data within a single time period is calculated. The mean of all Pearson correlation coefficients is taken as the first characteristic value of each type of monitoring data within a single time period. This first characteristic value reflects the coupling characteristic between the monitoring data and other monitoring data in the current time period. The coefficient of variation of all data in the monitoring data sequence for each type of monitoring data is calculated. The larger the coefficient of variation, the more significant the response of the corresponding monitoring data to the changes in the attitude of the pipe jacking machine in the current time period. The calculation of the Pearson correlation coefficient and the coefficient of variation are well-known techniques, and the specific process will not be elaborated further.

[0044] Furthermore, for each time period, if a change in the attitude of the tunnel jacking machine leads to a drastic change in one type of monitoring data relative to other monitoring data, given their strong coupling characteristics, then the current monitoring data will show a more significant response to the attitude change of the tunnel jacking machine at that current stage. Therefore, the product of the coefficient of variation of all data for a single type of monitoring data within a single time period and the first eigenvalue is used as the significance value of the influence of that single type of monitoring data within that single time period, characterizing the degree to which the monitoring data is significantly affected by the attitude change of the tunnel jacking machine at the current time period.

[0045] As a preferred implementation, based on the significant impact value of a single type of monitoring data in a single time period, the difference between a single type of monitoring data and its preset value in a single time period, and the difference between the difference between a single type of monitoring data and its preset value in a single time period and other types of monitoring data in a single time period, the change response characteristic value of a single type of monitoring data in a single time period is obtained, which is used to characterize the degree of response of a single type of monitoring data to the attitude deviation of the pipe jacking machine in a single time period.

[0046] In this embodiment, the first The monitoring data in the first The change response characteristic value over a time period is denoted as . Its specific expression is: In the formula, Indicates the first The monitoring data in the first The change response characteristic value over a time period; Indicates the first The monitoring data in the first The significant value of the impact over a time period; and They represent the first The monitoring data in the first The and the first The mean of the absolute differences between all monitoring data and their corresponding preset values ​​over a given time period; This represents the total number of time periods within the monitoring period containing the y-th time period. It should be noted that in the actual application of the pipe jacking machine, a preset value needs to be set for each type of monitoring data based on the actual on-site exploration results. This preset value is a standard value for each type of monitoring data that is automatically set by the pipe jacking machine during actual operation based on the on-site exploration results. The specific value is set according to the exploration results of the actual application scenario.

[0047] Calculated The larger the value, the more likely it is to be in the first... The first time period The greater the responsiveness of the change characteristics of the monitoring data to the attitude deviation of the pipe jacking machine, the more accurate the attitude control prediction and analysis of the pipe jacking machine under the y-th time period will be.

[0048] Step 4: Based on the total number of data and change response characteristic values ​​of a single type of monitoring data in each time period of a single monitoring period, obtain the moving time window parameters of the single type of monitoring data in a single monitoring period, and then use the model predictive control algorithm to control the monitoring data in the attitude control process of the pipe jacking machine.

[0049] Through the above steps, firstly, considering the environmental differences in the different propulsion processes within the working environment of the pipe jacking machine, monitoring points for optimizing the attitude control of the pipe jacking machine were set. Based on the set monitoring points, the differences in the stage-by-stage attitude changes generated during the actual control process were analyzed, and then the time periods of different monitoring data in response to attitude changes were accurately divided. Based on the divided time periods, the response characteristics of different monitoring data to attitude deviations caused by changes in the propulsion process during the operation of the pipe jacking machine were analyzed, and then the accuracy of the prediction control duration of different monitoring data for the attitude control of the pipe jacking machine was accurately analyzed.

[0050] Furthermore, in the actual monitoring process, for one type of monitoring data, if the amount of data in a single time period is large, that is, the corresponding time period is long, and the response characteristics to the changes in attitude deviation caused by the changes in the advancement process are more significant within that time period, it indicates that the current monitoring data has significant attitude change response characteristics over a long time range during the operation of the pipe jacking machine. Therefore, a larger moving window should be set for predictive analysis to analyze its trend characteristics over a relatively long period of time, thereby achieving accurate prediction analysis and control of attitude information.

[0051] In a preferred embodiment, the moving time window parameter of a single type of monitoring data within a single monitoring period is obtained based on the total number of data points and the change response characteristic values ​​of that data point across different time intervals within a single monitoring period. The flowchart for obtaining the moving time window parameter of a single type of monitoring data within a single monitoring period is shown below. Figure 2 As shown.

[0052] In this embodiment, the first The moving time window parameter of the monitoring data in a single monitoring period is denoted as: The specific calculation formula is as follows: In the formula, Indicates the first The moving time window parameter of the monitoring data within a single monitoring period; Indicates the first The monitoring data in the first The number of data points within a given time period; Indicates the first The monitoring data in the first The change response characteristic value over a time period Indicates the first The summation of the change response characteristic values ​​of a type of monitoring data across all time periods within a single monitoring period; This represents the total number of time periods within the monitoring period containing the y-th time period.

[0053] It should be noted that the aforementioned moving time window parameter refers to the length of the moving time window for predicting each type of data in the MPC (Model Predictive Control) algorithm, i.e., the corresponding number of predicted data. If the response of the monitoring data to attitude changes during the operation of the pipe jacking machine is significant over a relatively long period of time, then at the last moment of the current monitoring period, a larger moving time window should be set for the model predictive control of the monitoring data to analyze its trend characteristics over a relatively long period of time, thereby optimizing and adjusting the model prediction parameters in the attitude control process of the pipe jacking machine.

[0054] Furthermore, the attitude monitoring and control of the pipe jacking machine in this application is implemented using the MPC algorithm. Specifically, a model prediction algorithm is used to perform feedback control analysis on each type of monitoring data during the attitude control process of the pipe jacking machine. During the operation of the pipe jacking machine, each time it passes a monitoring point, the moving time window parameter of each type of monitoring data within the corresponding monitoring period at that monitoring point is obtained through the above steps. The obtained moving time window parameter can fully reflect the changes in the geological environment under different advancement processes, as well as the differences in the response characteristics of each monitoring data to the attitude control of the pipe jacking machine. The calculated moving time window parameter of each type of monitoring data in a single monitoring period is used as the moving time window length for the MPC algorithm to predict each type of monitoring data in a single monitoring period, thereby optimizing the operating attitude of the pipe jacking machine. By implementing rolling optimization adjustments through the monitoring period and combining them with a feedback correction mechanism, the impact of environmental disturbances and system uncertainties can be effectively compensated, thereby achieving precise control of the attitude of the pipe jacking machine and ensuring the safety and efficiency of the construction process. The detailed predictive control implementation process of the MPC algorithm is well known to those skilled in the art and will not be described in detail here.

[0055] Based on the same inventive concept as the above methods, this application also provides a pipe jacking machine attitude control system for municipal engineering construction, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described methods for controlling the attitude of a pipe jacking machine in municipal engineering construction.

[0056] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0057] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0058] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for controlling the posture of a pipe jacking machine in municipal engineering construction, characterized in that, The method includes the following steps: Real-time acquisition of various monitoring data during the operation of the pipe jacking machine; The set of all monitoring data at each time point is taken as the monitoring data set at each time point; the monitoring time is evenly divided into multiple monitoring periods, and the distance matrix of each monitoring period is obtained based on the distance between the monitoring data sets at all times within each monitoring period; irrelevant variables in a single distance matrix are obtained, and the monitoring period corresponding to the distance matrix is ​​divided into multiple time periods based on the time points corresponding to the irrelevant variables; Based on the dispersion of a single type of monitoring data within a single time period and its correlation with other types of monitoring data, the significant impact value of a single type of monitoring data within a single time period is obtained; and by combining the difference between a single type of monitoring data and its preset value within a single time period, and the difference between the difference between a single type of monitoring data and its preset value with other types of monitoring data within a single time period, the change response characteristic value of a single type of monitoring data within a single time period is obtained. Based on the total number of data and change response characteristic values ​​of a single type of monitoring data in each time period of a single monitoring period, the movement time window parameters of the single type of monitoring data in a single monitoring period are obtained, and then the monitoring data in the attitude control process of the pipe jacking machine are controlled by the model predictive control algorithm.

2. The posture control method for pipe jacking machines in municipal engineering construction as described in claim 1, characterized in that, The specific process for obtaining the distance matrix for each monitoring period is as follows: A distance matrix for a single monitoring period is constructed based on the Euclidean distance between the monitoring data sets of any two times within a single monitoring period. The distance matrix for the single monitoring period contains the distance matrix for the [missing information - likely a specific time period]. Line number The column element is the first [element] within a single monitoring period. The moment and the first The Euclidean distance between the monitoring data sets at each time point.

3. The method for controlling the posture of a pipe jacking machine in municipal engineering construction as described in claim 1, characterized in that, The specific process for obtaining irrelevant variables in a single distance matrix is ​​as follows: Principal component analysis (PCA) is used to obtain irrelevant variables in a single distance matrix.

4. The posture control method for pipe jacking machines used in municipal engineering construction as described in claim 2, characterized in that, The specific process of dividing the monitoring period corresponding to the distance matrix into multiple time periods is as follows: the two moments corresponding to each irrelevant variable are recorded as the abrupt change moments of the corresponding distance matrix; the monitoring period corresponding to the distance matrix is ​​divided into multiple time periods using all the abrupt change moments of the distance matrix.

5. The posture control method for a pipe jacking machine in municipal engineering construction as described in claim 1, characterized in that, The process for obtaining the significance value of the single type of monitoring data within a single time period is as follows: The sequence formed by sorting each type of monitoring data in chronological order within a single time period is taken as the monitoring data sequence for each type of monitoring data within the single time period. Calculate the Pearson correlation coefficient between a single type of monitoring data and other types of monitoring data within a single time period, and use the mean of all Pearson correlation coefficients as the first characteristic value of the single type of monitoring data within a single time period. The product of the coefficient of variation of all data for a single type of monitoring data within a single time period and the first eigenvalue is taken as the significance value of the single type of monitoring data within a single time period.

6. The method for controlling the posture of a pipe jacking machine in municipal engineering construction as described in claim 1, characterized in that, The formula for calculating the change response characteristic value of the single type of monitoring data in a single time period is: In the formula, Indicates the first The monitoring data in the first The change response characteristic value over a time period; Indicates the first The monitoring data in the first The significant value of the impact over a time period; and They represent the first The monitoring data in the first The and the first The mean of the absolute differences between all monitoring data and their corresponding preset values ​​over a given time period; This represents the total number of time periods within the monitoring period containing the y-th time period.

7. The posture control method for a pipe jacking machine in municipal engineering construction as described in claim 6, characterized in that, The preset values ​​are standard values ​​for each type of monitoring data that are automatically set by the pipe jacking machine during actual operation based on the results of on-site exploration.

8. The posture control method for a pipe jacking machine in municipal engineering construction as described in claim 1, characterized in that, The formula for calculating the moving time window parameter of the single type of monitoring data in a single monitoring period is as follows: In the formula, Indicates the first The moving time window parameter of the monitoring data within a single monitoring period; Indicates the first The monitoring data in the first The number of data points within a given time period; Indicates the first The monitoring data in the first The change response characteristic value over a time period Indicates the first The summation of the change response characteristic values ​​of a type of monitoring data across all time periods within a single monitoring period; This represents the total number of time periods within the monitoring period containing the y-th time period.

9. The method for controlling the posture of a pipe jacking machine in municipal engineering construction as described in claim 1, characterized in that, The specific process of using the model predictive control algorithm to control the monitoring data in the attitude control process of the pipe jacking machine is as follows: the calculated moving time window parameter of each monitoring data in a single monitoring period is used as the moving time window length for the MPC algorithm to predict each monitoring data in a single monitoring period, and the operating attitude of the pipe jacking machine is optimized and controlled.

10. A posture control system for a pipe jacking machine used in municipal engineering construction, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the pipe jacking machine attitude control method for municipal engineering construction as described in any one of claims 1-9.

Images