Early warning method for deviation of tunneling axis of shield tunneling machine based on data analysis

Abstract

The invention relates to the technical field of shield tunneling machine tunneling axis deviation early warning, and discloses a shield tunneling machine tunneling axis deviation early warning method based on data analysis. According to the method, related data of the shield tunneling machine are collected through a sensing monitoring system, noise is removed from the collected data, abnormal data are deleted, the data format is unified, the deviation value of a shield tunneling machine theoretical tunneling route and the shield tunneling axis is calculated according to the data with the unified format, and the deviation value of the shield tunneling axis is analyzed, researched and judged. Judging whether the deviation exceeds a preset deviation range or not, establishing an early warning rule, determining an early warning level and outputting early warning information and suggestions according to a real-time deviation judgment result, adjusting operation parameters of the shield tunneling machine in real time according to an early warning result, calculating deviation of the tunneling axis of the shield tunneling machine in a data analysis mode, and performing deviation early warning. And errors possibly caused by manual parameter setting are avoided, an effective processing scheme and real-time adjustment suggestions are provided according to the early warning level of the deviation, and the construction safety of the shield tunneling machine is improved.

Description

Technical Field

[0001] The invention relates to the technical field of shield machine tunneling axis deviation early warning, and in particular to a shield machine tunneling axis deviation early warning method based on data analysis. Background Art

[0002] The shield machine's excavation axis is the core reference line in the entire shield tunnel construction process. It is an ideal trajectory planned according to design requirements and determines the shield machine's underground driving path. An accurate axis can ensure that the tunnel is smoothly constructed according to the designed position and depth. If the shield machine deviates from the axis during excavation, it may penetrate low-strength areas, surface buildings or other facilities, causing safety accidents or engineering losses. Therefore, identifying deviations in advance and making corrections can effectively reduce the possibility of accidents and ensure the safety of construction personnel and equipment.

[0003] Currently, many early warning systems still rely on manually set parameters and manual analysis, lacking effective handling solutions and real-time adjustment suggestions for deviations, which reduces the safety of shield machine construction. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a shield machine tunneling axis deviation early warning method based on data analysis, which has the characteristics of collecting shield machine tunneling position, inclination angle, deviation angle, propulsion force and propulsion speed data through a sensor monitoring system, removing noise from the collected data, deleting abnormal data and unifying the data format, calculating the shield machine theoretical tunneling route and the shield machine tunneling axis deviation value according to the data in the unified format, real-time monitoring of the actual tunneling situation of the shield machine, and analyzing and judging the shield machine tunneling axis deviation value to determine whether it exceeds a preset deviation range, establishing early warning rules according to the real-time deviation judgment result, determining the early warning level and outputting early warning information and suggestions, adjusting the operating parameters of the shield machine in real time according to the early warning result, calculating the deviation of the shield machine tunneling axis by data analysis, and performing deviation early warning, thereby avoiding errors that may be caused by manually setting parameters, and proposing effective processing solutions and real-time adjustment suggestions for the warning level of the deviation, thereby improving the safety of shield machine construction and solving the above problems.

[0006] (II) Technical solution

[0007] To achieve the above object, the present invention provides the following technical solution: a shield machine excavation axis deviation early warning method based on data analysis, comprising the following steps:

[0008] S1. Collect the shield machine's excavation position, inclination angle, deviation angle, propulsion force and propulsion speed data through the sensor monitoring system;

[0009] S2, remove data noise from all the data collected in S1, delete abnormal data and unify the data format;

[0010] S3. Calculate the deviation between the theoretical tunneling route of the shield machine and the tunneling axis of the shield machine according to the data in a unified format;

[0011] S4. Monitor the actual tunneling situation of the shield machine in real time, and analyze and judge the deviation value of the tunneling axis of the shield machine to determine whether it exceeds the preset deviation range;

[0012] S5. According to the real-time deviation judgment results, establish warning rules, determine the warning level and output warning information and suggestions;

[0013] S6. Adjust the operating parameters of the shield machine in real time according to the early warning results.

[0014] Preferably, the formula for removing the collected data noise by S2 is as follows:

[0015]

[0016] In the formula, MA(d i ) represents the data after noise removal, k represents the denoising window size, which determines how many data points are used to calculate the moving average, and d i+j Represents the data of the current point and its neighboring points, which is used to calculate the moving average of the current point. j represents the count subscript. It means summing the first data up to the k-1th data. Used to divide the summed value.

[0017] Preferably, the formula for deleting the collected abnormal data in S2 is as follows:

[0018]

[0019] In the formula, |Zx| represents the degree of deviation between the data point and the average value, which is used to determine whether the data is abnormal data, and d i represents the i-th data point in the data set, n represents the total number of data points, and i represents the count subscript. It means to add the first data of the collected data to the nth data. This formula is used to calculate the mean value of the data. It means adding the squared results of all deviations to get the total sum of squared deviations. The square root of this value is used to get the standard deviation. When |Zx| is greater than 2, the data point is considered to be an abnormal data.

[0020] Preferably, the formula for the unified data collection format of S2 is as follows:

[0021] One-hot-vector=0ne-hot-encode(category)

[0022] In the formula, One-hot-vector represents the data after receiving the converted format, and One-hot-encode(category) represents the conversion function, which converts the input data category into a binary unit vector recognized by the computer.

[0023] Preferably, the formula for calculating the theoretical tunneling route of the shield machine according to the unified formatted data in S3 is as follows:

[0024] X theory (t) = X0 + v x *t

[0025] Y theory (t) = Y0 + v y *t

[0026] In the formula, X theory (t) represents the horizontal route of excavation, Y theory (t) represents the longitudinal route of excavation, (X0, Y0) represents the coordinates of the starting point, v x 、v y represents the velocity component in the excavation direction, and t represents the time variable.

[0027] Preferably, the formula for calculating the shield machine tunneling axis deviation value in S3 is as follows:

[0028]

[0029] In the formula, Pclx represents the shield machine excavation axis deviation value, (X actual , Y actual ) represents the actual excavation coordinate, (X theory (t), Y theory (t)) represents the theoretical excavation coordinate.

[0030] Preferably, the S4 analyzes and determines the deviation value of the shield machine's excavation axis to determine whether it exceeds a preset deviation range, in the following manner:

[0031]

[0032] In the formula, Pdjg represents the deviation judgment result. When the absolute value of Pclx is greater than A, the deviation of the shield machine's excavation axis is further analyzed. When the absolute value of Pclx is less than or equal to A, the deviation of the shield machine's excavation axis is within the normal range.

[0033] Preferably, the S5 establishes an early warning rule according to the real-time deviation judgment result, and determines which level the deviation belongs to when the deviation changes:

[0034] When the absolute value of Pclx is less than or equal to A, the shield machine excavation axis deviation is at the no-warning level;

[0035] When the absolute value of Pclx is greater than A and less than or equal to B, the shield machine excavation axis deviation is at the attention level;

[0036] When the absolute value of Pclx is greater than B and less than or equal to C, the shield machine excavation axis deviation is at the warning level;

[0037] When the absolute value of Pclx is greater than C, the shield machine excavation axis deviation is at a serious level.

[0038] Preferably, the S5 formulates corresponding output information and operation suggestions for different warning levels as follows:

[0039] No warning level: normal operation, continue monitoring;

[0040] Attention level: Increase monitoring frequency and record deviation trends;

[0041] Warning level: It is recommended to stop the machine for inspection and analyze the cause;

[0042] Severity level: Shut down immediately, conduct a comprehensive inspection, and request technical support.

[0043] Preferably, the S6 automatically adjusts the main control parameters of the shield machine through the DCS distributed control system according to the warning level, optimizes key parameters such as propulsion force and cutter head speed in real time, and corrects the shield machine's excavation axis when it monitors that the shield machine's excavation axis deviation exceeds a preset range.

[0044] Compared with the prior art, the present invention provides a shield machine excavation axis deviation early warning method based on data analysis, which has the following beneficial effects:

[0045] The present invention collects data on tunneling position, inclination angle, deviation angle, propulsion force and propulsion speed of the shield machine through a sensor monitoring system, removes noise from the collected data, deletes abnormal data and unifies the data format, calculates the deviation value between the theoretical tunneling route of the shield machine and the tunneling axis of the shield machine according to the data in the unified format, monitors the actual tunneling situation of the shield machine in real time, analyzes and judges the deviation value of the tunneling axis of the shield machine to determine whether it exceeds a preset deviation range, establishes early warning rules according to the real-time deviation judgment result, determines the early warning level and outputs early warning information and suggestions, adjusts the operating parameters of the shield machine in real time according to the early warning result, calculates the deviation of the tunneling axis of the shield machine by data analysis, and performs deviation early warning, thereby avoiding errors that may be caused by manually setting parameters, and proposes effective processing solutions and real-time adjustment suggestions for the early warning level of the deviation, thereby improving the safety of shield machine construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the steps of the method of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Many current early warning systems still rely on manual parameter setting and manual analysis, lacking effective processing solutions and real-time adjustment suggestions for deviations, which reduces the safety of shield machine construction. Therefore, a shield machine excavation axis deviation early warning method based on data analysis is proposed. Figure 1 , the method comprises the following steps:

[0049] S1. Collect the shield machine's excavation position, inclination angle, deviation angle, propulsion force and propulsion speed data through the sensor monitoring system;

[0050] Multiple high-precision sensors, such as GNSS positioning system and laser rangefinder, are used to collect the position changes of the shield machine in real time. The inclination angle and deviation angle are measured by inclination sensor and angle sensor to ensure the posture control during the excavation process. The propulsion force and propulsion speed are obtained by pressure sensor and tachometer to ensure that the propulsion performance of the shield machine meets the construction requirements. All data are transmitted to the central control system through the data acquisition module;

[0051] S2, remove data noise from all the data collected in S1, delete abnormal data and unify the data format;

[0052] Among them, the formula for removing the collected data noise is as follows:

[0053]

[0054] Data noise usually comes from sensor errors, environmental interference, etc. After removing the noise, the obtained data is closer to the true value, thereby improving the accuracy of the tunneling status and laying the foundation for subsequent analysis and decision-making. In the formula, MA(d i ) represents the data after noise removal, k represents the denoising window size, which determines how many data points are used to calculate the moving average, and d i+j Represents the data of the current point and its neighboring points, which is used to calculate the moving average of the current point. j represents the count subscript. It means summing the first data up to the k-1th data. It is used to divide the summed value to reduce noise interference, improve the sensitivity of dynamic monitoring, and more quickly identify small deviations in the excavation process, so as to achieve timely warning and reduce potential risks;

[0055] The formula for deleting abnormal data is as follows:

[0056]

[0057] Abnormal data may be caused by equipment failure, human error or system failure. Deleting this data can ensure that the remaining data more truly reflects the excavation trend of the shield machine, making the analysis results more representative and credible. In the formula, |Zx| represents the degree of deviation between the data point and the average value, which is used to determine whether the data is abnormal data, and d i represents the i-th data point in the data set, n represents the total number of data points, and i represents the count subscript. It means to add the first data of the collected data to the nth data. This formula is used to calculate the mean value of the data. It means adding the squared results of all deviations to get the total sum of squared deviations. The square root of this value is used to get the standard deviation. When |Zx| is greater than 2, the data point is considered to be abnormal data. Deleting unnecessary abnormal data can significantly reduce the size of the data set, reduce the complexity of data processing and storage, improve the execution efficiency of the algorithm, and save computing resources.

[0058] The formula for the unified data format is as follows:

[0059] One-hot-vector=0ne-hot-encode(category)

[0060] Data from different sources may use different formats. After the data format is unified, it is possible to achieve seamless integration of various types of data, simplify the data processing process, and improve the operability of the system. In the formula, One-hot-vector represents the data after receiving the converted format, and One-hot-encode(category) represents the conversion function, which converts the input data category into a binary unit vector recognized by the computer. The unified format eliminates the need for additional conversion and processing during data analysis, improves analysis efficiency, and ensures that the data can be presented intuitively during visualization, which is convenient for operators to understand and make decisions;

[0061] S3. Calculate the deviation between the theoretical tunneling route of the shield machine and the tunneling axis of the shield machine according to the data in a unified format;

[0062] The formula for calculating the theoretical tunneling route of the shield machine is as follows:

[0063] X theory (t) = X0 + v x *t

[0064] Y theory (t) = Y0 + v y *t

[0065] The theoretical excavation route is determined according to the design drawings and construction requirements. Calculating a clear theoretical path can provide a clear operation direction and goal for the shield machine, which helps the construction team maintain consistency. In the formula, X theory (t) represents the horizontal route of excavation, Y theory (t) represents the longitudinal route of excavation, (X0, Y0) represents the coordinates of the starting point, v x 、v y It represents the velocity component in the excavation direction, and t represents the time variable. By calculating the theoretical excavation route, it can provide a real-time control basis for the operation of the shield machine, ensuring that the shield machine always runs according to the predetermined route during the excavation process, effectively avoiding the risks caused by deviation from the trajectory;

[0066] The calculation formula of shield machine excavation axis deviation value is as follows:

[0067]

[0068] By calculating the deviation value, the operator can actively adjust the thrust and inclination angle of the shield machine to ensure that it always stays on the ideal route and effectively control the construction accuracy. In the formula, Pclx represents the deviation value of the shield machine's excavation axis, (X actual , Y actual ) represents the actual excavation coordinate, (X theory (t), Y theory(t)) represents the theoretical excavation coordinate. The calculation of the deviation value provides key data support for the intelligent monitoring system. The system can set thresholds and early warning mechanisms. Once the deviation exceeds the allowable range, an alarm will be issued immediately to improve the response speed and processing capability;

[0069] S4. Monitor the actual tunneling situation of the shield machine in real time, and analyze and judge the deviation value of the tunneling axis of the shield machine to determine whether it exceeds the preset deviation range;

[0070] The method for judging whether the preset deviation range is exceeded is as follows:

[0071]

[0072] In the formula, Pdjg represents the deviation judgment result. When the absolute value of Pclx is greater than A, the shield machine excavation axis deviation is further analyzed. When the absolute value of Pclx is less than or equal to A, the shield machine excavation axis deviation is within the normal range. A is the deviation range value set by the system, which is equal to 3. By analyzing the excavation axis deviation value, the operating status of the shield machine can be monitored in real time, providing timely feedback to the construction team, which is conducive to judging whether the shield machine is operating within the preset safety range. The judgment based on data analysis reduces the subjectivity of experience judgment, improves the scientific nature of decision-making, and makes construction management more transparent and efficient.

[0073] S5. According to the real-time deviation judgment results, establish warning rules, determine the warning level and output warning information and suggestions;

[0074] According to the real-time deviation judgment results, establish early warning rules, and when the deviation changes, determine which level it belongs to:

[0075] When the absolute value of Pclx is less than or equal to A, the shield machine excavation axis deviation is at the no-warning level;

[0076] When the absolute value of Pclx is greater than A and less than or equal to B, the shield machine excavation axis deviation is at the attention level;

[0077] When the absolute value of Pclx is greater than B and less than or equal to C, the shield machine excavation axis deviation is at the warning level;

[0078] When the absolute value of Pclx is greater than C, the shield machine excavation axis deviation is at a serious level;

[0079] A, B, and C are the deviation thresholds set by the system, which are 3, 3.5, and 4. By setting early warning rules, the construction team can quickly respond to various excavation conditions to ensure that when deviations occur, necessary control and adjustment measures can be taken quickly to reduce risks. At the same time, the establishment of early warning rules makes the management and response to deviations more detailed. Different response strategies can be set according to the severity of the deviation, which improves the flexibility and pertinence of management.

[0080] For different warning levels, the corresponding output information and operation suggestions are formulated as follows:

[0081] No warning level: normal operation, continue monitoring;

[0082] Attention level: Increase monitoring frequency and record deviation trends;

[0083] Warning level: It is recommended to stop the machine for inspection and analyze the cause;

[0084] Severity level: Shut down the system immediately, conduct a comprehensive inspection, and request technical support;

[0085] The output warning information and suggestions can not only guide construction operations, but also help management to evaluate and manage the overall risks of the project and make emergency plans. Based on the warning feedback and suggestions, the construction party can continuously optimize the operation strategy and construction plan of the shield machine, perform technical iterations, and improve the overall level of future projects.

[0086] S6. Adjust the operating parameters of the shield machine in real time according to the early warning results;

[0087] When it is detected that the deviation of the tunneling axis of the shield machine exceeds the preset range, the distributed control system will respond automatically and collect key parameters such as the position information, posture data and propulsion force of the shield machine in real time through high-precision sensors. These data are analyzed through the integrated monitoring platform to determine the nature and severity of the current deviation. Based on the pre-established early warning rules, the system will automatically calculate the optimal adjustment plan, including adjusting the main control parameters such as propulsion parameters, cutter head speed, propulsion speed and grouting pressure to ensure that the shield machine can return to the predetermined tunneling route in time. At the same time, the system will provide real-time feedback of the adjustment results through a visual interface so that the operator can understand the dynamic image at any time and intervene manually when necessary.

[0088] Through the application of the above method, the deviation of the shield machine's excavation axis is calculated by data analysis, and deviation warning is carried out, avoiding the errors that may be caused by manual setting of parameters. Effective processing solutions and real-time adjustment suggestions are proposed according to the warning level of the deviation, thereby improving the safety of shield machine construction.

[0089] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A shield machine excavation axis deviation early warning method based on data analysis, characterized in that: The following steps are involved: S1. Collect the shield machine's excavation position, inclination angle, deviation angle, propulsion force and propulsion speed data through the sensor monitoring system; S2, remove data noise from all the data collected in S1, delete abnormal data and unify the data format; S3. Calculate the deviation between the theoretical tunneling route of the shield machine and the tunneling axis of the shield machine according to the data in a unified format; S4. Monitor the actual tunneling situation of the shield machine in real time, and analyze and judge the deviation value of the tunneling axis of the shield machine to determine whether it exceeds the preset deviation range; S5. According to the real-time deviation judgment results, establish warning rules, determine the warning level and output warning information and suggestions; S6. Adjust the operating parameters of the shield machine in real time according to the early warning results.

2. The shield machine excavation axis deviation early warning method based on data analysis according to claim 1 is characterized by: The formula for removing the noise from the collected data by S2 is as follows: In the formula, MA(d i ) represents the data after noise removal, k represents the denoising window size, which determines how many data points are used to calculate the moving average, and d i+j Represents the data of the current point and its neighboring points, which is used to calculate the moving average of the current point. j represents the count subscript. It means summing the first data up to the k-1th data. Used to divide the summed value.

3. The shield machine excavation axis deviation early warning method based on data analysis according to claim 2 is characterized by: The formula for deleting the collected abnormal data in S2 is as follows: In the formula, |Zx| represents the degree of deviation between the data point and the average value, which is used to determine whether the data is abnormal data, and d i represents the i-th data point in the data set, n represents the total number of data points, and i represents the counting subscript. It means to add the first data of the collected data to the nth data. This formula is used to calculate the mean value of the data. It means adding the squared results of all deviations to get the total sum of squared deviations. The square root of this value is used to get the standard deviation. When |Zx| is greater than 2, the data point is considered to be an abnormal data.

4. The shield machine excavation axis deviation early warning method based on data analysis according to claim 3 is characterized by: The formula for the unified data collection format of S2 is as follows: One-hot-vector=One-hot-encode(category) In the formula, one-hot-vector represents the data after receiving the converted format, and one-hot-encode(category) represents the conversion function, which converts the input data category into a binary unit vector recognized by the computer.

5. The shield machine excavation axis deviation early warning method based on data analysis according to claim 4 is characterized by: The formula for calculating the theoretical tunneling route of the shield machine according to the data in the unified format in S3 is as follows: X theoty (t)=X0+v x *t Y theory (t)=Y0+v y *t In the formula, X theory (t) represents the horizontal route of excavation, Y theory (t) represents the longitudinal route of excavation, (X0, Y0) represents the coordinates of the starting point, v x 、v y represents the velocity component in the excavation direction, and t represents the time variable.

6. The shield machine excavation axis deviation early warning method based on data analysis according to claim 5 is characterized by: The formula for calculating the deviation value of the shield machine's tunneling axis by S3 is as follows: In the formula, Pclx represents the shield machine excavation axis deviation value, (X actual ,Y actual ) represents the actual excavation coordinate, (X theory (t),Y theory (t)) represents the theoretical excavation coordinate.

7. The shield machine excavation axis deviation early warning method based on data analysis according to claim 6 is characterized by: The S4 analyzes and determines the deviation value of the shield machine's excavation axis to determine whether it exceeds the preset deviation range, in the following manner: In the formula, Pdjg represents the deviation judgment result. When the absolute value of Pclx is greater than A, the deviation of the shield machine's excavation axis is further analyzed. When the absolute value of Pclx is less than or equal to A, the deviation of the shield machine's excavation axis is within the normal range.

8. The shield machine excavation axis deviation early warning method based on data analysis according to claim 7 is characterized by: The S5 establishes warning rules based on the real-time deviation judgment results, and determines which level the deviation belongs to when it changes: When the absolute value of Pclx is less than or equal to A, the shield machine excavation axis deviation is at the no-warning level; When the absolute value of Pclx is greater than A and less than or equal to B, the shield machine excavation axis deviation is at the attention level; When the absolute value of Pclx is greater than B and less than or equal to C, the shield machine excavation axis deviation is at the warning level; When the absolute value of Pclx is greater than C, the shield machine excavation axis deviation is at a serious level.

9. The shield machine excavation axis deviation early warning method based on data analysis according to claim 8 is characterized by: The S5 formulates corresponding output information and operation suggestions for different warning levels as follows: No warning level: normal operation, continue monitoring; Attention level: Increase monitoring frequency and record deviation trends; Warning level: It is recommended to stop the machine for inspection and analyze the cause; Severity level: Shut down immediately, conduct a comprehensive inspection, and request technical support.

10. The shield machine excavation axis deviation early warning method based on data analysis according to claim 9, characterized in that: The S6 automatically adjusts the main control parameters of the shield machine through the DCS distributed control system according to the warning level, optimizes key parameters such as propulsion force and cutter head speed in real time, and corrects the shield machine's excavation axis when it monitors that the shield machine's excavation axis deviation exceeds a preset range.

Images