Methods for identifying data stability segments during shield tunneling

Abstract

The embodiments of this application relate to the field of electronic digital data processing, and particularly to a method for identifying stable data segments in a tunnel boring machine (TBM) process. The method for identifying stable data segments in a TBM process provided by the embodiments of this application includes the following steps: S10: acquiring data from the TBM tunneling process; S20: determining the effective cycle data of the tunneling cycle within the data; S30: determining the thrust and cutterhead torque in the effective cycle data; S40: determining the initial stable data segment based on the thrust and cutterhead torque; S50: removing outliers from the initial stable data segment and performing trend fitting to determine the final stable data segment. By determining the thrust and cutterhead torque data in the effective TBM tunneling cycle, the stable data segment is determined by multiple parameters, thereby removing outliers and improving the accuracy of stable data segment identification. This provides a high-quality data foundation for subsequent construction assessments or geological analyses.

Description

Technical Field

[0001] The embodiments of this application relate to the field of electronic digital data processing, and in particular to a method for identifying data stability segments in a tunnel boring machine (TBM) excavation process. Background Technology

[0002] The statements herein are provided merely as background information in connection with this application and do not necessarily constitute prior art.

[0003] During tunnel excavation, tunnel boring machines collect various construction parameters in real time. These parameters reflect the dynamic changes in the construction process and contain multi-source information reflecting geological conditions, excavation status, and surrounding rock characteristics. Analyzing these construction parameters helps to analyze the geological environment and thus determine the tunnel construction status.

[0004] To improve the usability and accuracy of construction parameter data, representative data from the stable advance section are typically selected for processing. The stable advance section refers to a typical interval where the tunnel boring machine is in a stable excavation state and is less affected by external disturbances. Data from the stable section can more accurately reflect the properties of the surrounding rock and the construction status. Summary of the Invention

[0005] A brief overview of this application is provided below to offer a basic understanding of certain aspects thereof. It should be understood that this overview is not an exhaustive summary of the application. It is not intended to identify key or essential parts of the application, nor is it intended to limit its scope. Its purpose is merely to present certain concepts in a simplified form as a prelude to the more detailed description that follows.

[0006] Embodiments of this application provide a method for identifying a stable data segment in a tunnel boring machine (TBM) process, comprising the following steps: S10: acquiring data of the TBM tunneling process; S20: determining the effective cycle data of the tunneling cycle in the data; S30: determining the thrust and cutterhead torque in the effective cycle data; S40: determining the initial stable data segment based on the thrust and cutterhead torque; S50: removing outliers from the initial stable data segment and performing trend fitting to determine the final stable data segment.

[0007] The method for identifying stable data segments in the shield tunneling process provided in the embodiments of this application determines the propulsion force and cutterhead torque data in the effective shield tunneling cycle, so that the stable data segment is determined by multiple parameters, thereby eliminating outliers and improving the accuracy of stable data segment identification. This provides a high-quality data foundation for subsequent construction assessment or geological analysis. Attached Figure Description

[0008] To further illustrate the above and other advantages and features of this application, the specific embodiments of this application will be described in more detail below with reference to the accompanying drawings. The drawings, together with the following detailed description, are included in and form a part of this specification. Elements having the same function and structure are indicated by the same reference numerals. It should be understood that these drawings only depict typical examples of this application and should not be considered as limiting the scope of this application.

[0009] Figure 1 This is a schematic diagram illustrating the fluctuation of construction data over time during the tunnel boring machine (TBM) excavation process. Figure 2 This is a schematic diagram of a single, clearly defined stable data segment obtained according to the method provided in the embodiments of this application; Figure 3 This is a schematic diagram of multiple distinct data stability segments obtained according to the method provided in the embodiments of this application; Figure 4 This is a schematic diagram showing that the stable data segment is not obvious according to the method provided in the embodiments of this application; Figure 5 This is a schematic diagram showing that the stable data segment obtained according to the method provided in the embodiments of this application is not very obvious; Figure 6 The method provided in the embodiments of this application is for... Figure 2 A diagram illustrating the segmentation of data in the data; Figure 7 It is identified according to the method provided in the embodiments of this application. Figure 3 A schematic diagram of the stable data segment in the data; Figure 8 It is identified according to the method provided in the embodiments of this application. Figure 4 A schematic diagram of the stable data segment in the data; Figure 9 It is identified according to the method provided in the embodiments of this application. Figure 5 A schematic diagram of the stable data segment in the data. Detailed Implementation

[0010] Exemplary embodiments of this application will be described below with reference to the accompanying drawings. For clarity and brevity, not all features of actual implementations are described in the specification. However, it should be understood that many implementation-specific decisions must be made in the development of any such actual embodiment to achieve the developer's specific goals, such as complying with constraints related to the system and business, and these constraints may vary depending on the implementation. Furthermore, it should be understood that while development work can be very complex and time-consuming, such development work is merely a routine task for those skilled in the art who benefit from the content of this application.

[0011] It should also be noted that, in order to avoid obscuring this application with unnecessary details, only the equipment structure and / or processing steps closely related to the solution according to this application are shown in the accompanying drawings, while other details that are not closely related to this application are omitted.

[0012] The following disclosure provides several different implementations or examples for carrying out this application. To simplify the disclosure of this application, specific examples of components and methods are described below. Of course, these are merely examples and are not intended to limit this application. In the description of the embodiments of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0013] Currently, the identification of stable sections in tunneling mainly relies on manual experience or screening methods based on single parameter thresholds, such as selecting thrust, penetration depth, or cutterhead rotation speed. However, these methods are difficult to comprehensively reflect the overall stability of the tunneling process, have poor ability to respond to emergencies or construction disturbances, and depend on manually setting experience thresholds, lacking unified stability criteria and standardized processing procedures, making them difficult to adapt to complex and changing geological and construction conditions.

[0014] Figure 1 This is a schematic diagram illustrating the fluctuations in construction data over time during tunnel boring machine (TBM) excavation, such as... Figure 1 As shown, the tunnel boring machine (TBM) construction process exhibits significant phased characteristics, with data changes reflecting multiple working conditions. The parameters at each stage demonstrate strong non-stationarity and high volatility. Furthermore, under complex geological conditions or long-distance continuous tunneling, the data often contains noise interference, abnormal fluctuations, and trend changes, increasing the difficulty of data analysis and stable segment extraction.

[0015] To address the aforementioned problems, embodiments of this application provide a method for identifying data stability segments in a tunnel boring machine (TBM) process, comprising the following steps: S10: acquiring data from the TBM tunneling process; S20: determining valid cycle data of the tunneling cycle within the data; S30: determining the thrust and cutterhead torque within the valid cycle data; S40: determining an initial data stability segment based on the thrust and cutterhead torque; S50: removing outliers from the initial data stability segment and performing trend fitting to determine the final data stability segment.

[0016] The method for identifying stable data segments in the shield tunneling process provided in the embodiments of this application determines the propulsion force and cutterhead torque data in the effective shield tunneling cycle, so that the stable data segment is determined by multiple parameters, thereby eliminating outliers and improving the accuracy of stable data segment identification. This provides a high-quality data foundation for subsequent construction assessment or geological analysis.

[0017] Figure 2This is a schematic diagram of a single, clearly defined stable data segment obtained according to the method provided in the embodiments of this application. Figure 3 This is a schematic diagram illustrating multiple distinct data stability segments obtained according to the method provided in the embodiments of this application. Figure 4 This is a schematic diagram illustrating that the stable data segment obtained according to the method provided in the embodiments of this application is not obvious. Figure 5 This is a schematic diagram showing that the stable data segment obtained according to the method provided in the embodiments of this application is not very obvious. In some embodiments, such as... Figures 2-5 As shown, Figures 2-5 The construction data structure based on time division is shown, where red data points represent the propulsion force at each time point (in...). Figures 2-5 In the figure, the total thrust is represented by the data, and the blue data points represent the cutterhead torque data at each moment.

[0018] In some embodiments, such as Figure 2 As shown in the figure, during certain time periods, the propulsion (total thrust) data and cutterhead torque data consistently exhibit small fluctuations, indicating that they contain a single, distinct period of data stability.

[0019] In some embodiments, such as Figure 3 As shown in the figure, the total thrust data and cutterhead torque data intermittently exhibit small fluctuations over multiple short time periods during the time period indicated that there are several distinct data stability periods.

[0020] In some embodiments, such as Figure 4 As shown in the figure, during the time period indicated, the total thrust data and cutterhead torque data show a trend of stabilization after frequent fluctuations, indicating that the stable data segments contained within the figure are not obvious.

[0021] In some embodiments, such as Figure 5 As shown in the figure, the cutterhead torque data fluctuates frequently during the time period indicated in the figure, and the changes in total thrust data and cutterhead torque data are not synchronized, indicating that the data stability period contained therein is not very obvious.

[0022] Figure 6 The method provided in the embodiments of this application is for... Figure 2 A diagram illustrating the segmentation of data. Figure 7 It is identified according to the method provided in the embodiments of this application. Figure 3 A schematic diagram of the stable data segment in the data. Figure 8 It is identified according to the method provided in the embodiments of this application. Figure 4 A schematic diagram of the stable data segment in the data. Figure 9 It is identified according to the method provided in the embodiments of this application. Figure 5A schematic diagram of the data stability segment in the middle, in some embodiments, such as Figures 6-9 As shown, the method for identifying data stability segments in the shield tunneling process provided by the embodiments of this application is used to identify... Figures 2-5 The segmented construction data shows the location of the stable data segment and demonstrates the smoothness of the data curve.

[0023] In some embodiments, such as Figure 6 As shown, Figure 2 The pink portion of the construction data within the medium-term period shows slight variations around the mean line of the same stable segment; this pink portion is identified as a stable segment, with a small number of discrete values ​​in the cutterhead torque data. The shaded portion of the construction data shows a small upward trend; this shaded portion is identified as an upward segment, indicating... Figure 2 The data in the middle is relatively stable and singular.

[0024] In some embodiments, such as Figure 7 As shown, Figure 3 During the mid-term, a small portion of the construction data in the shaded area shows a rapid upward trend; this shaded area is identified as the rising segment. The construction data in the orange and pink areas fluctuate slightly around the mean line of the stable segment; these orange and pink areas are identified as the stable segment. Both the cutterhead torque and total thrust data show a small number of discrete values ​​deviating from the mean line, indicating... Figure 3 The data in the data exhibits several distinct stable segments.

[0025] In some embodiments, such as Figure 8 As shown, Figure 4 Within the mid-period, there are two shaded areas where the data shows a rapid upward trend; these shaded areas are identified as the upward segment. The construction data in the orange, pink, light green, and dark green sections fluctuate slightly around the mean line of the stable segment; these orange, pink, light green, and dark green sections are identified as the stable segment. Within the stable segments of the orange and dark green data, there are a small number of discrete values ​​in both the cutterhead torque and total thrust data that deviate from the mean line, indicating... Figure 4 Although the data in the data may not show obvious stable periods at first glance, it can still be divided into multiple stable periods by using different mean lines.

[0026] In some embodiments, such as Figure 9 As shown, Figure 5 During the mid-term, the data in the shaded area shows a rapid upward trend, and this shaded area is identified as the rising segment. The construction data in the orange, pink, light green, dark green, purple, and brown areas each fluctuate slightly around the mean line of the stable segment, and these areas are identified as the stable segment. Within the stable segments of the dark green, purple, and brown data, there are a small number of discrete values ​​in both the cutterhead torque and total thrust data that deviate from the mean line, indicating... Figure 5Although the data in the data may not be clearly stable at first glance, it can still be divided into multiple stable data segments by using different mean lines.

[0027] In some embodiments, such as Figures 6-9 As shown, although the construction data during the tunnel boring machine (TBM) excavation process exhibits different fluctuation states after being divided into construction cycles, the method provided in the embodiments of this application effectively utilizes the coupling relationship between multiple parameters, still able to identify stable data segments of varying lengths, avoiding omissions in stable data segment identification, and comprehensively reflecting the overall stability state of the tunneling process; and, as Figure 6-9 As shown, although the amount of data in the shaded area is relatively small, the method provided by the embodiments of this application can accurately identify the rising segment it represents, avoiding interference from the rising segment data with the identification of the stable data segment; at the same time, as Figure 9 As shown, the method provided by the embodiments of this application can identify data stability segments where data stability segments are not very obvious, and can adapt to the data processing needs of complex working conditions.

[0028] In some embodiments, the data acquired in step S10 includes: thrust, cutterhead torque, cutterhead rotation speed, penetration depth, and tunnel advancement length. Step S20 further includes the following steps: S21: Determine that the tunnel boring machine is in the tunneling state based on the acquired data of thrust, cutterhead torque, cutterhead rotation speed, penetration depth, and tunnel advancement length; S22: Determine valid cycle data based on the tunneling process, tunnel advancement length, and data sampling time. Acquiring multiple parameters such as thrust, cutterhead torque, cutterhead rotation speed, penetration depth, and tunnel advancement length allows for the filtering of valid data from different perspectives based on multiple parameter values, improving the accuracy of judging the tunneling process of the tunnel boring machine. Combining the tunneling process, tunnel advancement length, and data sampling time makes the division of valid cycles more accurate.

[0029] In some embodiments, in step S21, a state discrimination function can be used to determine the state of the thrust, cutterhead torque, cutterhead speed, penetration depth, and tunnel advancement length. Based on the state, it can be determined that the tunnel boring machine is in the tunneling state. This allows for the determination of the tunnel boring machine's construction state through multiple parameters, ensuring the effectiveness of the selected parameters. The state discrimination function can determine whether one or more of the thrust, cutterhead torque, cutterhead speed, penetration depth, and tunnel advancement length are positive or negative.

[0030] In some embodiments, in step S21, the product of thrust, cutterhead torque, cutterhead speed, penetration depth, and tunnel advance length can be determined. When the product is positive, the tunnel boring machine is determined to be in the tunneling state. The data of thrust, cutterhead torque, cutterhead speed, penetration depth, and tunnel advance length in the tunneling state are retained as alternative data for subsequent stable sections.

[0031] In some embodiments, in step S21, the data on tunnel advance length may also be non-decreasingly corrected to ensure the physical rationality of the parameters.

[0032] In some embodiments, in step S22, valid loop data are determined when the tunnel advance length is within a predetermined range (e.g., 0.3m-1.8m) and the data sampling time is greater than a predetermined value (e.g., 180 seconds), and multiple valid loops are divided in this manner.

[0033] In some embodiments, only effective tunneling cycles with a tunneling duration greater than 300 seconds and an advance length between 0.3m and 1.8m can be retained to ensure data representativeness and engineering validity.

[0034] In some embodiments, step S40 further includes the following steps: S41: Normalizing the propulsion force and the cutterhead torque; S42: Sampling the normalized propulsion force and cutterhead torque at fixed intervals and determining their standard deviation; S43: Determining the initial stable data segment based on the standard deviation. Since the numerical scales of the propulsion force and the cutterhead torque differ significantly, normalizing them unifies the scale, facilitating subsequent processing. By determining the standard deviation of the samples, the data fluctuation coefficient and dispersion within each time period can be quantified, which helps in classifying the normalized data.

[0035] In some embodiments, in step S41, normalization is performed as follows: S411: Determine the maximum and minimum values ​​of the propulsion force and the cutterhead torque, and the difference between the maximum and minimum values; S412: Determine the difference between each value of the propulsion force and the minimum value of the cutterhead torque; S413: Based on the values ​​determined in step S411 and step S412, determine the normalized value of each data point of the propulsion force and the cutterhead torque. By processing the maximum and minimum values, the computational load of normalization can be reduced, and the processing efficiency can be improved.

[0036] In some embodiments, in step S413, the value for normalization can be determined based on the quotient of the value determined in step S412 and the value determined in step S411, which can unify the data scale distribution.

[0037] In some embodiments, in step S43, determining that the standard deviation is less than a predetermined value and determining that multiple consecutive standard deviations are less than the predetermined value, an initial stable data segment is determined. Retaining standard deviations less than the predetermined value can eliminate outliers, making the data distribution of the initial stable data segment more concentrated and improving data quality.

[0038] In some embodiments, step S42 may include the following steps: S421: determining a predetermined number of samples (e.g., 30); S422: continuously sampling the normalized result based on the predetermined number of samples and valid cyclic data; S423: determining multiple standard deviations based on the continuous sampling results. By continuously sampling the normalized data, it is possible to identify whether each sample belongs to the initial stable data segment during the continuous sampling process, preventing the omission of valid data.

[0039] In some embodiments, step S43 may further include the following steps: S431: determining a predetermined standard deviation threshold (e.g., 0.09); S432: data with a standard deviation lower than the predetermined standard deviation threshold are candidate stable segments; S433: merging the candidate stable segments to obtain an initial stable data segment. Removing data with a standard deviation not less than the predetermined standard deviation threshold can remove discrete data within the initial stable data segment.

[0040] In some embodiments, in step S43, short periods lasting less than 60 seconds may also be excluded to avoid interference with subsequent data processing.

[0041] In some embodiments, step S50 further includes the following steps: S51: using the interquartile range (ICR) method to remove outliers from the initial stable data segment; S52: determining the relationship between the feed force and the cutterhead torque and time; S53: determining the final stable data segment based on the relationship determined in step S52. Using the ICR method to remove outliers from the initial stable data segment can further remove individual discrete data from the initial stable data segment, improving the data quality of the final stable data segment and making it more stable.

[0042] In some embodiments, in step S52, the relationship between the feed force and the cutterhead torque conforms to the following expression: TH(t) = β TH ×t+α TH TOR(t)=β TOR ×t+α TOR Where t represents time; TH(t) represents the propulsion force at time t; TOR(t) represents the cutterhead torque at time t; β TH The slope representing the change in propulsion force over time; α TH Indicates the thrust intercept; β TOR The slope representing the change of the cutter head torque over time; α TOR This represents the cutterhead torque intercept. This allows for the quantification of the relationship between the propulsion force and the cutterhead torque and the propulsion time, which helps to effectively determine the data stability segment.

[0043] In some embodiments, step S52 may further include the following step: S521: Determine β by fitting.TH and β TOR The value; S522: According to β TH β TOR The final stable data segment is determined by setting the value of the slope and a predetermined slope threshold. By comparing the slopes of the fitting results, the trend of the initial stable data segment can be quantified, making it easier to determine whether it is the final stable data segment.

[0044] In some embodiments, in step S522, β can be... TH and β TOR The value of β is compared with a predetermined slope threshold; based on the comparison result, the monotonic trend state of the initial stable segment is determined. When β TH and β TOR If the absolute value of the slope does not exceed the predetermined slope threshold, and the corresponding initial stable data segment does not have a significant monotonic trend, then it is a valid stable data segment.

[0045] In some embodiments, the predetermined slope threshold can be set to 2 so that the slope of the effective stable data segment does not exceed 2, ensuring that there is no significant monotonic trend, so that the finally determined stable data segment is stable and effective.

[0046] In some embodiments, the propulsion force and cutterhead torque in step S52 are normalized to unify the data distribution scale.

[0047] Regarding the embodiments of this application, it should also be noted that, without conflict, the embodiments of this application and the features in the embodiments can be combined with each other to obtain new embodiments.

[0048] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. The scope of protection of this application shall be determined by the scope of the claims.

Claims

1. A method for identifying data stability segments during shield tunneling, characterized in that, It includes the following steps: S10: Obtain data from the tunnel boring process; S20: Determine the valid cycle data of the tunneling cycle in the data; S30: Determine the propulsion force and cutterhead torque in the effective cycle data; S40: Determine the initial data stabilization segment based on the propulsion force and the cutterhead torque; S50: Remove outliers from the initial stable data segment and perform trend fitting to determine the final stable data segment; Step S40 also includes the following steps: S41: Normalize the propulsion force and the cutter head torque; S42: Sample the normalized propulsion force and the cutterhead torque in step S41 at fixed intervals and determine their standard deviation. S43: Determine the initial stable data segment based on the standard deviation; In step S41, normalization is performed as follows: S411: Determine the maximum and minimum values ​​of the propulsion force and the cutterhead torque, and the difference between the maximum and the minimum values; S412: Determine the difference between each value of the propulsion force and the cutterhead torque and the minimum value; S413: Based on the values ​​determined in step S411 and step S412, determine the normalized value of each data point in the propulsion force and the cutterhead torque; In step S43, it is determined that the standard deviation is less than a predetermined value, and a plurality of consecutive standard deviations are less than the predetermined value, thereby determining the initial data stability segment; The S50 step also includes the following steps: S51: Use the interquartile range method to remove outliers from the initial stable data segment; S52: Determine the relationship between the propulsion force and the cutterhead torque and time; S53: Based on the relationship determined in step S52, determine the final stable data segment; In step S52, the relationship between the propulsion force and the cutterhead torque conforms to the following expression: TH(t)=β TH ×t+a TH ; TOR(t)=β TOR ×t+a TOR ; Where t represents the time; TH(t) represents the value of the propulsion force at time t; TOR(t) represents the value of the cutterhead torque at time t; β TH The slope representing the change in propulsion force over time; α TH Indicates the thrust intercept; β TOR The slope representing the change of the cutter head torque over time; α TOR Indicates the cutter head torque intercept; The β is determined by fitting. TH and the β TOR The value; According to the β TH The β TOR The final stable data segment is determined by the value of the slope and the predetermined slope threshold.

2. The method according to claim 1, characterized in that, The data obtained in step S10 includes: thrust, cutterhead torque, cutterhead rotation speed, penetration depth, and tunnel advancement length; Step S20 also includes the following steps: S21: Based on the obtained data on thrust, cutterhead torque, cutterhead speed, penetration depth, and tunnel advancement length, determine that the tunnel boring machine is in the tunneling state; S22: Determine the effective cyclic data based on the tunneling process, the tunnel advancement length, and the data sampling time.

3. The method according to claim 2, characterized in that, In step S21, the states of the propulsion force, cutterhead torque, cutterhead rotation speed, penetration depth, and tunnel advancement length are determined using a state discrimination function. Based on the stated status, it is determined that the tunnel boring machine is in the tunneling state.

4. The method according to claim 2, characterized in that, In step S22, the effective cyclic data is determined when the tunnel advancement length is within a predetermined range and the data sampling time is greater than a predetermined value.

5. The method according to claim 1, characterized in that, The propulsion force and the cutterhead torque in step S52 have been normalized.

Images