Method for identifying data stable section in shield tunneling process

Abstract

The embodiment of the invention relates to the field of electric digital data processing, in particular to a method for identifying a data stable section in a shield tunneling process. The method for identifying the data stable section in the shield tunneling process provided by the embodiment of the invention comprises the following steps: S10: acquiring data in the shield tunneling process; s20, determining effective cycle data of a tunneling cycle in the data; s30, propulsive force and cutterhead torque in the effective circulation data are determined; s40, determining an initial data stable section according to the propulsive force and the cutterhead torque; and S50, eliminating abnormal values of the initial data stable segment, carrying out trend fitting, and determining a final data stable segment. By determining the propulsive force and cutterhead torque data in effective circulation of shield tunneling, the data stable section is jointly determined by various parameters, abnormal values in the data stable section are removed, the recognition precision of the data stable section is improved, and a high-quality data basis can be provided for subsequent construction evaluation or geological analysis.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of electric digital data processing, in particular to a method for identifying a data stable section of a shield tunneling process. BACKGROUND

[0002] The statements herein are merely provided to give a basic understanding of the application, and do not necessarily constitute the prior art.

[0003] During tunneling, a shield machine can collect various construction parameters in real time, which can reflect the dynamic changes of the construction process and also contain multi-source information reflecting stratum conditions, tunneling states and surrounding rock characteristics. Analyzing these construction parameters can help analyze the geological environment and further determine the tunnel construction state.

[0004] To improve the usability and analysis accuracy of construction parameter data, representative push stable section data is usually selected for processing. The push stable section refers to a typical interval where the shield machine is in a stable tunneling state and is less disturbed by external interference. Stable section data can more truly reflect the properties of surrounding rock and the construction state. SUMMARY

[0005] In the following, a brief summary of the present application is given to provide a basic understanding of some aspects of the present application. It should be understood that this summary is not an exhaustive overview of the present application. It is not intended to identify key or important parts of the present application nor is it intended to limit the scope of the present application. Its purpose is merely to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.

[0006] Embodiments of the present application provide a method for identifying a data stable section of a shield tunneling process, comprising the following steps: S10: obtaining data of a shield tunneling process; S20: determining valid cycle data of a tunneling cycle in the data; S30: determining push force and cutter torque in the valid cycle data; S40: determining an initial data stable section according to the push force and the cutter torque; S50: eliminating outliers of the initial data stable section and performing trend fitting to determine a final data stable section.

[0007] The method for identifying a data stable section of a shield tunneling process provided by embodiments of the present application determines the push force and cutter torque data in the valid cycle of the shield tunneling, so that the data stable section is determined by multiple parameters, and then outliers are eliminated, improving the accuracy of data stable section identification and providing a high-quality data basis for subsequent construction evaluation or geological analysis. BRIEF DESCRIPTION OF DRAWINGS

[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 is also to be noted that, in order not to obscure the application with unnecessary detail, only the structures and / or processing steps that are directly related to the solution according to the application are shown in the drawings, while other details that are less relevant to the application are omitted.

[0012] The following disclosure provides a plurality of different embodiments or examples for implementing the present application. In order to simplify the disclosure of the present application, the components and methods of specific examples are described below. Of course, they are only examples and the purpose is not to limit the present application. In the description of the embodiments of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless explicitly and specifically limited.

[0013] At present, the identification of the stable stage mainly relies on artificial experience or screening methods based on single parameter threshold, such as selecting the thrust, penetration or cutter head speed. However, such methods are difficult to fully reflect the overall stability of the tunneling process, have poor response to sudden situations or construction interference, and depend on artificial setting of experience threshold, lack of unified stability criterion and standardized processing procedures, and are difficult to adapt to complex and variable geological and construction conditions.

[0014] Figure 1 is a schematic diagram of the fluctuation of construction data with time in the process of shield tunneling, as shown in Figure 1 The shield construction process has significant stage characteristics, and the data changes reflect multiple working condition stages. The parameters of each stage show strong non-stationarity and high volatility. Moreover, under complex geological conditions or long-distance continuous tunneling, there are often noise interference, abnormal fluctuations and trend changes in the data, increasing the difficulty of data analysis and stable stage extraction.

[0015] In view of the above problems, the embodiments of the present application provide a method for identifying a data stable stage in a shield tunneling process, which comprises the following steps: S10: acquiring data of the shield tunneling process; S20: determining effective cycle data of a tunneling cycle in the data; S30: determining the thrust and the cutter head torque in the effective cycle data; S40: determining an initial data stable stage according to the thrust and the cutter head torque; S50: eliminating outliers of the initial data stable stage and performing trend fitting to determine a final data stable stage.

[0016] The method for identifying a data stable stage in a shield tunneling process provided by the embodiments of the present application determines the thrust and the cutter head torque data in the effective cycle of shield tunneling, so that the data stable stage is determined by multiple parameters, and then the outliers are eliminated, improving the accuracy of data stable stage identification and providing a high-quality data basis for subsequent construction evaluation or geological analysis.

[0017] Figure 2is a schematic diagram of a single obvious data stable segment obtained by the method provided by the embodiment of the present application, Figure 3 is a schematic diagram of multiple obvious data stable segments obtained by the method provided by the embodiment of the present application, Figure 4 is a schematic diagram of non-obvious data stable segments obtained by the method provided by the embodiment of the present application, Figure 5 is a schematic diagram of very non-obvious data stable segments obtained by the method provided by the embodiment of the present application, in some embodiments, as Figures 2-5 indicated, Figures 2-5 shows a construction data structure based on time division, wherein the red data points represent the data of the corresponding propelling force (in Figures 2-5 , represented by total propelling force) at each time point, and the blue data points represent the data of the corresponding cutter head torque at each time point.

[0018] In some embodiments, as Figure 2 indicated, within the part of the period shown in the figure, the propelling force (total propelling force) data and the cutter head torque data continuously present small fluctuation changes, indicating that a single obvious data stable segment is contained therein.

[0019] In some embodiments, as Figure 3 indicated, within the period shown in the figure, the total propelling force data and the cutter head torque data intermittently present small fluctuation changes within multiple short time periods, indicating that multiple obvious data stable segments are contained therein.

[0020] In some embodiments, as Figure 4 indicated, within the period shown in the figure, the total propelling force data and the cutter head torque data present changes that tend to be stable after frequent fluctuations, indicating that the data stable segments contained therein are not obvious.

[0021] In some embodiments, as Figure 5 indicated, within the period shown in the figure, the cutter head torque data presents frequent fluctuation changes, and the total propelling force data is not synchronized with the changes of the cutter head torque data, indicating that the data stable segments contained therein are very non-obvious.

[0022] Figure 6 is a schematic diagram of the segmentation of the data in Figure 2 by the method provided by the embodiment of the present application, Figure 7 is a schematic diagram of the identification of the data stable segments in Figure 3 by the method provided by the embodiment of the present application, Figure 8 is a schematic diagram of the identification of the data stable segments in Figure 4 by the method provided by the embodiment of the present application, Figure 9 is a schematic diagram of the identification of the data stable segments in Figure 5a schematic diagram of the data stable segment in the data, in some embodiments, as shown in Figures 6-9 the method for identifying the data stable segment of the shield tunneling process provided by the embodiments of the present application identifies Figures 2-5 the data stable segment in the segmented construction data, shows the position of the data stable segment, and shows the stability of the data curve.

[0023] In some embodiments, as shown in Figure 6 , Figure 2 the pink part of the construction data in the time period changes slightly around the same stable segment mean line, the pink part is identified as a stable segment, and there are a small number of discrete values in the cutter torque data; a small part of the construction data in the shaded part shows a rapid upward trend, the shaded part is identified as an upward segment, indicating Figure 2 the data stable segment in the data is long and single.

[0024] In some embodiments, as shown in Figure 7 , Figure 3 a small part of the construction data in the shaded part in the time period shows a rapid upward trend, the shaded part is identified as an upward segment; the orange and pink parts of the construction data each change slightly around the stable segment mean line, the orange and pink parts are identified as stable segments, and there are a small number of discrete values deviating from the mean line in the cutter torque data and the total thrust data, indicating Figure 3 there are multiple obvious data stable segments in the data.

[0025] In some embodiments, as shown in Figure 8 , Figure 4 there are two shaded parts in the time period, and the data in the shaded parts shows a rapid upward trend, the shaded parts are identified as upward segments; the orange, pink, light green, and dark green parts of the construction data each change slightly around the stable segment mean line, the orange, pink, light green, and dark green parts are identified as stable segments; in the stable segments of the orange and dark green data, there are a small number of discrete values deviating from the mean line in the cutter torque data and the total thrust data, indicating Figure 4 Although the data stable segment in the data is not obvious in the sense, it can still be divided into multiple data stable segments by different mean lines.

[0026] In some embodiments, as shown in Figure 9 , Figure 5 the data in the shaded part in the time period shows a rapid upward trend, the shaded part is identified as an upward segment; the orange, pink, light green, dark green, purple, and brown parts of the construction data each change slightly around the stable segment mean line, the orange, pink, light green, dark green, purple, and brown parts are identified as stable segments; in the stable segments of the dark green, purple, and brown data, there are a small number of discrete values deviating from the mean line in the cutter torque data and the total thrust data, indicating Figure 5Although the data in the figure is intuitively not very obvious, the data stable segments can still be divided into multiple data stable segments by different mean lines.

[0027] In some embodiments, as shown in FIG. 6, although the construction data in the shield tunneling process presents different fluctuation states after being divided into construction cycles, the method provided by the embodiments of the present application effectively utilizes the coupling relationship between multiple parameters, and can still identify data stable segments with different lengths, avoid missing data stable segments, and comprehensively reflect the overall stable state of the tunneling process. Figures 6-9 As shown in FIG. 6, although the data in the shadow part is less, the method provided by the embodiments of the present application can accurately identify the rising segment represented by the data, and avoid the interference of the rising segment data on the identification of the data stable segment. Figures 6-9 As shown in FIG. 6, the method provided by the embodiments of the present application can identify data stable segments that are not very obvious, and can adapt to the data processing needs of complex working conditions. Figure 9

[0028] In some embodiments, the data obtained in S10 includes the thrust, cutter torque, cutter speed, penetration, and tunnel advancing length. In S20, the following steps are further included: S21: determining that the shield machine is in the tunneling state according to the obtained data of the thrust, cutter torque, cutter speed, penetration, and tunnel advancing length; S22: determining the effective cycle data according to the tunneling process, tunnel advancing length, and sampling time of the data. Obtaining multiple parameters such as the thrust, cutter torque, cutter speed, penetration, and tunnel advancing length can filter effective data from different angles according to multiple parameter values, thereby improving the accuracy of judging the tunneling process of the shield machine. In combination with the tunneling process, tunnel advancing length, and data sampling time, the division of the effective cycle is more accurate.

[0029] In some embodiments, in S21, the state of the thrust, cutter torque, cutter speed, penetration, and tunnel advancing length can be determined by using a state discrimination function, and the shield machine is determined to be in the tunneling state according to the state. In this way, the construction state of the shield machine can be determined by multiple parameters, and the effectiveness of the filtered parameters can be ensured. The state discrimination function can determine one or more of the thrust, cutter torque, cutter speed, penetration, and tunnel advancing length to be positive or negative.

[0030] In some embodiments, in S21, the product of the thrust, cutter torque, cutter speed, penetration, and tunnel advancing length can be determined. When the product is positive, the shield machine is determined to be in the tunneling state, and the data of the thrust, cutter torque, cutter speed, penetration, and tunnel advancing length in the tunneling state are reserved as candidate data for subsequent stable segments.

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

[0032] In some embodiments, in the step S22, the tunnel advancing length is in a predetermined range (for example, 0.3m-1.8m) and the sampling time of the data is greater than a predetermined value (for example, 180 seconds), the effective cycle data is determined, and in this way, the effective cycles are divided.

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

[0034] In some embodiments, in the step S40, the step further comprises the following steps: S41: normalizing the advancing force and the cutter torque; S42: sampling the advancing force and the cutter torque after the normalization in the step S41 with a fixed interval and determining the standard deviations thereof; and S43: determining the initial data stable section according to the standard deviations. Since the numerical scales of the advancing force and the cutter torque are greatly different, the normalization of the two can unify the scales and facilitate the subsequent processing; by determining the standard deviations of the samples, the data fluctuation and the dispersion degree in each time period can be quantified, which is helpful for classifying the normalized data.

[0035] In some embodiments, in the step S41, the normalization is performed in the following way: S411: determining the maximum value and the minimum value in the advancing force and the cutter torque and the difference between the maximum value and the minimum value; S412: determining the difference between each value in the advancing force and the cutter torque and the minimum value; and S413: determining the normalized value of each data in the advancing force and the cutter torque according to the value determined in the step S411 and the value determined in the step S412. Through the maximum and minimum value processing, the calculation amount of the normalization can be reduced and the processing efficiency can be improved.

[0036] In some embodiments, in the step S413, the normalized value can be determined according to the quotient of the value determined in the step S412 and the value determined in the step S411, which can unify the data scale distribution.

[0037] In some embodiments, in the step S43, the initial data stable section is determined when the standard deviation is less than a predetermined value and a plurality of consecutive standard deviations are less than the predetermined value. Retaining the standard deviation less than the predetermined value can eliminate the abnormal values of the data, so that the data distribution of the initial data stable section is more concentrated and the data quality is improved.

[0038] In some embodiments, in the step S42, the following steps can be included: S421: determining a predetermined sampling number (e.g., 30); S422: continuously sampling the normalized result according to the predetermined sampling number and the valid cycle data; and S423: determining a plurality of standard deviations according to the continuously sampled result. By continuously sampling the normalized data, it can be identified whether each sampling belongs to the initial data stable segment in the process of continuous sampling, so as to prevent missing of valid data.

[0039] In some embodiments, in the step S43, the following steps can be further included: S431: determining a predetermined standard deviation threshold (e.g., 0.09); S432: the candidate stable segment is the standard deviation lower than the predetermined standard deviation threshold; and S433: merging the candidate stable segments to obtain the initial data stable segment. Eliminating the data with the standard deviation not less than the predetermined standard deviation threshold can eliminate the discrete data in the initial data stable segment.

[0040] In some embodiments, in the step S43, short time periods with a duration less than 60 seconds can be further eliminated to avoid interference with subsequent data processing.

[0041] In some embodiments, in the step S50, the following steps can be further included: S51: eliminating outliers in the initial data stable segment by using the interquartile range method; S52: determining the relationship between the thrust and the cutter torque and time; and S53: determining the final data stable segment according to the relationship determined in the step S52. Eliminating outliers in the initial data stable segment by using the interquartile range method can further remove individual discrete data in the initial data stable segment, improve the data quality of the final data stable segment, and make it more stable.

[0042] In some embodiments, in the step S52, the relationship between the thrust and the cutter torque conforms to the following expressions: TH(t) = β TH ×t + α TH ; TOR(t) = β TOR ×t + α TOR ; wherein t represents time; TH(t) represents the value of the thrust at t time; TOR(t) represents the value of the cutter torque at t time; β TH represents the slope of the thrust changing with time; α TH represents the intercept of the thrust; β TOR represents the slope of the cutter torque changing with time; and α TOR represents the intercept of the cutter torque. In this way, the relationship between the thrust and the cutter torque and the propulsion time can be quantified, which is helpful to effectively determine the data stable segment.

[0043] In some embodiments, in the step S52, the following steps can be further included: S521: determining β TH and α TH by fitting; S522: determining β TOR and α TOR by fitting; and S523: determining the final data stable segment according to the relationship between the thrust and the cutter torque and time.TH and the value of β TOR ; S522: determining the final data stable segment according to the value of β TH , the value of β TOR and a predetermined slope threshold. By comparing the slope of the fitting result, the trend of the initial data stable segment can be quantified to determine whether it is the final data stable segment.

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

[0045] In some embodiments, the predetermined slope threshold can be set to 2, so that the slope of the valid data stable segment does not exceed 2, ensuring that it does not have a significant monotonic trend, so that the finally determined data stable segment is stable and valid.

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

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

[0048] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of identifying a data stable section of a tunneling process, characterized in that, It comprises the following steps: S10: obtaining data of the tunneling process of the shield tunneling machine; S20: determining effective cycle data of a tunneling cycle in the data; S30: determining a thrust force and a cutter head torque in the effective cycle data; S40: determining an initial data stable section according to the thrust force and the cutter head torque; S50: eliminating outliers of the initial data stable section and performing trend fitting to determine a final data stable section.

2. The method according to claim 1, wherein the data obtained in the step S10 comprises a thrust force, a cutter head torque, a cutter head rotating speed, a penetration and a tunnel advancing length. In the step S20, the following steps are further included: S21: determining that the shield tunneling machine is in a tunneling state according to the obtained data of the thrust force, the cutter head torque, the cutter head rotating speed, the penetration and the tunnel advancing length; S22: determining the effective cycle data according to the tunneling process, the tunnel advancing length and a sampling time of the data.

3. The method according to claim 2, wherein in the step S21, a state determining function is used to determine the state of the thrust force, the cutter head torque, the cutter head rotating speed, the penetration and the tunnel advancing length, and the state of the shield tunneling machine is determined according to the state.

4. The method according to claim 2, wherein in the step S22, the tunnel advancing length is in a predetermined range and the sampling time of the data is greater than a predetermined value, and the effective cycle data is determined.

5. The method according to claim 1, wherein in the step S40, the following steps are further included: S41: performing normalization processing on the thrust force and the cutter head torque; S42: sampling the thrust force and the cutter head torque after the normalization processing in the step S41 with a fixed interval and determining a standard deviation thereof; S43: determining the initial data stable section according to the standard deviation.

6. The method according to claim 5, wherein in the step S41, the normalization processing is performed in the following manner: S411: determining a maximum value and a minimum value in the thrust force and the cutter head torque and a difference between the maximum value and the minimum value; S412: determining a difference between each value in the thrust force and the cutter head torque and the minimum value; S413: determining a normalized value of each data in the thrust force and the cutter head torque according to the value determined in the step S411 and the value determined in the step S412.

7. The method according to claim 5, wherein in the step S43, the standard deviation is determined to be less than a predetermined value, and a plurality of continuous standard deviations are determined to be less than the predetermined value, and the initial data stable section is determined.

8. The method according to claim 1, wherein in the step S50, the following steps are further included: S51: eliminating outliers of the initial data stable section by using a quartile range method; S52: determining a relationship between the thrust force and the cutter head torque and time; S53: determining the final data stable section according to the relationship determined in the step S52. ​ ​ ​ ​ ​ ​ ​ ​ 9. The method of claim 8, wherein, In step S52, the relationship between the thrust force and the cutterhead torque is in accordance with the following expression: TH(t) = β TH × t + α TH ; TOR(t) = β TOR × t + α TOR ; wherein t represents the time; TH(t) represents the value of the thrust force at time t; TOR(t) represents the value of the cutterhead torque at time t; β TH represents the slope of the change of the thrust force with time; a TH represents the intercept of the thrust force. β TOR represents the slope of the disc torque over time; α TOR represents the disc torque intercept.

10. The method of claim 9, wherein, determining the values of the β TH and the β TOR by means of a fitting. According to the value of the beta TH , the value of the beta TOR and a predetermined slope threshold, a final data stable segment is determined.

11. The method of claim 8, wherein, The thrust force and the cutterhead torque in step S52 are normalized.

Images