A shield construction status prediction method

Abstract

The present invention relates to the field of shield construction technology, and more particularly to a method for predicting shield construction status. The prediction model constructed by the present invention is trained using construction data before a preset construction node, and then the geological conditions of the ring to be measured are determined by identifying a longitudinal geological fill map. The geological conditions of the ring to be measured are input into the prediction model to obtain the operating parameter data of the shield machine in the ring to be measured. The present invention can predict the construction status of the shield machine during subsequent construction. Users can achieve the desired effect by setting the operating parameters of the shield machine based on the prediction results, thereby improving work efficiency and solving the technical problem of low shield construction efficiency in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of shield construction, and in particular to a shield construction state prediction method. Background Art

[0002] Nowadays, the construction of shield tunneling machinery and equipment in my country's railway, highway, municipal, flood control, hydropower and other tunnel engineering applications is gradually increasing, and the demand for underground engineering equipment is growing. Due to the various complex operating environments such as ultra-large diameter, ultra-long distance, deep burial, high pressure, and variable geology, the requirements for equipment selection and construction methods are extremely high. As the country's requirements for environmental protection, engineering quality, occupational health, etc. are getting higher and higher, the development of tunnel construction equipment towards automation and intelligence has become an inevitable trend in the industry. The diversity and variability of geological conditions during the construction process often make it impossible for users to accurately predict the subsequent construction status of the shield machine. They can only adapt to changes in geological conditions by adjusting the shield machine parameters. Whenever the geological conditions change, it is necessary to repeatedly adjust the shield machine parameters for trial push to achieve the predetermined effect (mainly the excavation speed), which undoubtedly reduces the efficiency of shield construction. Summary of the Invention

[0003] The present invention provides a shield construction state prediction method, which solves the technical problem of low shield construction efficiency in the prior art.

[0004] In order to achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows:

[0005] In an embodiment of the first aspect, the present invention provides a shield construction state prediction method, the method comprising:

[0006] Acquire construction data in real time during the construction process, including stratum information data and shield machine working parameter data;

[0007] Constructing a prediction model, constructing a training set using the construction data under a single geological condition before a preset construction node, and training the prediction model;

[0008] Acquire and identify a longitudinal geological filling map image starting from the preset construction node to obtain stratum information data of the ring to be predicted;

[0009] The stratum information data of the ring to be predicted is used as the input of the prediction model, and the shield machine working parameter data output by the prediction model is the prediction result of the subsequent construction status.

[0010] In certain embodiments, the shield machine operating parameter data includes a total cutterhead thrust, a cutterhead rotational speed, and a tunneling speed of the shield machine at a preset total cutterhead thrust and a preset cutterhead rotational speed.

[0011] In certain embodiments, when the geological condition of the ring to be measured is a single condition, the process of obtaining the formation information data of the ring to be predicted includes:

[0012] Acquire a longitudinal geological filling map image starting from the construction node, and set characteristic values ​​for different colors representing different geological conditions and vertical line colors representing the frame of the ring to be predicted in the image;

[0013] Scanning the pixels in the image one by one, comparing them with the color feature values ​​of the vertical lines representing the ring frame to be measured, identifying the vertical lines representing the ring frame to be predicted, and using the quadrilateral area formed by the vertices of two adjacent vertical lines as the ring area to be measured;

[0014] The pixels in the ring area to be measured are scanned one by one, and their colors are compared with the characteristic values ​​to identify the colors in the ring area to be measured, thereby obtaining the geological conditions of the ring to be measured, that is, the stratum information.

[0015] In certain embodiments, when the geological conditions in the ring to be measured are complex conditions, the stratigraphic information data of the ring to be measured includes the type, quantity, and proportion of each single geological condition therein.

[0016] In certain embodiments, when the geological conditions in the ring to be measured are complex conditions, the color areas representing different single geological conditions in the ring area to be measured are obtained respectively through the process described in claim 3; then the sizes of the color areas and their proportions in the ring area to be measured are calculated respectively; the sizes of the color areas are the number of single geological conditions corresponding to them, and the proportions of the color areas in the ring area to be measured are the proportions of the single geological conditions corresponding to them in the ring to be measured.

[0017] In certain embodiments, when the geological conditions of the ring to be measured are complex conditions, the shield machine operating parameter data of the ring to be measured is obtained by the following steps:

[0018] Obtaining, by means of the prediction model, the tunneling speed of the shield machine under the geological conditions of each single condition in the ring to be tested when the shield machine adopts a preset total cutterhead thrust and a preset cutterhead speed;

[0019] The proportion of each single geological condition in the ring to be measured is used as the weight of the corresponding tunneling speed, and the weighted tunneling speeds are added together to obtain the tunneling speed of the shield machine in the ring to be measured, that is, the tunneling speed of the shield machine under the geological conditions of the composite conditions when the preset total cutterhead thrust and preset cutterhead speed are used.

[0020] In certain embodiments, when constructing the training set, the construction data is cleaned to remove abnormal data; and the training set is constructed using the cleaned construction data.

[0021] In an embodiment of the second aspect, the present invention provides a shield construction state prediction device, comprising:

[0022] A data acquisition module is used to obtain construction data in real time during the construction process, wherein the construction data includes stratum information data and shield machine working parameter data;

[0023] A model building module is used to build a prediction model, construct a training set based on the construction data under a single geological condition before a preset construction node, and train the prediction model;

[0024] The prediction module is used to use the stratum information data of the ring to be predicted as the input of the prediction model, and the shield machine working parameter data output by the prediction model is the prediction result of the subsequent construction status.

[0025] In an embodiment of the third aspect, the present invention provides a storage medium comprising at least one instruction, which implements the method as described in any of the preceding items when the instruction is executed.

[0026] In an embodiment of the fourth aspect, the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method described in any one of the preceding items when executed.

[0027] Beneficial effects

[0028] The prediction model constructed by the present invention is trained using construction data prior to a preset construction node. The geological conditions of the ring to be measured are then determined by identifying a longitudinal geological infill map. These conditions are then input into the prediction model to obtain the operating parameter data for the shield machine in the ring to be measured. The present invention can predict the construction status of the shield machine during subsequent construction. Users can then set the shield machine's operating parameters based on the prediction results to achieve the desired effect, improving work efficiency and resolving the technical issue of low shield construction efficiency in existing technologies.

[0029] Additional aspects and advantages of the embodiments of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] The methods, systems, and / or programs in the accompanying drawings will be further described according to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example numerals represent similar structures in the various views of the drawings.

[0032] Figure 1 1 is a flow chart of a shield construction status prediction method in an embodiment of the first aspect;

[0033] Figure 2 This is a schematic diagram of construction data collection in one embodiment;

[0034] Figure 3 This is another schematic diagram of construction data collection in one embodiment;

[0035] Figure 4 This is a construction data curve diagram before a preset construction node in one embodiment;

[0036] Figure 5 This is a graph showing the construction data of the 105th ring in one embodiment;

[0037] Figure 6 This is a parameter combination table of the total thrust and rotational speed of some cutterheads under the geological conditions of massive strongly weathered mixed granite in one embodiment;

[0038] Figure 7 The present invention is a table of tunneling speeds of a shield machine under a preset total cutterhead thrust and a preset cutterhead speed under massive strongly weathered mixed granite geological conditions in one embodiment;

[0039] Figure 8 This is a data flow chart of obtaining stratum information of a ring to be predicted when the geological condition is a single condition in one embodiment;

[0040] Figure 9 This is a schematic diagram of a longitudinal geological filling map in one embodiment;

[0041] Figure 10 This is a flow chart of shield machine operating parameter data for obtaining a ring to be measured when the geological conditions are complex conditions in one embodiment;

[0042] Figure 11 2. It is a structural block diagram of a shield construction state prediction device in an embodiment of the second aspect;

[0043] Figure 12 It is a structural block diagram of a computer device in an embodiment of the fourth aspect.

[0044] Description of Reference Numerals

[0045] 10-Shield construction status prediction device;

[0046] 11-Data acquisition module; 12-Model building module; 13-Prediction module;

[0047] 21-processor; 22-memory; 23-bus. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0049] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0050] See also Figure 1 In an embodiment of the first aspect, the present application provides a shield construction status prediction method, comprising:

[0051] S1. Acquire construction data in real time during the construction process. The construction data includes stratum information data and shield machine working parameter data.

[0052] In some embodiments, sensors and monitoring systems are arranged at the shield machine construction site to collect data during the construction process in real time. The data of the sensors used include stratum sensors, shield machine working parameter sensors and construction environment sensors. The monitoring system is used to monitor the shield process information in real time and record construction data. The collected data includes stratum information, shield machine working parameters, and construction environment parameters. The data collection frequency can be adjusted according to actual conditions. The present invention adopts an intelligent management and control BIM+5D system, and the collection center obtains the working parameters of the shield machine in real time through transmission protocols such as MQ, HTTP, TCP and UDP, such as Figure 2 and Figure 3 As shown in the figure, it includes soil pressure, cutterhead torque, total cutterhead thrust, cutterhead speed, tunneling speed, grouting flow rate and shield machine attitude angle, etc. The acquired signals are then decomposed and the time-frequency domain features are extracted to judge the operating status of the shield machine. Commonly used methods include Fourier decomposition, wavelet decomposition, Hilbert envelope analysis, etc.

[0053] S2. Build a prediction model, construct a training set using construction data under single geological conditions before a preset construction node, and train the prediction model.

[0054] Specifically, the single geological conditions referred to in this invention include: sandy clay soil, fully weathered mixed granite, earthy strongly weathered mixed granite, massive strongly weathered mixed granite, moderately weathered mixed granite, and slightly weathered mixed granite. Moderately weathered mixed granite and slightly weathered mixed granite are classified as hard rock in this invention.

[0055] In some embodiments, the preset construction node is the 201st ring, and the construction data under single geological conditions in the 1st to 200th rings are used to construct the training set.

[0056] Specifically, when constructing the training set, the construction data is first cleaned, and the construction data after removing abnormal data is used to construct the training set.

[0057] In some embodiments, a median filtering method can be used to clean abnormal data points. After repeated verification, data with large total cutterhead thrust and cutterhead torque but low excavation speed and abnormal instantaneous peak values ​​of parameters such as cutterhead torque, cutterhead thrust and excavation speed are determined as abnormal data points.

[0058] Furthermore, the cleaned construction data and the original construction data are stored separately. The cleaned construction data is used to construct a training set, and the original construction data is used for traceability and secondary analysis.

[0059] See also Figure 4 and Figure 5 In some implementations, the total cutterhead thrust, the cutterhead rotational speed, and the tunneling speed of the shield machine at a preset total cutterhead thrust and a preset cutterhead rotational speed are selected as the main data for training the prediction model. Figure 4 This is a construction data curve diagram before a preset construction node provided in an embodiment. Figure 5 This is a graph of construction data for the 105th ring provided in one embodiment.

[0060] Specifically, the total cutterhead thrust and cutterhead speed data under each single geological condition in the construction data are first fitted by Gaussian to obtain the frequency distribution and frequency density of each parameter. After summarizing, the parameter combinations of all the total cutterhead thrust and cutterhead speed under each single geological condition are obtained as the preset total cutterhead thrust and preset cutterhead speed. Taking the single geological condition of massive strongly weathered mixed granite as an example, the parameter combinations of some cutterhead thrust and cutterhead speed are obtained as follows Figure 6As shown. Then, the tunneling speeds corresponding to the total cutterhead thrust and the cutterhead speed in the construction data, which have absolute differences within 5% of the preset total cutterhead thrust and the preset cutterhead speed, are summarized to obtain the tunneling speed of the shield machine under the preset total cutterhead thrust and the preset cutterhead speed. The correspondence between some single geological conditions, the preset total cutterhead thrust, the preset cutterhead speed and the tunneling speed of the shield machine under the preset total cutterhead thrust and the preset cutterhead speed obtained through the above steps is shown as follows: Figure 7 shown.

[0061] It is understood that the prediction model can adopt a model built based on a machine learning algorithm in the existing technology. The specific machine learning algorithm can be selected according to the actual situation, such as support vector machine (SVM), random forest, neural network, etc. Cross-validation and other methods can be used during the training process to timely evaluate the performance and accuracy of the model.

[0062] S3. Obtain and identify the longitudinal geological filling map image starting from the preset construction node to obtain the stratigraphic information data of the ring to be predicted.

[0063] See also Figure 8 Specifically, when the geological condition of the ring to be measured is a single condition, the process of obtaining the stratigraphic information data of the ring to be predicted includes:

[0064] S31. Obtain a longitudinal geological filling map image starting from the construction node, and set characteristic values ​​for different colors representing different geological conditions in the image and the color of the vertical line representing the frame of the ring to be predicted.

[0065] See also Figure 9 , specific, vertical geological filling Figure 1 Typically in CAD format. The longitudinal geological fill map is obtained by the surveying and mapping department before construction. The map is divided into several areas filled with different colors, representing different geological conditions. The vertical lines in the map represent the boundaries of each ring.

[0066] In actual application, the longitudinal geological fill map is first imported into the system, and the DXF file is loaded through the Loader provided by three.js. With the help of Vue technology, the drawing can be viewed directly in the browser. The drawing is loaded to the appropriate position on the screen by zooming in and out and dragging. Finally, the starting ring at this time is set, and all rings after the starting ring are rings to be predicted.

[0067] In some embodiments, hexadecimal feature values ​​may be set for the color of the vertical line in the image and the color representing the address condition.

[0068] S32. Scan the pixels in the image one by one, compare them with the color feature values ​​of the vertical lines representing the border of the ring to be measured, identify the vertical lines representing the border of the ring to be measured, and use the quadrilateral area formed by the vertices of two adjacent vertical lines as the ring area to be measured.

[0069] S33. Scan the pixels in the ring area to be measured one by one, compare the colors of the pixels with the characteristic values, identify the colors in the ring area to be measured, and obtain the geological conditions of the ring to be measured, that is, the stratum information.

[0070] Furthermore, when the geological conditions in the ring to be measured are complex conditions, the stratum information data of the ring to be measured includes the type, quantity and proportion of each single geological condition therein.

[0071] Furthermore, the information of the ring formation to be measured under the complex geological conditions is obtained by the following method:

[0072] After obtaining the color regions representing different single geological conditions within the ring region to be measured through steps S31 to S33, the size of each color region and its proportion within the ring region to be measured are calculated. The size of the color region represents the number of single geological conditions it corresponds to, and the proportion of the color region within the ring region to be measured represents the proportion of the corresponding single geological condition within the ring region to be measured.

[0073] S4. The stratum information data of the ring to be predicted is used as the input of the prediction model. The shield machine working parameter data output by the prediction model is the prediction result of the subsequent construction status.

[0074] Specifically, when the geological condition of the ring to be tested is a single condition, the prediction model can directly output the tunneling speed of the shield machine under the single geological condition at each preset cutterhead total thrust and preset cutterhead speed.

[0075] See also Figure 10 When the geological conditions of the ring to be tested are complex conditions, the shield machine operating parameter data of the ring to be tested is obtained through the following steps:

[0076] S41. Obtain the tunneling speed of the shield machine under the geological conditions of each single condition in the test loop using a preset total cutterhead thrust and a preset cutterhead speed through the prediction model.

[0077] S42. The proportion of each single geological condition in the ring to be measured is used as the weight of the corresponding tunneling speed, and the weighted tunneling speeds are added together to obtain the tunneling speed of the shield machine in the ring to be measured, that is, the tunneling speed of the shield machine under the geological conditions of the composite conditions when the preset total cutterhead thrust and the preset cutterhead speed are used.

[0078] The user can set the shield machine parameters according to the required excavation speed using the corresponding preset cutterhead total thrust and preset cutterhead speed for trial pushing.

[0079] See also Figure 11 In an embodiment of the second aspect, the present application provides a shield construction status prediction device, comprising a data acquisition module, a model building module and a prediction module. The data acquisition module is used to obtain construction data in real time during the construction process, and the construction data includes stratum information data and shield machine working parameter data. The model building module is used to construct a prediction model, and a training set is constructed with construction data under a single geological condition before a preset construction node to train the prediction model. The prediction module is used to use the stratum information data of the ring to be predicted as the input of the prediction model, and the shield machine working parameter data output by the prediction model is the prediction result of the subsequent construction status.

[0080] Each module can be integrated on one processor, or each module can exist separately in different processors, or two or more modules can be integrated in one processor. In addition to being implemented in the form of hardware such as processors, the above modules can also be implemented in the form of software functional modules.

[0081] Each unit module of the shield construction state prediction device can respectively execute the corresponding steps in any of the above-mentioned shield construction state prediction devices, so each unit module will not be described in detail here. For details, please refer to the above corresponding step descriptions.

[0082] In an embodiment of the third aspect, the present invention provides a computer-readable storage medium comprising at least one instruction, which implements any of the above-mentioned shield construction status prediction methods when the instruction is executed.

[0083] See also Figure 12 In an embodiment of the fourth aspect, the present invention provides a computer device comprising a processor 21, a memory 22, and a computer program stored in the memory and executable on the processor, wherein the computer program implements any of the above-mentioned shield construction status prediction methods when executed.

[0084] The processor 21 and the memory 22 are connected via a bus. The bus 23 may include any number of interconnected buses 23 and bridges. The bus 23 connects various circuits of one or more processors 21 and the memory 22. The bus 23 may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. These are all well known in the art and are not further described herein.

[0085] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. A shield construction status prediction method, characterized in that: include: Acquire construction data in real time during the construction process, the construction data including stratum information data and shield machine operating parameter data; the shield machine operating parameter data including total cutterhead thrust, cutterhead speed, and the tunneling speed of the shield machine at a preset total cutterhead thrust and preset cutterhead speed; Constructing a prediction model, constructing a training set using the construction data under a single geological condition before a preset construction node, and training the prediction model; Acquire and identify a longitudinal geological filling map image starting from the preset construction node to obtain stratum information data of the ring to be predicted; The stratum information data of the ring to be predicted is used as the input of the prediction model, and the shield machine working parameter data output by the prediction model is the prediction result of the subsequent construction status; When the geological condition of the ring to be predicted is a single condition, the process of obtaining the stratum information data of the ring to be predicted includes: Acquire a longitudinal geological filling map image starting from the construction node, and set characteristic values ​​for different colors representing different geological conditions and vertical line colors representing the frame of the ring to be predicted in the image; Scanning the pixels in the image one by one, comparing them with the color feature values ​​of the vertical lines representing the ring frame to be measured, identifying the vertical lines representing the ring frame to be predicted, and using the quadrilateral area formed by the vertices of two adjacent vertical lines as the ring area to be measured; The pixels in the ring area to be measured are scanned one by one, and their colors are compared with the characteristic values ​​to identify the colors in the ring area to be measured, thereby obtaining the geological conditions of the ring to be measured, that is, the stratum information.

2. A shield construction status prediction method according to claim 1, characterized in that: When the geological conditions in the ring to be measured are complex conditions, the stratum information data of the ring to be measured includes the type, quantity and proportion of each single geological condition therein.

3. A shield construction status prediction method according to claim 2, characterized in that: When the geological conditions in the ring to be measured are complex conditions, first, the color areas representing different single geological conditions in the ring to be measured are obtained by the method of obtaining the stratigraphic information data of the ring to be predicted when the geological conditions are single conditions; then the sizes of the color areas and their proportions in the ring to be measured are calculated respectively; the sizes of the color areas are the number of single geological conditions corresponding to them, and the proportions of the color areas in the ring to be measured are the proportions of the single geological conditions corresponding to them in the ring to be measured.

4. A shield construction status prediction method according to claim 3, characterized in that: When the geological conditions of the ring to be measured are complex conditions, the shield machine operating parameter data of the ring to be measured is obtained through the following steps: Obtaining, by means of the prediction model, the tunneling speed of the shield machine under the geological conditions of each single condition in the ring to be tested when the shield machine adopts a preset total cutterhead thrust and a preset cutterhead speed; The proportion of each single geological condition in the ring to be measured is used as the weight of the corresponding tunneling speed, and the weighted tunneling speeds are added together to obtain the tunneling speed of the shield machine in the ring to be measured, that is, the tunneling speed of the shield machine under the geological conditions of the composite conditions when the preset total cutterhead thrust and preset cutterhead speed are used.

5. A shield construction status prediction method according to claim 1, characterized in that: When constructing the training set, the construction data is cleaned to remove abnormal data; and the training set is constructed using the cleaned construction data.

Images