Rock mass parameter prediction method and device for tunnel construction

Abstract

The present application discloses a rock mass parameter prediction method and device for tunnel construction. The method comprises: obtaining tunnel construction data to be predicted, the tunnel construction data includes image information and sensor information data generated by the tunneling equipment during the construction of the rock mass to be predicted, obtaining a tunnel construction rock mass parameter prediction model trained based on tunnel construction sample data including image information and sensor information, performing rock mass parameter prediction processing on the tunnel construction data to be predicted according to the tunnel construction rock mass parameter prediction model, and obtaining target rock mass parameter data. In the present application, the rock mass parameter prediction model is set to predict the rock mass parameters of the image information and sensor information data generated by the tunneling equipment during the tunneling construction in the rock mass to be predicted in the tunnel, thereby solving the problem of low accuracy of rock mass parameter prediction in tunnel excavation in the prior art and improving the accuracy of rock mass parameter prediction during tunnel construction.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a method and device for predicting rock mass parameters for tunnel construction. Background Art

[0002] The application of intelligent equipment and the development of mechanized construction are promoting the improvement of the comprehensive performance of full-section hard rock tunnel boring machines (TBMs), and the corresponding equipment and construction costs are also high; when encountering more difficult faults caused by the strata in front of the face, the delay in construction period and the missed best tunnel construction time have a great impact on the project. In the existing technology, the judgment of the tunnel rock mass is mainly achieved through manual analysis, or by classifying or grading the rock mass, and the prediction accuracy of the tunnel excavation rock mass parameters is low.

[0003] Therefore, the existing technology has the problem of low prediction accuracy of rock mass parameters for tunnel excavation. Summary of the invention

[0004] The main purpose of this application is to provide a method and device for predicting rock mass parameters for tunnel construction, so as to solve the problem of low accuracy in predicting rock mass parameters during tunnel excavation in the prior art and to improve the accuracy of predicting rock mass parameters during tunnel excavation.

[0005] In order to achieve the above-mentioned object, in a first aspect of the present application, a rock mass parameter prediction method for tunnel construction comprises:

[0006] Determining the construction data of the tunnel to be predicted, wherein the construction data of the tunnel to be predicted is used to represent the data including image information and sensor information generated by the tunneling equipment when constructing the rock mass to be predicted;

[0007] Acquire a tunnel construction rock mass parameter prediction model, wherein the tunnel construction rock mass parameter prediction model is a rock mass parameter prediction model trained based on tunnel construction sample data including image information and sensor information;

[0008] The tunnel construction data to be predicted are processed for rock mass parameter prediction according to the tunnel construction rock mass parameter prediction model to obtain target rock mass parameter data, wherein the target rock mass parameter data is the rock mass parameter data of the rock mass to be predicted.

[0009] Optionally, performing rock mass parameter prediction processing on the tunnel construction data to be predicted according to the tunnel construction rock mass parameter prediction model to obtain target rock mass parameter data includes:

[0010] Identify the tunnel construction data to be predicted to obtain image data of the tunnel construction to be predicted and sensor data of the tunnel construction to be predicted, wherein the image data of the tunnel construction to be predicted is data for representing the image information, and the sensor data of the tunnel construction to be predicted is data for representing the sensor information;

[0011] Preprocessing the tunnel construction image data to be predicted and the tunnel construction sensor data to be predicted to obtain tunnel construction feature data to be predicted, wherein the preprocessing includes image recognition processing of the tunnel construction image data to be predicted and data analysis processing of the tunnel construction sensor data to be predicted;

[0012] The rock mass parameter prediction model is used to perform rock mass parameter prediction processing on the tunnel construction characteristic data to be predicted to obtain the target rock mass parameter data.

[0013] Optionally, obtaining the tunnel construction rock mass parameter prediction model based on tunnel construction sample data training includes:

[0014] Acquire the tunnel construction sample data to be processed, wherein the tunnel construction sample data to be processed is data related to rock mass parameters during tunnel excavation, including image information and sensor information data;

[0015] Preprocessing the tunnel construction sample data to be processed to obtain training sample feature data, wherein the preprocessing includes image recognition processing of image information and data analysis processing of sensor information; and

[0016] Model training processing is performed on the training sample characteristic data to obtain the tunnel construction rock mass parameter prediction model.

[0017] Optionally, preprocessing the to-be-processed tunnel construction sample data to obtain training sample feature data includes:

[0018] Identify the tunnel construction sample data to be processed to obtain image data of the tunnel construction sample to be processed and sensor data of the tunnel construction sample to be processed, wherein the image data of the tunnel construction sample to be processed is data used to represent image information in the tunnel construction sample data to be processed, and the sensor data of the tunnel construction sample to be processed is data used to represent sensor information in the tunnel construction sample to be processed;

[0019] Performing soil slag image recognition processing on the tunnel construction sample image data to be processed to obtain process sample soil slag feature data, wherein the process sample soil slag feature data is feature data of soil slag generated during tunnel construction by excavation equipment;

[0020] Preprocessing the sensor data of the tunnel construction sample to be processed based on data analysis to obtain process vibration characteristic data, wherein the process vibration characteristic data is characteristic data of vibration generated during the tunnel construction process of the excavation equipment; and

[0021] The process sample slag characteristic data and the process vibration characteristic data are screened and optimized to obtain the training sample characteristic data.

[0022] Optionally, the process sample slag feature data and the process vibration feature data are screened and optimized to obtain the training sample feature data, including:

[0023] Identifying the tunnel construction sample data to be processed to obtain rock mass parameter characteristic data of the sample to be processed;

[0024] Matching the process sample slag characteristic data and the process vibration characteristic data corresponding to the sample rock mass parameter characteristic data to be processed to obtain process training sample characteristic data; and

[0025] The process training sample characteristic data is screened and optimized according to preset reference sample characteristic data to obtain the training sample characteristic data.

[0026] Optionally, performing model training processing on the training sample characteristic data to obtain the tunnel construction rock mass parameter prediction model includes:

[0027] Identifying the training sample characteristic data to obtain sample construction characteristic data, wherein the sample construction characteristic data includes sample slag characteristic data, sample vibration characteristic data and sample rock mass parameter characteristic data;

[0028] Performing model training processing on the sample slag characteristic data, the sample vibration characteristic data and the sample rock mass parameter characteristic data to obtain a rock mass parameter prediction model for process tunnel construction;

[0029] Determining whether the rock mass parameter prediction model for tunnel construction in the process satisfies a preset prediction effect evaluation rule;

[0030] If the conditions are met, the tunnel construction rock mass parameter prediction model is obtained, wherein the tunnel construction rock mass parameter prediction model is the process tunnel construction rock mass parameter prediction model;

[0031] If not, the process tunnel construction rock mass parameter prediction model is iteratively trained until the preset prediction effect evaluation rule is met to obtain the tunnel construction rock mass parameter prediction model.

[0032] According to a second aspect of the present application, a rock mass parameter prediction device for tunnel construction is proposed, comprising:

[0033] A data acquisition module, used to determine the construction data of the tunnel to be predicted, wherein the construction data of the tunnel to be predicted is used to represent the data including image information and sensor information generated by the tunneling equipment when constructing the rock mass to be predicted;

[0034] A prediction model acquisition module, used to acquire a tunnel construction rock mass parameter prediction model, wherein the tunnel construction rock mass parameter prediction model is a rock mass parameter prediction model trained based on tunnel construction sample data including image information and sensor information;

[0035] The prediction module is used to perform rock mass parameter prediction processing on the tunnel construction data to be predicted according to the tunnel construction rock mass parameter prediction model to obtain target rock mass parameter data, wherein the target rock mass parameter data is the rock mass parameter data of the rock mass to be predicted.

[0036] Optionally, the prediction module includes:

[0037] an identification module, used for identifying the tunnel construction data to be predicted, and obtaining image data of the tunnel construction to be predicted and sensor data of the tunnel construction to be predicted, wherein the image data of the tunnel construction to be predicted is data for representing the image information, and the sensor data of the tunnel construction to be predicted is data for representing the sensor information;

[0038] A preprocessing module, used for preprocessing the image data of the tunnel construction to be predicted and the sensor data of the tunnel construction to be predicted to obtain characteristic data of the tunnel construction to be predicted, wherein the preprocessing includes image recognition processing of the image data of the tunnel construction to be predicted and data analysis processing of the sensor data of the tunnel construction to be predicted;

[0039] The rock mass parameter prediction module is used to perform rock mass parameter prediction processing on the tunnel construction characteristic data to be predicted according to the tunnel construction rock mass parameter prediction model to obtain the target rock mass parameter data.

[0040] According to a third aspect of the present application, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned rock mass parameter prediction method for tunnel construction.

[0041] According to the fourth aspect of the present application, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the above-mentioned rock parameter prediction method for tunnel construction.

[0042] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0043] In the present application, by acquiring the tunnel construction data to be predicted, the tunnel construction data includes the image information and sensor information data generated by the tunneling equipment during the construction of the rock mass to be predicted, a tunnel construction rock parameter prediction model obtained by training based on the tunnel construction sample data including the image information and sensor information is obtained, and rock parameter prediction processing is performed on the tunnel construction data to be predicted according to the tunnel construction rock parameter prediction model to obtain target rock parameter data. In the present application, by setting the tunnel construction rock parameter prediction model, rock parameter prediction is performed on the image information and sensor information data generated by the tunneling equipment during the tunneling construction in the rock mass to be predicted in the tunnel, thereby solving the problem of low accuracy in rock parameter prediction of tunnel excavation in the prior art and improving the accuracy of rock parameter prediction during tunnel construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0045] Figure 1 A flow chart of a rock mass parameter prediction method for tunnel construction provided in this application;

[0046] Figure 2 A flow chart of a rock mass parameter prediction method for tunnel construction provided in this application;

[0047] Figure 3 A flow chart of a rock mass parameter prediction method for tunnel construction provided in this application;

[0048] Figure 4 A flow chart of a rock mass parameter prediction method for tunnel construction provided in this application;

[0049] Figure 5 A schematic diagram of the structure of a rock mass parameter prediction device for tunnel construction provided in this application;

[0050] Figure 6 A schematic diagram of the structure of another rock mass parameter prediction device for tunnel construction provided in this application. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0052] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0053] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.

[0054] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.

[0055] In addition, the terms "installed", "set", "provided with", "connected", "connected", and "socketed" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0056] Figure 1 A flow chart of a rock mass parameter prediction method for tunnel construction provided in this application, such as Figure 1 As shown, the method comprises the following steps:

[0057] S101: Determine the tunnel construction data to be predicted;

[0058] The predicted tunnel construction data is used to represent the data including image information and sensor information generated by the tunneling equipment during the construction of the predicted rock mass, wherein the image information is the image information of the debris generated during the construction of the tunneling equipment, which is acquired by the image acquisition module provided on the tunneling equipment; the sensor information is the information acquired by the sensors or sensor data acquisition devices during the construction of the tunneling equipment, including the vibration information acquired by the vibration sensor.

[0059] S102: Obtaining a rock mass parameter prediction model for tunnel construction;

[0060] The tunnel construction rock mass parameter prediction model is a rock mass parameter prediction model obtained by training based on tunnel construction sample data including image information and sensor information;

[0061] Figure 2 A flow chart of a rock mass parameter prediction method for tunnel construction provided in this application, such as Figure 2 As shown, the method comprises the following steps:

[0062] S201: Obtaining tunnel construction sample data to be processed;

[0063] The tunnel construction sample data to be processed are data related to rock mass parameters during tunnel excavation, including image information and sensor information data. The tunnel construction sample data include multiple sample rock masses and data generated by excavation equipment in the sample rock masses. The data generated by the excavation equipment in the sample rock masses include slag image information and equipment vibration sensor information. The first tunnel construction sample data are data related to the first sample rock mass, including the first sample rock mass parameters, the first sample slag image information and the first sample equipment vibration sensor information. The second tunnel construction sample data are data related to the second sample rock mass, including the second sample rock mass parameters, the second sample slag image information and the second sample equipment vibration sensor information.

[0064] In an optional embodiment of the present application, a suitable image acquisition cycle is selected according to the single excavation duration and cutter head rotation speed of the TBM equipment under different rock conditions to ensure that the cutter head rotates one circle within one image acquisition cycle to obtain new debris, and one excavation process (the TBM from start to stop is regarded as one excavation) is defined as an interval, so that the identified debris information corresponds to a set of rock parameters, which is used as a sample; according to different rock conditions, TBM shutdown support and excavation progress, a certain vibration data recording duration (i.e., one excavation process) is selected to correspond to a set of rock parameters and serve as a sample.

[0065] S202: Preprocessing the tunnel construction sample data to be processed to obtain training sample feature data;

[0066] Preprocessing includes image recognition processing of image information and data analysis processing of sensor information.

[0067] Figure 3 A flow chart of a rock mass parameter prediction method for tunnel construction provided in this application, such as Figure 3 As shown, the method comprises the following steps:

[0068] S301: Identify the tunnel construction sample data to be processed to obtain the tunnel construction sample image data to be processed and the tunnel construction sample sensor data to be processed;

[0069] The image data of the tunnel construction samples to be processed are data used to represent the image information in the tunnel construction sample data to be processed, and the sensor data of the tunnel construction samples to be processed are data used to represent the sensor information in the tunnel construction samples to be processed.

[0070] S302: Performing soil slag image recognition processing on the tunnel construction sample image data to be processed to obtain process sample soil slag feature data;

[0071] The process sample slag characteristic data is the characteristic data of slag generated during the tunnel construction process of the excavation equipment. The tunnel construction sample image data to be processed includes slag images. The slag images are processed by slag image recognition to obtain the process sample slag characteristic data, including: curvature coefficient, non-uniformity coefficient, maximum particle size and roughness index, etc. The tunnel construction sample image data to be processed corresponding to the same sample rock mass may include multiple groups of slag images. The slag characteristic data corresponding to each group of slag images are identified and calculated by slag image recognition technology to obtain multiple groups of sample slag characteristic data. The characteristic data average value of the multiple groups of sample slag characteristic data is calculated to obtain the above process sample slag characteristic data.

[0072] S303: Preprocessing the sensor data of the tunnel construction samples to be processed based on data analysis to obtain process vibration characteristic data;

[0073] The process vibration characteristic data is the characteristic data of vibration generated during the tunnel construction process of the tunnel boring equipment. The vibration characteristic data of the tunnel boring equipment in the sample interval is included in the sensor data of the tunnel construction sample to be processed corresponding to the same sample rock mass. The vibration characteristic data of the tunnel boring equipment is analyzed, and the vibration information characteristics in the sample interval are calculated, including the effective value, average amplitude, peak value, average extreme value, etc. of the vibration acceleration. The calculated characteristic data used to represent the effective value, average amplitude, peak value and average extreme value of the vibration acceleration are used as the process vibration characteristic data.

[0074] S304: Screening and optimizing the process sample slag characteristic data and the process vibration characteristic data to obtain training sample characteristic data.

[0075] The tunnel construction sample data to be processed is identified to obtain the rock mass parameter characteristic data of the sample to be processed; the process sample slag characteristic data and process vibration characteristic data corresponding to the rock mass parameter characteristic data of the sample to be processed are matched to obtain the process training sample characteristic data; the process training sample characteristic data is screened and optimized according to the preset reference sample characteristic data to obtain the training sample characteristic data. The reference sample characteristic data includes the data of vibration information generated in the no-load state of the tunneling equipment, and the reference sample characteristic data also includes the data of slag information and vibration information generated in the startup phase of the tunneling equipment. Based on the reference sample characteristic data, the process sample slag characteristic data and process vibration characteristic data are screened to obtain the sample characteristic data in the stable phase. By setting the screening and optimization processing of the process sample slag characteristic data and the process vibration characteristic data, the model training complexity in the process of training the tunnel construction rock mass parameter prediction model is reduced, and the accuracy of the trained tunnel construction rock mass parameter prediction model is improved.

[0076] S203: Perform model training processing on the training sample feature data to obtain a tunnel construction rock mass parameter prediction model.

[0077] Figure 4 A flow chart of a rock mass parameter prediction method for tunnel construction provided in this application, such as Figure 4 As shown, the method comprises the following steps:

[0078] S401: Identify the training sample feature data to obtain sample construction feature data;

[0079] The sample construction characteristic data include sample slag characteristic data, sample vibration characteristic data and sample rock mass parameter characteristic data;

[0080] S402: Performing model training processing on sample slag characteristic data, sample vibration characteristic data and sample rock mass parameter characteristic data to obtain a rock mass parameter prediction model for process tunnel construction;

[0081] Acquire first sample construction characteristic data, wherein the first sample construction characteristic data includes first sample slag characteristic data, first sample vibration characteristic data and first sample rock mass parameter characteristic data;

[0082] Performing model training processing on the first preset model according to the first sample slag characteristic data, the first sample vibration characteristic data and the first sample rock mass parameter characteristic data to obtain a rock mass integrity classification model;

[0083] In an optional embodiment of the present application, a rock integrity classification prediction model is constructed based on a random forest algorithm, and the constructed rock integrity classification prediction model is trained through first sample construction feature data. The first sample construction feature data includes first sample slag feature data, first sample vibration feature data and first sample rock parameter feature data. The first sample rock parameter feature data includes rock strength and volume joint number. The first sample slag feature data includes: curvature coefficient, uniformity coefficient, maximum particle size and roughness index. The first sample vibration feature data includes effective value of vibration acceleration, average amplitude, peak value and average extreme value. The sample rock integrity feature data is determined through the first sample rock parameter feature data. Through grid search, learning curves of random forest tree number, maximum depth and maximum feature number are established respectively. The first sample excavation feature data is trained, and the target random forest tree number, target maximum depth and target maximum feature number are determined according to the learning curves of random forest tree number, maximum depth and maximum feature number respectively. The target random forest number, target maximum depth and target maximum feature number are brought into the preset rock mass integrity classification prediction model to obtain the target rock mass integrity classification prediction model.

[0084] In another optional embodiment of the present application, model training is performed based on the first sample construction characteristic data, and a model is established and predicted for the rock integrity based on the random forest algorithm; in order to prevent overfitting or underfitting of the model training, the hyperparameters of the model are continuously inverted to achieve hyperparameter selection values ​​that have good predictive accuracy for the surrounding rock integrity; and a softmax multi-classification function is introduced.

[0085] Acquire second sample construction characteristic data, where the second sample construction characteristic data includes second sample slag characteristic data, second sample vibration characteristic data, and second sample rock mass parameter characteristic data;

[0086] According to the rock mass integrity classification model, the second sample construction characteristic data is subjected to rock mass integrity classification prediction to obtain process sample rock mass classification characteristic data;

[0087] The second preset model is trained according to the second sample slag characteristic data, the second sample vibration characteristic data, the second sample rock mass parameter characteristic data and the process sample rock mass classification characteristic data to obtain a process tunnel construction rock mass parameter prediction model.

[0088] In an embodiment of the present application, a rock integrity classification model is constructed and trained based on the first sample construction feature data, and rock integrity classification prediction is performed on the second sample construction feature data through the rock integrity classification model to obtain process sample rock classification feature data, and a tunnel construction rock parameter prediction model is jointly trained based on the process sample rock classification feature data and the second sample construction feature data. By constructing a rock integrity classification model and performing rock integrity classification prediction on the second sample construction feature data, the data dimension of the training feature data in the second sample construction feature data is increased. By increasing the data dimension of model training, the accuracy of the trained tunnel construction rock parameter prediction model is improved.

[0089] S403: Determine whether the tunnel construction rock mass parameter prediction model meets the preset prediction effect evaluation rules, and obtain the tunnel construction rock mass parameter prediction model.

[0090] If the conditions are met, a tunnel construction rock mass parameter prediction model is obtained, where the tunnel construction rock mass parameter prediction model is the process tunnel construction rock mass parameter prediction model;

[0091] If it is not satisfied, the process tunnel construction rock mass parameter prediction model is iteratively trained until the preset prediction effect evaluation rules are met to obtain the tunnel construction rock mass parameter prediction model.

[0092] In an optional embodiment of the present application, the prediction effect of the tunnel construction rock mass parameter prediction model is calculated to obtain test set sample data, and the prediction effect of the tunnel construction rock mass parameter prediction model is evaluated based on the test set sample data. The model is evaluated by three evaluation indicators: root mean square error (RMSE), mean absolute error (MAE), and R2 (R Squared).

[0093]

[0094]

[0095]

[0096] Among them, y i Indicates the actual value of rock mass parameters, represents the predicted value of rock mass parameters, Represents the average value of actual values ​​of rock mass parameters.

[0097] In another optional embodiment of the present application, the rock mass integrity classification prediction model is evaluated for model effect by setting the accuracy rate P and the Kappa coefficient k. Among them, p0 is the accuracy, N is the total number of samples, and N i represents the actual total number of samples in the i-th category, Indicates the total number of samples predicted for the i-th category.

[0098] In the embodiment of the present application, by setting up a prediction effect evaluation for the process tunnel construction rock mass parameter prediction model, the process tunnel construction rock mass parameter prediction model is screened to improve the accuracy of the target tunnel construction rock mass parameter prediction model.

[0099] S103: performing rock mass parameter prediction processing on the tunnel construction data to be predicted according to the tunnel construction rock mass parameter prediction model to obtain target rock mass parameter data;

[0100] The target rock mass parameter data is the data of the rock mass parameters of the rock mass to be predicted. The tunnel construction data to be predicted is identified to obtain the image data of the tunnel construction to be predicted and the sensor data of the tunnel construction to be predicted. The image data of the tunnel construction to be predicted is data used to represent image information, and the sensor data of the tunnel construction to be predicted is data used to represent sensor information. The image data of the tunnel construction to be predicted and the sensor data of the tunnel construction to be predicted are preprocessed to obtain the characteristic data of the tunnel construction to be predicted. The preprocessing includes image recognition processing of the image data of the tunnel construction to be predicted and data analysis processing of the sensor data of the tunnel construction to be predicted. The rock mass parameter prediction processing is performed on the characteristic data of the tunnel construction to be predicted according to the tunnel construction rock mass parameter prediction model to obtain the target rock mass parameter data.

[0101] Figure 5 A schematic diagram of the structure of a rock mass parameter prediction device for tunnel construction provided in this application, such as Figure 5 As shown, the device comprises:

[0102] A data acquisition module 51 is used to determine the construction data of the tunnel to be predicted, wherein the construction data of the tunnel to be predicted is used to represent the data including image information and sensor information generated by the tunneling equipment when constructing the rock mass to be predicted;

[0103] A prediction model acquisition module 52 is used to acquire a tunnel construction rock mass parameter prediction model, wherein the tunnel construction rock mass parameter prediction model is a rock mass parameter prediction model trained based on tunnel construction sample data including image information and sensor information;

[0104] The prediction module 53 is used to perform rock mass parameter prediction processing on the tunnel construction data to be predicted according to the tunnel construction rock mass parameter prediction model to obtain target rock mass parameter data, wherein the target rock mass parameter data is the rock mass parameter data of the rock mass to be predicted.

[0105] Figure 6A schematic diagram of the structure of another rock mass parameter prediction device for tunnel construction provided in this application, such as Figure 6 As shown, the device comprises:

[0106] The identification module 61 is used to identify the tunnel construction data to be predicted, and obtain the tunnel construction image data to be predicted and the tunnel construction sensor data to be predicted, wherein the tunnel construction image data to be predicted is data for representing image information, and the tunnel construction sensor data to be predicted is data for representing sensor information;

[0107] A preprocessing module 62 is used to preprocess the image data of the tunnel construction to be predicted and the sensor data of the tunnel construction to be predicted to obtain characteristic data of the tunnel construction to be predicted, wherein the preprocessing includes image recognition processing of the image data of the tunnel construction to be predicted and data analysis processing of the sensor data of the tunnel construction to be predicted;

[0108] The rock mass parameter prediction module 63 is used to perform rock mass parameter prediction processing on the tunnel construction characteristic data to be predicted according to the tunnel construction rock mass parameter prediction model to obtain target rock mass parameter data.

[0109] The specific manner of executing the operation of each unit in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0110] To summarize, in the present application, by acquiring the tunnel construction data to be predicted, the tunnel construction data includes the image information and sensor information data generated by the tunneling equipment during the construction of the rock mass to be predicted, a tunnel construction rock parameter prediction model obtained by training based on the tunnel construction sample data including the image information and sensor information is obtained, and rock parameter prediction processing is performed on the tunnel construction data to be predicted according to the tunnel construction rock parameter prediction model to obtain the target rock parameter data. In the present application, by setting the tunnel construction rock parameter prediction model, rock parameter prediction is performed on the image information and sensor information data generated by the tunneling equipment during the tunneling construction in the rock mass to be predicted in the tunnel, thereby solving the problem of low accuracy in rock parameter prediction of tunnel excavation in the prior art and improving the accuracy of rock parameter prediction during tunnel construction.

[0111] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0112] Obviously, those skilled in the art should understand that the above-mentioned units or steps of the present application can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0113] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A rock mass parameter prediction method for tunnel construction, characterized in that: include: Determining the construction data of the tunnel to be predicted, wherein the construction data of the tunnel to be predicted is used to represent the data including image information and sensor information generated by the tunneling equipment when constructing the rock mass to be predicted; Acquire a tunnel construction rock mass parameter prediction model, wherein the tunnel construction rock mass parameter prediction model is a rock mass parameter prediction model trained based on tunnel construction sample data including image information and sensor information; The tunnel construction rock mass parameter prediction model obtained by training based on the tunnel construction sample data includes: obtaining the tunnel construction sample data to be processed, wherein the tunnel construction sample data to be processed is data related to rock mass parameters during tunnel excavation, including image information and sensor information data; preprocessing the tunnel construction sample data to be processed to obtain training sample feature data, wherein the preprocessing includes image recognition processing of image information and data analysis processing of sensor information; and performing model training processing on the training sample feature data to obtain the tunnel construction rock mass parameter prediction model; The model training process is performed on the training sample characteristic data to obtain the tunnel construction rock mass parameter prediction model, including: Identify the training sample feature data to obtain sample construction feature data, wherein the sample construction feature data includes sample slag feature data, sample vibration feature data and sample rock mass parameter feature data; perform model training processing on the sample slag feature data, the sample vibration feature data and the sample rock mass parameter feature data to obtain a process tunnel construction rock mass parameter prediction model; Determine whether the process tunnel construction rock mass parameter prediction model satisfies the preset prediction effect evaluation rules; if so, obtain the tunnel construction rock mass parameter prediction model, wherein the tunnel construction rock mass parameter prediction model is the process tunnel construction rock mass parameter prediction model; if not, perform iterative training processing on the process tunnel construction rock mass parameter prediction model until the preset prediction effect evaluation rules are met, and obtain the tunnel construction rock mass parameter prediction model; The tunnel construction data to be predicted are processed for rock mass parameter prediction according to the tunnel construction rock mass parameter prediction model to obtain target rock mass parameter data, wherein the target rock mass parameter data is the rock mass parameter data of the rock mass to be predicted.

2. The rock mass parameter prediction method according to claim 1, characterized in that: According to the tunnel construction rock mass parameter prediction model, the rock mass parameter prediction processing is performed on the tunnel construction data to be predicted, and the target rock mass parameter data is obtained, including: Identify the tunnel construction data to be predicted to obtain image data of the tunnel construction to be predicted and sensor data of the tunnel construction to be predicted, wherein the image data of the tunnel construction to be predicted is data for representing the image information, and the sensor data of the tunnel construction to be predicted is data for representing the sensor information; Preprocessing the tunnel construction image data to be predicted and the tunnel construction sensor data to be predicted to obtain tunnel construction feature data to be predicted, wherein the preprocessing includes image recognition processing of the tunnel construction image data to be predicted and data analysis processing of the tunnel construction sensor data to be predicted; The rock mass parameter prediction model is used to perform rock mass parameter prediction processing on the tunnel construction characteristic data to be predicted to obtain the target rock mass parameter data.

3. The rock mass parameter prediction method according to claim 1, characterized in that: Preprocessing the tunnel construction sample data to be processed to obtain training sample feature data includes: Identify the tunnel construction sample data to be processed to obtain image data of the tunnel construction sample to be processed and sensor data of the tunnel construction sample to be processed, wherein the image data of the tunnel construction sample to be processed is data used to represent image information in the tunnel construction sample data to be processed, and the sensor data of the tunnel construction sample to be processed is data used to represent sensor information in the tunnel construction sample to be processed; Performing soil slag image recognition processing on the tunnel construction sample image data to be processed to obtain process sample soil slag feature data, wherein the process sample soil slag feature data is feature data of soil slag generated during tunnel construction by excavation equipment; Preprocessing the sensor data of the tunnel construction sample to be processed based on data analysis to obtain process vibration characteristic data, wherein the process vibration characteristic data is characteristic data of vibration generated during the tunnel construction process of the excavation equipment; and The process sample slag characteristic data and the process vibration characteristic data are screened and optimized to obtain the training sample characteristic data.

4. The rock mass parameter prediction method according to claim 3, characterized in that: The process sample slag feature data and the process vibration feature data are screened and optimized to obtain the training sample feature data including: Identifying the tunnel construction sample data to be processed to obtain rock mass parameter characteristic data of the sample to be processed; Matching the process sample slag characteristic data and the process vibration characteristic data corresponding to the sample rock mass parameter characteristic data to be processed to obtain process training sample characteristic data; and The process training sample characteristic data is screened and optimized according to preset reference sample characteristic data to obtain the training sample characteristic data.

5. A rock mass parameter prediction device for tunnel construction, characterized in that: include: A data acquisition module, used to determine the construction data of the tunnel to be predicted, wherein the construction data of the tunnel to be predicted is used to represent the data including image information and sensor information generated by the tunneling equipment when constructing the rock mass to be predicted; A prediction model acquisition module, used to acquire a tunnel construction rock mass parameter prediction model, wherein the tunnel construction rock mass parameter prediction model is a rock mass parameter prediction model trained based on tunnel construction sample data including image information and sensor information; The tunnel construction rock mass parameter prediction model obtained by training based on the tunnel construction sample data includes: obtaining the tunnel construction sample data to be processed, wherein the tunnel construction sample data to be processed is data related to rock mass parameters during tunnel excavation, including image information and sensor information data; preprocessing the tunnel construction sample data to be processed to obtain training sample feature data, wherein the preprocessing includes image recognition processing of image information and data analysis processing of sensor information; and performing model training processing on the training sample feature data to obtain the tunnel construction rock mass parameter prediction model; The model training process is performed on the training sample characteristic data to obtain the tunnel construction rock mass parameter prediction model, including: Identify the training sample feature data to obtain sample construction feature data, wherein the sample construction feature data includes sample slag feature data, sample vibration feature data and sample rock mass parameter feature data; perform model training processing on the sample slag feature data, the sample vibration feature data and the sample rock mass parameter feature data to obtain a process tunnel construction rock mass parameter prediction model; Determine whether the process tunnel construction rock mass parameter prediction model satisfies the preset prediction effect evaluation rules; if so, obtain the tunnel construction rock mass parameter prediction model, wherein the tunnel construction rock mass parameter prediction model is the process tunnel construction rock mass parameter prediction model; if not, perform iterative training processing on the process tunnel construction rock mass parameter prediction model until the preset prediction effect evaluation rules are met, and obtain the tunnel construction rock mass parameter prediction model; The prediction module is used to perform rock mass parameter prediction processing on the tunnel construction data to be predicted according to the tunnel construction rock mass parameter prediction model to obtain target rock mass parameter data, wherein the target rock mass parameter data is the rock mass parameter data of the rock mass to be predicted.

6. The rock mass parameter prediction device according to claim 5, characterized in that: The prediction module comprises: an identification module, used for identifying the tunnel construction data to be predicted, and obtaining image data of the tunnel construction to be predicted and sensor data of the tunnel construction to be predicted, wherein the image data of the tunnel construction to be predicted is data for representing the image information, and the sensor data of the tunnel construction to be predicted is data for representing the sensor information; A preprocessing module, used for preprocessing the image data of the tunnel construction to be predicted and the sensor data of the tunnel construction to be predicted to obtain characteristic data of the tunnel construction to be predicted, wherein the preprocessing includes image recognition processing of the image data of the tunnel construction to be predicted and data analysis processing of the sensor data of the tunnel construction to be predicted; The rock mass parameter prediction module is used to perform rock mass parameter prediction processing on the tunnel construction characteristic data to be predicted according to the tunnel construction rock mass parameter prediction model to obtain the target rock mass parameter data.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the rock mass parameter prediction method for tunnel construction according to any one of claims 1 to 4.

8. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the rock parameter prediction method for tunnel construction as described in any one of claims 1-4.

Images