Drilling and blasting method tunnel construction quality evaluation method and system based on multi-source heterogeneous data

By employing a multi-source heterogeneous data tunnel construction quality assessment method, utilizing data acquisition, preprocessing, and model interpretation, combined with cloud-edge-device technology, the problem of data independence in drill-and-blast tunnel construction quality detection was solved, achieving efficient and accurate construction quality assessment.

CN118966877APending Publication Date: 2024-11-15SHANDONG UNIV +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410998085.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

In existing technologies, the quality inspection of tunnel construction using the drill-and-blast method mainly relies on manual inspection, which is cumbersome, inefficient, and the inspection data is independent, making it difficult to achieve comprehensive application.

Method used

A tunnel construction quality assessment method using multi-source heterogeneous data is adopted. Through data acquisition, preprocessing, deep classification and model interpretation, combined with cloud-edge-device technology for data sharing and fusion, a tunnel construction quality database is established to realize the comprehensive application of multiple data sources.

Benefits of technology

It improves the efficiency of data collection and processing, enables rapid and accurate assessment of tunnel construction quality, solves the problem of independent data being difficult to integrate and apply, and assists in construction quality assessment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966877A_ABST
    Figure CN118966877A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of tunnel construction, and provides a drilling and blasting method tunnel construction quality evaluation method and system based on multi-source heterogeneous data, and the method comprises the steps: collecting various data in a tunnel construction process; preprocessing the collected data and adding a label; performing deep classification on the data added with the labels and then transmitting the data to a database for classified storage, including sending the data to a corresponding interpretation model for interpretation according to a first label, classifying, packaging and transmitting the interpreted data to a cloud for data processing, and performing deep classification on the data at the cloud; and in combination with various model algorithms and standard specifications of tunnel construction quality detection, project data stored in the database are called to evaluate the drilling and blasting method tunnel construction quality. The problem that construction quality data parameters are relatively independent and difficult to comprehensively apply is solved, and tunnel construction quality evaluation on the basis of sufficient data sharing and fusion is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of tunnel construction, and in particular relates to a method and system for evaluating the quality of tunnel construction using a drilling and blasting method based on multi-source heterogeneous data. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In the construction of drill-and-blast tunnels, the current construction quality inspection is still mainly based on manual inspection. The main implementation methods are manual handheld equipment inspection or visual inspection, etc. The inspection steps are cumbersome, slow, and inefficient. In addition, the data parameters of each inspection item are relatively independent. Even for some inspection items that use visual inspection, there is a problem that the data parameters are difficult to be effectively saved, which affects the subsequent construction quality evaluation.

[0004] With the development of intelligent technology, intelligent detection and evaluation methods are gradually applied to construction quality. The current intelligent detection and evaluation methods can only detect and evaluate one or a few projects, and there are problems such as multi-source detection data, relative independence and difficulty in comprehensive application. Summary of the invention

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a method and system for evaluating the construction quality of a tunnel using the drilling and blasting method based on multi-source heterogeneous data, which solves the problem that construction quality data parameters are relatively independent and difficult to apply comprehensively, and realizes the evaluation of tunnel construction quality based on full data sharing and integration.

[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0007] A first aspect of the present invention provides a method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data, comprising:

[0008] Collect various data during tunnel construction;

[0009] Adding a first label after preprocessing the collected data;

[0010] The data after adding the first label is deeply classified and then transmitted to the tunnel construction quality database for classified storage;

[0011] Combining multiple model algorithms and standard specifications for tunnel construction quality inspection, the project data stored in the database is used to evaluate the construction quality of drill and blast tunnels;

[0012] The deep classification of the data after adding the first label includes: sending the data to the corresponding interpretation model for interpretation according to the first label, and classifying and packaging the interpreted data and transmitting them to the cloud for data processing, and deeply classifying the data in the cloud;

[0013] The deep classification of data in the cloud includes: deep classification of image data based on an image recognition model to obtain concrete leakage, cracks and water leakage data;

[0014] Based on the cloud processing model, the radar grayscale image data is deeply classified to obtain the thickness and density of concrete;

[0015] Based on the point cloud processing model, the laser point cloud data is deeply classified to obtain the tunnel excavation section elevation, excavation profile size and over-excavation and under-excavation data;

[0016] The rebound test data is deeply classified through the strength analysis model to obtain the concrete strength information.

[0017] A second aspect of the present invention provides a drilling and blasting tunnel construction quality assessment system based on multi-source heterogeneous data, comprising:

[0018] The data collection module is configured to: collect various data during the tunnel construction process;

[0019] The data preprocessing module is configured to: preprocess the collected data and then add a first label;

[0020] The data classification and storage module is configured to: perform deep classification on the data after adding the first label and then transmit the data to the tunnel construction quality database for classification and storage;

[0021] The deep classification of the data after adding the first label includes: sending the data to the corresponding interpretation model for interpretation according to the first label, and classifying and packaging the interpreted data and transmitting them to the cloud for data processing, and deeply classifying the data in the cloud;

[0022] The deep classification of data in the cloud includes: deep classification of image data based on an image recognition model to obtain concrete leakage, cracks and water leakage data;

[0023] Based on the cloud processing model, the radar grayscale image data is deeply classified to obtain the thickness and density of concrete;

[0024] Based on the point cloud processing model, the laser point cloud data is deeply classified to obtain the tunnel excavation section elevation, excavation profile size and over-excavation and under-excavation data;

[0025] The rebound test data is deeply classified through the strength analysis model to obtain the concrete strength information;

[0026] The quality assessment module is configured to: combine multiple model algorithms and standard specifications for tunnel construction quality inspection, and call the project data stored in the database to evaluate the construction quality of the drill and blast tunnel.

[0027] The third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in a method for evaluating tunnel construction quality by drilling and blasting method based on multi-source heterogeneous data as described in the first aspect of the present invention.

[0028] The fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as described in the first aspect of the present invention are implemented.

[0029] One or more of the above technical solutions have the following beneficial effects:

[0030] (1) The present invention analyzes, classifies, and comprehensively processes the construction quality parameters of the drill and blast tunnel based on multiple data sources, and incorporates them into a database, thereby realizing the comprehensive application of construction quality parameters from multiple data sources, effectively assisting in construction quality assessment, and solving the problem that construction quality data parameters are relatively independent and difficult to comprehensively apply.

[0031] (2) The present invention uses a quality inspection robot to collect data, with fast data collection speed and high efficiency; cloud-edge-end technology is used in data transmission and processing, that is, the robot end transmits the detection data to the edge workstation, and the workstation interprets, classifies, packages and other pre-processes the data and uploads the processed data to the cloud for deep classification and then stores it in the corresponding database; the data processing speed is fast and the accuracy is high.

[0032] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 This is a flow chart of the construction quality parameter library building method of the first embodiment.

[0035] Figure 2 This is a flow chart of cloud-edge data transmission and data processing for the first embodiment.

[0036] Figure 3This is the image data of the first embodiment.

[0037] Figure 4 This is the radar data of the first embodiment.

[0038] Figure 5 This is the laser point cloud data of the first embodiment.

[0039] Figure 6 This is the rebound detection data of the first embodiment. DETAILED DESCRIPTION

[0040] Embodiment 1

[0041] like Figure 1 As shown, this embodiment discloses a method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data, including:

[0042] Step 1: Collect various data during tunnel construction;

[0043] Step 2: Add the first label after preprocessing the collected data;

[0044] Step 3: After deeply classifying the data after adding the first label, the data is transmitted to the tunnel construction quality parameter library for classified storage;

[0045] Step 4: Combining multiple model algorithms and standard specifications for tunnel construction quality inspection, the project data stored in the database is used to evaluate the construction quality of the drill and blast tunnel.

[0046] like Figure 2 As shown, the present invention is based on cloud-edge-end technology. The robot end transmits the detection data to the edge workstation. The workstation interprets, classifies, packages and other pre-processes the data and uploads the processed data to the cloud for deep classification and then stores it in the corresponding database.

[0047] In step 1, the data sources include image data, radar detection data, laser point cloud data, and rebound detection data;

[0048] Data collection is performed using a construction quality inspection robot equipped with a data collection device, including a high-definition camera, a geological radar, a 3D laser scanning device, and a cloud rebound tester;

[0049] High-definition cameras are used to collect image data of leaks, cracks, and water seepage; geological radars are used to collect radar data of thickness and density; three-dimensional laser scanning devices are used to collect laser point cloud data of excavation elevation and excavation size; and cloud rebound instruments are used to collect rebound data of concrete strength.

[0050] For example, in this embodiment, a construction quality inspection robot equipped with a data acquisition device is used to enter the H1DK+485 to H1DK1+497 mileage section of the No. 1 horizontal tunnel of the KD2 tunnel to collect data. The collected image data is as follows: Figure 3 As shown; radar data as Figure 4 As shown; laser point cloud data as Figure 5 As shown; rebound data as Figure 6 shown.

[0051] In step 2, the collected data is preprocessed and then a first label is added, including:

[0052] Step 201: The data preprocessing model is trained based on the differences in file formats between the data, and an attention mechanism is introduced so that the model can only recognize the data format that has been input for training.

[0053] Step 202: The data on the robot side is identified through the data preprocessing model, and classified according to the preset data type, and a unique first label is assigned to the classified data, the first label including the data type, detection location, detection time, etc.

[0054] Step 203: Send the classified data to the corresponding interpretation model according to the first label for interpretation, and classify and package the interpreted data and transmit them to the cloud for data processing, and perform deep classification on the data in the cloud.

[0055] The first label added in the present application is used to indicate the data type. For example, for the collected image data, it is marked as an image through a label, and the data will be assigned to the image interpretation model through the identification of the label, and the data will be subsequently identified and processed; if the data is radar data, it is marked as a radar map through a label, and the data label will be identified and assigned to the radar map interpretation model, and the data will be subsequently processed to output the interpreted data.

[0056] In step 3, for the image data, the image recognition model is trained using leaks, cracks, and water leakage images, so that it can recognize leaks, cracks, and water leakage images, perform deep classification on them, and output the leaks, cracks, and water leakage conditions;

[0057] For radar data, the cloud processing model is used to identify the radar grayscale image data and output information such as concrete thickness and density;

[0058] For laser point cloud data, the point cloud processing model is used to identify the laser point cloud map and output information such as tunnel elevation, excavation contour, and over-excavation and under-excavation.

[0059] For the rebound hammer data, the rebound hammer data is analyzed through the strength analysis model to output the strength information.

[0060] All output information is assigned a second label, which includes data type, test item, test time, and test location. Each output data is matched to the database of each test item according to the second label.

[0061] In the present invention, the data is labeled twice. The first label is used to classify the data types, including radar data, image data, laser point cloud data, and rebound tester data, and then transmit them to the corresponding model for processing and output. The second label is used to label the data output by the model for the second time, marking the corresponding detection items, detection time, and detection location.

[0062] Establish a drill-and-blast tunnel construction quality database: The drill-and-blast tunnel construction quality database consists of an excavation parameter information database, a primary support parameter information database, and a lining parameter information database.

[0063] Enter the processed cloud data into the database, including: entering the centerline and elevation of the excavation section and the excavation profile dimensions into the excavation parameter information database;

[0064] Enter the shotcrete thickness, shotcrete density, shotcrete flatness, missed shots, and surface cracks into the initial support parameter information database;

[0065] The lining concrete thickness, lining concrete density, lining concrete strength, water leakage and surface cracks are entered into the lining parameter information database.

[0066] Among them, shotcrete is formed by loading pre-mixed cement, sand, gravel, water and a certain amount of admixtures into a sprayer, using high-pressure air to send it to the nozzle and mix it with the accelerator, and then spraying it onto the rock surface at a very high speed.

[0067] Lining concrete refers to the cast-in-place concrete applied on the inner side of the initial support during tunnel construction. It requires first making a mold and then pouring concrete into the mold.

[0068] The difference between shotcrete and lining concrete is:

[0069] 1. The surface of shotcrete is rough, while the surface of lining concrete is smooth; 2. Shotcrete is thin, while lining concrete is thick; 3. Shotcrete is constructed in the initial support stage, after the steel arch frame is completed; lining concrete is constructed after the initial support is completed.

[0070] In step 4, the construction quality of the drill and blast tunnel is evaluated by combining multiple model algorithms and standard specifications for tunnel construction quality inspection and calling the project data stored in the database.

[0071] The database can be used as a training data set to train the model. Based on the data assimilation method, the measured data is combined with the model recognition results, the model recognition results are corrected by the measured data, and the model is continuously optimized, and the cycle is repeated to improve the accuracy of model recognition.

[0072] This data can be used as an input data source for the construction quality assessment system to assess the construction quality. The data of each test item in the database is input into the construction quality assessment system, and the data is matched to each assessment item through the labels carried by the data. Specific test items can also be selected through the software for assessment. The overall construction quality can also be assessed to understand the construction quality of the tunnel, clarify the construction defects in the tunnel and its location in the tunnel.

[0073] The present invention clarifies various inspection items by investigating the standard specifications for tunnel construction quality inspection; the specifications include but are not limited to "High-speed Railway Tunnel Engineering Construction Quality Acceptance Standard" (TB 10753-2018), "Railway Concrete Engineering Construction Quality Acceptance Standard" (TB10424-2018), and "Railway Tunnel Lining Quality Non-destructive Testing Procedure" (TB 10223-2004).

[0074] Embodiment 2

[0075] This embodiment discloses a drilling and blasting tunnel construction quality assessment system based on multi-source heterogeneous data fusion, including:

[0076] The data collection module is configured to: collect various data during the tunnel construction process;

[0077] The data preprocessing module is configured to: preprocess the collected data and then add a first label;

[0078] The data classification and storage module is configured to: perform deep classification on the data after adding the first label and then transmit the data to the tunnel construction quality database for classification and storage;

[0079] The deep classification of the data after adding the first label includes: sending the data to the corresponding interpretation model for interpretation according to the first label, and classifying and packaging the interpreted data and transmitting them to the cloud for data processing, and deeply classifying the data in the cloud;

[0080] The deep classification of data in the cloud includes: deep classification of image data based on an image recognition model to obtain concrete leakage, cracks and water leakage data;

[0081] Based on the cloud processing model, the radar grayscale image data is deeply classified to obtain the thickness and density of concrete;

[0082] Based on the point cloud processing model, the laser point cloud data is deeply classified to obtain the tunnel excavation section elevation, excavation profile size and over-excavation and under-excavation data;

[0083] The rebound test data is deeply classified through the strength analysis model to obtain the concrete strength information;

[0084] The quality assessment module is configured to: combine multiple model algorithms and standard specifications for tunnel construction quality inspection, and call the project data stored in the database to evaluate the construction quality of the drill and blast tunnel.

[0085] Embodiment 3

[0086] The purpose of this embodiment is to provide a computer-readable storage medium.

[0087] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in a method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as described in Example 1 of the present disclosure.

[0088] Embodiment 4

[0089] The purpose of this embodiment is to provide an electronic device.

[0090] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in a method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as described in Example 1 of the present disclosure are implemented.

[0091] The steps involved in the apparatuses of the above embodiments 2, 3 and 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0092] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, 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. The present invention is not limited to any specific combination of hardware and software.

[0093] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A drilling and blasting tunnel construction quality assessment method based on multi-source heterogeneous data. It is characterized in that include: Collect various data during tunnel construction; Adding a first label after preprocessing the collected data; The data after adding the first label is deeply classified and then transmitted to the tunnel construction quality database for classified storage; Combining multiple model algorithms and standard specifications for tunnel construction quality inspection, the project data stored in the database is used to evaluate the construction quality of drill and blast tunnels; The deep classification of the data after adding the first label includes: sending the data to the corresponding interpretation model for interpretation according to the first label, and classifying and packaging the interpreted data and transmitting them to the cloud for data processing, and deeply classifying the data in the cloud; The deep classification of data in the cloud includes: deep classification of image data based on an image recognition model to obtain concrete leakage, cracks and water leakage data; Based on the cloud processing model, the radar grayscale image data is deeply classified to obtain the thickness and density of concrete; Based on the point cloud processing model, the laser point cloud data is deeply classified to obtain the tunnel excavation section elevation, excavation profile size and over-excavation and under-excavation data; The rebound test data is deeply classified through the strength analysis model to obtain the concrete strength information.

2. A method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as claimed in claim 1, It is characterized in that The various data collected during the drilling and blasting tunnel construction process include: during the drilling and blasting tunnel construction process, using a camera to collect concrete leakage, cracks and water leakage image data; using a geological radar to collect radar grayscale image data of concrete thickness and density; using a three-dimensional laser scanning device to collect laser point cloud data of tunnel excavation elevation and excavation size; using a cloud rebound instrument to collect rebound detection data of concrete strength.

3. A method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as claimed in claim 2, It is characterized in that The preprocessing of the collected data includes: identifying the format of the data and classifying the data according to preset data types.

4. A method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as claimed in claim 3, It is characterized in that The preprocessed data is assigned a first label, where the first label includes a data type, a detection location, and a detection time.

5. A method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as claimed in claim 1, It is characterized in that After the data after adding the first label is deeply classified, the method further includes: assigning a second label to the data obtained after the deep classification, the second label including the data type, the detection item, the detection time and the detection location; The deeply classified data are matched to the tunnel construction quality database of each inspection project according to the second label for classification and storage.

6. A method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as claimed in claim 1, It is characterized in that The tunnel construction quality database includes: an excavation parameter information database, a primary support parameter information database and a lining parameter information database.

7. A method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as claimed in claim 6, It is characterized in that The excavation parameter information database is used to store the excavation section elevation, excavation profile dimensions and over-excavation and under-excavation data of the tunnel; The primary support parameter information database is used to store the thickness, density, flatness, leakage and surface crack data of shotcrete; The lining parameter information database is used to store lining concrete thickness, density, strength, water leakage and surface crack data.

8. A drilling and blasting tunnel construction quality assessment system based on multi-source heterogeneous data. It is characterized in that include: The data collection module is configured to: collect various data during the tunnel construction process; The data preprocessing module is configured to: preprocess the collected data and then add a first label; The data classification and storage module is configured to: perform deep classification on the data after adding the first label and then transmit the data to the tunnel construction quality database for classification and storage; The deep classification of the data after adding the first label includes: sending the data to the corresponding interpretation model for interpretation according to the first label, and classifying and packaging the interpreted data and transmitting them to the cloud for data processing, and deeply classifying the data in the cloud; The deep classification of data in the cloud includes: deep classification of image data based on an image recognition model to obtain concrete leakage, cracks and water leakage data; Based on the cloud processing model, the radar grayscale image data is deeply classified to obtain the thickness and density of concrete; Based on the point cloud processing model, the laser point cloud data is deeply classified to obtain the tunnel excavation section elevation, excavation profile size and over-excavation and under-excavation data; The rebound test data is deeply classified through the strength analysis model to obtain the concrete strength information; The quality assessment module is configured to: combine multiple model algorithms and standard specifications for tunnel construction quality inspection, and call the project data stored in the database to evaluate the construction quality of the drill and blast tunnel.

9. A computer-readable storage medium having a program stored thereon, It is characterized in that When the program is executed by a processor, the steps in the method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the steps in the method for evaluating the construction quality of a tunnel using a drilling and blasting method based on multi-source heterogeneous data as described in any one of claims 1 to 7 are implemented.