Tunnel blasting damage automatic identification system
Through the automatic tunnel blasting damage recognition system combining data acquisition, numerical simulation and intelligent identification technology, the problems of low efficiency and poor accuracy of traditional detection methods are solved, and accurate monitoring and evaluation of damage after tunnel blasting is realized, and detection efficiency and identification are improved. Accuracy.
Patent Information
- Application Number
- CN202411565601.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2025-02-18
AI Technical Summary
Traditional tunnel blasting damage detection methods rely on manual experience and naked eye observation, and have problems with low detection efficiency and poor accuracy, and it is difficult to meet the needs of real-time monitoring and evaluation during construction.
An automated tunnel blasting damage recognition system was designed, combining data acquisition, numerical simulation and intelligent recognition technology, data was collected through high-resolution cameras and laser scanners, and damage recognition and stress simulation were used to use deep learning algorithms and finite element analysis. Generate a security assessment report.
It realizes automatic detection and evaluation of damage after tunnel blasting, improves detection efficiency and accuracy, can analyze stress status in real time, assist in judging damage risks, and continuously improves recognition accuracy through deep learning.
Smart Images
Figure CN119470437A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of tunnel construction, in particular to an automatic identification system for tunnel blasting damage. Background Art
[0002] Blasting operations during tunnel construction often cause certain damage to surrounding structures. Traditional damage detection methods mainly rely on manual experience and visual observation, which have problems such as low detection efficiency and poor accuracy. In addition, with the advancement of construction technology, the demand for real-time monitoring and evaluation of tunnel blasting damage is increasing. Therefore, it is particularly important to develop a system that can automatically identify tunnel blasting damage. Summary of the invention
[0003] The purpose of the present invention is to provide an automatic identification system for tunnel blasting damage, which can realize accurate monitoring and evaluation of tunnel damage through the combination of data acquisition, numerical simulation and intelligent identification technology.
[0004] To achieve the above-mentioned object, the present invention proposes an automatic identification system for tunnel blasting damage, characterized in that the system comprises a damage identification module, a data acquisition module, a numerical simulation module and a control system, for realizing automatic detection and evaluation of damage after tunnel blasting.
[0005] Preferably, the data acquisition module uses a high-resolution camera and a laser scanner to collect image data and three-dimensional point cloud data in the tunnel in real time.
[0006] Preferably, the damage identification module processes the collected image data through a convolutional neural network (CNN) based on a deep learning algorithm to automatically identify the type and degree of damage to the tunnel.
[0007] Preferably, the numerical simulation module uses finite element analysis (FEM) to simulate the stress changes caused by tunnel blasting and generate a stress distribution diagram.
[0008] Preferably, the numerical simulation module is characterized in that the calculation of the stress change is based on the following formula:
[0009] σ=F / A (1)
[0010] Among them, σ is stress, F is force, and A is cross-sectional area.
[0011] Preferably, the control system generates a corresponding safety assessment report through comprehensive analysis of the damage identification results and the stress distribution diagram.
[0012] Preferably, the safety assessment report is evaluated according to the following mathematical model:
[0013] R=α·D+β·S (2)
[0014] Among them, R is the safety assessment result, D is the damage degree, S is the stress state, and α and β are weight coefficients.
[0015] Preferably, the system can automatically generate time series data of damage detection to facilitate subsequent analysis and decision making.
[0016] Preferably, the deep learning algorithm can gradually improve the accuracy and speed of identifying tunnel damage through continuous learning and training.
[0017] Preferably, the system is scalable and can integrate other sensor modules to improve the comprehensiveness and accuracy of monitoring.
[0018] The beneficial effects of the present invention based on its technical solution are:
[0019] 1. The present invention can automatically identify the damage after tunnel blasting, thus improving the detection efficiency and accuracy;
[0020] 2. Through numerical simulation technology, the system can analyze the stress state of the tunnel in real time and assist in determining damage risks;
[0021] 3. Combined with deep learning technology, the system can continuously learn and improve recognition accuracy to adapt to different construction environments;
[0022] 4. The system is scalable and can integrate multiple sensors according to needs to improve the comprehensiveness of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 This is a flow chart of an automatic identification system for tunnel blasting damage according to the present invention;
[0024] Figure 2 It is a schematic diagram of the damage identification system in the present invention;
[0025] Figure 3 It is the arrangement diagram of the tunnel monitoring points in the present invention;
[0026] Figure 4 It is a schematic diagram of intelligent prediction damage identification in the present invention;
[0027] Figure 5 It is a schematic diagram of numerical simulation damage identification in the present invention;
[0028] 1-Damage identification module; 2-Data acquisition module; 21-High-resolution camera; 22-Laser scanner; 3-Numerical simulation module; 4-Control system; 5-Computer system; 6-Tunnel construction parameter module; 7-Tunnel face; 8-Schematic diagram of intelligent prediction damage identification principle; 81-Damage parameter input terminal; 82-Damage parameter output terminal; 9-Numerical simulation modeling module; 92-Numerical simulation data output module; 91-Numerical simulation system; 10-Monitoring data storage; DETAILED DESCRIPTION
[0029] In order to achieve the purpose of the present invention and to better understand the technical solution and effects, the embodiments of the present invention will be further described in conjunction with the accompanying drawings.
[0030] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for controlling over-excavation and under-excavation in a mining tunnel excavation according to the present invention; in order to achieve the above-mentioned purpose, the purpose of the present invention is to provide an automatic identification system for tunnel blasting damage, which realizes accurate monitoring and evaluation of tunnel damage through the combination of data acquisition, numerical simulation and intelligent identification technology.
[0031] To achieve the above-mentioned purpose, the present invention proposes an automatic identification system for tunnel blasting damage, characterized in that the system includes a damage identification module, a data acquisition module, a numerical simulation module and a control system, which is used to realize automatic detection and evaluation of damage after tunnel blasting. Figure 2 , 1- damage identification module; 2- data acquisition module; 3- numerical simulation module; 4- control system; 5- computer system; 6- tunnel construction parameter module.
[0032] The data acquisition module uses a high-resolution camera and a laser scanner to collect image data and three-dimensional point cloud data in the tunnel in real time. Figure 3 , 21- high-resolution camera; 22- laser scanner.
[0033] The damage identification module is based on a deep learning algorithm and processes the collected image data through a convolutional neural network (CNN) to automatically identify the type and extent of damage in the tunnel. Figure 4 , 8-Schematic diagram of intelligent prediction damage identification principle; 81-damage parameter input terminal; 82-damage parameter output terminal.
[0034] The numerical simulation module uses the finite element analysis method (FEM) to simulate the stress changes caused by tunnel blasting and generate stress distribution diagrams. Figure 5 , 9- numerical simulation modeling module; 92- numerical simulation data output module; 91- numerical simulation system; 10- monitoring data storage.
[0035] The numerical simulation module is characterized in that the calculation of the stress change is based on the following formula:
[0036] σ=F / A (1)
[0037] Among them, σ is stress, F is force, and A is cross-sectional area.
[0038] The control system generates a corresponding safety assessment report through comprehensive analysis of the damage identification results and the stress distribution diagram.
[0039] The safety assessment report is evaluated based on the following mathematical model:
[0040] R=α·D+β·S (2)
[0041] Among them, R is the safety assessment result, D is the damage degree, S is the stress state, and α and β are weight coefficients.
[0042] The system can automatically generate time series data of damage detection to facilitate subsequent analysis and decision-making. The deep learning algorithm can gradually improve the accuracy and speed of identifying tunnel damage through continuous learning and training.
[0043] The system is scalable and can be integrated with other sensor modules to improve the comprehensiveness and accuracy of monitoring.
Claims
1. The present invention proposes an automatic identification system for tunnel blasting damage, which is characterized by: The system includes a damage identification module, a data acquisition module, a numerical simulation module and a control system, and is used to realize automatic detection and evaluation of damage after tunnel blasting.
2. The automatic identification system for tunnel blasting damage according to claim 1 is characterized in that: The data acquisition module uses a high-resolution camera and a laser scanner to collect image data and three-dimensional point cloud data in the tunnel in real time.
3. The automatic identification system for tunnel blasting damage according to claim 1 is characterized in that: The damage identification module is based on a deep learning algorithm and processes the collected image data through a convolutional neural network (CNN) to automatically identify the type and degree of damage to the tunnel.
4. The automatic identification system for tunnel blasting damage according to claim 1 is characterized in that: The numerical simulation module uses the finite element analysis method (FEM) to simulate the stress changes caused by tunnel blasting and generate a stress distribution diagram.
5. The numerical simulation module according to claim 4, characterized in that: The calculation of the stress change is based on the following formula: σ=F / A (1) Among them, σ is stress, F is force, and A is cross-sectional area.
6. The automatic identification system for tunnel blasting damage according to claim 1 is characterized in that: The control system generates a corresponding safety assessment report through comprehensive analysis of the damage identification results and the stress distribution diagram.
7. The control system according to claim 6, characterized in that: The safety assessment report is evaluated based on the following mathematical model: R=α·D+β·S (2) Among them, R is the safety assessment result, D is the damage degree, S is the stress state, and α and β are weight coefficients.
8. The automatic identification system for tunnel blasting damage according to claim 1 is characterized in that: The system can automatically generate time series data of damage detection to facilitate subsequent analysis and decision-making.
9. The automatic identification system for tunnel blasting damage according to claim 1, characterized in that: The deep learning algorithm can gradually improve the accuracy and speed of identifying tunnel damage through continuous learning and training.
10. The automatic identification system for tunnel blasting damage according to claim 1, characterized in that: The system is scalable and can be integrated with other sensor modules to improve the comprehensiveness and accuracy of monitoring.