Tunnel construction quality evaluation system and method

Abstract

The invention discloses a tunnel construction quality evaluation system and method. The evaluation system comprises a data acquisition module, a quality evaluation standard system, an early warning and notification module and a data management module. Wherein the data acquisition module is used for acquiring construction vehicle data, construction site sensors and site photographing; the quality evaluation standard system comprises drilling quality evaluation, back break evaluation, primary support thickness evaluation, anchor rod construction quality evaluation, waterproof and drainage pipe quality evaluation, steel bar binding quality evaluation, secondary lining quality evaluation and primary support flatness evaluation; the early warning and notification module integrates early warning signals from all the evaluation modules; and the data management module is responsible for storing data generated by each independent module and executing cross-module data analysis. According to the tunnel construction quality evaluation system, by integrating advanced monitoring equipment, an automatic algorithm and comprehensive data analysis, the quality control effect in the tunnel construction process is remarkably improved.

Description

Technical Field

[0001] The invention relates to the technical field of building construction management, and in particular to a tunnel construction quality evaluation system and method. Background Art

[0002] In modern infrastructure construction, tunnel engineering is an important part of transportation networks and urban construction. Its construction quality is directly related to the safety and economic benefits of the project. The tunnel construction process involves multiple complex processes, including drilling, primary support installation, waterproofing measures, steel bar binding and concrete pouring. The quality of each step must be strictly controlled to ensure the stability and durability of the final structure.

[0003] Traditional tunnel construction quality evaluation methods mainly rely on manual inspection, such as visual inspection and simple manual testing on site by experienced engineers and technicians. Manual inspection usually requires a lot of time and manpower, especially in large-scale or geographically complex tunnel projects. With the development of science and technology, especially the advancement of information technology and automation technology, modern tunnel construction urgently needs a new quality evaluation system that can automatically collect and analyze quality data, provide real-time feedback and early warning, so as to improve evaluation efficiency, reduce human errors, optimize resource allocation, and ultimately improve the construction quality and safety of the entire tunnel project.

[0004] As the scale and complexity of tunnel construction projects continue to increase, existing quality evaluation methods can no longer meet the needs of high efficiency and high accuracy. Specifically, existing technologies face the following major shortcomings:

[0005] 1. Inefficiency: Traditional manual inspection methods are time-consuming and labor-intensive, and their efficiency is extremely limited, especially in large tunnel projects or those with complex terrain. This inefficiency may lead to project delays and increase engineering costs.

[0006] 2. Accuracy and consistency issues: Since the quality evaluation process is highly dependent on the experience and judgment of individual engineers or technicians, different inspectors may obtain inconsistent evaluation results. This subjectivity may make it difficult to achieve standardization and regularization of quality control.

[0007] 3. Lack of real-time performance: Traditional methods have serious defects in response time. Quality problems found cannot be dealt with immediately, and sometimes they cannot be effectively resolved before they become serious safety hazards.

[0008] 4. Difficulties in data integration and analysis: Existing technologies make it difficult to effectively integrate and deeply analyze the collected data, which limits the ability to extract insights from the data to guide future quality improvement measures.

[0009] In view of the above-mentioned shortcomings of the prior art, the present invention proposes a new tunnel construction quality evaluation system.

[0010] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0011] The purpose of the present invention is to provide a tunnel construction quality evaluation system and method to solve the problems existing in the prior art.

[0012] In order to achieve the above object, the present invention adopts the following technical solutions:

[0013] The present invention provides a tunnel construction quality evaluation system, which includes: a data acquisition module, a quality evaluation standard system, an early warning and notification module, and a data management module; wherein:

[0014] The data acquisition module is used to collect construction vehicle data, construction site sensor data and on-site photography; and then transmit the collected data to the quality evaluation standard system;

[0015] The quality evaluation standard system includes drilling quality evaluation, over-excavation and under-excavation evaluation, primary support thickness evaluation, anchor construction quality evaluation, drainage pipe quality evaluation, steel bar binding quality evaluation, secondary lining quality evaluation and primary support flatness evaluation;

[0016] The warning and notification module integrates warning signals from all evaluation modules; when any module detects a potential quality problem, the module will comprehensively consider relevant data from other modules to determine whether it is necessary to upgrade the warning level or expand the notification scope;

[0017] The data management module is responsible for storing the data generated by each independent module and performing cross-module data analysis; through this analysis, possible correlations and patterns between different evaluation modules are identified.

[0018] Further, the drilling quality evaluation is specifically as follows:

[0019] High-precision geological radar and laser scanners are used to monitor the diameter, depth and angle of the borehole in real time. By comparing with the design parameters, the system evaluates the deviation of the borehole in real time and automatically records all data. If the drilling parameters exceed the preset safety range, the system will immediately trigger an early warning and notify the responsible personnel at the construction site through mobile terminals so that corrective measures can be taken quickly.

[0020] The evaluation of drilling quality adopts error analysis algorithm, including calculating the deviation between measured value and designed value; the diameter, depth and angle deviation of the drilling hole will be calculated by the following formula:

[0021]

[0022] in Indicates deviation, It is the actual value measured by geological radar and laser scanner. is a design parameter; if If it exceeds the preset safety range, the system will automatically trigger an early warning.

[0023] Furthermore, the over-excavation and under-excavation evaluation is specifically as follows:

[0024] Utilize 3D measuring equipment to measure the actual geometry of the excavation surface and automatically calculate the difference from the designed excavation volume; accurately point out any over-excavation or under-excavation. When it exceeds the permitted standards of the project, the system will automatically issue an early warning and record relevant data to ensure that the construction strategy can be adjusted in a timely manner;

[0025] The quantitative assessment of over-break and under-break will be completed through the volume calculation formula, which is as follows:

[0026] ;

[0027] in Indicates the over-excavation volume. and They represent the volumes of actual excavation and designed excavation respectively; this calculation is achieved by acquiring data with 3D measuring equipment to ensure the accuracy and efficiency of each excavation.

[0028] Further, the initial support thickness evaluation is as follows:

[0029] The thickness of the shotcrete layer is monitored by sensors embedded in it. Through real-time data feedback, the system evaluates whether the initial support thickness meets the design specification requirements. If the thickness is detected to be lower than the standard value, the system will automatically issue an early warning and notify the engineering technicians by email or SMS to ensure timely reinforcement.

[0030] Compliance testing of primary branch thickness will utilize statistical analysis methods, specifically using the Z-score formula to evaluate the standardized deviation of thickness:

[0031] ;

[0032] in is the measured initial support thickness, and are the mean and standard deviation of historical data respectively; if If the value exceeds a certain threshold, the system will determine it as quality abnormality and issue an early warning.

[0033] Further, the anchor construction quality evaluation is as follows:

[0034] Sensors are used to monitor the installation depth, angle and tension of the anchors. All data are compared with the design specifications in real time to ensure that each anchor is installed in strict accordance with the technical requirements. If there is any deviation, the system will immediately trigger an early warning and recommend adjustments or re-construction.

[0035] The quality control of anchor bolts will apply vector analysis to ensure installation accuracy; by calculating the angular deviation between the actual installation angle of the anchor bolt and the designed angle, using the cosine theorem:

[0036] ;

[0037] in is the angular deviation, and Represent the design vector and measured vector respectively; the system monitors the installation accuracy in real time through this method.

[0038] Furthermore, the quality evaluation of the drainage pipe is as follows:

[0039] Detect the installation position and connection sealing of the drainage pipe to ensure that each part of the drainage system is correctly installed according to the design standards; through the waterproof performance test, the system evaluates the overall effect of the drainage system. If leakage or other problems are found, the system will automatically issue an early warning.

[0040] Further, the steel bar binding quality evaluation is as follows:

[0041] Using visual recognition technology, the system conducts a comprehensive inspection of the position, spacing and binding of steel bars; after comparing with the design drawings, the system instantly identifies any binding work that does not meet the specifications and prompts the construction team to make corrections.

[0042] Furthermore, the secondary lining quality evaluation is specifically as follows:

[0043] The thickness and density of the secondary lining are monitored through embedded sensors and external scanning equipment to ensure that the secondary lining structure is intact and free of defects; the system will continuously monitor and record relevant data to evaluate the overall quality of the secondary lining and issue timely warnings when any problems are found.

[0044] Further, the initial support flatness evaluation is specifically as follows:

[0045] Using a laser flatness detector, the system accurately measures the surface of the primary support. After data analysis, the system will evaluate whether the flatness of the primary support meets the project requirements. Any deviation beyond the allowable deviation will trigger an early warning, and the system will provide specific adjustment suggestions to ensure that quality standards are met.

[0046] A method for evaluating tunnel construction quality, the method comprising the following steps:

[0047] Step 1: Design quality evaluation index system:

[0048] Indicator formulation: define comprehensive quality evaluation indicators, covering drilling quality, over-break and under-break, primary support thickness, anchor construction, drainage pipe installation, steel bar binding, secondary lining construction and primary support flatness;

[0049] Hierarchical classification: Classify the evaluation indicators into process quality indicators and overall project quality indicators to ensure quality monitoring from both micro and macro levels;

[0050] Step 2: Data collection and preprocessing:

[0051] Automated data collection: Use on-site sensors and scanning equipment to monitor key parameters during construction in real time and automatically transmit data to a central database;

[0052] Preprocessing and classification: Preprocess the collected data, including denoising, standardization and classification, to optimize the subsequent data analysis and learning process;

[0053] Step 3: Deep learning model construction and training:

[0054] Model framework construction: Create a deep learning model, including a data input layer, multiple hidden layers, and an output layer, to handle complex data relationships and predict quality assessment results;

[0055] Continuous learning and optimization: Train and fine-tune the model based on historical data and continuously collected new data to continuously improve the accuracy and response speed of the model;

[0056] Step 4: Real-time quality evaluation and early warning:

[0057] Real-time evaluation execution: Input real-time data into the model for analysis, evaluate the quality status of each process, and ensure immediate access to evaluation results;

[0058] Activation of the early warning mechanism: Based on the evaluation results of the model, if quality problems or deviations are detected, the early warning system will be activated immediately and relevant personnel will be informed through the electronic notification system;

[0059] Step 5: Quality feedback and decision support:

[0060] Quality feedback system: Display real-time and historical quality data through a visual dashboard, providing the project management team with intuitive quality status and trend analysis;

[0061] Decision support: Using the data analysis results provided by the deep learning model to support the construction management team in making scientific decisions, including adjusting construction technology, improving processes, or reallocating resources;

[0062] Step 6: Continuous iteration of models and systems:

[0063] Model iteration: Continuously optimize and adjust the parameters of the deep learning model based on new problems and challenges encountered in actual construction;

[0064] System evaluation and upgrade: Regularly evaluate the effectiveness of the entire quality evaluation system, and upgrade the system and expand its functions based on the evaluation results and technological progress.

[0065] By adopting the above technical solution, the present invention has the following beneficial effects:

[0066] Improve evaluation efficiency: Through automated data collection and processing, manual intervention is significantly reduced, the quality evaluation process is accelerated, and the entire evaluation process is made more efficient and economical.

[0067] Enhanced evaluation accuracy and consistency: The system uses standardized evaluation indicators and algorithms to reduce the impact of human factors and ensure that the evaluation results of different projects and at different time points are highly consistent and repeatable.

[0068] Real-time monitoring and early warning: Integrate real-time data processing and early warning mechanisms to detect quality problems in the early stages and notify relevant personnel, effectively avoiding the deterioration of problems and improving the safety management level of tunnel construction.

[0069] Optimize data management and decision support: The system can effectively store and analyze the collected data in a structured manner, provide data-based insights, support management to make more scientific decisions, and improve resource allocation efficiency.

[0070] Through these technological innovations, the present invention not only solves the limitations of the existing technology, but also provides a more efficient, accurate and intelligent tunnel construction quality evaluation tool, which helps to improve the quality management level of the entire industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0072] Figure 1 A structural diagram of a tunnel construction quality evaluation system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0075] Combination Figure 1 As shown, the embodiment of the present invention provides a new tunnel construction quality evaluation system; including: a data acquisition module, a quality evaluation standard system, an early warning and notification module and a data management module; wherein,

[0076] The data acquisition module is used to collect construction vehicle data, construction site sensor data and on-site photography; and then transmit the collected data to the quality evaluation standard system;

[0077] The quality evaluation standard system includes drilling quality evaluation, over-excavation and under-excavation evaluation, primary support thickness evaluation, anchor construction quality evaluation, drainage pipe quality evaluation, steel bar binding quality evaluation, secondary lining quality evaluation and primary support flatness evaluation;

[0078] The warning and notification module integrates warning signals from all evaluation modules; when any module detects a potential quality problem, the module will comprehensively consider relevant data from other modules to determine whether it is necessary to upgrade the warning level or expand the notification scope;

[0079] The data management module is responsible for storing the data generated by each independent module and performing cross-module data analysis; through this analysis, possible correlations and patterns between different evaluation modules are identified.

[0080] The specific rating methods for each evaluation unit in the quality evaluation standard system are as follows:

[0081] Drilling quality evaluation:

[0082] The drilling process is one of the key processes in tunnel construction, and its quality directly affects the safety and efficiency of subsequent construction. This system uses high-precision geological radar and laser scanners to monitor the diameter, depth and angle of the borehole in real time. By comparing with the design parameters, the system can evaluate the deviation of the borehole in real time and automatically record all data. If the drilling parameters exceed the preset safety range, the system will immediately trigger an early warning and notify the responsible personnel at the construction site through the mobile terminal so that corrective measures can be taken quickly.

[0083] The evaluation of drilling quality adopts the error analysis algorithm, which mainly includes calculating the deviation between the measured value and the designed value. The diameter, depth and angle deviation of the drilling hole will be calculated by the following formula:

[0084]

[0085] in Indicates deviation, It is the actual value measured by geological radar and laser scanner. is a design parameter. If If it exceeds the preset safety range, the system will automatically trigger an early warning.

[0086] Super under-digging evaluation:

[0087] Following the borehole evaluation, the over-break and under-break evaluation focuses on the control of earthwork volume during tunnel excavation, which is extremely important for structural stability and material costs. The system uses 3D measurement equipment to measure the actual geometry of the excavation surface and automatically calculates the difference from the designed excavation volume. This module can accurately point out any over-break or under-break. When it exceeds the allowed standards of the project, the system will automatically issue an early warning and record relevant data to ensure that the construction strategy can be adjusted in time.

[0088] The quantitative assessment of over-break and under-break will be completed through the volume calculation formula, which is as follows:

[0089]

[0090] in Indicates the over-excavation volume. and Representing the actual excavation volume and the designed excavation volume respectively. This calculation is achieved by obtaining data with 3D measuring equipment to ensure the accuracy and efficiency of each excavation.

[0091] Initial support thickness evaluation:

[0092] The thickness of the primary support is an important parameter for the safety of the tunnel support structure. After evaluating the drilling and over-excavation, the system monitors the thickness through sensors embedded in the shotcrete layer. Through real-time data feedback, the system evaluates whether the thickness of the primary support meets the design specifications. If the thickness is detected to be below the standard value, the system will automatically issue an early warning and notify the engineering technicians by email or SMS to ensure timely reinforcement.

[0093] Compliance testing of primary branch thickness will utilize statistical analysis methods, specifically using the Z-score formula to evaluate the standardized deviation of thickness:

[0094]

[0095] in is the measured initial support thickness, and are the mean and standard deviation of historical data respectively. If the value exceeds a certain threshold, the system will determine it as quality abnormality and issue an early warning.

[0096] Anchor construction quality evaluation:

[0097] The accuracy of anchor bolt installation is critical to the stability of the tunnel. The system uses specially designed sensors to monitor the installation depth, angle and tension of the anchor bolts. All data is compared with the design specifications in real time to ensure that each anchor bolt is installed in strict accordance with technical requirements. If there is any deviation, the system will immediately trigger an early warning and recommend adjustments or re-construction.

[0098] The quality control of anchor bolts will apply vector analysis to ensure installation accuracy. By calculating the angular deviation between the actual installation angle of the anchor bolt and the design angle, the cosine theorem is used:

[0099]

[0100] in is the angular deviation, and Represent the design vector and the measured vector respectively. The system monitors the installation accuracy in real time through this method.

[0101] Quality evaluation of drainage pipes:

[0102] The effectiveness of the drainage system is directly related to the waterproof and drainage capabilities of the tunnel. This system detects the installation position and connection tightness of the drainage pipes to ensure that every part of the drainage system is correctly installed according to the design standards. Through the waterproof performance test, the system evaluates the overall effectiveness of the drainage system. If leaks or other problems are found, the system will automatically issue an early warning.

[0103] Evaluation of steel bar binding quality:

[0104] In the structural support system, the correct arrangement and binding of steel bars is the key to ensuring the strength and durability of the tunnel structure. Using visual recognition technology, the system conducts a comprehensive inspection of the position, spacing and binding of steel bars. After comparing with the design drawings, the system can instantly identify any binding work that does not meet the specifications and prompt the construction team to make corrections.

[0105] Secondary lining quality evaluation:

[0106] The quality of the secondary lining construction directly affects the final quality and service life of the tunnel. The system monitors the thickness and density of the secondary lining through embedded sensors and external scanning equipment to ensure that the secondary lining structure is intact and free of defects. The system will continuously monitor and record relevant data to evaluate the overall quality of the secondary lining and issue early warnings in time if any problems are found.

[0107] Initial support flatness evaluation:

[0108] The flatness of the primary support is one of the important indicators for evaluating the overall quality of the tunnel. Using a laser flatness detector, the system accurately measures the surface of the primary support. After data analysis, the system will evaluate whether the flatness of the primary support meets the project requirements. Any deviation beyond the allowable deviation will trigger an early warning, and the system will provide specific adjustment suggestions to ensure that quality standards are met.

[0109] In order to ensure the efficient operation of the tunnel construction quality evaluation system and optimize data flow, this system is designed with close links between modules and data integration mechanisms to ensure that each evaluation module not only operates independently but also supports and enhances each other to form a collaborative comprehensive evaluation network.

[0110] Data sharing and real-time updates:

[0111] All evaluation modules—such as drilling quality evaluation, over-excavation evaluation, and primary support thickness evaluation—are connected to a central database that receives data from field equipment modules in real time. This ensures that any problems or changes detected in one module are immediately known and processed by other modules. For example, if the drilling quality evaluation module finds that the drilling deviation is large, this information will immediately notify the primary support flatness evaluation module, because the drilling deviation may affect the installation quality of the primary support.

[0112] Integration of early warning systems:

[0113] The early warning and notification module, as a core interconnected node, integrates early warning signals from all evaluation modules. When any module detects a potential quality problem, the early warning system will comprehensively consider the relevant data from other modules to determine whether it is necessary to upgrade the warning level or expand the notification scope. For example, if the anchor construction quality evaluation module and the rebar binding quality evaluation module report problems at the same time, the system may determine that this indicates a wider structural problem and issue a wider warning.

[0114] Cross-module data analysis:

[0115] The data management module is responsible not only for storing the data generated by each independent module, but also for performing cross-module data analysis. Through this analysis, possible correlations and patterns between different evaluation modules can be identified. For example, analyzing the data of secondary lining quality evaluation and primary support flatness evaluation may reveal that the quality of primary support construction directly affects the quality of secondary lining construction, which can help improve the construction process and prevent problems in advance.

[0116] Optimized decision support:

[0117] The system's advanced algorithms are not limited to data processing within a single module, but also combine data from multiple evaluation modules to support more complex decision-making. This integrated data analysis ensures that project managers can obtain a comprehensive perspective and develop the best construction strategy and quality improvement plan based on the system's global quality evaluation.

[0118] Through this highly integrated and intelligent design, the tunnel construction quality evaluation system can ensure that the various evaluation modules are not only connected at the data level, but also complement and coordinate at the functional and strategic levels, greatly enhancing the overall performance of the system and the accuracy of the evaluation. This system design improves the management efficiency and quality assurance level of tunnel construction projects, and provides a powerful tool for construction teams to face complex and challenging construction environments.

[0119] In order to ensure the high-quality completion of the tunnel construction project, this application has designed a detailed quality evaluation process, which not only covers every link from data collection to real-time evaluation, but also integrates advanced deep learning models to achieve data-driven decision support and continuous improvement. The following is a detailed description of the quality evaluation steps:

[0120] Step 1: Design a quality evaluation index system

[0121] Indicator formulation: Define comprehensive quality evaluation indicators, covering drilling quality, over-break and under-break, primary support thickness, anchor construction, drainage pipe installation, steel bar binding, secondary lining construction and primary support flatness.

[0122] Hierarchical classification: Classify the evaluation indicators into process quality indicators and overall project quality indicators to ensure quality monitoring from both micro and macro levels.

[0123] Step 2: Data collection and preprocessing

[0124] Automated Data Collection: Utilize on-site sensors and scanning equipment to monitor key parameters of the construction process in real time and automatically transmit data to a central database.

[0125] Preprocessing and classification: Preprocess the collected data, including denoising, standardization, and classification, to optimize the subsequent data analysis and learning process.

[0126] Step 3: Deep learning model construction and training

[0127] Model framework construction: Create a deep learning model, including a data input layer, multiple hidden layers, and an output layer, to process complex data relationships and predict quality assessment results.

[0128] Continuous learning and optimization: The model is trained and fine-tuned based on historical data and new data that is continuously collected to continuously improve the accuracy and response speed of the model.

[0129] Step 4: Real-time quality evaluation and early warning

[0130] Real-time evaluation execution: Input real-time data into the model for analysis, evaluate the quality status of each process, and ensure immediate access to evaluation results.

[0131] Early warning mechanism activation: Based on the evaluation results of the model, if quality problems or deviations are detected, the early warning system will be activated immediately and relevant personnel will be informed through the electronic notification system.

[0132] Step 5: Quality Feedback and Decision Support

[0133] Quality Feedback System: Displays real-time and historical quality data through a visual dashboard, providing the project management team with intuitive quality status and trend analysis.

[0134] Decision support: Use the data analysis results provided by the deep learning model to support the construction management team in making scientific decisions, such as adjusting construction technology, improving processes, or reallocating resources.

[0135] Step 6: Continuous iteration of models and systems

[0136] Model iteration: Continuously optimize and adjust the parameters of the deep learning model based on new problems and challenges encountered in actual construction.

[0137] System evaluation and upgrade: Regularly evaluate the effectiveness of the entire quality evaluation system, and upgrade the system and expand its functions based on the evaluation results and technological progress.

[0138] Through these steps, the tunnel construction quality evaluation system can ensure efficient and accurate quality control throughout the construction process, greatly improve the project success rate, and reduce risks and costs.

[0139] The tunnel construction quality evaluation system of the present invention significantly improves the quality control effect during tunnel construction by integrating advanced monitoring equipment, automated algorithms and comprehensive data analysis. The main technical benefits of the system are described in detail below:

[0140] 1. Improve evaluation efficiency: Through real-time automated monitoring and evaluation, the system significantly reduces the time and labor required for traditional manual inspection. For example, borehole quality evaluation and over-break and under-break evaluation can be completed in minutes through automatic data collection and instant calculation, while traditional methods may take hours or even longer.

[0141] 2. Enhanced evaluation accuracy and consistency: The system uses high-precision geological radar, laser scanners and various sensors to ensure accurate data collection. Combined with advanced algorithms such as error analysis and statistical analysis, the evaluation results are highly accurate and repeatable, greatly reducing errors and deviations caused by human factors.

[0142] 3. Real-time monitoring and early warning: The system’s early warning mechanism can detect and notify relevant personnel in the early stages of quality problems. For example, if the initial support thickness does not meet the specifications, the system will automatically calculate the deviation and issue an immediate early warning, allowing the engineering team to respond quickly and take remedial measures to avoid further expansion of the problem.

[0143] 4. Optimize data management and decision support: All collected data are stored in a structured manner and used to generate detailed quality reports and trend analysis, which are of great reference value for project management. The comprehensive use of data not only helps management to formulate construction strategies scientifically, but also provides valuable experience and data support for future projects.

[0144] 5. Improve project safety and reduce risks: The system significantly improves the safety standards of tunnel construction through continuous quality monitoring and instant early warning. It reduces safety accidents and structural failures that may be caused by quality problems, thereby reducing the risks and potential economic losses of the entire project.

[0145] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A tunnel construction quality evaluation system, characterized in that: The evaluation system includes: a data collection module, a quality evaluation standard system, an early warning and notification module, and a data management module; wherein, The data acquisition module is used to collect construction vehicle data, construction site sensor data and on-site photography; and then transmit the collected data to the quality evaluation standard system; The quality evaluation standard system includes drilling quality evaluation, over-excavation and under-excavation evaluation, primary support thickness evaluation, anchor construction quality evaluation, drainage pipe quality evaluation, steel bar binding quality evaluation, secondary lining quality evaluation and primary support flatness evaluation; The warning and notification module integrates warning signals from all evaluation modules; when any module detects a potential quality problem, the module will comprehensively consider relevant data from other modules to determine whether it is necessary to upgrade the warning level or expand the notification scope; The data management module is responsible for storing the data generated by each independent module and performing cross-module data analysis; through this analysis, possible correlations and patterns between different evaluation modules are identified.

2. The tunnel construction quality evaluation system according to claim 1, characterized in that: The drilling quality evaluation is as follows: High-precision geological radar and laser scanners are used to monitor the diameter, depth and angle of the borehole in real time. By comparing with the design parameters, the system evaluates the deviation of the borehole in real time and automatically records all data. If the drilling parameters exceed the preset safety range, the system will immediately trigger an early warning and notify the responsible personnel at the construction site through mobile terminals so that corrective measures can be taken quickly. The evaluation of drilling quality adopts error analysis algorithm, including calculating the deviation between measured value and designed value; the diameter, depth and angle deviation of the drilling hole will be calculated by the following formula: ； in Indicates deviation, It is the actual value measured by geological radar and laser scanner. is a design parameter; if If it exceeds the preset safety range, the system will automatically trigger an early warning.

3. The tunnel construction quality evaluation system according to claim 1, characterized in that: The over-excavation and under-excavation evaluation is specifically as follows: Utilize 3D measuring equipment to measure the actual geometry of the excavation surface and automatically calculate the difference from the designed excavation volume; accurately point out any over-excavation or under-excavation. When it exceeds the permitted standards of the project, the system will automatically issue an early warning and record relevant data to ensure that the construction strategy can be adjusted in a timely manner; The quantitative assessment of over-break and under-break will be completed through the volume calculation formula, which is as follows: ； in Indicates the over-excavation volume. and They represent the volumes of actual excavation and designed excavation respectively; this calculation is achieved by acquiring data with 3D measuring equipment to ensure the accuracy and efficiency of each excavation.

4. The tunnel construction quality evaluation system according to claim 1, characterized in that: The initial support thickness evaluation is as follows: The thickness of the shotcrete layer is monitored by sensors embedded in it. Through real-time data feedback, the system evaluates whether the initial support thickness meets the design specification requirements. If the thickness is detected to be lower than the standard value, the system will automatically issue an early warning and notify the engineering technicians by email or SMS to ensure timely reinforcement. Compliance testing of primary branch thickness will utilize statistical analysis methods, specifically using the Z-score formula to evaluate the standardized deviation of thickness: ； in is the measured initial support thickness, and are the mean and standard deviation of historical data respectively; if If the value exceeds a certain threshold, the system will determine it as quality abnormality and issue an early warning.

5. The tunnel construction quality evaluation system according to claim 1, characterized in that: The anchor construction quality evaluation is as follows: Sensors are used to monitor the installation depth, angle and tension of the anchors. All data are compared with the design specifications in real time to ensure that each anchor is installed in strict compliance with the technical requirements. If there is any deviation, the system will immediately trigger an early warning and recommend adjustments or re-construction. The quality control of anchor bolts will apply vector analysis to ensure installation accuracy; by calculating the angular deviation between the actual installation angle of the anchor bolt and the designed angle, using the cosine theorem: ； in is the angular deviation, and Represent the design vector and measured vector respectively; the system monitors the installation accuracy in real time through this method.

6. The tunnel construction quality evaluation system according to claim 1, characterized in that: The quality evaluation of the drainage pipe is as follows: Detect the installation position and connection sealing of the drainage pipe to ensure that each part of the drainage system is correctly installed according to the design standards; through the waterproof performance test, the system evaluates the overall effect of the drainage system. If leakage or other problems are found, the system will automatically issue an early warning.

7. The tunnel construction quality evaluation system according to claim 1, characterized in that: The steel bar binding quality evaluation is as follows: Using visual recognition technology, the system conducts a comprehensive inspection of the position, spacing and binding of steel bars; after comparing with the design drawings, the system instantly identifies any binding work that does not meet the specifications and prompts the construction team to make corrections.

8. The tunnel construction quality evaluation system according to claim 1, characterized in that: The secondary lining quality evaluation is as follows: The thickness and density of the secondary lining are monitored through embedded sensors and external scanning equipment to ensure that the secondary lining structure is intact and free of defects; the system will continuously monitor and record relevant data to evaluate the overall quality of the secondary lining and issue timely warnings when any problems are found.

9. The tunnel construction quality evaluation system according to claim 1, characterized in that: The initial support flatness evaluation is specifically as follows: Using a laser flatness detector, the system accurately measures the surface of the primary support. After data analysis, the system will evaluate whether the flatness of the primary support meets the project requirements. Any deviation beyond the allowable deviation will trigger an early warning, and the system will provide specific adjustment suggestions to ensure that quality standards are met.

10. A method for evaluating the quality of tunnel construction using the tunnel construction quality evaluation system according to any one of claims 1 to 9, characterized in that: The method comprises the following steps: Step 1: Design quality evaluation index system: Indicator formulation: define comprehensive quality evaluation indicators, covering drilling quality, over-break and under-break, primary support thickness, anchor construction, drainage pipe installation, steel bar binding, secondary lining construction and primary support flatness; Hierarchical classification: Classify the evaluation indicators into process quality indicators and overall project quality indicators to ensure quality monitoring from both micro and macro levels; Step 2: Data collection and preprocessing: Automated data collection: Use on-site sensors and scanning equipment to monitor key parameters during construction in real time and automatically transmit data to a central database; Preprocessing and classification: Preprocess the collected data, including denoising, standardization and classification, to optimize the subsequent data analysis and learning process; Step 3: Deep learning model construction and training: Model framework construction: Create a deep learning model, including a data input layer, multiple hidden layers, and an output layer, to handle complex data relationships and predict quality assessment results; Continuous learning and optimization: Train and fine-tune the model based on historical data and continuously collected new data to continuously improve the accuracy and response speed of the model; Step 4: Real-time quality evaluation and early warning: Real-time evaluation execution: input real-time data into the model for analysis, evaluate the quality status of each process, and ensure immediate access to evaluation results; Activation of the early warning mechanism: Based on the evaluation results of the model, if quality problems or deviations are detected, the early warning system will be activated immediately and relevant personnel will be informed through the electronic notification system; Step 5: Quality feedback and decision support: Quality feedback system: Display real-time and historical quality data through a visual dashboard, providing the project management team with intuitive quality status and trend analysis; Decision support: Using the data analysis results provided by the deep learning model to support the construction management team in making scientific decisions, including adjusting construction technology, improving processes, or reallocating resources; Step 6: Continuous iteration of models and systems: Model iteration: Continuously optimize and adjust the parameters of the deep learning model based on new problems and challenges encountered in actual construction; System evaluation and upgrade: Regularly evaluate the effectiveness of the entire quality evaluation system, and upgrade the system and expand its functions based on the evaluation results and technological progress.

Images