Tunnel construction multi-source sensing fusion dynamic closed-loop control system and self-adaptive deviation correction method

Abstract

The invention relates to the technical field of tunnel engineering construction, in particular to a tunnel construction multi-source sensing fusion dynamic closed-loop control system and a self-adaptive deviation correction method, and the system comprises a multi-source sensor module, a data acquisition and transmission module, a data fusion and analysis module, a control decision module and an execution mechanism and feedback module; through the multi-source sensing fusion technology, various information of tunnel construction can be comprehensively and accurately obtained, the construction deviation is monitored in real time, the precision of tunnel construction is controlled at a higher level, the later rectification cost caused by the construction deviation is reduced, potential safety risks can be found in time in combination with intelligent analysis and early warning functions, and the safety of tunnel construction is improved. Measures are taken in advance for treatment, safety accidents such as tunnel collapse are effectively prevented, and the life safety of constructors is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel engineering construction, and particularly to a multi-source sensing fusion dynamic closed-loop control system and an adaptive deviation correction method for tunnel construction. Background Art

[0002] During the tunnel construction process, accurate measurement, effective monitoring, and timely deviation correction are crucial for ensuring the quality, safety, and progress of the project. Traditional tunnel construction technologies have many deficiencies in these aspects.

[0003] Existing measurement techniques have limited means, mainly relying on conventional measurement instruments such as total stations and levels. The measurement content is limited to basic information such as the geometric dimensions and positions of the tunnel, and it is difficult to obtain key data such as internal stress and strain of the surrounding rock and groundwater pressure. Moreover, these instruments are greatly affected by environmental factors, and the measurement accuracy drops severely in environments with poor light, high humidity, and vibration, unable to meet the high-precision measurement requirements under complex geological conditions;

[0004] In terms of monitoring, monitoring devices are scattered, data collection is incomplete, and there is a lack of systematicness. Various monitoring data (such as displacement, settlement, and stress of the support structure) cannot be effectively integrated, making it difficult for construction personnel to grasp the overall tunnel construction status. In addition, the monitoring frequency is often fixed and cannot be dynamically adjusted according to the construction situation, easily missing key change information;

[0005] In data processing and analysis, manual processing or simple algorithms are mostly used, making it difficult to handle massive and complex data. Valuable information cannot be mined from multi-source data in a timely and accurate manner, resulting in a lack of scientific basis for construction decisions and being unable to effectively guide construction;

[0006] The deviation correction measures are also relatively lagging and rough. Usually, adjustments are made only after obvious deviations, and the deviation correction plan lacks pertinence and does not fully consider factors such as geological conditions and construction techniques, which not only affect the construction progress and quality but may also cause waste of resources. Therefore, a multi-source sensing fusion dynamic closed-loop control system and an adaptive deviation correction method for tunnel construction are proposed. Summary of the Invention

[0007] In view of this, the present invention provides a multi-source sensing fusion dynamic closed-loop control system and an adaptive deviation correction method for tunnel construction to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0008] The technical solution of the present invention is implemented as follows: The multi-source sensing fusion dynamic closed-loop control system for tunnel construction includes a multi-source measurement and monitoring sensor module, a data acquisition and transmission module, an intelligent data fusion and analysis module, an intelligent decision-making and control module, and an execution and feedback module.

[0009] Further preferably, the multi-source measurement and monitoring sensor module includes a laser ranging sensor, a gyroscope, an accelerometer, a pressure sensor, a displacement sensor, a ground penetrating radar, etc. The laser ranging sensor is used to measure the distance between the tunnel face and the constructed section in real time, providing data for construction progress monitoring. The gyroscope and accelerometer are installed on the construction equipment and can accurately measure the attitude changes of the equipment, including information such as angles and inclinations. The pressure sensors are arranged in the surrounding rock and support structure of the tunnel to monitor the surrounding rock pressure and the stress of the support structure. The displacement sensor is used to measure the displacement of the tunnel lining and the surrounding rock, timely detecting potential deformation risks. The ground penetrating radar can detect the geological conditions within a certain range ahead, obtaining geological information in advance. The groundwater sensor monitors the changes in the groundwater level and water pressure. In addition, an unmanned aerial vehicle equipped with a high-definition camera device is used to regularly monitor the tunnel entrance and the surrounding environment, obtaining information on topographic and geomorphic changes. Various sensors work together to ensure comprehensive and accurate collection of multi-source data during the construction process.

[0010] Further preferably, for the data acquisition and transmission module, after the data collected by each sensor undergoes preliminary filtering and preprocessing, including operations such as denoising, filtering, and data filling, to improve the data quality, it is sent to the central control unit through wired or wireless transmission methods. Redundant transmission technology is adopted for transmission. At the same time, the transmitted data is encrypted to prevent the data from being stolen or tampered with during transmission.

[0011] Further preferably, for the intelligent data fusion and analysis module, after the central control unit receives the multi-source sensor data, it first performs data format conversion and standardization processing to make different types of data have a unified format. Deep learning algorithms are used for data fusion. The convolutional neural network (CNN) is used to extract and fuse features from laser scanning data and image data. Through fusion, it can more accurately reflect the actual state of tunnel construction. Big data analysis technology is used to deeply mine historical data and real-time data, predicting possible problems during the construction process, identifying cracks, defects, etc. on the surface of the tunnel lining. The long short-term memory network (LSTM) is used to analyze time series data (such as the changes in strain and pressure over time), predicting data trends. Combining with big data analysis technology, a tunnel construction database is established to store historical data and real-time data, providing data support for subsequent analysis. At the same time, data mining algorithms are used to mine the potential relationships between construction parameters, geological conditions and tunnel deformation and stress from massive data, providing a scientific basis for construction decision-making.

[0012] Further preferably, based on the data fusion and analysis results, the intelligent decision-making and control module generates control instructions by using an expert system and intelligent optimization algorithms. When the measurement data shows that the tunnel has a deviation or the monitoring data indicates a potential safety risk, the system automatically starts the decision-making process. For example, if the tunneling direction of the tunnel deviates from the designed route, the genetic algorithm is used to calculate the optimal deviation correction plan in combination with the geological conditions and current construction parameters, including the thrust adjustment of the propulsion cylinders, the turning angle of the cutter head, etc.; if the surrounding rock pressure is monitored to be close to the warning value, the system automatically adjusts the construction progress according to the risk level, strengthens the support measures, and gives specific construction suggestions, such as increasing the number of bolts, the thickness of shotcrete, etc.

[0013] Further preferably, for the execution and feedback module, the control instructions act on the tunnel construction equipment and the construction process through the actuator. The actuator includes the propulsion system of the shield machine, the cutter head drive system, the support equipment, etc. After the execution operation, the relevant data is collected again by the sensors and fed back to the data acquisition and transmission module to form a dynamic closed-loop control. For example, during the deviation correction process, the attitude and position changes of the shield machine are monitored in real time, and the deviation correction parameters are dynamically adjusted according to the feedback data to ensure that the shield machine accurately returns to the designed route. At the same time, various data during the construction process are recorded for subsequent construction analysis and experience summary to continuously optimize the system decision-making model.

[0014] The multi-source sensing fusion dynamic adaptive deviation correction method for tunnel construction includes the following steps:

[0015] S1. Real-time multi-source data acquisition and deviation calculation;

[0016] S2. Intelligent analysis of deviation causes;

[0017] S3. Formulation of precise deviation correction strategies;

[0018] S4. Deviation correction execution and dynamic adjustment.

[0019] 8. The multi-source sensing fusion dynamic adaptive deviation correction method for tunnel construction according to claim 7, characterized in that: in the S1, during the tunnel construction process, the multi-source sensors continuously collect measurement and monitoring data. The collected real-time data is compared with the design standards to calculate the position deviation, attitude deviation, construction parameter deviation, etc. of the tunnel. For example, the tunnel section data obtained by the laser scanning measuring instrument is compared with the designed section data to calculate the contour deviation; combining the gyroscope, accelerometer and laser ranging data to determine the attitude deviation of the shield machine; comparing the actual tunneling speed, thrust and other construction parameters with the set parameters to obtain the construction parameter deviation.

[0020] Further preferably, in the step S2, once a deviation is detected, the system immediately starts an intelligent analysis program, deeply mines multi-source data by using machine learning algorithms, combines information such as geological conditions, construction techniques, and equipment operation status, and analyzes the causes of the deviation. For example, if the tunneling direction of the shield machine deviates, the system analyzes geological data to determine whether it encounters a stratum with uneven hardness, checks the operation data of the equipment to examine whether the pressure of the propulsion cylinders is balanced, and traces historical construction data to check whether there is an accumulated error. At the same time, referring to the experience cases in the expert knowledge base, a comprehensive judgment is made on the cause of the deviation to improve the accuracy of the analysis.

[0021] Further preferably, in the step S3, according to the cause of the deviation and the real-time construction situation, the intelligent decision-making and control module formulates a precise deviation correction strategy. For the deviation caused by geological conditions, such as the shield machine sinking due to encountering a soft soil stratum, a combination of measures such as increasing the thrust of the bottom propulsion cylinders, adjusting the cutting parameters of the cutter head, and changing the earth excavation volume is taken for deviation correction; for the deviation caused by equipment failures, such as the failure of sensors affecting the measurement accuracy, the sensors are replaced or calibrated in time, and the current state is estimated based on historical data and the data of backup sensors, and the construction parameters are adjusted to maintain the stability of the construction. When formulating the deviation correction strategy, the construction cost, progress, quality, and the impact on the surrounding environment are comprehensively considered, and an optimization algorithm is used to find the optimal deviation correction plan. In the step S4, the deviation correction strategy is implemented by an actuator. During the implementation process, the sensors monitor the deviation correction effect in real time. If the deviation correction effect does not meet the expectation, the system re-analyzes the cause of the deviation, adjusts the deviation correction strategy, and performs the deviation correction operation again until the deviation is controlled within the allowable range. For example, during the deviation correction process of the shield machine, the attitude and position data of the shield machine are collected at regular time intervals, and the deviation correction parameters are fine-tuned according to the actual adjustment situation to ensure that the shield machine can accurately and smoothly return to the designed route. At the same time, the data during the deviation correction process is recorded for subsequent construction analysis and experience summary to continuously optimize the adaptive deviation correction method.

[0022] Due to the adoption of the above technical solutions in the embodiments of the present invention, the following advantages are achieved:

[0023] First, through the multi-source sensing fusion technology, the present invention can comprehensively and accurately obtain various information of tunnel construction, monitor construction deviations in real time, control the accuracy of tunnel construction at a higher level, reduce the later rectification cost caused by construction deviations, and combine the intelligent analysis and early warning functions to timely discover potential safety risks, take measures in advance for treatment, effectively prevent the occurrence of safety accidents such as tunnel collapses, and ensure the life safety of construction workers.

[0024] Second, the adaptive deviation correction method of the present invention can quickly respond to construction deviations, timely adjust construction parameters, and avoid construction stagnation caused by deviation accumulation. At the same time, by optimizing construction decisions and reasonably arranging construction progress, the utilization rate of construction equipment is improved, thereby significantly enhancing the overall efficiency of tunnel construction and shortening the construction period.

[0025] Third, the intelligent data fusion and analysis module of the present invention uses deep learning algorithms and big data technologies to deeply mine and analyze massive multi-source data, extract valuable information from it, and provide a scientific basis for intelligent decision-making. Based on these analysis results, the intelligent decision-making and control module quickly formulates accurate and efficient construction decisions and control instructions. In the face of construction deviations, it can quickly respond and generate the optimal deviation correction plan, significantly improving construction efficiency, reducing unnecessary losses of construction time and costs, realizing the optimal allocation of construction resources, and promoting the construction management towards intelligence and high efficiency.

[0026] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will be readily apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0028] Figure 1 It is a system module diagram of the present invention;

[0029] Figure 2 It is a method flow diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] In the following, only some exemplary embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present invention. Therefore, the drawings and the description are considered to be exemplary in nature rather than restrictive.

[0031] The embodiments of the present invention will be described in detail below with reference to the drawings.

[0032] Such as Figure 1-2As shown in the figure, the embodiment of the present invention provides a multi-source sensing fusion dynamic closed-loop control system for tunnel construction, including a multi-source measurement and monitoring sensor module, a data acquisition and transmission module, an intelligent data fusion and analysis module, an intelligent decision-making and control module, and an execution and feedback module.

[0033] In one embodiment, the multi-source measurement and monitoring sensor module includes a laser rangefinder, a gyroscope, an accelerometer, a pressure sensor, a displacement sensor, and a ground penetrating radar, etc. The laser rangefinder is used to measure the distance between the tunnel face and the constructed section in real time, providing data for construction progress monitoring. The gyroscope and accelerometer are installed on the construction equipment and can accurately measure the attitude changes of the equipment, including information such as angles and inclinations. The pressure sensors are arranged in the surrounding rock and support structure of the tunnel to monitor the surrounding rock pressure and the stress of the support structure. The displacement sensors are used to measure the displacement of the tunnel lining and the surrounding rock to detect potential deformation risks in a timely manner. The ground penetrating radar can detect the geological conditions within a certain range ahead to obtain geological information in advance. The groundwater sensor monitors the changes in the groundwater level and water pressure. In addition, an unmanned aerial vehicle equipped with a high-definition camera device is used to regularly monitor the tunnel entrance and the surrounding environment to obtain topographic and geomorphic change information. All kinds of sensors work together to ensure the comprehensive and accurate acquisition of multi-source data during the construction process.

[0034] In one embodiment, for the data acquisition and transmission module, after the data collected by each sensor undergoes preliminary filtering and preprocessing, including operations such as denoising, filtering, and data filling, to improve the data quality, it is sent to the central control unit through wired or wireless transmission methods. The redundant transmission technology is adopted for transmission. At the same time, the transmitted data is encrypted to prevent the data from being stolen or tampered with during the transmission process.

[0035] In one embodiment, for the intelligent data fusion and analysis module, after the central control unit receives the multi-source sensor data, it first performs data format conversion and standardization processing to make different types of data have a unified format. Deep learning algorithms are used for data fusion. The convolutional neural network (CNN) is used to extract and fuse features from laser scanning data and image data. Through fusion, it can more accurately reflect the actual state of tunnel construction. Big data analysis technology is used to deeply mine historical data and real-time data to predict possible problems during the construction process, identify cracks and defects on the surface of the tunnel lining, etc. The long short-term memory network (LSTM) is used to analyze time series data (such as the change of strain and pressure over time) to predict data trends. Combining with big data analysis technology, a tunnel construction database is established to store historical data and real-time data to provide data support for subsequent analysis. At the same time, data mining algorithms are adopted to mine the potential relationships between construction parameters, geological conditions and tunnel deformation and stress from massive data, providing a scientific basis for construction decision-making.

[0036] In one embodiment, the intelligent decision-making and control module, based on the data fusion and analysis results, uses an expert system and intelligent optimization algorithms to generate control instructions. When the measurement data shows that the tunnel is deviated or the monitoring data indicates potential safety risks, the system automatically starts the decision-making process. For example, if the tunneling direction of the tunnel deviates from the designed route, the genetic algorithm is used to calculate the optimal deviation correction plan in combination with the geological conditions and current construction parameters, including the thrust adjustment of the propulsion cylinders, the turning angle of the cutter head, etc.; if the surrounding rock pressure is monitored to be close to the warning value, the system automatically adjusts the construction progress according to the risk level, strengthens the support measures, and gives specific construction suggestions, such as increasing the number of bolts and the thickness of shotcrete.

[0037] In one embodiment, the execution and feedback module, the control instructions act on the tunnel construction equipment and the construction process through the actuator. The actuator includes the propulsion system of the shield machine, the cutter head drive system, the support equipment, etc. After the execution operation, the relevant data is collected again by the sensor and fed back to the data acquisition and transmission module to form a dynamic closed-loop control. For example, during the deviation correction process, the attitude and position changes of the shield machine are monitored in real time, and the deviation correction parameters are dynamically adjusted according to the feedback data to ensure that the shield machine accurately returns to the designed route. At the same time, the data of each item in the construction process is recorded for subsequent construction analysis and experience summary, and the system decision-making model is continuously optimized.

[0038] The dynamic adaptive deviation correction method for multi-source sensor fusion in tunnel construction includes the following steps:

[0039] S1. Real-time multi-source data acquisition and deviation calculation;

[0040] S2. Intelligent analysis of deviation causes;

[0041] S3. Formulation of precise deviation correction strategies;

[0042] S4. Deviation correction execution and dynamic adjustment.

[0043] 8. The dynamic adaptive deviation correction method for multi-source sensor fusion in tunnel construction according to claim 7, characterized in that: in S1, during the tunnel construction process, the multi-source sensors continuously collect measurement and monitoring data. The collected real-time data is compared with the design standards to calculate the position deviation, attitude deviation, construction parameter deviation, etc. of the tunnel. For example, the tunnel section data obtained by the laser scanning measuring instrument is compared with the design section data to calculate the contour deviation; in combination with the gyroscope, accelerometer and laser ranging data, the attitude deviation of the shield machine is determined; by comparing the actual tunneling speed, thrust and other construction parameters with the set parameters, the construction parameter deviation is obtained.

[0044] In one embodiment, in S2, once a deviation is detected, the system immediately starts an intelligent analysis program, deeply mines multi-source data using machine learning algorithms, combines information such as geological conditions, construction techniques, and equipment operating status, and analyzes the causes of the deviation. For example, if the tunneling direction of the shield machine deviates, the system analyzes geological data to determine whether it encounters a stratum with uneven hardness, checks the equipment operating data to examine whether the pressure of the propulsion cylinders is balanced, and traces historical construction data to check for cumulative errors. At the same time, referring to the experience cases in the expert knowledge base, a comprehensive judgment is made on the cause of the deviation to improve the accuracy of the analysis.

[0045] In one embodiment, in S3, according to the cause of the deviation and the real-time construction situation, the intelligent decision-making and control module formulates a precise deviation correction strategy. For the deviation caused by geological conditions, such as the shield machine sinking due to encountering soft soil strata, a combination of measures such as increasing the thrust of the bottom propulsion cylinders, adjusting the cutting parameters of the cutter head, and changing the earth excavation volume is taken for deviation correction; for the deviation caused by equipment failures, such as sensor failures affecting the measurement accuracy, the sensors are replaced or calibrated in a timely manner, and the current state is estimated based on historical data and the data of backup sensors, and the construction parameters are adjusted to maintain the stability of the construction. When formulating the deviation correction strategy, the construction cost, progress, quality, and the impact on the surrounding environment are comprehensively considered, and an optimization algorithm is used to find the optimal deviation correction plan. In S4, the deviation correction strategy is implemented through the actuator. During the implementation process, the sensors continuously monitor the deviation correction effect. If the deviation correction effect does not meet the expectation, the system re-analyzes the cause of the deviation, adjusts the deviation correction strategy, and performs the deviation correction operation again until the deviation is controlled within the allowable range. For example, during the deviation correction process of the shield machine, the attitude and position data of the shield machine are collected at regular time intervals, and the deviation correction parameters are finely adjusted according to the actual adjustment situation to ensure that the shield machine can accurately and smoothly return to the designed route. At the same time, the data during the deviation correction process is recorded for subsequent construction analysis and experience summary to continuously optimize the adaptive deviation correction method.

[0046] As described above, only the specific implementation manners of the present invention are provided, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various changes or substitutions, and these should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claimed rights.

Claims

1. Tunnel construction multi-source sensor fusion dynamic closed-loop control system, characterized by: It includes multi-source measurement and monitoring sensor module, data acquisition and transmission module, intelligent data fusion and analysis module, intelligent decision-making and control module and execution and feedback module.

2. The multi-source sensor fusion dynamic closed-loop control system for tunnel construction according to claim 1 is characterized by: The multi-source measurement and monitoring sensor module includes a laser ranging sensor, a gyroscope, an accelerometer, a pressure sensor, a displacement sensor, and a geological radar. The laser ranging sensor is used to measure the distance between the tunnel face and the constructed section in real time to provide data for construction progress monitoring. The gyroscope and accelerometer are installed on the construction equipment and can accurately measure the posture changes of the equipment, including angles, inclinations and other information. The pressure sensor is arranged in the surrounding rock and supporting structure around the tunnel to monitor the surrounding rock pressure and the stress of the supporting structure. The displacement sensor is used to measure the displacement of the tunnel lining and surrounding rock to timely discover potential deformation risks. The geological radar can detect the geological conditions within a certain range ahead and obtain geological information in advance. The groundwater sensor monitors the groundwater level and water pressure changes. In addition, a drone equipped with high-definition camera equipment is used to regularly monitor the tunnel entrance and surrounding environment to obtain information on terrain changes. Various sensors work together to ensure comprehensive and accurate collection of multi-source data during the construction process.

3. The multi-source sensor fusion dynamic closed-loop control system for tunnel construction according to claim 1 is characterized by: In the data acquisition and transmission module, the data collected by each sensor is initially filtered and preprocessed, including denoising, filtering, data completion and other operations to improve data quality, and then sent to the central control unit via wired or wireless transmission. Redundant transmission technology is used for transmission. At the same time, the transmitted data is encrypted to prevent the data from being stolen or tampered with during transmission.

4. The multi-source sensor fusion dynamic closed-loop control system for tunnel construction according to claim 1 is characterized by: The intelligent data fusion and analysis module, after receiving the multi-source sensor data, the central control unit first performs data format conversion and standardization processing to make different types of data have a unified format, uses deep learning algorithms to perform data fusion, and uses convolutional neural networks (CNNs) to extract and fuse features of laser scanning data and image data. Through fusion, it can more accurately reflect the actual status of tunnel construction, and use big data analysis technology to deeply mine historical data and real-time data to predict problems that may arise during construction and identify cracks and defects on the surface of the tunnel lining; through long short-term memory networks (LSTMs), time series data (such as changes in strain and pressure over time) are analyzed to predict data trends. In combination with big data analysis technology, a tunnel construction database is established to store historical data and real-time data to provide data support for subsequent analysis. At the same time, a data mining algorithm is used to mine the potential relationship between construction parameters, geological conditions and tunnel deformation and force from massive data to provide a scientific basis for construction decisions.

5. The multi-source sensor fusion dynamic closed-loop control system for tunnel construction according to claim 1 is characterized by: The intelligent decision-making and control module generates control instructions based on the data fusion and analysis results using expert systems and intelligent optimization algorithms. When the measurement data shows that the tunnel has deviated or the monitoring data indicates that there is a safety risk, the system automatically starts the decision-making process. For example, if the tunnel excavation direction deviates from the designed route, the genetic algorithm is used in combination with the geological conditions and the current construction parameters to calculate the optimal correction plan, including the thrust adjustment of the propulsion cylinder, the steering angle of the cutter head, etc.; if the surrounding rock pressure is monitored to be close to the warning value, the system automatically adjusts the construction progress and strengthens the support measures according to the risk level, and gives specific construction suggestions, such as increasing the number of anchor rods and the thickness of shotcrete.

6. The multi-source sensor fusion dynamic closed-loop control system for tunnel construction according to claim 1 is characterized by: In the execution and feedback module, control instructions act on tunnel construction equipment and the construction process through the actuator. The actuator includes the propulsion system, cutterhead drive system, support equipment, etc. of the shield machine. After the operation is executed, the relevant data is collected again through sensors and fed back to the data acquisition and transmission module to form a dynamic closed-loop control. For example, during the deviation correction process, the posture and position changes of the shield machine are monitored in real time, and the deviation correction parameters are dynamically adjusted according to the feedback data to ensure that the shield machine accurately returns to the designed route. At the same time, various data during the construction process are recorded for subsequent construction analysis and experience summary, and the system decision model is continuously optimized.

7. A dynamic adaptive deviation correction method for multi-source sensor fusion in tunnel construction, equipped with a dynamic closed-loop control system for multi-source sensor fusion in tunnel construction as claimed in any one of claims 1 to 6, characterized in that: The following steps are involved: S1, real-time multi-source data collection and deviation calculation; S2. Intelligent analysis of deviation causes; S3. Formulate precise deviation correction strategies; S4. Correction execution and dynamic adjustment.

8. The method for dynamic adaptive deviation correction of multi-source sensor fusion in tunnel construction according to claim 7 is characterized by: In S1, during the tunnel construction process, multi-source sensors continuously collect measurement and monitoring data, compare the collected real-time data with the design standards, and calculate the position deviation, attitude deviation, construction parameter deviation, etc. of the tunnel. For example, the tunnel section data obtained by the laser scanning measuring instrument is compared with the design section data to calculate the contour deviation; the attitude deviation of the shield machine is determined by combining the gyroscope, accelerometer and laser ranging data; the actual excavation speed, thrust and other construction parameters are compared with the set parameters to obtain the construction parameter deviation.

9. The method for dynamic adaptive deviation correction of multi-source sensor fusion in tunnel construction according to claim 7 is characterized by: In S2, once a deviation is detected, the system immediately starts the intelligent analysis program. The machine learning algorithm is used to deeply mine multi-source data, and the cause of the deviation is analyzed by combining geological conditions, construction technology, equipment operation status and other information. For example, if the tunneling direction of the shield machine deviates, the system analyzes the geological data to determine whether it encounters uneven soft and hard strata, checks the equipment operation data to check whether the thrust cylinder pressure is balanced, and traces back the historical construction data to check whether there is a cumulative error. At the same time, refer to the experience cases in the expert knowledge base to make a comprehensive judgment on the cause of the deviation and improve the accuracy of the analysis.

10. The tunnel construction multi-source sensor fusion dynamic adaptive deviation correction method according to claim 7 is characterized by: In the S3, according to the cause of the deviation and the real-time construction situation, the intelligent decision-making and control module formulates an accurate correction strategy. For deviations caused by geological conditions, such as encountering soft soil layers that cause the shield machine to sink, a combination of measures such as increasing the thrust of the bottom propulsion cylinder, adjusting the cutterhead cutting parameters, and changing the excavation volume are taken to correct the deviation; for deviations caused by equipment failures, such as sensor failures affecting measurement accuracy, the sensor is replaced or calibrated in a timely manner, and the current status is estimated based on historical data and spare sensor data, and the construction parameters are adjusted to maintain construction stability. When formulating the correction strategy, the construction cost, progress, quality and impact on the surrounding environment are comprehensively considered, and the optimization algorithm is used to find Find the optimal correction scheme. In S4, the correction strategy is implemented by the actuator. During the execution process, the sensor monitors the correction effect in real time. If the correction effect does not meet the expectations, the system re-analyzes the cause of the deviation, adjusts the correction strategy, and performs the correction operation again until the deviation is controlled within the allowable range. For example, during the correction process of the shield machine, the posture and position data of the shield machine are collected at regular time intervals, and the correction parameters are fine-tuned according to the actual adjustment situation to ensure that the shield machine can accurately and smoothly return to the designed route. At the same time, the data during the correction process is recorded for subsequent construction analysis and experience summary, and the adaptive correction method is continuously optimized.

Images