Shield / TBM construction intelligent management and quality assurance system

Abstract

The invention discloses an intelligent management and quality assurance system for shield / TBM construction. Belongs to the field of shield tunneling machine construction management. The system is based on a BIM model, and a comprehensive data integration system is formed by integrating PLC tunneling parameters, automatic monitoring data, on-site video monitoring data, classified statistical data of personnel going in and out of a well and important project file data. And data analysis and mining are carried out through a machine learning algorithm, and operation parameters are predicted. The system is further provided with a real-time monitoring and early warning module and a video monitoring module, so that geological conditions and field operation conditions can be detected in real time. And meanwhile, the management of personnel entry and exit and file data is realized through the management module, so that the project management efficiency is improved and the project quality is ensured.

Description

Technical Field

[0001] The invention belongs to the field of shield machine construction management, and more specifically relates to an intelligent management and quality assurance system for shield / TBM construction. Background Art

[0002] The shield method is currently the most commonly used construction method in tunnel engineering. With the acceleration of urbanization and the continuous expansion of underground engineering, higher requirements are placed on the intelligent management and quality assurance of shield / tunnel boring equipment. However, traditional construction methods often rely on manual information collection and decision-making, which often has problems such as low efficiency and large errors.

[0003] The existing intelligent management systems for shield construction mainly focus on functions such as operating status monitoring, early warning and alarm, and data statistical analysis of shield equipment. However, these systems mainly rely on the supplier's own shield equipment and information system, and have poor compatibility with equipment or systems from other manufacturers. At the same time, there are still deficiencies in the processing and optimization of various complex working conditions, and it is impossible to fully ensure the quality and efficiency of shield construction.

[0004] A BIM (Building Information Modeling) model is a three-dimensional, building model used in the construction of buildings and related projects. This model is used throughout the building life cycle, from design and construction to maintenance and demolition. However, despite its wide application potential, BIM is not widely used in the field of underground construction. One of the main obstacles is the special nature and complexity of underground projects.

[0005] For these reasons, there is a demand for a system that can comprehensively manage and ensure the quality of shield / TBM construction, so as to better cope with various complex working conditions and improve the efficiency and quality of the project. Summary of the invention

[0006] The present invention proposes an intelligent management and quality assurance system for shield / TBM construction. This system manages various data in the shield / TBM construction process in a systematic and modeled manner, and introduces machine learning algorithms for data analysis and prediction, thereby achieving real-time monitoring and assurance of construction quality, and at the same time, improving engineering management efficiency.

[0007] In order to achieve the above object, the present invention is implemented by adopting the following technical scheme: the system comprises: With BIM model as the core, a data integration system is formed by integrating PLC excavation parameters, automated monitoring data, on-site video monitoring data, classified statistics of personnel entering and leaving the well, and important engineering documents and materials; Machine learning algorithms for data analysis of TBM excavation parameters, data mining of excavation parameter variation patterns in different strata and burial depths, and prediction of cutterhead speed and jack thrust operating parameters; Automated real-time monitoring and early warning module to detect and warn of adverse geology and groundwater in front of the excavation face; The video monitoring module accesses all video monitoring data of the construction site so that ground personnel can understand the working conditions near the underground TBM excavation surface in real time; A management module for personnel entry and exit and document information to improve project management efficiency and ensure project quality.

[0008] In one embodiment, the data integration system comprises: BIM model creation: First, based on the engineering design parameters and geographic information from the Geographic Information System (GIS), a BIM model of the project is created, including all information related to the shield machine, tunnel, soil, and geological engineering; Data acquisition: The tunneling parameters are obtained from the PLC of the shield machine, including the engineering data of high-frequency sampling of cutterhead speed, power, torque, and thrust pressure; the geological environment data, soil pressure, displacement, and soil moisture content obtained by the automated monitoring equipment are transmitted to the data center in real time by underground sensors; Data preprocessing: The data obtained above are standardized and integrated. The standardization process includes cleaning the data, identifying and processing errors and abnormal data; Integration of multi-dimensional heterogeneous data: Integrate pre-processed tunneling parameters, automated monitoring data, on-site video surveillance data, classified statistics of personnel entering and leaving the well, and important engineering documents into the BIM model to form a big data environment with rich information and good data consistency; Database construction: The above integrated data is imported into the database through relevant software to build a complete engineering database.

[0009] In one embodiment, the specific process of predicting the operating parameters is as follows: First, the required engineering data is obtained from the database, including excavation parameters, geological environment data, and operation parameters; For the excavation parameters in different strata and burial depths, the relationship between them was found through multivariate linear regression analysis; for predicting the cutterhead speed and jack thrust operating parameters, the random forest regression algorithm was selected; Model training: Previous engineering data is used as training data and input into the random forest regression model. Through training, a model is obtained that can predict the cutter head speed and jack thrust operating parameters.

[0010] In one embodiment, the automated real-time monitoring and early warning module includes: Through various geological detectors, the formation information is collected in real time; Determine the underground geological structure by processing and analyzing the collected data; When the analysis results exceed the preset threshold, the system will automatically generate an early warning and send the early warning information to the engineering staff.

[0011] In one embodiment, the video monitoring module includes: By installing cameras at various key locations on the construction site, on-site work conditions can be obtained in real time, including personnel flow and equipment operating status.

[0012] In one embodiment, the management module includes: By combining RFID, accurate real-time monitoring of personnel entering and leaving the construction site is carried out, including personnel location, personnel identity, and entry and exit time; File management: Build a file information database that contains all engineering documents, drawings, and reports; classify and label files for quick retrieval.

[0013] Beneficial effects of the present invention: 1. Efficient data integration: The system takes the BIM model as its core, integrating PLC excavation parameters, automated monitoring data, on-site video surveillance data, classified statistics of personnel entering and leaving the well, and important engineering documents and information, achieving efficient integration of multiple heterogeneous data and greatly improving data processing efficiency.

[0014] 2. Intelligent data analysis and early warning: The system uses big data and machine learning algorithms to mine massive excavation parameters, discover the changing patterns of TBM excavation parameters in different strata and burial depths, and predict operating parameters such as cutter head speed and jack thrust. To a certain extent, it makes up for the drawback that the selection of TBM excavation parameters in the past relied heavily on experience.

[0015] 3. Improve the quality of project construction: The system's automated monitoring and early warning function can detect and warn of poor geology and groundwater in front of the excavation face, making it convenient for the site to take preventive measures in advance, reducing project risks and improving the quality of project construction.

[0016] 4. Improve project management efficiency: The system accesses all video surveillance data from the construction site, allowing ground personnel to understand the operating conditions near the underground TBM excavation surface in real time. It also improves project management efficiency by coordinating detailed personnel entry and exit management and document management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a system block diagram of the present invention; Figure 2Flow chart of random forest algorithm for data analysis of TBM excavation parameters in the present invention. DETAILED DESCRIPTION

[0018] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Typical embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in the present invention. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0019] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used in the present invention in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Typical embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in the present invention. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0020] like Figure 1 As shown, the system comprises: With BIM model as the core, a data integration system is formed by integrating PLC excavation parameters, automated monitoring data, on-site video surveillance data, classified statistics of people entering and leaving the well, and important engineering documents and information.

[0021] BIM model creation: First, create a BIM model of the project based on the project design parameters and geographic information from the Geographic Information System (GIS). The BIM model is three-dimensional and contains all information related to the project, including the shield machine, tunnel, soil, geology, etc. The BIM model is also the information core of the system.

[0022] Data acquisition: The tunneling parameters are obtained from the PLC (Programmable Logic Controller) of the shield machine, including high-frequency sampling engineering data such as cutter head speed, power, torque, and thrust pressure. At the same time, the geological environment data obtained by the automated monitoring equipment, such as soil pressure, displacement, soil moisture content, etc., are transmitted to the data center in real time by underground sensors. The on-site video monitoring equipment captures the on-site working scene and automatically obtains the classified statistical data of the personnel entering and leaving the well and the relevant engineering documents.

[0023] Data preprocessing: The data obtained above are standardized and integrated. The standardization process includes cleaning the data, identifying and processing errors and abnormal data. This can maintain the quality and accuracy of the data and facilitate subsequent data analysis.

[0024] Integration of multi-source heterogeneous data: Integrate the preprocessed tunneling parameters, automated monitoring data, on-site video surveillance data, classification and statistical data of personnel entering and leaving the well, and important engineering document materials into the BIM model to form a big data environment with rich information and good data consistency. This environment presents various states and data of tunnel tunneling under the same window, facilitating subsequent analysis and management.

[0025] Database construction: The above-integrated data is imported into the database through relevant software to construct a complete engineering database. According to the type and characteristics of the data, a relational database or a non-relational database can be selected for storage.

[0026] As Figure 2 shown, perform data analysis on the TBM tunneling parameters, adopt machine learning algorithms, mine the variation laws of tunneling parameters under different strata and burial depths, and predict the operating parameters such as cutterhead speed and jack thrust.

[0027] S1. Data preparation: First, obtain the required engineering data from the database, including tunneling parameters, geological environment data, operating parameters, etc. If these data do not have a unified dimension, data standardization or normalization processing is also required.

[0028] S2. Data analysis: For the tunneling parameters under different strata and burial depths, discover their relationships through multiple linear regression analysis. For predicting operating parameters such as cutterhead speed and jack thrust, select random forest regression. Random forest is a non-linear regression model that can handle complex non-linear relationships between multiple features.

[0029] S3. To generate a random forest, multiple decision trees need to be generated. The generation of each decision tree follows the following steps: S301. First, there are m samples, and each sample has n features. Randomly select a sample, and then randomly select p features (p < n) from the n features. This forms a training set. On this training set, a decision tree can be generated.

[0030] S302. The generation of the decision tree is based on the CART algorithm, that is, each split of the decision tree is to minimize the variance of the target variable. At each node of the decision tree, the model will search for the optimal split, that is, the feature and split point that can lead to the greatest improvement in the purity of the child nodes. Mathematically speaking, for a certain split variable j and split point s, define two regions and , and then solve: where c1 and c2 are the output values of the two regions, taking the average value of the target values within the regions.

[0031] s is the split point, which is used to decide when to split a node; j is the segmentation variable, which is used to determine which feature to use for segmentation; R1(j, s) and R2(j, s) are two regions generated after segmentation, where R1(j, s) contains all samples whose feature j value is less than or equal to s, and R2(j, s) contains all samples whose feature j value is greater than s; y is the observed output or target variable, which is the target you want to predict; X represents the input variables, which contain all the input data used for prediction.

[0032] Xj refers to the jth feature in X. In the decision tree algorithm, we hope to find the best j, that is, to minimize the variance of the target variable value (y) in each partition after partitioning according to this feature.

[0033] S303. Repeat the above step S302 to generate a large number of decision trees to form a forest.

[0034] After obtaining the random forest model, for a new input sample, just input it into all decision trees and output the average of the prediction results obtained by all trees as the final prediction result.

[0035] In the shield / TBM construction process, an adaptive control model that can adapt to various complex geological conditions is extremely important. Random forest can efficiently and accurately predict key excavation parameters such as cutter head speed and jack thrust due to its excellent nonlinear fitting ability, high robustness to outliers, and interpretability of model results. Through real-time feedback on the model prediction results, engineers can adjust the excavation strategy and parameters in a timely manner to ensure tunnel construction safety and quality, greatly improving construction efficiency.

[0036] The automated real-time monitoring and early warning module can detect and warn of adverse geology and groundwater in front of the excavation face.

[0037] First, various geological detectors, such as acoustic wave detectors, geomagnetic detectors, georesistance detectors, etc., are used to collect stratum information in real time. This information may include the thickness of underground rock layers, groundwater levels, and locations of crustal fractures.

[0038] By processing and analyzing the collected data, we can determine the underground geological structure and predict possible problems in advance, such as rock being too hard or groundwater level being too high.

[0039] When the analysis results exceed the preset threshold, the system will automatically generate an alert and send the alert information to engineering personnel, giving them enough time to take appropriate countermeasures.

[0040] The video surveillance module accesses all video surveillance data from the construction site so that ground personnel can understand the operating conditions near the underground TBM excavation surface in real time.

[0041] By installing cameras at various key locations on the construction site, on-site work conditions can be obtained in real time, including personnel flow, equipment operating status, etc.

[0042] The video data undergoes preliminary processing (such as denoising, improving clarity, etc.) for subsequent analysis.

[0043] By feeding the video data into pre-trained target detection and behavior recognition models, the working status on site can be monitored and analyzed in real time.

[0044] A management module for personnel entry and exit and document information to improve project management efficiency and ensure project quality.

[0045] Personnel management: By combining technologies such as RFID or QR codes, accurate real-time monitoring of personnel entering and leaving the construction site can be carried out, including personnel location, personnel identity, entry and exit time, etc. Through data analysis, personnel distribution and personnel dynamics can be predicted to facilitate personnel scheduling and safety management.

[0046] File management: A file information database can be built, which contains all engineering documents, drawings, reports, etc. This database can classify and label files for quick retrieval.

[0047] The realization of the above modules needs to be combined with the BIM model and database mentioned above, as well as the final construction quality improvement mentioned later, to form a data-driven shield / TBM construction management system. In addition to improving construction quality, such a system can also conduct real-time monitoring and early warning, so it can greatly improve construction safety, and at the same time effectively save manpower and material resources and improve work efficiency.

[0048] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0049] It should be understood that the detailed description of the technical solutions of the present invention by means of the preferred embodiments is illustrative rather than restrictive. A person skilled in the art may modify the technical solutions described in the embodiments, or replace some of the technical features by equivalents, based on reading the specification of the present invention; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent management and quality assurance system for shield / TBM construction, characterized by: The system comprises: With BIM model as the core, a data integration system is formed by integrating PLC excavation parameters, automated monitoring data, on-site video monitoring data, classified statistics of personnel entering and leaving the well, and important engineering documents and materials; The data integration system comprises: BIM model creation: First, based on the engineering design parameters and geographic information from the Geographic Information System (GIS), a BIM model of the project is created, including all information related to the shield machine, tunnel, soil, and geological engineering; Data acquisition: The tunneling parameters are obtained from the PLC of the shield machine, including the engineering data of high-frequency sampling of cutterhead speed, power, torque, and thrust pressure; the geological environment data, soil pressure, displacement, and soil moisture content obtained by the automated monitoring equipment are transmitted to the data center in real time by underground sensors; Data preprocessing: The data obtained above are standardized and integrated. The standardization process includes cleaning the data, identifying and processing errors and abnormal data; Integration of multi-dimensional heterogeneous data: Integrate pre-processed tunneling parameters, automated monitoring data, on-site video surveillance data, classified statistics of personnel entering and leaving the well, and important engineering documents into the BIM model to form a big data environment with rich information and good data consistency; Database construction: The above integrated data is imported into the database through relevant software to build a complete engineering database; Conduct data analysis on TBM excavation parameters, use machine learning algorithms to mine the changing patterns of excavation parameters in different strata and burial depths, and predict the cutterhead speed and jack thrust operating parameters; The specific process of predicting the operating parameters is as follows: First, the required engineering data is obtained from the database, including excavation parameters, geological environment data, and operation parameters; For the excavation parameters in different strata and burial depths, the relationship between them was found through multivariate linear regression analysis; for predicting the cutterhead speed and jack thrust operation parameters, the random forest regression algorithm was selected; Model training: Use previous engineering data as training data and input it into the random forest regression model. Through training, a model is obtained to predict the cutter head speed and jack thrust operation parameters. Automated real-time monitoring and early warning module to detect and warn of adverse geology and groundwater in front of the excavation surface; The video monitoring module accesses all video monitoring data of the construction site so that ground personnel can understand the working conditions near the underground TBM excavation surface in real time; A management module for personnel entry and exit and document information to improve project management efficiency and ensure project quality.

2. The intelligent management and quality assurance system for shield / TBM construction according to claim 1 is characterized by: The automated real-time monitoring and early warning module includes: Through various geological detectors, the formation information is collected in real time; Determine the underground geological structure by processing and analyzing the collected data; When the analysis results exceed the preset threshold, the system will automatically generate an early warning and send the early warning information to the engineering staff.

3. The intelligent management and quality assurance system for shield / TBM construction according to claim 1 is characterized by: The video monitoring module comprises: By installing cameras at various key locations on the construction site, on-site work conditions can be obtained in real time, including personnel flow and equipment operating status.

4. The intelligent management and quality assurance system for shield / TBM construction according to claim 1 is characterized by: The management module includes: By combining RFID, accurate real-time monitoring of personnel entering and leaving the construction site is carried out, including personnel location, personnel identity, and entry and exit time; File management: Build a file information database that contains all engineering documents, drawings, and reports; classify and label files for quick retrieval.

Images