Shield muck fine-grained soil content real-time detection system based on multi-parameter fusion and deduction method

Abstract

The invention relates to the technical field of shield construction, in particular to a shield muck fine-grained soil content real-time detection system and deduction method based on multi-parameter fusion, and the system comprises a multi-parameter sensor unit, a data acquisition and transmission unit, a data processing and analysis unit and a display unit. According to the system, the content of fine-grained soil in muddy water separated from the muck is rapidly detected by using an intelligent densimeter after the muddy water is precipitated, a correction algorithm based on a data difference rule obtained by an indoor test is introduced, fine-grained soil content data detected by the intelligent densimeter is corrected, and a multi-parameter fusion algorithm is applied to determine the content of the fine-grained soil in the muddy water. Various processed shield muck data are comprehensively analyzed, rapid detection and analysis of fine-grained soil component changes in the shield muck are achieved, the problems that a traditional densimeter method is long in time consumption, complex in operation and poor in adaptability are solved through the system, real-time monitoring of the fine-grained soil content is achieved through the detection system, and the detection accuracy of the fine-grained soil component changes in the shield muck is improved. And a basis is provided for resource utilization of the muck.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of shield construction, in particular to a shield muck fine-grained soil content real-time detection system and deduction method based on multi-parameter fusion. BACKGROUND

[0002] In the process of shield tunnel construction, the properties of muck have a crucial influence on construction safety, efficiency and engineering quality, among which, the fine-grained soil content is a key parameter of muck, which is directly related to the flowability, stability of muck and the degree of wear on shield equipment, etc., and accurate grasp of the fine-grained soil content in shield muck helps construction personnel to timely adjust construction parameters, such as muck improvement scheme, shield advancing speed, muck output control, etc., so as to ensure the smooth progress of construction and reduce construction risk and cost.

[0003] Some existing detection methods based on sensors can only detect a single parameter, which is difficult to comprehensively and accurately reflect the real content of fine-grained soil in muck, and due to the complex shield construction environment and the comprehensive influence of various factors on the properties of muck, single parameter detection is easily disturbed, resulting in inaccurate detection results.

[0004] In addition, the traditional fine-grained soil content detection method based on density meter is time-consuming, requires high operation personnel, and cannot adapt to the rapid change of stratum, but in the process of shield tunneling, the composition change of fine-grained soil in muck will not only affect the construction measures of muck improvement in the process of tunneling, but also affect the process design of subsequent muck recycling link, therefore, the present application proposes a shield muck fine-grained soil content real-time detection system and deduction method based on multi-parameter fusion. SUMMARY

[0005] The present application aims to provide a shield muck fine-grained soil content real-time detection system and deduction method based on multi-parameter fusion to solve the above problems.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0007] The shield muck fine-grained soil content real-time detection system based on multi-parameter fusion comprises a multi-parameter sensor unit, a data acquisition and transmission unit, a data processing and analysis unit and a display unit.

[0008] The multi-parameter sensor unit measures the particle size distribution of muck particles in real time through a laser particle size analyzer, detects the water content of muck in real time through a water content sensor, detects and determines the density of muck through a density sensor, separates muck through a mud-water separation device to obtain mud water, and detects the density of the settled mud water through an intelligent density meter.

[0009] The data acquisition and transmission unit is used for collecting and processing the electric signals or digital signals output by the multi-parameter sensor unit, and then transmitting the shield muck data to the data processing and analysis unit in real time.

[0010] The data processing and analysis unit corrects the fine soil content data detected by the intelligent density meter by filtering and denoising the shield muck data and introducing a correction algorithm based on the data difference law obtained through indoor experiments, and comprehensively analyzes the various processed shield muck data by using a multi-parameter fusion algorithm, and calculates the fine soil content in the shield muck in combination with the muck weight and the coarse particle grading parameters.

[0011] The display unit displays the calculation results of the muck fine soil content, the real-time measurement data of each sensor, the muck weight, the coarse particle grading and the related construction parameters in real time, and the alarm immediately sends out an audible and visual alarm signal when the detected fine soil content exceeds the preset reasonable range.

[0012] Further, the multi-parameter sensor unit includes a particle size analysis module, a water content detection module, a muck density detection module, a slurry separation module and a slurry density detection module.

[0013] The particle size analysis module measures the particle size distribution of the muck particles in real time through a laser particle size analyzer to obtain the particle size proportion information of the fine soil in the muck.

[0014] The water content detection module detects the water content of the muck in real time through a water content sensor.

[0015] The muck density detection module detects and determines the muck density through a density sensor.

[0016] The slurry separation module separates the muck through a slurry separation device to obtain slurry.

[0017] The slurry density detection module detects the density of the settled slurry through an intelligent density meter, and calculates the fine soil content in the slurry according to the corresponding relationship between the slurry density and the fine soil content.

[0018] Further, in the data acquisition and transmission unit, the electric signals or digital signals output by the multi-parameter sensor unit are converted into a unified data format, a high-precision A / D converter is used for digital processing of the analog signals, the multi-sensor data are integrated through a data acquisition card, and the collected data are transmitted to the data processing and analysis unit in real time by using wireless communication technology.

[0019] Further, the data processing and analysis unit includes a preliminary verification module, a data processing module, a data alignment module, a data correction module, a multi-parameter feature extraction module, a multi-parameter fusion algorithm operation module and a data management module.

[0020] The preliminary verification module receives the data of the data acquisition and transmission unit in real time through a preset communication interface protocol, and performs preliminary verification on the integrity and format of the data during the receiving process. For data with problems, the preliminary verification module automatically sends a retransmission request to the data acquisition and transmission unit.

[0021] The data processing module uses multiple filtering algorithms to process multiple shield muck data.

[0022] The data alignment module uses time synchronization technology to calibrate and align the timestamps of the multiple shield muck data of each sensor, so that all parameters remain consistent in the time dimension, forming a unified time series data set.

[0023] The data correction module corrects the fine-grained soil content data detected by the intelligent density meter by introducing a correction algorithm based on the data difference law obtained from indoor experiments.

[0024] The multi-parameter feature extraction module extracts features from the preprocessed and corrected data, mines feature information related to the fine-grained soil content, calculates the mass of fine-grained soil in unit volume of muck combined with the muck weight data, and calculates the ratio of coarse particles to fine-grained soil combined with the coarse particle grading data, forming a multi-dimensional feature vector.

[0025] The multi-parameter fusion algorithm operation module uses a multi-parameter fusion algorithm to comprehensively analyze the extracted multi-dimensional feature vector and calculate the content of fine-grained soil in the shield muck.

[0026] The data management module uses a distributed database architecture to store the processed data, including raw sensor data, preprocessed data, correction results, fusion calculation results, and related feature parameters. At the same time, the data is backed up to the local hard disk and cloud storage regularly.

[0027] Further, in the data processing module, for continuous data output by the laser particle size analyzer, moisture content sensor and density sensor, a median filter algorithm is used to remove transient pulse interference; for data output by the intelligent density meter, a Kalman filter algorithm is used to predict the expected value of the data by establishing a dynamic model, and to dynamically correct according to the deviation between the actual measurement value and the predicted value.

[0028] Further, the data correction module corrects the fine-grained soil content data detected by the intelligent density meter by introducing a correction algorithm based on the data difference law obtained from indoor experiments, including the following steps:

[0029] A1、In the indoor test stage, a large number of muck samples with different fine-grained soil contents are collected, and the intelligent density meter detection method and the traditional laboratory screening method are used for detection respectively, and a difference database of the detection results of the two methods is established.

[0030] A2、In the correction algorithm, the real-time detection value of the intelligent densimeter is taken as input, the corresponding correction coefficient is calculated by querying the difference database and combining a linear regression model or a BP neural network model, and the detection value is corrected;

[0031] A3、Periodically update the difference database to include the latest field detection data and laboratory comparison data, and continuously optimize the parameters of the correction model.

[0032] The deduction method of the shield muck fine-grained soil content real-time detection system based on multi-parameter fusion includes the following steps:

[0033] I. Establish a historical database: During shield construction, the system continuously collects and stores multi-parameter detection data, shield tunneling parameters and geological condition information at different construction stages to establish a historical database;

[0034] II. Data feature extraction: In-depth analysis of the data in the historical database, extract the characteristic parameters closely related to the change of fine-grained soil content, and determine which parameters have strong correlation with the fluctuation of fine-grained soil content under different stratum conditions through statistical analysis method;

[0035] III. Data feature selection: Use data mining technology to mine the potential correlation features between parameters, and use feature selection algorithm to select the most representative feature parameter subset that contributes most to the deduction of fine-grained soil content from the extracted features;

[0036] IV. Build a deduction model: Based on the selected feature parameters, use machine learning algorithm or time series analysis method to build a fine-grained soil content deduction model;

[0037] V. Real-time deduction and result output: During shield construction, real-time input of current multi-parameter detection data, muck weight, coarse-grained grading, shield tunneling parameters and geological condition information into the verified and optimized deduction model, the model quickly predicts the change trend of shield muck fine-grained soil content in the next 5-10 ring tunneling period according to the input data, and outputs the deduction result to the display unit for display.

[0038] Further, in step IV, the following steps are included:

[0039] B1. Based on the selected feature parameters, use machine learning algorithm or time series analysis method to build a fine-grained soil content deduction model;

[0040] B2. During model construction, use part of the data in the historical database as a training set to optimize and adjust the parameters of the model;

[0041] B3, use the remaining part of the data in the history database as a test set to verify the constructed deduction model, and evaluate the prediction performance of the model by calculating the error index between the prediction result of the model and the actual fine-grained soil content data in the test set;

[0042] B4, if the error of the model is large, further analyze the reason, take corresponding optimization measures, and then train and verify the model again until the model reaches satisfactory prediction accuracy and stability.

[0043] The beneficial effects of the present application are:

[0044] 1, in the present application, the system quickly detects the fine-grained soil content in the slurry separated from the slag by sedimentation through an intelligent densitometer, introduces a correction algorithm based on the data difference law obtained from indoor tests to correct the fine-grained soil content data detected by the intelligent densitometer, uses a multi-parameter fusion algorithm to comprehensively analyze a plurality of processed shield slag data, combines the weight and coarse-grained grading parameters of the slag, realizes rapid detection and analysis of the fine-grained soil component change in the shield slag, can more timely reflect the change of the slag property, and can fully utilize the complementarity between parameters, compared with the original method, more comprehensively and accurately reflects the real content of fine-grained soil, improves the reliability of the detection result, realizes the fusion of a plurality of rapid detection methods, solves the problems of long time consumption, complex operation and poor adaptability of the traditional densitometer method, realizes real-time monitoring of the fine-grained soil content through the detection system, and provides a basis for the resource utilization of the slag.

[0045] 2, in the present application, the deduction method of the shield slag fine-grained soil content real-time detection system based on multi-parameter fusion, by establishing a history database, data feature extraction, data feature selection, constructing a deduction model, real-time deduction and result output, the deduction model fuses the newly added parameters, can more comprehensively predict the fine-grained soil content change trend, enhance the construction controllability and safety, and promote the intelligent level of shield construction. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 The system principle diagram of the shield slag fine-grained soil content real-time detection system based on multi-parameter fusion of the present application;

[0047] Figure 2 The method flowchart of the deduction method of the shield slag fine-grained soil content real-time detection system based on multi-parameter fusion of the present application.

[0048] In the figure: 1, multi-parameter sensor unit; 2, data acquisition and transmission unit; 3, data processing and analysis unit; 4, display unit; 11, particle size analysis module; 12, water content detection module; 13, slag density detection module; 14, mud-water separation module; 15, mud-water density detection module; 31, preliminary verification module; 32, data processing module; 33, data alignment module; 34, data correction module; 35, multi-parameter feature extraction module; 36, multi-parameter fusion algorithm operation module; 37, data management module. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0050] Embodiment 1: Please refer to Figure 1 and Figure 2 The design proposes an embodiment of a real-time detection system for fine-grained soil content of shield slag based on multi-parameter fusion, which includes a multi-parameter sensor unit 1, a data acquisition and transmission unit 2, a data processing and analysis unit 3, and a display unit 4.

[0051] The multi-parameter sensor unit 1 measures the particle size distribution of the slag particles in real time through a laser particle size analyzer, detects the water content of the slag in real time through a water content sensor (using a capacitive or microwave sensor), detects and determines the density of the slag through a density sensor, separates the slag through a mud-water separation device to obtain mud-water, and detects the density of the settled mud-water through an intelligent densimeter. The multi-parameter sensor unit 1 includes a particle size analysis module 11, a water content detection module 12, a slag density detection module 13, a mud-water separation module 14, and a mud-water density detection module 15.

[0052] The particle size analysis module 11 measures the particle size distribution of the slag particles in real time through a laser particle size analyzer to obtain the particle size proportion information of fine-grained soil in the slag; the water content detection module 12 detects the water content of the slag in real time through a water content sensor; the slag density detection module 13 detects and determines the density of the slag through a density sensor; the mud-water separation module 14 separates the slag through a mud-water separation device to obtain mud-water; and the mud-water density detection module 15 detects the density of the settled mud-water through an intelligent densimeter, and calculates the content of fine-grained soil in the mud-water according to the corresponding relationship between the mud-water density and the fine-grained soil content.

[0053] The data acquisition and transmission unit 2 is used for collecting and processing the electrical signals or digital signals output by the multi-parameter sensor unit 1, including converting the electrical signals or digital signals output by the multi-parameter sensor unit 1 into a unified data format, digitizing the analog signals by using a high-precision A / D converter, integrating the multi-sensor data by using a data acquisition card, transmitting the collected data to the data processing and analysis unit 3 in real time by using wireless communication technology, and finally transmitting the shield muck data to the data processing and analysis unit 3 in real time.

[0054] The data processing and analysis unit 3 performs filtering and denoising processing on the shield muck data, introduces a correction algorithm based on the data difference law obtained from indoor tests, corrects the fine-grained soil content data detected by the intelligent density meter, and uses a multi-parameter fusion algorithm to comprehensively analyze the various processed shield muck data, calculates the content of fine-grained soil in the shield muck in combination with the weight of the muck and the coarse-grained grading parameters, and the data processing and analysis unit 3 includes a preliminary verification module 31, a data processing module 32, a data alignment module 33, a data correction module 34, a multi-parameter feature extraction module 35, a multi-parameter fusion algorithm operation module 36, and a data management module 37.

[0055] The preliminary verification module 31 receives the data of the data acquisition and transmission unit 2 in real time through a pre-set communication interface protocol, and performs preliminary verification on the integrity and format of the data during the receiving process, checks whether the data has problems such as packet loss, field absence, or format error, and automatically sends a retransmission request to the data acquisition and transmission unit 2 for the data with problems.

[0056] The data processing module 32 processes various shield muck data by using various filtering algorithms for data fluctuations and abnormal values caused by factors such as electromagnetic interference and mechanical vibration in the shield construction environment, removes transient pulse interference by using a median filtering algorithm for continuous data output by the laser particle size analyzer, water content sensor, and density sensor, effectively eliminates isolated abnormal points in the data, and at the same time preserves the trend characteristics of the data; for the data output by the intelligent density meter, a Kalman filtering algorithm is used to predict the expected value of the data by establishing a dynamic model, and to dynamically correct the deviation between the actual measurement value and the predicted value, thereby smoothing the data fluctuations and improving the stability of the data.

[0057] The data alignment module 33 software adopts high-precision time synchronization technology (due to the differences in detection principle and response speed of different sensors, the time stamps of the output data may be different, in order to ensure the accuracy of multi-parameter fusion analysis), and calibrates and aligns the time stamps of various shield muck data of each sensor based on the high-precision clock inside the system. Linear interpolation or spline interpolation algorithm is used for data completion, so that all parameters are consistent in time dimension, forming a unified time series data set;

[0058] The data correction module 34 corrects the fine-grained soil content data detected by the intelligent density meter by introducing a correction algorithm based on the data difference law obtained from indoor tests, including the following steps:

[0059] A1, in the indoor test stage, a large number of muck samples with different fine-grained soil content are collected, and the intelligent density meter detection method and the traditional laboratory screening method (as a standard method) are used for detection respectively, and a difference database of the detection results of the two methods is established;

[0060] A2, in the correction algorithm, the real-time detection value of the intelligent density meter is taken as the input, the corresponding correction coefficient is calculated by querying the difference database and combining the linear regression model or BP neural network model, and the detection value is corrected to eliminate the systematic error between the rapid detection method and the traditional detection method;

[0061] A3, the difference database is updated regularly, the latest field detection data and laboratory comparison data are included, and the parameters of the correction model are continuously optimized to ensure that the correction accuracy continues to improve with the construction process;

[0062] The multi-parameter feature extraction module 35 extracts features from the preprocessed and corrected data, and mines feature information related to fine-grained soil content (for the particle size distribution data output by the laser particle size analyzer, the volume fraction of fine-grained soil particles, particle size distribution standard deviation, characteristic particle size, etc. are extracted, for the moisture content and density data, the mean, variance, and change rate are extracted, for the fine-grained soil content data corrected by the intelligent density meter, the instantaneous value, sliding average value, and cumulative change amount are extracted), combined with the muck weight data to calculate the fine-grained soil mass in unit volume of muck, combined with the coarse-grained grading data to calculate the ratio of coarse-grained and fine-grained soil, forming a multi-dimensional feature vector;

[0063] The multi-parameter fusion algorithm operation module 36 uses a multi-parameter fusion algorithm to comprehensively analyze the extracted multi-dimensional feature vector and calculate the content of fine-grained soil in shield muck;

[0064] The data management module 37 stores the processed data, including original sensor data, pre-processed data, correction results, fusion calculation results and related characteristic parameters, in a distributed database architecture, and backs up the data to a local hard disk and cloud storage regularly.

[0065] The display unit 4 displays the calculation results of the fine-grained soil content of the muck, the real-time measurement data of each sensor, the muck weight, the coarse-grained grading, and the related construction parameters in real time. When the detected fine-grained soil content exceeds the pre-set reasonable range, the alarm immediately sends an audible and visual alarm signal to remind the construction personnel to take appropriate measures in a timely manner, such as adjusting the amount of muck improvement additive and optimizing the shield tunneling parameters. The alarm threshold can be flexibly set by the construction personnel in the system according to different engineering geological conditions and construction requirements.

[0066] In this embodiment, the system quickly detects the fine-grained soil content in the slurry separated from the muck by sedimentation using an intelligent densimeter, introduces a correction algorithm based on the data difference law obtained from indoor tests, corrects the fine-grained soil content data detected by the intelligent densimeter, and uses a multi-parameter fusion algorithm to comprehensively analyze multiple processed shield muck data in combination with the muck weight and coarse-grained grading parameters. The fine-grained soil content data can be quickly obtained, and after fusion with other parameters, the real-time and rapidity of detection are further improved, and the changes in muck properties can be more timely reflected. At the same time, the complementarity between parameters can be fully utilized, and compared with the original method, the real fine-grained soil content can be more comprehensively and accurately reflected, the reliability of the detection results is improved, the fusion of multiple rapid detection methods is realized, the dependence on traditional laboratory detection is reduced, and the labor and time costs are reduced. The system solves the problems of long time consumption, complex operation and poor adaptability of the traditional densimeter method, realizes real-time monitoring of fine-grained soil content through the detection system, and provides a basis for muck resource utilization.

[0067] Embodiment 2: Please refer to Figure 1 and Figure 2 The design proposes an implementation, a deduction method of a shield muck fine-grained soil content real-time detection system based on multi-parameter fusion, including the following steps:

[0068] I. Establish a historical database: During shield construction, the system continuously collects and stores multi-parameter detection data (including particle size distribution, moisture content, density, fine-grained soil content data detected and corrected by an intelligent densimeter, muck weight, coarse-grained grading, and corresponding fine-grained soil content calculation results) at different construction stages, shield tunneling parameters (such as pushing speed, cutterhead speed, torque, etc.), and geological condition information (such as stratum type, rock-soil physical and mechanical parameters, etc.), and establishes a historical database, providing rich samples for subsequent deduction analysis.

[0069] II. Data feature extraction: In-depth analysis of data in the historical database, extraction of characteristic parameters closely related to the change of fine-grained soil content, in addition to the previously mentioned characteristics, also includes mud-water related parameters (such as mud-water density, fine-grained soil content in mud-water, etc.), slag weight characteristics, coarse-grained soil grading characteristics, etc. Through statistical analysis method, determine which parameters change and fine-grained soil content fluctuation has strong correlation under different stratum conditions;

[0070] III. Data feature selection: Use data mining technology to mine potential correlation features between parameters, use feature selection algorithm to select the most representative and most contributing feature parameter subset from the extracted features, to reduce data dimension, improve the calculation efficiency and accuracy of the deduction model;

[0071] IV. Construction of deduction model: Based on the selected feature parameters, use machine learning algorithm or time series analysis method to construct fine-grained soil content deduction model, including the following steps:

[0072] B1, based on the selected feature parameters, use machine learning algorithm or time series analysis method to construct fine-grained soil content deduction model, for example, can use support vector regression (SVR) algorithm, long short-term memory network (LSTM) model or autoregressive integrated moving average model (ARIMA) etc., support vector regression algorithm through finding an optimal hyperplane to realize the regression prediction of fine-grained soil content; Long short-term memory network model can effectively handle the long-term dependence relationship in time series data, capture the change trend of fine-grained soil content with time and construction process; Autoregressive integrated moving average model is suitable for predicting time series data with stationarity or after difference processing;

[0073] B2, in the process of building model, use part of the data in the historical database as training set, optimize and adjust the parameters of the model, so that it can accurately fit the complex relationship between fine-grained soil content and each characteristic parameter;

[0074] B3, use the remaining part of the data in the historical database as test set, verify the constructed deduction model, calculate the error index between the model prediction result and the actual fine-grained soil content data in the test set, evaluate the prediction performance of the model;

[0075] B4. If the error of the model is large, further analyze the reasons, take corresponding optimization measures, then train and verify the model again, calculate the error index between the prediction result of the model and the actual fine-grained soil content data in the test set, such as root mean square error (RMSE), mean absolute error (MAE), etc., to evaluate the prediction performance of the model. If the error of the model is large and does not meet the actual engineering requirements, further analyze the reasons, which may be unreasonable feature selection, improper model parameter setting or insufficient training data, etc. To solve these problems, take corresponding optimization measures such as reselecting features, adjusting model parameters or increasing training data, then train and verify the model again until the model reaches satisfactory prediction accuracy and stability.

[0076] V. Real-time inference and result output: During the shield construction process, the current multi-parameter detection data, spoil weight, coarse-grained gradation, shield tunneling parameters and geological condition information are input into the verified and optimized inference model. The model quickly predicts the change trend of the fine-grained soil content of the shield spoil in the next 5-10 ring tunneling period according to the input data, and outputs the inference result to the display unit 4 for display.

[0077] In this embodiment, the inference method of the shield spoil fine-grained soil content real-time detection system based on multi-parameter fusion can more comprehensively predict the change trend of the fine-grained soil content by establishing a historical database, extracting data features, selecting data features, constructing an inference model, real-time inference and result output. The inference model integrates the newly added parameters, which can enhance the controllability and safety of the construction and promote the intelligent level of the shield construction.

[0078] In the present application, the shield muck fine-grained soil content real-time detection system mainly comprises a multi-parameter sensor unit 1, a data acquisition and transmission unit 2, a data processing and analysis unit 3 and a display unit 4, the multi-parameter sensor unit 1 measures the particle size distribution of muck particles in real time, detects the water content of muck, detects and determines the density of muck, and detects the density of slurry after sedimentation through multiple sensors; the data acquisition and transmission unit 2 transmits shield muck data to the data processing and analysis unit 3 in real time; the data processing and analysis unit 3 performs filtering and denoising processing on shield muck data, introduces a correction algorithm based on the data difference law obtained from indoor tests, corrects the fine-grained soil content data detected by the intelligent densimeter, uses a multi-parameter fusion algorithm to comprehensively analyze multiple processed shield muck data, combines the weight of muck and the coarse-grained grading parameters, and calculates the content of fine-grained soil in shield muck; finally, the display unit 4 displays the calculation results of fine-grained soil content of muck, real-time measurement data of each sensor, weight of muck, coarse-grained grading and related construction parameters in real time; when the detected fine-grained soil content exceeds the preset reasonable range, the alarm immediately sends an audible and visual alarm signal to remind the construction personnel to take appropriate measures in time, such as adjusting the amount of muck improvement additives and optimizing shield tunneling parameters, and the alarm threshold can be flexibly set by the construction personnel in the system according to different engineering geological conditions and construction requirements.

[0079] The system quickly detects the fine-grained soil content in slurry separated from muck after sedimentation by using an intelligent densimeter, introduces a correction algorithm based on the data difference law obtained from indoor tests, corrects the fine-grained soil content data detected by the intelligent densimeter, uses a multi-parameter fusion algorithm to comprehensively analyze multiple processed shield muck data, realizes rapid detection and analysis of changes in fine-grained soil components in shield muck, solves the problems of long time consumption, complex operation and poor adaptability of traditional densimeter method, and realizes real-time monitoring of fine-grained soil content through the detection system, providing a basis for muck resource utilization.

[0080] Although embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and alterations can be made thereto without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A real-time detection system for fine-grained soil content in shield tunnel excavation soil based on multi-parameter fusion, characterized in that, It includes a multi-parameter sensor unit (1), a data acquisition and transmission unit (2), a data processing and analysis unit (3), and a display unit (4); The multi-parameter sensor unit (1) measures the particle size distribution of the slag particles in real time through a laser particle size analyzer, detects the moisture content of the slag in real time through a moisture content sensor, detects and determines the density of the slag through a density sensor, separates the slag to obtain mud and water through a mud-water separation device, and detects the density of the settled mud and water through an intelligent density meter. The data acquisition and transmission unit (2) is used to acquire electrical or digital signals output by the multi-parameter sensor unit (1) and process them, and then transmit the shield tunneling slag data to the data processing and analysis unit (3) in real time. The data processing and analysis unit (3) filters and denoises the shield tunnel slag data, introduces a correction algorithm based on the data difference law obtained from indoor tests, corrects the fine soil content data detected by the intelligent density meter, and uses a multi-parameter fusion algorithm to comprehensively analyze the shield tunnel slag data after various processing. Combining the slag weight and coarse particle gradation parameters, it calculates the content of fine soil in the shield tunnel slag. The display unit (4) displays in real time the calculation results of the fine soil content of the slag, the real-time measurement data of each sensor, the weight of the slag, the coarse particle gradation and related construction parameters. When the detected fine soil content exceeds the preset reasonable range, the alarm immediately issues an audible and visual alarm signal.

2. The real-time detection system for fine-grained soil content of shield tunnel slag based on multi-parameter fusion as described in claim 1, characterized in that, The multi-parameter sensor unit (1) includes a particle size analysis module (11), a moisture content detection module (12), a slag density detection module (13), a mud-water separation module (14), and a mud-water density detection module (15). The particle size analysis module (11) measures the particle size distribution of slag particles in real time using a laser particle size analyzer to obtain the particle size ratio of fine soil in slag. The moisture content detection module (12) detects the moisture content of the slag in real time through a moisture content sensor; The slag density detection module (13) detects and determines the slag density through a density sensor; The mud-water separation module (14) separates the slag and soil to obtain mud and water through a mud-water separation device; The mud-water density detection module (15) detects the density of the settled mud-water using an intelligent density meter, and calculates the content of fine-grained soil in the mud-water based on the correspondence between the mud-water density and the content of fine-grained soil.

3. The real-time detection system for fine-grained soil content of shield tunnel slag based on multi-parameter fusion as described in claim 1, characterized in that, In the data acquisition and transmission unit (2), the electrical or digital signals output by the multi-parameter sensor unit (1) are converted into a unified data format, and the analog signals are digitized using a high-precision A / D converter. The multi-sensor data are integrated through a data acquisition card, and the acquired data is transmitted to the data processing and analysis unit (3) in real time using wireless communication technology.

4. The real-time detection system for fine-grained soil content of shield tunnel slag based on multi-parameter fusion as described in claim 1, characterized in that, The data processing and analysis unit (3) includes a preliminary verification module (31), a data processing module (32), a data alignment module (33), a data correction module (34), a multi-parameter feature extraction module (35), a multi-parameter fusion algorithm operation module (36), and a data management module (37); The preliminary verification module (31) receives data from the data acquisition and transmission unit (2) in real time through a preset communication interface protocol. During the receiving process, it performs a preliminary verification of the integrity and format of the data. For data with problems, it automatically sends a retransmission request to the data acquisition and transmission unit (2). The data processing module (32) uses various filtering algorithms to process various shield tunneling slag data; The data alignment module (33) uses time synchronization technology to calibrate and align the timestamps of various shield tunneling slag data from various sensors, so that all parameters are consistent in the time dimension and form a unified time series dataset. The data correction module (34) corrects the fine-grained soil content data obtained by the smart densitometer by introducing a correction algorithm based on the data difference law obtained from indoor tests; The multi-parameter feature extraction module (35) extracts features from the preprocessed and corrected data, mines the feature information related to the fine soil content of each parameter, calculates the fine soil mass in a unit volume of slag soil by combining the slag weight data, calculates the ratio of coarse particles to fine soil by combining the coarse particle gradation data, and forms a multi-dimensional feature vector. The multi-parameter fusion algorithm operation module (36) uses the multi-parameter fusion algorithm to comprehensively analyze the extracted multi-dimensional feature vectors and calculate the content of fine soil in the shield tunnel slag. The data management module (37) uses a distributed database architecture to store the processed data, including raw sensor data, preprocessed data, correction results, fusion calculation results and related feature parameters, and regularly backs up the data to local hard disk and cloud storage.

5. The real-time detection system for fine-grained soil content of shield tunnel slag based on multi-parameter fusion according to claim 4, characterized in that, In the data processing module (32), for the continuous data output by the laser particle size analyzer, moisture content sensor and density sensor, the median filtering algorithm is used to remove instantaneous pulse interference; for the data output by the intelligent density meter, the Kalman filtering algorithm is used to predict the expected value of the data by establishing a dynamic model, and to dynamically correct it according to the deviation between the actual measured value and the predicted value.

6. The real-time detection system for fine-grained soil content of shield tunnel slag based on multi-parameter fusion according to claim 4, characterized in that, The data correction module (34) corrects the fine-grained soil content data obtained by the smart densitometer by introducing a correction algorithm based on the data difference law obtained from indoor tests, including the following steps: A1. During the indoor testing phase, a large number of slag soil samples with different fine-grained soil contents were collected and tested using both the intelligent density meter method and the traditional laboratory sieving method. A database of the differences between the test results of the two methods was established. A2. In the correction algorithm, the real-time detection value of the smart densitometer is used as input. By querying the difference database and combining it with a linear regression model or a BP neural network model, the corresponding correction coefficient is calculated to correct the detection value. A3. Regularly update the difference database, incorporating the latest field test data and laboratory comparison data, and continuously optimize the parameters of the correction model.

7. A derivation method for a real-time detection system of fine-grained soil content in shield tunnel excavation based on multi-parameter fusion, applicable to the real-time detection system of fine-grained soil content in shield tunnel excavation based on multi-parameter fusion as described in any one of claims 1-6, characterized in that, Includes the following steps: I. Establishing a historical database: During the tunnel boring machine (TBM) construction process, the system continuously collects and stores multi-parameter detection data, TBM tunneling parameters, and geological condition information at different construction stages to establish a historical database; II. Data Feature Extraction: In-depth analysis of historical database data is conducted to extract feature parameters closely related to changes in fine-grained soil content. Statistical analysis methods are used to determine which parameters are strongly correlated with fluctuations in fine-grained soil content under different geological conditions. III. Data Feature Selection: Data mining techniques are used to uncover potential correlation features between various parameters. Feature selection algorithms are then used to select the most representative subset of feature parameters that contribute the most to the inference of fine-grained soil content from among the numerous extracted features. IV. Constructing the projection model: Based on the selected feature parameters, a fine-grained soil content projection model is constructed using machine learning algorithms or time series analysis methods; V. Real-time simulation and result output: During the shield tunneling process, the current multi-parameter detection data, slag weight, coarse particle gradation, shield tunneling parameters and geological conditions information are input into the verified and optimized simulation model in real time. Based on the input data, the model quickly predicts the changing trend of fine soil content of shield slag during the next 5-10 ring tunneling period and outputs the simulation results to the display unit (4) for display.

8. The deduction method for the real-time detection system of fine-grained soil content in shield tunnel slag based on multi-parameter fusion as described in claim 7, characterized in that, Step IV includes the following steps: B1. Based on the selected feature parameters, a model for extrapolating the content of fine-grained soil is constructed using machine learning algorithms or time series analysis methods. B2. During the model building process, a portion of the data in the historical database is used as the training set to optimize and adjust the model parameters; B3. Use the remaining data in the historical database as a test set to verify the constructed inference model. Evaluate the model's predictive performance by calculating the error index between the model's prediction results and the actual fine-grained soil content data in the test set. B4. If the model error is large, further analyze the reasons, take corresponding optimization measures, and then train and validate the model again until the model achieves satisfactory prediction accuracy and stability.

Images