TRD construction quality detection method and system

Abstract

The invention relates to the technical field of intelligent civil engineering, in particular to a TRD construction quality detection method and system. The method comprises the following steps: acquiring construction real-time data; performing soil characteristic analysis and construction state analysis according to the construction real-time data to obtain soil characteristic data and construction state data; performing construction state change analysis according to the soil characteristic data and the construction state data to obtain construction state change data; and performing construction parameter optimization according to the construction state change data to obtain construction parameter optimization data so as to perform TRD construction quality detection auxiliary operation. By analyzing the relationship between the soil mechanical properties (such as density, sound velocity, porosity and the like) and the operation state (such as cutterhead load, rotation speed, stirring depth and the like) of the construction equipment, the deep analysis of the coupling relationship between the soil and the construction state is realized, and the construction efficiency and quality are improved.

Description

Technical Field

[0001] The present invention relates to the field of smart civil engineering technology, and in particular to a TRD construction quality detection method and system. Background Art

[0002] In modern civil engineering and foundation construction, the TRD (Trench cutting Re-mixing Deep wall) method is widely used in underground continuous walls, soft soil foundation reinforcement and anti-seepage projects. The TRD method achieves full mixing of soil and curing agent through rotary cutting and mixing of the cutter disc, and its construction quality directly affects the stability and durability of the project. In complex geological environments (such as hard interlayers, soft soil layers, etc.), the dynamic changes in soil properties and construction status often affect the construction quality, and traditional methods cannot perceive and adjust these changes in real time. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a TRD construction quality detection method and system to solve at least one of the above technical problems.

[0004] The present application provides a TRD construction quality detection method, the method comprising:

[0005] S1. Obtain real-time construction data;

[0006] S2. Perform soil property analysis and construction status analysis based on real-time construction data to obtain soil property data and construction status data;

[0007] S3. Perform construction status change analysis based on soil property data and construction status data to obtain construction status change data;

[0008] S4. Optimize construction parameters according to the construction status change data to obtain construction parameter optimization data for TRD construction quality inspection auxiliary operations.

[0009] The present invention realizes real-time perception of the entire construction process to ensure the comprehensiveness and real-time nature of the data. Soil property analysis can identify the geological conditions of the construction area (such as density, humidity, porosity, etc.), providing an accurate basis for the analysis of construction state changes. Construction state analysis can grasp the equipment operation status (such as cutter head speed, feed speed, etc.) in real time, effectively monitor the construction progress and warn of potential problems. Through dynamic analysis of soil property data and construction state data, the state change trend during the construction process can be accurately predicted. Potential risks (such as cutter head overload, uneven mixing, etc.) can be predicted to provide a scientific basis for optimizing construction parameters. Improve the foresight of construction management and reduce quality risks caused by delayed response to state changes. Based on the construction state change data, an intelligent algorithm is used to dynamically adjust the construction parameters (such as mixing depth, rotation speed, etc.) to ensure that the construction quality meets the design requirements. Avoid resource waste caused by improper parameter settings (such as excessive agitators or equipment wear) and improve construction efficiency. Form a closed-loop control mechanism to achieve the complete process of "detection-analysis-optimization-feedback".

[0010] Optionally, S1 includes:

[0011] S11, through the multi-modal sensor integrated in the TRD equipment, real-time data including soil resistance, cutterhead rotation speed and depth displacement are collected to obtain the original construction data;

[0012] S12, performing geographic information fusion on the original construction data to obtain geographic annotated construction data;

[0013] S13. Perform real-time multi-source data integration on the geographically annotated construction data to obtain real-time construction data.

[0014] The multimodal sensor in the present invention can comprehensively cover soil characteristics and construction equipment status, ensuring the multi-dimensionality and accuracy of data collection. Through the precise annotation of geographic information, the correspondence between construction data and actual location is ensured, supporting regional analysis of geological characteristics. Real-time multi-source data integration solves the problem of inconsistent data types of multimodal sensors, ensuring that the integrated real-time construction data can be directly called.

[0015] Optionally, S2 includes:

[0016] S21, extracting soil characteristic features and construction status features from the real-time construction data to obtain soil characteristic feature data and construction status feature data respectively;

[0017] S22, performing multi-dimensional correlation of characteristics according to soil property feature data and construction status feature data to obtain construction feature relationship data;

[0018] S23, generating a soil model based on the construction characteristic relationship data to obtain a soil mechanical model;

[0019] S24, extracting soil characteristics from the soil mechanics model to obtain soil characteristic data;

[0020] S25, performing construction status modeling on the construction feature relationship data to obtain a construction status model;

[0021] S26. Extract the construction status of the construction status model to obtain construction status data.

[0022] In the present invention, multi-dimensional feature extraction is used to accurately identify the physical properties of the soil and the status of the construction equipment in the construction environment. The dynamic interactive relationship between soil characteristics and construction status is revealed, providing a basis for the cause analysis of construction problems. Combined with the construction feature relationship, a high-precision soil mechanics model that is more in line with the actual construction is generated. Based on the soil mechanics model, the key mechanical properties of the soil, such as shear strength, stiffness modulus, etc., are extracted through stress-strain analysis and dynamic response analysis. The construction status model can predict key states (such as equipment load changes) in real time and reduce the risk of construction accidents. The output of the construction status model is parsed, and the key state characteristics of the construction process (such as equipment operating efficiency, mixing depth, rotation speed, etc.) are extracted to generate construction status data.

[0023] Optionally, the soil characteristic feature extraction includes:

[0024] Extracting first soil characteristic features from the real-time construction data to obtain first soil characteristic feature data;

[0025] Performing a second soil characteristic feature extraction on the real-time construction data to obtain second soil characteristic feature data, wherein the first soil characteristic feature extraction and the second soil characteristic feature extraction are different soil characteristic feature extraction methods;

[0026] The first soil characteristic feature data and the second soil characteristic feature data are fused to obtain soil characteristic feature data.

[0027] In the present invention, the first soil characteristic feature extraction and the second soil characteristic feature extraction are used to analyze the real-time construction data in different ways to ensure the multi-dimensionality and integrity of the soil characteristic feature data. The diversity and depth of soil characteristic analysis are enhanced to avoid feature omissions or distortions that may be caused by a single method. By combining a variety of soil characteristic feature extraction methods and utilizing their respective technical advantages, more accurate and reliable characteristic data can be generated. The feature fusion process can correct the errors generated by different methods and improve data consistency. The fusion process eliminates the limitations of a single feature extraction method and provides a comprehensive description of soil characteristics.

[0028] Optionally, the real-time construction data includes soil vibration wave data, which is collected by a seismic wave sensor or a high-frequency vibration sensor, and the first soil characteristic feature extraction includes:

[0029] Perform time domain characteristic analysis on soil vibration wave data in real-time construction data to obtain soil time domain characteristic data;

[0030] Performing frequency domain data transformation on soil time domain characteristic data to obtain soil frequency domain characteristic data;

[0031] Performing energy spectrum decomposition on soil frequency domain characteristic data to obtain soil spectrum decomposition data;

[0032] Performing dynamic response parameter mapping on soil spectrum decomposition data to obtain first soil characteristic feature data;

[0033] The energy spectrum decomposition includes:

[0034] Perform time-frequency joint transformation on soil time-domain characteristic data to obtain local time-frequency characteristic data;

[0035] Extracting spectrum energy distribution of local time-frequency feature data to obtain spectrum energy distribution data;

[0036] Perform multi-scale spectrum decomposition on the spectrum energy distribution data to obtain multi-scale spectrum data;

[0037] Performing spectrum correlation analysis on multi-scale spectrum data to obtain spectrum correlation matrix data;

[0038] Perform energy characteristic clustering processing on the spectrum correlation matrix data to obtain the soil spectrum energy clustering characteristics;

[0039] Reconstruct the characteristic spectrum of soil spectrum energy clustering features to obtain soil reconstructed spectrum data;

[0040] Soil spectrum decomposition data is generated according to the soil reconstructed spectrum data to obtain soil spectrum decomposition data.

[0041] The present invention provides a multi-dimensional analysis of soil dynamic characteristics and frequency domain energy characteristics, providing reliable data support for construction status adjustment and optimization. Through multi-scale spectral decomposition and dynamic response parameter mapping of soil vibration wave data, the response characteristics of soil under complex construction conditions can be accurately identified. The adaptability of TRD construction under complex geological conditions is improved and construction errors are reduced. The output soil characteristic data directly serves the intelligent construction model, providing a basis for full-process monitoring and dynamic optimization of construction quality. Dynamic parameter mapping and feature data reconstruction reduce data noise and errors, making construction status prediction and parameter optimization more accurate. Through real-time monitoring and efficient data processing, construction risks are reduced and overall construction efficiency is improved.

[0042] In the present invention, time domain data is converted into time-frequency distribution to reveal the changing rules of vibration characteristics with time and frequency. Dynamically changing local time-frequency characteristics are provided to support fine-grained analysis. The energy density at different frequencies is accurately calculated to quantify the response intensity of the soil on the vibration spectrum. Direct support is provided for the identification and characteristic modeling of high-energy frequency bands. The energy characteristics of soil vibration waves are refined and separated into high frequency, medium frequency and low frequency to provide a hierarchical description of dynamic characteristics. Data redundancy or frequency information loss in characteristic analysis is avoided. The correlation and coupling characteristics between frequency components are revealed to provide structured information for frequency domain modeling. Cross-band characteristic fusion is supported to enhance the depth of data integration. Spectral energy characteristics are classified to identify the relationship between specific frequency bands and geological characteristics (such as faults and cracks). The clustering results directly serve the zoning analysis and construction status adjustment of the construction area. The spectrum spectrum is reconstructed based on the clustering characteristic data to generate clearer energy distribution characteristics. The reconstructed spectrum provides visual and intuitive support for construction status prediction.

[0043] Optionally, the real-time construction data includes soil acoustic wave data, which is collected by an acoustic wave sensor, and the second soil characteristic feature extraction includes:

[0044] Perform multi-band acoustic wave transmission analysis on the soil acoustic wave data in the real-time construction data to obtain soil acoustic wave transmission data;

[0045] Calculate the sound velocity of soil sound wave transmission data to obtain soil sound velocity data;

[0046] Extract the acoustic wave reflection characteristics of the soil sound velocity data to obtain soil reflection characteristic parameter data;

[0047] Performing sound wave attenuation analysis on soil emission characteristic parameter data to obtain soil sound wave attenuation data;

[0048] Performing sound wave propagation simulation on soil sound wave attenuation data to obtain soil sound wave propagation data;

[0049] Soil characteristic parameters are inverted according to the soil acoustic wave propagation data to obtain second soil characteristic feature data.

[0050] In the present invention, the acoustic wave data of different frequency bands are analyzed to extract the transmission time, amplitude and phase change of each frequency band. The acoustic wave propagation velocity of the soil is calculated according to the length of the acoustic wave transmission path and the time difference, and the environmental parameters are combined for correction, and the sound velocity is calculated in real time to accurately reflect the acoustic behavior of the soil under different depths, humidity and pressure conditions. The reflection coefficient and reflection amplitude are calculated by analyzing the reflection characteristics of the sound waves at different interfaces (such as cracks and soil layer junctions). The energy attenuation coefficient of the sound wave is calculated when it is transmitted in the soil medium, and the absorption capacity of the soil for sound waves of different frequency bands is analyzed in combination with the frequency characteristics. The loss of the soil medium to the sound wave energy is evaluated in real time, and the absorption characteristics of the soil are quantified. The propagation path, waveform changes and energy distribution of the sound wave in the soil are simulated to intuitively reflect the internal structure of the soil. Combined with the sound wave propagation data, the mechanical and physical properties of the soil are extracted through the inversion algorithm (such as full waveform inversion, Bayesian optimization), and the key characteristics such as soil density, elastic modulus, and porosity are generated with high precision through the inversion algorithm.

[0051] Optionally, the soil reflection characteristic parameter data includes sound wave scattering characteristic data, and the sound wave scattering characteristic data is extracted by:

[0052] The soil physical model is constructed based on the real-time construction data to obtain discrete soil grid data;

[0053] Annotate the acoustic wave source parameters according to the discrete soil grid data to obtain the acoustic wave source annotation data;

[0054] Perform acoustic wave scattering simulation on the acoustic wave source annotation data and soil sound velocity data to obtain scattered acoustic field distribution data;

[0055] The scattering intensity and directionality of the scattered sound field distribution data are analyzed to obtain the sound wave scattering characteristic data.

[0056] In the present invention, a discrete soil grid model is constructed based on real-time construction data (such as acoustic wave data and geological survey information), which includes physical parameters such as soil density, porosity, and humidity, supports the modeling of layered soil and heterogeneous media, and adapts to the needs of different construction environments. The acoustic wave source parameters are marked in the soil grid model, including the acoustic wave source position, frequency range, waveform type (such as sine wave, pulse wave), etc. The propagation and scattering behavior of sound waves in the soil are simulated, and scattered sound field distribution data is generated to reproduce the reflection, scattering and diffraction phenomena caused by cracks, obstacles, etc. encountered by sound waves in the soil. The scattered sound field distribution data is quantitatively analyzed, the scattering intensity and directivity are calculated, and a scattering characteristic spectrum is generated. The spatial distribution and frequency response of the scattered sound field are used to identify the sound wave propagation path and energy loss.

[0057] Optionally, S3 includes:

[0058] S31, performing construction status change processing according to soil property data and construction status data to obtain construction status change trend data;

[0059] S32, extracting abnormal isolated points according to the construction status change trend data to obtain abnormal isolated construction point data;

[0060] S33, performing abnormal classification according to the construction abnormality isolated point data to obtain construction abnormality classification data;

[0061] S34, performing change causal analysis on the construction abnormality classification data to obtain construction change causal data;

[0062] S35, integrating the construction status change trend data, the construction abnormality isolated point data and the construction change cause and effect data to obtain the construction status change data.

[0063] In the present invention, soil property data and construction status data are combined to generate construction status change trend data, identify the dynamic change characteristics of soil and equipment status during construction, and support real-time adjustment. Anomaly detection algorithms (such as isolation forest algorithm, DBSCAN clustering) are used to extract construction abnormality isolated points from trend data, efficiently identify abnormal points that deviate from the trend, and locate potential problems. The construction abnormality isolated points are classified, and different types of anomalies are identified. The anomalies are divided into equipment anomalies, soil property anomalies, construction process anomalies, etc., to provide targeted support for analysis and resolution. The causal relationship of the abnormal classification data is derived to identify the deep reasons for the changes in the construction status, reveal the causal relationship behind the anomaly, and help decision makers accurately lock in the cause of the anomaly. A unified presentation of trends, anomalies and causal analysis results is achieved to form data results of construction status changes.

[0064] Optionally, S4 includes:

[0065] S41, generating an optimization target according to the construction status change data to obtain construction optimization target data;

[0066] S42, selecting optimization variables according to the construction optimization target data to obtain construction optimization variable data;

[0067] S43. Target optimization is performed on the construction status change data according to the construction optimization variable data to obtain construction parameter optimization data for TRD construction quality inspection auxiliary operations.

[0068] The present invention uses in-depth analysis of construction status change data and generation of optimization targets to adjust construction variables in a targeted manner, optimize construction parameters, and ensure that construction quality meets design requirements. Optimization targets and variable selection are combined with real-time construction status change data, which can quickly adapt to complex or dynamic construction environments and enhance the adaptability of construction equipment and processes. The precise optimization process reduces problems such as excessive equipment load and material waste, improves construction efficiency, and ensures high quality of construction results. By optimizing variable selection and parameter adjustment, unnecessary resource consumption and loss of construction equipment are reduced. Scientific optimization reduces the risk of construction accidents or failures and ensures the safety of construction.

[0069] Optionally, the present invention further provides a TRD construction quality detection system, which is used to execute the TRD construction quality detection method as described above, and the TRD construction quality detection system comprises:

[0070] Construction real-time data collection module, used to obtain real-time construction data;

[0071] The real-time construction analysis module is used to analyze soil characteristics and construction status based on real-time construction data to obtain soil characteristics data and construction status data;

[0072] A construction status change processing module is used to analyze the construction status change according to the soil characteristic data and the construction status data to obtain the construction status change data;

[0073] The construction parameter optimization module is used to optimize the construction parameters according to the construction status change data, and obtain the construction parameter optimization data to carry out TRD construction quality inspection auxiliary operations.

[0074] The purpose of the present invention is to collect multidimensional data such as soil resistance, cutterhead rotation speed, depth displacement, etc. in real time through a multimodal sensor network to ensure the comprehensiveness and accuracy of construction data. Extract parameters such as soil dynamic characteristics, density, porosity, etc. Dynamically monitor the status of construction equipment (such as cutterhead load, feed speed), generate construction status data, and reflect the actual situation of equipment operation and construction technology in real time. Multi-dimensionally associate soil characteristic data with construction status data to generate construction characteristic relationship data to provide input for state change analysis. The combination of soil mechanics model and construction status model improves the accuracy of construction characteristic modeling. Extract abnormal points from the change trend and classify them to accurately locate the type of construction abnormality (such as equipment failure, geological problems). Through causal analysis technology, the deep reasons behind the abnormality are revealed, providing a scientific basis for problem tracing and construction decision-making. Use optimization algorithms to target optimize construction status data, dynamically adjust construction parameters, and ensure that construction quality and efficiency reach the best level. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting implementations made with reference to the following drawings:

[0076] Figure 1 A flowchart showing a method for detecting TRD construction quality according to an embodiment is shown;

[0077] Figure 2 A flowchart showing a method for collecting construction real-time data according to an embodiment of the present invention is provided;

[0078] Figure 3 A flowchart showing a method for real-time construction analysis according to an embodiment is shown;

[0079] Figure 4 A flowchart showing a method for processing a construction state change according to an embodiment of the present invention is provided;

[0080] Figure 5 A flowchart showing the steps of a construction parameter optimization method according to an embodiment is shown;

[0081] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0082] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0083] In addition, the drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0084] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0085] See also Figures 1 to 5 , the present application provides a TRD construction quality detection method, the method comprising:

[0086] S1. Obtain real-time construction data;

[0087] In one embodiment, a variety of sensors are installed on the construction equipment, including pressure sensors, acceleration sensors, acoustic wave sensors, and displacement sensors. Key data such as soil resistance, equipment vibration, acoustic wave propagation characteristics, and cutter head depth are collected in real time. The collected data is transmitted to the central control system through a wireless transmission module, and combined with the geographic information of the construction area, the complete recording and spatial annotation of the real-time construction data is realized.

[0088] In one embodiment, force sensors, acceleration sensors, displacement sensors, and pressure sensors are installed on construction equipment (such as chain saws and cutter heads) to monitor data during equipment operation in real time. Conductivity detectors and moisture sensors are buried in the soil of the construction area to monitor the conductivity and humidity of the soil in real time. The data collected by the sensor is transmitted to the on-site monitoring terminal in real time through the Industrial Internet of Things (IoT) gateway. The data includes timestamp, cutter head position, soil conductivity, equipment applied pressure, and soil moisture. The collected data is denoised (such as using a sliding average method) to obtain a cleaned data set, and the data is stored in groups and divided into blocks by time period.

[0089] S2. Perform soil property analysis and construction status analysis based on real-time construction data to obtain soil property data and construction status data;

[0090] In one embodiment, in the control system, real-time data is processed and used to analyze soil characteristics and construction status: soil characteristic analysis evaluates soil density, moisture distribution and resistance changes at different depths through data correlation to generate a soil layer profile. Construction status analysis uses the vibration signal and applied pressure of the equipment to determine whether the operating status of the construction equipment is normal, such as whether the equipment is overloaded or the soil resistance increases abnormally.

[0091] In one embodiment, based on the soil conductivity σ i and humidity H i , use the following formula to evaluate soil density ρ: ρ = k1 × σ i +k2×H i , where i is the time order term, and k1 and k2 are coefficients expressed based on experience. Based on real-time soil property data, a soil profile is generated to characterize soil heterogeneity. Based on the mechanical feedback data F of the construction equipment i and acceleration a i , calculate the force and motion state of the device: τ = F i / A, A is the contact area of ​​the equipment blade. Combined with the equipment position data P i(x,y,z) to determine whether the construction status is normal, for example, whether there is overpressure or equipment jam.

[0092] S3. Perform construction status change analysis based on soil property data and construction status data to obtain construction status change data;

[0093] In one embodiment, the control system performs dynamic change analysis on soil property data and construction status data: the system uses data trend analysis methods to identify the changing trends of soil resistance and equipment status during construction and draws real-time status curves. At the same time, anomaly detection methods are used to extract abnormal isolated points in the construction process, such as sudden resistance increases or drastic changes in equipment vibration. The system performs causal analysis on the context data of the abnormal points and marks the soil properties (such as excessive local density) or equipment parameters (such as pressure outside the normal range) that cause the abnormalities.

[0094] In one embodiment, the previous time t i-1 Construction status data (t i-1 ,τ i-1 ,a i-1 ) and the current time t i The state (t i , τ i , a i ) to compare and calculate the rate of change: Δτ=(τ i -τ i-1 ) / (t i -t i-1 ), Δa=(a i -a i-1 ) / (t i -t i-1 ), generate a construction status change curve, and detect whether there are any abnormalities in the construction process, such as sudden stress increase or acceleration fluctuation. Define the threshold range Δτ max -Δτ min and Δa max -Δa min ,When Δτ or Δa exceeds the threshold, the anomaly is marked and the relevant time and location are recorded.

[0095] S4. Optimize construction parameters according to the construction status change data to obtain construction parameter optimization data for TRD construction quality inspection auxiliary operations.

[0096] In one embodiment, based on the construction status change data, the system sets construction optimization goals, such as maximizing construction efficiency, minimizing energy consumption, reducing abnormal occurrences, etc. Combined with the capacity constraints of the construction equipment, the system optimizes and adjusts the rotation speed of the cutter disc, the pressure applied by the equipment, and the progress speed: After the optimization target is determined, the system gives priority to variables that have a significant impact on the target, such as adjusting the rotation speed of the cutter disc and the thrust of the equipment. The system calculates the new equipment operating parameters through the optimization algorithm and feeds them back to the construction equipment. The construction equipment operates according to the optimized parameters, and the real-time monitoring of the construction data verifies the effectiveness of the optimization plan, significantly improving the construction efficiency, while reducing the occurrence of equipment overload and abnormal shutdowns.

[0097] In one embodiment, a multi-dimensional optimization objective function is constructed based on soil property data ρ, construction state change data Δτ, Δa, and construction parameters (such as cutter head speed v, cutting angle θ, and pressure F): Where E(v,θ) is the energy consumption model or the mathematical expression of energy consumption relationship, which describes the energy consumption per unit time. S(F) is the construction stability model or the mathematical expression of construction stability, which describes the relationship between abnormal rate and pressure. C1 is the weight coefficient of the energy consumption model, and C2 is the weight coefficient of the construction stability model. Adjust the construction parameters based on historical data to make the objective function gradually approach the minimum value. Update the operating status of the equipment by feeding back the optimization parameters. Get the optimized construction parameters (v * ,θ * , F * ) and feed it back to the construction equipment to guide subsequent construction operations.

[0098] Optionally, S1 includes:

[0099] S11, through the multi-modal sensor integrated in the TRD equipment, real-time data including soil resistance, cutterhead rotation speed and depth displacement are collected to obtain the original construction data;

[0100] In one embodiment, the following sensors are installed on the TRD equipment: Soil resistance sensor: real-time measurement of the resistance of the cutter disc in contact with the soil, recording information such as soil density. Rotation speed sensor: monitors the rotation speed of the cutter disc to evaluate the working efficiency of the equipment. Depth displacement sensor: measures the real-time position of the cutter disc and accurately records the construction depth. During the construction process, these sensors collect data at fixed time intervals to form a raw construction data stream containing resistance value, rotation speed and depth.

[0101] S12, performing geographic information fusion on the original construction data to obtain geographic annotated construction data;

[0102] In one embodiment, the construction equipment is also equipped with a high-precision GPS positioning module to record the three-dimensional spatial position of the construction equipment in real time. The collected original construction data is associated with the location information of the equipment, and geographic coordinates (such as longitude, latitude and depth) are added to each set of data. Through geographic information fusion, construction data with location annotations are generated to accurately represent the construction status of different spatial points.

[0103] S13. Perform real-time multi-source data integration on the geographically annotated construction data to obtain real-time construction data.

[0104] In one embodiment, the geo-annotated data and the multi-modal data collected by the sensor are integrated under a unified time axis. The data of soil resistance, rotation speed and depth displacement are synchronized through the timestamp alignment method, and real-time multi-source construction data is generated. The integrated real-time construction data can be further analyzed for soil property evaluation and construction status monitoring.

[0105] Optionally, S2 includes:

[0106] S21, extracting soil characteristic features and construction status features from the real-time construction data to obtain soil characteristic feature data and construction status feature data respectively;

[0107] In one embodiment, the real-time construction data includes soil resistance, acoustic wave propagation characteristics, cutter head depth displacement and equipment operation parameters. Using resistance data and acoustic wave characteristics, soil density, moisture and stratification characteristics at different depths are extracted to generate a soil stratification profile. Combined with the rotation speed and acceleration of the equipment, the dynamic parameters of the equipment operation, such as the cutter head rotation speed, equipment force, resistance change rate and torque change rate, are extracted to monitor whether the construction equipment is in normal working condition.

[0108] S22, performing multi-dimensional correlation of characteristics according to soil property feature data and construction status feature data to obtain construction feature relationship data;

[0109] In one embodiment, soil characteristic feature data and construction status feature data are jointly analyzed, and the correlation between soil characteristic changes and equipment operation status is found by matching the spatial location and time point of the data. For example, when the soil density is high in some areas, the rotation speed of the equipment decreases significantly, forming a set of construction characteristic relationship data with physical correlation.

[0110] In one embodiment, more importantly, spatial alignment is performed on soil property feature data and construction status feature data to obtain construction feature alignment data; physical feature screening is performed on the construction feature alignment data to obtain construction feature screening data; maximum information coefficient calculation is performed on the construction feature screening data to obtain construction feature correlation data; dynamic lag window analysis is performed on the construction feature correlation data to obtain construction feature association data; high-dimensional graph mapping is performed on the construction feature association data to obtain construction feature relationship data.

[0111] According to the real-time position of the construction equipment (such as depth and horizontal position), the two sets of data are matched. In the soil characteristic area with sparse data, the interpolation method is used to fill in the missing data points to ensure that the construction status data can be aligned with the soil characteristic data at each spatial point. Priority is given to retaining features that are significantly physically associated with the construction objectives (such as efficiency and abnormality rate). Eliminate features with large noise or redundant features. Perform statistical analysis on the distribution of each feature variable, and eliminate features with abnormal data distribution or too small a range of variation (such as low-correlated soil sound velocity changes). According to the dynamic characteristics of the construction equipment and the physical properties of the soil, select the core features: Equipment parameters: cutterhead rotation speed, propulsion speed, pressure. Soil parameters: resistance gradient, porosity, density. Use the construction characteristics to screen the data to calculate the maximum information coefficient (MIC) between each feature: Calculate the MIC value for each pair of features (such as soil density and rotation speed, porosity and pressure). The MIC value range is 0,1, and the closer the value is to 1, the stronger the association between the two features. For example, it is found that the MIC value of soil resistance gradient and propulsion speed is high, indicating that there is a strong association between them. For each pair of features, a time window (such as 3 seconds, 5 seconds) is set to analyze the delayed effect of the change of one feature on another feature. The length of the time window is dynamically adjusted to find the lag time corresponding to the maximum correlation. For example, it is found that the change in the rotation speed of the cutterhead has a lag of 1-2 seconds on the propulsion speed, indicating that the operation adjustment of the construction equipment requires a certain reaction time. According to the construction feature association data, the association relationship is mapped to a high-dimensional space to generate a feature relationship graph: a correlation graph is constructed, and each feature is used as a node in the graph. According to the strength of the correlation between the features, weighted edges are added, and the weight of the edge is determined by the MIC value and the lag analysis results. The complex relationship between the features is displayed through a high-dimensional graph: the edges between the nodes reflect the direct association of the features. The edges with larger weights reveal the key relationships in the construction process (such as the interactive effect of the resistance gradient and the rotation speed of the cutterhead).

[0112] S23, generating a soil model based on the construction characteristic relationship data to obtain a soil mechanical model;

[0113] In one embodiment, a soil mechanics model suitable for the construction area is generated based on the construction characteristic relationship data through finite element analysis and finite element calculation, combined with soil resistance and density characteristics. The model can describe the bearing capacity and resistance variation characteristics of the soil at different depths.

[0114] S24, extracting soil characteristics from the soil mechanics model to obtain soil characteristic data;

[0115] In one embodiment, the soil mechanics model is used to further extract parameters in the model to generate specific soil characteristic data, including: soil density at different depths; resistance characteristics of each layer of soil; and dynamic response characteristics of the soil.

[0116] S25, performing construction status modeling on the construction feature relationship data to obtain a construction status model;

[0117] In one embodiment, a construction state model is established based on the construction characteristic relationship data and combined with the dynamic parameters of the equipment. The model can dynamically describe the relationship between the equipment operating parameters (such as rotation speed, pressure) and the construction efficiency, and at the same time reflect the potential triggering mechanism of construction anomalies. For example, a multivariate linear regression model is used to describe a simple linear relationship. If the data presents nonlinear characteristics, a nonlinear regression model (such as a polynomial model) or a time series model is selected. Alternatively, a tree-based model (such as a random forest or a gradient boosting tree) or a neural network model is used when considering the complex interactive relationship between multiple variables.

[0118] S26. Extract the construction status of the construction status model to obtain construction status data.

[0119] In one embodiment, the construction status model is used to extract key status data in the construction process, such as: the stability of equipment operation; construction efficiency in different time periods; and the spatiotemporal distribution of potential anomalies (such as excessive equipment load or unstable operation).

[0120] Optionally, the soil characteristic feature extraction includes:

[0121] Extracting first soil characteristic features from the real-time construction data to obtain first soil characteristic feature data;

[0122] In one embodiment, the construction equipment collects soil resistance data of the cutter head at different depths through a resistance sensor and a depth sensor. The system uses this data to extract the first soil characteristic feature, analyzes the resistance values ​​at different depths in the construction area, and evaluates the change of soil density with depth. According to the gradient change of resistance, the layered characteristics of the soil are identified, and soil layered profile data are generated, thereby obtaining the first soil characteristic feature data, which contains the density and layering information of each layer of soil, providing a basis for the mechanical property analysis of the soil.

[0123] Performing a second soil characteristic feature extraction on the real-time construction data to obtain second soil characteristic feature data, wherein the first soil characteristic feature extraction and the second soil characteristic feature extraction are different soil characteristic feature extraction methods;

[0124] In one embodiment, the construction equipment also collects soil acoustic wave propagation data through an integrated acoustic wave sensor. The system uses the acoustic wave propagation characteristics to extract the second soil characteristic feature, analyzes the acoustic wave propagation speed at different depths and locations, and evaluates the uniformity and porosity of the soil. Based on the reflection and attenuation characteristics of the sound waves, abnormal areas in the soil (such as high-density particles or voids) are further identified. The generated second soil characteristic feature data reflects the acoustic characteristics and microstructural information of the soil, supplementing the results of the first method.

[0125] The first soil characteristic feature data and the second soil characteristic feature data are fused to obtain soil characteristic feature data.

[0126] In one embodiment, the feature data obtained by the first and second extraction methods are fused, and the two sets of feature data are spatially aligned according to depth and position. The mechanical properties (resistance and density) and acoustic properties (sound velocity and attenuation) of the soil are integrated to generate unified soil characteristic feature data. The fused soil characteristic feature data includes the mechanical properties, acoustic properties and stratification information of the soil, providing more comprehensive basic data for construction parameter optimization and construction quality assessment.

[0127] Optionally, the real-time construction data includes soil vibration wave data, which is collected by a seismic wave sensor or a high-frequency vibration sensor, and the first soil characteristic feature extraction includes:

[0128] Perform time domain characteristic analysis on soil vibration wave data in real-time construction data to obtain soil time domain characteristic data;

[0129] In one embodiment, soil vibration wave data is recorded in real time by sensors, and these data include the response signal of the soil under the action of the vibration source. The time variation of the vibration wave signal is statistically analyzed to extract the characteristics of the signal such as the average value, peak value and fluctuation amplitude. These time domain characteristic data reflect the response intensity of the soil to the vibration and the overall characteristics of the signal waveform, such as the attenuation trend of the amplitude over time.

[0130] Performing frequency domain data transformation on soil time domain characteristic data to obtain soil frequency domain characteristic data;

[0131] In one embodiment, based on the soil's time domain characteristic data, the construction team performed frequency domain analysis on the vibration wave signal, converted the time domain signal into a frequency domain signal, and extracted the amplitude and energy distribution at different frequencies. By observing the spectrum, the main frequency components and energy concentration areas were identified, reflecting the frequency response characteristics of the soil.

[0132] Performing energy spectrum decomposition on soil frequency domain characteristic data to obtain soil spectrum decomposition data;

[0133] In one embodiment, the frequency domain data of the soil is subjected to energy spectrum decomposition, the energy distribution of the frequency domain signal is divided into different frequency bands, and the energy contribution of each frequency band is calculated respectively. Through the decomposition process, the system identifies that some frequency bands contribute more to the overall energy, and these frequency bands may correspond to special characteristics in the soil structure, such as dense areas or void areas.

[0134] Performing dynamic response parameter mapping on soil spectrum decomposition data to obtain first soil characteristic feature data;

[0135] In one embodiment, based on the energy spectrum decomposition data, the system further performs a dynamic response analysis to extract soil dynamic response parameters at specific frequencies, such as damping characteristics and vibration modulus. By mapping these parameters to the soil model of the construction area, the soil dynamic response distribution at different locations is generated.

[0136] The energy spectrum decomposition includes:

[0137] Perform time-frequency joint transformation on soil time-domain characteristic data to obtain local time-frequency characteristic data;

[0138] In one embodiment, the vibration signal of the soil during the construction process is collected, and the system performs a time-frequency joint transformation on the time domain signal, combines the time domain characteristics of the soil vibration signal with the frequency domain characteristics, and generates the local characteristics of the vibration signal on the time and frequency axis. The local time-frequency characteristic data shows the response of the soil to vibrations of different frequencies in different time periods, laying the foundation for energy distribution analysis.

[0139] Extracting spectrum energy distribution of local time-frequency feature data to obtain spectrum energy distribution data;

[0140] In one embodiment, based on the local time-frequency feature data, the system analyzes the spectral energy distribution of the soil vibration signal. The energy proportion of different frequency bands is extracted to determine the main energy concentration area of ​​the vibration wave signal. Through this distribution extraction, the system can identify the absorption and transmission characteristics of the soil to vibrations of different frequencies.

[0141] Perform multi-scale spectrum decomposition on the spectrum energy distribution data to obtain multi-scale spectrum data;

[0142] In one embodiment, the system further refines the spectrum energy distribution data and performs multi-scale spectrum decomposition. The spectrum is divided into multiple scale ranges (such as low frequency, medium frequency and high frequency), and the energy contribution of each scale is calculated respectively. The multi-scale decomposition reflects the soil's ability to respond to vibrations in different frequency ranges, especially the differences in deep or shallow soil.

[0143] Performing spectrum correlation analysis on multi-scale spectrum data to obtain spectrum correlation matrix data;

[0144] In one embodiment, by analyzing multi-scale spectral data, the system calculates the correlation between different frequency bands. The energy changes of each frequency band are compared to evaluate their mutual influence in space or time. The correlation analysis reveals the dynamic connection between different regions of the soil and provides support for understanding the overall vibration behavior of the soil.

[0145] Perform energy characteristic clustering processing on the spectrum correlation matrix data to obtain the soil spectrum energy clustering characteristics;

[0146] In one embodiment, a cluster analysis is performed on the spectrum correlation matrix data. By grouping regions with similar energy characteristics in the spectrum into one category, a representative soil spectrum energy clustering feature is generated. The clustering result reveals the regional characteristics in the soil, such as certain regions that are concentrated with high energy absorption or low energy transmission.

[0147] Reconstruct the characteristic spectrum of soil spectrum energy clustering features to obtain soil reconstructed spectrum data;

[0148] In one embodiment, the spectral characteristic map of the soil is reconstructed using the clustering results. The results of the spectral energy clustering are mapped to the spatial position of the construction area to generate a reconstructed spectrum map of the soil. The spectrum clearly shows the distribution law of the soil spectral characteristics and provides intuitive guidance for complex problems that arise during the construction process.

[0149] Soil spectrum decomposition data is generated according to the soil reconstructed spectrum data to obtain soil spectrum decomposition data.

[0150] In one embodiment, the energy distribution, directivity and frequency response characteristics of each frequency band are extracted from the soil reconstructed spectrum data obtained from the previous analysis: Spectral energy distribution: records the energy ratio of different frequency bands, reflecting the absorption or reflection characteristics of soil to sound waves in each frequency range. Directivity distribution: describes the distribution of sound wave energy in different propagation directions, revealing the internal non-uniformity of the soil. Main frequency range: determines the resonant frequency and high energy concentration frequency band of the soil.

[0151] Based on the input soil reconstructed spectrum data, the system conducts a detailed decomposition of the soil's spectrum characteristics, such as frequency band division: the frequency range is divided into three regions: low frequency, medium frequency and high frequency, and the frequency band range is selected according to the physical properties of the soil (such as low frequency corresponds to large-grained soil, high frequency corresponds to fine-grained soil); segmented energy calculation: the total energy and energy ratio of each frequency band are calculated separately to identify the soil's absorption intensity of sound waves in each frequency band; local characteristic extraction: the spectrum characteristics of specific areas (such as areas with strong sound wave reflection) are analyzed separately to extract the special responses of local frequency bands.

[0152] The dynamic behavior of the spectral characteristics with frequency changes was further analyzed, such as response curve fitting: using the reconstructed spectrum data, the dynamic response curve of the soil is fitted to show the trend of the frequency response characteristics of the soil with frequency changes. Key characteristic parameters are extracted, such as resonant frequency: the frequency at which the soil responds most strongly to sound waves, indicating the characteristic scale of the internal structure of the soil; energy attenuation rate: the attenuation rate of energy in different frequency bands with propagation distance, which is used to evaluate the sound absorption capacity of the soil; directivity parameters: the changes in spectral characteristics in different propagation directions, which are used to identify the non-uniform distribution inside the soil.

[0153] The decomposed spectral characteristics are associated with the physical properties of the soil, such as the relationship between soil density and spectral energy: soil with higher density usually exhibits stronger low-frequency energy, while soil with lower density exhibits a high proportion of high-frequency energy; the relationship between soil particle distribution and frequency band characteristics: coarse-grained soil is more inclined to low-frequency propagation, while fine-grained soil has better propagation characteristics in the high-frequency band; acoustic characteristics of abnormal areas: abnormal energy distribution detected in a specific area may indicate voids or density changes in the soil.

[0154] Based on the above analysis results, soil spectrum decomposition data was generated, including segmented energy distribution: the energy proportion of each frequency band and the total energy; dynamic response characteristics: the dynamic response curve of the soil to sound waves, including resonant frequency, energy attenuation rate and directional distribution; local characteristic description: spectrum characteristic data of a specific area, which is used to identify abnormal areas and non-uniform soil distribution.

[0155] Optionally, the real-time construction data includes soil acoustic wave data, which is collected by an acoustic wave sensor, and the second soil characteristic feature extraction includes:

[0156] Perform multi-band acoustic wave transmission analysis on the soil acoustic wave data in the real-time construction data to obtain soil acoustic wave transmission data;

[0157] In one embodiment, the acoustic wave sensor of the construction equipment transmits acoustic waves to the soil at different depths and records the propagation time of the acoustic waves in the soil and the received signal strength. The acoustic wave data is decomposed into multiple frequency bands to analyze the propagation characteristics of the acoustic waves in different frequency ranges. By comparing the propagation time and signal amplitude of each frequency band, the acoustic wave transmission data of the soil at different depths and frequency bands is obtained.

[0158] Calculate the sound velocity of soil sound wave transmission data to obtain soil sound velocity data;

[0159] In one embodiment, the sound velocity distribution in the soil is calculated based on the sound wave transmission data. The sound velocity of the soil at different depths is estimated according to the time and distance of the sound wave propagation. The sound velocity data can reflect the distribution characteristics of soil density and porosity, thereby indirectly evaluating the compressibility and uniformity of the soil.

[0160] Extract the acoustic wave reflection characteristics of the soil sound velocity data to obtain soil reflection characteristic parameter data;

[0161] In one embodiment, the reflection characteristics of sound waves at the soil layer interface are analyzed. Based on the received reflected sound wave signal, the reflection intensity and time delay of different layer interfaces are extracted. Through the change of reflection intensity, the system identifies the impedance difference of the soil layer interface and determines the soil stratification and local abnormal areas.

[0162] Performing sound wave attenuation analysis on soil emission characteristic parameter data to obtain soil sound wave attenuation data;

[0163] In one embodiment, the propagation attenuation characteristics of sound waves in soil are deeply analyzed. The signal intensity attenuation of sound waves at different depths is calculated to evaluate the soil's ability to absorb sound waves. The sound wave attenuation characteristics of soil can reveal the size of its particle gaps and internal microstructure characteristics.

[0164] In one embodiment, the energy attenuation is calculated based on the propagation path of the sound wave in the soil, the frequency band attenuation rate is calculated for each frequency band, and the energy attenuation and frequency band attenuation rate are integrated into the soil sound wave attenuation data.

[0165] Performing sound wave propagation simulation on soil sound wave attenuation data to obtain soil sound wave propagation data;

[0166] In one embodiment, based on the sound wave attenuation data, the soil sound wave propagation equation is established, and the waveform superposition of multi-path propagation is simulated by combining the sound speed and path length, so as to simulate the propagation of sound waves in the soil. A soil sound wave propagation model is constructed to simulate the propagation path of sound waves at different depths and directions. Through simulation, the energy distribution and propagation barriers of sound waves inside the soil are systematically analyzed.

[0167] Soil characteristic parameters are inverted according to the soil acoustic wave propagation data to obtain second soil characteristic feature data.

[0168] In one embodiment, the soil characteristic parameters are inverted and analyzed. Combined with the sound velocity and attenuation data, the key parameters such as soil density, porosity and elastic modulus are obtained by inversion. The inversion is performed through the soil acoustic wave equation. The propagation of sound waves in the soil conforms to the wave equation and is controlled by the soil density and elastic modulus. The sound velocity is determined by the density and elastic modulus of the soil, while the attenuation of the sound wave is determined by the porosity and inter-particle friction characteristics of the soil. The sound wave propagation data is matched with the soil acoustic model through an iterative inversion method. The error minimization target of the sound velocity and attenuation is defined to ensure that the inversion parameters make the simulation results closest to the actual data. The density, porosity and elastic modulus are used as inversion parameters, and the initial values ​​are set based on the geological survey data of the construction area. The parameters are gradually adjusted according to the error value until the error meets the set accuracy requirements. The density of each layer of soil is inverted through the sound velocity data and the soil model. A higher sound velocity corresponds to a higher density, while a lower sound velocity corresponds to a looser or more water-rich soil layer. Based on the sound wave attenuation data, the porosity of the soil is estimated. High attenuation rate corresponds to soil with greater porosity because sound waves lose more energy in the pores. The elastic modulus is calculated using the sound velocity and density inversion results. The elastic modulus reflects the ability of the soil to resist deformation and is closely related to the pressure feedback of the construction equipment on the soil.

[0169] Optionally, the soil reflection characteristic parameter data includes sound wave scattering characteristic data, and the sound wave scattering characteristic data is extracted by:

[0170] The soil physical model is constructed based on the real-time construction data to obtain discrete soil grid data;

[0171] In one embodiment, a three-dimensional soil physical model is constructed based on real-time construction data, including soil density, sound velocity, and layer thickness information. Soil in the construction area is layered to identify soil layers with different densities, sound velocities, and impedances. The soil model is divided into small discrete units using mesh discretization technology, each of which contains specific physical parameters (such as density and sound velocity).

[0172] Annotate the acoustic wave source parameters according to the discrete soil grid data to obtain the acoustic wave source annotation data;

[0173] In one embodiment, based on the discrete grid data, the system defines parameters for the sound wave source and labels it. The location and depth of the sound wave source are determined and labeled as specific cells in the grid. The emission frequency, initial intensity and propagation direction of the sound wave source are defined to ensure that the sound wave is consistent with the actual construction conditions when propagating in the model.

[0174] Perform acoustic wave scattering simulation on the acoustic wave source annotation data and soil sound velocity data to obtain scattered acoustic field distribution data;

[0175] In one embodiment, the propagation and scattering of sound waves in the soil are simulated by combining the sound wave source annotation data and the soil sound velocity data. The propagation path of the sound wave in different areas of the soil after being emitted from the source point is simulated. When the sound wave encounters the interface of different soil layers, the scattering phenomenon is recorded, including the direction and intensity of reflection, refraction and multiple scattering. The scattered sound field distribution data in the soil is obtained through simulation, and the data shows the energy distribution and scattering characteristics of the sound wave in the soil.

[0176] The scattering intensity and directionality of the scattered sound field distribution data are analyzed to obtain the sound wave scattering characteristic data.

[0177] In one embodiment, the scattered sound field distribution data is deeply analyzed. The sound wave scattering intensity in different areas of the soil is calculated to identify high scattering areas and low scattering areas. The propagation direction of the scattered sound waves is analyzed to generate a directional distribution map of the sound wave scattering, revealing the influence of the internal structure of the soil on the propagation of the sound waves.

[0178] Optionally, S3 includes:

[0179] S31, performing construction status change processing according to soil property data and construction status data to obtain construction status change trend data;

[0180] In one embodiment, the change trend of soil characteristic data and construction status data over time is analyzed, such as linear trend or recurrent convolutional neural network algorithm, to generate construction status change trend data. For example, when the equipment pressure increases with the construction depth, the soil resistance also shows a trend of gradually increasing, but abnormal fluctuations may occur in certain locations.

[0181] S32, extracting abnormal isolated points according to the construction status change trend data to obtain abnormal isolated construction point data;

[0182] In one embodiment, based on the construction status change trend data, the system further identifies abnormal points in the construction process. Based on the abnormal template library or the isolated decision tree algorithm, through the analysis of the trend data, it is found that the pressure and resistance data suddenly deviate from the normal range in certain time periods, such as the abnormal increase of equipment pressure at a certain depth. The deviation is marked as an isolated construction abnormal point, and the time, location and related parameters of the abnormality are recorded.

[0183] In one embodiment, a statistical method is used to detect isolated points based on the construction status change trend data. k is the empirical coefficient, δ is the data standard deviation, and when a certain dimension of data exceeds this range, it is marked as an outlier. Use density analysis methods (such as the local outlier factor method) to further identify isolated points in high-dimensional data. Calculate the local outlier factor LOF of each point: Where p is the target point (the point that needs to be judged as an outlier), q is the other points in the neighborhood of p (that is, the set of points within the neighborhood of p), is the k-nearest neighbor set of point p, including the k points closest to p, O(q) is the local reachable density of point q, and when LOF> the preset isolated point abnormal threshold, it is marked as an abnormal point. The LOF value describes the comparison between the local density of point p and the density of its neighborhood points: When LOF(p)≈1: it means that the local density of point p is similar to the local density of its neighborhood points, and p is not an outlier. When LOF(p)>1: it means that the density of point p is lower than that of its neighborhood points, and it is an outlier. When LOF(p)<1: it means that the density of point p is higher than that of its neighborhood points, and it is not an outlier.

[0184] S33, performing abnormal classification according to the construction abnormality isolated point data to obtain construction abnormality classification data;

[0185] In one embodiment, the extracted abnormal isolated point data is classified. According to the characteristics of the abnormal occurrence (such as a sudden increase in resistance, a decrease in rotation speed, or an increase in equipment vibration), the abnormal points are divided into different types through mapping through a support vector machine algorithm or an abnormal event parameter library. For example, some abnormalities are classified as abnormalities caused by equipment overload, while others are caused by a sudden change in soil density.

[0186] In one embodiment, the context features of the abnormal points are extracted, including the trend changes before and after the abnormality occurs. An unsupervised classification algorithm (such as a clustering method) is used to classify the abnormal points into several categories. The center point of each category is calculated and marked as the construction abnormality classification label data to obtain the construction abnormality classification data.

[0187] S34, performing change causal analysis on the construction abnormality classification data to obtain construction change causal data;

[0188] In one embodiment, the classified abnormal data is used to perform causal analysis of changes. Combined with soil characteristic data, the relationship between the abnormality and soil properties (such as density and porosity) is analyzed. For example, the abnormal points in a certain area are attributed to the significant increase in the resistance of the soil layer at that location, causing the equipment operation load to exceed the normal range.

[0189] In one embodiment, time series analysis is used to determine the causal impact of soil properties or construction status data on anomalies based on causality tests. X→Y (causal) if Var(Y|X) < Var(Y), where X→Y means that variable X has a causal impact on variable Y, Var(Y|X) is the residual fluctuation range of Y given X, Var(Y) is the overall change range of Y, that is, the degree of fluctuation of YYY when X is not considered, and Var(Y|X) < Var(Y) means that the conditional variance of Y given X is less than the total variance, indicating that X can significantly reduce the uncertainty of Y, demonstrating that X has a causal impact on Y. Perform regression analysis on the time series before and after the anomaly point to extract the causal path. The causal model is linear regression: Y = β0 + β1X t-1 + μ t , where Y is the dependent variable, the target variable affected by the causal variable, β0 is the intercept, the baseline level when X is constant, β1 is the regression coefficient, representing the t-1 causal effect intensity of X on Y, X t-1 is the lagged causal variable, the variable affecting the current Y, and μ t is the error term, representing the unexplained random factors or other influences. When β1 ≠ 0 and the significance test passes, record the causal relationship. Construction change causal data = {(X→Y, β1}.

[0190] S35. Integrate the construction status change trend data, construction anomaly outlier data, and construction change causal data to obtain the construction status change data.

[0191] In one embodiment, the construction status change trend data, outlier data, and change causal data are integrated. A comprehensive construction status change report is constructed, covering the construction dynamic trend, anomaly characteristics, and their causes.

[0192] Optionally, S4 includes:

[0193] S41. Generate optimization objectives based on the construction status change data to obtain construction optimization objective data;

[0194] In one embodiment, according to the construction status change data, including the dynamic change trends of pressure, rotational speed, and soil resistance, construction optimization objectives are set. Objective 1: Maximize construction efficiency - increase the construction depth per unit time. Objective 2: Minimize equipment energy consumption - reduce the energy consumption of the equipment in high-resistance areas. Objective 3: Minimize the anomaly occurrence rate - reduce the frequency of anomaly outliers, for example, avoid equipment shutdown due to excessive equipment pressure.

[0195] S42. Select optimization variables based on the construction optimization objective data to obtain construction optimization variable data;

[0196] In one embodiment, controllable construction variables are identified from the construction status change data: Cutter head rotation speed: directly affects construction efficiency and soil resistance balance. Equipment pressure: controls the equipment's ability to cut the soil and affects the abnormality rate. Advance speed: adjusts the forward speed of the construction equipment to adapt to different soil conditions.

[0197] S43. Target optimization is performed on the construction status change data according to the construction optimization variable data to obtain construction parameter optimization data for TRD construction quality inspection auxiliary operations.

[0198] In one embodiment, the selected optimization variables are adjusted to achieve the optimization goal: Cutter head rotation speed optimization: In high resistance areas, the rotation speed is reduced to avoid equipment overload; in low resistance areas, the rotation speed is increased to increase construction efficiency. Equipment pressure optimization: Near abnormal isolated points, the equipment pressure is appropriately reduced to reduce the risk of abnormality; in uniform soil areas, a higher pressure is maintained to improve cutting capacity. Advance speed optimization: In dense soil areas, the advancement speed is slowed down to ensure smooth operation of the equipment; in loose soil areas, the advancement speed is appropriately accelerated to improve construction efficiency.

[0199] Optionally, the present invention further provides a TRD construction quality detection system, which is used to execute the TRD construction quality detection method as described above, and the TRD construction quality detection system comprises:

[0200] Construction real-time data collection module, used to obtain real-time construction data;

[0201] The real-time construction analysis module is used to analyze soil characteristics and construction status based on real-time construction data to obtain soil characteristics data and construction status data;

[0202] A construction status change processing module is used to analyze the construction status change according to the soil characteristic data and the construction status data to obtain the construction status change data;

[0203] The construction parameter optimization module is used to optimize the construction parameters according to the construction status change data, and obtain the construction parameter optimization data to carry out TRD construction quality inspection auxiliary operations.

[0204] Therefore, from any point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the attached application documents rather than the above description, and it is intended that all changes falling within the meaning and scope of equivalent elements of the application documents are included in the present invention.

[0205] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A TRD construction quality detection method, characterized in that: The TRD construction quality detection method comprises: S1. Obtain real-time construction data; S2. Perform soil property analysis and construction status analysis based on real-time construction data to obtain soil property data and construction status data; S3. Perform construction status change analysis based on soil property data and construction status data to obtain construction status change data; S4. Optimize construction parameters according to the construction status change data to obtain construction parameter optimization data for TRD construction quality inspection auxiliary operations.

2. A TRD construction quality detection method according to claim 1, characterized in that: S1 includes: Through the multi-modal sensors integrated in the TRD equipment, soil resistance, cutterhead rotation speed and depth displacement are collected in real time to obtain the original construction data; Perform geographic information fusion on the original construction data to obtain geographic annotated construction data; Perform real-time multi-source data integration on geographically annotated construction data to obtain real-time construction data.

3. A TRD construction quality detection method according to claim 1, characterized in that S2 include: Extract soil characteristic features and construction status features from the real-time construction data to obtain soil characteristic feature data and construction status feature data respectively; Perform multi-dimensional correlation of characteristics based on soil characteristic feature data and construction status feature data to obtain construction feature relationship data; Generate soil model based on construction characteristic relationship data to obtain soil mechanical model; Extract soil characteristics from soil mechanical model to obtain soil characteristic data; Conduct construction status modeling on the construction characteristic relationship data to obtain a construction status model; The construction status model is subjected to construction status extraction to obtain construction status data.

4. A TRD construction quality detection method according to claim 3, characterized in that: The soil characteristic feature extraction includes: Extracting first soil characteristic features from the real-time construction data to obtain first soil characteristic feature data; Performing a second soil characteristic feature extraction on the real-time construction data to obtain second soil characteristic feature data, wherein the first soil characteristic feature extraction and the second soil characteristic feature extraction are different soil characteristic feature extraction methods; The first soil characteristic feature data and the second soil characteristic feature data are fused to obtain soil characteristic feature data.

5. A TRD construction quality detection method according to claim 4, characterized in that: The real-time construction data includes soil vibration wave data, which is collected by seismic wave sensors or high-frequency vibration sensors. The first soil characteristic feature extraction includes: Perform time domain characteristic analysis on soil vibration wave data in real-time construction data to obtain soil time domain characteristic data; Performing frequency domain data transformation on soil time domain characteristic data to obtain soil frequency domain characteristic data; Performing energy spectrum decomposition on soil frequency domain characteristic data to obtain soil spectrum decomposition data; Performing dynamic response parameter mapping on soil spectrum decomposition data to obtain first soil characteristic feature data; The energy spectrum decomposition includes: Perform time-frequency joint transformation on soil time-domain characteristic data to obtain local time-frequency characteristic data; Extracting spectrum energy distribution of local time-frequency feature data to obtain spectrum energy distribution data; Perform multi-scale spectrum decomposition on the spectrum energy distribution data to obtain multi-scale spectrum data; Performing spectrum correlation analysis on multi-scale spectrum data to obtain spectrum correlation matrix data; Perform energy characteristic clustering processing on the spectrum correlation matrix data to obtain the soil spectrum energy clustering characteristics; Reconstruct the characteristic spectrum of soil spectrum energy clustering features to obtain soil reconstructed spectrum data; Soil spectrum decomposition data is generated according to the soil reconstructed spectrum data to obtain soil spectrum decomposition data.

6. A TRD construction quality detection method according to claim 4, characterized in that: The real-time construction data includes soil acoustic wave data, which is collected by acoustic wave sensors. The second soil characteristic feature extraction includes: Perform multi-band acoustic wave transmission analysis on the soil acoustic wave data in the real-time construction data to obtain soil acoustic wave transmission data; Calculate the sound velocity of soil sound wave transmission data to obtain soil sound velocity data; Extract the acoustic wave reflection characteristics of the soil sound velocity data to obtain soil reflection characteristic parameter data; Performing sound wave attenuation analysis on soil emission characteristic parameter data to obtain soil sound wave attenuation data; Performing sound wave propagation simulation on soil sound wave attenuation data to obtain soil sound wave propagation data; Soil characteristic parameters are inverted according to the soil acoustic wave propagation data to obtain second soil characteristic feature data.

7. A TRD construction quality detection method according to claim 6, characterized in that: The soil reflection characteristic parameter data includes the acoustic wave scattering characteristic data, and the extraction method of the acoustic wave scattering characteristic data includes: The soil physical model is constructed based on the real-time construction data to obtain discrete soil grid data; Annotate the acoustic wave source parameters according to the discrete soil grid data to obtain the acoustic wave source annotation data; Perform acoustic wave scattering simulation on the acoustic wave source annotation data and soil sound velocity data to obtain scattered acoustic field distribution data; The scattering intensity and directionality of the scattered sound field distribution data are analyzed to obtain the sound wave scattering characteristic data.

8. A TRD construction quality detection method according to claim 1, characterized in that S3 include: Process the construction status change according to the soil characteristic data and the construction status data to obtain the construction status change trend data; Extract abnormal isolated points based on the construction status change trend data to obtain abnormal isolated construction point data; Perform abnormal classification based on construction abnormality isolated point data to obtain construction abnormality classification data; Conduct change causal analysis on construction abnormality classification data to obtain construction change causal data; The construction status change trend data, construction abnormality isolated point data and construction change cause and effect data are integrated to obtain the construction status change data.

9. A TRD construction quality detection method according to claim 1, characterized in that S4 include: Generate optimization targets based on construction status change data to obtain construction optimization target data; Select optimization variables according to the construction optimization target data to obtain construction optimization variable data; The construction status change data is optimized according to the construction optimization variable data to obtain the construction parameter optimization data for TRD construction quality inspection auxiliary work.

10. A TRD construction quality detection system, characterized in that: Used to perform the TRD construction quality detection method according to any one of claims 1 to 9, the TRD construction quality detection system comprises: Construction real-time data collection module, used to obtain real-time construction data; The real-time construction analysis module is used to analyze soil characteristics and construction status based on real-time construction data to obtain soil characteristics data and construction status data; A construction status change processing module is used to analyze the construction status change according to the soil characteristic data and the construction status data to obtain the construction status change data; The construction parameter optimization module is used to optimize the construction parameters according to the construction status change data, and obtain the construction parameter optimization data to carry out TRD construction quality inspection auxiliary operations.

Images